VisLab Sponsors Milan-to-Shanghai Driverless Trek 133
incuso writes "VisLab announced the most advanced challenge so far ever organized for autonomous vehicles. Two driverless electric cars will perform a trip from Italy to China to demonstrate the feasibility of autonomous driving in real traffic conditions. Each vehicle will be equipped with five laser scanners, seven cameras, GPS, inertial measurement unit, three Linux PCs, and an x-by-wire driving system. The mission will start on July 10 in Milan, Italy, and will reach Shanghai, China, on October 10 (10/10/10) on a 13,000 km route though Italy, Slovenia, Croatia, Bosnia and Herzegovina, Serbia, Romania, Ukraine, Russia, Kazakhstan, and finally China."
Several key concepts missing from the summary (Score:1, Informative)
These are " non-polluting and no-oil based ... vehicles" created as examples of "sustainable mobility ... central to the [World] Expo"
Autonomous is not really an accurate description: Humans will control the first vehicle. The second will follow the route of the first.
I expect China will disassemble, reverse engineer, and then copy these vehicles en masse. [[//satire]]
Avoiding conflict (Score:2, Informative)
Re:The catch is, (Score:3, Informative)
Visalab is sending along 2 backup cars, 4 maintenance trucks, and 2 media vans with the two auto-vehicles, so they could probably just have someone get out and drive the cars (or just sit at the wheel) in the parts where they'll get in legal trouble for having the cars be autonomous. There are also long stretches (like Russia), where the cars will be the only thing on the road.
Not fully autonomous, human controls the lead car (Score:1, Informative)
The first vehicle will drive autonomously in selected sections of the trip and will conduct experimental tests on sensing, decision, and control subsystems, and will continuously collect data. Although limited, human interventions will be needed to define the route and intervene in critical situations.
The second vehicle will automatically follow the route defined by the preceding vehicle, requiring no human intervention (100% autonomous). This will be regarded as a readily exploitable vehicle, able to move on predefined routes; at the end of the trip, its technology will be transferred to a set of vehicles to move in the inner part of Rome in the close future.
Re:Several key concepts missing from the summary (Score:1, Informative)
If you read well, they say that leader can also be far from the follower. This is totally new and not covered by the DARPA Challenges, in which they participated (they say that their TerraMax vehicle reached the end of the Grand Challenge in 2005)
Re:Several key concepts missing from the summary (Score:4, Informative)
The first vehicle will drive autonomously in selected sections of the trip and will conduct experimental tests on sensing, decision, and control subsystems, and will continuously collect data. Although limited, human interventions will be needed to define the route and intervene in critical situations. The second vehicle will automatically follow the route defined by the preceding vehicle, requiring no human intervention (100% autonomous). This will be regarded as a readily exploitable vehicle, able to move on predefined routes; at the end of the trip, its technology will be transferred to a set of vehicles to move in the inner part of Rome in the close future.
The first vehicle is a bit more than a drone and the second one is a bit more than a mere follower. From what they say, once the trip has been made once, a vehicle could be autonomously doing the road without following anyone. That is an interesting achievment.
Re:What about the fuel? (Score:3, Informative)
FTA:
"Two electric vehicles will perform a 13,000 km trip mainly powered by solar energy, with no driver; two backup vehicles will be part of the trip as well. As a support, 4 Overland trucks will follow the expedition to provide a mechanic shop, storage, and accommodation; "
So they're solar and then they have FOUR trucks following them for support. Fuel shouldn't be a problem.
Why don't we see more of these? I remember watching a show nearly 20 yrs ago about a self-driving car running on a 486 processor. They had video of it driving and everything, looked like it did very well. Now we have quad core processors for less than $200 and we still don't have self driving cars. What happened? I'd imagine as cpus and sensors got cheaper we'd see faster reaction speeds.