Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach
The longitudinal trajectory planning of connected and autonomous vehicle (CAV) has been widely studied in the literature to reduce travel time or fuel consumptions. The safety impact of CAV trajectory planning to the mixed traffic flow with both CAV and human-driven vehicle (HDV), however, is not we...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2021/6117890 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560610790866944 |
|---|---|
| author | Yanqiu Cheng Chenxi Chen Xianbiao Hu Kuanmin Chen Qing Tang Yang Song |
| author_facet | Yanqiu Cheng Chenxi Chen Xianbiao Hu Kuanmin Chen Qing Tang Yang Song |
| author_sort | Yanqiu Cheng |
| collection | DOAJ |
| description | The longitudinal trajectory planning of connected and autonomous vehicle (CAV) has been widely studied in the literature to reduce travel time or fuel consumptions. The safety impact of CAV trajectory planning to the mixed traffic flow with both CAV and human-driven vehicle (HDV), however, is not well understood yet. This study presents a reinforcement learning modeling approach, named Monte Carlo tree search-based autonomous vehicle safety algorithm, or MCTS-AVS, to optimize the safety of mixed traffic flow, on a one-lane roadway with signalized intersection control. Crash potential index (CPI) is defined to quantitively measure the safety performance of the mixed traffic flow. The CAV trajectory planning problem is firstly formulated as an optimization model; then, the solution procedure based on reinforcement learning is proposed. The tree-expansion determination module and rollout termination module are developed to identify and reduce the unnecessary tree expansion, so as to train the model more efficiently towards the desired direction. The case study results showed that the proposed algorithm was able to reduce the CPI by 76.56%, when compared with a benchmark model without any intelligence, and 12.08%, when compared with another benchmark model that the team developed earlier. These results demonstrated the satisfactory performance of the proposed algorithm in enhancing the safety of the mixed traffic flow. |
| format | Article |
| id | doaj-art-9684212d0284433a8e65bd88cda67d98 |
| institution | Kabale University |
| issn | 0197-6729 2042-3195 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-9684212d0284433a8e65bd88cda67d982025-02-03T01:27:05ZengWileyJournal of Advanced Transportation0197-67292042-31952021-01-01202110.1155/2021/61178906117890Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning ApproachYanqiu Cheng0Chenxi Chen1Xianbiao Hu2Kuanmin Chen3Qing Tang4Yang Song5Department of Traffic Engineering, College of Transportation Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaDepartment of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USADepartment of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USADepartment of Traffic Engineering, College of Transportation Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaDepartment of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USADepartment of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USAThe longitudinal trajectory planning of connected and autonomous vehicle (CAV) has been widely studied in the literature to reduce travel time or fuel consumptions. The safety impact of CAV trajectory planning to the mixed traffic flow with both CAV and human-driven vehicle (HDV), however, is not well understood yet. This study presents a reinforcement learning modeling approach, named Monte Carlo tree search-based autonomous vehicle safety algorithm, or MCTS-AVS, to optimize the safety of mixed traffic flow, on a one-lane roadway with signalized intersection control. Crash potential index (CPI) is defined to quantitively measure the safety performance of the mixed traffic flow. The CAV trajectory planning problem is firstly formulated as an optimization model; then, the solution procedure based on reinforcement learning is proposed. The tree-expansion determination module and rollout termination module are developed to identify and reduce the unnecessary tree expansion, so as to train the model more efficiently towards the desired direction. The case study results showed that the proposed algorithm was able to reduce the CPI by 76.56%, when compared with a benchmark model without any intelligence, and 12.08%, when compared with another benchmark model that the team developed earlier. These results demonstrated the satisfactory performance of the proposed algorithm in enhancing the safety of the mixed traffic flow.http://dx.doi.org/10.1155/2021/6117890 |
| spellingShingle | Yanqiu Cheng Chenxi Chen Xianbiao Hu Kuanmin Chen Qing Tang Yang Song Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach Journal of Advanced Transportation |
| title | Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach |
| title_full | Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach |
| title_fullStr | Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach |
| title_full_unstemmed | Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach |
| title_short | Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach |
| title_sort | enhancing mixed traffic flow safety via connected and autonomous vehicle trajectory planning with a reinforcement learning approach |
| url | http://dx.doi.org/10.1155/2021/6117890 |
| work_keys_str_mv | AT yanqiucheng enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach AT chenxichen enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach AT xianbiaohu enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach AT kuanminchen enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach AT qingtang enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach AT yangsong enhancingmixedtrafficflowsafetyviaconnectedandautonomousvehicletrajectoryplanningwithareinforcementlearningapproach |