STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Navigation; Results From the DARPA Subterranean Challenge

Although autonomy has gained widespread usage in structured and controlled environments, robotic autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, rubble, and other postdisaster sites pose unique and challenging problems for autonomous navigation. Based on our participation in the Defense Advanced Research Projects Agency (DARPA) Subterranean Challenge, we propose an approach to improve autonomous traversal of robots in subterranean environments that are perceptually degraded and completely unknown through a traversability and planning framework called stochastic traversability evaluation and planning (STEP). We present 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the conditional value-at-risk (CVaR), 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming (SQP)-based model predictive control (MPC), 4) fast recovery behaviors to account for unexpected scenarios that may cause failure, and 5) risk-based gait adaptation for quadrupedal robots. We illustrate and validate extensive results from our experiments on wheeled and legged robotic platforms in field studies at the Valentine Cave, CA, USA (cave environment), Kentucky Underground (KU), KY, USA (mine environment), and Louisville Mega Cavern, KY, USA (final competition site for the DARPA Subterranean Challenge with tunnel, urban, and cave environments).