Data-driven Interpretable Hybrid Robot Dynamics

TL;DR

This paper presents a data-driven approach combining symbolic regression and SINDy to identify interpretable residual dynamics models for robots, outperforming neural networks in accuracy and generalization, and providing physically meaningful torque predictions.

Contribution

The paper introduces a hybrid modeling framework that uses symbolic regression and SINDy to derive compact, interpretable residual dynamics models for robots, improving over black-box methods.

Findings

Accurately recover inertial, Coriolis, gravity, and viscous effects with small error.

Symbolic regression residuals generalize better than SINDy and neural networks on real data.

Provides physically meaningful models that extend nominal 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.