A Synergistic Framework for Learning Shape Estimation and Shape-Aware Whole-Body Control Policy for Continuum Robots
Mohammadreza Kasaei, Farshid Alambeigi, Mohsen Khadem
TL;DR
The paper tackles the dual challenge of estimating the shape of soft continuum robots and controlling them in a shape-aware manner. It proposes a synergistic framework built from two Augmented Neural Ordinary Differential Equations (ANODEs): Shape-NODE for continuous shape estimation guided by Cosserat-rod priors, and Control-NODE for a shape-aware whole-body policy trained in an MPC-like fashion. The approach yields robust shape prediction, accurate trajectory tracking, and obstacle avoidance, validated through extensive simulations and real-robot experiments, outperforming end-to-end, Neural-ODE, and RNN baselines in accuracy and generalization. This work advances practical, generalizable control of soft robots in complex environments with improved interpretability thanks to the incorporated physical priors.
Abstract
In this paper, we present a novel synergistic framework for learning shape estimation and a shape-aware whole-body control policy for tendon-driven continuum robots. Our approach leverages the interaction between two Augmented Neural Ordinary Differential Equations (ANODEs) -- the Shape-NODE and Control-NODE -- to achieve continuous shape estimation and shape-aware control. The Shape-NODE integrates prior knowledge from Cosserat rod theory, allowing it to adapt and account for model mismatches, while the Control-NODE uses this shape information to optimize a whole-body control policy, trained in a Model Predictive Control (MPC) fashion. This unified framework effectively overcomes limitations of existing data-driven methods, such as poor shape awareness and challenges in capturing complex nonlinear dynamics. Extensive evaluations in both simulation and real-world environments demonstrate the framework's robust performance in shape estimation, trajectory tracking, and obstacle avoidance. The proposed method consistently outperforms state-of-the-art end-to-end, Neural-ODE, and Recurrent Neural Network (RNN) models, particularly in terms of tracking accuracy and generalization capabilities.