Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle
- https://doi.org/10.2991/aisr.k.201029.067How to use a DOI?
- anthropomorphic manipulator, dynamic environment, dynamic obstacles, machine learning, convolutional neural networks
Currently, the rapidly developing direction of anthropomorphic robotics attracts great interest of developers. This is due to the need to perform routine, harmful and hazardous types of work without direct human intervention, which is the key to ensuring the safety of the tasks performed. The article discusses the issue of optimizing the trajectory of the manipulator when performing operations in the working area with an obstacle. To achieve this goal, an algorithm for controlling the movement of an anthropomorphic manipulator in a working area with dynamic obstacles is proposed using deep learning technology with amplification of a convolutional artificial neural network based on the DQN learning algorithm. This algorithm is more scalable than peers because it can be used for a wide variety of path planning problems in both deterministic and non-deterministic environments. The results of modeling the operation of a manipulator with seven rotational degrees of mobility in the working area with a typical obstacle in the form of a sphere are presented. The presented simulation results demonstrate the effectiveness of the proposed method and the need for its further development.
- © 2020, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Vyacheslav Petrenko AU - Mikhail Gurchinsky AU - Fariza Tebueva AU - Sergey Ryabtsev PY - 2020 DA - 2020/11/10 TI - Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle BT - Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020) PB - Atlantis Press SP - 359 EP - 364 SN - 1951-6851 UR - https://doi.org/10.2991/aisr.k.201029.067 DO - https://doi.org/10.2991/aisr.k.201029.067 ID - Petrenko2020 ER -