Learning-based Adaptive Control of Quadruped Robots for Active Stabilization on Moving Platforms

TL;DR

This paper introduces LAS-MP, a learning-based control system enabling quadruped robots to actively stabilize on moving platforms by adaptively adjusting posture and estimating states, validated through extensive experiments.

Contribution

The work presents a novel learning-based framework with adaptive policies and state estimators tailored for quadruped robots on dynamic platforms, including systematic training methods.

Findings

Superior balancing performance over baselines

Effective state estimation from proprioceptive data

Robustness across diverse platform motions

Abstract

A quadruped robot faces balancing challenges on a six-degrees-of-freedom moving platform, like subways, buses, airplanes, and yachts, due to independent platform motions and resultant diverse inertia forces on the robot. To alleviate these challenges, we present the Learning-based Active Stabilization on Moving Platforms (\textit{LAS-MP}), featuring a self-balancing policy and system state estimators. The policy adaptively adjusts the robot's posture in response to the platform's motion. The estimators infer robot and platform states based on proprioceptive sensor data. For a systematic training scheme across various platform motions, we introduce platform trajectory generation and scheduling methods. Our evaluation demonstrates superior balancing performance across multiple metrics compared to three baselines. Furthermore, we conduct a detailed analysis of the \textit{LAS-MP}, including ablation studies and evaluation of the estimators, to validate the effectiveness of each component.