Visual Affordance and Function Understanding: A Survey

TL;DR

This survey reviews current methods and challenges in visual affordance and function understanding for robots, emphasizing detection, segmentation, reasoning, and scene understanding in complex visual environments.

Contribution

It provides a comprehensive overview of the state of the art, open problems, and research gaps in visual affordance and functionality understanding for robotic applications.

Findings

Summarizes recent advances in affordance detection and segmentation.

Identifies key open problems and research gaps.

Highlights importance of functional scene understanding in robotics.

Abstract

Nowadays, robots are dominating the manufacturing, entertainment and healthcare industries. Robot vision aims to equip robots with the ability to discover information, understand it and interact with the environment. These capabilities require an agent to effectively understand object affordances and functionalities in complex visual domains. In this literature survey, we first focus on Visual affordances and summarize the state of the art as well as open problems and research gaps. Specifically, we discuss sub-problems such as affordance detection, categorization, segmentation and high-level reasoning. Furthermore, we cover functional scene understanding and the prevalent functional descriptors used in the literature. The survey also provides necessary background to the problem, sheds light on its significance and highlights the existing challenges for affordance and functionality learning.