Invariant Feature Mappings for Generalizing Affordance Understanding Using Regularized Metric Learning

TL;DR

This paper introduces a metric learning approach to develop invariant features for object affordance understanding, enabling robots to better interpret and manipulate objects by focusing on relevant sensory features.

Contribution

It proposes a regularized metric learning method that identifies features responsible for affordances, improving generalization and transfer learning in robotic perception.

Findings

Learned feature transforms cluster objects with similar affordances

Regularization reduces irrelevant feature influence

Enhanced affordance abstraction and reasoning capabilities

Abstract

This paper presents an approach for learning invariant features for object affordance understanding. One of the major problems for a robotic agent acquiring a deeper understanding of affordances is finding sensory-grounded semantics. Being able to understand what in the representation of an object makes the object afford an action opens up for more efficient manipulation, interchange of objects that visually might not be similar, transfer learning, and robot to human communication. Our approach uses a metric learning algorithm that learns a feature transform that encourages objects that affords the same action to be close in the feature space. We regularize the learning, such that we penalize irrelevant features, allowing the agent to link what in the sensory input caused the object to afford the action. From this, we show how the agent can abstract the affordance and reason about the similarity between different affordances.