Deep Reinforcement Learning for Robotic Pushing and Picking in Cluttered Environment

Abstract

In this paper, a novel robotic grasping system is established to automatically pick up objects in cluttered scenes. A composite robotic hand composed of a suction cup and a gripper is designed for grasping the object stably. The suction cup is used for lifting the object from the clutter first and the gripper for grasping the object accordingly. We utilize the affordance map to provide pixel-wise lifting point candidates for the suction cup. To obtain a good affordance map, the active exploration mechanism is introduced to the system. An effective metric is designed to calculate the reward for the current affordance map, and a deep Q-Network (DQN) is employed to guide the robotic hand to actively explore the environment until the generated affordance map is suitable for grasping. Experimental results have demonstrated that the proposed robotic grasping system is able to greatly increase the success rate of the robotic grasping in cluttered scenes.

arXiv commenthas been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems 2019

Cited by in corpus (6)

• Visual Foresight Trees for Object Retrieval from Clutter with Nonprehensile Rearrangement
• MQA: Answering the Question via Robotic Manipulation
• Deep Reinforcement Learning Based on Local GNN for Goal-conditioned Deformable Object Rearranging
• Graph-Transporter: A Graph-based Learning Method for Goal-Conditioned Deformable Object Rearranging Task
• Efficient learning of goal-oriented push-grasping synergy in clutter
• Policy learning in SE(3) action spaces