Learning Neural Observer-Predictor Models for Limb-level Sampling-based Locomotion Planning

TL;DR

This paper introduces a neural observer-predictor framework that accurately forecasts limb-level robot motion, enabling safe, collision-aware planning in complex environments for legged robots.

Contribution

The paper presents a novel learning-based observer-predictor with provable stability guarantees, improving motion prediction accuracy for limb-level planning in legged robots.

Findings

Successfully integrated into an MPPI-based planner for a quadruped

Demonstrated effective limb-aware planning in narrow passages

Validated robustness through hardware experiments

Abstract

Accurate full-body motion prediction is essential for the safe, autonomous navigation of legged robots, enabling critical capabilities like limb-level collision checking in cluttered environments. Simplified kinematic models often fail to capture the complex, closed-loop dynamics of the robot and its low-level controller, limiting their predictions to simple planar motion. To address this, we present a learning-based observer-predictor framework that accurately predicts this motion. Our method features a neural observer with provable UUB guarantees that provides a reliable latent state estimate from a history of proprioceptive measurements. This stable estimate initializes a computationally efficient predictor, designed for the rapid, parallel evaluation of thousands of potential trajectories required by modern sampling-based planners. We validated the system by integrating our neural predictor into an MPPI-based planner on a Vision 60 quadruped. Hardware experiments successfully demonstrated effective, limb-aware motion planning in a challenging, narrow passage and over small objects, highlighting our system's ability to provide a robust foundation for high-performance, collision-aware planning on dynamic robotic platforms.