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

TL;DR

This paper introduces a cognitively inspired framework for class-incremental learning in robotics, enabling robots to learn new object classes with limited data while retaining previous knowledge, achieving state-of-the-art results.

Contribution

A novel hippocampus-inspired model that uses cluster-based memory replay to prevent forgetting in few-shot class-incremental learning for robotics.

Findings

Achieved state-of-the-art performance on object classification datasets.

Successfully demonstrated continual learning on a robot with limited supervision.

Effectively prevents forgetting during incremental learning.

Abstract

For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class 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 datasets 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.