当前位置: X-MOL 学术J. Adv. Transp. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Multiobjective Cooperative Driving Framework Based on Evolutionary Algorithm and Multitask Learning
Journal of Advanced Transportation ( IF 2.0 ) Pub Date : 2022-01-21 , DOI: 10.1155/2022/6653598
Xia Jiang 1 , Jian Zhang 1, 2 , Qing-yang Li 1 , Tian-yi Chen 3
Affiliation  

The development of connected and automated vehicle (CAV) techniques brings an upcoming revolution to traffic management. The control of CAVs in potential conflict areas such as on-ramps and intersections will be complex to traffic management when considering their deployment. There is still a lack of a general framework for dispatching CAVs in these bottlenecks, which is expected to ensure safety, traffic efficiency, and energy consumption in real time. This study aimed to fill the technique gap, and a comprehensive cooperative intelligent driving framework is put forward to study the problem, which can be used in both on-ramp and intersection scenarios. Based on a multi-objective evolutionary algorithm, CAVs are denoted as a sequence to be searched in solution space, while a multitask learning neural network with adaptive loss function is implemented for optimization target feedback to surrogate the simulation test procedure. The simulation results show that the proposed framework can get satisfying performance with low time and energy consumption. It can reduce time consumption by up to 16.51% for the on-ramp scenario and 9.8% for the intersection scenario, while reducing energy consumption by up to 16.39% and 11.39% for the two scenarios. Meanwhile, an analysis of computation time is carried out, illuminating the flexibility and controllability of the new strategy.

中文翻译:

基于进化算法和多任务学习的多目标协同驱动框架

联网和自动驾驶汽车 (CAV) 技术的发展为交通管理带来了一场即将到来的革命。在考虑部署 CAV 时,在入口匝道和十字路口等潜在冲突区域的 CAV 控制对于交通管理来说将是复杂的。在这些瓶颈中仍然缺乏调度 CAV 的通用框架,该框架有望实时确保安全、交通效率和能源消耗。本研究旨在填补技术空白,提出了一个综合协作智能驾驶框架来研究该问题,该框架可用于匝道和交叉路口场景。基于多目标进化算法,CAVs 表示为在解空间中搜索的序列,同时实现了具有自适应损失函数的多任务学习神经网络,用于优化目标反馈,以替代模拟测试过程。仿真结果表明,所提出的框架可以在低时间和低能耗的情况下获得令人满意的性能。它可以在匝道场景下最多减少16.51%的时间消耗,在交叉路口场景下可以减少9.8%,同时在两种场景下最多可以减少16.39%和11.39%的能耗。同时,对计算时间进行了分析,阐明了新策略的灵活性和可控性。它可以在匝道场景下最多减少16.51%的时间消耗,在交叉路口场景下可以减少9.8%,同时在两种场景下最多可以减少16.39%和11.39%的能耗。同时,对计算时间进行了分析,阐明了新策略的灵活性和可控性。它可以在匝道场景下最多减少16.51%的时间消耗,在交叉路口场景下可以减少9.8%,同时在两种场景下最多可以减少16.39%和11.39%的能耗。同时,对计算时间进行了分析,阐明了新策略的灵活性和可控性。
更新日期:2022-01-21
down
wechat
bug