Decentralized Traffic Flow Optimization Through Intrinsic Motivation

Traffic congestion has long been an ubiquitous problem which is exacerbating with the rapid growth of megacities. In this proof-of-concept work we study intrinsic motivations (specifically empowerment) to control autonomous car behavior to improve traffic flow. In standard models of traf- fic dynamics, self-organized traffic jams emerge spontaneously from the individual behavior of cars, affecting traffic over long distances. Our novel car behavior strategy improves traffic flow while still being decentralized and using only locally avail- able information without explicit coordination. Decentralization is essential for various reasons, not least to be able to absorb robustly substantial levels of uncertainty.
Our scenario is based on the well-established traffic dynamics model (Nagel-Schreckenberg cellular au- tomaton). In a fraction of the cars of this model, we substitute the default behavior by empowerment, our intrinsic motivation-based method. This pro- posed model significantly improves overall traffic flow, mitigates congestion, and reduces the average traffic jam time up to 67%.