Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics
For roboticists needing accurate dynamics models for model-based control, this work provides a method that preserves physical structure while adapting to changing conditions, improving reliability.
The paper proposes a structure-preserving residual learning framework for Euler-Lagrange robot dynamics that decomposes model mismatch into physically constrained components and a sparse history-dependent latent interaction model, enabling selective online adaptation. Experiments on multiple robotic platforms show improved dynamics prediction and trajectory tracking under coupled and time-varying dynamics.
Accurate dynamics models are essential for model-based robotic control, yet nominal Euler--Lagrange models often become inaccurate in the presence of payload variation, unmodeled coupling, friction, aerodynamic effects, and changing operating conditions. Most learning-based correction methods improve prediction accuracy by introducing a single additive residual, but do not preserve the internal mechanical structure of Euler--Lagrange systems. This leads to models that do not preserve symmetry, positive-definiteness, or the coupling between inertia and velocity-dependent terms, which can result in physically inconsistent predictions and reduced reliability when embedded in model-based controllers. We propose a structure-preserving residual learning framework that decomposes model mismatch into an inertia correction, the corresponding induced Coriolis term, and a generalized-force residual. The mechanical component is learned under physical constraints, while the disturbance-sensitive component is represented through a sparse history-dependent latent interaction model and adapted online using Bayesian linear regression. This separation preserves key mechanical structure while restricting adaptation to the part of the dynamics most affected by changing conditions. Experiments across multiple robotic platforms, including mobile, aerial, and manipulator systems, show that the proposed method improves dynamics prediction and trajectory tracking under coupled and time-varying dynamics. These results highlight the value of combining structured residual modeling, compact latent interaction selection, and selective online adaptation for real-world model-based control.