Physics-Guided Hierarchical Reward Mechanism for Learning-Based Robotic Grasping

TL;DR

This paper introduces a physics-guided hierarchical reward mechanism for deep reinforcement learning in robotic grasping, significantly enhancing learning efficiency and generalizability in multi-fingered robotic hands.

Contribution

The work proposes a novel physics-informed hierarchical reward system that improves learning speed and generalization in autonomous robotic grasping tasks.

Findings

Outperforms standard deep reinforcement learning methods in grasping tasks

Enhances learning efficiency through physics-guided metrics

Improves generalizability across different objects

Abstract

Learning-based grasping can afford real-time grasp motion planning of multi-fingered robotics hands thanks to its high computational efficiency. However, learning-based methods are required to explore large search spaces during the learning process. The search space causes low learning efficiency, which has been the main barrier to its practical adoption. In addition, the trained policy lacks a generalizable outcome unless objects are identical to the trained objects. In this work, we develop a novel Physics-Guided Deep Reinforcement Learning with a Hierarchical Reward Mechanism to improve learning efficiency and generalizability for learning-based autonomous grasping. Unlike conventional observation-based grasp learning, physics-informed metrics are utilized to convey correlations between features associated with hand structures and objects to improve learning efficiency and outcomes. Further, the hierarchical reward mechanism enables the robot to learn prioritized components of the grasping tasks. Our method is validated in robotic grasping tasks with a 3-finger MICO robot arm. The results show that our method outperformed the standard Deep Reinforcement Learning methods in various robotic grasping tasks.