As an engineer myself, I find robocars a very cool idea. And as (it seems) one of the few people who drives a lot but doesn't particularly enjoy it often, I would really like to use them. However, I would push against them for the one reason that it gives lots of power to the government and anyone who reads the news knows that there is an increasing trend in serious abuses of that power.

First is a complete lack of privacy - there are now records on everywhere you drive. I have enough of that with Texas toll tags, photos of license plates and I hear more such sensors are coming.

Second is that if a cracker gains access, even just to monitor, he can wreak tremendous damage to lives.

Third, the system will generate marketing data that will be sold by the state and used against us to place billboards and driver-selective advertising. We almost have this today with cell phone tracking re bluetooth and other avenues. John Smith drives by the McDonalds and a sign practically invites him in my name and his favorite dish.

Fourth, in the event of any kind of protest or revolution, the state can shut down cars, giving them total control over transportation that they currently have over air travel and are slowing gaining on train and bus travel. Imagine a Do-Not-Fly list extended to a Do-Not-Drive list, where anyone with trigger names has their car shut off when they get within a mile of the Whitehouse.

Please consider these issues and add a new chapter to your excellent series that addresses them. The governments are NOT going to get more benign and we must not hand them more keys over our lives. As EFF Chairman all of these and more must surely have crossed your mind in writing your essays.

"it the leading cause of death. "
No, do your statistics properly. Everything is the leading category of anything. Say accident kills 60%, disease kills 40%. The we could say the causes of death are 1. disease 2. workplace accident 3. traffic accident. Just state your percentage, don't try to rank categories that you haven't even bothered to elucidate (let alone justify). Because the time has indeed come for quality "robocar" advocacy.

The last DARPA Grand Challenge was held 11/3/07. Where is the one for this year? There was one in 2004 and 2005, and for some reason 2006 was skipped and so it's apparently the case with 2008, but what about 2009 and beyond? Disturbingly, when I go to the webpages of the finalists, most of them are still acting as if the 2007 event were held yesterday. Is that it? Is it done forever? Of course, the point of the challenge was not to design cars to take over the role of human drivers in city/highway traffic, but I got to believe there is still a lot more these cars can be challenged with before they can actually be deployed in the battlefield. I sure hope it comes back in 2009. Two years is a lot of time to make improvements. In addition to getting the researchers to compete and make better cars, it also gets people interested and more comfortable with the idea.

I've had a similar idea that I describe here http://highscalability.com/scaling-traffic-people-pod-pool-demand-self-driving-robotic-cars-who-automatically-refuel-cheap-sola - Scaling Traffic: People Pod Pool of On Demand Self Driving Robotic Cars who Automatically Refuel from Cheap Solar. Keep up the good work. It will happen sometime.

"But few will buy the Tango today."

I suspect this is not so much a distrust of the batteries but more an issue of price.
The design is unusual, but I think it is a great solution for the single commuter.

Availability is also another factor, there are a few interesting EVs on the market but are either high cost high performance or just not sold outside their local area, i.e. California USA!

What we need is a cost comparable commuter vehicle that can cover at least 100 miles per charge at a reasonable speed 50 - 60 MPH.

Maybe the sentence should read

"But few CAN buy the Tango today."

Derek

One aspect of robot cars that would contribute to their relative safety is that they're more likely to cooperate with one another. It's one thing to set up a program that guides one's own car... but if the cars can communicate with one another, then we'd see better on-road cooperation. For example, if my car had to switch to another lane to make a turnoff, it could send a request to other robot-controlled cars in that lane, which could ease off and allow me the space I'd need.

As for the issue of centralized control, and the guvmint shutting down drivers... well, they can do this now _anyway_, and it requires a lot of messy and occasionally dangerous police work.

Here's an interesting question; what about emergencies? I can see ambulances and police cars requesting "emergency access" which'd nudge other cars out of the way. But would ordinary drivers be able to request such access in rare occasions (like the classic wife-in-labor situation)?

Hi Brad,

Great series -- really got me thinking about the possibilities, and convinced me that these are a better alternative to PRT, which I've been a fan of for a few years.

