Dreaming mechanism for training bio-inspired driving agents
Publised on 5th International Conference on Intelligent Human Systems Integration, 2019, San Diego, CA, USA
This paper addresses one of the key ideas embraced by the European funded H2020 research project Dreams4Cars: to borrow resemblances from the way humans learn to drive. We developed an artiﬁ cial driving agent, called “Co-driver”, characterized by an architecture mimicking the fundamental components of the human brain involved in the learning of complex sensorimotor abilities, like driving. We implemented a dream-like mechanism to train and test the self-driving agent, and we will show two case studies demonstrating the effectiveness of such approach.