Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics
2026-06-08 • Robotics
Robotics
AI summaryⓘ
The authors address the problem that standard physics models for robots often become inaccurate when conditions change, like when the robot carries different weights or faces friction. They propose a new way to correct these models that keeps important mechanical properties intact by splitting the error into parts related to inertia, forces, and velocity effects. Their method learns these parts separately and adapts online only where needed, making the predictions more reliable. Tests on various robots show their approach improves control and tracking accuracy under changing conditions.
Euler-Lagrange modelsmodel-based controldynamics modelinginertiaCoriolis forcesresidual learningBayesian linear regressiontrajectory trackingrobotic manipulatorsonline adaptation
Authors
Rishabh Dev Yadav, Samaksh Ujjawal, Sihao Sun, Spandan Roy, Wei Pan
Abstract
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.