Poor travel-time reliability, meaning that travel times for the same journey are highly variable and unpredictable, gives rise to similar negative impacts on the environment and the economy as does traffic congestion. Moreover, being able to offer a high degree of travel-time reliability will facilitate the uptake of sustainable road transportation including future public, shared, and on-demand mobility services, and on-time delivery of freight. Unpredictability arises partly from poor coordination between vehicles.
This project will explore the use of multi-agent reinforcement learning to enable automated vehicles to learn to coordinate their behaviours so as to harmonize traffic flow with the specific goal of offering highly predicable travel times.