So, as an interested computer geek, I'm curious about where to go from here. Are there companies that are putting money into this kind of work? Or will it really take a presidential call to action for things to get moving? If the latter, what's the best way to start getting up to speed on some of this -- building my own self-navigating robots? Learning AI?

Appreciate your (or anyone else's) input on these questions.

Best,
Sean

Great set of articles on robotic cars.

I had written about electric powered robotic cars as well.
http://nextbigfuture.com/2008/07/electric-powered-exclusive-robotic-car.html

My belief is that the city robocar only zones is the best way to start deploying robotic cars sooner.
The current versions of robotic cars are very close to being up to the job of navigating slower city streets.

I had not realized how poor the efficiency was of the US public transportation system.
This is of course not the case in places like Hong Kong and Japan and some places in europe where rider density
is far higher.

My brother at University of Miami in Florida related hearing a story from our mother, which I hadn't heard first hand, about life back in pre WW-II Yugoslavia in a German-speaking village near Belgrade.

A person could go to a party and get drunk as a skunk (think of Die Fledermaus -- partying and drinking and practical jokes represented in that comic opera were very much the cultural norm, at least for Grandpa's generation and friends). When it was time to leave, you simply needed to be lucky enough to have a friend stuff you into your horse-draw carriage -- instead of play a joke on you by leaving you on a park bench in a bat costume like in the opera.

Then all you had to do was give the horse a verbal command "Home!" The horse was inclined to return to its stable of dry straw bedding and fresh hay anyway, and you would be driven home, automatically and safely.

A horse is not nature's brightest creature, but it seems what you are trying to do is invent a computer and accompanying software to be at least as capable as a horse, or at least with regard to image processing, path planning, and obstacle avoidance. And a computer that doesn't leave "presents" on the roadway for someone else to clean up.

I'm glad I found this article, because I have been advocating this for a while, but you have a much bigger audience.

As an engineer, I'm sick of wasting my time driving when I know car itself could do the job much of the time. I even joined a DARPA Urban Challenge team, but it was poorly run so I dropped out.

I'll bet that the time wasted during driving adds up to an enormous amount of lost productivity, and a tiny bit of that value, spent on this project, could go a long ways.

I'd love to have an electric car (because they are better to drive), but frankly, not being a member of the Church of Climate Change, I'd be happy if my SUV could do the job. In fact, I've been think about how to interface to the cruise control...

Keep it up!

BTW, a long term (expensive infrastructure) solution to the battery charging problem is battery exchange. You drive to a service station, a robotic machine extracts your discharged smart battery pack, inserts a fully charged one, and charges your card based on the cost of the transaction (battery age, energy costs, overhead, a little profit). Notice that this uses a current approach (servicestations) - always a good thing if you can do it, and is more efficient (the power distribution capacity increase is focused on a few places rather than every home) and

I want my robocar to fly. And it should mix me drinks while we're flying. For me to even consider buying it it must give me shiatsu massages as a default, without me asking. BJs would be nice, too, and maybe a big 'ol steely dan should be standard equipment for the ladies. And I thought of a cool way to help even more with parking congestion. Why not install some sort of anti-gravity AI? That way my robocar could just float over my destination (e.g. a Star Trek convention) and I could just slide down a rope. Better still, all robocars could come with transporters that could zap us that last 50 feet from our hovering cars to our final destination . Better still, why not skip right over the robocar part and just give everyone a personal or family-sized transporter. That'd be awesome! No more traffic, no more accidents ('cept the occasional genetic blending with flies like in the movie). And all those highways could be turned into bike trails! Or open space! Or community gardens!

Yea. The future is gonna be so cool.

Wonderful, another step towards making me more subservient to the whim of politicians.

next, you'll want to automate my thermostat so the A.I. can decide the proper temperature for me.
Wait, that one's going to be here first.

You'll take the keys to my "dumb" car when you pry them from my cold, dead hands.

I get a little concerned over the idea that you seem to be working on Step G (or so), when we haven't gotten past Step B yet: The current leader in "practical robotics" is iRobot; yet their 5th-generation Roomba, which is capable of several things beyond what the Discovery (series 4), can now clean multiple rooms in a single "mission"; yet it is no longer possible to use two Roombas in adjacent rooms (which the simpler 4th-generation Discovery could do).

