People drive vehicles on a very wide variety of roads today. Some roads are well-maintained, well-mapped and are relatively easy for cars to handle. Other roads are literally in a war zone and look the part. But people can drive vehicles on all of them. What will it take to allow a vehicle to do the same on autopilot?
-
Features
What technology will a driverless car need in order to operate on existing roads?
- Thread starter bigfield
- Start date
skepticalbip
Contributor
- Joined
- Apr 21, 2004
- Messages
- 7,304
- Basic Beliefs
- Everything we know is wrong (to some degree)
AI
Shadowy Man
Contributor
I already regularly see Google's driverless cars on the roads around where I work.
bilby
Fair dinkum thinkum
- Joined
- Mar 6, 2007
- Messages
- 33,978
- Gender
- He/Him
- Basic Beliefs
- Strong Atheist
A human driver processes inputs (sight, sound, touch, smell, and taste); processes those inputs, to determine what needs to be done; and then makes the appropriate changes to the controls (steering, brakes, throttle etc.).
A software agent doing the same task has more information, and obtains that information faster than a human driver - it can have visible input from cameras mounted so as to eliminate blind spots, plus it might also have radar, infrared, information from other vehicles nearby, information about the precise torque at each wheel, etc. etc.; It can process that information more rapidly than a human, and without boredom, distraction, or degradation of performance due to drugs, alcohol, or fatigue; and it can exercise more precise control than a human, potentially directly adjusting any aspect of the vehicle and it's engine/motor thousands of times per second to achieve the optimum results.
In principle, a self driving car should be better able to handle poorly maintained roads than a human driver. The problems with current self driving cars is that they are not programmed to be sufficiently gung-ho and stupid to do the things that humans regularly do, that are mostly not fatal by good luck, rather than good judgement.
A human driving on a poorly lit road at night in a downpour will guess that the road he can't see carries on straight (or follows the contours of the land around a curve he also can't see), and might well get it right 99.9 times out of a hundred. A self driving car will calculate the odds of a crash at one in a thousand, declare that an unacceptable risk, and do what a human driver SHOULD have done, which is to not proceed until it can be sure of where the road is. Humans don't like that. They prefer to get there, even if the cost is that once every couple of decades they end up crashing off the road into a ditch.
Google's cars are bad at handling four way stops, not because they don't have the appropriate rules for such junctions, but because nobody else on the road obeys the rules. If four Google cars arrive at such a junction, they all stop, then all move in turn, based on the road rules. But if a human driver is present, he edges forward, trying to bully the other motorists into giving him a right of way he technically doesn't have; the Google car is 100% always intimidated by this (because it is programmed to always give way to any moving vehicle in the junction), so it never gets through until all the human drivers are gone.
Human drivers are arseholes, and try to bully each other. The thing that stops most of them from doing this constantly is that the behaviour is usually ineffective - the driver they are trying to bully often refuses to yield, and it becomes a game of 'chicken'. With the bully in the position where he stands to get a dent AND a ticket, while the guy with right of way only stands to get a dent, the bully is best served by backing down. But when the car is programmed to avoid collisions at all costs, the bully knows that neither dent nor ticket are possible - the software agent will always cave rather than take the slightest risk.
What self driving cars need, if they are to share the road with humans, and not get intimidated, is togrow be programmed with a pair.
The most important optional accessory for a future self driving car will be a robot arm that can, when circumstances dictate, extend from the driver's side window, and give the finger to other motorists.
Self driving cars will be very effective, once the software is able to make the very difficult distinction between being a defensive driver, and being a total pussy.
A software agent doing the same task has more information, and obtains that information faster than a human driver - it can have visible input from cameras mounted so as to eliminate blind spots, plus it might also have radar, infrared, information from other vehicles nearby, information about the precise torque at each wheel, etc. etc.; It can process that information more rapidly than a human, and without boredom, distraction, or degradation of performance due to drugs, alcohol, or fatigue; and it can exercise more precise control than a human, potentially directly adjusting any aspect of the vehicle and it's engine/motor thousands of times per second to achieve the optimum results.
In principle, a self driving car should be better able to handle poorly maintained roads than a human driver. The problems with current self driving cars is that they are not programmed to be sufficiently gung-ho and stupid to do the things that humans regularly do, that are mostly not fatal by good luck, rather than good judgement.
