The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)
Online ISSN : 2424-3124
2021
Session ID : 1A1-E14
Conference information

Robotic Grasping based on Point Cloud Recognition and Deep Reinforcement Learning
*Yuliu WangYusuke YoshiyasuEiichi Yoshida
Author information
CONFERENCE PROCEEDINGS RESTRICTED ACCESS

Details
Abstract

We propose a deep reinforcement learning method to learn to produce grasping strategies using 3D point clouds as input. We facilitate a training process by using a tensor-based distributed training framework to perform many trial-and-errors with a wide variety of objects. Our approach greatly increases the number of object categories that can be handled and exhibits a strong generalization ability to grasp unknown object categories.

Content from these authors
© 2021 The Japan Society of Mechanical Engineers
Previous article Next article
feedback
Top