'TartanDrive' Dataset Could Train Self-Driving ATVs
Researchers took an ATV on wild rides to gather data about how it interacts with a challenging off-road environment — 'TartanDrive' could be used to train self-driving ATVs in the future.
"Unlike autonomous street driving, off-road driving is more challenging because you have to understand the dynamics of the terrain in order to drive safely and to drive faster," said Wenshan Wang , a project scientist in the Robotics Institute.
Transcript
00:00:05 researchers from carnegie mellon university took an all-terrain vehicle on wild rides through tall grass loose gravel and mud to gather data about how the atv interacted with a challenging off-road environment they drove the heavily instrumented atv aggressively at speeds up to 30 miles an hour they slid through turns took it up and down hills and even got it stuck in the mud
00:00:27 all while gathering data such as video the speed of each wheel and the amount of suspension shock travel from seven types of sensors the resulting data set called tartan drive includes about two hundred thousand of these real world interactions the researchers believe the data is the largest real-world multi-modal off-road
00:00:49 driving data set both in terms of the number of interactions and types of sensors previous work on off-road driving is often involved annotated maps which provide labels such as mud grass vegetation or water to help the robot understand the terrain but that sort of information isn't often available and even when it is might not be useful
00:01:10 a map area labeled as mud for example may or may not be drivable robots that understand dynamics can reason about the physical world the research team found that the multimodal sensor data they gathered for tartan drive enabled them to build prediction models superior to those developed with simpler non-dynamic data driving aggressively also pushed the atv
00:01:33 into a performance realm where an understanding of dynamics became essential though most work on self-driving vehicles focuses on street driving the first applications likely will be off-road in controlled access areas where the risk of collisions with people and other vehicles is limited the team's tests were performed at a
00:01:52 site near pittsburgh that cmu's national robotics engineering center uses to test autonomous off-road vehicles humans drove the atv though they used a drive-by-wire system to control steering and speed the human driver was forced to go through the same control interface as the robot would in that way the actions the human takes
00:02:12 can be used directly as input for how the robot should act tartan drive will be presented at ikra 2022 and the team's paper has been nominated for icra's outstanding learning paper