Incremental Object Recognition in Robotics with Extension to New Classes in Constant Time

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 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 a challenging object recognition task in a robotic setting. Empirical evidence on both problems shows that our approach is significantly faster than its batch counterparts while achieving comparable or better classification performance when classes are unbalanced.