It seems that the 4th-generation used a single "command center" to program everything to the same (remote) clock, including the Virtual Walls; the 5th-generation Roombas each have their own Scheduler, and now use RF to turn the Virtual Walls on and off -- and the Virtual Walls are "keyed" to individual Roombas, so now, when one Roomba finishes its schedule, it turns off the Virtual Wall that had kept the other Roomba in its own playpen.

Apparently, iRobot thought that they'd had the "simple" problem so well contained that they could increase the "complex problem" capacity, and unfortunately, they overlooked something. (It's commonly noted that "software is someone else's idea of how to solve your problem".)

By your own admission, the first robocars are likely to kill people; but, What If (great Sci-Fi question): Steps C, D, and E get us to the point where there are a number of Robocars on the road, and everything seems to work; steps F and G bring us to your "school of fish" robocar-traffic-solution; and then some tiny, overlooked detail -- the "Naw, no one would EVER do THAT with a car" (as, apparently at iRobot, no customer was ever expected to use multiple Roombas on the same floor) -- causes your school of fish to all swerve TOWARD the fire-truck that all the programmers had expected it to AVOID --

-- and then hundreds of people are killed or maimed in one single "oops".

The shuttle explosion killed seven people, and ground the entire space program to a halt; what will a "cluster collision" (I could've used a different term there, hehe) do to any nascent Robocar program? And how can you be SURE you've solved ALL of the problems before you turn two tons of autonomy loose on the streets?

... that iRobot seems to have no idea how to solve the abovementioned cooperation problem; their own monolithic mindset keeps them from seeing anything other than the problems that they themselves come up with.

I'll feel safe riding in a robocar when...

1. It can routinely merge into the traffic stream of an uncontrolled freeway that is just at the edge of spontaneous slowdown capacity, like everyone is going 50 mph even though the limit is 65.

2. It can successfully negotiate a left turn thru a 4-way by 4-lanes intersection with an unexpected traffic light breakdown, in traffic with mixed human and robotic drivers, in the midst of a blinding Texas thunderstorm.

Piece of cake for many humans...

The current condition of the various car manufacturing companies world wide and the impact of that on the rest of various economies is illustrative..

Assuming that huge public investment in mass transit could effect a huge change in car ridership, this is the impact that would have on these industries and various service sectors.. for better or worse.

RoboCars on the other hand could be (probably will be) manufactured by the existing car manufacturers, serviced by the same service sector, on roads built by the same contractors... etc. It provides a way to move most of the current industry and service sector employment forward into new areas with the least disruption. And as pointed out without huge public investment (that mass transit requires).

Robocars are also useful everywhere... not just in areas where sufficent density exists to justify mass transit.

The killer app. The idea is to make the self-checkout stand at the grocer mobile. Order over the Internet,wait an hour, and the robovan shows up at your curbside.

A variant of the idea is the autonomous electric cargo van. The cargo van can guide itself for a mile using battery, but for long hauls, the cargo vans align themselves,and electrically connect. Then diesel electric hauler powers the convoy up and moves them down the road, to the next freight switching lot. Any parking lot becomes an automated freight yard. Cargo vans can be dropped off at the grocer where they drive themselves to the unloading dock.

The main benefits will come from robocars on the highways. This is where the high speed accidents occur, and thus the majority of fatalities, as well as where most of the traffic congestion is. Once the majority of cars on the highways are computer controlled, traffic accidents will be greatly reduced, and the resulting congestion reduced as well. Fewer cars slowing down to rubberneck, and fewer erratic drivers will also help to reduce congestion.

Your ideas about robocars on city streets and the resulting improvements to society are interesting and well thought out, but I think this is much farther down the road. By the time it becomes practical, many things will have changed which we simply cannot predict. In addition, I think there will be a great deal of resistance of people to completely giving up control of their vehicles.

Highway-only robocars, however, may be viewed as just an extension of the current cruise control, so people may be more willing to accept them. You could drive yourself onto the freeway and activate the computer control. You then relax or attend to other business while the car navigates through the freeway interchanges, and then lets you know when it's close to the exit that you need to take. You then take over control, exit the freeway, and continue to your destination. This is a much easier problem than dealing with intersections and city streets. And we're much closer to that reality now, with adaptive cruise control and lane sensing technology, so it's easy to see this happening in the near future. And it could also become mandatory for people wishing to talk on a cell phone while on the highway to put their car under computer control.

