Data-Driven Safety Verification for Legged Robots

TL;DR

This paper introduces a probabilistic safety verification framework for legged robots that learns from system trajectories, enabling safety assessment without explicit dynamic models, applicable to complex systems during planning and execution.

Contribution

The novel framework allows safety verification of complex legged robots without requiring explicit dynamic equations, using a learning-based assessment function adaptable online.

Findings

Accurately predicts safety during planning and execution phases.

Demonstrates effectiveness on quadruped and humanoid tasks.

Handles sim-to-real gap through online adaptation.

Abstract

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.