A reader recently asked about the synergies between robocars and ultracapacitors/supercapacitors. It turns out they are not what you would expect, and it teaches some of the surprising lessons of robocars.
Ultracaps are electrical storage devices, like batteries, which can be charged and discharged very, very quickly. That makes them interesting for electric cars, because slow charging is the bane of electric cars. They also tend to support a very large number of charge and discharge cycles — they don’t wear out the way batteries do. Where you might get 1,000 or so cycles from a good battery, you could see several tens of thousands from an ultracap.
Today, ultracaps cost a lot more than batteries. LIon batteries (like in the Tesla and almost everything else) are at $500/kwh of capacity and falling fast — some forecast it will be $200 in just a few years, and it’s already cheaper in the Tesla. Ultracaps are $2,500 to $5,000 per kwh, though people are working to shrink that.
They are also bigger and heavier. They are cited as just 10 wh/kg and on their way to 20 wh/kg. That’s really heavy — LIon are an order of magnitude better at 120 wh/kg and also improving.
So with the Ultracap, you are paying a lot of money and a lot of weight to get a super-fast recharge. It’s so much money that you could never justify it if not for the huge number of cycles. That’s because there are two big money numbers on a battery — the $/kwh of capacity — which means range — and the lifetime $/kwh, which affects your economics. Lifetime $/kwh is actually quite important but mostly ignored because people are so focused on range. An ultracap, at 5x the cost but 10x or 20x the cycles actually wins out on lifetime $/kwh. That means that while it will be short range, if you have a vehicle which is doing tons of short trips between places it can quickly recharge, the ultracap can win on lifetime cost, and on wasted recharging time, since it can recharge in seconds, not hours. That’s why one potential application is the shuttle bus, which goes a mile between stops and recharges in a short time at every stop.
How do robocars change the equation? In some ways it’s positive, but mostly it’s not.
Robocars don’t mind going out of their way to charge, at least not too far out of their way. Humans hate this. So you don’t need to place charging stations conveniently, and you can have a smaller number of them.
Robocars don’t care how long it takes to charge. The only issue is they are not available for service while charging. Humans on the other hand won’t tolerate much wait at all.
Robocars will eventually often be small single-person vehicles with very low weight compared to today’s cars. In fact, most of their weight might be battery if they are electric.
Users don’t care about the power train of a taxi or its energy source. Only the fleet manager cares, and the fleet manager is all about cost and efficiency and almost nothing else.
Now we see the bad news for the ultracap. It’s main advantage is the fast recharge time. Robots don’t care about that much at all. Instead, the fleet manager does care about the downtime, but the cost of the downtime is not that high. You need more vehicles the more downtime you have during peak loads, but as vehicles are wearing out by the km, not the year, the only costs for having more vehicles are the interest rate and the storage (parking) cost.
The interest cost is very low today. Consider a $20,000 vehicle. At 3%, you’re paying $1.60 per day in interest. So 4 hours of recharge downtime (only at peak times when you need every vehicle) doesn’t cost very much, certainly not as much as the extra cost of an ultracap. The cost of parking is actually much more, but will be quite low in the beginning because these vehicles can park wherever they can get the best rate and the best rate is usually zero somewhere not too far away. That may change in time, to around $2/day for surface parking of mini-vehicles, but free for now in most places.
In addition to the high cost, the ultracap comes with two other big downsides. The first is the weight and bulk. Especially when a vehicle is small and is mostly battery, adding 200kg of battery actually backfires, and you get diminishing returns on adding more in such vehicles. The other big downside is the short range. Even with the fast recharge time, you would have to limit these vehicles to doing only short cab hops in urban spaces of just a few miles, sending them off after just a few rides to get a recharge.
A third disadvantage is you need a special charging station to quick charge an ultracap. While level 2 electric car charging stations are in the 7-10kw range, and rapid chargers are in the 50kw-100kw range, ultracap chargers want to be in the megawatt or more range, and that’s a much more serious proposition, and a lot more work to build them.
Finally, while ultracaps don’t wear out very fast, they might still depreciate quickly the same way your computer does — because the technology keeps improving. So while your ultracap might last 20 years, you won’t want it any more compared to the cheaper, lighter, higher capacity one you can buy in the future. It can still work somewhere, like grid storage, but probably not in your car.
The fact that robocars don’t need fast refueling in convenient locations opens up all sorts of energy options. Natural gas, hydrogen, special biofuels and electricity all become practical even with gasoline’s 100 year headstart when it comes to deployment and infrastructure, and even sometimes in competition with gasoline’s incredible convenience and energy density. But what the robocar brings is not always a boon to every different form of energy storage.
One technique that makes sense for robocars (and taxis) is battery swap. Battery swap was a big failure for human driven cars, for reasons I have outlined in other posts. But robocars and taxis don’t mind coming back to a central station, or even making an appointment for a very specific time to do their swap. They don’t even mind waiting for other cars to get their swaps, and can put themselves into the swap station when told to — very precisely if needed. Here it’s a question of whether it’s cheaper to swap or just pay the interest and parking on more cars.
Ultracaps are also used to help with regenerative braking, since they can soak up power from hard regenerative braking faster than batteries. That’s mostly not a robocar issue, though in general robocars will brake less hard and accelerate less quickly — trying to give a smooth ride to their passengers rather than an exciting one — so this has less importance there too.
Still, for convenience, the first robocars will probably be gasoline and electric.
2 months mostly on the road, so here’s a roundup of the “real” news stories in the field.
Google begins PR campaign and talks about accidents
As the world’s most famous company, Google doesn’t need to seek press and the Chauffeur project has kept fairly quiet, but it just opened a new web site which will feature monthly reports on the status of the project. The first report gives details of all the accidents in the project’s history, which we discussed earlier. A new one just took place in the last month, but like the others, it did not involve the self-driving software. Google’s cars continue to not cause any accidents, though they have been at the receiving end of a modestly high number of impacts, perhaps because they are a bit unusual.
The zero at-fault accident number is both impressive, and possibly involves a bit of luck. Perhaps it even raises unrealistic expectations of perfection, because I believe there will be at-fault accidents in the future for both Google and other teams. Most teams, when they were first building their vehicles, had minor accidents where cars hit curbs or obstacles on test tracks, but the track records of almost all teams since then are surprisingly good. One way that’s not luck, of course, is the presence of safety drivers ready to take the controls if something goes wrong. They are trained and experienced, though some day, being human, some of them will make mistakes.
Baidu to build a prototype
In November I gave a “Big Talk” for Baidu in Beijing on cars. Perhaps there is something about search engines because they have made announcements about their own project. Like Google, Baidu has expertise in mapping and various AI techniques, including the advice of Andrew Ng, whose career holds many parallels to that of Sebastian Thrun who started Google’s project. (Though based on my brief conversations with Andrew I don’t think he’s directly involved.)
Virginia opens test roads
The state of Virginia has designated 70 miles of roads for robocar testing. That’s a good start for testing by those working in that state, but it skirts what to me is a dangerous idea — the thought that there would be “special” roads for robocars designated by states or road authorities. The fantastic lesson of the Darpa grand challenges was the idea that the infrastructure remains stupid and the car becomes smart, so that the car can go anywhere once its builders are satisfied it can handle that road. So it’s OK to test on a limited set of roads but it’s also vital to test in as many situations as you can, so you need to get off that set of roads as soon as you can.
Zoox startup un-stealthed
Zoox is probably the first funded startup working on a real, fully automated robocar. They were recently funded by DFJ ventures and set up shop in rented space at the SLAC linear accelerator lab. Zoox was begun by Tim Kentley-Klay, a designer and entrepreneur from Australia, and he later joined forces with Jesse Levinson, a top researcher from Stanford’s self-driving car projects.
I’ve known about Zoox since it begain and had many discussions. They first got some attention a while back with Tim’s designs, which are quite different from typical car designs, and presume a fully functional robocar — the designs feature no controls for the humans, and don’t even have a windshield to see forward in some cases. (Indeed, they don’t have a “forward” since an essential part of the design is to be symmetrical and move equally well in both directions, avoiding the need for some twists and turns.) I like many elements of the Zoox vision, though in fact I think it is even more ambitious than Google’s, at least from a car design standpoint, which is quite audacious in a world where most of the players think Google is going too far.
