Continual learning of visual concepts for robots through limited supervision

Ali Ayub, Alan R. Wagner

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For many real-world robotics applications, robots need to continually adapt and learn new concepts. Further, robots need to learn through limited data because of scarcity of labeled data in the real-world environments. To this end, my research focuses on developing robots that continually learn in dynamic unseen environments/scenarios, learn from limited human supervision, remember previously learned knowledge and use that knowledge to learn new concepts. I develop machine learning models that not only produce State-of-the-results on benchmark datasets but also allow robots to learn new objects and scenes in unconstrained environments which lead to a variety of novel robotics applications.

Original languageEnglish (US)
Title of host publicationHRI 2021 - Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction
PublisherIEEE Computer Society
Pages610-612
Number of pages3
ISBN (Electronic)9781450382908
DOIs
StatePublished - Mar 8 2021
Event2021 ACM/IEEE International Conference on Human-Robot Interaction, HRI 2021 - Virtual, Online, United States
Duration: Mar 8 2021Mar 11 2021

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
ISSN (Electronic)2167-2148

Conference

Conference2021 ACM/IEEE International Conference on Human-Robot Interaction, HRI 2021
CountryUnited States
CityVirtual, Online
Period3/8/213/11/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Continual learning of visual concepts for robots through limited supervision'. Together they form a unique fingerprint.

Cite this