EN
    您的位置: 首页 > 研究成果 > 研究论文
 
按时间查看




Car-following method based on inverse reinforcement learning for autonomous vehicle decision-making
作者 Hongbo Gao,Guanya Shi,Guotao Xie,Bo Cheng
出版年份 2018 引用
摘要
There are still some problems need to be solved though there are a lot of achievements in the fields of automatic driving. One of those problems is the difficulty of designing a car-following decision-making system for complex...展开全文
There are still some problems need to be solved though there are a lot of achievements in the fields of automatic driving. One of those problems is the difficulty of designing a car-following decision-making system for complex traffic conditions. In recent years, reinforcement learning shows the potential in solving sequential decision optimization problems. In this article, we establish the reward function R of each driver data based on the inverse reinforcement learning algorithm, and r visualization is carried out, and then driving characteristics and following strategies are analyzed. At last, we show the efficiency of the proposed method by simulation in a highway environment.收起全文

基于行星传动的双模混合动力履带车辆传动系统结构设计
作者 秦兆博,罗禹贡,解来卿,陈文强,李克强
出版年份 2018 引用
摘要
该文提出了一种具有双输出的混联式混合动力履带车辆的传动系统结构设计。该结构具有双输出轴分别连接左、右履带,通过与3排行星齿轮结构连接,可以实现两侧履带的精确独立控制,通过控制发动机工作状态,使车辆的运行效率最优,在充分保证直线行驶性能的同时...展开全文
该文提出了一种具有双输出的混联式混合动力履带车辆的传动系统结构设计。该结构具有双输出轴分别连接左、右履带,通过与3排行星齿轮结构连接,可以实现两侧履带的精确独立控制,通过控制发动机工作状态,使车辆的运行效率最优,在充分保证直线行驶性能的同时,增强行进中转向能力。相比于现有的复杂混合动力履带车辆传动系统,该设计可以省去转向机构,并提升系统综合运行能力。采用自动建模的方法对所有可行结构进行动力学分析,结合不同结构类型的特点确定双模结构组合方式。通过系统特性初筛、性能精细筛选得到满足设计要求的结构。通过动态规划算法对所选结构进行典型工况下的燃油经济性分析。仿真结果表明,得到的最优方案比目前常用的串联式混合动力履带推土机具有更优的直线行驶、转向行驶和燃油经济性能。收起全文

Double-layer speed optimization for reducing fuel consumption with vehicle-to-infrastructure communication
作者 Biao Xu,Xiaolong Chen ,Keqiang Li ,Manjiang Hu ,Yougang Bian,Qianwen Yu,Jianqiang Wang
出版年份 2018 引用
摘要
Speed profiles affect fuel economy tremendously, especially, when vehicles running on an urban road with numerous signalized intersections. To improve fuel economy, in this study, we propose a double-layer speed optimization met...展开全文
Speed profiles affect fuel economy tremendously, especially, when vehicles running on an urban road with numerous signalized intersections. To improve fuel economy, in this study, we propose a double-layer speed optimization method with real-time computation that considers traffic signal information collected via vehicle-to- infrastructure communication and traffic conditions. In the first layer, we use a Dijkstra algorithm to optimize the average eco-speed between adjacent intersections with full-horizon traffic signal information, and in the second layer, we use an optimal control method to plan a real-time speed profile with average speed constraints. We conduct numerous field tests using a test bed and an experimental vehicle platform. The test results demonstrate that by computing optimal solutions in real time, the proposed double-layer speed optimization method has the potential to improve fuel economy and decrease trip time.收起全文

Distributed conflict-free cooperation for multiple connected vehicles at unsignalized intersections
作者 Biao Xu,Shengbo Eben Li,Yougang Bian,Shen Li,Xuegang Jeff Ban,Jianqiang Wang,Keqiang Li
出版年份 2018 引用
摘要
Connected vehicles will change the modes of future transportation management and organization, especially at intersections. In this paper, we propose a distributed conflict-free cooperation method for multiple connected vehicles at ...展开全文
Connected vehicles will change the modes of future transportation management and organization, especially at intersections. In this paper, we propose a distributed conflict-free cooperation method for multiple connected vehicles at unsignalized intersections. We firstly project the approaching vehicles from different traffic movements into a virtual lane and introduce a conflict-free geometry topology considering the conflict relationship of involved vehicles, thus constructing a virtual platoon. Then we present the modeling of communication topology to describe two modes of information transmission between vehicles. Finally, a distributed controller is designed to stabilize the virtual platoon for conflict-free cooperation at intersections. Numerical simulations validate the effectiveness of this method.收起全文

