Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots

TL;DR

This paper introduces a reference-augmented offline learning framework utilizing a differentiable RNN surrogate for precise 6-DOF control of tendon-driven continuum robots, addressing nonlinear and hysteresis challenges.

Contribution

It proposes a novel multi-scale augmentation scheme and a differentiable RNN-based dynamics surrogate to improve control accuracy and robustness without extra hardware.

Findings

50.9% reduction in average position error

Outperforms Jacobian-based methods in precision and stability

Effective across various speeds

Abstract

Tendon-Driven Continuum Robots (TDCRs) pose significant control challenges due to their highly nonlinear, path-dependent dynamics and non-Markovian characteristics. Traditional Jacobian-based controllers often struggle with hysteresis-induced oscillations, while conventional learning-based approaches suffer from poor generalization to out-of-distribution trajectories. This paper proposes a reference-augmented offline learning framework for precise 6-DOF tracking control of TDCRs. By leveraging a differentiable RNN-based dynamics surrogate as a gradient bridge, we optimize a control policy through an augmented reference distribution. This multi-scale augmentation scheme incorporates stochastic bias, harmonic perturbations, and random walks, forcing the policy to internalize diverse tracking error recovery mechanisms without additional hardware interaction. Experimental results on a three-section TDCR platform demonstrate that the proposed policy achieves a 50.9\% reduction in average position error compared to non-augmented baselines and significantly outperforms Jacobian-based methods in both precision and stability across various speeds.