Program Summary
The Robotic Autonomy in Complex Environments with Resiliency (RACER) program is focused on developing and demonstrating new autonomy algorithm technologies, rather than vehicle or sensor 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. At a minimum, the program goal is software performance to move off-road at speeds on par with a human driver.
The self-driving car industry has made rapid advances via a vehicle platform-based, agile develop-test-develop-test model that has accumulated data to help train algorithms and refine approaches. Simulation-based development approaches use the same data for algorithm tuning. On-road autonomy algorithms operate in well-structured and highly predictable environments with limited obstacles. However, military off-road autonomy algorithms and capability development has lagged due to the challenging complexity of off-road terrain environments and need to travel in them at relevant speeds.
While RACER seeks to leverage advances in on-road autonomy, the project is investigating innovative approaches that enable revolutionary progress in algorithms operating on systems rather than science or research that primarily results in evolutionary improvements to the existing state of practice.
RACER will demonstrate game-changing autonomous UGV mobility, focused on speed and resiliency, using a combination of simulation and advanced platforms. It tests algorithms in the field at DARPA-hosted experiments across the country on a variety of terrain. 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.