Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach
Several issues in designing a vehicle platoon control system must be considered; among them, the speed consensus and space/gap regulation between the vehicles play the primary role. In addition, reliable and fast gap-closing/opening actions are highly recommended for establishing a platoon system. N...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Future Transportation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-7590/2/4/57 |
| _version_ | 1797458106526990336 |
|---|---|
| author | Mehran Berahman Majid Rostami-Shahrbabaki Klaus Bogenberger |
| author_facet | Mehran Berahman Majid Rostami-Shahrbabaki Klaus Bogenberger |
| author_sort | Mehran Berahman |
| collection | DOAJ |
| description | Several issues in designing a vehicle platoon control system must be considered; among them, the speed consensus and space/gap regulation between the vehicles play the primary role. In addition, reliable and fast gap-closing/opening actions are highly recommended for establishing a platoon system. Nonetheless, the lack of research on designing a single algorithm capable of simultaneously coping with speed-tracking and maintaining a secure headway, as well as the gap-closing/opening problems, is apparent. As deep reinforcement learning (DRL) applications in driving strategies are promising, this paper develops a multi-task deep deterministic policy gradient (DDPG) car-following algorithm in a platoon system. The proposed approach combines gap closing/opening with a unified platoon control strategy; as such, an effective virtual inter-vehicle distance is employed in the developed DRL-based platoon controller reward. This innovative new distance definition, which is based on the action taken by the ego-vehicle, leads to a precise comprehension of the agent’s actions. Moreover, by imposing a specific constraint on a variation of the ego-vehicle’s relative speed with respect to its predecessor, the speed chattering of the ego-vehicle is reduced. The developed algorithm is implemented in the realistic traffic simulator, SUMO (Simulation of Urban Mobility), and the performance of the developed control strategy is evaluated under different traffic scenarios. |
| first_indexed | 2024-03-09T16:33:21Z |
| format | Article |
| id | doaj.art-70d7c1d324124af6be9615490823e013 |
| institution | Directory Open Access Journal |
| issn | 2673-7590 |
| language | English |
| last_indexed | 2024-03-09T16:33:21Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Transportation |
| spelling | doaj.art-70d7c1d324124af6be9615490823e0132023-11-24T14:59:28ZengMDPI AGFuture Transportation2673-75902022-12-01241028104610.3390/futuretransp2040057Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient ApproachMehran Berahman0Majid Rostami-Shahrbabaki1Klaus Bogenberger2Department of Electrical and Computer Engineering, Shiraz University, Shiraz 51154-71348, IranChair of Traffic Engineering and Control, Technical University of Munich, 80333 Munich, GermanyChair of Traffic Engineering and Control, Technical University of Munich, 80333 Munich, GermanySeveral issues in designing a vehicle platoon control system must be considered; among them, the speed consensus and space/gap regulation between the vehicles play the primary role. In addition, reliable and fast gap-closing/opening actions are highly recommended for establishing a platoon system. Nonetheless, the lack of research on designing a single algorithm capable of simultaneously coping with speed-tracking and maintaining a secure headway, as well as the gap-closing/opening problems, is apparent. As deep reinforcement learning (DRL) applications in driving strategies are promising, this paper develops a multi-task deep deterministic policy gradient (DDPG) car-following algorithm in a platoon system. The proposed approach combines gap closing/opening with a unified platoon control strategy; as such, an effective virtual inter-vehicle distance is employed in the developed DRL-based platoon controller reward. This innovative new distance definition, which is based on the action taken by the ego-vehicle, leads to a precise comprehension of the agent’s actions. Moreover, by imposing a specific constraint on a variation of the ego-vehicle’s relative speed with respect to its predecessor, the speed chattering of the ego-vehicle is reduced. The developed algorithm is implemented in the realistic traffic simulator, SUMO (Simulation of Urban Mobility), and the performance of the developed control strategy is evaluated under different traffic scenarios.https://www.mdpi.com/2673-7590/2/4/57deep reinforcement learningdeep deterministic policy gradientconnected and automated vehiclesvehicular platooneffective inter-vehicle distance |
| spellingShingle | Mehran Berahman Majid Rostami-Shahrbabaki Klaus Bogenberger Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach Future Transportation deep reinforcement learning deep deterministic policy gradient connected and automated vehicles vehicular platoon effective inter-vehicle distance |
| title | Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach |
| title_full | Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach |
| title_fullStr | Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach |
| title_full_unstemmed | Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach |
| title_short | Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach |
| title_sort | multi task vehicle platoon control a deep deterministic policy gradient approach |
| topic | deep reinforcement learning deep deterministic policy gradient connected and automated vehicles vehicular platoon effective inter-vehicle distance |
| url | https://www.mdpi.com/2673-7590/2/4/57 |
| work_keys_str_mv | AT mehranberahman multitaskvehicleplatooncontroladeepdeterministicpolicygradientapproach AT majidrostamishahrbabaki multitaskvehicleplatooncontroladeepdeterministicpolicygradientapproach AT klausbogenberger multitaskvehicleplatooncontroladeepdeterministicpolicygradientapproach |