Learning Quiet Walking for a Small Home Robot

TL;DR

This paper presents a reinforcement learning approach to enable quadruped robots to walk quietly at home by reducing foot contact velocity, addressing user concerns about noise during robot locomotion.

Contribution

It introduces a sim-to-real RL framework that combines adaptive PD gains, foot contact sensors, and curriculum learning to minimize footstep noise in quadruped robots.

Findings

Learned policies outperform baseline and handcrafted controllers in quietness.

Trade-off identified between robustness and quietness.

Framework successfully reduces foot contact velocity, decreasing noise.

Abstract

As home robotics gains traction, robots are increasingly integrated into households, offering companionship and assistance. Quadruped robots, particularly those resembling dogs, have emerged as popular alternatives for traditional pets. However, user feedback highlights concerns about the noise these robots generate during walking at home, particularly the loud footstep sound. To address this issue, we propose a sim-to-real based reinforcement learning (RL) approach to minimize the foot contact velocity highly related to the footstep sound. Our framework incorporates three key elements: learning varying PD gains to actively dampen and stiffen each joint, utilizing foot contact sensors, and employing curriculum learning to gradually enforce penalties on foot contact velocity. Experiments demonstrate that our learned policy achieves superior quietness compared to a RL baseline and the carefully handcrafted Sony commercial controllers. Furthermore, the trade-off between robustness and quietness is shown. This research contributes to developing quieter and more user-friendly robotic companions in home environments.