Enhancing Navigation Efficiency of Quadruped Robots via Leveraging Personal Transportation Platforms

TL;DR

This paper introduces RL-ATR, a reinforcement learning approach enabling quadruped robots to ride personal transporters, significantly improving long-range navigation efficiency and reducing energy consumption, validated through comprehensive simulation studies.

Contribution

The paper presents a novel RL-based method for quadruped robots to actively ride transporters, including a policy and state estimators, expanding robot mobility options.

Findings

Proficient command tracking in simulation across various models

Reduced energy consumption compared to legged locomotion

Component ablation studies highlight individual contributions

Abstract

Quadruped robots face limitations in long-range navigation efficiency due to their reliance on legs. To ameliorate the limitations, we introduce a Reinforcement Learning-based Active Transporter Riding method (\textit{RL-ATR}), inspired by humans' utilization of personal transporters, including Segways. The \textit{RL-ATR} features a transporter riding policy and two state estimators. The policy devises adequate maneuvering strategies according to transporter-specific control dynamics, while the estimators resolve sensor ambiguities in non-inertial frames by inferring unobservable robot and transporter states. Comprehensive evaluations in simulation validate proficient command tracking abilities across various transporter-robot models and reduced energy consumption compared to legged locomotion. Moreover, we conduct ablation studies to quantify individual component contributions within the \textit{RL-ATR}. This riding ability could broaden the locomotion modalities of quadruped robots, potentially expanding the operational range and efficiency.