Slashdot Mirror

← Back to Stories (view on slashdot.org)

Self-Driving Car Will Make Trip From San Francisco To New York City

Posted by samzenpus on from the bo-hands dept.

An anonymous reader writes with news that Delphi Automotive is undertaking the longest test of a driverless car yet, from the Golden Gate Bridge to midtown Manhattan. "Lots of people decide, at one point or another, to drive across the US. College kids. Beat poets. Truckers. In American folklore, it doesn't get much more romantic than cruising down the highway, learning about life (or, you know, hauling shipping pallets). Now that trip is being taken on by a new kind of driver, one that won't appreciate natural beauty or the (temporary) joy that comes from a gas station chili dog: a robot. On March 22, an autonomous car will set out from the Golden Gate Bridge toward New York for a 3,500-mile drive that, if all goes according to plan, will push robo-cars much closer to reality. Audi's taken its self-driving car from Silicon Valley to Las Vegas, Google's racked up more than 700,000 autonomous miles, and Volvo's preparing to put regular people in its robot-controlled vehicles. But this will be one of the most ambitious tests yet for a technology that promises to change just about everything, and it's being done not by Google or Audi or Nissan, but by a company many people have never heard of: Delphi."

90 of 132 comments (clear)

  1. Paris to Beijing by Anonymous Coward · · Score: 1

    Cross country in the USA is rather blah, compared to Citroen's drive from Paris to Beijing many moons ago.

  2. Or will it? by istartedi · · Score: 2, Funny

    Will it, or will it just go off for a few lube jobs and tell us it did that? When AI learns how to cook the books, then I'll be impressed... and scared.

    --
    For all intensive purposes, "whom" is no longer a word. That begs the question, "who cares"?
    1. Re:Or will it? by Anonymous Coward · · Score: 1

      Ask yourself this question "If I'd gotten laid this morning, would I really care about telling OP he's teh stupid and I'm smart?"

    2. Re:Or will it? by causality · · Score: 1

      I'm sick of stupid people talking.

      He was just joking. When stupid people talk, they generally assume everyone else is as stupid as they are. Thus they ignore what you clearly are saying and how it was obviously intended to be interpreted, because that would make sense -- and you're as stupid as they are, right? -- so that just can't be what you meant. Then they twist the meaning around, play idiotic word games, and perform various mental gymnastics. Then they ascribe the results to you; the fascinating part is that they can do this themselves while believing that you are responsible. Then they state what was obvious all along, patting themselves on the back because of how "wrong" you are and how "right" they have been all along. Finally Daddy will be proud and find time for them, or those bullies back in school will regret picking on them, or whatever their problem was that made them so insecure in the first place. Until next time someone posts anything ever-so-slightly controversial, anyway.

      Nothing short of turning a three-line post into paragraphs of legalese covering each potential interpretation of all terms used would satisfy them, as though such personalities aren't destroying the fun of this site already. Even in that case, I suspect they'd find a way to be a nuisance.

      --
      It is a miracle that curiosity survives formal education. - Einstein
    3. Re:Or will it? by Immerman · · Score: 1

      Hell, human consciousness may well just be complex automation of macro-scale behavior programmed by DNA, so what's your point?

      --
      --- Most topics have many sides worth arguing, allow me to take one opposite you.
    4. Re:Or will it? by ShanghaiBill · · Score: 3, Insightful

      AI will not write books, do programming, etc. Strong AI is a myth.

      Unless human brains have some magical powers (like a soul blessed by God), there is no logical reason that machines shouldn't eventually be smarter than humans. The only question is how far off it is. There has lately been some big progress on deep neural nets. There is also steady progress in symbolic AI and knowledge ontology. My guess is that we will get there in a couple decades, using a hybrid solution.

      AI is just complex automation PROGRAMMED BY HUMANS.

      That doesn't mean that it is limited by human intelligence. Good chess programs can easily beat the programmer that wrote them.

    5. Re:Or will it? by speedplane · · Score: 1

      AI will not write books, do programming, etc. Strong AI is a myth.

      Unless human brains have some magical powers (like a soul blessed by God), there is no logical reason that machines shouldn't eventually be smarter than humans. The only question is how far off it is.

      Not necessarily. It's entirely possible that if we build smarter machines, they will, in turn, make us smarter. If we start implanting computer chips in our brains and nano-electronic optics in our eyes, humans themselves can change and advance, and it's entirely possible that we can "beat" computers indefinitely.

      --
      Fast Federal Court and I.T.C. updates
    6. Re:Or will it? by tehcyder · · Score: 1

      Hell, human consciousness may well just be complex automation of macro-scale behavior programmed by DNA, so what's your point?

      It may be a symphonic poem conducted by the God Pan dreaming, but until you have some evidence for it, it's equally meaningless.

      --
      To have a right to do a thing is not at all the same as to be right in doing it
    7. Re:Or will it? by tehcyder · · Score: 2

      Unless human brains have some magical powers (like a soul blessed by God), there is no logical reason that machines shouldn't eventually be smarter than humans.

