Small Variance Asymptotics for Non-Parametric Online Robot Learning

TL;DR

This paper introduces SOSC, an online clustering algorithm based on small variance asymptotics for Bayesian non-parametric models, enabling scalable, adaptive robot manipulation learning and intention recognition in real-time.

Contribution

The paper develops a novel online sequence clustering algorithm that combines non-parametric mixture models with probabilistic PCA and HSMM, tailored for robot learning and manipulation tasks.

Findings

SOSC effectively clusters data online with adaptive, low-dimensional subspaces.

The model accurately recognizes operator intentions in teleoperation scenarios.

Experiments demonstrate successful online adaptation and assistance in robot manipulation.

Abstract

Small variance asymptotics is emerging as a useful technique for inference in large scale Bayesian non-parametric mixture models. This paper analyses the online learning of robot manipulation tasks with Bayesian non-parametric mixture models under small variance asymptotics. The analysis yields a scalable online sequence clustering (SOSC) algorithm that is non-parametric in the number of clusters and the subspace dimension of each cluster. SOSC groups the new datapoint in its low dimensional subspace by online inference in a non-parametric mixture of probabilistic principal component analyzers (MPPCA) based on Dirichlet process, and captures the state transition and state duration information online in a hidden semi-Markov model (HSMM) based on hierarchical Dirichlet process. A task-parameterized formulation of our approach autonomously adapts the model to changing environmental situations during manipulation. We apply the algorithm in a teleoperation setting to recognize the intention of the operator and remotely adjust the movement of the robot using the learned model. The generative model is used to synthesize both time-independent and time-dependent behaviours by relying on the principles of shared and autonomous control. Experiments with the Baxter robot yield parsimonious clusters that adapt online with new demonstrations and assist the operator in performing remote manipulation tasks.