Humanoid robots navigate without vision using touch and planning
TAPNAV: Humanoid Navigation through Tactile Active Perception
Robotics
Summary
Humanoid robots normally use cameras to find their way, but in places where vision doesn't work, they get lost quickly. The authors developed a system called TAPNAV that helps robots move toward their goal by feeling their surroundings with touch instead of relying on sight. TAPNAV combines information from the robot's movement sensors and touch to keep track of its position and plans routes and probing moves that reduce uncertainty. The system was tested in simulations and on a real robot, where it outperformed other methods by completing tasks more reliably.
What this means in practice
- •For robotics engineers: Build humanoid robots that navigate in dark or visually occluded areas using tactile sensing instead of cameras.
- •For search and rescue teams: Deploy robots that can explore visually challenging environments by physically probing surfaces to maintain localization and reach goals.
Authors
Huaze Liu, Zhenyu Wu, Jaehwi Jang, Junjie Sheng, Andrew Collins, Aaron Xie, Zhaoyuan Gu, Kaijie Zhu, Ding Jiang, Kevin Cai, Ye Zhao
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.