Design Con 2015
Breaking News
Comments
kfield
User Rank
Blogger
At the ready
kfield   10/16/2013 10:20:39 AM
NO RATINGS
I think the article nails the problem right on with this quote: "Drivers being asked to take more driver education courses and stay alert all the time behind the wheel inside a self-driving car, in a way, defeats the whole purpose of autonomous cars." My 90-year-old father recently underwent a driving evaluation (at his children's insistence!) and his skills and reaction time dropped significantly when he was talking versus concentrating solely on driving. I can only imagine how difficult it would be to pay strict enough attention when in an autonomous vehicle to be able to react quickly in an emergency.

Caleb Kraft
User Rank
Blogger
Re: At the ready
Caleb Kraft   10/16/2013 11:20:53 AM
NO RATINGS
I don't think the two are parallel. All of that training that they are mentioning is for commercial pilots who are carrying passengers. This would be analgous to a self driving bus, not a car. The testing that a privot pilot goes through, though more rigorous, is analgous to a driver's license.

I don't think we need a commercial pilot's strict training to be handed the reigns of our own personal vehicles.


There is still the issue of slower response time because you aren't already focused on the task of driving, but the same could almost be said for cruise control to a lesser degree.

Rcurl
User Rank
Rookie
Re: At the ready
Rcurl   10/16/2013 12:34:43 PM
NO RATINGS
@Caleb: I know it's a bit off-topic, but your post reminded me of an old saying:

"When it's time for me to go I hope I die in my sleep, like my Grand-Dad, instead of screaming in terror, like his passengers!"

Etmax
User Rank
Rookie
Re: At the ready
Etmax   10/17/2013 4:16:10 AM
NO RATINGS
:-) :-):-):-):-):-):-):-):-):-):-):-):-):-):-)

ScRamjet
User Rank
Freelancer
Re: At the ready
ScRamjet   10/31/2013 3:54:23 PM
NO RATINGS
Caleb;

The problem is not the carrying of passengers, it is the competency of the individual involved.

Think occasional Saturday small plane Pilot VS Capt Sully who made the famous landing in the Hudson River.

There is your comparison. My point is that the drivers on the road today are not ready to suddenly take over an emergency situation. Many of them are barely competent when they started out coming into that situation already in control and aware of the road.

Pilots are well trained and periodically tested. Drivers are not.

Pilots generally will have some time to evaluate the problem before it becomes critical, Since they are flying at controllled spacing of thousands of feet of altitude. Drivers do not have 1) controlled spacing from anything, 2)Periodic Training and retesting.

I will not own a self driving car unless it has a NASCAR rated protection cage in it.

And I'll be uncomfortable even then.

krisi
User Rank
CEO
Re: At the ready
krisi   12/11/2013 5:38:25 PM
NO RATINGS
I agree, driving skills are going downhil...with population aging it will only gets worse...and with cars taking over driving it will get even worse, there will be no way for an average driver to take over in a difficult sitution, such an imaginary individual will do not know what to do

Joe.Sleator
User Rank
Manager
Re: At the ready
Joe.Sleator   12/15/2013 5:52:06 AM
NO RATINGS
I strongly agree with your observations!

A few opinions to add, and why I think those opinions are valid:

- I fly

- I drive cars

- I write firmware, software, and do a bit of hardware as well

- I'm also qualified to drive trains

Given this, especially the trains bit, I do understand fatigue, and how it can degrade one's performance without much warning.

So, here's the scenario:

A person who doesn't realize how tired they are, maybe coming home from a long shift or a party (but without being inebriated) is in their auto-drive vehicle.

They start getting a fairly large number of false-alarms, and are also eager to get home and relax. Hidden in that stack of "annoying distractions" is a REAL situation which will occur at some time during the false alarms.

A person will tend to develop a wrote, nonthinking "muscle-memory" reaction to numerous false-alarms, especially if they are all similar, and occur frequently enough. An untrained person may even become emotionally affected, "annoyed" by their car continually insisting that they back up its logic with human intervention.

For example, in aviation, when there's a stall-warning sound, we quickly look at the ASI and simultaneously relax back-pressure on the stick, or sometimes even add forward pressure. Depending on the aircraft, we might also be vigilant for a wing dropping in either direction.

In aircraft, in a pitot-icing and stall-sensor icing scenario, near VNE, this could be almost instantly fatal. False-alarm stall warnings can also occur in gusty or turbulent conditions. Again, if the speed is already too high, causing the aircraft to speed up in this case could be very bad.

Luckily, the stall-warning doesn't false-alarm very often. But if it does, and the pilot is fatigued and suffering from "get-home-itis" their reactions may be inappropriate.

In a train, the repeated warning (such as slip/slide on a rainy or icy day) might be masking a more insidious problem, like critical loss of braking authority or the inability to climb a hill safely. Malfuntioning safety equipment, which continually warns of minor or nonexistent situations, only contributes to the workload and fatigue factor.

So, I think that a "check-ride" in an automatic driving car, with an experienced co-driver is probably a very good idea, if only to brief the new driver on the kinds of situations that might arise.

I think the scandal of one or two self-drive cars injuring someone due to "operator error" would far outweigh the resistance to updake of the consumer against self-drive cars due to some "mandatory briefing" drive that had to occur to take ownership of the car.

It seems ludicrous that a new and potentially very dangerous large piece of metal, regardless of how smart it is, shouldn't require any additional training at all to operate safely. That could simply be some exercises in "taking over" the controls when the auto-disconnect alarm sounds, in various scenarios.

 

goafrit
User Rank
Manager
Re: At the ready
goafrit   10/18/2013 3:39:07 PM
NO RATINGS
>> "Can you draw a parallel between a pilot flying an airplane on autopilot and a driver in a self-driving car?"

Considering that you can have a maximum of say 8 passengers, I do not see the reason why we need people in these self-driving cars. If the thesis is to drive someone to the mall, when people are seated, why not make one of the people have a driving license. But if the idea is to send the car to pick things in the mall without people in it, then it makes a lot of sense. While you can be in a car and be reading expecting it to drive itself, it does not offer a lot of productivity when compared to airplanes.

goafrit
User Rank
Manager
Re: At the ready
goafrit   10/18/2013 3:42:06 PM
NO RATINGS
>> "Drivers being asked to take more driver education courses and stay alert all the time behind the wheel inside a self-driving car, in a way, defeats the whole purpose of autonomous cars." 

Sure, it is autonomous but you cannot have a nap in the car. You cannot even be distracted. Yet, it is an autonomous self-driving car. The main challenge is that the economics of replacing humans in driving cars is not that huge. You are going to part with four guys. Suddenly, no one needs to drive as the car can drive itself. What have you truly saved economically?

Sanjib.A
User Rank
CEO
Re: At the ready
Sanjib.A   10/22/2013 12:11:03 AM
NO RATINGS
I agree with kfield. The need for a "self-driving car" is to provide comfort as like a Chauffeur Driven car. But if the user needs to be alert to take over the "auto-driver" in a crisis situation, then the entire purpose of providing "comfort" is defeated. I cannot think about such a car being useful on the roads in India, where there could be crisis situations in most of the journey time!! And after all these, if the "auto-driver" system freaks out,...it would be a nightmare. After all, not everyone could afford a "Batman's car". :)

grover_gren
User Rank
Rookie
unmanned vehicle safety
grover_gren   10/16/2013 11:02:53 AM
NO RATINGS
I agree with Karen here: the need for adittional user training kind of defeats the objective.

So logic dictates if you are not relying on the user to handle exceptions then the system must be able to. This gets us into use cases, risk analysis and trying to mitigate exceptional events. As you know there are tons of books and consultany available on this.

But if you can't mitigate the system risks to a low enough level (indeed -  what level!?!), then it's time to look at controlling the environment instead, e.g. barriers, segregation, automatic speed limiters, and all the other possible safety measures that some drivers see as 'infrigement of personal liberty'.

As I have been saying for years, as a practising engineer I would never get a saftey case approved for a system that involves minimally-trained users piloting multiple-ton vehicles along a stretch of tarmac, with closing speeds of 130mph "This new system proposal - you are telling us that there's NO barrier in the centre??! - Are you kidding!!"

So we are stuck with a dangerous, boiled-frog system that some people abuse for thrill-seeking. Until there's a change in user attitude and a system re-design from ground-up, then the introduction of automation will remain an aspiration.         

JCreasey
User Rank
Freelancer
Re: unmanned vehicle safety
JCreasey   10/16/2013 12:00:51 PM
NO RATINGS
The article clearly reveals that the implementers (Google et al) have no clue how to build a large scale viable system at all.

Having millions of independent (autonomous islands) car systems built and tested by various manufacturers is a recipe for disaster IMO. They should be looking more to the "Highway in the Sky" efforts, where a centralized (though distributed) system is responsible for object management. 

If the infrastructure provides all the management (and route planning) then at least we have only one major system to debug, and any modifications and fixes are rolled out universally. Enablement would be incremental based on highway traffic flow and speeds, and the car side implementation becomes much simpler. On local side streets it may even be that simple "follow the buried cable" implementations would be viable to extend the coverage where speeds are low.

Cars would be driven manually until in range of the enabled road sections when a driver could then enlist into the system. If the infrastructure prompts the driver to take manual control again and they cannot; (asleep, drunk, ill, or simply inattentive) then the system moves the car off the highway and parks. This puts the onus on the government I know, but I think that is where the responsibility for control should rest. 

The risks become higher when you mix controlled and manual traffic, so it may be we have to segregate autonomous traffic until every vehicle is capable of being controlled automatically. If speeds and highway density are to go up, then it's certainly time for people to realize that use of the highways is not a personal liberty or right.

Tiger Joe
User Rank
Rookie
Re: unmanned vehicle safety
Tiger Joe   10/18/2013 9:57:55 AM
NO RATINGS
I was with you until your statement

". If the infrastructure prompts the driver to take manual control again and they cannot; (asleep, drunk, ill, or simply inattentive) then the system moves the car off the highway and parks. This puts the onus on the government I know, but I think that is where the responsibility for control should rest."

That sends a strong message.  There's no freaking way I'm going to hand over control of my vehicle to the government.  Can you imagine, some 'incident' gets some bureaucrat to push a button, causing all traffic on the freeway to come to a standstill?  We are stuck in gridlock until the situation is resolved.  Given the two week shutdown we just got out of, I don't trust any quick resolution in the matter.

IMHO, the whole idea of self-driving vehicles is  a 'walk before you run' problem.  If we can't solve the problem to confine use on limited access highways only, forget it.  By 'solve' I mean graduating it to common consumer acceptance.  We would hand control of our car as soon as we get onto the freeway as readily as we do when stepping on a bus, train or plane.  And we would get that control back in our hands, when taking the off-ramp.

And the problem of driving on city streets where reading signs, obstacles in traffic, lights and more, is intractible by comparison.

 

JCreasey
User Rank
Freelancer
Re: unmanned vehicle safety
JCreasey   10/18/2013 10:36:04 AM
NO RATINGS
@Tiger Joe. The government own the roads/freeways today and it's not a huge problem. 

I meant to convey that the government were responsible (since I'd suggest they should own the automation computer control and sensor infrastructure for autonomous driving) for stopping a vehicle before it leaves the controlled road section if a driver does not respond to the prompt to take back manual control. 

It would be interesting to understand what the Google car algorithms would do if it prompted for the driver to take control and he/she did not? Since it does not prompt the driver until after some event that triggered the need to change status, and one assumes that the changeover time would be several seconds at least, then at 60mph it would seem unworkable.

..is the prompt because a sensor failed? ...or is it outside it's range of response capability? ..Would it simply stop? ..or slow down? ..how suddenly? ..would it try to clear the traffic lanes to stop? 

I totally agree with you that implementation should begin with freeways and controlled road sections. This reduces the the problem from it's current "boil the ocean size". If we can't make that work, then we are in trouble.

junko.yoshida
User Rank
Blogger
Re: unmanned vehicle safety
junko.yoshida   10/18/2013 3:04:08 PM
NO RATINGS
@JCreasey, you wrote:

It would be interesting to understand what the Google car algorithms would do if it prompted for the driver to take control and he/she did not?

Exactly. That's the crux of the issue. And that's the question Mr. Safety at Google did not want to give direct answer. His response was, as I wrote in the story, that we simply don't know how drivers react to such situation. Therefore, we don't know how a self-driving car should respond to that. 

Bert22306
User Rank
CEO
Re: unmanned vehicle safety
Bert22306   10/18/2013 5:20:27 PM
NO RATINGS
"It would be interesting to understand what the Google car algorithms would do if it prompted for the driver to take control and he/she did not?"

Don't know about Google, but if I wrote the algorithm, I'd always default to "slow down, move to emergency lane, stop." Whatever situation arises for which the automatic controls can't handle it and the human driver is unavailable. As this is happening, either V2V and/or just the proximity sensors in cars behind it, will slow down traffic.

So, that says that true autonomous driving should only occur on roads that have been set up for such contingencies, e.g. roads which have some shoulder or emergency lane available. (The alternative is that traffic will more often come to a complete standstill, if drivers aren't ready to take over quickly.)

Sensors will also need redundancy. For example, it would be nice for the car to have more than one way of determining where the emergency lane is. If not with an onboard sensor, then with a V2I signal.

I don't really think any of this is terribly futuristic. We have airplanes flying and landing on autopilot, we have trains with no driver, why not cars? For planes and trains, the path they can travel is well determined. So we have to do the same with autonomous cars.

JCreasey
User Rank
Freelancer
Re: unmanned vehicle safety
JCreasey   10/18/2013 7:52:42 PM
NO RATINGS
@Bert. 

"So, that says that true autonomous driving should only occur on roads that have been set up for such contingencies, e.g. roads which have some shoulder or emergency lane available. (The alternative is that traffic will more often come to a complete standstill, if drivers aren't ready to take over quickly.)"

I totally agree with the comment (for automated islands) but would add that you should not mix automated and manual driven vehicles. Imagine an automated car slowing down because of say sensor oe driver failure on a six lane highay with all the traffic doing 60mph. Not pretty.

If you mix manual and automated vehicles, then how do you deal with the manual driver not letting the automated one in (for some unexplained emergency). Is there such a thing as being rude to an automated car?

DrQuine
User Rank
CEO
Re: unmanned vehicle safety
DrQuine   10/20/2013 12:23:58 AM
NO RATINGS
In the slow motion version of the problem (steady traffic flow), if the Google algorithms cannot make sense of the environmental information due to mud, snow, or sensor failure, it has a difficult problem. I think the nearest analogy is what does the human driver do when mud sprays onto the windshield blinding the driver and the windshield wipers cannot clear it. Somehow the human needs to get engaged in the problem solving process while the vehicle slows down and pulls to the side. In the crisis version of the problem (impending collision), the inability of the algorithm to solve the problem before the crash makes it unlikely that a human brought into the problem at the last instant can find a solution.  We're on our way to an accident, the seat belt tensioners are engaged and the air bags are about to blow.

