Unmanned off-road vehicles with increased autonomy the goal of DARPA projectNews
October 08, 2020
ARLINGTON, Va. Improving the algorithms and software that guide self-driving military vehicles is the focus of a new project from the Defense Advanced Research Projects Agency (DARPA); the goal of the research is to build autonomous off-road vehicles that behave like a human driver.
DARPA’s Robotic Autonomy in Complex Environments with Resiliency (RACER) program, which will play out over four years, will develop and field-test new algorithm technologies that maximize the sensor and mechanical limits of unmanned ground vehicles (UGVs).
Although it is true that there are existing vehicle platforms that can handle difficult terrain, their autonomy algorithms and software often cannot process and respond to input data fast enough to both maintain necessary speed and be advantageous to the soldiers on a mission.
“In order to achieve RACER goals of increased speed and resilience, we need to embrace learning approaches that automatically tune system parameters in real time,” said Stuart Young, program manager leading the RACER project. “Successful software will extract features from sensor data and use that information to make on-the-spot driving decisions.”
A forthcoming Broad Agency Announcement (BAA) -- to be posted to beta.SAM.gov -- will include full program details.