Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
×
Transportation Technology

Cadillac SRX Converted Into Self-Driving Car 149

fergus07 writes "There's been much talk about self-driving cars in recent times and the latest glimpse into this autonomous future comes from Carnegie Mellon University where researchers have loaded a Cadillac SRX with an array of sensors that allow it to manage highway traffic, congested roadways, and even merging on and off ramps."
This discussion has been archived. No new comments can be posted.

Cadillac SRX Converted Into Self-Driving Car

Comments Filter:
  • So what happens when a light has a communication error and the car ends up in a bad crash? who is at fault and what happens to the victims who have bills that are pillaging up while the courts are working out who will have to pay them.

    • Re: (Score:3, Funny)

      by Anonymous Coward

      what happens to the victims who have bills that are pillaging up while

      You keep using that word, I do not think it means what you think it means.

    • My guess is that, at least initially, a driver will be required to be in the drivers seat at all times ready to override any actions taken by the car. In that case, the driver would likely be at fault for not correcting any action taken by the car that leads to an accident, just as in some vehicles out on the roads now, a driver is responsible for making sure he/she doesn't crash into other cars even when there is a system that can detect obstacles and take action or if the car can park automatically.

      • My guess is that, at least initially, a driver will be required to be in the drivers seat at all times ready to override any actions taken by the car

        At which point, WTF is the point of the self driving car?

        If I need to be paying attention every second in case the computer does something stupid (and need to be able to anticipate every point at which it could do something stupid), it will require as much or more attention as if I was driving anyway.

        I have no interest in a self driving car, and I certainly wou

        • I just don't see people actually wanting this technology

          Yes, I can't imagine anyone who'd rather be able to nap, read a book, or do anything other than staring at the bumper in front of them during a regular weekday commute.

          • by gstoddart ( 321705 ) on Monday September 09, 2013 @11:49AM (#44798145) Homepage

            You assume that people could trust the technology. My personal experience is the rest of the drivers on the road will still do stupid and random shit, which has a good chance of negating any of the benefits of a car on auto-pilot.

            What you're describing is better served with public transit or something.

            When you have a huge fraction of your cars still being older and not using this technology, a lot of the assumptions about how this safe will be goes out the window.

            I'd love to see these systems handle someone in the right turn lane with their signal on swooping over 3 lanes and turning left. And the cost involved in changing every car over to this would be so high as to make it a pipe dream.

            • My personal experience is the rest of the drivers on the road will still do stupid and random shit, which has a good chance of negating any of the benefits of a car on auto-pilot.

              You are assuming that the self driving vehicle would be less able to deal with "stupid and random shit" than a given human. Computers can potentially have greater situational awareness and also react faster than humans. A car could communicate with other vehicles regarding position and speed and road conditions. A car can have 360 degree vision day or night, clear or foggy. A car can estimate distance to the car ahead of it to within millimeters whereas people are often wrong by dozens of meters. Cars

          • by kc9jud ( 1863822 )

            I just don't see people actually wanting this technology

            Yes, I can't imagine anyone who'd rather be able to nap, read a book, or do anything other than staring at the bumper in front of them during a regular weekday commute.

            You missed this other part of gstoddart's comment:

            If I need to be paying attention every second in case the computer does something stupid (and need to be able to anticipate every point at which it could do something stupid), it will require as much or more attention as if I was driving anyway.

            Maybe you shouldn't be commenting on Slashdot while napping, reading a book, or anything else...

