Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots
Ziqing Zou, Ke Qiu, Haojian Lu, Rong Xiong, Yue Wang
TLDR
This paper introduces a reference-augmented offline learning framework for precise 6-DOF tracking control of Tendon-Driven Continuum Robots.
Key contributions
- Proposes a reference-augmented offline learning framework for precise 6-DOF TDCR tracking control.
- Uses a differentiable RNN dynamics surrogate as a gradient bridge for policy optimization.
- Employs multi-scale augmentation (bias, perturbations, random walks) for diverse error recovery.
- Achieves 50.9% position error reduction and outperforms Jacobian methods in precision.
Why it matters
This paper addresses critical control challenges in Tendon-Driven Continuum Robots, improving their precision and stability. By introducing a novel reference-augmented learning framework, it enables robots to handle complex dynamics and generalize better. This advancement is crucial for deploying TDCRs in delicate applications requiring high accuracy.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.