This study presents a three-lane highway overtaking strategy for an automated vehicle, which is based on a heuristic planning reinforcement learning algorithm. The proposed decision-making controller focuses on keeping the autonomous vehicle operating safely and efficiently. First, the modelling of the overtaking driving scenario is introduced and the reference approaches named intelligent driver model and minimise overall braking induced by lane changes are formulated. Second, the Dyna-H algorithm, which combines the modified Q-learning algorithm with a heuristic planning policy, is utilised for highway overtaking decision-making. Three different heuristic strategies are formulated to improve learning efficiency and compare performance. This algorithm is applied to determine the lane change and speed selection for an ego vehicle in the environment with uncertainties. Finally, the performance of Dyna-H is estimated in the autonomous overtaking scenario by comparing it with the reference and traditional learning methods. Furthermore, the Dyna-H-enabled decision-making strategies are validated and analysed in an open-sourcing driving dataset. Results prove that the proposed decision-making strategy could produce superior performance in convergence rate and control.
Heuristics-oriented overtaking decision making for autonomous vehicles using reinforcement learning
IET Electrical Systems in Transportation ; 10 , 4 ; 417-424
2020-11-13
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
learning efficiency , modified Q-learning algorithm , learning (artificial intelligence) , automated vehicle , intelligent driver model , Dyna-H-enabled decision-making strategies , decision-making controller , decision making , mobile robots , three-lane highway , road traffic , ego vehicle , lane changes , driver information systems , heuristic planning policy , minimise overall braking , road safety , road vehicles , autonomous overtaking scenario , traditional learning methods , autonomous vehicle , heuristics-oriented , highway overtaking decision-making , different heuristic strategies , lane change , overtaking driving scenario , decision-making strategy , traffic engineering computing , speed selection , heuristic planning reinforcement learning algorithm
Metadata by IET is licensed under CC BY 3.0
SAGE Publications | 2022
|Automatic driving vehicle overtaking decision-making method based on deep reinforcement learning
Europäisches Patentamt | 2022
|High‐level decision‐making for autonomous overtaking: An MPC‐based switching control approach
Wiley | 2024
|