The Task Force on Action and Perception is primarily concerned with the developmental processes involved in the emergence of representations of action and perception in humans and artificial agents in continual learning. These processes include action-perception cycle, active perception, continual sensory-motor learning, environmental-driven scaffolding, and intrinsic motivation. As the algorithms for learning single tasks in controlled environments are improving, new challenges have gained relevance. They include multi-task learning, multimodal sensorimotor learning and lifelong adaptation to injury, growth and ageing. Members of this task force are strongly motivated by behavioural and neural data and develop mathematical and computational models to improve robot performance and/or to attempt to unveil the underlying mechanisms that lead to continual adaptation to changing environment or embodiment and continual learning in open-ended environments. Members of this task force make extensive use of raw sensor data in multi-task robotic experiments.
The goals of this task force would be: