Learning Affordances from Interactive Exploration using an Object-level Map

TL;DR

This paper presents a method for robots to learn object affordances through interactive exploration by integrating an object-level map, leading to more accurate and efficient affordance prediction models in unknown environments.

Contribution

The paper introduces an interactive exploration pipeline with an object-level map that improves affordance learning accuracy and efficiency over existing methods.

Findings

Denser and more accurate affordance annotations achieved.

Enhanced exploration efficiency compared to baseline methods.

Improved accuracy of affordance prediction models.

Abstract

Many robotic tasks in real-world environments require physical interactions with an object such as pick up or push. For successful interactions, the robot needs to know the object's affordances, which are defined as the potential actions the robot can perform with the object. In order to learn a robot-specific affordance predictor, we propose an interactive exploration pipeline which allows the robot to collect interaction experiences while exploring an unknown environment. We integrate an object-level map in the exploration pipeline such that the robot can identify different object instances and track objects across diverse viewpoints. This results in denser and more accurate affordance annotations compared to state-of-the-art methods, which do not incorporate a map. We show that our affordance exploration approach makes exploration more efficient and results in more accurate affordance prediction models compared to baseline methods.