Learning Actuator-Aware Spectral Submanifolds for Precise Control of Continuum Robots
This work addresses precise control for continuum robots, offering a practical improvement over prior methods by eliminating an actuation-calibration step.
The paper tackled the problem of controlling continuum robots with high-dimensional, nonlinear dynamics by proposing control-augmented spectral submanifolds (caSSMs) that incorporate control inputs into state representation, resulting in a 40% reduction in open-loop prediction error and a 52% reduction in closed-loop tracking error compared to existing methods.
Continuum robots exhibit high-dimensional, nonlinear dynamics which are often coupled with their actuation mechanism. Spectral submanifold (SSM) reduction has emerged as a leading method for reducing high-dimensional nonlinear dynamical systems to low-dimensional invariant manifolds. Our proposed control-augmented SSMs (caSSMs) extend this methodology by explicitly incorporating control inputs into the state representation, enabling these models to capture nonlinear state-input couplings. Training these models relies solely on controlled decay trajectories of the actuator-augmented state, thereby removing the additional actuation-calibration step commonly needed by prior SSM-for-control methods. We learn a compact caSSM model for a tendon-driven trunk robot, enabling real-time control and reducing open-loop prediction error by 40% compared to existing methods. In closed-loop experiments with model predictive control (MPC), caSSM reduces tracking error by 52%, demonstrating improved performance against Koopman and SSM based MPC and practical deployability on hardware continuum robots.