You can see details in this report on Zoox from IEEE. I haven’t reported on Zoox under FrieNDA courtesy — in fact the early consultations with “Singularity University” described in the article are actually discussions with me.
Zoox is not the first small startup. Kyle Haight’s “Cruise” has been at it a while aiming at a much less ambitious supervised product, and truck platooning company Peleton has even simpler goals, but expect to see more startups enter the fray and fight with the big boys in the year to come.
Mercedes E Class
Speaking of supervised cruising, the report is that the 2016 Mercedes E Class will offer highway speed cruising in the USA. This has been on offer in Europe in the past. As I wrote earlier, I am less enthused about supervised cruising products and think they will not do tremendously well. Tesla’s update to offer the same in their cars will probably get the most attention.
In addition, many stories reported that Tesla had “solved” the liability problem of robocars through the design of their lane change system. In their system (and in several other discussed designs — they did not come up with this) the car won’t change lanes until the human signals it is OK to do so, usually by something like hitting the turn signal indicator. The Tesla plan is for a supervised car, and in a supervised car all liability is already supposed to go to the human supervisor.
Changing lanes safely is surprisingly challenging, because there is always the chance somebody is zooming up behind you at a rather rapid rate of speed. That’s common merging into a carpool lane, or on German autobahn trips. Most supervised cars have only forward sensing, but to change lanes safely you need to notice a car coming up fast from behind you, and you need to see it quite a distance away. This requires special sensors, such as rear radars, which most cars don’t have. So the solution of having the human check the mirrors works well for now.
More and more stories keep getting excited by “connected car” technology, in particular V2V communications using DSRC. They even write that these technologies are essential for robocars, and it gets scary when people like the transportation secretary say this. I wish the press covering this would take the simple step of asking the top teams who are working on robocars whether they plan to depend on, or even make early use of vehicle to vehicle communications. They will find out the answers will range form “no, not really” to a few vague instances of “yes, someday” from car companies who made corporate support commitments to V2V. The engineers don’t actually think they will find the technology crucial. The fact that the people actually building robocars have only a mild interest, if any, in V2V, while the people who staked their careers on V2V insist it’s essential should maybe suggest to the press that the truth is not quite what they are told.
This weekend I went to Pomona, CA for the 2015 DARPA Robotics Challenge which had robots (mostly humanoid) compete at a variety of disaster response and assistance tasks. This contest, a successor of sorts to the original DARPA Grand Challenge which changed the world by giving us robocars, got a fair bit of press, but a lot of it was around this video showing various robots falling down when doing the course:
What you don’t hear in this video are the cries of sympathy from the crowd of thousands watching — akin to when a figure skater might fall down — or the cheers as each robot would complete a simple task to get a point. These cheers and sympathies were not just for the human team members, but in an anthropomorphic way for the robots themselves. Most of the public reaction to this video included declarations that one need not be too afraid of our future robot overlords just yet. It’s probably better to watch the DARPA official video which has a little audience reaction.
Don’t be fooled as well by the lesser-known fact that there was a lot of remote human tele-operation involved in the running of the course.
What you also don’t see in this video is just how very far the robots have come since the first round of trials in December 2013. During those trials the amount of remote human operation was very high, and there weren’t a lot of great fall videos because the robots had tethers that would catch them if they fell. (These robots are heavy and many took serious damage when falling, so almost all testing is done with a crane, hoist or tether able to catch the robot during the many falls which do occur.)
We aren’t yet anywhere close to having robots that could do tasks like these autonomously, so for now the research is in making robots that can do tasks with more and more autonomy with higher level decisions made by remote humans. The tasks in the contest were:
Starting in a car, drive it down a simple course with a few turns and park it by a door.
Get out of the car — one of the harder tasks as it turns out, and one that demanded a more humanoid form
Go to a door and open it
Walk through the door into a room
In the room, go up to a valve with circular handle and turn it 360 degrees
Pick up a power drill, and use it to cut a large enough hole in a sheet of drywall
Perform a surprise task — in this case throwing a lever on day one, and on day 2 unplugging a power cord and plugging it into another socket
Either walk over a field of cinder blocks, or roll through a field of light debris
Climb a set of stairs
The robots have an hour to do this, so they are often extremely slow, and yet to the surprise of most, the audience — a crowd of thousands and thousands more online — watched with fascination and cheering. Even when robots would take a step once a minute, or pause at a task for several minutes, or would get into a problem and spend 10 minutes getting fixed by humans as a penalty. read more »
Some headlines (I’ve been on the road and will have more to say soon.)
Google announces it will put new generation buggies on city streets
Google has done over 2.7 million km of testing with their existing fleet, they announced. Now, they will be putting their small “buggy” vehicle onto real streets in Mountain View. The cars will stick to slower streets and are NEVs that only go 25mph.
While this vehicle is designed for fully automatic operation, during the testing phase, as required, it will have a temporary set of controls for the safety driver to use in case of any problem. Google’s buggy, which still has no official name, has been built in a small fleet and has been operating on test tracks up to this point. Now it will need to operate among other road users and pedestrians.
Accidents with, but not caused by self-driving cars cause press tizzy.
The press were terribly excited when reports filed with the State of California indicated that there had been 4 accidents reported — 3 for Google and 1 for Delphi. Google reported a total of 11 accidents in 6 years of testing and over 1.5 million miles.
Headlines spoke loudly about the cars being in accidents, but buried in the copy was the fact that none of the accidents by any company were the fault of the software. Several took place during human driving, and the rest were accidents that were clearly the fault of the other party, such as being rear ended or hit while stopped.
Still, some of the smarter press noticed, this is a higher rate of being in an accident than normal, in fact almost double — human drivers are in an accident about every 250,000 miles and so should have had only 6.
The answer may be that these vehicles are unusual and have “self driving car” written on them. They may be distracting other drivers, making it more likely those drivers will make a mistake. In addition, many people have told me of their thoughts when they encountered a Google car on the road. “I thought about going in front of it and braking to see what it would do,” I’ve been told by many. Aside from the fact that this is risky and dickish, and would just cause the safety drivers to immediately disengage and take over, in reality they all also said they didn’t do it, and experience in the cars shows that it’s very rare for other drivers to actually try to “test” the car.
But perhaps some people who think about it do distract themselves and end up in an accident. That’s not good, but it’s also something that should go away as the novelty of the cars decreases.
Mercedes and Freightliner test in Nevada
There was also lots of press about a combined project of Mercedes/Daimler and Freightliner to test a self-driving truck in Nevada. There is no reason that we won’t eventually have self-driving trucks, of course, and there are direct economic benefits for trucking fleets to not require drivers.
Self-driving trucks are not new off the road. In fact the first commercial self-driving vehicles were mining trucks at the Rio Tinto mine in Australia. Small startup Peleton is producing a system to let truckers convoy, with the rear driver able to go hands-free. Putting them on regular roads is a big step, but it opens some difficult questions.
First, it is not wise to do this early on. Systems will not be perfect, and there will be accidents. You want your first accidents to be with something like Google’s buggy or a Prius, not with an 18-wheel semi-truck. “Your first is your worst” with software and so your first should be small and light.
Secondly, this truck opens up the jobs question much more than other vehicles, where the main goal is to replace amateur drivers, not professionals. Yes, cab drivers will slowly fade out of existence as the decades pass, but nobody grows up wanting to be a cab driver — it’s a job you fall into for a short time because it’s quick and easy work that doesn’t need much training. While other people build robots to replace workers, the developers of self-driving cars are mostly working on saving lives and increasing convenience.
Many jobs have been changed by automation, of course, and this will keep happening, and it will happen faster. Truck drivers are just one group that will face this, and they are not the first. On the other hand, the reality of robot job replacement is that while it has happened at a grand scale, there are more people working today than ever. People move to other jobs, and they will continue to do so. This may not be much satisfaction for those who will need to go through this task, but the other benefits of robocars are so large that it’s hard to imagine delaying them because of this. Jobs are important, but lives are even more important.
