Recent test runs in the Mojave Desert show improvements in speed and autonomy
The Robotic Autonomy in Complex Environments with Resiliency (RACER) program, led by DARPA, recently conducted its third experiment to evaluate the performance of off-road unmanned vehicles. Teams from Carnegie Mellon University, NASA’s Jet Propulsion Laboratory, and the University of Washington participated in the test runs, which took place in the challenging terrain of the Mojave Desert at the U.S. Army’s National Training Center in Ft. Irwin, California.
Autonomous navigation in unpredictable environments
The goal of the RACER program is to demonstrate the autonomous movement of combat-scale vehicles in complex, mission-relevant off-road environments. The program aims to test and develop new autonomy algorithm technologies that enable Unmanned Ground Vehicles (UGVs) to maneuver on unstructured off-road terrain at speeds that are only limited by considerations of sensor performance, mechanical constraints, and safety.
Third experiment highlights improvements in speed and autonomy
During the recent experiment, the RACER teams completed more than 55 driverless runs, covering between roughly 4 and 11 miles each, at speeds of about 25mph. The teams completed 246 miles over 24.6 total hours on course with a robotic fleet of 12 RFVs. The experiment demonstrated significant improvements in off-road speeds while reducing any interaction with the vehicle during test runs.
Overcoming challenging terrain
The terrain at Fort Irwin provided a number of obstacles, such as large and small rocks, bushes, ditches, and trees, which limited vehicle speed and could completely disable it if improperly navigated. The success of the RACER teams depended upon how they perceived the terrain, planned paths, and controlled their robotic vehicles at high average speeds.
Looking ahead to phase 2
The second phase of the RACER program will focus on maturing software stacks and testing autonomy over longer off-road courses with fewer interventions. The participating teams will port implementations of their autonomy solutions onto large-scale demonstration platforms, which will be representative of a combat-scale vehicle. They will also be required to increase speeds to twice that of the first phase performance metrics.
Advancing off-road autonomy for future UGVs
The RACER program seeks to leverage advances in on-road autonomy while investigating innovative approaches that enable revolutionary progress in algorithms operating on systems. The program provides UGV platforms that research teams can use to develop autonomous software capabilities through repeated cycles of tests on unstructured off-road landscapes.
Goals include not only autonomy algorithms, but also creation of simulation-based approaches and environments that will support rapid advancement of self-driving capabilities for future UGVs.