        • If someone has to sit behind the wheel pretending to drive then self-driving cars will never catch on. However, the goal is to have vehicles that do not need someone waiting to take over at a moment's notice. Once true self-driving cars are available I suspect that they will catch on very fast. Most driving is tedious. Vehicle that allows people to do something constructive while their vehicle takes them wherever they need to go will probably be quite popular. And then there is the aging population tha

          • by cusco ( 717999 )
            the aging population that wants to stay mobile

            I used to work for the Retired and Senior Volunteer Program in northern Michigan. Probably 1/3 of my job was to find transportation for people who could no longer drive. The typical scenario was that someone in Detroit or Grand Rapids or Chicago would reach 65, retire, and decide to move to northern Michigan where they've spent most of their summer vacations. They buy a place on Spider Lake (if they have money) or in Bingham (if they don't), and enjoy the
        • If the technology actually works to the point that it truly is autonomous, that will be amazing. It will mean I can go on long drives and actually look out the window. I can read or write or watch movies during my commute. Plenty of people will like that. If it works.
        • My guess is that, at least initially, a driver will be required to be in the drivers seat at all times ready to override any actions taken by the car

          At which point, WTF is the point of the self driving car?

          If I need to be paying attention every second in case the computer does something stupid (and need to be able to anticipate every point at which it could do something stupid), it will require as much or more attention as if I was driving anyway.

          I have no interest in a self driving car, and I certainly wouldn't pay for the privilege. If I wanted that, I could take the bus or the train.

          I just don't see people actually wanting this technology, and since we'll never convert all of the cars on the road to this system, it means at best a fraction of your cars are self driving and playing by one set of rules -- while the rest of your drivers are doing the same random shit they do now.

          This has always struck me as a technology which nobody actually wants.

          It's like so many of these 'futurist' things which are impractical, will be too expensive, and which will never happen. This is a research project which might have some applications ... but which will never be practical for widespread use.

          As Joshua Shaffer said... there are many, many people who have 45+ minute commutes. Those commutes could be spent doing leisure activities, chatting with friends/family, doing work, or even sleeping. It would also open up more people to taking longer commutes because that time is no longer wasted driving a car. Finally, you wouldn't even have to OWN the car. A pool of cars could be shared by people with dissimilar schedules.

        • by sjbe ( 173966 ) on Monday September 09, 2013 @12:17PM (#44798599)

          At which point, WTF is the point of the self driving car?

          To get to the point where they actually are safer than one being actively piloted by a human. Furthermore even if they never become completely self-driving there will be a lot of very useful spin off technology that is going to come from this research. The legal framework for these cars can be updated when appropriate. That is the easiest problem with the technology since we already know how to do that.

          I just don't see people actually wanting this technology, and since we'll never convert all of the cars on the road to this system

          Yes people do actually want this technology. In fact I'd go so far as to say people who don't even think they want it actually do even if they don't know it yet. There already are self-parking cars, cars with automatic speed control/braking, stability control, ABS, traction control, navigation aids, drive by wire steering/braking, cruise control, and more. All those things are portions of a driverless vehicle. It's by no means a solved problem but we already rely on a host of technologies to make us better at driving than we could be unassisted.

          I would dearly love to be able to get to/from work (~30 minute each way commute) without having to waste an hour every day with the non-productive task of driving. It is a huge waste of my time. It potentially solves other problems as well like helping handicapped people, reducing drunk driving, freeing up huge amounts of non-productive time and more.

          We don't actually have to convert all the cars to driverless. It would potentially only take a fraction of them to be self piloting to improve road safety. I assure you that you do not really want my 94 year old grandmother behind the wheel of a car. I would welcome a self driving car to take her around. Any driverless solution will have to be robust enough to deal with unpredictable events at least as well as a human. A well designed system could have better situational awareness than any driver. My field of vision is only about 160 degrees even when I'm not distracted. A computer would have 360 vision day or night, be able to communicate with other vehicles regarding position and speed and direction, be able to react faster than any human, be far less prone to distraction, and actually obey the rules of the road. The engineering obstacles are large but so are the potential benefits.

        • by idji ( 984038 )
          commercial jetliners are self-flying - they still have two pilots. relax, "driverless" driving is coming, and for a long period of transition "hybrid" mode will be available. you get what you want.
      • Are you saying that if you were behind the wheel in a self-driving car and it ran a red light, you wouldn't be the first one to sue the auto maker (assuming you survived)? I don't see any way that the auto-maker wins in a court case in that scenario, unless there are laws that explicitly say you have to drive the car and the manufacturer has no-fault protection. If the latter is the case, then what's the point? Am I going to let the machine do the work if I'm solely responsible for when it screws up?