It’s also worth noting that today there is a large shortage of truck drivers, and as such the early robotic trucks will not be taking any jobs.
I’m more interested in tiny delivery “trucks” which I call “deliverbots.” For long haul, having large shared cargo vehicles makes sense, but for delivery, it can be better to have a small robot do the job and make it direct and personal.
The world of sensors continues to grow. This wideband software based radar from a student team won a prize. It claims to produce a 3D image. Today’s automotive radars have long range but very low resolution. High resolution radar could replace lidar if it gets enough resolution. Radar sees further, and sees through fog, and gives you a speed value, and LIDAR falls short in those areas.
Also noteworthy is this article on getting centimeter GPS accuracy with COTS GPS equipment. They claim to be able to eliminate a lot of multipath through random movements of the antennas. If true, it could be a huge localization breakthrough. GPS just isn’t good enough for robocar positioning. Aside from the fact it goes away in some locations like tunnels, and even though modern techniques can get sub-cm accuracy, it you want to position your robocar with it, and it alone, you need it to essentially never fail. But it does.
That said, most other localization systems, including map and image based localization, benefit from getting good GPS data to keep them reliable. The two systems together work very well, and making either one better helps.
Transportation Secretary Fox advances DoT plan
Secretary Fox has been out writing articles and Speaking in Silicon Valley about their Beyond Traffic effort. They promise big promotion of robocars which is good. Sadly, they also keep promoting the false idea that vehicle to vehicle communications are valuable and will play a significant role in the development of robocars. In my view, many inside the DoT staked their careers on V2V, and so feel required to promote it, even though it has minimal compelling applications and may actually be rejected entirely by the robocar community because of security issues.
This debate is going to continue for a while, it seems.
Maps, maps, maps
Nokia has put its “Here” map division up for sale, and a large part of the attention seems to related to their HD Maps project, aimed at making maps for self-driving. (HERE published a short interview with me on the value of these maps.
It will be interesting to see how much money that commands. At the same time, TomTom, the 3rd mapping company, has announced it will begin making maps for self-driving cars — a decision they made in part because of encouragement from yours truly.
Uber dwarfs taxis
Many who thought Uber’s valuation is crazy came to that conclusion because they looked at the size of the Taxi industry. To the surprise of nobody who has followed Uber, they recently revealed that in San Francisco, their birthplace, they are now 3 times the size of the old taxi industry, and growing. It was entirely the wrong comparison to make. The same is true of robocars. They won’t just match what Uber does, they will change the world.
There’s more news to come, during a brief visit to home, but I’m off to play in Peoria, and then Africa next week!
Earlier this week I was sent some advance research from the U of Michigan about car sickness rates for car passengers. I found the research of interest, but wish it had covered some questions I think are more important, such as how carsickness is changed by potentially new types of car seating, such as face to face or along the side.
To my surprise, there was a huge rush of press coverage of the study, which concluded that 6 to 12% of car passengers get a bit queasy, especially when looking down in order to read or work. While it was worthwhile to work up those numbers, the overall revelation was in the “Duh” category for me, I guess because it happens to me on some roads and I presumed it was fairly common.
Oddly, most of the press was of the “this is going to be a barrier to self-driving cars” sort, while my reaction was, “wow, that happens to fewer people than I thought!”
Having always known this, I am interested in the statistics, but to me the much more interesting question is, “what can be done about it?”
For those who don’t like to face backwards, the fact that so many are not bothered is a good sign — just switch seats.
Some activities are clearly better than others. While staring down at your phone or computer in your lap is bad during turns and bumps, it may be that staring up at a screen watching a video, with your peripheral vision very connected to the environment, is a choice that reduces the stress.
I also am interested in studying if there can be clues to help people reduce sickness. For example, the car will know of upcoming turns, and probably even upcoming bumps. It could issue tones to give you subtle clues as to what’s coming, and when it might be time to pause and look up. It might even be the case that audio clues could substitute for visual clues in our plastic brains.
The car, of course, should drive as gently as it can, and because the software does not need a tight suspension to feel the road, the ride can be smoother as well.
Another interesting thing to test would be having your tablet or phone deliberately tilt its display to give you the illusion you are looking at the fixed world when you look at it, or to have a little “window” that shows you a real world level so your eyes and inner ears can find something to agree on.
More advanced would be a passenger pod on hydraulic struts able to tilt with several degrees of freedom to counter the turns and bumps, and make them always be such that the forces go up and down, never side to side. With proper banking and tilting, you could go through a roundabout (often quite disconcerting when staring down) but only feel yourself get lighter and heavier.
Most of the robocar press this week has been about the Delphi drive from San Francisco to New York, which completed yesterday. Congratulations to the team. Few teams have tried to do such a long course and so many different roads. (While Google has over a million miles logged in their testing by now, it’s not been reported that they have done 3,500 distinct roads; most testing is done around Google HQ.)
The team reported the vehicle drove 99% of the time. This is both an impressive and unimpressive number, and understanding that is key to understanding the difficulty of the robocar problem.
One of the earliest pioneers, Ernst Dickmanns did a long highway drive 20 years ago, in 1995. He reported the system drove 95% of the time, kicking out every 10km or so. This was a system simply finding the edge of the road, and keeping in the lane by tracking that. Delphi’s car is much more sophisticated, with a very impressive array of sensors — 10 radars, 6 lidars and more, and it has much more sophisticated software.
99% is not 4% better than 95%, it’s 5 times better, because the real number is the fraction of road it could not drive. And from 99%, we need to get something like 10,000 times better — to 99.9999% of the time, to even start talking about a real full-auto robocar. Because in the USA we drive 3 trillion miles per year, taking about 60 billion hours, a little over half of it on the highway. 99.9999% for all cars would mean still too many accidents if 1 time in a million you encountered something and could not handle it.
However, this depends on what we mean by “being unable to handle it.”
If not handling means “has a fatal accident” that could map to 3,600,000 of those, which would be 100x the human rate and not acceptable.
If not handling it means “has any sort of accident” then we’re pretty good, about 1/4th of the rate of human accidents
If not handling it means that the vehicle knows certain roads are a problem, and diverts around them or requests human assistance, it’s no big problem at all.
Likewise if not handling it means identifying a trouble situation, and slowing down and pulling off the road, or even just plain stopping in the middle of the road — which is not perfectly safe but not ultra-dangerous either — it’s also not a problem.
At the same time, our technology is an exponential one, so it’s wrong to think that the statement that it needs to be 10,000 times better means the system is only 1/10,000th of the way there. In fact, getting to the goal may not be that far away, and Google is much further along. They reported a distance of over 80,000 miles between necessary interventions. Humans have accidents about ever 250,000 miles.
(Delphi has not reported the most interesting number, which is necessary unexpected interventions per million miles. To figure out if an intervention is necessary, you must replay the event in simulator to see what the vehicle would have done had the safety driver not intervened. The truly interesting number is the combination of interventions/mm and the fraction of roads you can drive. It’s easier, but boring, to get a low interventions/mm number on one plain piece of straight highway, for example.)
It should also be noted that Delphi’s result is almost entirely on highways, which are the simplest roads to drive for a robot. Google’s result is also heavily highway biased, though they have reported a lot more surface street work. None of the teams have testing records in complex and chaotic streets such as those found in the developing world, or harsh weather.
It is these facts which lead some people to conclude this technology is decades away. That would be the right conclusion if you were unaware of the exponential curve the technologies and the software development are on.
Huge Hyundai investment
For some time, I’ve been asking where the Koreans are on self-driving cars. Major projects arose in many major car companies, with the Germans in the lead, and then the US and Japan. Korea was not to be seen.
Hyundai announced they would produce highway cruise cars shortly (like other makers) but they also announced they would produce a much more autonomous car by 2020 — a similar number to most car makers as well. Remarkable though was the statement that they would invest over $70 billion in the next 4 years on what they are calling “smart cars,” including hiring over 7,000 people to work on them. While this number includes the factories they plan to build, and refers to many technologies beyond robocars, it’s still an immense number. The Koreans have arrived.
