1,642 Hits in 10.3 sec

Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic [article]

Wei Zhou, Dong Chen, Jun Yan, Zhaojian Li, Huilin Yin, Wanchen Ge
2021 arXiv   pre-print
In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing  ...  Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios.  ...  The authors are grateful for the efforts of our colleagues in the Sino-German Center of Intelligent Systems, Tongji University. We are grateful for the suggestions on our manuscript from Dr. Qi Deng.  ... 
arXiv:2111.06318v1 fatcat:ucpkp2vy3jgw5idlqa6peohnam

Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic [article]

Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah
2021 arXiv   pre-print
We introduce a multi-agent variant of the synchronous Advantage Actor-Critic (A2C) algorithm and train agents that coordinate with each other and can affect the behavior of human drivers to improve traffic  ...  With the adoption of autonomous vehicles on our roads, we will witness a mixed-autonomy environment where autonomous and human-driven vehicles must learn to co-exist by sharing the same road infrastructure  ...  Multi-agent Advantage Actor-Critic As we discussed in Section 3, a major challenge in multiagent reinforcement learning is dealing with the set of learning agents that are evolving concurrently and therefore  ... 
arXiv:2107.05664v1 fatcat:2mr44i7y7fgfdkifcqyn3akusa

Efficient Connected and Automated Driving System with Multi-agent Graph Reinforcement Learning [article]

Tianyu Shi, Jiawei Wang, Yuankai Wu, Luis Miranda-Moreno, Lijun Sun
2021 arXiv   pre-print
Instead of learning a reliable behavior for ego automated vehicle, we focus on how to improve the outcomes of the total transportation system by allowing each automated vehicle to learn cooperation with  ...  Connected and automated vehicles (CAVs) have attracted more and more attention recently.  ...  In this paper, we address the CAV cooperation problem in mixed autonomy by incorporating Connected Automated Vehicle Graph (CAVG) into multi-agent reinforcement learning (MARL) to model the mutual interplay  ... 
arXiv:2007.02794v5 fatcat:6ybpqsfeendbnjipmcdp532llm

Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffic Environments [article]

Qi Liu, Zirui Li, Xueyuan Li, Jingda Wu, Shihua Yuan
2022 arXiv   pre-print
An efficient and reliable multi-agent decision-making system is highly demanded for the safe and efficient operation of connected autonomous vehicles in intelligent transportation systems.  ...  Results show that the implementation of GNN can well represents the interaction between vehicles, and the combination of GNN and DRL is able to improve the performance of the generation of lane-change  ...  In [11] , graph convolutional reinforcement learning method is proposed for multi-agent decision-making; two multi-head attention graph convolutional layers are utilized for features extraction of agents  ... 
arXiv:2201.12776v1 fatcat:enwmno3ufjd7dg2fhp3y7ymnl4

Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey [article]

Ammar Haydari, Yasin Yilmaz
2020 arXiv   pre-print
In this paper, the latest deep reinforcement learning (RL) based traffic control applications are surveyed.  ...  New data-driven approaches bring out a new research direction for all control-based systems, e.g., in transportation, robotics, IoT and power systems.  ...  Authors in [150] introduces a traffic simulator which provides a new environment with cooperative multi-agent learning approach for analyzing the behaviours of autonomous vehicles.  ... 
arXiv:2005.00935v1 fatcat:hkuxij7axncehbgwczxxfecqzm

Stable and Efficient Shapley Value-Based Reward Reallocation for Multi-Agent Reinforcement Learning of Autonomous Vehicles [article]

Songyang Han, He Wang, Sanbao Su, Yuanyuan Shi, Fei Miao
2022 arXiv   pre-print
process of physical systems and demonstrate prominent performance in a wide array of CPS domains, such as connected autonomous vehicles (CAVs).  ...  With the development of sensing and communication technologies in networked cyber-physical systems (CPSs), multi-agent reinforcement learning (MARL)-based methodologies are integrated into the control  ...  The environment can be mixed traffic with both autonomous and human-driven vehicles.  ... 
arXiv:2203.06333v2 fatcat:ll2awnnvkfayve7ddfjinqw5bi

Collaborative Autonomous Driving—A Survey of Solution Approaches and Future Challenges

Sumbal Malik, Manzoor Ahmed Khan, Hesham El-Sayed
2021 Sensors  
In this survey, we review the current solution approaches in cooperation for autonomous vehicles, based on various cooperative driving applications, i.e., smart car parking, lane change and merge, intersection  ...  Sooner than expected, roads will be populated with a plethora of connected and autonomous vehicles serving diverse mobility needs.  ...  [28] exploited reinforcement learning to implement the cooperative lane change approach for connected vehicles.  ... 
doi:10.3390/s21113783 pmid:34072603 fatcat:6ghmjdiguvclxgtub3nxf6icsq

Cooperative Multiagent Deep Deterministic Policy Gradient (CoMADDPG) for Intelligent Connected Transportation with Unsignalized Intersection

