One thing I would love someone to explain is how can people assume cars are going to be automated soon when both planes and trains haven't been automated for various reasons. They are different issues I have gathered but essentially shouldn't trains be dead simple but to this day at least the trains(not metras though) often have someone to stop the train in case of emergencies. Planes are more complex but have lower crash ratings and less obstacles but can't stop and still have 2 plus pilots.
Yup, that air france flight and I would guess many train incidents too.
I'm surprised we do not compare self driving cars to trains more often. Trains are on tracks and still require drivers who have to hold onto deadman switches.
Full automation of cars with no driver are not coming any time soon.
The difference is, they have traffic controllers and the train have their own dedicated rails, almost no obstructions and a train into train crash danger situation rarely arises.
The planes have a lot of maneuvering space to all sides.
Car traffic and streets are more dense and often have humans crossing them without regards to laws, bicycles, motorbikes, road construction and bad weather.
Not saying one auto pilot system is better than the other, however, they operate in different environments.
I've wondered why rail isn't automated. Trains have accidents but they have a (mostly) 1D, simple existence. Cars and trucks are mostly 2D, with many more variables and one-off situations. Fix rail accidents and you get a huge win.
Besides, trains run on tracks, each of which accomodates one train at any given time and rarely intersect; additionally, there's all sorts of signalling and safety infrastructure embedded with the track...
In stark contrast with lane-swerving cars, intersections everywhere, temporary rerouting because of roadworks &c.
Running trains must be orders of magnitude simpler than fully autonomous vehicles.
As for planes, they have a massive benefit in being engineered and maintained for levels of reliability no car can ever hope to achieve, having an awful lot of empty air around them (not to mention being able to move in the Z plane, too, to avoid collisions.
I don't doubt there are many lessons to be learned by designers of autonomous vehicles from work already put down in the fields of trains and planes - however, I'd argue they are very different problems.
Rail systems aren't really comparable because, well, they're on rails. You have five more degrees of freedom when flying an aircraft.
A train driver's main job is to have good reflexes. Aside from opening the doors in case of fire, I can't think of a railway accident that couldn't have been prevented by simply stopping the train(s) in time. A driverless train simply needs an emergency stop button and a way for passengers to get out in an emergency.
Can someone explain why there aren't that many autonomous _trains_? And I don't mean SFO airport train and others like it, but a real, full-size train moving people or goods around the country. Seems like every other year a train flies off the rails due to nothing more than negligence of train's engineer. Why not automate this completely? You don't even have to steer.
Possibly late here, but why aren't more / all trains automated? The route is static; Speed should be easy to determine; AFAIK they aren't mechanically unreliable enough to warrant a full-time mechanic on-board; LIDAR and image recognition can detect hazards on the track.
It seems silly that there have been such strides in automating automobiles before trains.
Wile waking up a sleepy conductor seems like a good idea, how much longer is a train conductor job going to exist? I feel like rail is the the one form of transportation that is most susceptible to automation. Since trains are usually run by slow-moving government agencies, I see how they may have lagged behind the times. Although this is stupidly oversimplified, a train is like an elevator on its side, and we don't have many elevator operators these days.
Railroads are different though. You can always just stop in case of a problem. In an aircraft not so much..
That's why trains have a dead man's switch but planes don't. Though I guess at some point in the future they may. Cirrus already has a system that can be engaged by the passengers in case of a problem with the pilot and that will perform a completely autonomous landing. That's on tiny aircraft though.
Given that trains require far less cognitive load to operate than a tractor trailer (sorry engineers!), and yet still require humans to operate.. I wonder if ever?
I'm actually curious why trains haven't been automated at this point (in the US at least). It seems like an ideal first step (no navigational issues, retrofit some collision avoidance mechanisms, remote control, etc, and you are up and running).
Oh, new trains are full auto, no worries. Retrofitting an entire fleet and tracks, now there's the issue - follow the money, and you'll see why even automatic trains are only programmed to follow the usual route, and for diversions, the driver would need to step in. Plus having a person in the cockpit to push the Big Red Button helps with all sorts of legal issues.
Cars can stop much more easily than trains. Trains can take one or two miles to stop. That's hard to do with LIDAR.
There have been failures of automation. BART was fully automated. Then one train misread a speed command from a trackside gadget, and sped up to over 60 MPH when it was supposed to be slowing down to 20 to prepare to stop at a station. Unfortunately, the station was the end of the line (Fremont), and the train ran off the end into the parking lot.
On the other hand, that was in the 1970s. Some new systems have been fully automated. The Las Vegas Monorail is fully automated. At the end of the line, it asks you to exit, but there's nobody there to make you, so I didn't. Then it runs out on this dead end to switch over to the other line, where it will fall off 20 or 30 feet if it doesn't stop in time. It's a bit scary, but it worked...
There are fairly automated trains but only in very controlled and low-speed environments. (e.g. "people movers" at airports).
But, to the broader point, I can't help but feel that a lot of people are conflating "able to tool down 280 with a human on board who is fully capable of taking over control--albeit not instantaneously" (or a next gen cruise control, if you would) with "a robot chauffeur who can drop the kids off at soccer practice." The second problem--which includes dealing with all the unpredictable things that happen on secondary roads--would seem to be enormously more difficult than the first.
A lot of trains are to various degrees. A lot of passenger services are entirely automatic with a conductor just shutting doors and checking tickets.
Freight trains probably aren't worth automating right now. Trains are huge, only one guy there, probably useful to have him there anyway if there is a mechanical fault (vs blocking the line for hours while the nearest person flys/drives to the train).
reply