2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)最新文献_第10页

Optimization of Safety and Comfort in Car-following Scene Based on Reinforcement Learning 基于强化学习的汽车跟随场景安全性与舒适性优化

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661246

Yingbo Sun, Yuan Chu, Xuewu Ji

{"title":"Optimization of Safety and Comfort in Car-following Scene Based on Reinforcement Learning","authors":"Yingbo Sun, Yuan Chu, Xuewu Ji","doi":"10.1109/CVCI54083.2021.9661246","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661246","url":null,"abstract":"In order to ensure the safety and comfort performance in the car-following scene, based on the existing research, this paper chooses to use a deep reinforcement learning algorithm to build the following model and explore its performance in safety and comfort. Our research contents are as follows : (1) summarize the existing research about car-following, and summarize the principles of the existing vehicle following models; (2) do research on car-following safety and comfort index parameters; (3) use the principle of Deep Deterministic Policy Gradient (DDPG), and build up our car-following model based on DDPG algorithm; (4) build the car-following simulation environment in SUMO platform and train the model; (5) for testing our model, we use Intelligent Driver Model (IDM) for comparison and analyzed the simulation result from safety and comfort. Finally, it is concluded that our model can further improve vehicle comfort while ensuring safety. The research of this subject is helpful to the safe and comfortable driving in the car-following driving scene, and has certain significance and practical value in further improving the automatic driving technology of the vehicle.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126353104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Steering Control of Four-wheel Independent Drive Electric Vehicle 四轮独立驱动电动汽车转向控制研究

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661167

W. Zhu, Gang Li, L. Lu

{"title":"Research on Steering Control of Four-wheel Independent Drive Electric Vehicle","authors":"W. Zhu, Gang Li, L. Lu","doi":"10.1109/CVCI54083.2021.9661167","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661167","url":null,"abstract":"To improve the four-wheel independent drive electric vehicle handling and stability in the steering traveling, designed under different speed steering control strategies. When the vehicle is turning at low speed, the differential control based on the Ackerman steering model is adopted; when the vehicle is turning at high speed, the yaw moment control based on the two-degree-of-freedom model is adopted. In order to avoid excessive rigidity in strategy switching caused by vehicle speed changes, when the vehicle speed is driving at a medium speed, the PID controller is selected to track the ideal vehicle speed when turning. On the CarSim and MATLAB/Simulink joint simulation platform, the whole vehicle model is built, and the double-shifting working condition and the snake-like working condition are selected for simulation verification. The results show that the control strategies at different vehicle speeds can ensure the stability of the vehicle when turning, and can better track the expected vehicle speed when the vehicle is turning, and improve the maneuverability of the four-wheel drive electric vehicle.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121670431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Distracted driving recognition using Vision Transformer for human-machine co-driving 基于Vision Transformer的人机协同驾驶分心驾驶识别

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661254

Huiqin Chen, Hao Liu, Xiexing Feng, Hailong Chen

引用次数: 2

Mobile source emission model based on temporal features transfer* 基于时间特征转移的移动源发射模型*

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661261

Zhenyi Xu, Ruibin Wang, Renjun Wang, Xiushan Xia

引用次数: 1

[CVCI 2021 Front cover] [CVCI 2021封面]

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/cvci54083.2021.9661182

引用次数: 0

A Self-optimization Algorithm of Multi-style Smart Parking Driven by Experience, Knowledge and Data 基于经验、知识和数据的多风格智能停车自优化算法

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661152

Huifen Xie, Ze Zhang, K. Song

{"title":"A Self-optimization Algorithm of Multi-style Smart Parking Driven by Experience, Knowledge and Data","authors":"Huifen Xie, Ze Zhang, K. Song","doi":"10.1109/CVCI54083.2021.9661152","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661152","url":null,"abstract":"In this paper, a new algorithm based on experience, knowledge, and data was proposed to address the problems that the traditional automatic parking algorithms, specifically for parallel parking, have large global computing requirements, high real-time computing power requirements, and limit the optimization space. Firstly, a parking operation model based on segmented logic and judgment criteria from the driver’s experience was built for the entire parking process. Secondly, a multi-style evaluation system based on parking knowledge and customer demand was established. It refers to the volatility boundary of the index and uses Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS), Rank Correlation Analysis (G1), and entropy methods to determine the weight distributing model. Finally, based on an optimization test, the data was analyzed and the parameter relationship between variable and index was fit. A rapid self-optimizing algorithm was designed by combining the relation-ship mentioned above with the Particle Swarm Optimization (PSO) algorithm. It has been verified that the algorithm has increased the parking scores of SUVs and light buses at different starting points by 28.35% and 16.68% in 5.77s and 4.72s. Compared with traditional optimization algorithms, the algorithm designed in this paper saves 84.47% and 85.10% of the time. Therefore, the efficiency and adaptability in multiple situations of the rapid self-optimization algorithm have been verified.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128198594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on curve braking based on sensor fusion 基于传感器融合的弯道制动研究