Bert22306
User Rank
CEO
Re: unmanned vehicle safety
Bert22306   10/20/2013 4:54:11 PM
NO RATINGS
I'm with you, DrQuine. I think that the most difficult task will be the vision algorithms, but not that it's an impossible task.

Back when AI was being much ballyhooed, I asked during a meeting at work why anyone thought it was so different. My non-engineer boss said it's like not being able to distinguish between a human or a machine when interfacing with AI.

I said to him, you don't understand. I don't think humans are that smart or unpredictable. Rule-based programming, with lots of nested if statements, and a few coin tosses thrown in there once in awhile, if you really want to emulate humans.

junko.yoshida
User Rank
Blogger
Re: unmanned vehicle safety
junko.yoshida   10/21/2013 11:40:26 PM
NO RATINGS
DrQuine, I agree with you.

What makes us humans believe that we can come up with a solution -- just in the 10-second warning period -- for problems autonomous cars couldn't figure out how to solve. 

But this sill be a nagging issue -- because it directly relates to "who's fault is this" question. Drivers and insurance companies will continue to argue, and I am pretty sure that carmakers don't want to be held responsible.

 

alfybill
User Rank
Rookie
Hundreds have been killed in the airline equivalent
alfybill   10/16/2013 11:52:13 AM
NO RATINGS
Several airline accidents have been caused by this situation.  Their autopilots do their best, with the pilots too often not monitoring the situation on a continuous basis.  When the plane's autopilot says suddenly, 'I'm done, it's all yours!' the result has been deadly.

 

Also, I think the problem for cars is MUCH worse that for airplanes.  The required reaction time are so much shorter.

pseudoid
User Rank
Manager
man Versus Machine, and the winner is...
pseudoid   10/16/2013 12:30:20 PM
NO RATINGS
Some of the latest Porsche 911 versions no longer offer manual transmissions, as Porsche's dual clutch (DPK) automatic transmission is said to be able to perform the task (of shifting gears)  much more efficiently and quicker (>order of magnitude) than a human.  There is a lot to think about within this above sentence alone and not enough space to discuss them all here.  To take the driver out of the 'driving'  equation and turn him/her into just an occupant is a monumental task by itself.  The major 'drivers' behind this effort is many-fold; including the fact that there are over 30,000 motor vehicle-related deaths per year (89/day, but on the decline) in US, alone (http://tinyurl.com/dcy8qb).  Of course, there are other very important reasons for want of human-transport automation, including the environmental effects of traffic jams/accidents and wasted time, as byproducts.

IMHO, there needs to be a separate infrastructure for such 'driverless' vehicles.  Putting such topics to the side, I would like to draw a situation here to ponder: On a 2-lane bridge, there is a school bus full of children in an imminent head-on crash with a [very] intelligent vehicle.  Realizing that a horrific/imminent accident is about to occur, this [very] intelligent vehicle decides to take its lone occupant out of the gene pool by driving itself off the bridge, in order to save the lives of many children.  This is not such a far-fetched situation. 

Now, let us extend this similar scenario a bit further and remove the bus from that same bridge and replace it with a 1968 Camaro SS [my fave].  I am venturing to guess that the driver behind wheel of that antique Chevy continues to drive (and live), while watching the intelligent vehicle (and occupant) do a swan dive off that same bridge.  I want to be that Luddite in the Camaro!

junko.yoshida
User Rank
Blogger
Assumptions made by carmakers
junko.yoshida   10/16/2013 12:13:04 PM
NO RATINGS
I think the first assumption made by carmakers is that the autonomous car will get to the point where the self-driving car needs to handle "exceptions" will be limited.

For many engineers who routinely deal with "exceptions," this is the premise hard to accept.

The second assumption by the automotive industry, however, is a more interesting one. As more and more drivers get used to ADAS (advanced driver assitance systems) in their new cars, they will ebrace a certain level of automation much more readily, and they won't be so averse to the potential riks of autonomous cars.

That is a scenario more likely to pan out, I think.

Wobbly
User Rank
CEO
Re: Assumptions made by carmakers
Wobbly   10/16/2013 12:57:23 PM
NO RATINGS
I agree.

1) drivers that grow up with 'assistive' technology are going to be much more accepting of fully autonomous technology.

2) current drivers are very poor at handling 'exceptions' when they are already clearly at the wheel.

3) technology is quickly advancing to where autonomous cars will experience far fewer 'exceptions' (three or four orders of magnitude) than humans do, in the best of situations, and on far higher orders for drivers that are a) drunk b)tired c)inexperienced d)aged e)distracted f)angry g)stressed ...... [go ahead and add to the list]

Fully autonomus vehicles using existing roadways, no added infrastructure, are a rapidly approaching reality. Consumer acceptance will be an issue initially, but that will wash out over time. Particularly once the insurance costs of fully autonomous vehicles are compared to insurance costs on vehicles with manual controls. You may still want to drive your car, but it is going to hit you severely in your wallet.

Some Guy
User Rank
Manager
I'll take Autonomous over a Texting Teen, or DUI anytime
Some Guy   10/16/2013 1:35:47 PM
We are arguing this from the perspective that human piloted cars are perfect -- they aren't. So the comparison can't be between Autonomous and not Autonomous. The real Risk Assessment has to be Autonomous vs. Human. I'm confident that an Autonomous car isn't going to break into the Ethanol and operate drunk. (Perhaps less confident that it won't become inattentive while texting it's robot friends or corporate mother.)

And its not just Autonomous failures, vs. NO traditional car failures either. I have experienced uncommanded acceleration in a 1970-era, mechanical failure, car, and an uncommanded shift from Drive to 2nd at highway speeds in first generation electronic automatic transmissions. Autonomous vehicles are not different in kind, just in scope. They will have to be designed to be Fault Tolerant and to Fail Safe; we actually already have decades of experience with those designs in automotive as electronics and embedded SW were integrated into the designs.

Finally, with respect to the training, airplane pilots require from 40 to 100's of hours training, vs. 5-40 for cars. Only professional pilots/drivers have continuing training requirements mandated for them. None of us require training to operate an elevator, and in the long-term, Autonomous cars will become for our grandchildren what elevators are for us today. You get in, you push the button, and you eventually arrive at your destination.

Or you don't and it (usually) fails safely and you wait for rescue.

Sheetal.Pandey
User Rank
Manager
Re: I'll take Autonomous over a Texting Teen, or DUI anytime
Sheetal.Pandey   10/16/2013 2:28:26 PM
NO RATINGS
Google car is in th news from quite some time. When are they launching and where.

