Learning to Act Properly: Predicting and Explaining Affordances from Images
This work addresses the challenge of teaching artificial agents to understand and reason about appropriate actions in diverse environments, which is incremental as it builds on existing datasets and methods.
The paper tackles the problem of affordance reasoning in real-world scenes by predicting and explaining action-object affordances from egocentric images, respecting both physical and social constraints, and introduces a new dataset ADE-Affordance and a Graph Neural Network model for this task.
We address the problem of affordance reasoning in diverse scenes that appear in the real world. Affordances relate the agent's actions to their effects when taken on the surrounding objects. In our work, we take the egocentric view of the scene, and aim to reason about action-object affordances that respect both the physical world as well as the social norms imposed by the society. We also aim to teach artificial agents why some actions should not be taken in certain situations, and what would likely happen if these actions would be taken. We collect a new dataset that builds upon ADE20k, referred to as ADE-Affordance, which contains annotations enabling such rich visual reasoning. We propose a model that exploits Graph Neural Networks to propagate contextual information from the scene in order to perform detailed affordance reasoning about each object. Our model is showcased through various ablation studies, pointing to successes and challenges in this complex task.