Self-Supervised Learning for Joint Pushing and Grasping Policies in Highly Cluttered Environments

TL;DR

This paper introduces a deep reinforcement learning method enabling robots to effectively push and grasp objects in cluttered environments, achieving high task success rates and outperforming existing approaches.

Contribution

A dual reinforcement learning model for joint pushing and grasping in cluttered scenes, demonstrating high resilience and superior performance over state-of-the-art methods.

Findings

Achieved 98% task completion in simulation.

Performed extensive experiments with 1000 test runs.

Outperformed recent state-of-the-art approaches.

Abstract

Robots often face situations where grasping a goal object is desirable but not feasible due to other present objects preventing the grasp action. We present a deep Reinforcement Learning approach to learn grasping and pushing policies for manipulating a goal object in highly cluttered environments to address this problem. In particular, a dual Reinforcement Learning model approach is proposed, which presents high resilience in handling complicated scenes, reaching an average of 98% task completion using primitive objects in a simulation environment. To evaluate the performance of the proposed approach, we performed two extensive sets of experiments in packed objects and a pile of object scenarios with a total of 1000 test runs in simulation. Experimental results showed that the proposed method worked very well in both scenarios and outperformed the recent state-of-the-art approaches. Demo video, trained models, and source code for the results reproducibility purpose are publicly available. https://sites.google.com/view/pushandgrasp/home