# Derivative-free online learning of inverse dynamics models

arXiv: https://arxiv.org/abs/1809.05074 · HTML: https://mlsanity.com/paper/1809.05074/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models](https://mlsanity.com/paper/2110.01894/) (2021)
- [Online Dynamics Learning for Predictive Control with an Application to Aerial Robots](https://mlsanity.com/paper/2207.09344/) (2022)
- [Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application](https://mlsanity.com/paper/2101.12115/) (2021)
- [Meta-Learning Online Control for Linear Dynamical Systems](https://mlsanity.com/paper/2208.10259/) (2022)
- [A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification](https://mlsanity.com/paper/2310.06585/) (2023)
- [Learning Control from Raw Position Measurements](https://mlsanity.com/paper/2301.13183/) (2023)
- [Enhanced Prediction of Multi-Agent Trajectories via Control Inference and State-Space Dynamics](https://mlsanity.com/paper/2408.12609/) (2024)
- [Model-based Policy Search for Partially Measurable Systems](https://mlsanity.com/paper/2101.08740/) (2021)

## Abstract (arXiv)

This paper discusses online algorithms for inverse dynamics modelling in robotics. Several model classes including rigid body dynamics (RBD) models, data-driven models and semiparametric models (which are a combination of the previous two classes) are placed in a common framework. While model classes used in the literature typically exploit joint velocities and accelerations, which need to be approximated resorting to numerical differentiation schemes, in this paper a new `derivative-free' framework is proposed that does not require this preprocessing step. An extensive experimental study with real data from the right arm of the iCub robot is presented, comparing different model classes and estimation procedures, showing that the proposed `derivative-free' methods outperform existing methodologies.