      Once you can build a (physical or digital) model that explains why Mozart or Einstein's brains worked as they did compared with the average human being, I'll take comments like this seriously.

      My guess is that we will get there in a couple decades

      Indeed, like controlled nuclear fusion producing unlimited free energy, True AI is always twenty years off.

      --
      To have a right to do a thing is not at all the same as to be right in doing it
    8. Re:Or will it? by Immerman · · Score: 1

      And what evidence would you require? There's a dismayingly large amount of research that suggests that free will may not actually exist.

      --
      --- Most topics have many sides worth arguing, allow me to take one opposite you.
    9. Re:Or will it? by istartedi · · Score: 1

      I think you may have done a better job of elucidating this than I did when I ranted along similar lines on Slashdot.

      We still don't have a name for this Godwin-like law though, which perhaps is most succinctly formulated as "anything that can be inferred will be inferred". I suppose that would simply make it a corollary of Murphy's Law; but I still think it deserves its own law.

      --
      For all intensive purposes, "whom" is no longer a word. That begs the question, "who cares"?
    10. Re:Or will it? by causality · · Score: 1

      Heh I don't know about that, you did a really fine job yourself. My main contribution was the recognition that much of it comes from the personal insecurities of the perpetrators. Your own recognition of the tendency itself was certainly accurate and I found your illustration of it witty and amusing.

      Few people are philosophers (in the sense that Thoreau used the term [see his comment on the news]), so they don't perform regular introspection and they aren't constantly seeking to understand and overcome their weaknesses and character flaws. That causes all sorts of insanity, like making the same mistake over and over again while clinging to a victim mentality that blames anyone or everyone else.

      Otherwise, people would make these false inferences a time or two, receive a rebuff, and say "hmm maybe I should be more careful about making assumptions and putting words in the virtual mouths of others". By asking them to cease, you're actually asking them to sort out all of the personal baggage they would have already faced if they had the courage. Most people/sheeple/whatever you want to call them would rather repeat their insanity.

      --
      It is a miracle that curiosity survives formal education. - Einstein
  3. If this works, everything will change. by billylo · · Score: 1

    Good luck to the Delphi team. Just imagine the possibilities.

    1. Re:If this works, everything will change. by causality · · Score: 2

      Good luck to the Delphi team. Just imagine the possibilities.

      The article briefly mentions that there are humans inside [yes, I read it]. Until then, I was wondering how they planned to handle refueling (and maybe in the future, recharging). When they figure that one out, imagine what this kind of system will do to the trucking industry.

      --
      It is a miracle that curiosity survives formal education. - Einstein
    2. Re:If this works, everything will change. by drinkypoo · · Score: 4, Insightful

      I was wondering how they planned to handle refueling (and maybe in the future, recharging). When they figure that one out, imagine what this kind of system will do to the trucking industry.

      They don't even have to figure that one out. All they have to do is institute full service fueling to replace cardlock fuel stops. The trucks pull in, someone wanders over and fuels them, the trucks pull out again when they detect that the tank has been closed and the attendant has moved away. Extensive monitoring and high-resolution cameras will eliminate the need to have a human on board entirely.

      Presumably, a car with a telepresence robot in it (just enough to communicate with attendants, not to drive the car) could conceivably already cross the country simply by stopping at full-service stations, if not for the legal impediments.

      Besides commuting, OTR trucking really is the "killer app" for self-driving automobiles, and it's coming sooner than people think.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    3. Re:If this works, everything will change. by causality · · Score: 1

      I've never seen a full-service gas station in my state, nor a neighboring state I sometimes visit. I might have a real problem if I had to depend on one for any reason. I've heard that some states have nothing but full-serice stations because of union clout, but I wouldn't want to count on that alone to move entire shipments across the country. Naturally, YMMV.

      Now if I exercise a little benefit of doubt and put a little thought into how your idea might work (see my above post on why stupid insecure people refuse to try this -- it deprives them of their deep-seated need to say "hah you're wrong!"), such systems being commonplace may create more demand for full-service stations. The truck-driving jobs lost might be partly offset by new jobs being created since these stations will need attendants. This is consistent with the overall American trend of replacing solid blue-collar jobs with entry-level service type jobs.

      I wonder how long that hypothetical arrangement could last? Eventually you can expect that someone will create an economical, reliable way to make these cars self-fueling or self-charging.

      --
      It is a miracle that curiosity survives formal education. - Einstein
    4. Re:If this works, everything will change. by Immerman · · Score: 1

      So basically all the fun of a road trip, but nobody gets stuck driving. I'm down.

      --
      --- Most topics have many sides worth arguing, allow me to take one opposite you.
    5. Re:If this works, everything will change. by Anonymous Coward · · Score: 1

      Why should it be required to stop at a refueling station, if there's no meat-bag on board? I would presume automated refueling to be a relatively simple problem solve, in comparison to engineering an autonomous automobile. An autonomous cargo hauler could summon a roving (autonomous) tanker and refuel while in transit, much like in-flight refueling for military aircraft.

    6. Re:If this works, everything will change. by jpapon · · Score: 3, Insightful

      This is consistent with the overall American trend of replacing solid blue-collar jobs with entry-level service type jobs.

      I fail to see how trucker is a "solid blue-collar job" while "gas station refueler" is somehow an "entry-level service type job". They're both pretty typical blue collar jobs.

      I would say adding a full-service attendant at every truck stop gas station is probably the least complicated and easiest-to-implement part of an automated nation-wide self-driving truck shipping system. You're really focusing on the simplest part of the problem.

      --
      -- Let us endeavor so to live that when we pass even the undertaker shall be sorry. -- M. Twain
    7. Re:If this works, everything will change. by burtosis · · Score: 2, Interesting

      Extensive monitoring and high-resolution cameras will eliminate the need to have a human on board entirely.

      Besides commuting, OTR trucking really is the "killer app" for self-driving automobiles, and it's coming sooner than people think.

      HaHaHa. Yes you can watch the semi slam on the brakes for a piece of cardboard that gets blown by the wind and creates a multi car pileup. I'm not sure how that helps.
      I take it you have never worked on any computer vision papers or any teams that have tried vehicle automation? Because even autonomous freeway driving in the USA is far far far off - perhaps 30 years or more. When you see someone with algorithms that can actually do better than the bottom 5-10% of human drivers (under the same apples to apples situation) then we would have something. That something does not exist today.

    8. Re:If this works, everything will change. by YrWrstNtmr · · Score: 1

      On road refueling? Oh please.
      You do realize that in-flight refueling requires multiple human operators.

      1 to fly the tanker
      1 to fly the boom
      1 to fly the A/C being refueled.

      With some tankers, you can combine the first two, but still, multiple humans involved.

    9. Re:If this works, everything will change. by drinkypoo · · Score: 3, Insightful

      HaHaHa. Yes you can watch the semi slam on the brakes for a piece of cardboard that gets blown by the wind and creates a multi car pileup. I'm not sure how that helps.

      Existing automotive driving assistance systems are already immune to this problem. They use radar to tell the difference between a plastic bag or a piece of cardboard, and something with mass.

      Granted, a mylar balloon will probably produce the kind of results you're looking for, but there don't seem to be near as many of those on the highways as pieces of cardboard, so I can see why you didn't go for that example.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    10. Re:If this works, everything will change. by tompaulco · · Score: 2

      This is consistent with the overall American trend of replacing solid blue-collar jobs with entry-level service type jobs. I wonder how long that hypothetical arrangement could last?

      Well eventually, as more and more blue collar jobs are replaced with entry level service jobs, nobody will be able to afford the goods and services produced, so the need for OTR trucking will go away, and the companies that make the products will go away, so the need for IT people like us will go away. Everybody wins!

      --
      If you are not allowed to question your government then the government has answered your question.
    11. Re:If this works, everything will change. by burtosis · · Score: 1

      Not every system uses just radar. Lidar, computer vision, and sonic sensors would all register an object. The way the sensors are fused may in fact register the cardboard as an object. The fact is simple sensor fusion and khalman filtering isn't as simple as implementing a grad school project.

    12. Re:If this works, everything will change. by Anonymous Coward · · Score: 1

      Since the truck is automated, why do we need an attendant at all? We can make a simple fueling interface that is completely new that both the fueling station and the truck have, that is not just completely automated, but provides security and vandal resistance. For example, a hardened steel shutter that won't open on the truck unless the fueling station passes the right authentication handshake... to prevent siphoning, and similar on the station to prevent someone from trying to enter the facility. Done right, it would speed things up by a long shot. Truck stops, fueling arm engages with a high volume pump, when the diesel tanks are full, arm disengages, truck moves on down the road, perhaps 5-10 minutes tops.

    13. Re:If this works, everything will change. by drinkypoo · · Score: 1

      The fact is simple sensor fusion and khalman filtering isn't as simple as implementing a grad school project.

      Oh noes, it's hard.

      But wait, there's a whole lot of money in solving it...

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    14. Re:If this works, everything will change. by Dutch+Gun · · Score: 3, Insightful

      I take it you have never worked on any computer vision papers or any teams that have tried vehicle automation? Because even autonomous freeway driving in the USA is far far far off - perhaps 30 years or more.

      Cars with autonomous freeway driving will be out in just a couple of years, according to automotive manufacturers. Nearly all the major players are predicting fully autonomous cars will be a solved problem sometime between 2020 and 2025.

      Keep in mind that cars can and will make use of a variety of sensors besides vision that are much easier and reliable to process. I'm betting the first generation of automated highway driving uses no vision systems at all... just radar, lidar, and sonar, plus GPS for nativation. More to the point, they can use ALL of them at once. Those are more than enough to handle highway driving. Cars today are already using some of these systems for their intelligent cruise control, auto-parking, and collision avoidance systems.

      Make no mistake... computers are going to be FAR better drivers than humans. No getting drowsy or falling asleep. No distractions by the passengers in the seat next to you or the rugrats in the back. No rear-ending cars while looking at your cellphone or putting on makeup or one of the ten thousand stupid things humans do every day behind the wheel. Fully autonomous cars can't come fast enough, and they'll likely be coming a hell of a lot faster than you think.

