CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics

Ali Ayub, Alan R. Wagner

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this article, we consider the problem of few-shot incremental learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification data sets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.

Original languageEnglish (US)
Pages (from-to)2004-2013
Number of pages10
JournalIEEE Transactions on Cognitive and Developmental Systems
Volume15
Issue number4
DOIs
StatePublished - Dec 1 2023

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this