Self-Driving Vehicles/Autonomous Vehicle Technology

[Altec]

The most correct answer for this issue is for the car to ensure it's stopping distance is always within sensor range including some margin to the left/right of where the car will be going.

What you're left with is a scenario where a person lands on the roadway from above (jump from cliff with parachute?) immediately infront of the car and the only answer is to stop as rapidly as possible and perhaps automatically alert emergency services there has been an incident (I hate the word accident; there are extremely few accidents).

In reality, the behaviour that will be learned* will be around a deer or moose running out into the road perpendicular to traffic at a full run with poorly visible margins.

* There is less programming of specifics than you might think; it's mostly training by example. A tremendous amount of programming time goes into making learning systems but ultimately the programmer is not making decisions on how the car should drive itself (except for a limit or tweak here and there). This is very different from Automatic Train Control where the details are very specifically coded into the system. Cars deal with too many scenarios.

Stopping distance can change based on many different things.

Moral talk about automated cars is stupid and pointless in most cases.

 

[BMO]

"Grandpa, people actually used to drive cars? Were you guys insane? That sounds super dangerous"

- excerpt from a conversation 50 years from now

Honestly, I remember first getting my license and how scary driving actually was the first time. The reason it doesn't seem amazing is because we're exposed to it so much. But that fact that nearly everywhere on the planet has infrastructure for cars and that we drive them less than 100 years after they were mass produced is insane. All I need is driverless cars and a space colony to be built outside of earth and my sci-fi dreams will have become a reality!

 

[BMO]

http://electrek.co/2015/12/21/tesla...on-full-autonomous-driving-from-3-years-to-2/

Tesla CEO Elon Musk drops his prediction of full autonomous driving from 3 years to just 2

During the same talk, which took place in October, Musk said that fully autonomous cars are about 3 years away, a prediction he made several times in the past year or so. But today we learn that Musk updated his prediction to just 2 years....

 

[Woodbridge_Heights]

Here's some pertinent information, which I posted in another forum.

Useful information about NTHSA self driving capability levels

Level 0 -- Your old manual-shift car

Level 1 -- Your newer car with cruise control.

Level 2 -- That fancy car with automatic lanekeeping and adaptive cruise.

Level 3 -- You can safely text behind the wheel, but must intervene in an alarm.

Level 4 -- It can self-valet empty. It also can drive your kids unaccompanied to hockey practice in the middle of a snowstorm.

Tesla Autopilot is nearly Level 3; although legally it must be treated as Level 2 with full attention mandatory, and working/surfing/texting still not allowed. Eventually we may reach a point where Level 3 self-driving vehicle drivers are legally allowed to do light (interruptible) work like reading, watching movies, texting, etc, but must mandatorily intervene, say, within 10 seconds of an alarm (seatshaker, wheelshaker, klaxon alarm, etc).

_______________

Level 4 self-driving cars is going to be a big, wonderful, beautiful, very fancy Pandora's Box, with both rainbows/unicorns and skull/crossbones beaming out of it simultaneously, both utopia and dystopia. You will yank the giftwrap off the Pandora Box, suddenly causing it to pop Jack-In-A-Box style in a beautifully kablooey pop in a big shower of confetti/glitter -- figuratively speaking.

• Efficiency -- With the prospect of empty vehicles going home to do tasks for kids or spouses, this could be a traffic disaster for freeways. Legislation may be needed if people abuse the privelage of sending empty vehicles dozens of miles.
  
  
• Moral -- Cars that are faced with an unavoidable fatality decision are going to decide whether to save the occupants or pedestrians. Picture the scenario of a baby stroller suddenly running in front of the car at the last second, from behind roadside newspaper boxes (unavoidably unseen by the car's sensors until too late; now a fatality has to happen). Car must instantly decide to crash into baby stroller OR suddenly veer into a parked car/lamppost 1 meter to the side. Legally solve this. Now consider the sole occupant of car is your child being soccermomed unaccompanied to school. Whose life goes? Whose Responsibility? Legislative? Insurance? Etc.
  