      --
      Irony: Agile development has too much intertia to be abandoned now.
    15. Re:If this works, everything will change. by burtosis · · Score: 4, Interesting

      Cars with autonomous freeway driving will be out in just a couple of years, according to automotive manufacturers. Nearly all the major players are predicting fully autonomous cars will be a solved problem sometime between 2020 and 2025.

      Keep in mind that cars can and will make use of a variety of sensors besides vision that are much easier and reliable to process. I'm betting the first generation of automated highway driving uses no vision systems at all... just radar, lidar, and sonar, plus GPS for nativation. More to the point, they can use ALL of them at once. Those are more than enough to handle highway driving. Cars today are already using some of these systems for their intelligent cruise control, auto-parking, and collision avoidance systems.

      Make no mistake... computers are going to be FAR better drivers than humans. No getting drowsy or falling asleep. No distractions by the passengers in the seat next to you or the rugrats in the back. No rear-ending cars while looking at your cellphone or putting on makeup or one of the ten thousand stupid things humans do every day behind the wheel. Fully autonomous cars can't come fast enough, and they'll likely be coming a hell of a lot faster than you think.

      Funny because sensor fusion isn't so simple. It's a big step from auto following a car to actual autonomous driving on freeways in a more reliable way than even the worst human drivers. Comparing the state of the art today to sunny day freely moving traffic human drivers - we are no where near humans. Add heavy rain, dirty sensors, snow, road construction, etc and we will have need for humans to sit and nanny autonomous vehicles from the inside for a long time.
      Furthermore all this "solved problem in 10 years" smacks of the leading computer scientists in the 60s claiming they could beat the best human in 10 years. Then it was another 10. Granted it was only 4 times of saying 10 years so yes eventually. Further still there is the legal ramifications of when the first human fatality due to autonomous driving occurs - common sense and logic will take a back seat to "think of the children" in the USA and we both know it. We are more likely 30 years out than 5-10. However what chaps my hide is people saying this stunt of using a combination of cruise control, lane following, and car distance following is autonomous driving is like saying Siri is strong AI.

    16. Re:If this works, everything will change. by burtosis · · Score: 1

      There sure is. I have no doubt that sometime in the future, barring some kind of planetary catastrophe, it will be solved. The article is just a stunt and nothing more, id be much more impressed by a well cited DARPA urban challenge paper or any serious work than the article. 30-50 years out for true autonomous freeway driving in the USA is my guess - for both the legal and technical challenges.

    17. Re:If this works, everything will change. by vovin · · Score: 1

      OTR trucking pays quite well as an independent you can gross ~400K/year.
      It is skilled .. you need a Class A license and know your trade.

      Gas station attended pays minimum wage, and robots don't tip.

    18. Re:If this works, everything will change. by Anonymous Coward · · Score: 1

      More importantly, no need to worry about breaks and lunches. Also no pesky 12 hour 2nd lunch rule, yada yada.

    19. Re:If this works, everything will change. by Kjella · · Score: 2

      The article briefly mentions that there are humans inside [yes, I read it]. Until then, I was wondering how they planned to handle refueling (and maybe in the future, recharging). When they figure that one out, imagine what this kind of system will do to the trucking industry.

      When they figure what out? All you need is $5 of electronics to open the fuel tank and a robot arm to hit a stationary, active target that can light itself up like a Christmas tree and say here I am. A month sounds like a long time to solve this problem, more the kind you have a prototype made over the weekend. A year max to create an integrated solution of how to find gas stations & gas prices, locate a pump, two way authentication so nobody can pour sugar in the tank, payment and so on. The only reason we don't solve it today is because it's not a problem worth solving. By the time we have actual self-driving cars that can drive with no passengers - which is still many years away - I'm sure we'll have a few self-tanking stations. And if you want the business from robo-cars, the market will take care of the rest.

      --
      Live today, because you never know what tomorrow brings
    20. Re:If this works, everything will change. by burtosis · · Score: 1

      Delphi team.

      I might not know much about the programming, but I know that every source file ends with a full stop.

      end.

      While that is true runtime errors are a bigger pain in the ass.

    21. Re:If this works, everything will change. by Dutch+Gun · · Score: 2

      Have you seen videos of Google's car deftly navigating it's way through city streets, pedestrians, bicycles (even recognizing hand signals), railroads, construction zones, and other such obstacles? They're not claiming it's perfect yet, but I think you're underestimating how close these companies are to a real, working solution.

      As far as legal issues... yeah, there will be lawsuits, but that's nothing new for the automotive industry. Self-driving is such a massively compelling feature, though, that it's absolutely going to happen.

      I guess we'll just have to wait about a decade to see who's right.

      --
      Irony: Agile development has too much intertia to be abandoned now.
    22. Re:If this works, everything will change. by burtosis · · Score: 1

      Yes I have watched them. I also worked in a robotics lab for almost 8 years where tons of computer vision, lidar, radar, sonar, etc were used in various projects. I don't consider myself an expert in autonomous cars but ill wager i know a lot more than most fans of them.
      we can wait and see but I'm only slightly hopeful of autonomous driving being accepted in the US before my license is revoked when I'm too senile to pilot a car manually.

    23. Re:If this works, everything will change. by Bigby · · Score: 1

      I would agree with the prospect of "fully" autonomous driving being too far out to even hope for. However, I think we will have limited-access highway-only autonomy by 2020.

    24. Re:If this works, everything will change. by burtosis · · Score: 1

      I would agree with the prospect of "fully" autonomous driving being too far out to even hope for. However, I think we will have limited-access highway-only autonomy by 2020.

      I would be happy if that happened. However we would already need to have been starting legislation in place years ago, and be installing extra sensors, signs, and lane markers now for things to get done in only 5 years. This is the government lol. I too think limited freeway driving will be first but I'm not hopeful 10 years is enough.

    25. Re: If this works, everything will change. by MMC+Monster · · Score: 1

      Are autonomous vehicles limited by visual spectrum? I was under the impression they used a combination of visual spectrum, active radar, infrared, sonar, and lasers (amongst other, I would guess).

      --
      Help! I'm a slashdot refugee.
    26. Re: If this works, everything will change. by burtosis · · Score: 1

      Are autonomous vehicles limited by visual spectrum? I was under the impression they used a combination of visual spectrum, active radar, infrared, sonar, and lasers (amongst other, I would guess).

      Yes the major players use multiple types of sensors. The data is "fused" from them to create a virtual world representation (essentially) of the real world. You additionally merge error through mathematical techniques like Kalman filtering. However this is not straight forward. When sensors give conflicting results, or sensors become dirty, or faulty it becomes a very very hard problem. The hardest problems are extracting and fusing the data in reliable ways taking sensor problems into account and creating algorithms that can reliably act 'intelligently' using the extracted information. Vision tends to be the most difficult but can use relatively cheap sensors while outputting very rich data. Each type has pluses and minuses. It's likely we will need many more smart algorithms for sensor processing and simeltaneous localization and mapping along with more smart algorithms to get them all working together before its a reality. The google car is great, but just look at all the things it has to deal with in their videos.

    27. Re:If this works, everything will change. by jklovanc · · Score: 1

      I have watched those videos. Remember that they are the highlight reels and not the bloopers.

    28. Re:If this works, everything will change. by sjames · · Score: 1

      I'm guessing he's an MBA.

    29. Re:If this works, everything will change. by JWSmythe · · Score: 1

      The only places I've seen full service gas stations in the last 20 years are Oregon, New Jersey, and somewhere in Ontario.

      --
      Serious? Seriousness is well above my pay grade.
    30. Re:If this works, everything will change. by Euler · · Score: 1

      Wow, you can see the pavement on the highway and it isn't full of craters. The surface streets had a nice grid-like orientation and stoplights in logical places.

      Have you ever been upstate New York in winter, or Boston any time of year?

      Maybe it can be deployed sooner in limited areas that are well-mapped and have predictable road conditions. You will absolutely need to keep daily updates of detours and changes to stoplights, etc.

      I just wonder if any existing automotive companies will want the liability, or if this will create a rift: traditional automobile companies and auto-automobile companies.

    31. Re:If this works, everything will change. by speedplane · · Score: 1

      Cars with autonomous freeway driving will be out in just a couple of years, according to automotive manufacturers. Nearly all the major players are predicting fully autonomous cars will be a solved problem sometime between 2020 and 2025.

      Why is every cool technology always exactly ten years away?

      --
      Fast Federal Court and I.T.C. updates
    32. Re:If this works, everything will change. by cmdr_tofu · · Score: 1

      These guys are way smarter than me. I mean I can write some perl scripts, but I have no idea how to tackle some of the "robot car" challenges.

      For instance when to pull over... let's say there is a billboard with a picture of a police car with sirens flashing. Is that inconceivable? Would the robot car ever advance past it or just pull over? What if there are no safe places to pull over and an emergency vehicle needs to pass. Would the robot car know when it is appropriate to get itself stuck in a ditch (my thinking is that if there are 3 firetrucks and an ambulance trying to get by, driving into a ditch to let them pass is probably a smart move, but for a cop you probably want to continue to drive until there is a safe pull over spot)

      I would love a car that I can sleep or code or read in. I'd prefer a train, but at this point driving takes up too much of my life.

    33. Re:If this works, everything will change. by toddestan · · Score: 1

      Because the stuff we were looking forward to 10-20 years ago is now mundane. Hi-def Flat screen TVs? multi-core CPU? smartphones? LED light bulbs? Meh!

    34. Re:If this works, everything will change. by toddestan · · Score: 1

      Actually, I'm a bit surprised that we don't already have something like this, as there really isn't any reason why such a system couldn't be used by human-operated trucks too.

  4. CMU: Been There, Done That by Anonymous Coward · · Score: 1

    CMU Graduate students achieved this more than a decade ago. Wasn't highly publicized, but their PhD thesis work was autonomous driving and they achieved autonomous highway driving from East Coast to West Coast fully autonomous.

    1. Re: CMU: Been There, Done That by naturaverl · · Score: 1

      Citation please?