A human driving on a poorly lit road at night in a downpour will guess that the road he can't see carries on straight (or follows the contours of the land around a curve he also can't see), and might well get it right 99.9 times out of a hundred. A self driving car will calculate the odds of a crash at one in a thousand, declare that an unacceptable risk, and do what a human driver SHOULD have done, which is to not proceed until it can be sure of where the road is. Humans don't like that. They prefer to get there, even if the cost is that once every couple of decades they end up crashing off the road into a ditch.
Google's cars are bad at handling four way stops, not because they don't have the appropriate rules for such junctions, but because nobody else on the road obeys the rules. If four Google cars arrive at such a junction, they all stop, then all move in turn, based on the road rules. But if a human driver is present, he edges forward, trying to bully the other motorists into giving him a right of way he technically doesn't have; the Google car is 100% always intimidated by this (because it is programmed to always give way to any moving vehicle in the junction), so it never gets through until all the human drivers are gone.
Human drivers are arseholes, and try to bully each other. The thing that stops most of them from doing this constantly is that the behaviour is usually ineffective - the driver they are trying to bully often refuses to yield, and it becomes a game of 'chicken'. With the bully in the position where he stands to get a dent AND a ticket, while the guy with right of way only stands to get a dent, the bully is best served by backing down. But when the car is programmed to avoid collisions at all costs, the bully knows that neither dent nor ticket are possible - the software agent will always cave rather than take the slightest risk.
What self driving cars need, if they are to share the road with humans, and not get intimidated, is to
The most important optional accessory for a future self driving car will be a robot arm that can, when circumstances dictate, extend from the driver's side window, and give the finger to other motorists.
Self driving cars will be very effective, once the software is able to make the very difficult distinction between being a defensive driver, and being a total pussy.
fromderinside
Mazzie Daius
- Joined
- Oct 6, 2008
- Messages
- 15,945
- Basic Beliefs
- optimist
Its not what self driving cars need. Everything necessary for them is now in place. Its about what human driven cars need to operate in a world with self driving cars. Self driving cars need programs and systems to limit what human driven cars can do when they are on the road in positions where human error can result in a problem. If a human is so silly to drive in a world where self driving cars are common they can expect to be severely limited in what they can do.
Personally I see no reason for any human operated cars when self driving cars are introduced since most cars with humans in them will prefer communicating with humans or other media rather than having to concentrate on road management. In addition, once the technology is permitted most states will require human operated cars to be equipped with self driving technology and human activity limiting technology making self driving roads perfectly safe for everybody.
We have the technology. What we need is the argument for bring self driving into existence. I suggest promoting communication in travel as the advance in technology featured. Safety doesn't sell cars easily. Check how long its been to get to the point where cars are safe enough to require an almost intentional act to get into an accident.
I don't think we need go down the path followed by commercial aircraft where demands for pilots by consumers swamped reason. That was purely political and it set back air transportation, IMHO by about 50 years. sentiments are fine until the get into the way of safety and commerce and technology which is what happened with commercial aircraft.
Take a gander at what we're doing now with drones. That was possible over fifty years ago with analog systems. Now its demonstrably evident that machines with no need to accommodate pilots are much better at commerce and war.
Personally I see no reason for any human operated cars when self driving cars are introduced since most cars with humans in them will prefer communicating with humans or other media rather than having to concentrate on road management. In addition, once the technology is permitted most states will require human operated cars to be equipped with self driving technology and human activity limiting technology making self driving roads perfectly safe for everybody.
We have the technology. What we need is the argument for bring self driving into existence. I suggest promoting communication in travel as the advance in technology featured. Safety doesn't sell cars easily. Check how long its been to get to the point where cars are safe enough to require an almost intentional act to get into an accident.
I don't think we need go down the path followed by commercial aircraft where demands for pilots by consumers swamped reason. That was purely political and it set back air transportation, IMHO by about 50 years. sentiments are fine until the get into the way of safety and commerce and technology which is what happened with commercial aircraft.
Take a gander at what we're doing now with drones. That was possible over fifty years ago with analog systems. Now its demonstrably evident that machines with no need to accommodate pilots are much better at commerce and war.
Last edited:
Malintent
Veteran Member
electricity. definitely will need to use electricity. oh, and the wheel... can't imagine it wouldn't utilize wheel technology. If you want the model that comes with leather seats, then there is a whole world of Tanning technology needed...