Microrobot Vascular Parkour: Analytic Geometry-based Path Planning with Real-time Dynamic Obstacle Avoidance
🤖 AI Summary
To address the challenge of real-time, collision-free navigation for intravascular microrobots in densely cluttered, dynamic environments, this paper proposes a hierarchical autonomous navigation framework integrating Analytic Geometry-based Global Planning (AGP) with dual-mode local control (rule-based + reinforcement learning). AGP generates deterministic, scalable initial 2D/3D trajectories; the dual-mode controller enables millisecond-level (40 ms/frame), closed-loop motion prediction, image-feedback-driven obstacle avoidance, and collision detection. The method achieves stable target arrival in both simulation and physical experiments, reducing path length by 12–28% and significantly outperforming WA*, PSO, and RRT in planning efficiency. It supports real-time intravascular imaging at 25 fps. This work establishes a new paradigm for minimally invasive interventional robotics—offering high robustness, formal verifiability, and real-time performance under complex physiological constraints.
Application Category
📝 Abstract
Autonomous microrobots in blood vessels could enable minimally invasive therapies, but navigation is challenged by dense, moving obstacles. We propose a real-time path planning framework that couples an analytic geometry global planner (AGP) with two reactive local escape controllers, one based on rules and one based on reinforcement learning, to handle sudden moving obstacles. Using real-time imaging, the system estimates the positions of the microrobot, obstacles, and targets and computes collision-free motions. In simulation, AGP yields shorter paths and faster planning than weighted A* (WA*), particle swarm optimization (PSO), and rapidly exploring random trees (RRT), while maintaining feasibility and determinism. We extend AGP from 2D to 3D without loss of speed. In both simulations and experiments, the combined global planner and local controllers reliably avoid moving obstacles and reach targets. The average planning time is 40 ms per frame, compatible with 25 fps image acquisition and real-time closed-loop control. These results advance autonomous microrobot navigation and targeted drug delivery in vascular environments.
Problem
Research questions and friction points this paper is trying to address.
Real-time path planning for microrobots in blood vessels
Avoiding dense moving obstacles during vascular navigation
Achieving autonomous targeted drug delivery in dynamic environments
Innovation
Methods, ideas, or system contributions that make the work stand out.
Analytic geometry global planner for path planning
Reactive local controllers for obstacle avoidance
Real-time imaging for dynamic environment navigation
🔎 Similar Papers
No similar papers found.
