Tactile-based Reinforcement Learning for Adaptive Grasping under Observation Uncertainties

TL;DR

This paper introduces a tactile-based reinforcement learning approach using a tactile simulator and PPO to improve robotic grasping robustness under uncertain observations, especially in industrial scenarios with occlusions.

Contribution

It presents a novel tactile simulation environment and a reinforcement learning method that adaptively adjusts grasping strategies under observation uncertainties.

Findings

Enhanced grasping success rate in simulations

Improved stability of robotic grasping under occlusions

Effective adaptation to inaccurate object state estimations

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.