Having seen how much my parents lives closed down when they ceased to be able to drive, I am strongly hoping that robocars come along by the time I cease to be able to drive (maybe another 20 years, if I am lucky).

Also, I have several friends who cannot drive (epilepsy, seriously impaired vision) and have their lives significantly restricted by this. Robocars would give them a freedom the rest of us enjoy.

Finally, as someone who enjoys a beer or three, I would be very pleased not to have to have the "who is not drinking tonight" discussion. While I don't get drunk, I certainly go far beyond the safe level for driving (essentially, none) and an inexpensive robotaxi would be wonderful. (Yes, there are taxis here, but a manned taxi home can double the cost of the evening).

And how do you generate electricity? The efficiency of generation is about 60%, plus variable losses in transmission. Over 50% of electricity is generated by coal, so don't give me all this crap about "saving the planet".

Robotaxis are an utterly bad idea because of vandalism.

I haven't seen anything in you robocar blog on the Intellidrive government/industry program. Did I miss it?

The RoboCars are really the victory of science ie artificial intelligence and robotics. I also know my question may occur foolish if, but I need to know can the car will be able to take decision when something would be moving fastly above car say. something huge dropping above it. I know this is not checked by any individual driving the car but, i would be great if It can take decision when any action like this happens. if these module are included then I say its great and more inspiring.

thanks

Hi Brad,

Interesting stuff. Do you think it will make a difference (theoretically perhaps not) if the robocar's footprint will be smaller (or sleeker) than usual?

Hi Brad,

Interesting stuff. Do you think it will make a difference (theoretically perhaps not) if the robocar's footprint will be smaller (or sleeker) than usual?

The future of automated/autonomous personal transportation and freight delivery is neither a car nor a delivery truck and it is not the Google's driverless car either.

Why is anyone trying to figure out how to make a car or a truck drive themselves after they are designed and built to be driven? I suppose the reason is that we already have the vehicles and the roads; but, has anyone considered developing and implementing a fully automated/autonomous personal transportation and freight delivery system using vehicles no one has to drive from the start? I did and submitted a U.S. Patent Application for it.

The proposed transportation system consists of vehicles that move on steel rails on their own propulsion using electric motors and respond to voice or panel commands to drive itself to a physical address anywhere the tracks can take them. With the implementation of my transportation system proposal a dad or a mom will be able to place their kids in a fully automated/autonomous vehicle that will take them to school and that same vehicle can come back to take dad to work. At work he can send the vehicle back home so that his wife can do her errands. At the mall she can send the vehicle to a specialized parking facility for such vehicles and she will later be able to recall it with her cell phone. Back home she will have the groceries she purchased on the internet delivered to her from her favorite supermarket. Later that day grandma can send them a piece of pie she baked without ever having to leave her house.

There are no crossings along the tracks path and there's no need for track switches to route vehicles to its destination as each vehicle has a steering mechanism. Once the vehicles start moving there's no need for them to stop until they reach their destination. Location markers and electronic signals in the tracks along with sensors in the vehicles allows a computer on board each vehicle to use navigation software to determine the exact position of the vehicle at any time and program the fastest way to a destination. The information is relayed to computers at a master control that identifies each vehicle then handles and monitors vehicular flow along the tracks networks or trackways. As each vehicle get their power from the tracks assembly there's no need to recharge them. A power meter and a relay device in each vehicle communicating with a processing center allows for automatic electronic transactions so that each vehicle owner can be charged to their account for power consumption, tolls and vehicle registration.

Passengers and freight are transported inside a module that hangs from a propulsion dolly. Rubber bumpers attached at each end of the propulsion dollies allow the vehicles to travel bumper-to-bumper at a uniform constant speed during rush hour for optimal performance of the system. As the vehicles travel bumper-to-bumper at high speeds the system resembles a canning or bottling line in full operation. When the vehicles merge the system resembles a zipper being closed and as the vehicles diverge the system resembles a zipper being opened. The propulsion dolly motor will slow down or speed up controlled by a computer on board each vehicle to allow the vehicles to keep on rolling and merge without colliding with each other automatically.