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661181

Linhui Li, Ruitian Liang, Yifan Zhang, J. Lian, Xiaowei Guan

{"title":"Research on curve braking based on sensor fusion","authors":"Linhui Li, Ruitian Liang, Yifan Zhang, J. Lian, Xiaowei Guan","doi":"10.1109/CVCI54083.2021.9661181","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661181","url":null,"abstract":"The stability of the braking process of the intelligent vehicle is mainly divided into two parts: the accurate selection of the braking target and the stability during a braking on curve. For the selection of braking targets, this paper uses sensor fusion to identify and fit lane lines, and establishes a road curvature estimation model, which is used to identify the target vehicle in front of the lane, thereby effectively reducing vehicle mis-braking. The emergency braking of a vehicle in a curve is prone to instability. To solve this problem, a sliding-mode controller is worked out based on the joint control of the yaw rate and the side slip angle, in order to calculate the additional yaw moment. Then the additional yaw moment is converted into the braking moment of the wheels, so as to realize that the actual yaw rate and the side slip angle of the center of mass can follow the ideal value well. Finally, using Prescan, Carsim and MATLAB/Simulink for joint simulation, the results show that the proposed target vehicle recognition strategy based on sensor fusion can effectively reduce the vehicle’s mis-braking on curve, and after the torque is distributed through the designed sliding mode controller, it can effectively improve the braking stability of the vehicle.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126584813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predictive Cruise Control Algorithm Design for Commercial Vehicle Energy Saving Based on Mixed Integer Programming* 基于混合整数规划的商用车节能预测巡航控制算法设计

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661222

Xianning Li, Jinlong Hong, Yanjun Huang, Hong Chen

引用次数: 0

Evaluate the Connected Autonomous Vehicles Infrastructure using Digital Twin Model Based on Cyber-Physical Combination of Intelligent Network 基于网络物理结合的智能网联自动驾驶基础设施的数字孪生模型评估

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661190

Muhammad Usman Shoukat, Shuyou Yu, Shuming Shi, Yongfu Li, Jianhua Yu

{"title":"Evaluate the Connected Autonomous Vehicles Infrastructure using Digital Twin Model Based on Cyber-Physical Combination of Intelligent Network","authors":"Muhammad Usman Shoukat, Shuyou Yu, Shuming Shi, Yongfu Li, Jianhua Yu","doi":"10.1109/CVCI54083.2021.9661190","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661190","url":null,"abstract":"With the increment of connected vehicles, the level of intelligence becomes more and more irregular, so the difficulties of determining the dynamic safety of self-driving in mixed-transport flow have increased significantly. To solve the problems such as reliability, human-car-road perception, decision making, and control coordination assessment in an intelligent networked environment, this article established a multi-source dynamic game model to carry out the measurement of autonomous vehicle dynamics model, control estimation, decision strategy, forward and backward safety mechanism, and planning of mixed-traffic flow route. The digital twin has real-time, synchronous evolution, and interactivity with a semi-physical environment and a hardware-in-the-loop (HIL) model to control the accuracy of dynamic safety decisions for smart connected vehicles. This all process developed by combining with vehicle-to-everything (as a physical entity) and smart simulation test technology (as a virtual entity), which understands the compound and dynamic safety decision objects such as multi-agent view, multi-source data communication, vehicle switching, V2V transmission, and V2R synchronization for connected autonomous vehicles (CAVs) in the mixed-traffic flow atmospheres.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132310240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

LTGPv2: Rethinking local track geometry for Track-to-Track Association LTGPv2:重新思考track -to- track关联的局部轨迹几何

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661242

K. Zou, Tianle Zhou, Zou Zhou, Kai Ren, Yanhong Li, Xi Jiang, Xuedong Yuan

{"title":"LTGPv2: Rethinking local track geometry for Track-to-Track Association","authors":"K. Zou, Tianle Zhou, Zou Zhou, Kai Ren, Yanhong Li, Xi Jiang, Xuedong Yuan","doi":"10.1109/CVCI54083.2021.9661242","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661242","url":null,"abstract":"Track-to-track association (T2TA) is an essential part in situational awareness of advanced driving assistant systems. The accuracy of track-to-track association methods may degrade by missed detections and measurement bias. Although the local track geometry preservation algorithm has been proposed to improve the performance of T2TA, it may be affected as the target detection decreases. In this study, we proposed second version of the local track geometry preservation algorithm, called LTGPv2, which introduces another local track structure descriptor for T2TA. The local tracks of one sensor are represented by Gaussian mixture model (GMM) centroids, and are fitted to the corresponding local tracks of the other sensor. The T2TA problem is formulated as a maximum likelihood estimation problem with two local track geometry constraints to avoid the degradation of T2TA performance caused by missing detection. Then, an expectation–maximization (EM) algorithm is applied to solve it. Simulation results demonstrate that LTGPv2 obtain better performance than the state-of-the-art methods.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133227100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0