Fuzzy-RRT for Obstacle Avoidance in a 2-DOF Semi-Autonomous Surgical Robotic Arm

TL;DR

The paper addresses autonomous surgical robotics for long-duration space missions where communication delays limit teleoperation. It introduces a Fuzzy-RRT framework that couples Rapidly-exploring Random Trees with six Takagi-Sugeno-Kang fuzzy inference systems, optimized by a Genetic Algorithm within the Thales True AI platform, enabling real-time obstacle avoidance for a 2-DOF surgical arm. Results show dramatic efficiency and quality gains over standard RRT, including a 743% reduction in path search time and a 43% improvement in path cost, driven by adaptive fuzzy parameters and evolutionary optimization. The approach offers a scalable, explainable path-planning solution with potential for extension to 5-DOF collaboration and broader autonomous surgical capabilities in space and other constrained environments.

Abstract

AI-driven semi-autonomous robotic surgery is essential for addressing the medical challenges of long-duration interplanetary missions, where limited crew sizes and communication delays restrict traditional surgical approaches. Current robotic surgery systems require full surgeon control, demanding extensive expertise and limiting feasibility in space. We propose a novel adaptation of the Fuzzy Rapidly-exploring Random Tree algorithm for obstacle avoidance and collaborative control in a two-degree-of-freedom robotic arm modeled on the Miniaturized Robotic-Assisted surgical system. It was found that the Fuzzy Rapidly-exploring Random Tree algorithm resulted in an 743 percent improvement to path search time and 43 percent improvement to path cost.

Figures (5)

• Figure 1: Fuzzy Inference System for Parameter Generation
• Figure 2: Fitness of GFS over 10 Generations
• Figure 3: Comparison of path planning using standard RRT vs. Fuzzy RRT.
• Figure 4: Comparison of Iteration metrics between standard RRT and Fuzzy RRT.
• Figure 5: Comparison of Path Cost between standard RRT and Fuzzy RRT.