Incremental Robot Learning of New Objects with Fixed Update Time

TL;DR

This paper introduces an incremental learning algorithm for robotic object recognition that efficiently incorporates new classes over time, handling class imbalance and maintaining high accuracy with faster updates.

Contribution

It presents a novel incremental RLSC algorithm tailored for lifelong learning in robotics, capable of adding new object classes seamlessly and efficiently.

Findings

Achieves comparable or better accuracy than batch methods on benchmarks.

Handles class imbalance effectively during incremental learning.

Significantly reduces update time compared to traditional approaches.

Abstract

We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC) algorithm, and exploit its structure to seamlessly add new classes to the learned model. The presented algorithm addresses the problem of having an unbalanced proportion of training examples per class, which occurs when new objects are presented to the system for the first time. We evaluate our algorithm on both a machine learning benchmark dataset and two challenging object recognition tasks in a robotic setting. Empirical evidence shows that our approach achieves comparable or higher classification performance than its batch counterpart when classes are unbalanced, while being significantly faster.