Sheetal.Pandey
User Rank
Manager
Re: I'll take Autonomous over a Texting Teen, or DUI anytime
Sheetal.Pandey   10/16/2013 2:32:53 PM
NO RATINGS
Google car is in th news from quite some time. When are they launching and where.

junko.yoshida
User Rank
Blogger
Re: I'll take Autonomous over a Texting Teen, or DUI anytime
junko.yoshida   10/17/2013 6:43:50 PM
NO RATINGS
@sheetal, Google has not announced its launch date; let alone where. That said, many leading carmakers have publicly talked about their goals for rolling out their first "autonomous cars" by 2020. While I take it more of their aspirational goal, some told us that self-driving cars become a reality sooner than we think.

daleste
User Rank
CEO
Re: I'll take Autonomous over a Texting Teen, or DUI anytime
daleste   10/17/2013 9:01:22 PM
NO RATINGS
I always thought that a self-driving car would be great.  You can just relax and read the paper on the way to work.  I guess that is not ever going to happen unless you ride the train or bus.  When driving with cruise control, you still have to steer and watch for obstacles.  If the car did those for you, you would stop paying attention.  Reminds me of the story of the Saudi prince that came to Texas and rented an RV.  On the interstate in barren west Texas, he put it on cruise control and went in the back to get a beer.  It rolled 8 times before coming to a stop.

tkl1
User Rank
Rookie
Re: I'll take Autonomous over a Texting Teen, or DUI anytime
tkl1   10/22/2013 8:22:16 PM
NO RATINGS
RV, cruise control, beer, Saudi, Texas:  nope.

http://www.snopes.com/autos/techno/cruise.asp

Susan Rambo
User Rank
Blogger
Why? Because we can
Susan Rambo   10/16/2013 2:20:25 PM
NO RATINGS
Interesting discussion and interesting problem, but I'm thinking better mass transit (in the US at least) may be a more cost-effective and safe solution (if we're trying to reduce crowding on roads and people falling asleep at the wheel). There's that 1/2-true urban legend about the US spending millions of dollars to create a pen that writes in space, when the Soviets just used the pencil. I wonder if auto-driving car is analogous.

Bert22306
User Rank
CEO
Unintended acceleration, anyone?
Bert22306   10/16/2013 4:12:17 PM
Why all the drama about this hypothetical situaion, when we already have seen cases such as unintended acceleration, or failing brakes?

Actually, unintended acceleration of sorts happened to me, many years ago. It was in a car that had a cable-operated hand throttle, which acted on exactly the same throttle lever as the gas pedal. The cable rubbed a little, against the throttle lever, just in front of the firewall. Not having been lubricated, one time it kept the throttle partially open, when I let up on the accelerator.

Big whoop. I pushed down the clutch and shut off the engine, while coasting to the side of the road. Point is, these things have always been a possibility. Let's not get overly dramatic.

Cars have it easier than airplanes. The "fail safe" mode in a car is simply to slow down, move to the road edge or shoulder, and stop. Airplanes should be so lucky.

The other point is, I see no way for truly "autonomous cars" to be able to operate safely WITHOUT the V2I communications. None. So for "driver assisted" cars, the answer is actually very simple. Just like ABS, yaw control, and cruise control, the driver will have to be fully in control.

Caleb Kraft
User Rank
Blogger
Re: Unintended acceleration, anyone?
Caleb Kraft   10/16/2013 4:25:36 PM
absolutely. I've had a throttle stick open on more than one occassion, both due to a stuck cable and a missing throttle spring on my carb!

kfield
User Rank
Blogger
Re: Unintended acceleration, anyone?
kfield   10/16/2013 5:09:47 PM
NO RATINGS
@bert22306  You make some good points here. Runway truck lanes are another example

MeasurementBlues
User Rank
Blogger
Re: Unintended acceleration, anyone?
MeasurementBlues   10/16/2013 5:18:51 PM
NO RATINGS
Google car, Microsoft car: Both bring a whole new meaning to the word "crash."

kfield
User Rank
Blogger
Re: Unintended acceleration, anyone?
kfield   10/16/2013 5:09:59 PM
NO RATINGS
@bert22306  You make some good points here. Runway truck lanes are another example

junko.yoshida
User Rank
Blogger
Re: Unintended acceleration, anyone?
junko.yoshida   10/16/2013 6:23:53 PM
Bert, you may call it over-reaction on the part of consumers, but that anixiety issue is real, and it should not be underestimated. The automotive industry still has a long way to go; it needs to test, validate and prove technology for the very idea of self-driving to be accepted in a society -- in our generation. 

Bert22306
User Rank
CEO
Re: Unintended acceleration, anyone?
Bert22306   10/16/2013 7:02:59 PM
"Bert, you may call it over-reaction on the part of consumers, but that anixiety issue is real, and it should not be underestimated."

I wouldn't say "underestimated," as much as I'd say "misplaced." The anxiety comes from unrealistic expectations of this driver-assisted operation.

As someone else commented, there is no way that a bunch of different driver assist algorithms are going to be capable of supporting truly autonomous driving. I ask again, why do street signs, traffic signals, pavement makings, and all the rest, exist today? Answer: because you can't have a bunch of independent drivers, each with his/her own styles, reflexes, and skill level, drive on the same infrastructures safely WITHOUT our existing "V2I communications."

Replace this diverse groups of drivers with an equally diverse, independently developed, driver-assist algorithms. The situation is no different. Hence, EITHER we develop these V2I comms, OR driver-assisted vehicles will not be fully autonomous, and the driver will have to be engaged in the process all of the time.

Since V2I requires all manner of politician input, I don't see it happening to the extent we need, anytime soon. I realize the automakers like to minimize that, because they need to hype up their products with big promises. What these driver assist systems will do is improve safety, just like ABS and yaw control can do. Put that Google car cold, unplanned, on a twisty mountain road, and see how well it works.

So, I think all this anxiety is misplaced.

BarrySweezey
User Rank
Manager
Re: Unintended acceleration, anyone?
BarrySweezey   10/16/2013 7:24:26 PM
Bert, I hate to rehash, but what is one particular inability that will prevent autonomous cars from driving safely without changing the physical infrastructure?  Not a long list.  Your best example.  And what particular infrastructure change would you recommend for that particular inability?

If any changes to the infrastructure are required, autonomous cars will take a lot longer to be realized and cost a lot more.  So each claim that a particular infrastructure change is required should be extensively examined to see if there's a way around it.

I'm trying to avoid your argument that using street signs is v2i, therefore v2i is required.

 

BarrySweezey
User Rank
Manager
Re: Unintended acceleration, anyone?
BarrySweezey   10/16/2013 7:25:38 PM
NO RATINGS
1 saves
Bert, I hate to rehash, but what is one particular inability that will prevent autonomous cars from driving safely without changing the physical infrastructure?  Not a long list.  Your best example.  And what particular infrastructure change would you recommend for that particular inability?

If any changes to the infrastructure are required, autonomous cars will take a lot longer to be realized and cost a lot more.  So each claim that a particular infrastructure change is required should be extensively examined to see if there's a way around it.

I'm trying to avoid your argument that using street signs is v2i, therefore v2i is required.

 

sprite0022
User Rank
Manager
Re: Unintended acceleration, anyone?
sprite0022   10/16/2013 8:20:46 PM
NO RATINGS
I have a fantastic idea. Google etc should start a F1 style auto-car racing.

put their crap into real test before seducing consumers to buy it.

if google car can handle a 500 mile racing w/o a dent for 10 or 20 games I bet someone will throw their money in it.

sprite0022
User Rank
Manager
Re: Unintended acceleration, anyone?
sprite0022   10/16/2013 8:20:59 PM
NO RATINGS
I have a fantastic idea. Google etc should start a F1 style auto-car racing.

put their crap into real test before seducing consumers to buy it.

if google car can handle a 500 mile racing w/o a dent for 10 or 20 games I bet someone will throw their money in it.

sprite0022
User Rank
Manager
Re: Unintended acceleration, anyone?
sprite0022   10/16/2013 8:21:16 PM
NO RATINGS
I have a fantastic idea. Google etc should start a F1 style auto-car racing.

put their crap into real test before seducing consumers to buy it.

if google car can handle a 500 mile racing w/o a dent for 10 or 20 games I bet someone will throw their money in it.

sprite0022
User Rank
Manager
Re: Unintended acceleration, anyone?
sprite0022   10/16/2013 8:23:23 PM
NO RATINGS
I have a fantastic idea. Google etc should start a F1 style auto-car racing.

put their crap into real test before seducing consumers to buy it.

if google car can handle a 500 mile racing w/o a dent for 10 or 20 games I bet someone will throw their money in it.

