Domain-Adaptive Communication-Rate Optimization for Sim-to-Real Humanoid-Robot Wireless XR Teleoperation

TL;DR

This paper introduces a system for optimizing communication rates in wireless XR teleoperation of humanoid robots, balancing energy use and motion accuracy through simulation-based adaptation and theoretical analysis.

Contribution

It develops a novel communication-rate optimization framework with a PAC-Bayes analysis and a PPO-based algorithm for effective sim-to-real transfer in humanoid robot teleoperation.

Findings

Improves the tradeoff between reconstruction error and energy consumption.

Enhances robustness across different wireless channels and motion trajectories.

Provides theoretical insights into sim-to-real adaptation effects.

Abstract

Wireless extended reality (XR) teleoperation provides embodied interaction capability for collecting humanoid robot demonstrations, but the large-scale adoption is restricted by the overhead of high-frequency motion transmission. This paper develops a system framework that integrates sampling, transmission, interpolation, and reconstruction and formulates a communication-rate optimization that aims to minimize the communication energy while maintaining the reconstruction accuracy of robot motion trajectories through dimension-wise sampling-rate control. Since acquiring real-time feedback from physical robots is limited by hardware costs, it is necessary to solve the problem through simulator interaction with offline real-domain data correction. To guide sim-to-real adaptation, we provide a PAC-Bayes generalization characterization that reveals the effects of latent density-ratio estimation, finite-sample deviation, and encoder bias. Building on this analysis, we propose a proximal policy optimization (PPO) method with density-ratio weighting and trust-region regularization. Experiments on public humanoid teleoperation dataset show that the proposed method improves the tradeoff between reconstruction error and communication energy consumption under sim-to-real distribution shift. We further analyze the effectiveness of the proposed algorithm across various wireless channels and dynamic motion trajectories.