        I
        • The same can be said of self-parking cars, though, where as far as I know, the driver is still responsible. It's just another convenience. If you want to slack off and read a book while driving, sure, but IF you crash, then you're responsible for letting it happen. In the red light case, any driver should be able to detect that the car is not braking and override the autopilot. If you want to read a book then take the train/bus, at least for the foreseeable future.

          I'm just saying that this is likely what wi

      • My guess is that, at least initially, a driver will be required to be in the drivers seat at all times ready to override any actions taken by the car.

        I don't think so (at least in a rational world). These cars are going to be 10x better than a human driver right out of the gate.

      • This raises an interesting question I hadn't previously considered: in most states, liability insurance is required to drive on public roads. What insurance company will insure an autonomous car?

        I am usually the last person to take the position, "the free market will take care of it," but in this case ... maybe it can. When the insurance companies are ready to accept the risk, I think I will be as well.

        • by gewalker ( 57809 )

          This make shock you, but once insurance companies determines the automatic cars have lower and/and less serious accidents that manual cars, they will be glad to insure the cars at lower rates too.

          Except for one factor, the fear the tort lawyers will be able to win disproportionate damages based on the automatic feature failing to protect their clients. So, its not the actuaries that will screw you, its the lawyers.

        • Having thought about this for exactly 5 minutes, I have an opinion :)

          Set up a no-fault insurance system where everyone is required to have insurance. Let the insurance companies set the rates per car, so that better automated systems will have lower insurance rates. Print the average insurance cost on the window sticker for the car, same way mileage is set now.

          The most obvious unintended incentive with my proposal is that drivers and self-driving car manufacturers would focus on protecting their own car fro

      • My guess is that, at least initially, a driver will be required to be in the drivers seat at all times ready to override any actions taken by the car.

        Which means that 999 out of 1000 times, the human driver would wind up making things far worse than if he had let the computer handle it.

        You're assuming that the driver will stay constantly alert, and constantly watch what is going on around him, even when he is not driving. Common sense should tell you that it's not going to happen. The person in the car wi

    • I've wondered something similar about this myself. In an accident, the driver of the vehicle is the one who usually is considered to be responsible for the vehicle. Is the company that manufactured the "driverless" system at fault, or is the primary occupant liable for legal repercussions? Surely the legal system will have to work out a few kinks before we see driverless cars in common use.
    • The liability will probably end up being rolled into the insurance system. Automated vehicles will have black boxes and record everything that happens, so there will be none of the my word against his word that happens in so many crashes now. It will be quite easy to determine who or what was at fault. The growing use of dashboard cameras is already a step in this direction, and some US insurance companies already offer discounts if the driver installs a data recorder. If the problem is truly technical

    • by Dr Max ( 1696200 )
      It depends. When it's truly driver-less then insurance costs can be built into the cost of the vehicle and the car company would pay out (and if they can be as safe as they reckon, that shouldn't be much at all) or it could be a special plan with your insurance provider. Before proper driver-less cars your going to see advances on cruise control, stuff like lane centering, then highway driver, and car park parker; the driver will still be responsible in these cases but if the features don't work like advert
    • In the first place, the sensors will be redundant, and with good redundancy you can get one flaw every 20,000 years of use.

      In the second place, everyone will be liable. The driver, the manufacturer, maybe even the dealership that sold you the car. In order to preempt that, congress has the option to change the laws to limit liability of any of those parties, much like they've done with guns. If it weren't for special laws protecting gun manufacturers, there would be massive lawsuits which would kill the m
    • So what happens when a light has a communication error and the car ends up in a bad crash? who is at fault[?]

      Uh.... wait.... When the stoplight, the piece of equipment installed by the city and responsible for the right of way on the road, has an error, like showing two green lights when one of them should be red, which causes two cars to crash into each other? That scenario? I imagine the city is at fault. You know, cause we depend on them not fucking up street lights.

