Effective Learning of Social Affordances for HRI
Effective Learning of Social Affordances for HRI
Bilaterale Ausschreibung: Frankreich
Disciplines
Electrical Engineering, Electronics, Information Engineering (80%); Psychology (20%)
Keywords
-
Human-Robot Collaboration,
Machine Learning,
Planning,
Social Cognition,
Theory of Mind
Affordances are action opportunities directly perceived by an agent to interact with its environment. The concept is gaining interest in robotics, where it offers a rich description of the objects and the environment, focusing on the potential interactions rather than the sole physical properties. In this project we extend this notion to social affordances. The goal is for robots to autonomously learn not only the physical effects of interactive actions with humans, but also the humans` reactions they produce (emotion, speech, movement). For instance, pointing while gazing in the same direction makes humans orient towards the pointed direction, while pointing while looking at the finger makes humans look at the finger. Or, scratching the robot`s chin makes some but not all humans smile. The project will investigate how learning human-general and human-specific social affordances can enrich a robot`s action repertoire for human-aware task planning and efficient human-robot interaction.
- Universität Innsbruck - 100%
- Mehdi Khamassi, Sorbonne Université, international project partner
Research Output
- 1 Citations
- 1 Publications
-
2022
Title Editorial: Computational models of affordance for robotics DOI 10.3389/fnbot.2022.1045355 Type Journal Article Author Renaudo E Journal Frontiers in Neurorobotics Pages 1045355 Link Publication