Since November 2021, University of Washington researchers from the Paul G. Allen School of Computer Science and Engineering and the Applied Physics Laboratory have been advancing autonomous driving in off-road terrain with novel approaches to perception, planning, and control. UW has been developing this work under DARPA’s Robotic Autonomy in Complex Environments with Resiliency (RACER) program.
Off-road terrain lacks man-made structure and contains challenging features including diverse vegetation, uneven and low-friction surfaces, reduced visibility, obstacles, and rapidly changing terrain surface properties. Mud and other debris often interfere with the sensors. Because of these complications, existing self-driving industry approaches to perception, planning, and control fail when navigating at high-speeds in these conditions.
UW’s approach uses only onboard sensors and compute and does not reference GPS or predefined maps for localization. The team conducts autonomous vehicle testing in a variety of terrain and weather conditions in the State of Washington.
Music: Motorbreath by Metallica
#DARPA #RACER
