Adaptive control method predicts and counters dynamic disturbances accurately
Statistical Learning of Contractive Dynamical Representations for Composite Adaptive Control
Machine LearningRobotics
Summary
Controlling machines that face unpredictable forces, like a vehicle on slippery ground or a pendulum swinging, is hard because these forces can change and affect performance. The authors developed a new method that learns how these disturbances evolve over time by analyzing sensor data and control signals, helping the controller predict and adjust better. This approach improves control accuracy and robustness by combining classic disturbance handling techniques with modern learning-based adaptations.
What this means in practice
- •For robotics engineers: Improve robot control accuracy under changing external disturbances by learning predictive disturbance models from sensor data.
- •For autonomous vehicle developers: Enhance vehicle stability on difficult terrains by using learned disturbance representations that anticipate effects like liquid sloshing or sliding.
Authors
Min Kim, José Leonardo Brenes, Fred Hadaegh, Soon-Jo Chung
Abstract
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturbance-rejection methods. Specifically, we introduce a statistically principled hard expectation-maximization (hard-EM) procedure, with a Kalman smoother in the hard E-step, to identify dynamical representations of disturbance whose latent evolution is uniformly contractive. The learned representation evolves a latent disturbance-excitation state from measured plant features and control inputs and decodes that state into the time-varying disturbance acting on the nominal plant, thereby extending prior "fixed-decay" last-layer adaptive methods to a learned, predictive DAC-style formulation. Combined with Bayesian filtering of the learned latent state, this representation yields a composite adaptive tracking controller with predictive capability and provable exponential convergence to a bounded neighborhood. We validate our approach experimentally on a slippery ground vehicle carrying a liquid-sloshing tank and a pendulum load, and we further assess its robustness on a system of coupled Duffing oscillators. Across both settings, the method achieves accurate disturbance prediction and improved overall tracking performance relative to fixed-decay representation-learning ablations, LTI disturbance-accommodating baselines, and model-based PD baselines.