STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation
This addresses the challenge of robotic autonomy in unstructured environments such as wilderness and rubble, though it appears incremental as it builds on existing methods like MPC and CVaR.
The paper tackles the problem of autonomous navigation in extreme, off-road terrains by proposing STEP, a real-time approach for traversability evaluation and planning, validated on wheeled and legged robots in environments like an abandoned subway and underground lava tube.
Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an abandoned subway and an underground lava tube.