Passengers and freight modules can be any size and take any shape as long as they fit within the tracks boundaries and are able to traverse the curved and inclined track sections. Vehicles are privately owned and passengers are expected to ride with the same comforts and amenities of a modern automobile. The set-up of rental and taxi business operations using such vehicles is also a possibility. Vehicles can have movable seats so passengers can adjust them to face the forward movement or look back as the vehicle moves along the tracks. As the passengers and freight modules hang from a propulsion dolly this allows the modules to swing out in curved track sections so as to diffuse the centrifugal force and to remain in a horizontal position when the dolly traverses inclined track sections resulting in a more comfortable ride for passengers.

The vehicles passengers module can travel close to the ground as a car does and over obstacles and pedestrians along elevated track sections. Some track sections are designated to leave and pickup passengers at home and institutional, commercial and public spaces. Vehicles moving along elevated track sections will ride a loop until a space is available to leave and pickup passengers and will then descend to pedestrian level to do so. An array of conventional signals and barriers are used to protect pedestrians from being hit by a moving vehicle as passengers move from or to their vehicles. Once passengers leave their vehicles these can be sent anywhere on their own to pickup and transport other passengers or to a designated parking space and then these can later be recalled using a cell phone. Specialized multi story mechanized parking buildings for such vehicles are foreseen. The vehicles freight modules can also travel close to the ground to allow for easier loading and unloading of the modules. Detachable cargo containers can also be used instead of freight modules. Tracks can go inside a building, around buildings attached to the buildings and from one building to another attached to bridges high above the ground. To get high into a building and to a higher or a lower track vehicles travel a spiral track section. When vehicles get inside an enclosed space they come out traversing across the same track section they got in.

Batteries on each vehicle will provide for emergency power backup. If a vehicle losses propulsion due to a malfunction it will be pushed at the dolly bumpers by other vehicles to the next emergency exit. In the event of an accident or structural failure of the tracks a master control can stop all vehicles at once and redirect traffic. Vehicles can also be stopped manually from the inside of a passengers module or by using an external emergency stop button on premises accessible to anyone as a safety measure while they move close to the ground such as when leaving or picking up passengers. Catwalks with stairs to ground level installed at a convenient distance one from the other allow passengers to leave their vehicles in an emergency situation when the passengers modules are high above the ground.

No other transportation system in use today can claim driverless door-to-door freight delivery but my proposal does. Same thing for personal transportation even if it is to a building floor several stories from the ground or from one building to another at any height. No need to go to a station then wait in line to get a PRT (Personal Rapid Transit) pod car. PRT is not a reliable nor an efficient personal transportation and freight delivery alternative to a car and a freight truck because such vehicles only go from one station to another as a collective transportation system does and the only similarity to a personal transportation system is that people can travel in a private vehicle. Another drawback of current PRT is that you could end up waiting in line for a long time until a vehicle is available to pick you up. Is there a personal transportation system with vehicles that can travel bumper-to-bumper at a uniform constant speed during rush hour for optimal performance of the system? My proposal has them and when they do the system resembles a canning or a bottling line in full operation. Prior art contraptions that resemble features of my proposal are not a practical proposition for a personal transportation and freight delivery system that allows people to go anywhere they want and allows delivery of freight anywhere along the tracks, their main drawback being the vehicles guideway configuration.

Accordingly it is the object of my proposal to provide a personal transportation and freight delivery system that: 1-Is easy to build, setup and operate as a fully automated transportation system using conventional automation methods and equipment. 2-Is a reliable, safe and efficient alternative to a car and a freight delivery truck that can really save lives and reduce traffic accidents. No Google driverless autonomous car can accomplish this as their developers claim as they still rely on cars moving on roads. 3-Allows people to go anywhere the tracks will take them using their own fully automated/autonomous vehicle no one has to drive. 4-Is a reliable, safe and efficient alternative to a delivery truck using fully automated/autonomous vehicles no one has to drive to deliver all sorts of goods and merchandise anywhere along the tracks. 5-Can transport a single passenger more efficiently than a car does as the passengers modules can be shaped ergonomically to transport only one passenger. 6-Can transport freight more efficiently than a delivery truck does as the freight modules and detachable cargo containers can be shaped in any form and size. 7-Uses less land than streets, highways and freeways construction does. 8-Adapts easily to the existing urban outline. 9-Contributes less environmental pollution than cars and trucks do. 10-May help reduce oil dependence. Google driverless cars developers suggest autonomous cars will be able to reduce oil dependence yet they still rely on cars moving on roads. 11-Allows children, older people and people with disabilities to provide their own personal transportation since no driving skills are needed to operate such vehicles. 12-Allows passengers to carry out other activities while they go from one place to another since there’s no need to drive such vehicles. 13-Have the least moving parts subject to wear and tear and most components are easily accessible for proper maintenance and repairs. 14-Allows vehicles to travel over obstacles including cars and pedestrians. 15-Allows vehicles to travel inside a building and into an office space or a living space several stories above ground. 16-Allows vehicles to travel from one building to another at any height from the ground. 17-Enables a more comfortable ride for passengers than a car does in curved and inclined path stretches.

