Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment

Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment Publisher

Salehi A¹ ; Hosseinpour S¹ ; Tabatabaei N² ; Soltani Firouz M¹ ; Yu T³

Show Affiliations

1. Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agriculture, University of Tehran, Karaj, 31587-77871, Iran
2. Department of Medical Nanotechnology, School of Advanced Technologies in Medicine, Tehran University of Medical Sciences, Tehran, 14618-84513, Iran
3. South China University of Technology, Guangzhou International Campus, Guangzhou, 511442, China

Source: Micromachines Published:2024

Abstract

Microrobotics has opened new horizons for various applications, especially in medicine. However, it also witnessed challenges in achieving maximum optimal performance. One key challenge is the intelligent, autonomous, and precise navigation control of microrobots in fluid environments. The intelligence and autonomy in microrobot control, without the need for prior knowledge of the entire system, can offer significant opportunities in scenarios where their models are unavailable. In this study, two control systems based on model-free deep reinforcement learning were implemented to control the movement of a disk-shaped magnetic microrobot in a real-world environment. The training and results of an off-policy SAC algorithm and an on-policy TRPO algorithm revealed that the microrobot successfully learned the optimal path to reach random target positions. During training, the TRPO exhibited a higher sample efficiency and greater stability. The TRPO and SAC showed 100% and 97.5% success rates in reaching the targets in the evaluation phase, respectively. These findings offer basic insights into achieving intelligent and autonomous navigation control for microrobots to advance their capabilities for various applications. © 2024 by the authors.

Style	Citing Format
MLA	Salehi A, et al.. "Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment." Micromachines, vol. 15, no. 1, 2024, pp. -.
APA	Salehi A, Hosseinpour S, Tabatabaei N, Soltani Firouz M, Yu T (2024). Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment. Micromachines, 15(1), -.
Chicago	Salehi A, Hosseinpour S, Tabatabaei N, Soltani Firouz M, Yu T. "Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment." Micromachines 15, no. 1 (2024): -.
Harvard	Salehi A et al. (2024) 'Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment', Micromachines, 15(1), pp. -.
Vancouver	Salehi A, Hosseinpour S, Tabatabaei N, Soltani Firouz M, Yu T. Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment. Micromachines. 2024;15(1):-.
BibTex	@article{ author = {Salehi A and Hosseinpour S and Tabatabaei N and Soltani Firouz M and Yu T}, title = {Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment}, journal = {Micromachines}, volume = {15}, number = {1}, pages = {-}, year = {2024} }
RIS	TY - JOUR AU - Salehi A AU - Hosseinpour S AU - Tabatabaei N AU - Soltani Firouz M AU - Yu T TI - Intelligent Navigation of a Magnetic Microrobot With Model-Free Deep Reinforcement Learning in a Real-World Environment JO - Micromachines VL - 15 IS - 1 SP - EP - PY - 2024 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract