Object Pose Estimation through Dexterous Touch
This addresses pose estimation for robotics in visually challenging environments, but appears incremental as it builds on existing tactile and RL methods.
The paper tackles the problem of robust object pose estimation in robotics under limited visual data by using sensorimotor exploration with a robot hand to collect tactile data and iteratively refine shape and pose, showing that it can identify critical pose features without prior geometry knowledge.
Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited and local contact information, making it challenging to reconstruct the pose from partial data. Our approach uses sensorimotor exploration to actively control a robot hand to interact with the object. We train with Reinforcement Learning (RL) to explore and collect tactile data. The collected 3D point clouds are used to iteratively refine the object's shape and pose. In our setup, one hand holds the object steady while the other performs active exploration. We show that our method can actively explore an object's surface to identify critical pose features without prior knowledge of the object's geometry. Supplementary material and more demonstrations will be provided at https://amirshahid.github.io/BimanualTactilePose .