Methods for teaching motion skills to robots focus on training for a single skill at a time. Robots capable of learning from demonstration can considerably benefit from the added ability to learn new movement skills without forgetting what was learned in the past. To this end, we propose an approach for continual learning from demonstration using hypernetworks and neural ordinary differential equation solvers. We empirically demonstrate the effectiveness of this approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations. Our results show that hypernetworks outperform other state-of-the-art continual learning approaches for learning from demonstration. In our experiments, we use the popular LASA benchmark, and two new datasets of kinesthetic demonstrations collected with a real robot that we introduce in this paper called the HelloWorld and RoboTasks datasets. We evaluate our approach on a physical robot and demonstrate its effectiveness in learning real-world robotic tasks involving changing positions as well as orientations. We report both trajectory error metrics and continual learning metrics, and we propose two new continual learning metrics. Our code, along with the newly collected datasets, is available at https://github.com/sayantanauddy/clfd. © 2023 The Author(s)

Continual learning from demonstration of robotics skills / Auddy, Sayantan; Hollenstein, Jakob; Saveriano, Matteo; Rodríguez-Sánchez, Antonio; Piater, Justus. - In: ROBOTICS AND AUTONOMOUS SYSTEMS. - ISSN 0921-8890. - 165:(2023), p. 104427. [10.1016/j.robot.2023.104427]

Continual learning from demonstration of robotics skills

Matteo Saveriano;
2023-01-01

Abstract

Methods for teaching motion skills to robots focus on training for a single skill at a time. Robots capable of learning from demonstration can considerably benefit from the added ability to learn new movement skills without forgetting what was learned in the past. To this end, we propose an approach for continual learning from demonstration using hypernetworks and neural ordinary differential equation solvers. We empirically demonstrate the effectiveness of this approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations. Our results show that hypernetworks outperform other state-of-the-art continual learning approaches for learning from demonstration. In our experiments, we use the popular LASA benchmark, and two new datasets of kinesthetic demonstrations collected with a real robot that we introduce in this paper called the HelloWorld and RoboTasks datasets. We evaluate our approach on a physical robot and demonstrate its effectiveness in learning real-world robotic tasks involving changing positions as well as orientations. We report both trajectory error metrics and continual learning metrics, and we propose two new continual learning metrics. Our code, along with the newly collected datasets, is available at https://github.com/sayantanauddy/clfd. © 2023 The Author(s)
2023
Auddy, Sayantan; Hollenstein, Jakob; Saveriano, Matteo; Rodríguez-Sánchez, Antonio; Piater, Justus
Continual learning from demonstration of robotics skills / Auddy, Sayantan; Hollenstein, Jakob; Saveriano, Matteo; Rodríguez-Sánchez, Antonio; Piater, Justus. - In: ROBOTICS AND AUTONOMOUS SYSTEMS. - ISSN 0921-8890. - 165:(2023), p. 104427. [10.1016/j.robot.2023.104427]
File in questo prodotto:
File Dimensione Formato  
sayantan.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 5.31 MB
Formato Adobe PDF
5.31 MB Adobe PDF Visualizza/Apri

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/11572/378968
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact