Decentralized control of connected automated vehicle trajectories in mixed traffic at an isolated signalized intersection

摘要

It is concerned that system-level benefits of connected automated vehicle control might only prevail in a far-future centralized control environment, whereas the benefits could be much offset in a near-future decentralized control system. To address this concern, this paper proposes a decentralized control model for connected automated vehicle trajectory optimization at an isolated signalized intersection with a single-lane road where each connected automated vehicle aims to minimize its own travel time, fuel consumption and safety risks. To improve the computational tractability, the original complex decentralized control model is reformulated into a discrete model. A benchmark centralized control model is also formulated to compare with the decentralized control model. The DIRECT algorithm is adopted to solve the above models. Numerical results show that the decentralized control model has better computational efficiency (with an average solution time of 10 s) than the centralized control model (with an average solution time of 60 s) without significant loss of the system optimality (with an average of 3.91%). Finally, analysis on connected automated vehicle market penetration shows that the extra benefit of the centralized control model is not obvious either in under-saturated traffic (less than 1%) or at a low connected automated vehicle market penetration rate in critically-saturated and oversaturated traffic (less than 3% when the market penetration rate is lower than 20%). The results suggest that, as apposed to the earlier concern, the near-future decentralized control scheme that requires less technology maturity and infrastructure investment can achieve benefits similar to the far-future centralized control scheme with much simpler operations in under-saturated traffic, or in critically-saturated traffic and over-saturated traffic with a low connected automated vehicle market penetration rate.