I often speak about deliverbots — the potential for ground based delivery robots. There is also excitement about drone (UAV/quadcopter) based delivery. We’ve seen many proposed projects, including Amazon prime Air and much debate. Many years ago I also was perhaps the first to propose that drones deliver a defibrillator anywhere and there are a few projects underway to do this.
Some of my students in the Singularity University Graduate Studies Program in 2011 really caught the bug, and their team project turned into Matternet — a company with a focus in drone delivery in the parts of the world without reliable road infrastructure. Example applications including moving lightweight items like medicines and test samples between remote clinics and eventually much more.
I’m pleased to say they just announced moving to a production phase called Matternet One. Feel free to check it out.
When it comes to ground robots and autonomous flying vehicles, there are a number of different trade-offs:
Drones will be much faster, and have an easier time getting roughly to a location. It’s a much easier problem to solve. No traffic, and travel mostly as the crow flies.
Deliverbots will be able to handle much heavier and larger cargo, consuming a lot less energy in most cases. Though drones able to move 40kg are already out there.
Regulations stand in the way of both vehicles, but current proposed FAA regulations would completely prohibit the drones, at least for now.
Landing a drone in a random place is very hard. Some drone plans avoid that by lowering the cargo on a tether and releasing the tether.
Driving to a doorway or even gate is not super easy either, though.
Heavy drones falling on people or property are an issue that scares people, but they are also scared of robots on roads and sidewalks.
Drones probably cost more but can do more deliveries per hour.
Drones don’t have good systems in place to avoid collisions with other drones. Deliverbots won’t go that fast and so can stop quickly for obstacles seen with short range sensors.
Deliverbots have to not hit cars or pedestrians. Really not hit them.
Deliverbots might be subject to piracy (people stealing them) and drones may have people shoot at them.
Drones may be noisy (this is yet to be seen) particularly if they have heavier cargo.
Drones can go where their are no roads or paths. For ground robots, you need legs like the BigDog.
Winds and rain will cause problems for drones. Deliverbots will be more robust against these, but may have trouble on snow and ice.
In the long run, I think we’ll see drones for urgent, light cargo and deliverbots for the rest, along with real trucks for the few large and heavy things we need.
I’ve been on the road, and there has been a ton of news in the last 4 weeks. In fact, below is just a small subset of the now constant stream of news items and articles that appear about robocars.
Delphi has made waves by undertaking a road trip from San Francisco to New York in their test car, which is equipped with an impressive array of sensors. The trip is now underway, and on their page you can see lots of videos of the vehicle along the trek.
The Delphi vehicle is one of the most sensor-laden vehicles out there, and that’s good. In spite of all those who make the rather odd claim that they want to build robocars with fewer sensors, Moore’s Law and other principles teach us that the right procedure is to throw everything you can at the problem today, because those sensors will be cheap when it comes time to actually ship. Particularly for those who say they won’t ship for a decade.
At the same time, the Delphi test is mostly of highway driving, with very minimal urban street driving according to Kristen Kinley at Delphi. They are attempting off-map driving, which is possible on highways due to their much simpler environment. Like all testing projects these days, there are safety drivers in the cars ready to intervene at the first sign of a problem.
Delphi is doing a small amount of DSRC vehicle to infrastructure testing as well, though this is only done in Mountain View where they used some specially installed roadside radio infrastructure equipment.
Delphi is doing the right thing here — getting lots of miles and different roads under their belt. This is Google’s giant advantage today. Based on Google’s announcements, they have more than a million miles of testing in the can, and that makes a big difference.
Hype and reality of Tesla’s autopilot announcement
Telsa has announced they will do an over the air upgrade of car software in a few months to add autopilot functionality to existing models that have sufficient sensors. This autopilot is the “supervised” class of self driving that I warned may end up viewed as boring. The press have treated this as something immense, but as far as I can tell, this is similar to products built by Mercedes, BMW, Audi and several other companies and even sold in the market (at least for traffic jams) for a couple of years now.
The other products have shied away from doing full highway speed in commercial products, though rumours exist of it being available in commercial cars in Europe. What is special about Tesla’s offering is that it will be the first car sold in the US to do this at highway speed, and they may offer supervised lane change as well. It’s also interesting that since they have been planning this for a while, it will come as a software upgrade to people who bought their technology package earlier.
UK project budget rises to £100 million
What started with a £10 million pound prize has grown in the UK has become over 100m in grants in the latest UK budget. While government research labs will not provide us with the final solutions, this money will probably create some very useful tools and results for the private players to exploit.
MobilEye releases their EyeQ4 chip
MobilEye from Jerusalem is probably the leader in automotive machine vision, and their new generation chip has been launched, but won’t show up in cars for a few years. It’s an ASIC packed with hardware and processor cores aimed at doing easy machine vision. My personal judgement is that this is not sufficient for robocar driving, but MobilEye wants to prove me wrong. (The EQ4 chip does have software to do sensor fusion with LIDAR and Radar, so they don’t want to prove me entirely wrong.) Even if not good enough on their own, ME chips offer a good alternate path for redundancy
Chris Urmson gives a TeD talk about the Google Car
Talks by Google’s team are rare — the project is unusual in trying to play down its publicity. I was not at TeD, but reports from there suggest Chris did not reveal a great deal new, other than repeating his goal of having the cars be in practical service before his son turns 16. Of course, humans will be driving for a long time after robocars start becoming common on the roads, but it is true that we will eventually see teens who would have gotten a licence never get around to getting one. (Teems are already waiting longer to get their licences so this is not a hard prediction.)
The war between DSRC and more wifi is heating up.
2 years ago, the FCC warned that since auto makers had not really figured out much good to do
with the DSRC spectrum at 5.9ghz, it was time to repurpose it for unlicenced use, like more WiFi.
This is not a very good deal for the driver. After Uber’s 20% cut, that’s 72 cents/mile. According to AAA, a typical car costs about 60 cents/mile to operate, not including parking. (Some cars are a bit cheaper, including the Prius favoured by UberX drivers.) In any event, the UberX driver is not making much money on their car.
The 18 cents/minute — $10.80 per hour, drops to only $8.64/hour while driving. Not that much above minimum wage. And I’m not counting the time spent waiting and driving to and from rides, nor the miles, which is odd that the flag drop fee. There is a $1 “safe rides fee” that Uber pockets (they are being sued over that.) And there is a $4 minimum, which will hit you on rides of up to about 2.5 miles.
So Uber drivers aren’t getting paid that well — not big news — but a bigger thing is the comparison of this with private car ownership.
As noted, private car ownership is typically around 60 cents/mile. The Uber ride then, is only 50% more per mile. You pay the driver a low rate to drive you, but in return, you get that back as free time in which you can work, or socialize on your phone, or relax and read or watch movies. For a large number of people who value their time much more than $10/hour, it’s a no-brainer win.
The average car trip for urbanites is 8.5 miles — though that of course is biased up by long road trips that would never be done in something like Uber. I will make a guess and drop urban trips to 6.
The Uber and private car costs do have some complications:
* That Safe Rides Fee adds $1/trip, or about 16 cents/mile on a 6 mile trip
* The minimum fee is a minor penalty from 2 to 2.5 miles, a serious penalty on 1 mile trips
* Uber has surge pricing some of the time that can double or even triple this price
As UberX prices drop this much, we should start seeing people deliberately dropping cars for Uber, just as I have predicted for robocars. I forecast robotaxi service can be available for even less. 60 cents/mile with no cost for a driver and minimal flag drop or minimum fees. In other words, beating the cost of private car ownership and offering free time while riding. UberX is not as good as this, but for people of a certain income level who value their own time, it should already be beating the private car.
We should definitely see 2 car families dropping down to 1 car plus digital rides. The longer trips can be well handled by services like Zipcar or even better, Car2Go or DriveNow which are one way.
The surge pricing is a barrier. One easy solution would be for a company like Uber to make an offer: “If you ride more than 4,000 miles/year with us, then no surge pricing for you.” Or whatever deal of that sort can make economic sense. Sort of frequent rider loyalty miles. (Surprised none of the companies have thought about loyalty programs yet.)