Bert22306
User Rank
CEO
Re: Unintended acceleration, anyone?
Bert22306   10/16/2013 8:33:06 PM
NO RATINGS
Hmmm. And how many work zones, potholes, or similar incidentals, would you expect in a Formula 1 race? But yes, that aside, it would make an intereting test. Of course, WITHOUT any V2I enhancements at all.

Bert22306
User Rank
CEO
Re: Unintended acceleration, anyone?
Bert22306   10/16/2013 8:29:53 PM
Barry, why are we rehashing? We already agreed that at a minumum, without making any changes to the existing infrastructure signals/markings etc. you would have to develop sensors in vehicles that can credibly, reliably, accurately READ these existing information systems. Traffic lights, obviously, speed limit signs, lane markings, INLCUDING in non-banal situations, such as work zones, merge signs, traffic reports would be nice, etc. etc. etc. You can't just rely on GPS and Google Maps, is the point. You need low latency, local information too.

I don't understand: "avoid your argument that using street signs is v2i, therefore v2i is required." So instead, what? We should ignore the fact that at very least the EXISTING V2I has to be accommodated, even though it hasn't been accommodated yet? This can't be ignored. Even if the problem can be as simple as enhancing the existing signals, signs, and pavement markings, for easier electronic scanning.

People have a way of wringing their hands when they aren't given to complete story. Until this V2I is fully addressed, I don't see fully autonomous vehicles being possible, and therefore I don't understand the frenzy about things going south. When your cruise control breaks, you simply put your foot on the gas pedal again. Same will happen if your proximity radar breaks. Hopefully, a warning will announce the failure, and the driver will know better than let that system have any driving responsibilities.

BarrySweezey
User Rank
Manager
Re: Unintended acceleration, anyone?
BarrySweezey   10/17/2013 11:52:41 AM
NO RATINGS
We agreed that autonomous cars have to be able to read signs.  That doesn't require a change to the physical infrastructure.  I'm asking you to identify one situation that absolutely does.

Bert22306
User Rank
CEO
Re: Unintended acceleration, anyone?
Bert22306   10/17/2013 3:42:44 PM
I sense we're going around in endless circles. As long as we agreed that the truly autonomous cars have to be able to read signs and road markings, we agree that they need some form of V2I. So: (a) UNTIL you demonstrate that these cars CAN read all the signs, without modification of said signs, and pavement markings also without modification, they aren't ready for prime time. And (b) we can all agree that V2I of one type or another is necessary, regardless of mods needed or not needed.

So, why are we back to questioning the need to V2I? I have no dog in this race, so I have no reason to pretend that an important piece of the puzzle is not necessary.

Another point. Let's say the road is in bad shape, e.g. during a harsh winter. There's no way a radar system will be high res enough to detect these problems. So if some manufacturers decide they will only use radar, as they're certainly permitted to do these days, their solution won't be credible, without some new form of V2I (local road sensors providing RF info to cars about potholes etc.).

KeithSchaub
User Rank
Manager
Re: Unintended acceleration, anyone?
KeithSchaub   10/17/2013 12:56:50 PM
Hi Everyone,

Maybe you don't need exhaustive sensors capable of reading and understanding every traffic sign and nuance. Why do I say this. Imagine your car is connected to internet. Now imagine you want to go from point A to point B. You input this into the car's GPS routing system. The car determines the route and accesses all of the available traffic information from an online traffic database, which has all of the road/traffic/signaling information. Since all other cars are connected, the car knows the traffic conditions, weather conditions, under construction conditions, etc. Of course, there will always be special cases (which is a very real challenge and will need to be addressed), but my point is that the car would have most (90%+) of the information, before it even started the route.

 

 

Bert22306
User Rank
CEO
Re: Unintended acceleration, anyone?
Bert22306   10/17/2013 3:44:15 PM
NO RATINGS
The "online traffic database" is a form of new V2I.

junko.yoshida
User Rank
Blogger
Re: Unintended acceleration, anyone?
junko.yoshida   10/17/2013 6:36:40 PM
NO RATINGS
@keith, you wrote: "Since all other cars are connected..." The problem is it's not a given for the time being. If we want to leverage so-called 'network effect,' we need every car to be connected.

BarrySweezey
User Rank
Manager
Re: Unintended acceleration, anyone?
BarrySweezey   10/18/2013 12:21:55 PM
NO RATINGS
If any car at a certain location is reporting it's speed, that's enough to know how traffic is moving.

MS243
User Rank
Manager
Re: Unintended acceleration, anyone?
MS243   10/18/2013 1:04:55 PM
NO RATINGS
And to the comment  on Just only report the speed -- One can allready get that from doppler from the cell phone towers -- there is no need for any links to the vehicles systems

junko.yoshida
User Rank
Blogger
Re: Unintended acceleration, anyone?
junko.yoshida   10/18/2013 3:24:44 PM
NO RATINGS
I think the point of V2I communication is manifold. Beyond reporting speeds, it should enable hazard warning, accident reporting, approaching emergency vehicle warning and even traffic lights violation warning.

You want V2I to work so that any info picked up by cars on the road will be automatically reported to the infrastructure, and as a result, that information is shared with other cars. 

V2I is there essentially to give you look-ahead info your cars can't see (even if your cars are loaded with sensors. And for this V2I communication to work, you need standardized way of communication -- and ideally, every car on the road has the ability to speak that language.

sprite0022
User Rank
Manager
Re: Unintended acceleration, anyone?
sprite0022   10/16/2013 8:30:51 PM
NO RATINGS
I have a fantastic idea. Google etc should start a F1 style auto-car racing.

put their crap into real test before seducing consumers to buy it.

if google car can handle a 500 mile racing w/o a dent for 10 or 20 games I bet someone will throw their money in it.

jaybus0
User Rank
CEO
Re: Unintended acceleration, anyone?
jaybus0   10/17/2013 8:32:43 AM
NO RATINGS
"The automotive industry still has a long way to go; it needs to test, validate and prove technology for the very idea of self-driving to be accepted in a society -- in our generation."


It will be accepted by few in our generation, mostly only those who are involved in creating it. That is not a huge problem, though. Cars have a long life. If a working system were introduced today, it would still be at least a decade before it was considered the norm. Our refusal will be overruled when a younger, more numerous generation accepts it.

mixed_signal
User Rank
Rookie
Re: Unintended acceleration, anyone?
mixed_signal   10/17/2013 1:53:20 PM
NO RATINGS
How many drivers in the US know that in a car with an automatic transmission you can push forward on the shift lever and it pops the transmission into neutral.  This requires no buttons or anything special, just slam it forward and it takes the engine out of gear.  (This is true of shift levers on the steering column or on the floor.)  That allows the engine to keep running so you have full power to the power steering and brakes, as well.

