Hybrid Learning of Time-Series Inverse Dynamics Models for Locally Isotropic Robot Motion

TL;DR

This paper introduces a hybrid learning architecture combining physics-based models and neural networks to accurately estimate inverse dynamics in robots during locally isotropic motion, addressing challenges posed by friction and hysteresis.

Contribution

It proposes a novel hybrid model with joint-wise rotational history encoding, significantly improving torque estimation accuracy over existing methods.

Findings

Outperforms state-of-the-art baselines by a factor of 10^3 in RMSE.

Achieves an RMSE of 0.14 Nm in torque estimation.

Demonstrates robustness in low-velocity, small-scale robot motions.

Abstract

Applications of force control and motion planning often rely on an inverse dynamics model to represent the high-dimensional dynamic behavior of robots during motion. The widespread occurrence of low-velocity, small-scale, locally isotropic motion (LIMO) typically complicates the identification of appropriate models due to the exaggeration of dynamic effects and sensory perturbation caused by complex friction and phenomena of hysteresis, e.g., pertaining to joint elasticity. We propose a hybrid model learning base architecture combining a rigid body dynamics model identified by parametric regression and time-series neural network architectures based on multilayer-perceptron, LSTM, and Transformer topologies. Further, we introduce novel joint-wise rotational history encoding, reinforcing temporal information to effectively model dynamic hysteresis. The models are evaluated on a KUKA iiwa 14 during algorithmically generated locally isotropic movements. Together with the rotational encoding, the proposed architectures outperform state-of-the-art baselines by a magnitude of 10$^3$ yielding an RMSE of 0.14 Nm. Leveraging the hybrid structure and time-series encoding capabilities, our approach allows for accurate torque estimation, indicating its applicability in critically force-sensitive applications during motion sequences exceeding the capacity of conventional inverse dynamics models while retaining trainability in face of scarce data and explainability due to the employed physics model prior.