Towards Generalization and Data Efficient Learning of Deep Robotic Grasping

no code implementations • 2 Jul 2020 • Zhixin Chen, Mengxiang Lin, Zhixin Jia, Shibo Jian

In this paper, we propose a DRL based robotic visual grasping framework, in which visual perception and control policy are trained separately rather than end-to-end.

Robotics

Vision-based Robot Manipulation Learning via Human Demonstrations

no code implementations • 1 Mar 2020 • Zhixin Jia, Mengxiang Lin, Zhixin Chen, Shibo Jian

We evaluate our approach in a real-world robot, using several simple and complex manipulation tasks commonly performed in daily life.

Robotics