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

Lateral Control Method of the Follower Vehicle in Local Decentralized Platooning 局部分散队列中跟随车辆的横向控制方法

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661166

Hanyang Zhuang, Xiaofeng Chen, Chunxiang Wang, Ming Yang

{"title":"Lateral Control Method of the Follower Vehicle in Local Decentralized Platooning","authors":"Hanyang Zhuang, Xiaofeng Chen, Chunxiang Wang, Ming Yang","doi":"10.1109/CVCI54083.2021.9661166","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661166","url":null,"abstract":"Vehicle platooning is an innovative technology for intelligent transportation systems. Each vehicle in the platoon is required to autonomously follow its front vehicle’s path unconditionally and accurately. Vehicle platooning based on global decentralized approaches relies on accurate and robust global positioning and reliable communication. However, high-precision global localization needs to be limited to a known area and communications cause problems such as security attacks. Considering the above factors, local decentralized approach for vehicle platooning is investigated as they do not rely on any infrastructure such as global localization and communications. The essential task of a follower vehicle in the platoon is to follow the path of its leader vehicle. In this paper, a path following method in this situation is developed to keep good track of the leader ’s path. A lidar is installed on the follower vehicles to measure the position and heading information the leader. A lateral control algorithm based on considering both the position and heading of the leader has been developed and verified on a three-vehicle platoon. The experiment results have shown more stable and smaller lateral error of the proposed method comparing to pure pursuit method. Moreover, the error of the heading angle has also been improved significantly on a crossing route.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"53 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":"129253835","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

Improved Adaptive Cruise Control for Autonomous Vehicles with Consideration of Crash Avoidance 考虑碰撞避免的自动驾驶汽车自适应巡航控制

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661195

Yu Zhang, Yunfeng Chu, Mingming Dong, Li Gao, Yechen Qin, Zhenfeng Wang

引用次数: 0

Balancing Accuracy and Efficiency: Fast Motion Planning Based on Nonlinear Model Predictive Control 平衡精度与效率:基于非线性模型预测控制的快速运动规划

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661264

F. Gao, Yu Han, D. Dang

{"title":"Balancing Accuracy and Efficiency: Fast Motion Planning Based on Nonlinear Model Predictive Control","authors":"F. Gao, Yu Han, D. Dang","doi":"10.1109/CVCI54083.2021.9661264","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661264","url":null,"abstract":"Nonlinear Model Predictive Control (NMPC) is an effective method for the motion planning of automated vehicles. With the working conditions become more nonlinear and complicated, it is necessary to design an efficient NMPC method while guarantee the control accuracy simultaneously. This work presents a fast NMPC method aiming for balancing accuracy and efficiency in multiple obstacle vehicles situations. Given the high nonlinearity of vehicle dynamics, Lagrange interpolation is adopted to discretize vehicle dynamics function and objective function to ensure accuracy with less discretization points. The interpolation order is chosen adaptively based on the numerical analysis of the distribution characteristics of discretization error. Moreover, a hybrid strategy is presented to construct the constraints for obstacle avoidance by combing the elliptic and linear time-varying ones together to make a good balance between the control accuracy and solving efficiency. The acceleration effect and performance of the motion planning algorithm designed by NMPC are validated by comparative numerical analysis in multiple obstacle vehicles scenarios.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"33 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":"114409539","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

Pedestrian Intention Prediction via Depth Augmented Scene Restoration 基于深度增强场景复原的行人意图预测

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661140

Dazhi Zhang, Feifan Shi, Yu Meng, Yan Xu, Xiaofeng Xiao, Wenbo Li

{"title":"Pedestrian Intention Prediction via Depth Augmented Scene Restoration","authors":"Dazhi Zhang, Feifan Shi, Yu Meng, Yan Xu, Xiaofeng Xiao, Wenbo Li","doi":"10.1109/CVCI54083.2021.9661140","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661140","url":null,"abstract":"Minimizing traffic accidents between vehicles and pedestrians is of great importance in constructing intelligent transportation systems. Pedestrian behavior prediction is one of the major solutions to achieve this goal. The current methods are all extracting key information in the two-dimensional plane of image (e.g., the scene map around pedestrians, semantic map), and there is no specific use of the unique information in the three-dimensional space. Besides, the relative distance information that accounts for the interaction between the target pedestrian and the scene has not been properly utilized, and this information is missing in the current behavioral benchmark dataset. To solve these challenges, we introduce a new view for pedestrian intention prediction. The distance from each pixel to the camera is firstly estimated by the method of monocular depth estimation, so that the two-dimensional pixels are remapped to the three-dimensional space. Then, a new deep learning variant model is proposed to adequately fuse information from different perspectives. In particular, the experiments based on large-scale traffic dataset JAAD [1] and PIE [2] show that the multi-view architecture has an outstanding performance than state-of-the-art (SOTA) methods.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"119 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":"114496094","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: 2