Another option that might make sense in car replacement is an electric scooter for trips under 2 miles, UberX like service for 2 to 30 miles, and car rental/carshare for trips over 30 miles.
If we don’t start seeing this happen, it might tell us that robocars may have a larger hurdle in getting people to give up a car for them than predicted. On the other hand, some people will actually much prefer the silence of a robocar to having to interact with a human driver — sometimes you are not in the mood for it. In addition, Americans at least are not quite used to the idea of having a driver all the time. Even billionaires I know don’t have a personal chauffeur, in spite of the obvious utility of it for people whose time is that valuable. On the other hand, having a robocar will not seem so ostentatious.
All over the world, people (and governments) are debating about regulations for robocars. First for testing, and then for operation. It mostly began when Google encouraged the state of Nevada to write regulations, but now it’s in full force. The topic is so hot that there is a danger that regulations might be drafted long before the shape of the first commercial deployments of the technology take place.
As such I have prepared a new special article on the issues around regulating robocars. The article concludes that in spite of a frequent claim that we want to regulate and standarize even before the technology has been out in the market for a while, this is in fact both a highly unusual approach, and possibly even a dangerous approach.
Regulating Robocar Safety : An examination of the issues around regulating robocar safety and the case for a very light touch
The government baked robocar projects in the UK are going full steam, with this press release from the UK government to accompany the unveiling of the prototype Lutz pod which should ply the streets of Milton Keynes and Greenwich.
The new pod follows a similar path to other fully-autonomous prototypes, reminding me of the EN-V from GM, the MIT City Car and the Google buggy prototype. It’s electric, meant for “last mile” and will lose its steering wheel once testing is over.
I also note they talk eagerly about the Meridian shuttle being tested in Greenwich, even though that’s a French vehicle.
When it comes to changes to the vehicle code, I think it’s premature. Even without looking at the proposed changes, I would say that we don’t know enough to work out what changes are needed, even though we all might be full of ideas.
One proposal is to remove the ban on tailgating to allow convoys. A reasonable enough thing, except people are not going to build convoys for quite some time, I think. The Volvo/SARTRE experiment found a number of problems with the idea, and you don’t want to do your first deployments with something that could crash 10 cars if it goes wrong instead of one. You do that later, once you feel very confident in your tech.
Another proposal called for changing how cyclists are treated. The law in the UK (and some other places) demands cyclists be given the full berth of a car, and in practice nobody ever does that, and if they did do it, it would mean they just followed along at bicycle speed, impeding traffic. One of those classic cases, like speed limits in the USA, where the law only works if nobody follows it. (Though cyclists would say that they should just get the full lane like the law says.)
We will need to fix these areas of the vehicle codes, but we should fix them only after we see a problem, unless it’s clear that the vehicles can’t be deployed without the change. Give the developers the chance to fix the problem on their own first. If you fix the law before you know what the vehicles will be like, you may ensconce old thinking into the law and have a hard time getting it out.
It is interesting to see Governments adapt so quickly to a disruptive technology. It’s quite probable that our hype is a bit too good and will come back to bite us. I predicted this sort of jurisdictional competition as governments realize they have a chance to make their regions become players in the new automotive industry, but they are embracing some things faster than I expected.
There is great buzz about some sensor-laden vehicles being driven around the USA which have been discovered to be owned by Apple Computer. The vehicles have cameras and LIDARs and GPS antennas and many are wondering is this an Apple Self-Driving Car? See also speculation from cult of Mac.
Here’s a video of the vehicle driving around the East Bay (50 miles from Cupertino) but they have also been seen in New York.
We don’t see the front of the vehicle, but it sure has plenty of sensors. On the front and back you see two Velodyne 32E Lidars. These are 32 plane LIDARS that cost about $30K. You see two GPS antennas and what appear to be cameras in all directions. You don’t see the front in these pictures, which is where the most interesting sensors will be.
So is this a robocar, or is this a fancy mapping car? Rumours about Apple working on a car have been swirling for a while, but one thing to contradict that has been the absence of sightings of cars like this. You can’t have an active program without testing on the roads. There are ways to hide LIDARS (and Apple is super secretive so they might) and even cameras to a degree, but this vehicle hides little.
Most curious are the Velodynes. They are tilted down significantly. The 32E unit sees from about 10 degrees up to 30 degrees down. Tilting them this much means you don’t see out horizontally, which is not at all what you want if this is for a self-driving car. These LIDARs are densely scanning the road close around the car, and higher things in the opposite direction. The rear LIDAR will be seeing out horizontally, but it’s placed just where you wouldn’t place it to see what’s in front of you. A GPS antenna is blocking the direct forward view, so if the goal of the rear LIDAR is to see ahead, it makes no sense.
We don’t see the front, so there might be another LIDAR up there, along with radars (often hidden in the grille) and these would be pretty important for any research car.
For mapping, these strange angles and blind spots are not an issue. You are trying to build a 3D and visible light scan of the world. What you do’t see from one point you get from another. For stree mapping, what’s directly in front and behind are generally road and not interesting, but what’s to the side is really interesting.
Also on the car is an accurate encoder on the wheel to give improved odemetry. Both robocars and mapping cars are interested in precise position information.
Arguments this is a robocar:
The Velodynes are expensive, high end and more than you need for mapping, though if cost is no object, they are a decent choice.
Apple knows it’s being watched, and might try to make their robocar look like a mapping car
There are other sensors we can’t seee
Arguments it’s a mapping car
As noted, the Velodynes are titled in a way that really suggests mapping. (Ford uses tilted ones but paired with horizontal ones.)
The cameras are aimed at the corners, not forward as you would want
They are driving in remote locations, which eventually you want to do, but initially you are more likely to get to the first stage close to home. Google has not done serious testing outside the Bay Area in spite of their large project.
The lack of streetview is a major advantage Google has over Apple, so it is not surprising they might make their own.
I can’t make a firm conclusion, but this leans toward it being a mapping car. Seeing the front (which I am sure will happen soon) will tell us more.
Another option is it could be a mapping car building advanced maps for a different, secret, self-driving car.
After yesterday’s story about Uber and CMU, a lot of speculation has flown that Uber will now be at odds with Google, both about building robocars and also on providing network taxi service, since another rumour said Google plans to launch an Uber like “ride share” service.
Since then, the Uber blog post and this interview with Uber folks tell a slightly different story. Uber is funding a research center at CMU, and giving lots of grants to academics. Details are not fully available, but typically this means being at an early research stage. With these research labs, academics are keen to publish all they do, so little gets done in secret. In many cases the sponsor gets a licence to the technology but it’s often not exclusive. If Uber wanted to build their own car, chances are they would do it in a more private lab.
Rumours that David Drummond would resign from the Uber board also have not panned out. Google has invested hugely in Uber (already for good return at the present valuation) and Google Maps offers you an Uber if you ask it for directions somewhere — it’s actually one of the easier interfaces for ordering one.
Rumours around Google’s efforts suggest that Big G has been testing a “ride share” app with employees and plans to launch it. Google has denied that, and says it loves Uber and Lyft. Further news revealed the rumours were about an internal carpooling system, not involving the self-driving cars. I could imagine confusion because Uber and others call themselves “ride sharing” which is a bit of a fabrication to not look like a taxi, while a carpooling app would be real ride sharing. (UberPool is real ride sharing.) Google, which has a terrible undersupply of parking is very keen on getting employees to ride its bus system and to carpool.
That said, Google has talked about the same thing I talk about — the true goal of robocar technology being the creation of a mobility on demand taxi service, like Uber but at a much lower cost. Google has not said that they would provide that themselves, or who they would partner with if they did it. Most people have presumed it might be Uber but I don’t think that’s at all assured.
At the same time, Uber has assured its drivers they are not going away for the foreseeable future. I suspect that’s an equivocation, and just means that we can’t see very far in the future right now!
I commonly see statements from connected car advocates that vehicle to vehicle (V2V) and vehicle to infrastructure communications are an important, even essential technology for robocar development. Readers of this blog will know I disagree strongly, and while I think I2V will be important (done primarily over the existing mobile data network) I suspect that V2V is only barely useful, with minimal value cases that have a hard time justifying its cost.
Of late, though, my forecast for V2V grows even more dismal, because I wonder if robocars will implement V2V with human-driven cars at all, even if it becomes common for ordinary cars to have the technology because of a legal mandate.
The problem is security. A robocar is a very dangerous machine. Compromised, it can cause a lot of damage, even death. As such, security will have a very strong focus in development. You don’t want anybody breaking into the computer systems or your car or anybody else’s. You really don’t want it.
One clear fact that people in security know — a very large fraction of computer security breaches caused by software faults have come from programs that receive input data from external sources, in particular when you will accept data from anybody. Internet tools are the biggest culprits, and there is a long history of buffer overflows, injection attacks and other trouble that has fallen on tools which will accept a message from just anyone. Servers (which openly accept messages from outside) are at the greatest risk, but even client tools like web browsers run into trouble because they go to vast numbers of different web sites, and it’s not hard to trick people to sending them to a random web site.
We work very hard to remove these vulnerabilities, because when you’re writing a web tool, you have no choice. You must accept input from random strangers. Holes still get found, and we pay the price.
The simplest strategy to improve your chances is to go deaf. Don’t receive inputs from outside at all. You can’t do that in most products, but if you can close off a channel without impeding functionality it’s a good approach. Generally you will do the following to be more secure:
Be a client, which means you make communications requests, you do not receive them.
You only connect to places you trust. You avoid allowing yourself to be directed to connect to other things
You use digital signature and encryption to assure that you really are talking to your trusted server.
This doesn’t protect you perfectly. Your home server can be compromised — it often will be running in an environment not as locked down as this. In fact, if it becomes your relay for messages from outside, as it must, it has a vector for attack. Still, the extra layer adds some security. read more »
Update: On the Uber blog we now see it’s more funding of research labs at CMU, on many topics
That’s a major step, if true. People have often pointed out how well Uber is poised to make use of robocar technology to bring computer summoned taxi service to the next level. If Uber did not exist, I would surely be building it to get that advantage. Many have assumed that since Google is a major investment partner in Uber that they would partner on this technology, but this suggests otherwise.
I write about Uber a lot here not just because of interest in what they do today, but because it teaches us a lot about how people will view Robocars in the future. Uber’s interface is very similar to what you might see for a robocar service, and the experience is fairly similar, just much more expensive. UberX is $1.30/mile plus 26 cents/minute with $2.20 flag drop. The Black service is $3.75/mile and 65 cents/minute with an $8 flag drop. I expect robocar tax service to be cheaper than 50 cents/mile with minimal per-minute charges. The flag drop is not yet easy to calculate. What richer people do with Uber teaches us what the whole public will do with robocars.
Uber lets you say where you are going but doesn’t demand it. That’s one thing I suspect will be different with your robotaxi, because it’s really nice if they can send you a vehicle chosen for the trip you have in mind. Ie. a small, efficient car without much range for short, single person trips. Robotaxi services will offer you the ability to not say your destination — but they will probably charge more for it, and that means most people will be willing to say their destination.
Uber does not hide their desire to get rid of all their drivers, which sounds like a strange strategy, but the truth is that cab driving is not something most people view as a career. It’s a quick source of money with no special skills, something people do until something better comes along, or in the gaps in their day to make extra cash. Unlike people losing jobs to robots on a factory line, nobody is particularly upset at the idea.
Some new results from the NGV Team at the University of Michigan describe different approaches for perception (detecting obstacles on the road) and localizations (figuring out precisely where you are.) Ford helped fund some of the research so they issued press releases about it and got some media stories. Here’s a look at what they propose.
Many hope to be able to solve robotics (and thus car) problems with just cameras. While LIDAR is going to become cheap, it is not yet, and cameras are much cheaper. I outline many of the trade-offs between the systems in my article on cameras vs lasers. Everybody hopes for a research breakthrough or computer vision breakthrough to make vision systems reliable enough for safe operation.
The Michigan lab’s approach is a special machine vision one. They map the road in advance in 3D and visible light by using a mapping car equipped with lots of expensive LIDAR and other sensors. They build a 3D representation of the road similar to what you need for a video game engine, and from that, with the use of GPUs, they can indeed create a 2D image of what a camera should see from any given point.
The car goes out into the world and its actual camera delivers a 2D frame of what it sees. Their system then compares that with generated 2D images of what the camera should see until it finds the closest match. Effectively, it’s like you looking out a window and then going into a video game and wandering around looking for a place that looks like what you see out that window, and then you know where the window is.
Of course it is not “wandering,” and they develop efficient search algorithms to quickly find the location that looks most like the real world image. We’ve all seen video games images, and know they only approximate the real world, so nothing will be an exact match, but if the system is good enough, there will be a “most similar” match that also corresponds with what other sensors, like your GPS and your odometer/dead reckoning system, tell you about where you probably are.
Localization with cameras has been done before, and this is a new approach taking advantage of new generations of GPUs, so it’s interesting. The big challenge is simulating the lighting, because the real world is full of different lighting, high dynamic range, and shadows. The human system has no problem understanding a stripe on the road as it moves through the shadow of a tree, but computer systems have a pretty tough time with that. Sun shadows can be mapped well with GPUs, but shadows from things like the moving limbs of trees are not possible to simulate, as are the shadows of other vehicles and road users. At night, light and shadows come from car headlights and urban lights. The team is optimistic about how well they will handle these problems.
The much larger challenge is object perception. Once you have a simulation of what the camera should see, you can notice when there are things present that are not in the prediction — like another car or pedestrian, or a new road sign. (Right now their system mostly is looking at the ground.) Once you identify the new region, you can attempt to classify it using computer vision techniques, and also by watching it move against the expected background.
This is where it gets challenging, because the bar is very high. To be used for driving it must effectively always work. Even if you miss 1 pedestrian in a million you have a real problem because there are billions of pedestrians encountered by a billion drivers every day. This is why people love LIDAR — if something (other than a mirror or sheet of glass) sufficiently large is sufficiently close you, you’re going to get laser returns from it, and not from what’s behind it. It has the reliability number that is needed.
The challenge of vision systems is to meet that reliability goal.
This work is interesting because it does a lot without relying on AI “computer vision” techniques. It is not trying to look at a picture and recognize a person. Humans are able to look at 2D pictures with bizarre lighting and still tell you not just what the things in the picture are, but often how far away they are and what they are doing. While we can be fooled in a 2D image, once you have a moving dynamic world, humans are, generally reliable enough at spotting other things on the road. (Though of course, with 1.2 million dead each year, and probably 50 million or more accidents, the majority because somebody was “not looking,” we are far from perfect.)
Some day, computer vision will be as good at recognizing and understanding the world as people are — and in fact surpass us. There are fields (like identifying traffic signs from photos) where they already surpass us. For those not willing to wait until that day, new techniques in perception that don’t require full object understanding are always interesting.
I should also point out that while lowering cost is of course a worthwhile goal, it is a false goal at this time. Today, maximal safety is the overriding goal, and as such, nobody will actually release a vehicle to consumers without LIDAR just to save the estimated 2017 cost of LIDAR, which will be sub-$500. Only later, when cameras get so good they completely replace LIDAR safety capabilities for less money would people release such a system to save cost. On the other hand, improving cameras to be used together with LIDAR is a real goal; superior safety, not lower cost.
Let me confess a secret fear. I suspect that the first “autopilot”
functions on cars is going to be a bit boring.
I’m talking the offerings like traffic jam assist from Mercedes, super cruise from Cadillac
and others. The faster highway assist versions which combine ADAS
functions like lane-keeping and adaptive cruise control to keep the
car in its lane and a fixed distance from the car in front of you.
What Tesla has promoted and what scrappy startup “Cruise” plans to offer
as a retrofit later this year. This is, in NHTSA’s flawed “levels”
document what could be called supervision type 2.
Some of them also offer lane change, if you approve the safety of
All these products will drive your car, slow or fast on highways,
but they require your supervision. They may fail to find the lane in
certain circumstances, because the makers are badly painted, or confusing,
or just missing, or the light is wrong. When they do they’ll kick out
and insist you drive. They’ll really insist, and you are expected to
be behind the wheel, watching and grabbing it quickly — ideally even
noticing the failure before the system does.
Some will kick out quite rarely. Others will do it several times during
a typical commute. But the makers will insist you be vigilant, not just
to cover their butts legally, but because in many situations you really
do need to be vigilant.
Testing shows that operators of these cars get pretty confident,
especially if they are not kicking out very often. They do things they
are told not to do. Pick up things to read. Do e-mails and texts.
This is no surprise — people are texting even now when the car isn’t
driving for them at all.
To reduce that, most companies are planning what they call
“countermeasures” to make sure you are paying attention to the road.
Some of them make you touch the wheel every 8 to 10 seconds. Some will
have a camera watching your eyes that sounds an alarm if you look away
from the road for too long. If you don’t keep alert, and ignore the
alarms, the cars will either come to a stop in the middle of the freeway,
or perhaps even just steer wild and run off the road. Some vendors
are talking about how to get the car to pull off safely to the side of
There is debate about whether all this will work, whether the
countermeasures or other techniques will assure safety. But let’s
leave that aside for a moment, and assume it works, and people stay safe.
I’m now asking the harder question, is this a worthwhile product?
I’ve touted it as a milestone — a first product put out to customers.
That Mercedes offered traffic jam assist in the 2014 S-Class and others
followed with that and freeway autopilots is something I tell people
in my talks to make it clear this is not just science fiction ideas and
cute prototypes. Real, commercial development is underway.
That’s all true, and I would like these products. What I fear though,
is whether it will be that much more useful or relaxing as adaptive cruise
control (ACC.) You probably don’t have ACC in your car. Uptake on it is
quite low — as an individual add-on, usually costing $1,000 to $2,000,
only 1-2% of car buyers get it. It’s much more commonly purchased as
part of a “technology package” for more money, and it’s not sure what
the driving force behind the purchase is.
Highway and traffic jam autopilot is just a “pleasant” feature, as is ACC.
It makes driving a bit more relaxing, once you trust it. But it doesn’t
change the world, not at all.
I admit to not having this in my car yet. I’ve sat in the driver’s seat of
Google’s car some number of times, but there I’ve been on duty to watch
it carefully. I got special driver training to assure I had the skills to
deal with problem situations. It’s very interesting, but not relaxing.
Some folks who have commuted long term in such cars have reported it to
A Step to greater things?
If highway autopilot is just a luxury feature, and doesn’t change
the world, is it a stepping stone to something that does? From a
standpoint of marketing, and customer and public reaction, it is.
From a technical standpoint, I am not so sure. read more »
In my earlier article on robocar challenges I gave very brief coverage to the issue of parking. Challenged on that, I thought it was time to expand.
The world “parking” means many things, and the many classes of parking problems have varying difficulties.
The taxi doesn’t park
One of the simplest solutions to parking involves robotaxi service. Such vehicles don’t really park, at least not where they dropped you off. They drop you off and go to their next customer. If they don’t have another ride, they can deliberately go to a place where they know they can easily park to wait. They don’t need to tackle a parking space that’s challenging at all.
Simple non-crowded lots
Parking in basic parking lots — typical open ground lots that are not close to full — is a pretty easy problem. So easy in fact, that we’ve seen a number of demonstrations, ranging back to Junior 3 and Audi Piloted Parking. Cars in the showroom now will identify parking spots for you (and tell you if you fit.) They have done basic parallel parking (with you on the brakes) for several years, and are starting to now even do it with you out of the car (but watching from a distance.) At CES VW showed the special case of parking in your own garage or driveway, where you show the car where it’s going to go.
The early demos required empty parking lots with no pedestrians, and even no other moving cars, but today reasonably well-behaved other cars should not be a big problem. That’s the thing about non-crowded lots: People are not hunting or competing for spaces. The robocars actually would be very happy to seek out the large empty sections at the back of most parking lots because you aren’t going to be walking out that far, the car is going to come get you.
The biggest issue is the question of pedestrians who can appear out from behind a minivan. The answer to this is simply that vehicles that are parking can and do go slow, and slow automatically gives you a big safety boost. At parking lot speed, you really can stop very quickly if a pedestrian appears out of nowhere. The car, after all, is not in a hurry, and can slow itself when close to minivans, or if it has noticed pedestrians who are moving near it and have disappeared behind vehicles. Out at the back of a parking lot, nobody cares if you go 5 km/h, or even right down the center of the lane to assure there are no surprises.
To the right we see a picture of Junior 3 entering a parking lot, hunting for a space and taking it — in 2009.
Mapping is still desirable for parking lots. This is particularly true because parking lots, not being public roads, set up their own sets of rules and put up signs meant only for humans. They may direct traffic to be one-way in certain areas in nonstandard ways. They may have gates when you have to pay or insert tickets. Parking spots will be marked reserved for certain cars (Electric vehicle, expectant mother, wheelchair, employee of the month, CEO, customers of company X) with signs meant for humans.
It’s not necessarily super hard to map a parking lot, just time consuming to encode all these rules. Unlike roads, which everybody drives, any given parking lot likely only serves the people who live, work or shop next to it — you will never park in 95% of the lots in your city, though you will drive most of its main roads. Somebody has to pay for the cost of that mapping — either because lots of people want to use the lot, or because the owner of the lot wants to encourage robocars. Fortunately, with the robocars doing things like using the least popular spots, or even valet parking as described below, there is a strong incentive to the owner of a lot to get it mapped and keep it mapped. Only lots that never fill out would have no incentive, and those lots can often be parked in without a map.
While you want trained mappers to confirm the geometry of a parking lot, coding in the signs and special rules is a task easily left to the parking lot owner. If the lot manager forgets to tag the CEO’s space as reserved, nobody is hurt (except the lot manager when the CEO arrives.)
Robocar parking mistakes are easy to fix. Robocars can put a phone number or URL on the back where you can go to complain about a robocar that is parked badly or blocking things. As long as that doesn’t happen too often, the cost of the support desk is manageable. The folks at the support desk can look out with the robot’s sensors and tell it to move. It’s not like finding a human driven car blocking something, where you have to find the owner. In a minute, the robocar will be gone.
More crowded lots
The challenge of parking lots, in spite of the low speeds, is that they don’t have well defined rules of the road. People ignore the arrows on the ground. They pause and wait for cars to exit. In really crowded lots, cars follow people who are leaving at walking speed, hoping to get dibs on their spot. They wait, blocking traffic, for a spot they claim as theirs. People fight for spots and steal spots. People park badly and cross over the lines.
As far as I know, nobody has tried to solve this challenge, and so it remains unsolved. It is one of the few problems in robocars that actually deserves the label of “AI,” though some think all driving is AI.
Even so, on the grand scheme of things, my intuition is that this is not one of the grand unsolved challenges of AI. Parking lots don’t have legalized rules of the road, but they do have rules and principles, and we all learn them the more we park. Creating a system that can do well with these rules using various AI tools seems like a doable challenge when the time comes. My intuition is that it’s a lot easier than winning on Jeopardy. This system will be able to take advantage of a couple of special abilities of the robocars:
They will be able to park and exit spots quickly and efficiently. They won’t be like the people you always see who do a 5 point turn to exit their parking spot when you (but not they) can see they still have 5 feet of room behind them.
In general, they will be superb parkers, centering themselves as well as possible inside spots
They don’t need room to open their doors, so they can park right next to walls and pillars.
Yes, they could also park right next to badly parked cars which have encroached into other spaces and thus made a space no human can use. There is a risk of course that the bad parker, who finds they can’t get in one side, might retaliate. (I’ve had a guy rip my mirror off in revenge.) In this case, though, they will have a photo of the licence plate and a sensor record of the revenge taking place!
In the event of problems or deadlock, they are open to the idea of just giving up and parking somewhere farther away that is easier to park in. Unlike humans they could drive as quickly in reverse as forward to back out of situations.
In spite of all this, the cars will want to avoid the full parking lots where the chaos happens. If there is another lot not far away, they will just go there, and require a couple minutes more advance notice from their master when summoned to pick them up. If there is nowhere nearby to park, the car will tell its passenger that she has to do the parking.
