History-Conditioned Flow Matching for Probabilistic Dynamics of Tendon-Driven Continuum Robots

This paper presents a history-conditioned physics-informed flow-matching framework for probabilistic dynamics prediction of tendon-driven continuum robots. The approach addresses uncertainties arising from material behavior, tendon transmission, friction, and contact by conditioning on motion and actuation histories. The framework enables probabilistic forecasting of robot motion under mechanical uncertainties inherent in continuum mechanisms.