A Bilingual Cognitive Robot that Learns like a Toddler

Ioanna Giorgi, Angelo Cangelosi, Giovanni L. Masala

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose an embodied architecture featuring a developmental agent and a social robot for human-robot verbal engagement at preschool level. Initially, we trained the agent on bilingual acquisition and demonstrated its skill to appropriately detect the spoken content and automatically match the human user’s language. Multilingual robot agents able to understand and communicate contexts in multiple tongues without loss of meaning in translations can greatly affect human cognitive and interaction capabilities. Furthermore, we teach the robot to gradually learn from experience new knowledge not specified at design time and autonomously use it for task-solving without being trained anew. The demonstrated system shows promising potential to becoming a low-cost social companion that can be easily integrated in the human world.
Original languageEnglish
Title of host publicationIEEE Symposium Series on Computational Intelligence (SSCI 2020)
PublisherIEEE
Publication statusAccepted/In press - 18 Sept 2020

Keywords

  • brain-inspired architecture
  • developmental agent
  • cognitive system
  • embodiment
  • bilingual robot
  • multi-language development
  • humanlike learning

Fingerprint

Dive into the research topics of 'A Bilingual Cognitive Robot that Learns like a Toddler'. Together they form a unique fingerprint.

Cite this