A Logic-Based Computational Framework for Inferring Cognitive Affordances

The concept of "affordance" refers to the relationship between human perceivers and aspects of their environment. Being able to infer affordances is central to commonsense reasoning, tool use and creative problem solving in artificial agents. Existing approaches to inferring affordances have focused on functional aspects, relying on either static ontologies or statistical formalisms to extract relationships between physical features of objects, actions, and the corresponding effects of their interaction. These approaches do not provide flexibility with which to reason about affordances in the open world, where affordances are influenced by changing context, social norms, historical precedence, and uncertainty. We develop a computational framework comprising a probabilistic rules-based logical representation coupled with a computational architecture (cognitive affordances logically expressed) to reason about affordances in a more general manner than described in the existing literature. Our computational architecture allows robotic agents to make deductive and abductive inferences about functional and social affordances, collectively and dynamically, thereby allowing the agent to adapt to changing conditions. We demonstrate our approach with experiments, and show that an agent can successfully reason through situations that involve a tight interplay between various social and functional norms.