I doubt many know this, but I'd be curious to see comments.  For example, even as talented an engineer as Bob Pease wrote espousing that one should turn the key/ignition lock (just the right amount, in a panic situation) to shut the engine off but keep the accessories running(!).  Of course, turning it too far toward 'off' would lock the steering column... 

betajet
User Rank
CEO
Re: Unintended acceleration, anyone?
betajet   10/17/2013 3:37:48 PM
NO RATINGS
mixed_signal asked: How many drivers in the US know that in a car with an automatic transmission you can push forward on the shift lever and it pops the transmission into neutral.

The joke answer is "all those drivers who know how to use a manual transmission" and are thus aware of what "neutral" means.  You can also add in "drivers who read the owner's manual" and pick up a couple percent.

Another answer is "all drivers who have used a drive-through car wash", since those establishments require you to put your car into neutral and will show you how if needed.

Wim Ton
User Rank
Rookie
Re: Unintended acceleration, anyone?
Wim Ton   10/28/2013 11:44:43 AM
NO RATINGS
Not that new. In an article in the New Scientist, a lawyer drew a parallel to horse drawn cariages; also a somewhat intelligent autonomous way of transport. An horses can be spooked and accelerate uncontrolled.

KevinCBaxter
User Rank
Manager
Self-driving repercussions
KevinCBaxter   10/16/2013 5:00:35 PM
Self-driving cars are simply the steep portion of a slippery slope, and no one is to blame. I grew up in the era of no seatbelts and my little league team riding to a Dairy Queen after a game in the back of the coach's pickup truck. Fast forward to a few weeks ago when my daughter screamed because I allowed the car to start moving before she had her seatbelt fastened.  

Increasingly insurance companies are giving discounts for allowing the electronic monitoring of our driving habits. And black boxes have now been legislated as required equipment on all new cars.

Once we have a generation of young people who have been brought up in self-driving cars it seems only logical that they will be afraid to drive manually, especially once the cars evolve to truly being safer drivers than people. In 30 or 40 years we will just be like cows, driven around without using our minds or having the nerve to do so.

Wobbly
User Rank
CEO
Re: Self-driving repercussions
Wobbly   10/17/2013 8:59:09 AM
Competitive driving will still exist as a sport. Transportation should never be treated as a sport, but trust me, in urban NJ, it often is. Route 287 during rush hour can be a real white knuckle experience.

Want to drive competitively, go to the track, which I do on occasion. During my youth, I raced short track, motocross, the occasional scrambles, and even tried my hand at road racing. No I consign myself to the occasional go-kart track. Less risk, nearly as much fun.

So for those with the adventurous spirit, there will always be outlets. None of the rest care at all, and why should they? Very few of us grow our own food, churn our own butter, slaughter our own chickens. Does that matter?

KevinCBaxter
User Rank
Manager
Self-driving repercussions
KevinCBaxter   10/16/2013 5:00:44 PM
NO RATINGS
Self-driving cars are simply the steep portion of a slippery slope, and no one is to blame. I grew up in the era of no seatbelts and my little league team riding to a Dairy Queen after a game in the back of the coach's pickup truck. Fast forward to a few weeks ago when my daughter screamed because I allowed the car to start moving before she had her seatbelt fastened.  

Increasingly insurance companies are giving discounts for allowing the electronic monitoring of our driving habits. And black boxes have now been legislated as required equipment on all new cars.

Once we have a generation of young people who have been brought up in self-driving cars it seems only logical that they will be afraid to drive manually, especially once the cars evolve to truly being safer drivers than people. In 30 or 40 years we will just be like cows, driven around without using our minds or having the nerve to do so.

junko.yoshida
User Rank
Blogger
Re: Self-driving repercussions
junko.yoshida   10/16/2013 5:52:50 PM
NO RATINGS
@KevinCBaxter, you wrote:

Once we have a generation of young people who have been brought up in self-driving cars it seems only logical that they will be afraid to drive manually, especially once the cars evolve to truly being safer drivers than people


That's an interesting futuristic notion.

I've also heard people talking about whether driving a self-driving car requires a driver's license. Again, even if that won't become a reality any time soon, it's an interesting notion.

rick merritt
User Rank
Author
Commuter scenario
rick merritt   10/16/2013 5:41:49 PM
NO RATINGS
Yeah, in the user scenarios often discussed at events, people talk about all the work we will get done or relaxation had while commuting...that's just not realistic for a long time I think.

MeasurementBlues
User Rank
Blogger
Re: Commuter scenario
MeasurementBlues   10/16/2013 6:01:54 PM
NO RATINGS
Relaxation while commuting is possible, but only if someone else is driving.

junko.yoshida
User Rank
Blogger
How do you validate autonomous cars?
junko.yoshida   10/16/2013 6:30:19 PM
NO RATINGS
One of the most interesting things -- although it is obvious -- I heard during the session is when the Continental executive touched upon the issue of the approval of a vehicle, as the toughest challenge ahead for autonomous cars.

Indeed. Think about millions of different driving scenarios.

How do you validate that?

JCreasey
User Rank
Freelancer
Re: How do you validate autonomous cars?
JCreasey   10/17/2013 1:07:30 AM
NO RATINGS
As I said earlier, infrastructure based control makes more sense; multiply your test cases for approval by the number of suppliers and 10k's tests rapidly do become millions of tests cases.

We do have the technology today to support drive by wire, and so with infrastructure based controls (V2I) we have the simplest way to automate driving.

Someone said V2I would be more expensive....but I would contend that it would be easier and cheaper to provide highway based sensors than mobile car based sensors...and with a better view of the world.

GordonScott
User Rank
Manager
Crisis? What Crisis?
GordonScott   10/17/2013 3:08:49 AM
NO RATINGS
Personally I'm at least as apprehensive about how, when or if the vehicle would recognise a "crisis beyond it's program".

 

Jerrysc
User Rank
Manager
Driver distraction
Jerrysc   10/17/2013 10:18:27 AM
The more driver aids there are, the more driver distraction will prevail, maybe just falling asleep from boredom. Drivers will be unprepared to take quick action, especially in the event of a crisis situation. Driver aids should only take over in the event of a crisis beyond the ability of the driver to manage. Google car drivers will have to be carefully selected and trained. Perhaps co-drivers will be required for backup.

GordonScott
User Rank
Manager
Re: Driver distraction
GordonScott   10/18/2013 4:57:11 AM
Whilst actually driving, many drivers today seem willing to make telephone calls, send or receive texts, put on make-up and so on.

With self driving cars, they'll be finishing that report, having a meeting over a video link, having breakfast, or maybe a motor-home driver in the toilet.  It'll happen (well, I guess the latter might not if it causes the vehicle to pull off the road because the driver has 'vanished').

junko.yoshida
User Rank
Blogger
Re: Driver distraction
junko.yoshida   10/18/2013 3:27:42 PM
NO RATINGS
ha ha, a vanished driver? That's a good one. Seriously, I saw once a driver eating a bowl of cereal (with milk) in Calif. That was 10 years ago. I did freak out when I saw that. 

MS243
User Rank
Manager
A very real problem with connected cars and vehicles are any wireless links
MS243   10/18/2013 12:03:11 PM
NO RATINGS
Wireless links are an inherent risk presently because virtually all these links use low power processors such as the ARM 7 which lack an MMU  and other security features to make them immune to hacking -- Even if processors use an MMU like the intel i7 series then every bit of code in the wireless link must be written to use the MMU (built into all the applications and the RTOS/OS) -- Hardware based security is even more complex and design intensive to implement, however given the huge numbers of these chips sold each year a secure design would be a winner in the market.

prabhakar_deosthali
User Rank
CEO
re:
prabhakar_deosthali   10/19/2013 2:51:46 AM
NO RATINGS
To say that it is a driverless car and still expect the human driver to be present , and not just be present ,but be alert enough to take over the control of the car in case the system is not able to handle a situation  makes the whole concept meaningless.