Considering that the proposed transportation system should have a significant influence in our daily lives and will allow for innovative changes in the architecture and design of our cities it is reasonable to expect that the implementation of a transportation system such as this could transform our way of life and the urban landscape in the XXI Century as the automobile did in the XX Century.

Thanks, AZ

I am far from convinced that robo cars will maintain the current safety standards which we currently have in place. Today in the middle of a bridge span, dry wall on the roof of a panel van began to lift off and fly toward traffic behind the van. There is no way a robo car could have handled this situation without causing further danger to the occupants or other vehicles around the robocar. For instance, the robo car would not have known a strong cross wind would carry the dry wall off the side of the bridge within 30 feet of lift off. The robo car would not have known the object was dry wall in the first place. Who knows what the "programmer" had coded into the software for this case. Clearly a lot more needs to be done and disclosed before we should endanger ourselves by allowing robo cars on the road.

It is also clear that robo cars are not the Utopian end all goal. In order to make use of a robo car safe, our rights to travel freely will most likely be diminished. The robo car's software can not account for all possible circumstances where a human brain will have had 5 solutions to the problem within 1/2 a second. There will be a movement to reduce influencing factors. This means people will have to have their rights taken away to make a robo car more safe.

This is not a matter of technology readiness, it is a matter personal freedom and our rights to travel anywhere freely and safely. A robo car is simply not up to that task.

I just discovered your blog and thesis and I love it. In the section called "The Curse of the Human Driver" I have discovered a typo. the sentence "While these death numbers are the most compelling argument for robocars, we seem to have become so innure to them that it may be the gasoline-saving consequences that you will see" should be "While these death numbers are the most compelling argument for robocars, we seem to have become so innured to them that it may be the gasoline-saving consequences that you will see"

This is not a critcism. I think your blog is very useful.

I would think that hydrogen fuel cell vehicles (FCVs) are a natural fit for robocars as not only do they provide the extra range (400 miles for a Hyundai ix35) but have the power to run the computers.

Just discovered your Robocars place and I find the information very interesting.
Will be handing references to clients and partners, as it paints a very accurace portait of the landscape (and will save us a lot of talk).

Now, about your article "Cameras or Lasers?" (http://ideas.4brad.com/robocars-are-future)

A new generation of low-resolution "flash-type" LIDARs are now coming out. They solve 5 out of the 7 disadvantages of LIDAR identified in your article:
- Expensive? Not!
- No Moving Parts
- High refresh rate
- Impervious to rain or snow (because of the introduction of “multiple return” – “Full waveform analysis” technology)
- Mounted inside – Behind windshield

Resolution and range are creeping upwards.

While they are not sufficient for fully automated driving.
LIDAR now does provide an affordable, reliable and safe solution for autonomous braking and automated cruise control applications.
Camera still has its place as a complement in other less safety-critical applications (lane keeping assist and sign recognition being examples).

Now, here is the shameless plug:
Aerostar is one of the players to watch in this area: www.aerostar.ca
The advanced signal processing in Aerostar's sensors is a good example of what the next generation holds, after Continental's SRL1, which already has wide market acceptance and is seen on a number of car brands.
(For fairness sake: http://www.conti-online.com/www/industrial_sensors_de_en/themes/srl_1_en.html).

is good but man uses a bigger font mah eyes burn