    2. Re: CMU: Been There, Done That by discontinuity · · Score: 4, Informative

      I just was going to mention the CMU project and someone beat me to it. They drove nearly autonomously from Pittsburgh to San Diego in 1995. Here are some (old) relevant links:

      The CMU project was not anything that was near consumer-ready and it also was not 100% autonomous. IIRC, humans had to intervene in more complicated driving scenarios and the autonomous system handled the open highway stuff. they report a figure of 96% or so autonomy by miles driven on a shorter trip from Pittsburgh to DC. So it's not like they had everything figured out back in 1995. But still...1995!

    3. Re: CMU: Been There, Done That by burtosis · · Score: 1

      Mod parent up because the tech beng touted as new and groundbreaking is simply 20 years old. Saying its autonomous is like saying Siri is strong AI

  5. Refueling by rossdee · · Score: 1

    A car with nobody in pulls up to a gas station...

    1. Re:Refueling by ArcadeMan · · Score: 1

      ... and then nobody fills it up.

      --
      Get free satoshi (Bitcoin) and Dogecoins
    2. Re:Refueling by sjames · · Score: 1

      A couple hours later an autonomous army vehicle arrives and shoots up the diner until the humans inside get the message and start filling tanks.

  6. Most ambitious by JVolkman · · Score: 1

    "When it’s not on the highway, one of the humans inside will take the wheel." Driving on highways is about as straight forward as driving gets. While neat, this doesn't seem as ambitions as autonomously driving through a city full of obstacles.

    1. Re:Most ambitious by mrvan · · Score: 2

      Highway driving is also the most boring part of driving, and on longer trips often the largest part. City and local driving is kind of fun, you have to pay attention and hopefully you get some nice scenery and usually takes at most 30 minutes. Highways are just boring and can easily take 10+ hours. Fully automated highway driving (even requiring me to stay behind the wheel but letting me read, work or sleep until/unless an alarm goes off) would certainly be a killer feature.

      I guess adaptive cruise control plus lane assist or whatever they call it comes close, so it should be possible to get it on the market soonish?

    2. Re:Most ambitious by Gaygirlie · · Score: 1

      "When it’s not on the highway, one of the humans inside will take the wheel."

      I agree with you. That quote right there pretty much undermines the whole "autonomously" - thing. Not to mention that it'll only be allowed to drive during a sunny day. Much, much less impressive than what the announcement here makes it look like. When the car can actually handle itself all the way from San Fransisco to New Your City (except for re-fueling), in any weather, night or day, including potholes on the road and construction work and whatnot *that's* when I'll be really impressed.

    3. Re:Most ambitious by dugancent · · Score: 1

      City driving sucks. I hate stop-and-go.

      --
      SJWs are the new boogeyman. -Me
    4. Re:Most ambitious by wvmarle · · Score: 1

      This handover from computer to human is what bugs me.

      How to do this reliably?

      Point in case: just yesterday I missed my bus stop on a routine commute, simply because I was too distracted by a stupid phone game. This is comparable to automated drives, as I do a stretch of city transport by hand (home to bus stop), there hop on the bus (human driven but from the passenger pov it could as well be a robot), take back control when I reach the exit point: press the button to get off and do the last bit of transit through city traffic by myself.

      OK you can set an alarm - even for your bus stop there are phone apps that can do that - but what if the human doesn't react and the robot reaches the desired exit, or the end of the highway? No guarantee there is a place to stop (may be occupied by other soundly sleeping drivers).

    5. Re:Most ambitious by sjames · · Score: 1

      First it rattles the windows with an excessively loud radio, then it goes goes into lowrider mode to shake you awake. If that fails, it calls 911 and reports your death.

  7. When it works little to nothing will have changed by burtosis · · Score: 2

    The car has a driver. It's nothing more than a slightly longer pre-mapped pre-planned trip with every last detail painstakingly manually entered. The vehicle cannot handle road construction, traffic problems, snow, simple decisions as to what is safer - like running over a blowing plastic bag or slamming on the brakes.
    I'm all for progress but this is just one more sensational click bait hype article. It's getting almost as bad as solar cell efficiency articles, which if you took them at face value we would be sitting at around one gazillion percent by now.

  8. NOT self driving! by Anonymous Coward · · Score: 1

    TFA says, "When it’s not on the highway, one of the humans inside will take the wheel".

    So it's self driving except for when it's not. Which is another way of saying it isn't a self driving car. It could not drive me from my house down to the local market.

    Also, jeez, how is Delphi "a company many people have never heard of"? It's HUGE. Employs 160,000 people. That's 3X as many as Google employs. Anyone who hasn't heard of Delphi must be living under a rock.

    1. Re:NOT self driving! by Imrik · · Score: 1

      Delphi is huge as a company, but it doesn't have much consumer presence compared to Google and the car manufacturers. Also, being based in the UK it isn't as well known in the US.

  9. Delphi by Warshadow · · Score: 1

    This is a company that used to be a part of GM and when GM spun it off into its own business they used it as a way to jettison all of the most useless members of upper management. These folks ran the company into the ground in a very short amount of time and then went through the longest bankruptcy in US history.