Tianhao Wu, Mingzhi Jiang, Lin Zhang
2020 Mathematical Problems in Engineering  
Thus, this paper proposes a Cooperative MADDPG (CoMADDPG) for connected vehicles at unsignalized intersection to solve this problem.  ...  Unsignalized intersection control is one of the most critical issues in intelligent transportation systems, which requires connected and automated vehicles to support more frequent information interaction  ...  Kim and Jeong proposed a cooperative traffic signal control scheme using traffic flow prediction for a multi-intersection [4] .  ... 
doi:10.1155/2020/1820527 fatcat:opkcxvn5vbhbfciytszlfmz7iy

A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning [article]

Xuan Di, Rongye Shi
2020 arXiv   pre-print
Models used for each phase are summarized, encompassing game theory, deep (reinforcement) learning, and imitation learning.  ...  It is the first-of-its-kind survey paper to comprehensively review literature in both transportation engineering and AI for mixed traffic modeling.  ...  This work is also partially supported by the National Science Foundation under award number CMMI-1943998 and Amazon AWS Machine Learning Research Award Gift (#US3085926).  ... 
arXiv:2007.05156v1 fatcat:6pr3en5opfguje77wpa4dwr6pi

Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios [article]

Bruno Brito, Achin Agarwal, Javier Alonso-Mora
2021 arXiv   pre-print
Autonomous navigation in dense traffic scenarios remains challenging for autonomous vehicles (AVs) because the intentions of other drivers are not directly observable and AVs have to deal with a wide range  ...  Hence, we propose to learn, via deep Reinforcement Learning (RL), an interaction-aware policy providing global guidance about the cooperativeness of other vehicles to an optimization-based planner ensuring  ...  Reinforcement Learning (RL) has shown great potential for autonomous driving in dense traffic scenarios [43] , [44] .  ... 
arXiv:2107.04538v1 fatcat:j7iuudg3ufey7pxwoz43np2hry

Flow: A Modular Learning Framework for Autonomy in Traffic [article]

Cathy Wu, Aboudy Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre M Bayen
2020 arXiv   pre-print
The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility.  ...  This article tackles technical challenges arising from the partial adoption of autonomy: partial control, partial observation, complex multi-vehicle interactions, and the sheer variety of traffic settings  ...  ACKNOWLEDGMENTS The authors would like to thank Professor Alexander Skabardonis for insightful discussions about vehicle dynamics; Leah Dickstein and Nathan Mandi for early prototyping; Nishant Kheterpal  ... 
arXiv:1710.05465v3 fatcat:kds7eowu5rhzziz7zzlc3xfhdi

Social Coordination and Altruism in Autonomous Driving [article]

Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah
2022 arXiv   pre-print
multi-agent reinforcement learning framework.  ...  Despite the advances in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehicles operated by humans  ...  Multi-agent Reinforcement Learning. Early solutions for multi-agent value-learning algorithms assume independently trained agents and are proved to perform poorly [7] .  ... 
arXiv:2107.00200v4 fatcat:tefw5v7dqvfh7ebdjghnaakzh4

Theory and Experiment of Cooperative Control at Multi-Intersections in Intelligent Connected Vehicle Environment: Review and Perspectives

Linan Zhang, Yizhe Wang, Huaizhong Zhu
2022 Sustainability  
under different conditions, the research examined driving modes of regular vehicles and intelligent connected vehicles, including car following and lane changing.  ...  control mechanism and multi-intersection coordinated control strategy for intelligent connected vehicle heterogeneous traffic flow.  ...  Liang X [58] proposed a deep reinforcement learning model for traffic signal control in a connected vehicle environment.  ... 
doi:10.3390/su14031542 fatcat:byylecdzbfayve3lleqbid2nq4

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic [article]

Dong Chen, Zhaojian Li, Mohammad Hajidavalloo, Kaian Chen, Yongqiang Wang, Longsheng Jiang, Yue Wang
2022 arXiv   pre-print
In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively  ...  On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs).  ...  Multi-agent Reinforcement Learning (MARL) MARL has found great successes across a wide range of multi-agent systems, including traffic light control [25] , games [26] , resource management in wireless  ... 
arXiv:2105.05701v2 fatcat:n4uu24qp2va6zbau542gdkwzj4

Cooperative Autonomous Vehicles that Sympathize with Human Drivers [article]

Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah
2021 arXiv   pre-print
) paradigm trains altruistic agents that realize safe and smooth traffic flow in competitive driving scenarios only from experiential learning and without any explicit coordination.  ...  In contrast with existing works that explicitly model the behavior of human drivers and rely on their expected response to create opportunities for cooperation, our Sympathetic Cooperative Driving (SymCoDrive  ...  RELATED WORK Multi-agent Reinforcement Learning. A major challenge for multi-agent reinforcement learning (MARL) is the in-herent non-stationarity of the environment.  ... 
arXiv:2107.00898v1 fatcat:diskrjyt25bhzfq3hcvkdguehe
« Previous Showing results 1 — 15 out of 1,642 results