Velocity control in a right-turn across traffic scenario for autonomous vehicles using kernel-based reinforcement learning

Recently, advanced control methods like machine leaning are increasingly applied to autonomous vehicle. This paper focuses on velocity control in a right-turn traffic scenario. A Markov Decision Processes(MDPs) is modeled and the actor-critic reinforcement learning architecture is employed. Then the...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2017 Chinese Automation Congress (CAC) s. 6211 - 6216
Hlavní autoři:	Yuxiang Zhang, Bingzhao Gao, Lulu Guo, Hong Chen, Jinghua Zhao
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.10.2017
Témata:	autonomous vehicle kernel-based least squares policy iteration (KLSPI) reinforcement learning (RL) Systems modeling
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Recently, advanced control methods like machine leaning are increasingly applied to autonomous vehicle. This paper focuses on velocity control in a right-turn traffic scenario. A Markov Decision Processes(MDPs) is modeled and the actor-critic reinforcement learning architecture is employed. Then the kernel-based least squares policy iteration algorithm(KLSPI) is applied. Simulation results show that the proposed method can perform different policy in different cases, which preliminarily verify the rationality.
DOI:	10.1109/CAC.2017.8243896