  
• Manned/Unmanned interactions Unmanned vehicles interacting with manned vehicles (bicyclists, drivers, buses, ambulances, police cars). How can a police car pull over an empty vehicle for an expired plate? Will governments be comfortable legally allowing empty vehicles? Will police be? Etc.
  
  
• Regulatory -- What you're allowed to do and what you're not allowed to do. People without a driver license stepping into a car? Drunk people stepping into the backseat of an empty self-driving car? How old must be children to go unaccompanied in a driverless car? Mailicious passengers trying to damage a self-driving taxi into causing an accident? Are you allowed to sleep for 8 hours in the bed at the back of a self-driving RV, or truck cab of a self-driving truck? What about self driving public transit (uber scale? carpool scale? minibus scale? large bus scale?) Etc. Etc. Etc.
  
  
• Robustness -- How many redundant sensors and cameras must a self-driving car have (e.g. safely function at damage/loss to 25% of sensors? 50% of sensors? 75% of sensors?), so they don't cause accidents when flying road debris damages a camera. This also affects regulatory and insurance, and creates ideas of futuristic safety testing regimens, to ensure they can survive major damage and still safely recover.
  
  
• Insurance -- What the insurance companies are willing to let you do with a Level 4 driverless car. Including all the above.
  
  
• Safety -- Can a level 4 self-driving car safely drive in the middle of a blinding record rainstorm or major snowstorm blizzard, while carrying children that don't know what to do in an emergency? Even Google Car is currently unable to drive reliably in a rainstorm at this time. Level 4 chauffers (like unmanned Uber) isn't going to be legal until you solve this.
  
  
• Security -- Must be upped massively. Hackers. It's already happened. Hackers remotely kill a jeep causing the car to almost park itself on a freeway! And hackers have already blinded driverless cars. Laser pointer tricks a driverless car.
  
  
• Cost -- The cost of solving all the above, factored into your car's sticker price, your government taxes, and your monthly bills (including insurance). It may be so expensive that most carowners will give up carownership, and just hail a neighbour's empty unused car, coming over to your house Uber-style (as a result, conveniently paying a part of that neighbour's car bill!).

We will see a hell of a lot of Level 3 soon (Tesla Autopilot is already almost Level 3).

We will even see Level 4 in designated areas (e.g. campuses, special lanes, designated roads, etc), maybe not too long after, but would not include the necessary intelligence to self-taxi people yet.

But the full legally allowed Level 4 self-chauffering freedom will build up like the Big One (the earthquake) for a VERY LONG TIME, and then go pop in a spetacular fancy Pandora Box of wonderfulness.

When will full Level 4 freedom occur?

Predictions vary widely, but is completely possible because of difficult thorny steps, it may not be until the very rough neighborhood of 2040s/2050s/2060s/2070s before we finally solve ALL THE ABOVE BULLETS to drive your children in the middle of a snowstorm, for 100% complete freedom on all Canada roads -- i.e. wide-open public roads (rather than private campuses or special lanes) -- and the old manual-drive cars on the roads fall apart and being retired -- before we see GTHA roads full of full Level 4 freedom self-driving cars. It is really a BIG step, because of all the above.

Looking forward to it! Would like to sleep in the back of a car while going to Ottawa at night, whenever the full Toronto-Ottawa highspeed trains are booked solid during holidays.

Re safety: A lot of this might even be resolved through autonomous driving of the vehicle itself. Travelling down a narrow residential street, the self piloting car travels at the speed limit (assuming programming prevents overiding this regulation and permitting speeding above the speed limit), other information may even inform the vehicle to slow down below the speed limit where a human driver might continue to drive at "unsafe" speeds. Some examples might be:
- Weather; raining or snowing causes visibility issues and increases stopping distance. Computer adjusts for this
- Time of day/year; google traffic is already pretty good at gathering traffic data. Push that info to the computer and it adjusts to deal with increased congestion. Even things like early morning, late afternoon on a weekday kids are out going to or coming back from school therefore more pedestrians so slow down. If the vehicle or network (google) detects increased pedestrian traffic at a certain time of day or area it will adjust.
- Vehicles could be outfitted with sensors such as infrared which can detect what a human eye can not
- If new road construction includes wireless beacons to indicate lanes etc the vehicle will be able to operate even in the reduced visibility of inclement weather.

