Tactile-based Reinforcement Learning for Adaptive Grasping under Observation Uncertainties
Xiao Hu, Yang Ye
TL;DR
The paper addresses robust robotic grasping under uncertain object observations typical in construction. It introduces a high-fidelity tactile feedback framework in MuJoCo and trains a PPO-based policy that uses downsampled tactile observations alongside proprioception to adapt grasp pose in real time. By randomizing object positions and shapes during training, the approach generalizes to varied contact scenarios and shapes. Experimental results in simulation show that tactile-driven policies achieve higher grasp stability and success rates than tactile-disabled baselines, demonstrating the practical value of tactile sensing for adaptive manipulation in environments with occlusions and noisy perception.
Abstract
Robotic manipulation in industrial scenarios such as construction commonly faces uncertain observations in which the state of the manipulating object may not be accurately captured due to occlusions and partial observables. For example, object status estimation during pipe assembly, rebar installation, and electrical installation can be impacted by observation errors. Traditional vision-based grasping methods often struggle to ensure robust stability and adaptability. To address this challenge, this paper proposes a tactile simulator that enables a tactile-based adaptive grasping method to enhance grasping robustness. This approach leverages tactile feedback combined with the Proximal Policy Optimization (PPO) reinforcement learning algorithm to dynamically adjust the grasping posture, allowing adaptation to varying grasping conditions under inaccurate object state estimations. Simulation results demonstrate that the proposed method effectively adapts grasping postures, thereby improving the success rate and stability of grasping tasks.