      Why is no one commenting on this? ....ok, so apparently

      "Our Cadillac also supports V2V and V2I communications," Rajkumar explains. This communication allows the SRX to connect with designed traffic lights and other vehicles that are equipped with the technology,

      There are systems in place to help driverless cars. Neat. But I imagine that if they fuck t

    • by Kjella ( 173770 )

      At least here in Norway you can't legally drive a car on public roads without insurance (in which case the government pays out if you cause an accident, then go after you both financially and legally) and I don't expect self driving cars to be any different. Either the regular auto insurance will offer one or the self-driving car companies would have to launch their own, in which case you're only liable for gross negligence on your part. Technical problems with the car are obviously not of that type, it's a

    • So what happens when a light has a communication error and the car ends up in a bad crash?

      You mean, like what happens every day with people at the wheel?

    • by JWW ( 79176 )

      This is a good question.

      The other question would be:

      Why are the outliers and very unlikely events that will happen because of self driving cars continued to be the excuse that prevents us from implementing them and saving the thousands of lives lost due to human error and incompetence on the highways every year?

    • So what happens when the breaks do not respond the the pedal and the car ends up in a bad crash? who is at fault and what happens to the victims who have bills that are piling up while the courts are working out who will have to pay them.

      If the communication error is from lack of maintenance, then it would be the owner and his insurance company. If it is from a defect in the system then it would be the manufacturer.

      For most parts there should be a way for a person to take control if needed.

    • by Molochi ( 555357 )

      Assuming those cars have a blackboxed drive log, it should be easier to determine what specifically is at fault and where.

      Just like now, you'll still have to carry insurance, just in case your car is the one that screws up or you want coverage for others' faults. You'll still want to read that contract to verify that it covers what you want so that you aren't waiting for a lawsuit to resolve.

      If I'm in an accident, my insurance company writes me check if I'm covered. If it's my fault (within certain limits)

  • as long as they don't make a 1982 Pontiac Trans Am [wikipedia.org] - this is not newsworthy for me
  • I wonder what the V2V communication is about. I expect that in an ideal world other automated vehicles could communicate obstacles, road condition, and velocity data to one another, but this seems ripe for abuse or exploitation. In a worst-case scenario, someone could use that to either completely stop traffic or to cause an accident.
    • Wow, that'd be almost as bad as the existence of some sort of centralized computer controlled mechanism for directing traffic. You know, something with red and green lights. Oh wait, we have those. But yeah traffic lights are totally ripe for abuse. Imagine if someone could control those. They could certainly stop traffic or cause accidents. I wonder why it's not a rampant problem afflicting society.... oh wait. This isn't a cyberpunk novel. Most street lights run on dumb timers and don't have any input. Ot

      • by cusco ( 717999 )
        Not sure about elsewhere, but here in the Seattle/Bellevue/Tacoma/Everett area the move has been to centralize traffic control to alleviate the rapidly degenerating traffic situation (population growth has greatly outstripped the area's ability to upgrade the road infrastructure.) Dept. of Transportation in King, Pierce and Snohomish counties can alter timing of lights, give preference to traffic moving in one direction over the other, stop all traffic in case of an emergency, grant/remove precedence to pe
    • V2V is peer-to-peer and really focused on reducing reaction times. It allows the car ahead to instantly tell the car behind it is braking. This means less latency for corrective action. This also helps non-autonomous cars since V2V equipped vehicles could, theoretically, suck up some of the shockwaves present in current highway driving.
  • by phantomfive ( 622387 ) on Monday September 09, 2013 @11:41AM (#44798017) Journal

    allow it to manage highway traffic, congested roadways, and even merging on and off ramps.

    This is how you know self-driving car tech is not quite ready, when they are bragging about being able to manage an off-ramp.

    Seriously folks, we are not going to have a fully autonomous car by 2020.

    • by h4rr4r ( 612664 )

      You mean it is already better than the average american driver? Sounds like they are right on track.

