Learning-Based Dynamics Modeling and Robust Control for Tendon-Driven Continuum Robots

2026-04-28

AI Summary

This work addresses the significant challenges in modeling and controlling tendon-driven continuum robots (TDCRs), which arise from strong nonlinearities induced by friction hysteresis and compliant transmission. To tackle this, the authors propose a differentiable learning framework that integrates high-fidelity dynamics modeling with robust neural control. The key innovation lies in a novel GRU-based dynamics model featuring bidirectional multi-channel connections and a residual prediction mechanism, which—used for the first time as an end-to-end differentiable gradient bridge—implicitly compensates for complex nonlinearities. Experimental validation on a three-segment physical TDCR demonstrates that the proposed method achieves high-precision trajectory tracking and exhibits strong robustness against unknown payloads, significantly outperforming conventional Jacobian-based approaches while effectively suppressing self-excited oscillations.

Abstract

Tendon-Driven Continuum Robots (TDCRs) pose significant modeling and control challenges due to complex nonlinearities, such as frictional hysteresis and transmission compliance. This paper proposes a differentiable learning framework that integrates high-fidelity dynamics modeling with robust neural control. We develop a GRU-based dynamics model featuring bidirectional multi-channel connectivity and residual prediction to effectively suppress compounding errors during long-horizon auto-regressive prediction. By treating this model as a gradient bridge, an end-to-end neural control policy is optimized through backpropagation, allowing it to implicitly internalize compensation for intricate nonlinearities. Experimental validation on a physical three-section TDCR demonstrates that our framework achieves accurate tracking and superior robustness against unseen payloads, outperforming Jacobian-based methods by eliminating self-excited oscillations.

Problem

• Tendon-Driven Continuum Robots
• nonlinearities
• dynamics modeling
• robust control
• frictional hysteresis

Innovation

• differentiable learning
• GRU-based dynamics model
• neural control
• tendon-driven continuum robots
• robustness