    There have been a number of really cool products that they were developing that they inexplicably shelved, so I won't be surprised at all if they get this working really well and then decide to pack it away and never do anything with it.

  10. To impress me, try cross-city drives instead. by wvmarle · · Score: 5, Insightful

    More impressive would be for the car to drive from one end of New York to the other. During the day, avoiding highways, dealing with really chaotic traffic on narrow, poorly marked roads full of distractions and ambiguities.

    Highways are simple. Traffic flows in one direction only, clearly marked and wide roads, no intersections, all roughly the same speed. No surprises. It's where by far the fewest accidents happen for human driven cars, even though it's boring and probably the part where human drivers pay least attention. Doing an hour of highways, ten hours of highways, 100 hours of highways - it's just more of the same. Now it's cross country, tomorrow it'll be cross country and back. And back again. As long as the fuel will last.

    1. Re:To impress me, try cross-city drives instead. by burtosis · · Score: 2

      Mod parent up. It's simply another slightly longer preplanned pre-mapped mountain of manually entered data test. The technology cant even do as well as a below average human in perfect sunny day few cars on the road freeway traffic. In a city it would rack up fatalities like a mountain dewed up teenager playing gtaV.

    2. Re:To impress me, try cross-city drives instead. by toddestan · · Score: 1

      Yeah, I don't get all the "fully autonomous cars will be here soon" posts. Sure, I can see cars that can handle themselves on the freeway, given clear weather and no construction. We're almost there anyway with the adaptive cruise control and lane keeping systems on cars you can buy today. But we're a long way from cars that can handle construction zones, two lane highways and rural roads, poorly maintained roads, gravel roads, bad weather, and the like. If I was a professional driver I wouldn't be worried quite yet. Once you can give an autonomous vehicle any random destination in the US and it can get there on its own without any human assistance then maybe they should be worried.

    3. Re:To impress me, try cross-city drives instead. by gatfirls · · Score: 1

      The most interesting thing to me will be the ability to handle a traffic jam situation where the car needs to get to an offramp but no one will honor the signal and let them in which is the case in most metro areas. You *have* to be a jerk to get things done sometimes.

  11. If it commits a traffic violation... by Davoid · · Score: 1

    who gets the ticket?

    --
    "Don't sweat the technique."
  12. Sure it's a publicity stunt, but... by berchca · · Score: 1

    Yes, Delphi, an basically unknown in the self-driving world, is trying to make a big splash by doing something that appears monumental while perhaps not actually making much of a leap forward in the technology. But out in most of America, self-driving cars are still pretty controversial. Accomplishments like this, assuming they pull it off, can make huge political advances.

    And I don't know about you, but I'll be mighty frustrated if, when the technology arrives, we're stuck waiting on the legal system.

  13. Car is not self driving. by burtosis · · Score: 3, Informative

    Let's call it for what it is - cruise control plus lane following plus automatic braking to prevent running into vehicles in front of them. It does not turn, it does not make smart safety decisions, it cannot handle simple variations in real conditions. It's as close to being an autonomous car as Siri is to being strong AI.

  14. no it won't. by YesIAmAScript · · Score: 3, Informative

    Delphi already said the car will only self-drive portions of the trip. Long portions of the trip, but only some portions nonetheless.

    "When it’s not on the highway, one of the humans inside will take the wheel."

    --
    http://lkml.org/lkml/2005/8/20/95
    1. Re:no it won't. by jklovanc · · Score: 1

      So this is a long distance test of simple lane following.

    2. Re:no it won't. by RyoShin · · Score: 1

      While it's true that this isn't a test of a fully self-driving car, solid, long distance driving is going to be the "kickstarter" for getting full self-driving automobiles into people's homes. Families are going to love setting out on the highway, setting the car to "maintain", and then everyone (driver included!) can just sleep or play games or whatever. Car alerts when it's running low on gas, there's a potential problem, or you're coming to a more congested area that requires human take-over.

      But then there are semis. Allowing truck drivers to sleep while their semi drives a steady route is going to save serious man hours and real hours (and likely many lives). This will likely come before the minivan does, because there are all sorts of extra pressures put on the trucking industry that are miniscule for consumer driving. You don't want to test this kind of thing with a giant truck, though, which is why it's a car. Test with the car, apply to the truck, prove the usefulness and reliability on the truck, apply to the car.

      As with most things consumer, we're going to see heavy use by businesses before they're common amongst people. City street auto-driving will likely be taken by FedEx or UPS first, moving on to driverless, inner-city taxis, and so forth.

  15. Squeegee Guy by Capt.Albatross · · Score: 3, Funny

    Just for a moment, I wished the the squeegee guys were back. I would like to see an interaction between a squeegee guy and this car at the exit of the Lincoln tunnel.

  16. Cannonball Run by PPH · · Score: 1

    I've seen the movie.

    --
    Have gnu, will travel.
  17. Cops by John+Jorsett · · Score: 5, Interesting

    Something I've lately been wondering: has anyone yet figured out how to get a robot vehicle to recognize when a cop is behind them with flashing lights and to pull over? Or, if an emergency vehicle is approaching with siren blaring, do likewise? Seems like that would be a good way to hijack the load of a robot truck.