      At 1700 everyday the on ramp to the freeway is a total mess even though there is lots of room to move to the left. It seems it is very rare for a human to be able to get on and move over into a higher speed lane. That is if they can even go up the ramp, because many driver in this area at least refuse to use the merging lane and believe they must merge onto the highway at the top of the ramp even if they have

      • What makes you think this autonomous car handled the situation any better?
        • by h4rr4r ( 612664 )

          I assumed that this would not be considered a passing score for the using on and off ramp test.

          I sure as hell would not call it one. Hopefully it can also manage yields and roundabouts. That or can we please start requiring actual driver training and testing?

          • Hopefully it can also manage yields and roundabouts.

            Looks like it can only handle freeway driving, so no.

            I assumed that this would not be considered a passing score for the using on and off ramp test.

            Unfortunately I can't find anywhere that gives the details of the driving test, so my assumption is they went at a time that didn't have a traffic jam on the off-ramp.

            • by h4rr4r ( 612664 )

              This seems way less self driving and more like poorly assisting then.

              I want a car that can drive me home from the bar. Anything short of that and I would be unlikely to be interested.

              • Yes. That was the (attempted) point of my original post. I feel like AI might be in for another winter after all the hyped promises it's been making recently (self-driving cars by 2020, full and complete cat brain simulations).
      • by cusco ( 717999 )
        As long as it's better than the car full of Asian kids that I saw stop in the middle lane of the freeway during rush hour a few days ago, back up, then cut across two lanes of traffic because they were going to miss their off ramp. Made me really glad I was riding the bus.
    • by Anonymous Coward

      allow it to manage highway traffic, congested roadways, and even merging on and off ramps.

      This is how you know self-driving car tech is not quite ready, when they are bragging about being able to manage an off-ramp.

      In Pittsburgh this is actually a rather significant achievement.

    • by PPH ( 736903 ) on Monday September 09, 2013 @12:17PM (#44798589)

      In these parts, Cadillacs that miss off-ramps just back up on the freeway and try again. If they can implement this behavior in an autonomous car, I'd say they are good to go.

    • 7 years is a long time for technology to improve. I mean, look at the Ford Focus. It parks with little to no help from the driver. I know it's a primitive example but it's an important one.

      The way I see it whenever the car feels it cannot continue navigation it will park and ask the driver to take over. The result of this is less experienced drivers so I'm not sure how we benefit until the things are 100% self sufficient.

      • The way I see it whenever the car feels it cannot continue navigation it will park and ask the driver to take over.

        Wow, that could be awful. I'm not the greatest parker, so I could totally see it getting itself stuck in some situation where I sure can't help it out.

    • by Kozz ( 7764 )

      I want to read about its success in navigating some of the highway system surrounding the twin cities in Minnesota.

      I remember once merging onto an interstate there (from the right) only to need to cross four lanes so that I could catch my exit (on the left) what seemed to be only a half-mile later. I probably endangered myself, my passengers and fellow motorists making that maneuver. This would be a good place to reduce accident risk. :)

      • by McFly777 ( 23881 )

        I want to read about its success in navigating some of the highway system surrounding the twin cities in Minnesota.

        I remember once merging onto an interstate there (from the right) only to need to cross four lanes so that I could catch my exit (on the left) what seemed to be only a half-mile later. I probably endangered myself, my passengers and fellow motorists making that maneuver. This would be a good place to reduce accident risk. :)

        You probably weren't supposed to use that entrance/exit combination. I know of at least two other cities where such a situation exists and they have solid white lines (not dashed) and signage specifically instructing you not to do it. (people still do, and accidents still happen). In both cases there were surface street exits that very quickly convey one to the same place as the freeway multiple-lane-crossing maneuver winds up.

    • It seems they can do all the routine parts of driving. The hard parts will be navigating detours, construction zones and obeying traffic cops, and doing all of that without reliable GPS. Still, it's exciting. I don't know if we'll even have a fully autonomous car by 2030, but I expect great advances in collision avoidance that will really help with all the baby boomers retiring.