Even in the most crowded lots, there is the potential to easily create zones of the parking lot that are marked:
“Robot Valet Parking only. All other cars may be blocked in or towed. No pedestrians.”
In the car’s map, it will indicate what server is handling the robo-valet section, though it is possible to have it work without any communication at all.
In the most basic version the car would ask permission to enter the lot. The database might even assign it a spot, but generally it would just enter and take any spot. By “any spot”, I mean any piece of pavement, ignoring the lines on the ground. At first the cars would choose spots that let them have an unblocked pack to leave. As soon as too many cars arrive to do that, they would switch to a more dense, valet pattern that blocks in some cars (the ones who said they were leaving latest.) It would report where it parked to the database, as well as how to send it a message, and when it expects to leave.
Other cars would arrive. Eventually one would block in your car. If the database has given them a way to communicate (probably over the internet, though if they had V2V they could use that) they might discuss who plans to leave first, and the cars would adjust themselves to put the cars that will leave sooner at the front. This is strongly in the interests of the cars. If you plan to be there a while, you want to go to the back so you don’t have to keep moving to let cars behind you out. But it still works, just not as well, if the cars just take any available spot.
When it’s time to leave, the cars could try to send a message over the data networks to the cars in front of them, but a simpler approach might be to just nudge slightly forward — a few cm will do it. This will cause the car in the direction of the nudge to notice, and it too would nudge forward, and so on, and so on until the front car moves out, and then all the cars in that row can move out, including your car, which leaves the lot. Then the other cars can move in to fill the spot. If they have a database which maps the cars in that section, they could try to be clever in how they re-fill the empty column to minimize movement.
There are even faster algorithms if you leave a few empty spaces. Robocars have the ability to move in concert to “move the space” and put it next to a car that wants to exit. It’s more efficient, but not needed.
The database becomes more useful if a human driver ignores the signs and tries to park in the lot. That’s because the database is the simplest way of spotting a vehicle that’s not supposed to be there. As a first step, the cars in the lot could start flashing their lights and honking their horns at the interloper, or even speak human language messages out a speaker. “Hey, this is the robot valet lot, you are blocking me in! We’re calling a tow truck to come remove you if you don’t leave.” Some idiots may still try, and the robots could arrange so that almost all of them can still get out, and if not, they might call that tow truck.
The robo-valet section can be at the back of the parking lot, or the top of a structure — those places the humans park in last. The owner of the lot has a huge incentive to do this, since they can make much more efficient use of their land with the tight valet-dense parking. All the owner has to do is register the lot section in a database — a database that a company like Google would probably be happy to offer for free to benefit their cars.
Human valets could also park cars in this area. They would just need to use an app on their smartphone that tells them where to park and allows them to register that they did it. The robots will want the human-parked cars to park at the back, because they will move out of the way when it’s time for the human parked car to be driven back out.
The main requirements for this parking area would be that it be reachable from the outside without going through a zone of chaos, and that it then be possible to also reach the pickup/dropoff point for passengers without the risk of getting stuck in chaos. Larger lots tend to have entrance lanes without spots on them that serve this purpose.
Pedestrians will still enter the lot, in spite of the sign. Just go extra slow if they are there, and perhaps talk to them and ask them to leave. While you won’t actually present a danger to them at your low speed, they probably will heed the advice of 3000lb robots. Perhaps tell them they have 15 seconds to put down their weapon.
To get really clever, the sign marking the border of the Robo-Valet area might itself be on a small robot. Thus, when the robo-valet area gets full, the sign can move to expand the area if space is available. You could expand even into areas occupied by human-parked cars — just know that they are there and don’t block them in — or move out of their way when needed. Eventually they leave and only robocars enter.
When the demand goes down, the sign can easily move to shrink the valet area.
A timeline of 2 to 5 years for deployment of a vehicle
Public disclosure that Roush of Michigan acted as contract manufacturer to build the new “buggy” models — an open secret since May
A list of other partners involved in building the car, such as Continental, LG (batteries), Bosch and others.
A restatement that Google does not plan to become a car manufacturer, and feels working with Detroit is the best course to make cars
A statement that Chris does not believe regulation will be a major barrier to getting the vehicles out, and they work regularly to keep NHTSA informed
A few more details about Google’s own LIDAR, indicating that units are the size of coffee cups. (You will note the new image of the buggy car does not have a Velodyne on the roof.)
More indication that things like driving in snow are not in the pipeline for the first vehicles
Almost all of this has been said before, though the date forecasts are moved back a bit. That doesn’t surprise me. As Google-watchers know, Google began by doing extensive, mostly highway based testing of modified hybrid cars, and declared last May that they were uncomfortable with the safety issues of doing a handoff to a human driver, and also that they have been doing a lot more on non-highway driving. This culminated with the unveiling of the small custom built buggy with no steering wheel. The shift in direction (though the Lexus cars are still out there) will expand the work that needs to be done.
Car company announcements out of the Detroit show were minor. The press got all excited when one GM executive said they “would be open to working with Google.” While I don’t think it was actually an official declaration, Google has said many times they have talked to all major car companies, so there would be no reason for GM to go out to the press to say they want to talk to Google. Much PR over nothing, I suspect.
Ford, on the other hand, actually backtracked and declared “we won’t be first” when it comes to this technology. I understand their trepidation. Being first does not mean being the winner in this game. But neither does being 2nd — there will be a time after which the game is lost.
There were concept vehicles displayed by Johnson Controls (a newcomer) and even a Chinese company which put a fish tank in the rear of the car. You could turn the driver’s seat around and watch your fish. Whaa?
In general, car makers were pushing their dates towards 2025. For some, that was a push back from 2020, for others a push forward from 2030, as both of those numbers have been common in predictions. I guess now that it’s 2015, 2020 is just to realistic a number to make an uncertain prediction about.
Earlier, Boston Consulting Group released a report suggesting robocars would be a $42B market in 2025 — the car companies had better get on it. With the global ground transportation market in the range of $7 trillion in my guesstimate, that’s a drop in the bucket, but also a huge number.
News from the Transportation Research Board annual meeting has been sparse. The combined conference of the TRB and AUVSI on self-driving cars in the summer has been the go-to conference of late, and other things usually happen at the big meeting. Released research suggested 10% of vehicles could be robocars in 2035 — a number I don’t think is nearly aggressive enough.
There also was tons of press over the agreement between NASA Ames and Nissan’s Sunnyvale research lab to collaborate. Again, not a big surprise, since they are next door to one another, and Martin Sierhuis the director of the research lab made his career over at Nasa. (Note of disclosure: I am good friends with Martin, and Singularity U is based at the NASA Research Park.)
Day 3 at CES started with a visit to BMW’s demo. They were mostly test driving new cars like the i3 and M series cars, but for a demo, they made the i3 deliver itself along a planned corridor. It was a mostly stock i3 electric car with ultrasonic sensors — and the traffic jam assist disabled. When one test driver dropped off the car, they scanned it, and then a BMW staffer at the other end of a walled course used a watch interface to summon that car. It drove empty along the line waiting for test drives, and then a staffer got in to finish the drive to the parking spot where the test driver would actually get in, unfortunately.
Also on display were BMW’s collision avoidance systems in a much more equipped research car with LIDARs, Radar etc. This car has some nice collision avoidance. It has obstacle detection — the demo was to deliberately drive into an obstacle, but the vehicle hits the brakes for you. More gently than the Volvo I did this in a couple of years ago.
More novel is detection of objects you might hit from the side or back in low speed operations. If it looks like you might sideswipe or back into a parking column or another car, the vehicle hits the brakes on you (harder) to stop it from happening.
Insurers will like this — low speed collisions in parking lots are getting to be a much larger fraction of insurance claims. The high speed crashes get all the attention, but a lot of the payout is in low speed.
I concluded with a visit to my favourite section of CES — Eureka Park, where companies get small lower cost booths, with a focus on new technology. Also in the Sands were robotics, 3D printing, health, wearables and more — never enough time to see it all.