    1. Re:Cops by stimpleton · · Score: 1

      Good point.

      Not stopping for a police officer who has spotted your autonomous car, and is confused, resentful, and god-fearin' might get you free air-conditioning via several dozen bullet holes.

      --

      In post Patriot Act America, the library books scan you.
    2. Re:Cops by RyoShin · · Score: 1

      I imagine there will be some sort of two-factor authentication. The car can recognize the lights or, more reliably, a standardized signal from the police vehicle. It begins to pull over and, while it does so, contacts a standard system to verify that the copy signalling is a legitimate one. If not recognized as a police vehicle, or the police car sends a "move past" signal, it would just move over/slow down to allow the emergency vehicle to pass.

      There are layers involved, of course, and wouldn't be fool-proof, but I think this is one of the easier problems to solve with self-driving vehicles.

  18. Re:When it works little to nothing will have chang by romanval · · Score: 2

    Actually, the smarter self driving cars CAN handle various obstacles such as road construction and lane closures. See https://www.youtube.com/watch?...

  19. Re:When it works little to nothing will have chang by burtosis · · Score: 2

    If you are talking about the google car video 2:30 into the video - yes cars can just barely - and unsafely - navigate through construction at like 5mph. Google is NOT claiming they can reliably handle construction. Please point me to a statement otherwise. Furthermore in that same video the car is meandering like a texting schoolgirl in its lane - dosen't inspire confidence in me at all. Get that laser rangefinder on top of the car dirty, such as dust from rain and road spray, then tell me how it works. (Answer is the vehicle wont work in rain).

  20. It can't speed by russotto · · Score: 1

    Ergo, it'll never make it through New Jersey unless it's on manual 90+% of the time.

  21. On the road again by paiute · · Score: 3, Funny

    Will this car pick me up if I put my thumbdrive out?

    --
    If Slashdot were chemistry it would look like this:Cadaverine
  22. Most ambitious? by swillden · · Score: 1

    I'm not dissing what these guys are doing; it's good to demonstrate the increasing capabilities of self-driving cars. But I don't think it's very accurate to call this the "most ambitious" test, because long-distance driving, especially on highways like the US interstate system, is about the easiest form of driving there is to automate. I'm much more impressed with the ability of Google's self-driving cars to negotiate crowded city streets safely.

    --
    Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
  23. Self driving cars will give a new meaning to by Cafe+Alpha · · Score: 1

    "Killer App"

    They'll kill people, animals, cause accidents, destroy property, and with luck, destroy the profits of the companies evil enough to push dumber than ant brains on us as drivers. Also, one can hope, they'll end the careers of every politician who was stupid enough to allow this.

    Get your protest signs ready.

    1. Re:Self driving cars will give a new meaning to by neminem · · Score: 1

      > "They'll kill people, animals, cause accidents, destroy property"
      Yes, they probably will. But the question is, will they kill fewer people and animals, cause fewer accidents, and destroy less property than the absolutely enormous number of people and animals killed, accidents caused, and property destroyed by *humans* driving cars? I expect by the time self-driving cars go mainstream, the answer will be a monumental yes, in which case, that's still a win for humans and the planet.

  24. Way too much hype. by jklovanc · · Score: 1

    This vehicle may drive parts of the way but it will not drive all the way. There will be times when the driver, who has to be there by law, will take over. Autonomous cars have yet to be able to navigate parking lots. There may not even be a string of states where autonomous cars can legally drive?

  25. Delphi - never heard of them?? by tomtermite · · Score: 1

    I guess if you are not 'in the know' about the automobile industry you might have missed, "one of the largest suppliers of audio systems, modules, and components to auto manufacturers and replacement parts to the after market worldwide..." and a driving force behind automated supply chain management.

    --
    - Ubique, Tom Termini www.bluedog.net - WebObjects / J2EE SOA / iPhone solutions for knowledge workers
  26. The downside... by gatfirls · · Score: 1

    I have adaptive cruise control and a lot of other technologies that projects like this use (lane assist, blind spot warning backup camera/radar etc) and I can honestly say it has made me a much worse/lazy driver. I find myself constantly relying on these solely instead of a check on my natural abilities. This is with me consciously knowing relying on them is a really bad thing.

    My anecdote may not apply to all but it certainly concerns me to the point of wanting to not use it. It reminds me of people in Oregon traveling to other states who have no idea how to pump gas because they do it for you by law there.

    They work great though and it would be awesome to actually be able to only rely on them but I worry about the hybrid approach because they are merely driving aids at this point and I can see people using them as pseudo automated cars and the long term negatives outweighing the positives.

  27. Sensors? by gatfirls · · Score: 1

    If they can figure out all of the other objects I would assume sensing white/red/blue flashing lights and pulling over wouldn't be an issue.

    The legal aspect of this is kind of cool when you think about it. If you are being pulled over for a BS reason (lane drift/illegal lane change/following to close/etc) you have a mountain of data to bring to court to refute the claim.