Non-linear dynamical systems represent a compact, flexible, and robust tool for reactive motion generation. The effectiveness of dynamical systems relies on their ability to accurately represent stable motions. Several approaches have been proposed to learn stable and accurate motions from demonstration. Some approaches work by separating accuracy and stability into two learning problems, which increases the number of open parameters and the overall training time. Alternative solutions exploit single-step learning but restrict the applicability to one regression technique. This paper presents a single-step approach to learn stable and accurate motions that work with any regression technique. The approach makes energy considerations on the learned dynamics to stabilize the system at run-time while introducing small deviations from the demonstrated motion. Since the initial value of the energy injected into the system affects the reproduction accuracy, it is estimated from training data using an efficient procedure. Experiments on a real robot and a comparison on a public benchmark shows the effectiveness of the proposed approach.

An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems / Saveriano, M.. - (2020), pp. 4407-4413. (Intervento presentato al convegno 2020 IEEE International Conference on Robotics and Automation, ICRA 2020 tenutosi a fra nel 2020) [10.1109/ICRA40945.2020.9196978].

An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems

Saveriano M.
2020-01-01

Abstract

Non-linear dynamical systems represent a compact, flexible, and robust tool for reactive motion generation. The effectiveness of dynamical systems relies on their ability to accurately represent stable motions. Several approaches have been proposed to learn stable and accurate motions from demonstration. Some approaches work by separating accuracy and stability into two learning problems, which increases the number of open parameters and the overall training time. Alternative solutions exploit single-step learning but restrict the applicability to one regression technique. This paper presents a single-step approach to learn stable and accurate motions that work with any regression technique. The approach makes energy considerations on the learned dynamics to stabilize the system at run-time while introducing small deviations from the demonstrated motion. Since the initial value of the energy injected into the system affects the reproduction accuracy, it is estimated from training data using an efficient procedure. Experiments on a real robot and a comparison on a public benchmark shows the effectiveness of the proposed approach.
2020
Proceedings - IEEE International Conference on Robotics and Automation
Piscataway, New Jersey, USA
Institute of Electrical and Electronics Engineers Inc.
978-1-7281-7395-5
Saveriano, M.
An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems / Saveriano, M.. - (2020), pp. 4407-4413. (Intervento presentato al convegno 2020 IEEE International Conference on Robotics and Automation, ICRA 2020 tenutosi a fra nel 2020) [10.1109/ICRA40945.2020.9196978].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/330151
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 4
social impact