Skip to content

论文arXiv 2610.1074821 天前

TAPNAV框架实现Unitree G1无视觉触觉主动感知导航 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:TAPNAV: Humanoid Navigation through Tactile Active Perception(arXiv 2610.10748)

核心内容 ​

针对人形机器人在无视觉环境中因本体感受里程计漂移导致定位失效的痛点,研究团队提出TAPNAV触觉主动感知导航框架。该方法不依赖视觉传感器,而是通过主动物理接触环境获取定位线索。系统在仿真及Unitree G1人形机器人真机上完成跨楼层平面与复杂障碍物几何验证,实验数据显示其状态估计误差低于传统基线方法,且在无视觉条件下实现了更高的导航任务完成率,证实了触觉交互作为可靠定位源的有效性。

TAPNAV架构包含位姿置信度维护、双层规划与全身控制三大模块。系统融合里程计、IMU及触觉接触观测构建位姿信念;全局规划器搜索路径时显式约束预测定位不确定性,利用环境结构创造触觉修正机会;局部规划器基于期望信息增益最大化选择探测动作。全身控制器协同解算 locomotion 与末端执行器接触轨迹,确保导航与主动探测动作的同步执行,实现了从感知规划到物理交互的闭环控制。

关键看点 ​

  • 触觉主动感知:摒弃视觉依赖,通过末端执行器主动探测周围结构获取定位线索,解决无视觉环境下本体感受里程计快速漂移问题
  • 双层规划架构:全局规划约束预测定位不确定性以寻找触觉修正点,局部规划基于期望信息增益最大化选择探测动作,实现感知与运动耦合
  • 多源状态估计:融合里程计、IMU与触觉接触观测维持位姿置信度,配合全身控制器协同locomotion与末端接触,保障导航与探测同步执行
  • G1实机验证:在Unitree G1及仿真平台跨场景测试,相比基线方法显著降低状态估计误差并提升任务完成率,验证触觉导航工程可行性

工程与产业观察 ​

TAPNAV为人形机器人在烟雾、黑暗等视觉拒止场景提供了可落地的非视觉导航范式。其核心工程价值在于将触觉从被动避障提升为主动定位源,通过信息增益驱动的物理交互弥补传感器缺失。这对具身智能在极端环境下的鲁棒性设计具有参考意义,也提示硬件研发需重视末端力控精度与触觉反馈带宽对主动感知算法的支撑作用。

英文摘要 (Abstract) ​

Navigation in vision-denied environments is challenging for humanoid robots because proprioceptive odometry drifts and localization uncertainty accumulates rapidly. We present TAPNAV, a tactile active-perception framework that enables humanoid navigation toward a goal by actively probing surrounding structures without relying on vision. TAPNAV maintains a pose belief from odometry, IMU, and tactile contact observations, and couples uncertainty-aware global route planning with information-gain-driven local probing. The global planner searches for routes that keep predicted localization uncertainty bounded by exploiting opportunities for tactile correction, while the local planner selects probe actions that maximize expected information gain. A whole-body controller coordinates the humanoid's locomotion and end-effector contact to execute the planned navigation and probe motions. We evaluate TAPNAV in simulation and on a Unitree G1 across different floor plans and obstacle geometries. TAPNAV achieves lower state estimation error and a higher task completion rate than baselines. These results demonstrate that actively planning physical interactions with the environment can provide localization cues for reliable humanoid navigation without vision.

作者:Huaze Liu, Zhenyu Wu, Jaehwi Jang, Junjie Sheng, Andrew Collins, Aaron Xie, Zhaoyuan Gu, Kaijie Zhu, Ding Jiang, Kevin Cai, Ye Zhao

来源

本页事实对应的公开页面,以原文为准。

  1. arXiv 2610.10748:TAPNAV: Humanoid Navigation through Tactile Active Perception访问 2026-10-12