Object-centric Representations for Interactive Online Learning with Non-Parametric Methods

TL;DR

This paper introduces an object-centric representation for online learning in robotics, enabling robots to adaptively interact with unknown objects in unstructured environments by transforming actions into object coordinates.

Contribution

The paper presents a novel object-centric approach that improves online learning scalability and robustness in unstructured environments, addressing limitations of traditional Bayesian non-parametric models.

Findings

Successful navigation of a manipulator among multiple unknown objects

Enhanced reasoning with online-collected data in task-relevant space

Scalable online learning of robot-object interactions

Abstract

Large offline learning-based models have enabled robots to successfully interact with objects for a wide variety of tasks. However, these models rely on fairly consistent structured environments. For more unstructured environments, an online learning component is necessary to gather and estimate information about objects in the environment in order to successfully interact with them. Unfortunately, online learning methods like Bayesian non-parametric models struggle with changes in the environment, which is often the desired outcome of interaction-based tasks. We propose using an object-centric representation for interactive online learning. This representation is generated by transforming the robot's actions into the object's coordinate frame. We demonstrate how switching to this task-relevant space improves our ability to reason with the training data collected online, enabling scalable online learning of robot-object interactions. We showcase our method by successfully navigating a manipulator arm through an environment with multiple unknown objects without violating interaction-based constraints.