Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation
Yiming Li1Tao Kong2Ruihang Chu3Yifeng Li2Peng 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 = {International Conference on Intelligent Robots and Systems (IROS)},
  year={2021}
}