Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning
Autonomous Intersection Management (AIM) for high-level Connected and Automated Vehicles (CAVs) has evolved from rule-based to optimisation-based policies. However, at congested major-minor intersections, optimising solely for efficiency can negatively impact vehicle fairness. This study addresses t...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/171244 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-171244 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1712442023-10-17T08:48:33Z Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning Wu, Yuanyuan Wang, David Zhi Wei Zhu, Feng School of Civil and Environmental Engineering Joint NTU-WeBank Research Centre on Fintech Engineering::Civil engineering Fairness Autonomous Intersection Management Autonomous Intersection Management (AIM) for high-level Connected and Automated Vehicles (CAVs) has evolved from rule-based to optimisation-based policies. However, at congested major-minor intersections, optimising solely for efficiency can negatively impact vehicle fairness. This study addresses this issue by proposing a deep reinforcement learning approach that optimises both traffic efficiency and fairness for AIM. In the modelled multi-objective Markov decision process, traffic fairness is measured by the difference between the crossing order and the approaching order of CAVs, while traffic efficiency is measured by average travel time. With unknown preferences of the objectives, Bellman optimality equation is generalised to obtain the optimal policies over the space of all possible preferences during the iterative training process. The effectiveness of the proposed method is evaluated in a simulated real-world intersection and compared with three benchmark policies, including the fairest policy for AIM: first-come-first-served. The learned policies perform best in reducing overall average vehicle delay, and demonstrate outstanding performance in balancing traffic fairness and efficiency. Ministry of Education (MOE) National Research Foundation (NRF) This study is supported by Singapore Ministry of Education Academic Research Fund [grant number Tier 1 RG79/21], and in part, by the National Research Foundation, Singapore under its AI Singapore Programme [AISG award number AISG2-RP-2020-019]. 2023-10-17T08:48:33Z 2023-10-17T08:48:33Z 2023 Journal Article Wu, Y., Wang, D. Z. W. & Zhu, F. (2023). Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning. Transportmetrica A: Transport Science. https://dx.doi.org/10.1080/23249935.2023.2232047 2324-9935 https://hdl.handle.net/10356/171244 10.1080/23249935.2023.2232047 2-s2.0-85165492991 en RG79/21 AISG2-RP-2020-019 Transportmetrica A: Transport Science © 2023 Hong Kong Society for Transportation Studies Limited. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Civil engineering Fairness Autonomous Intersection Management |
spellingShingle |
Engineering::Civil engineering Fairness Autonomous Intersection Management Wu, Yuanyuan Wang, David Zhi Wei Zhu, Feng Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
description |
Autonomous Intersection Management (AIM) for high-level Connected and Automated Vehicles (CAVs) has evolved from rule-based to optimisation-based policies. However, at congested major-minor intersections, optimising solely for efficiency can negatively impact vehicle fairness. This study addresses this issue by proposing a deep reinforcement learning approach that optimises both traffic efficiency and fairness for AIM. In the modelled multi-objective Markov decision process, traffic fairness is measured by the difference between the crossing order and the approaching order of CAVs, while traffic efficiency is measured by average travel time. With unknown preferences of the objectives, Bellman optimality equation is generalised to obtain the optimal policies over the space of all possible preferences during the iterative training process. The effectiveness of the proposed method is evaluated in a simulated real-world intersection and compared with three benchmark policies, including the fairest policy for AIM: first-come-first-served. The learned policies perform best in reducing overall average vehicle delay, and demonstrate outstanding performance in balancing traffic fairness and efficiency. |
author2 |
School of Civil and Environmental Engineering |
author_facet |
School of Civil and Environmental Engineering Wu, Yuanyuan Wang, David Zhi Wei Zhu, Feng |
format |
Article |
author |
Wu, Yuanyuan Wang, David Zhi Wei Zhu, Feng |
author_sort |
Wu, Yuanyuan |
title |
Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
title_short |
Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
title_full |
Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
title_fullStr |
Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
title_full_unstemmed |
Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
title_sort |
traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/171244 |
_version_ |
1781793815813685248 |