Asynchronous federated learning system for human–robot touch interaction

作者：

Highlights：

• Federated learning allows large-scale distributed learning and protects privacy.

• The robots are able to collaboratively interpret human–robot touch interactions.

• The robots decide when to upload their models to the central node asynchronously.

• Cooperation between robots improves the results from conventional learning methods.

摘要

•Federated learning allows large-scale distributed learning and protects privacy.•The robots are able to collaboratively interpret human–robot touch interactions.•The robots decide when to upload their models to the central node asynchronously.•Cooperation between robots improves the results from conventional learning methods.

论文关键词：Machine learning applications,Federated learning,Human–robot interaction,Social robots,Acoustic sensing,Touch recognition

论文评审过程：Received 30 December 2021, Revised 29 July 2022, Accepted 8 August 2022, Available online 13 August 2022, Version of Record 1 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118510