‘They are off the road again’ – Autonomous driving in the open field
Cette publication existe aussi en Français
The team gathered a large dataset on their 5 hour drive with 200.000 interactions
In city-like situations an autonomous drive can be relatively easy: you have the streets and intersections all mapped out. To a large extend you can predict what will happen where. When you take a vehicle off-road everything changes – if you go through a mud pool, you don’t know how deep it is, you don’t know what the terrains conditions are. It is all very dynamic.
A team of Carnegie Mellon University tried it all out for themselves, they drove an vehicle off-road and collected probably one of the largest dynamic dataset for off-road autonomous driving. In total 5 hours of data with 200.000 interactions. The call the set TartanDrive and they probably also had a nice time out in the fields.
They drove the heavily instrumented ATV aggressively at speeds up to 30 miles per hour. They slid through turns, took it up and down hills, and even got it stuck in the mud — 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 dataset, called TartanDrive, includes about 200,000 of these interactions. The five hours of data could be useful for training a self-driving vehicle to navigate off road.
“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 (RI).
Source: https://www.cmu.edu/news
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
