Research on Visual Localization and Gripping Technology of Robotic Arm Based on Deep Learning

Jiawei Tang

doi:10.62051/ijcsit.v2n1.53

Authors

Jiawei Tang

DOI:

https://doi.org/10.62051/ijcsit.v2n1.53

Keywords:

Learning; Robotic Arm; Visual Localization; Gripping Technology; Industrial Automation; Automatic Identification

Abstract

With the continuous development of industrial automation, robotic arms are more and more widely used in production lines. In order to realize the autonomous positioning and grasping function of robotic arm, this paper studies the visual positioning and grasping technology of robotic arm based on deep learning. The deep learning algorithm processes and analyzes the image, realizes the automatic identification and localization of the target object, and then guides the robotic arm to carry out accurate grasping. The experimental results show that this technology can effectively improve the positioning accuracy and grasping success rate of the robotic arm, which provides strong support for the intelligent upgrade of industrial automation production lines.

Downloads

Download data is not yet available.

References

Obstacle avoidance in space robotics: Review of major challenges and proposed solutions[J]. Tomasz Rybus. Progress in Aerospace Sciences, 2018.

Manipulator motion planning using flexible obstacle avoidance based on model learning[J]. Zhixuan Wei; Weidong Chen; Hesheng Wang; Jingchuan Wang.International Journal of Advanced Robotic Systems, 2017.

Asynchronous Methods for Deep Reinforcement Learning.[J]. Volodymyr Mnih; Adrià Puigdomènech Badia; Mehdi Mirza; Alex Graves; Timothy P. Lillicrap; Tim Harley; David Silver; Koray Kavukcuoglu.CoRR, 2016.

Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots.[J]. Lei Tai; Ming Liu 0001. CoRR, 2016.

Continuous control with deep reinforcement learning.[J]. Timothy P. Lillicrap; Jonathan J. Hunt; Alexander Pritzel; Nicolas Heess; Tom Erez; Yuval Tassa; David Silver; Daan Wierstra. CoRR, 2015.

Reinforcement Learning: An Introduction; by Richard S. Sutton and Andrew G. Barto, Adaptive Computation and Machine Learning series, MIT Press (Bradford Book), Cambridge, Mass., 1998, xviii + 322 pp, ISBN 0-262-19398-1,[J]. Alex M. Andrew.Robotica,1999(2).