Predictive trajectory planning for autonomous vehicles at intersections using reinforcement learning

In this work the authors put forward a predictive trajectory planning framework to help autonomous vehicles plan future trajectories. The authors develop a partially observable Markov decision process (POMDP) to model this sequential decision making problem, and a deep reinforcement learning solution methodology to learn high-quality policies. The POMDP model utilizes driving scenarios, condensed into graphs, as inputs. More specifically, an input graph contains information on the history trajectory of the subject vehicle, predicted trajectories of other agents in the scene (e.g., other vehicles, pedestrians, and cyclists), as well as predicted risk levels posed by surrounding vehicles to devise safe, comfortable, and energy-efficient trajectories for the subject vehicle to follow. In order to obtain sufficient driving scenarios to use as training data, the authors propose a simulation framework to generate socially acceptable driving scenarios using a real world autonomous vehicle dataset. The simulation framework utilizes Bayesian Gaussian mixture models to learn trajectory patterns of different agent types, and Gibbs sampling to ensure that the distribution of simulated scenarios matches that of the real-world dataset collected by an autonomous fleet. The authors evaluate the proposed work in two complex urban driving environments: a non-signalized T-junction and a non-signalized lane merge intersection. Both environments provide vastly more complex driving scenarios compared to a highway driving environment, which has been mostly the focus of previous studies. The framework demonstrates promising performance for planning horizons as long as five seconds. The authors compare safety, comfort, and energy efficiency of the planned trajectories against human-driven trajectories in both experimental driving environments, and demonstrate that it outperforms human-driven trajectories in a statistically significant fashion in all aspects.

• Record URL:
  https://doi.org/10.1016/j.trc.2023.104063
• Record URL:
  http://www.sciencedirect.com/science/article/pii/S0968090X23000529
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/0968090X
• Supplemental Notes:
  • © 2023 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Zhang, Ethan
  • 0000-0003-3249-0617
  • Zhang, Ruixuan
  • 0000-0002-9638-4883
  • Masoud, Neda
  • 0000-0002-6526-3317
• Publication Date: 2023-4

Language

• English

Media Info

• Media Type: Web
• Features: Appendices; Figures; References; Tables;
• Pagination: 104063
• Serial:
  • Transportation Research Part C: Emerging Technologies
  • Volume: 149
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0968-090X
  • Serial URL: http://www.sciencedirect.com/science/journal/0968090X

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Comfort; Complex systems; Energy consumption; Machine learning; Merging area; Multi-agent systems; Traffic safety; Trajectory control; Unsignalized intersections
• Subject Areas: Data and Information Technology; Energy; Highways; Operations and Traffic Management; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01878896
• Record Type: Publication
• Files: TRIS
• Created Date: Apr 10 2023 11:58AM