Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Neuro-Dynamic Programming
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
IEEE Wireless Communications
The emerging applications of intelligent vehicular networks for traffic efficiency
Proceedings of the third ACM international symposium on Design and analysis of intelligent vehicular networks and applications
Hi-index | 0.00 |
This paper presents a preliminary study on controlling traffic signals using information collected via vehicle-to-infrastructure (V2I) communication. The key idea is to use vehicle speed and position as state variable, and construct a state-space presentation of the control problem. We propose dynamic programming and its derivative methods to solve the problem. An advantage of using speed and position as state variables is that difficulties of defining queue and estimating queue length at real-time are circumvented. Dynamic programming methods aim to optimise control performance successively at real-time. The method presented here is the first few that address the increasing possibility of adopting V2I for urban traffic management.