Adaptation through prediction

multisensory active inference torque control

Journal Article (2023)
Author(s)

Cristian Meo (Student TU Delft)

G. Franzese (TU Delft - Learning & Autonomous Control)

Corrado Pezzato (TU Delft - Robot Dynamics)

M. Spahn (TU Delft - Learning & Autonomous Control)

Pablo Lanillos (Radboud Universiteit Nijmegen)

Research Group
Learning & Autonomous Control
Copyright
© 2023 Cristian Meo, G. Franzese, C. Pezzato, M. Spahn, Pablo Lanillos
DOI related publication
https://doi.org/10.1109/TCDS.2022.3156664
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Cristian Meo, G. Franzese, C. Pezzato, M. Spahn, Pablo Lanillos
Research Group
Learning & Autonomous Control
Issue number
1
Volume number
15
Pages (from-to)
32-41
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Adaptation to external and internal changes is of major importance for robotic systems in uncertain environments. Here, we present a novel multisensory active inference (AIF) torque controller for industrial arms that shows how prediction can be used to resolve adaptation. Our controller, inspired by the predictive brain hypothesis, improves the capabilities of current AIF approaches by incorporating learning and multimodal integration of low- and high-dimensional sensor inputs (e.g., raw images) while simplifying the architecture. We performed a systematic evaluation of our model on a 7DoF Franka Emika Panda robot arm by comparing its behavior with previous AIF baselines and classic controllers, analyzing both qualitatively and quantitatively adaptation capabilities and control accuracy. The results showed improved control accuracy in goal-directed reaching with high noise rejection due to multimodal filtering, and adaptability to dynamical inertial changes, elasticity constraints, and human disturbances without the need to relearn the model or parameter retuning.

Files

Adaptation_Through_Prediction_... (pdf)
(pdf | 1.89 Mb)
- Embargo expired in 03-05-2023
License info not available