CR-Solver: GPU-Accelerated Kinematics Solver for Tendon-driven Continuum Robots

2026-07-13

AI Summary

This work addresses the lack of motion planning tools for tendon-driven continuum robots that simultaneously achieve speed, accuracy, and practicality. Existing approaches often rely on rigid-body assumptions, rendering them ill-suited for the inherent compliance and complex environmental interactions of such robots. To overcome this limitation, the authors propose CR-Solver—a unified, two-stage framework based on constrained nonlinear optimization that, for the first time, integrates inverse kinematics, path following, and trajectory generation with GPU-accelerated parallel computation. Implemented entirely in Python, CR-Solver offers high scalability and low deployment barriers. Experimental results demonstrate over 95% success rates across three representative tasks, millimeter-level positioning accuracy, and significant speedups compared to conventional CPU-based solvers.

Abstract

Continuum robots provide intrinsic compliance, high dexterity, and safe physical interaction, enabling navigation and manipulation in confined and unstructured environments. Despite recent advances in sensing and control, heightening the need for precise motion generation, most widely used planning libraries are grounded in rigid-body assumptions, creating a critical gap for fast and practical tools for continuum robots. To address this, we present CR-Solver, a two-stage, optimization-based solver for the motion generation of tendon-driven continuum robots. Our method unifies inverse kinematics, path following, and trajectory planning within a single constrained nonlinear optimization framework. Leveraging GPU-accelerated parallel optimization, CR-Solver delivers fast, accurate, and constraint-aware solutions. We validate our approach on three tasks, demonstrating significant speedups over traditional CPU-based solvers while achieving a consistently high success rate above 95% and millimeter-level accuracy. The solver is implemented in pure Python, reducing the barrier to adoption and offering a practical, extensible foundation for continuum robots' high-performance motion planning.

Problem

• continuum robots
• motion generation
• kinematics solver
• tendon-driven
• real-time planning

Innovation

• GPU-accelerated optimization
• continuum robots
• tendon-driven actuation
• constrained nonlinear optimization
• motion planning