A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning

Due to the obvious randomness, pedestrian crossing behavior is hard to predict, which challenges the decision-making of autonomous vehicles (AVs). Recent solutions have been able to adapt to structured road scenes with crossing signals or markings. However, there is still a gap in extending the pede...

Full description

Saved in:
Bibliographic Details
Main Authors: Qing-Feng Lin, Heng-Yu Xue, Yang Lyu, Qing-Kun Li, Ju-Shang Ou
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10985827/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255715656007680
author Qing-Feng Lin
Heng-Yu Xue
Yang Lyu
Qing-Kun Li
Ju-Shang Ou
author_facet Qing-Feng Lin
Heng-Yu Xue
Yang Lyu
Qing-Kun Li
Ju-Shang Ou
author_sort Qing-Feng Lin
collection DOAJ
description Due to the obvious randomness, pedestrian crossing behavior is hard to predict, which challenges the decision-making of autonomous vehicles (AVs). Recent solutions have been able to adapt to structured road scenes with crossing signals or markings. However, there is still a gap in extending the pedestrian-vehicle interaction (PVI) performance in structured road scenes to unstructured road scenes. Therefore, this paper proposed a vehicle decision-making model considering pedestrian intention based on game theory and reinforcement learning (RL). We designed and conducted a simulation experiment based on a virtual reality platform. Then, leveraging game theory, we established a pedestrian crossing decision-making model considering pedestrian heterogeneity evoked by time pressure (TP). A reward function was developed to enhance driving performance by combining safety, efficiency, and comfort. The RL agent of AVs learns to control the vehicle speed in a pattern that maximizes cumulative rewards through trials and errors by interacting with pedestrians in the simulation environment. The results show that AVs can effectively and safely interact with heterogeneous pedestrians on unstructured roads based on the proposed model. This study contributes to developing AVs that interact better with pedestrians and improve traffic safety, efficiency, and user acceptance of autonomous vehicles.
format Article
id doaj-art-a3c4ecdb478a49c8a25e4f100c8c0e36
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a3c4ecdb478a49c8a25e4f100c8c0e362025-08-20T01:56:48ZengIEEEIEEE Access2169-35362025-01-0113877308773910.1109/ACCESS.2025.356673610985827A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement LearningQing-Feng Lin0https://orcid.org/0000-0003-2929-4754Heng-Yu Xue1Yang Lyu2Qing-Kun Li3https://orcid.org/0000-0002-1082-0630Ju-Shang Ou4School of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaAutomotive Software Innovation Center (Chongqing), Chongqing, ChinaIntelligent Policing Key Laboratory of Sichuan Province, Luzhou, ChinaDue to the obvious randomness, pedestrian crossing behavior is hard to predict, which challenges the decision-making of autonomous vehicles (AVs). Recent solutions have been able to adapt to structured road scenes with crossing signals or markings. However, there is still a gap in extending the pedestrian-vehicle interaction (PVI) performance in structured road scenes to unstructured road scenes. Therefore, this paper proposed a vehicle decision-making model considering pedestrian intention based on game theory and reinforcement learning (RL). We designed and conducted a simulation experiment based on a virtual reality platform. Then, leveraging game theory, we established a pedestrian crossing decision-making model considering pedestrian heterogeneity evoked by time pressure (TP). A reward function was developed to enhance driving performance by combining safety, efficiency, and comfort. The RL agent of AVs learns to control the vehicle speed in a pattern that maximizes cumulative rewards through trials and errors by interacting with pedestrians in the simulation environment. The results show that AVs can effectively and safely interact with heterogeneous pedestrians on unstructured roads based on the proposed model. This study contributes to developing AVs that interact better with pedestrians and improve traffic safety, efficiency, and user acceptance of autonomous vehicles.https://ieeexplore.ieee.org/document/10985827/Autonomous vehicledecision-makingpedestrian-vehicle interactiontime pressureunstructured roads
spellingShingle Qing-Feng Lin
Heng-Yu Xue
Yang Lyu
Qing-Kun Li
Ju-Shang Ou
A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
IEEE Access
Autonomous vehicle
decision-making
pedestrian-vehicle interaction
time pressure
unstructured roads
title A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
title_full A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
title_fullStr A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
title_full_unstemmed A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
title_short A Decision-Making Model for Autonomous Vehicles Considering Pedestrian’s Time Pressure Based on Game Theory and Reinforcement Learning
title_sort decision making model for autonomous vehicles considering pedestrian x2019 s time pressure based on game theory and reinforcement learning
topic Autonomous vehicle
decision-making
pedestrian-vehicle interaction
time pressure
unstructured roads
url https://ieeexplore.ieee.org/document/10985827/
work_keys_str_mv AT qingfenglin adecisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT hengyuxue adecisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT yanglyu adecisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT qingkunli adecisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT jushangou adecisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT qingfenglin decisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT hengyuxue decisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT yanglyu decisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT qingkunli decisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning
AT jushangou decisionmakingmodelforautonomousvehiclesconsideringpedestrianx2019stimepressurebasedongametheoryandreinforcementlearning