Data-Driven Safety Verification for Legged Robots
This addresses safety planning for legged robots, which is critical for real-world deployment but incremental as it builds on existing verification methods.
The paper tackles the challenge of safety verification for legged robots by introducing a probabilistic framework that learns an assessment function from collected trajectories, enabling verification without analytic dynamics models. Results show accurate safety predictions in tasks like quadruped balancing and humanoid reaching, generating robust trajectories and detecting disturbances.
Planning safe motions for legged robots requires sophisticated safety verification tools. However, designing such tools for such complex systems is challenging due to the nonlinear and high-dimensional nature of these systems' dynamics. In this letter, we present a probabilistic verification framework for legged systems, which evaluates the safety of planned trajectories by learning an assessment function from trajectories collected from a closed-loop system. Our approach does not require an analytic expression of the closed-loop dynamics, thus enabling safety verification of systems with complex models and controllers. Our framework consists of an offline stage that initializes a safety assessment function by simulating a nominal model and an online stage that adapts the function to address the sim-to-real gap. The performance of the proposed approach for safety verification is demonstrated using a quadruped balancing task and a humanoid reaching task. The results demonstrate that our framework accurately predicts the systems' safety both at the planning phase to generate robust trajectories and at execution phase to detect unexpected external disturbances.