Abstract
The traditional robotic arm control method is based on the precise mathematical model of the task and lacks adaptability. When the environment or task changes, the control effect is greatly compromised or even out of control. In recent years, Deep Reinforcement Learning (DRL), which has achieved great success in games, has been introduced into the control of robotic arms. TD3 (Twin Delayed Deep Deterministic Policy Gradient) is an improved algorithm based on DDPG (Deep Deterministic Policy Gradient). Like other DRL algorithms, TD3 also has the problem of low learning efficiency. This paper proposes a improved TD3 algorithm which can converge faster than TD3 algorithm in terms of reachability and obstacle avoidance. Finally, the improvement of the algorithm is verified by a simulation research on a 6-DOF ABB-IRB1200 robotic arm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hua, J., Zeng, L., Li, G., Ju, Z.: Learning for a robot: deep reinforcement learning, imitation learning, transfer learning. Sensors (Basel, Switzerland) (2021). https://doi.org/10.3390/s21041278
Wang, D., Deng, H., Pan, Z.: MRCDRL: multi-robot coordination with deep reinforcement learning. Neurocomputing (2020). https://doi.org/10.1016/j.neucom.2020.04.028
Akalin, N., Loutfi, A.: Reinforcement learning approaches in social robotics. Sensors (Basel, Switzerland) (2021). https://doi.org/10.3390/s21041292
Leinen, P., Esders, M., Schutt, K.T., Wagner, C., Tautz, F.S.: Autonomous robotic nanofabrication with reinforcement learning. Sci. Adv. (2020). https://doi.org/10.1126/sciadv.abb6987
Arel, I.: Deep reinforcement learning as foundation for artificial general intelligence. Atlantis Press (2012). https://doi.org/10.2991/978-94-91216-62-6_6
Rusu, A.A., et al.: Progressive neural networks (2016). arXiv.cs.LG. https://arxiv.org/abs/1606.04671
Fujimoto, S., Van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods (2018). arXiv.cs.AI. https://arxiv.org/abs/1802.09477
Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., de Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv e-prints (2015). https://dl.acm.org/doi/10.5555/3045390.3045601
Mnih, V., et al.: Playing atari with deep reinforcement learning. Comput. Sci. (2013). https://arxiv.org/abs/1312.5602
Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. Comput. Sci. (2015). https://arxiv.org/abs/1511.05952
Bu, L.: Research on robotic arm control based on deep reinforcement learning. China University of Mining and Technology (Jiangsu) (2019). http://cdmd.cnki.com.cn/article/cdmd-10290-1019854613.htm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, Y., Chen, D. (2022). Research of Improved TD3 in Robotic Arm Control. In: Jia, Y., Zhang, W., Fu, Y., Yu, Z., Zheng, S. (eds) Proceedings of 2021 Chinese Intelligent Systems Conference. Lecture Notes in Electrical Engineering, vol 805. Springer, Singapore. https://doi.org/10.1007/978-981-16-6320-8_7
Download citation
DOI: https://doi.org/10.1007/978-981-16-6320-8_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6319-2
Online ISBN: 978-981-16-6320-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)