Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery

TL;DR

This paper introduces a diffusion policy approach using imitation learning to enable robots to efficiently push, group, and grasp multiple objects simultaneously, improving multi-object delivery tasks.

Contribution

It presents a novel diffusion policy network trained via expert demonstrations to adaptively handle multi-object grouping and grasping in diverse scenarios.

Findings

Effective multi-object grouping and grasping demonstrated

Performance improves with more training data

Method adapts to different object quantities and scenarios

Abstract

Simultaneously grasping and delivering multiple objects can significantly enhance robotic work efficiency and has been a key research focus for decades. The primary challenge lies in determining how to push objects, group them, and execute simultaneous grasping for respective groups while considering object distribution and the hardware constraints of the robot. Traditional rule-based methods struggle to flexibly adapt to diverse scenarios. To address this challenge, this paper proposes an imitation learning-based approach. We collect a series of expert demonstrations through teleoperation and train a diffusion policy network, enabling the robot to dynamically generate action sequences for pushing, grouping, and grasping, thereby facilitating efficient multi-object grasping and delivery. We conducted experiments to evaluate the method under different training dataset sizes, varying object quantities, and real-world object scenarios. The results demonstrate that the proposed approach can effectively and adaptively generate multi-object grouping and grasping strategies. With the support of more training data, imitation learning is expected to be an effective approach for solving the multi-object grasping problem.