{"ID":2830719,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11900","arxiv_id":"2512.11900","title":"Data-driven Interpretable Hybrid Robot Dynamics","abstract":"We study data-driven identification of interpretable hybrid robot dynamics, where an analytical rigid-body dynamics model is complemented by a learned residual torque term. Using symbolic regression and sparse identification of nonlinear dynamics (SINDy), we recover compact closed-form expressions for this residual from joint-space data. In simulation on a 7-DoF Franka arm with known dynamics, these interpretable models accurately recover inertial, Coriolis, gravity, and viscous effects with very small relative error and outperform neural-network baselines in both accuracy and generalization. On real data from a 7-DoF WAM arm, symbolic-regression residuals generalize substantially better than SINDy and neural networks, which tend to overfit, and suggest candidate new closed-form formulations that extend the nominal dynamics model for this robot. Overall, the results indicate that interpretable residual dynamics models provide compact, accurate, and physically meaningful alternatives to black-box function approximators for torque prediction.","short_abstract":"We study data-driven identification of interpretable hybrid robot dynamics, where an analytical rigid-body dynamics model is complemented by a learned residual torque term. Using symbolic regression and sparse identification of nonlinear dynamics (SINDy), we recover compact closed-form expressions for this residual fro...","url_abs":"https://arxiv.org/abs/2512.11900","url_pdf":"https://arxiv.org/pdf/2512.11900v1","authors":"[\"Christopher E. Mower\",\"Rui Zong\",\"Haitham Bou-Ammar\"]","published":"2025-12-10T13:33:03Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}