  • Oh man i'd love this: I'm not even allowed to drive as i'm an epileptic and my partner would love it too, she can and does drive but if she didn't have to she'd be glad to be driven around by the car.

    But the real challenge is to find a manufacturer who's willing to dodge the sueball coming at them if one of those things goes wrong, even if it is (and it will have to be, and will be) 10 times safer than any human driver. Legal problems are going to snuff out this baby at birth.

    • A Self Driving car has a whole new layer of computers, servos, pumps, linkages, regulators, etc. that can and will break. It's bad enough you can be stranded in the middle of nowhere when you alternator fails, but now your car may shut down Friday, at 5:15 on the 405 Freeway because a safety feature disables it.

      Bad idea all the way around.

    • by cusco ( 717999 )
      I can drive, and would really rather not. My wife can drive, but insists on making me do it if we're both going somewhere. I figured out why old men drive slow, it's because they have their wife in the car. I would be pleased as punch to just sit back and let her yell at the autopilot when the driver 1/4 kilometer ahead changes lanes without signalling.
  • by Mashdar ( 876825 ) on Monday September 09, 2013 @11:54AM (#44798237)

    This capability has been implemented for years. The DARPA Grand Challenge has had many capable entrants, including (I believe) CMU. All of the described behavior was required years ago in the Grand Challenge.

    See DARPA Urban Challege 2007:

    http://archive.darpa.mil/grandchallenge/ [darpa.mil]

    To even qualify:
     

    National Qualification Event

    The NQE for the Urban Challenge was divided into three separate test areas, each with its own flavor and set of challenges:

    The NQE A test course required robots to safely merge into and out of two-way traffic in a tight, circulating course. Needless to say, this led to some hair-raising moments for some of the traffic drivers. Besides the complex timing and scoring being recorded by course officials, traffic drivers would alert officials to aggressive behavior with an ever-popular horn blast. Amazingly, in eight days of testing, only one traffic vehicle was actually struck by a robotic vehicle, a testament to the progress of the teams and DARPAâ(TM)s focus on safety.

    The meandering NQE B course tested robots on their ability to stay within a lane as they traversed this 2.8-mile course. One section, affectionately termed âoeThe Gauntletâ required the robots to delicately maneuver through a series of parallel parked cars and road obstacles. A final test on the NQE B course required the robots to find an assigned parking spot between adjacent parked cars, then safely pull into and back out of the spot before proceeding on its mission.

    NQE C was traffic intensive, consisting of a series of four-way stop intersections for the robot to negotiate, each with its own arrangement of traffic. Robots had to recognize the other vehicles at these intersections, determine the order of precedence and then safely proceed through the intersection when it was their turn. For the second half of the NQE C course, various road blocks were emplaced and the robots were tested on their ability to recognize the road block, execute a U-turn and dynamically replan a new route to complete their mission.

    • The main advance is the progression towards real-world sensor selection and packaging. If you look at all the cars which completed the Urban Challenge, and the Google cars, you'll notice the spinning Velodyne laser sensor on the roof. It is a great sensor and makes autonomous driving much easier. Unfortunately, that sucker costs more than most luxury cars and would never be deployed the real-world since nobody wants a spinning can on their roof.

      Carnegie Mellon would not have won the Urban Challenge without

  • >> Cadillac SRX Converted Into Self-Driving Car

    Audi had this problem back in the 80's.

  • Seriously, considering the demographic that actually buys Cadillac cars, it's the obvious make which needs this first ;-)

    • Funny, but Cadillac has done a lot to shed their old-person face and put on a newer young face.

      Actually some of their cars are actually pretty sporty now. Their CTS series and even the SRX are the same size as the average cars out there in their class, they actually look decent, and have decent horsepower.

      I know a few 20-somethings that have Cadillacs and they love them. Heck I had one too, but wanted to upgrade to a small SUV so I had to sell it.