 

It is better to have a driver assistance system where the control always lies with the human driver.

cookiejar
User Rank
CEO
autopilot is dfferent for cars
cookiejar   10/19/2013 12:56:00 PM
NO RATINGS
There's a big difference between an autopilot in a plane and in a car.  In the air, when autopilot is used, there are literally miles between aricraft.  And despite all the training, autopilot still guides planes straight into mountainsides. 

In aircraft situations, distance and timing become more critical around airports and landings - comparable to roadways.  In such time distance critical situations, your average pilot would normally have his autopilot off and is unlikely to be distracted reading or texting.  Even with landing automation, the pilot will no doubt have undivided attention.

So it appears nothing can save us from the perils of distracted driving, except less rather than more distractions available in cars.

Bert22306
User Rank
CEO
Re: autopilot is dfferent for cars
Bert22306   10/19/2013 5:38:06 PM
NO RATINGS
To counter that point, there is a way much safer emrgency mode for the driverless car: stop. Airplanes don't have that luxury.

I'm sure that before driverless trains were installed in airports all over the world, there was similar skepticism. And yet, here we are. I'm not sure why engineers would be so skeptical, since one would think that engineers have seen the march of controls automation moving in this direction for decades. Even in cars, for heaven's sake, where the only manual control left to the driver is SOME steering, SOME braking, as sometimes the throttle. (I'm referring to ABS, yaw control, and cruise control as steering, braking, and throttle that has already automated at least parts of these critical functions, always in ways that certainly the average driver can't hope to equal.)

Would an engineer really believe that there's some law of physics or nature or whatever, that absolutely forbids automatic control to get beyond this point? Seems odd, right?

cookiejar
User Rank
CEO
Re: autopilot is dfferent for cars
cookiejar   10/19/2013 6:46:27 PM
NO RATINGS
I grant you that on highways with very controlled access, autopilot in cars might perform nearly as well as an autopilot airport train.  But automatic trains run few and far between and are not of different manufacturer and performance.  Even in a very controlled highway, how would an autopiloted car react to transport trucks' shredded tires, stray moose or even sheets of ice lifting off the roofs of truck trailers and other debris let alone stray pedestrians?

The permutaions on the average road are orders higher than on a protected rail system.

Bert22306
User Rank
CEO
Re: autopilot is dfferent for cars
Bert22306   10/19/2013 7:03:43 PM
NO RATINGS
I would certainly agree that the driverless car will have to depend on more than just radar. The obstacles you mention would mostly be undetectable by radar. That's why I think that truly autonomous mode will require optical sensing, assistance from V2I, and of course algortihms to make sense of the information.

How does one develop autmatic control algorithms? A good starting point is, you ask yourself how you would do this manually, and then you have the algorithm emulate that behavior.

So for example, the shredded truck tire. Optical sensors will notice that. The algorithm then needs to determine whether it can swerve left or right, ar whether it has to slow down drastically (which would be the last choice).

If all cars on this segment of road are being driven autonomously, a suuden swerve will be a whole lot safer than it would be with emotional, mostly untrained humans in the mix.

A well executed V2I system would work even better, noticing the obstacle and signaling to cars upstream to get in another lane.

cookiejar
User Rank
CEO
Re: autopilot is dfferent for cars
cookiejar   10/19/2013 8:13:27 PM
NO RATINGS
Many decisions in everyday driving are tradeoffs.  One wouldn't swerve off the road for a pigeon, but in the case of a similar sized rock would be compelled to swerve or simply duck.  Too many people are killed every year swerving to avoid small animals like birds, dogs, cats, racoons or skunks.  The decision is more difficult as animals get larger - wolves, deer, moose or bears.  And of course the biggest problem of all for auto-piloted cars is pedestrians of all sizes, especially small children. 

I once witnessed a number of cars on a limited access highway spinning out on the road and off the guardrails immediately ahead of me.  Without consciously thinking, in my mind I quickly calculated their paths, down shifted and threaded my way unscathed.  Vehicles following me panic braked and joined the pileup.  While a computer could in theory be programmed to do what I did, it is highly unlikely.  Of course if they were all on autopilot, with ABS and stability control, this type of occurrence would be unlikely.

The problem with a public road system is the large variety of vehicles, unlike a limited access rail system.  The other problem is the time-frame for implementation.  Inevitably, there would be a time of both auto-piloted and human driven vehicles on the road.  At some point, one would only allow auto-piloted vehicles on the faster roadways.  Can you imagine the political infighting for such decisions in light of what just went on?  Is a dictatorship on the horizon?

The U.S. air traffic control automation program is a likely scenario.  Billions have been spent on this comparatively simple system.  Inevitably, as the prototypes were becoming promising, the technology became obsolete, unavailable and unserviceable, so a new development contract was let.  This cycle repeated many times over many decades.

So there's a great deal of politics in implementation at all levels, from designers to legislators.

I would be thrilled to be able to do office work in my auto-piloted car, just a many farmers do today in their auto-piloted tractors.  The question is will I live long enough to see the day?  Hopefully the auto-piloted car will have a better future than the flying cars promised decades ago.

   

 

Robotics Developer
User Rank
Rookie
Re: autopilot is dfferent for cars
Robotics Developer   10/19/2013 9:39:50 PM
NO RATINGS
I am not sure I buy the plane autopilot analogy.  Given the fact that planes are purposefully keep FAR apart while in the air and that cars have a lot more uncertainties than a plane.  Consider the very likely situation of a child stepping out onto a road from behind a car, both to be expected and Unexpected..  Planes have to deal with wind shear but most often they are aware of it via radar, not so little kids..  I would be very leery of any auto-pilot car in a suburban setting..

That said, I am oftentimes worried about the typical drivers today, with cell phones, radios, etc. keeping their attentions while driving.  It would be nice to see some safety systems inplace to help keep us from crashes..

Bert22306
User Rank
CEO
Re: autopilot is dfferent for cars
Bert22306   10/20/2013 4:49:13 PM
NO RATINGS
Planes also land on autpilot. We have Mars rovers that drive autonomously, avoiding obstacles or terrain that's too steep. We have drones that fly themselves and find their way back to base if they lose the remote control signal, and so forth. None of this is outside the realm of doable.

Plus, we have had all manner of computer games that can beat even the most expert of human players, e.g. at complex games like chess.

What makes car driving such an insurmountable feat, given that so many barely proficient humans can more or less master that art?

rick merritt
User Rank
Author
Re: autopilot is dfferent for cars
rick merritt   10/20/2013 8:53:22 PM
NO RATINGS
Wow, 73 comments! This one hit a nerve!

selinz
User Rank
Manager
Re: autopilot is dfferent for cars
selinz   10/20/2013 10:52:11 PM
NO RATINGS
back to the original question, how does it handover control? Simple. As soon as the steering wheel, brake, or gas pedal is touched, it stops controlling. period.

CBDunkerson
User Rank
Rookie
What human?
CBDunkerson   10/21/2013 11:27:28 AM
NO RATINGS
Given that the ultimate goal is to allow these cars to drive themselves without any human occupant at all, the question isn't really how does the car hand over control, but rather how does it handle 'exceptions'.