 

[mdrejhon]

http://electrek.co/2015/12/21/tesla...on-full-autonomous-driving-from-3-years-to-2/

Re safety: A lot of this might even be resolved through autonomous driving of the vehicle itself. [...]

The vehicle may even be ready in 3 years to be let run unattended on some roads -- but 100% unfettered freedom of sending a car to self-valet itself Canada-wide, on 100% any Canadian road (residential, school, freeways, downtown, etc) -- 100% Canadawide -- in any Canadian weather that humans would normally dare to drive in -- would probably be another 30+ years -- or possibly beyond (the 2050s-2070s range mentioned).

That is what my post refers to.

Basically the technical/legal/moral/govermental/etc obstacles overcome to sleep in a car, pick up a drunk, or self-valet your kids.

It's going to be a long progression of increasing freedoms for self-driving cars.

 

[TheTigerMaster]

Robot Buses Are Coming To America, To Pave The Way For Driverless Cars

http://www.fastcoexist.com/3052100/...al&utm_source=twitter.com&utm_campaign=buffer

 

[TheTigerMaster]

Smaller, autonomous busses to shuttle people from their points of origin to rapid transit stations is something I've thought has potential. It'd work by having commuters call a bus to their home (similar to Uber), and the commuter boards the bus that'll take them to a rapid transit station. On the way to the station the bus would stop to pick up any other commuters who've hailed a vehicles. This could be especially useful in suburban environments where bus routes may be infrequent and difficult to access.

 

[mdrejhon]

Smaller, autonomous busses to shuttle people from their points of origin to rapid transit stations is something I've thought has potential. It'd work by having commuters call a bus to their home (similar to Uber), and the commuter boards the bus that'll take them to a rapid transit station. On the way to the station the bus would stop to pick up any other commuters who've hailed a vehicles. This could be especially useful in suburban environments where bus routes may be infrequent and difficult to access.

Like GO Transit Dial-A-Bus -- except driverless.

That was a UberPOOL-style service that GO Transit ran during the 1970s.

Today, these kinds of services are being reborn (in many variants) thanks to the efficiencies of smartphone hailing (ala UberPOOL) and GPS efficiencies.

With a sufficiently large carpool fleet in operation, the best-fit carpool (one already headed past your location) would automatically be chosen to bring you to your destination rapid transit connection the fastest.

Operating costs of dynamic-route minibuses (cross between a taxi and a bus). Running in a loose-fitting approximate route, deviating to pick up passengers at their front door. The operating costs would be far lower than running a mostly-empty large infrequent suburban bus.

It would make sense that TTC would already operate such a driverless "shuttle bus taxi" service in low-density suburbs eventually.

 

[mdrejhon]

I would say, perhaps 2066 -- a 50 year timeline -- for driverless public transit to fully replace buses for milk runs on public roads.

But for campuses and more controlled situations, certainly well before then --

It's even happening this decade for driverless campus shuttles, where the audience is predictable (e.g. business people, daytime university students, etc).



A driverless campus shuttle is one thing.
A full-size milk run bus on public roads after midnight in a blizzard is another.

Consider the difficulties of trusting driverless public transit onto a strange milk run of passengers that potentially can attack other passengers, or vandalize the vehicle, or attempt to sabotage it to commit suicide. Liability considerations need to be solved, including video cameras, klaxon alarms, immediate auto-stop and quick-open doors, central monitoring of the fleet (even via virtual reality retina-sharp 360-degree live streaming video) in addition to AI monitoring and computers recognizing threatening situations and pulling over immediately and opening doors, etc.

We already have drivereless trains on fully grade-separated routes -- but driverless wheeled vehicles interacting directly with roads are a totally different ballgame in a totally different galaxy of difficulty.

