CoGrasp: 6-DoF Grasp Generation for Human-Robot Collaboration

TL;DR

CoGrasp introduces a deep learning approach for generating robot grasps that are compatible with human preferences, enabling safe and natural human-robot collaboration during object handling.

Contribution

The paper presents a novel neural network-based method, CoGrasp, that incorporates human preferences into robot grasp planning for collaborative tasks.

Findings

Achieves 88% success rate in stable, human-compatible grasps in real experiments.

Outperforms existing grasping methods in simulated and real-world tests.

User study shows improved safety and naturalness in human-robot co-grasping.

Abstract

Robot grasping is an actively studied area in robotics, mainly focusing on the quality of generated grasps for object manipulation. However, despite advancements, these methods do not consider the human-robot collaboration settings where robots and humans will have to grasp the same objects concurrently. Therefore, generating robot grasps compatible with human preferences of simultaneously holding an object becomes necessary to ensure a safe and natural collaboration experience. In this paper, we propose a novel, deep neural network-based method called CoGrasp that generates human-aware robot grasps by contextualizing human preference models of object grasping into the robot grasp selection process. We validate our approach against existing state-of-the-art robot grasping methods through simulated and real-robot experiments and user studies. In real robot experiments, our method achieves about 88\% success rate in producing stable grasps that also allow humans to interact and grasp objects simultaneously in a socially compliant manner. Furthermore, our user study with 10 independent participants indicated our approach enables a safe, natural, and socially-aware human-robot objects' co-grasping experience compared to a standard robot grasping technique.