      They're not the old-folk looking car anymore, they have som

      • by sribe ( 304414 )

        I was aware Cadillac was trying to shed their old-fogey image; I was not aware they had succeeded. (It took a long time...)

        • "Succeeded" is a relative term

          Some people will never change their mind about it. A person with a larger car than my CTS got into it and complained it was a boat / huge / etc. And how old it looked. Meanwhile my CTS looked a lot sportier than hers, and was smaller, had a lot of kick, etc. I should also mention, said girl was driving an old Buick full-size sedan.

          I was willing to let it slide though, because she was cute :-)

          Those people are never going to change their mind. I guess the only alternative is

  • by cellocgw ( 617879 ) <cellocgw.gmail@com> on Monday September 09, 2013 @12:47PM (#44799023) Journal

    Every time an automated car story shows up, a zillion people feel the need to show how sure they are that human drivers can handle more situations than the computers. First of all, why can't they (the ignoramuses posting this stuff) ever accept that hundreds of very smart engineers, not only at Google Research, have taken all sort of 'whoops what happened there' situations into account?

    Second, why are these posters incapable of noticing that other transportation systems such as the DC subways or nearly all modern jet aircraft, currently function very well completely autonomously? Yes, Cthulhu might pop up in the middle of a subway tunnel, but a human operator will do no better than the computer in avoiding it.
    One more reference: several USAF fighter aircraft are designed for high maneuverability, and are in fact unstable. Only tightly-bound wing surface control loops, fully computerized, keep the things flying in the intended direction.

    • Comment removed based on user account deletion
      • I'm one of those people who brings up these situations as I really do want answers to the many scenarios. My favourite scenario is when i'm a jaywalking pedestrian. Do I now have the power to stop all cars by simply walking into the street?

        My new scenario is garbage night in the city on two lane streets (one each way). Currently I have to go around the garbage truck into on-coming traffic when it is safe to do so. Will the self-driving car sit behind the garbage truck as it goes from house-to-house, business-to-business?

        It looks like we are mainly talking about highway driving right now as opposed to city. Though i'm still interested in a highway scenarios where the vehicle is in a lane that no longer continues and becomes and off-ramp lane. There are several of these on the 400 series highways in Toronto that cause traffic backups. What is the decision for such a scenario when cars are fast moving, bumper to bumper, and nobody is letting anybody else in? Will the vehicle take the off-ramp, stop, or cut somebody off?

        Once you know the decision trees for these scenarios, how will it affect your decisions as non-self-driving driver?

        Yes, a jaywalker causes traffic to stop. Oddlly enough, at least in most of the USA, that's the law now.

        If it's illegal to cross a double-yellow, then no you cannot pass a garbage truck. Or a school bus. OTOH, if they change the law, taking advantage of your car's ability to talk with the garbage truck and thus know if it's safe to go around it, you will.

        If your car, and all the other autonomous vehicles, know you are - or aren't- taking the exit, space will be automatically be generated for merging in e

      • by cusco ( 717999 )
        Garbage trucks are likely to be one of the first fully-autonomous vehicles. It's an absolutely brainless job that everyone hates, and pays pretty well because you have to shovel the money at people to get them to take it. Already most of the truck's operations are automated already, with the exception of the driver. This would also allow 24x7 operation of the truck, which are currently limited to one or two shifts per day. One truck doing the work of three, saving the salary of three drivers, and you co
  • by Quila ( 201335 ) on Monday September 09, 2013 @01:38PM (#44799839)

    I would love to see how this handles someone in the next lane suddenly moving into the car's lane, sideswiping it. It could look at the other side's lane or oncoming traffic too. For example, no oncoming traffic means safe to swerve into oncoming lane to avoid the sideswipe. Oncoming traffic or quickly upcoming traffic from behind, and it could just decide to accept the sideswipe as the least-harmful choice. It would be difficult for a human to take all this into account in under a second when just in regular driving mode (not racing, where they tend to keep 360 awareness).

A morsel of genuine history is a thing so rare as to be always valuable. -- Thomas Jefferson

Working...