Deep Reinforcement Learning-Based Semi-Autonomous Control for Magnetic Micro-robot Navigation with Immersive Manipulation

Magnetic micro-robots have demonstrated immense potential in biomedical applications, such as in vivo drug delivery, non-invasive diagnostics, and cell-based therapies, owing to their precise maneuverability and small size. However, current micromanipulation techniques often rely solely on a two-dimensional (2D) microscopic view as sensory feedback, while traditional control interfaces do not provide an intuitive manner for operators to manipulate micro-robots. These limitations increase the cognitive load on operators, who must interpret limited feedback and translate it into effective control actions. To address these challenges, we propose a Deep Reinforcement Learning-Based Semi-Autonomous Control (DRL-SC) framework for magnetic micro-robot navigation in a simulated microvascular system. Our framework integrates Mixed Reality (MR) to facilitate immersive manipulation of micro-robots, thereby enhancing situational awareness and control precision. Simulation and experimental results demonstrate that our approach significantly improves navigation efficiency, reduces control errors, and enhances the overall robustness of the system in simulated microvascular environments.

@article{mao2025_2503.06359,
  title={ Deep Reinforcement Learning-Based Semi-Autonomous Control for Magnetic Micro-robot Navigation with Immersive Manipulation },
  author={ Yudong Mao and Dandan Zhang },
  journal={arXiv preprint arXiv:2503.06359},
  year={ 2025 }
}