The SENSOPAC project combined machine learning techniques and modelling of biological systems to develop a machine capable of abstracting cognitive notions from sensorimotor relationships during interactions with its environment, and of generalising this knowledge to novel situations.
Through active sensing and exploratory actions the machine discovers the sensorimotor relationships and consequently learn the intrinsic structure of its interactions with the world and unravel predictive and causal relationships.
The project has demonstrated how a robotic system can bootstrap its development by constructing generalisation and discovering sensor-based abstractions, based on neuroscience findings on tactile sensory data representation and processing.