Long term progression here, I would think.

A theoretical possible driverless public transit progress:

Phase 1 -- campus transit -- this decade
Example: A single university campus or a single business park/campus (e.g. Microsoft). They are already trialling today.

Phase 2 -- Inter-campus transit on public roads -- 2020s
Example: Multiple corporate/university buildings spread throughout a city. Passenger pickup is controllable and safer by virtue of running during business hours in highly vibrant public places. Safety concerns are comparatively lower. Only needs remote video monitoring and immediate auto-stop to let people disembark immediately in any kind emergency.

Phase 3 -- Limited public transit buses on public roads -- 2030s
Example: A fixed bus route running at slow speeds on a public road intermingling with cars and other vehicles. Initially running in safe locales during daytime, during safe weather only, easily is able to stop curbside anywhere during safety concerns, and is able to becomes manned by a human bus driver (in person or even remotely) during inclement weather or technological failures.

Phase 4 -- Carpooled public transit -- 2040s
Example: A driverless "UberPOOL-like" service permitted to drive onto unmaintained/disorganized suburban roads. It needs to be able to recognize street hockey style situations, able to pickup drunks, kids, etc, and recognize bad situations quickly including passengers fighting each other, passengers that are having a heart attack, and without human intervention intelligently automatically call for help for the correct situation (police, vandalism, fire, health emergency, etc) and/or even redirect straight to the hospital, etc.

Phase 5 -- Full sized driverless buses, complete replacement of bus drivers -- 2050s/2060s/2070s
Example: The ability to safely run on all the most-rickety milk runs 24 hours a day, through any part of the city, even in the middle of a blizzard or thunderstorm, and quickly respond to developing situations such as abandoned babies, vandals, drunks, fights, heart attacks, even in a bus cramped full of standees.

It probably will vary from this progress (order may change, innovations such as lanes/roads dedicated to autonomous-vehicle-only, innovations in virtual reality video monitoring, etc) but you get the picture that it will be a very long term progression.

 

[Mercator]

The National with Peter Mansbridge had a great couple of segments tonight. One where they interviewed Keesmat regarding her thoughts on how the city might change with self-driving cars and another segment about Stratford, ON hopes to become a hotbed as a testing ground and insights into what Blackberry/QNX is working on.
http://www.cbc.ca/news/thenational

 

[ehlow]

Smaller, autonomous busses to shuttle people from their points of origin to rapid transit stations is something I've thought has potential. It'd work by having commuters call a bus to their home (similar to Uber), and the commuter boards the bus that'll take them to a rapid transit station. On the way to the station the bus would stop to pick up any other commuters who've hailed a vehicles. This could be especially useful in suburban environments where bus routes may be infrequent and difficult to access.

Uber is trying something very similar to this, pseudo bus public transit lines with hop on hop off.

In terms of automated bus public transit, it would be interesting to see buses grouped together into longer "trains" and maybe splitting off & combining dynamically based on demand, things like that.

 

[Duck]

Morgantown

 

[urbandreamer]

I see driverless vehicles replacing 99% of public transit needs by 2036.

 

[Duck]

What about people who can't afford cars?

I think what you mean is that you see driverless automobiles replacing 99% of fixed-guideway transport by 2036. Automobiles that can drive themselves but can be rented or used like a taxi would still be considered public transport, I think. It's just repurposing the existing roadway infrastructure, shifting away from self-driven personally-owened vehicles to automated technologies with cabins that are shared. It's sort of a merger of the concepts of PRT and conventional fixed-guideway transport.

 

[mdrejhon]

I see driverless vehicles replacing 99% of public transit needs by 2036.

Quantify the 99 percent.

...do you mean a 99 percent drop in transit users?
Nope.

...do you mean filling a 99 percent of Canada landmass with a missing transit need, like the villager or farmer's son who needs a minibus or "Uber-like" transit ride?
perhaps Yes.

I'd adjust the date though, given the hurdles.