Affordances describe the possibilities for an agent to perform actions with an object. While the sig- nificance of the affordance concept has been previ- ously studied from varied perspectives, such as psy- chology and cognitive science, these approaches are not always sufficient to enable direct transfer, in the sense of implementations, to artificial intel- ligence (AI)-based systems and robotics. However, many efforts have been made to pragmatically em- ploy the concept of affordances, as it represents great potential for AI agents to effectively bridge perception to action. In this survey, we review and find common ground amongst different strategies that use the concept of affordances within robotic tasks, and build on these methods to provide guid- ance for including affordances as a mechanism to improve autonomy. To this end, we outline com- mon design choices for building representations of affordance relations, and their implications on the generalisation capabilities of an agent when facing previously unseen scenarios. Finally, we identify and discuss a range of interesting research direc- tions involving affordances that have the potential to improve the capabilities of an AI agent.
|Title of host publication||Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21)|
|Publication status||Published - 19 Aug 2021|
|Event||30th International Joint Conference on Artificial Intelligence 2021 - Montreal-themed Virtual Reality, Montreal, Canada|
Duration: 19 Aug 2021 → 26 Aug 2021
|Conference||30th International Joint Conference on Artificial Intelligence 2021|
|Abbreviated title||IJCAI 2021|
|Period||19/08/21 → 26/08/21|