I'd argue that the vast majority of exceptions would be handled automatically by safety and route finding logic. For example, software directs the car to take a road, but sensors detect an obstruction blocking that road... safety logic would automatically prevent the car from hitting the obstruction and route guidance would then calculate an alternate route.

One area which needs further definition is 'illegal' activity. There are tons of motor vehicle laws on the books which humans violate all the time. For example, if you are on a one way road and there is an obstruction blocking the street (e.g. downed tree limb) a human will illegally back up to the last intersection and go a different way. Autonomous vehicles are going to need rules for when they are allowed to break the law... which will probably mean codifying the exceptions which humans have been using all along. However, this is more of a legal issue than a limitation of autonomous driving technology... they CAN handle these situations once we codify what they are allowed to do.

There isn't really a lot left once safety, route, and legal exceptions have been considered. One possibility might be human interaction... how does the car differentiate between a traffic cop directing it to go (despite the red light) and some random joker doing the same thing? That could be handled by giving cops and construction workers special signalling devices for autonomous cars, but it is an issue that needs to be worked out.

Personally, I suspect that there will be an 'operator' system for the transition from 'driver assist' features currently on the road to 'fully autonomous' vehicles. Just as an operator used to have to manually connect long distance telephone calls you might have autonomous vehicles sending information to a human in a control center who then tells the car what to do.... so the 'operator' would get a video of the cop directing traffic and tell the car when to go. Not driving the car, but just giving it simple instructions (e.g. 'go', 'back up', 'take Halsey street') when it encounters an 'exception' it can't figure out on its own. Again, safety logic is going to keep the car from hitting anything, but it may pull over to the side of the road to wait for instructions if it can't figure out how to get to its destination (e.g. rock slide has blocked the only road going there). Maybe those instructions come from an owner on their cell phone or maybe a professional operator, but they'd only be to prevent autonomous cars from sitting motionless in some safe location... getting to a safe location and stopping would be default behaviour for unknown conditions at all times.

junko.yoshida
User Rank
Blogger
Re: What human?
junko.yoshida   10/21/2013 11:30:16 PM
NO RATINGS
@CBDunkerson, thanks for your detailed response. Fascinating. You have obviously given a lot of thoughts on this.

You wrote:

how does the car differentiate between a traffic cop directing it to go (despite the red light) and some random joker doing the same thing? That could be handled by giving cops and construction workers special signalling devices for autonomous cars, but it is an issue that needs to be worked out.


Yes, that's something I have never heard other people talking about. 

Robotics Developer
User Rank
Rookie
Re: What human?
Robotics Developer   10/28/2013 7:51:50 PM
NO RATINGS
What about the "normal" situation where you are driving on a multi-lane highway and as you start to approach a car on the left (normal passing lane) you notice the driver ahead is looking in your lane (possibly telegraphing an unsignaled lane change) as an experienced driver I look out for that all the time and slow down to avoid getting hit.  Would we expect that kind of insight from an autonomous car or does the whole autonomous car movement require that EVERYONE be in autonomous cars?  I have seen cars swerve at nothing simply because the driver sneezed!  Again, as a long time driver I was able to notice the behavior (driver shaking) and avoid getting hit.  What happens if I get hit into an accident while driving my autonomous car, am I at fault or?

 

I have driven a robot using radio control with a tight user feedback loop(www.usfirst.org) and saw real ugly happen quickly.  At 120lb and traveling 10 to 18feet/sec a failed sensor can cause serious mayhem.  Even with the watchdog monitors and disable/kill switches it takes some time to stop the robot imagine a 1/2 or 3/4 ton car moving at 65mph!  It is mind boggling to think about the possible results.  Even planes use pilots with all their capacity to autopilot there is just no substitute for a pilot.

LoserTriesAgain
User Rank
Rookie
Re: What human?
LoserTriesAgain   10/25/2013 10:40:30 AM
NO RATINGS
I'm missing the point. Why would cars be driving around WITHOUT occupants?

 

CBDunkerson
User Rank
Rookie
Re: What human?
CBDunkerson   10/25/2013 1:40:35 PM
NO RATINGS
Why would cars be driving around without occupants?

To go where future occupants are to pick them up, go park somewhere after dropping occupants off, take itself in for maintenance, drive to a store to have purchases loaded inside... you know, basically most of the things cars do WITH occupants.

MS243
User Rank
Manager
Loss of skill
MS243   10/22/2013 5:49:23 AM
NO RATINGS
A very real issue as well could be the loss of skill on the part of human drivers ----- with all the automation everyone will lose skill at manual driving

AZskibum
User Rank
CEO
Re: Loss of skill
AZskibum   10/29/2013 1:49:18 PM
NO RATINGS
I think that loss of skill on the part of human drivers has already been happening for quite a few years, and will get worse as our cars get smarter. It's a gradual but slippery slope.

kv2x1
User Rank
Rookie
kv2x1's post
kv2x1   1/15/2014 2:03:17 AM
NO RATINGS
Nice post. Thanks for sharing!

 

 

server ftp



Top Comments of the Week
Flash Poll
Like Us on Facebook

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
EE Life
Frankenstein's Fix, Teardowns, Sideshows, Design Contests, Reader Content & More
Carlos Bueno

Adventures in Userland
Carlos Bueno
Post a comment
Editor’s Note: Excerpted from Lauren Ipsum: A story about computer science and other improbable things, author Carlos Bueno introduces us to Lauren and her adventures in ...

Max Maxfield

Tired Old iPad 2 vs. Shiny New iPad Air 2
Max Maxfield
9 comments
I remember when the first iPad came out deep in the mists of time we used to call 2010. Actually, that's only four years ago, but it seems like a lifetime away -- I mean; can you remember ...

Martin Rowe

Make This Engineering Museum a Reality
Martin Rowe
Post a comment
Vincent Valentine is a man on a mission. He wants to make the first house to ever have a telephone into a telephone museum. Without help, it may not happen.

Rich Quinnell

Making the Grade in Industrial Design
Rich Quinnell
16 comments
As every developer knows, there are the paper specifications for a product design, and then there are the real requirements. The paper specs are dry, bland, and rigidly numeric, making ...

Special Video Section
The LT8640 is a 42V, 5A synchronous step-down regulator ...
The LTC2000 high-speed DAC has low noise and excellent ...
How do you protect the load and ensure output continues to ...
General-purpose DACs have applications in instrumentation, ...
Linear Technology demonstrates its latest measurement ...
10:29
Demos from Maxim Integrated at Electronica 2014 show ...
Bosch CEO Stefan Finkbeiner shows off latest combo and ...
STMicroelectronics demoed this simple gesture control ...
Keysight shows you what signals lurk in real-time at 510MHz ...
TE Connectivity's clear-plastic, full-size model car shows ...
Why culture makes Linear Tech a winner.
Recently formed Architects of Modern Power consortium ...
Specially modified Corvette C7 Stingray responds to ex Indy ...
Avago’s ACPL-K30T is the first solid-state driver qualified ...
NXP launches its line of multi-gate, multifunction, ...
Doug Bailey, VP of marketing at Power Integrations, gives a ...
See how to ease software bring-up with DesignWare IP ...
DesignWare IP Prototyping Kits enable fast software ...
This video explores the LT3086, a new member of our LDO+ ...
In today’s modern electronic systems, the need for power ...