Cooperative Method of Traffic Signal Optimization and Speed Control of Connected Vehicles at Isolated Intersections
作者 Biao Xu,Xuegang Jeff Ban,Yougang Bian,Wan Li,Jianqiang Wang,Shengbo Eben Li
出版年份 2018 引用
摘要
Signalized intersections play an important role in transportation efficiency and vehicle fuel economy in urban areas. This paper proposes a cooperative method of traffic signal control and vehicle speed optimization for connected auto...展开全文
Signalized intersections play an important role in transportation efficiency and vehicle fuel economy in urban areas. This paper proposes a cooperative method of traffic signal control and vehicle speed optimization for connected automated vehicles, which optimizes the traffic signal timing and vehicles' speed trajectories at the same time. The method consists of two levels, i.e., roadside traffic signal optimization and onboard vehicle speed control. The former calculates the optimal traffic signal timing and vehicles' arrival time to minimize the total travel time of all vehicles; the latter optimizes the engine power and brake force to minimize the fuel consumption of individual vehicles. The enumeration method and the pseudospectral method are applied in roadside and onboard optimization, respectively. Simulation studies are conducted to compare the proposed method with benchmark methods. The results show significant improvement of transportation efficiency and fuel economy by the cooperation method.收起全文

Maneuver Prediction and Planning for Automated and Connected Vehicles based on Interaction and Gaming Awareness under Uncertainty
作者 Manjiang Hu,Guotao Xie,Hongbo Gao,Dongpu Cao,Li Qiang
出版年份 2018 引用
摘要
The complex and mixed traffic environment makes it a challenge for the widespread use of automated and connected vehicles (ACVs). It is necessary for these systems to have a better understanding of the traffic environment includ...展开全文
The complex and mixed traffic environment makes it a challenge for the widespread use of automated and connected vehicles (ACVs). It is necessary for these systems to have a better understanding of the traffic environment including interaction and gaming between multiple vehicles. In this study, a maneuver prediction and planning framework is proposed on the basis of game theories for complex and mixed traffic scenarios via Vehicle-to-Everything (V2X) communication. In this framework, the interaction and gaming between multiple vehicles are considered by employing the extensive form game theories. In the payoff function, the risk assessment model based on trajectory prediction under uncertainty is employed to assess collision risks. Driving efficiency and preference are also combined in the payoff function. Uncertainty elements, including estimation and prediction, are considered to predict and plan by using Nash equilibrium of the extensive form game theory in mixed and behavioral strategies.Finally,this framework is applied and proved in different lane-changes cenarios.There sults show that this framework could predict other vehicles’ driving maneuvers and plan maneuvers for ego vehicles by considering interaction and gaming between multiple vehicles, which helps ACVs understand the environment better and make the cooperative maneuver planning in complex traffic scenarios.收起全文

The Technology of Intelligent Driving Visual Perception Based on Driving Brain
作者 Xinyu Zhang,Hongbo Gao,Guotao Xie,Buyun Gao,Deyi Li
出版年份 2018 引用
摘要

A Driving Behavior Awareness Model based on a Dynamic Bayesian Network and Distributed Genetic Algorithm
作者 Guotao Xie,Hongbo Gao,Bin Huang,Lijun Qian,Jianqiang Wang
出版年份 2018 引用
摘要
It is necessary for automated vehicles (AVs) and advanced driver assistance systems (ADASs) to have a better understanding of the traffic environment including driving behaviors. This study aims to build a driving behavior aware...展开全文
It is necessary for automated vehicles (AVs) and advanced driver assistance systems (ADASs) to have a better understanding of the traffic environment including driving behaviors. This study aims to build a driving behavior awareness (DBA) model that can infer driving behaviors such as lane change. In this study, a dynamic Bayesian network DBA model is proposed, which includes three layers, namely, the observation, hidden and behavior layer. To enhance the performance of the DBA model, the network structure is optimized by employing a distributed genetic algorithm (GA). Using naturalistic driving data in Beijing, the comparison between the optimized model and other non-optimized models such as the hidden Markov model (HMM) and HMM with a mixture of Gaussian outputs (GM-HMM) indicates that the optimized model could estimate driving behaviors earlier and more accurately.收起全文



  Copyright © 2019 www.hive-hnu.org All rights reseved. 版权所有: 湖南大学智能车辆课题组HIVE
通讯地址: 湖南大学工程训练中心A栋 邮编:410082