Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation

Yiming Li¹, Tao Kong², Ruihang Chu³, Yifeng Li², Peng Wang¹, Lei Li²,

¹Chinese Academy of Sciences, ²ByteDance AI Lab, ³The Chinese University of Hong Kong

Overview

Grasping in cluttered scenes has always been a great challenge for robots, due to the requirement of the ability to well understand the scene and object information. In this work, we propose to formalize the 6-DoF grasp pose estimation as a simultaneous multi-task learning problem. In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information. The whole framework is jointly optimized and end-to-end differentiable. Our model is evaluated on large scale benchmarks as well as real robot system.

Results

6 DoF Grasp pose estimation results on GraspNet-1billion dataset.

Demo video here.

BibTeX

@inproceedings{li2021sscl,
  title={Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation},
  author={Li, Yiming and Kong, Tao and Chu, Ruihang and Li, Yifeng, Wang, Peng and Li, Lei},
  booktitle = {None},
  year={2021}
}