Active safe motion planning for intelligent vehicles in dynamic environments 动态环境下智能汽车的主动安全运动规划

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661147

H. Tian, Jianqiang Wang, Heye Huang

{"title":"Active safe motion planning for intelligent vehicles in dynamic environments","authors":"H. Tian, Jianqiang Wang, Heye Huang","doi":"10.1109/CVCI54083.2021.9661147","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661147","url":null,"abstract":"Motion planning is an essential component in intelligent vehicle study. Rapidly-exploring Random Tree(RRT) and its variants are popular algorithms that have been successfully applied in solving motion planning problems. However, obtaining an optimal trajectory while concerning driving safety in dynamic environments is a difficult problem. In this study, we present an active safe RRT(AS-RRT) motion planning algorithm that enable the intelligent vehicle to avoid collision risks and find an efficient path in the dynamic environment. The algorithm firstly reconstructs a potential field-based configuration space for static obstacles and moving vehicles, which defines the risk regions. Then, it develops an RRT tree through samples in the space with considerations of nonholonomic constraints of the vehicles. A comprehensive cost function is used for the priority sequence mechanism to get an initial trajectory. After that, the trajectory is asymptotically optimized gradually by decreasing the cost iteratively. Simulation results demonstrated that the proposed algorithm improved the vehicles’ motion planning safety performance in dynamic environments.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"11 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":"115274042","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

A Cooperative Game-based Lateral Control Authority Allocation for Human-machine Co-driving in Large Conflict Scenarios 大型冲突场景下基于合作博弈的人机协同驾驶横向控制权限分配

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661173

Changhua Dai, C. Zong, Dong Zhang

引用次数: 0

Coordinated longitudinal and lateral vehicle stability control based on the combined-slip tire model in the MPC framework MPC框架下基于组合滑移轮胎模型的车辆纵向和横向协调稳定性控制

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661187

Zihan Li, Ping Wang, Hanghang Liu, Yufeng Hu, Hong Chen

引用次数: 0

Cooperative Merging Trajectory Optimization of Connected and Automated Vehicles in the Mixed Traffic: a Receding Horizon Control Approach 混合交通中网联与自动驾驶车辆协同归并轨迹优化:一种后退地平线控制方法

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661122

Haoji Liu, Guo-dong Yin, Weichao Zhuang, Rongcan Li

{"title":"Cooperative Merging Trajectory Optimization of Connected and Automated Vehicles in the Mixed Traffic: a Receding Horizon Control Approach","authors":"Haoji Liu, Guo-dong Yin, Weichao Zhuang, Rongcan Li","doi":"10.1109/CVCI54083.2021.9661122","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661122","url":null,"abstract":"The Cooperative on-ramp merging control of the connected and automated vehicle (CAV) can effectively address problems of traffic congestion, excessive energy consumption, and even traffic accident in the on-ramp merging areas. However, the uncertain maneuver of human-driven vehicles (HDVs) in mixed traffic scenarios brings trouble in making merging control for CAVs. In this paper, we proposed a receding horizon on-ramp merging control strategy for CAVs to address the mixed traffic merging control problem. First, control constrained optimal control problems for CAVs corresponding to two control modes are formulated. The flexible merging control mode optimizes merging trajectory with flexible merging time and position, while the mandatory merging control mode gives a fixed merging position to prevent the on-ramp CAV from driving beyond the longitudinal boundary. All the formulated optimal control problems are solved by Pontryagin’s minimum principle. Then, a receding horizon switching control framework is employed, in which the uncertain maneuver of the HDV is regarded as disturbance, thus CAVs collect HDV states, choose proper control modes, and replan their own trajectories repeatedly. Simulation results show that the proposed on-ramp merging control strategy can make CAVs merge flexibly in different scenarios and has the potential in improving safety, optimization, and robustness for the mixed traffic on-ramp merging control.","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":"128204843","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

Life Cycle Assessment of High-Voltage Cable Assembly in High-speed Railways 高速铁路高压电缆组件生命周期评价

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661209

Zhuoyun Li, Xiaochen Dong, Jicheng Chen, Hui Zhang

引用次数: 0

Cold start control of solid oxide fuel cell-internal combustion engine system 固体氧化物燃料电池-内燃机系统冷启动控制

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661170

Zhiyao Xu, Yu Zhang, Shengya Hou, B. Gao, Jinwu Gao

引用次数: 2