Self-Explainable Affordance Learning with Embodied Caption

TL;DR

This paper introduces a self-explainable affordance learning method with embodied captions, enabling robots to articulate intentions and improve understanding of action possibilities in complex scenes.

Contribution

It presents a novel model combining affordance grounding with self-explanation, along with a new dataset and metrics for visual affordance learning with language explanations.

Findings

Effective in bridging vision and language for affordance understanding

Improves robot explanation capabilities in complex scenes

Demonstrates superior performance through extensive experiments

Abstract

In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks. However, they encounter a main challenge of action ambiguity, illustrated by the vagueness like whether to beat or carry a drum, and the complexities involved in processing intricate scenes. Moreover, it is important for human intervention to rectify robot errors in time. To address these issues, we introduce Self-Explainable Affordance learning (SEA) with embodied caption. This innovation enables robots to articulate their intentions and bridge the gap between explainable vision-language caption and visual affordance learning. Due to a lack of appropriate dataset, we unveil a pioneering dataset and metrics tailored for this task, which integrates images, heatmaps, and embodied captions. Furthermore, we propose a novel model to effectively combine affordance grounding with self-explanation in a simple but efficient manner. Extensive quantitative and qualitative experiments demonstrate our method's effectiveness.