The SENSOPAC project will combine machine learning techniques and modeling 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. The machine through active sensing and exploratory actions will discover the sensorimotor relationships and consequently learn the intrinsic structure of its interactions with the world and unravel predictive and causal relationships.
Together with action policy formulation and decision making, this will underlie the machine's abilities to create abstractions, to suggest and test hypotheses, and develop self-awareness. Detailed neural models of key brain areas will be embedded into functional models of perception, motivation, decision making, planning and control, effectively bridging and contributing to Neuroscience and Engineering. The project will demonstrate how a naive system can bootstrap its cognitive development by constructing generalization and discovering abstractions with which it can conceptualize its environment and its ownself.
The continuous developmental approach will combine self-supervised and reinforcement learning with motivational drives to form a truly autonomous artificial system. A systematic and integrated approach to studying active sensing and motor control in animals in a hierarchy of defined tasks will offer insights into skilled behaviour that will lead to fruitful applications of bio-inspired mechanisms for perception, cognition and intelligent control. The project relies on the synergy between multiple scientific institutions including a SME, an industrial and RTD partners who are leaders in their fields. Throughout the project, continuous interactions between experimentalists, theoreticians, engineers and roboticists will take place in order to coordinate the most rigorous development and testing of a complete artificial cognitive system.
Funding SchemeIP - Integrated Project
52900 Ramat Gan
221 00 Lund
EH8 9YL Edinburgh
901 87 Umea
75252 Paris Cedex 05