arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09628cs.RO
收藏

TeleGate: 通过门控专家选择与运动先验实现全身人形机器人远程操作

TeleGate: Whole-Body Humanoid Teleoperation via Gated Expert Selection with Motion Prior

School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；AnyWit Robotics Co., Ltd., Shushan District, Hefei, Anhui, China（安徽合肥蜀山 district AnyWit 机器人有限公司）

Jie Li, Bing Tang, Feng Wu

备注：
Accepted by RSS 2026. Project page: https://anywitresearch.github.io/TeleGate/
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出TeleGate框架，通过门控网络动态激活专家策略，结合VAE运动先验模块预测未来动作，实现高精度动态动作远程操作。

摘要：

实时全身远程操作是人形机器人在非结构化环境中执行复杂任务的关键方法。然而，开发一个能稳健支持多样化人类动作的统一控制器仍是一个重大挑战。现有方法通常将多个专家策略蒸馏成一个通用策略，这不可避免地导致性能下降，尤其是在高度动态动作上。本文提出了TeleGate，一种统一的全身远程操作框架，能够在各种动作上实现高精度跟踪，同时避免知识蒸馏固有的性能损失。我们的核心思想是通过训练一个轻量级门控网络，保留领域特定专家策略的全部能力，该网络根据本体感觉状态和参考轨迹动态激活专家。此外，为了补偿实时远程操作中未来参考轨迹的缺失，我们引入了一个基于VAE的运动先验模块，从历史观测中提取隐含的未来动作意图，从而为需要预测的动作（如跳跃和站立）提供前瞻性控制。我们在仿真中进行了实证评估，并在Unitree G1人形机器人上部署了我们的技术。仅使用2.5小时的运动捕捉数据进行训练，我们的TeleGate在多样化的动态动作（如跑步、跌倒恢复和跳跃）上实现了高精度的实时远程操作，显著优于基线方法在跟踪精度和成功率方面。

英文摘要：

Real-time whole-body teleoperation is a critical method for humanoid robots to perform complex tasks in unstructured environments. However, developing a unified controller that robustly supports diverse human motions remains a significant challenge. Existing methods typically distill multiple expert policies into a single general policy, which often inevitably leads to performance degradation, particularly on highly dynamic motions. This paper presents TeleGate, a unified whole-body teleoperation framework for humanoid robots that achieves high-precision tracking across various motions while avoiding the performance loss inherent in knowledge distillation. Our key idea is to preserve the full capability of domain-specific expert policies by training a lightweight gating network, which dynamically activates experts in real-time based on proprioceptive states and reference trajectories. Furthermore, to compensate for the absence of future reference trajectories in real-time teleoperation, we introduce a VAE-based motion prior module that extracts implicit future motion intent from historical observations, enabling anticipatory control for motions requiring prediction such as jumping and standing up. We conducted empirical evaluations in simulation and also deployed our technique on the Unitree G1 humanoid robot. Using only 2.5 hours of motion capture data for training, our TeleGate achieves high-precision real-time teleoperation across diverse dynamic motions (e.g., running, fall recovery, and jumping), significantly outperforming the baseline methods in both tracking accuracy and success rate.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