2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)最新文献_第3页

Lidar Points’ Bumpy Distortion Model, Displacements and Experiments 激光雷达点的凹凸畸变模型、位移和实验

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661154

Xiangyong Liu, W. Tian, Junwei Yu, Junqiao Zhao

引用次数: 0

SmogNet: A Point Cloud Smog Segmentation Network for Unmanned Vehicles SmogNet:用于无人驾驶车辆的点云烟雾分割网络

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661231

Hanbo Tang, Tao Wu, B. Dai

引用次数: 5

Preparation of Papers for IFAC Conferences & Symposia: Research on model predictive control of lane keeping based on particle swarm optimization IFAC会议及研讨会论文准备:基于粒子群优化的车道保持模型预测控制研究

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661145

Shi Peicheng, Wan Peng

{"title":"Preparation of Papers for IFAC Conferences & Symposia: Research on model predictive control of lane keeping based on particle swarm optimization","authors":"Shi Peicheng, Wan Peng","doi":"10.1109/CVCI54083.2021.9661145","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661145","url":null,"abstract":"Aiming at the problems of large deviation and long calculation time in the process of lane departure, a lane keeping model predictive control (MPC) method based on particle swarm optimization (PSO) is proposed, which uses MPC to effectively controls the vehicle, and uses particle swarm optimization algorithm to optimize the control time domain NP and prediction time domain Nc of MPC, which can reduce the number of iterations of model predictive control. Firstly, the particle swarm optimization algorithm is used to optimize the model predictive control. When the objective function reaches the minimum value, stop the iteration to reduce the amount of calculation; Then, the optimized lane keeping controller is Co-simulated by CarSim and Simulink for testing the control effect. The simulation results show that compared with the other three control methods proposed in this paper, this control method can control the vehicle driving on the lane more accurately, and the control accuracy can be improved by about 16%. In addition, the model predictive control based on particle swarm optimization improves the control accuracy and takes into account the stability of vehicle driving and the smoothness of control.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"62 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":"121510167","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

Trajectory Tracking Control for Four-Wheel Independently Driven Electric Vehicle Based on Model Predictive Control and Sliding Model Control 基于模型预测控制和滑模控制的四轮独立驱动电动汽车轨迹跟踪控制

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661227

Yuwei Tong, Hui Jing, Bing Kuang, G. Wang, Fei Liu, Zhe Yang

{"title":"Trajectory Tracking Control for Four-Wheel Independently Driven Electric Vehicle Based on Model Predictive Control and Sliding Model Control","authors":"Yuwei Tong, Hui Jing, Bing Kuang, G. Wang, Fei Liu, Zhe Yang","doi":"10.1109/CVCI54083.2021.9661227","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661227","url":null,"abstract":"This paper is to resolve the instability problem of trajectory tracking of four-wheel independently driven vehicles under high-speed conditions, an integrated control method of active front steering (AFS) and direct yaw moment (DYC) is designed. AFS controller to assure that the vehicle tracks the desired trajectory as far as possible. and DYC controller to assure vehicle stability during trajectory tracking. In the upper controller, the AFS controller is designed found on the model predictive control (MPC) theory, and the direct yaw moment control (DYC) based on the sliding mode control (SMC) theory. In the lower controller, the additional yaw moment is converted to the torque of four wheels considering the dynamic vertical load distribution of the vehicle. The simulation results demonstrate that the second-order sliding mode control (SOSMC) can effectively reduce the chattering problem caused by the traditional first-order sliding mode control (FOSMC), and the integrated control method improves the accuracy and stability of intelligent vehicle trajectory tracking.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"106 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":"124869239","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

Point cloud map creation based on laser and IMU information fusion 基于激光和IMU信息融合的点云图生成

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661174

Yibing Zhao, Zhenqiang Ma, Weiqi Wang, Bin Li, ShuYong Xing

{"title":"Point cloud map creation based on laser and IMU information fusion","authors":"Yibing Zhao, Zhenqiang Ma, Weiqi Wang, Bin Li, ShuYong Xing","doi":"10.1109/CVCI54083.2021.9661174","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661174","url":null,"abstract":"It is very necessary for driverless vehicles to understand the surrounding environment information in real time. However, the data observed by a single sensor always has the uncertain noise, which leads to map drift and undesirable mapping effect. Multi-sensor fusion technology can effectively make up for the above shortcomings and improve the mapping effect. The paper proposes an algorithm based on the fusion of inertial navigation sensor and laser odometry, in the data preprocessing stage, the IMU data information is used to perform linear interpolation calculations on the position of each frame of laser point cloud. The calculated position data information is used to remove motion distortion for each frame of laser point cloud and improve the matching accuracy. In the process of mapping, the error state Kalman filter algorithm was employed to fuse the position of the laser odometry and the IMU, and the improved algorithm reduces the average error of the global trajectory by 3.60005 m. By intermittently initializing the IMU odometry, the cumulative error of the IMU is reduced, the IMU odometry was re-initialized by applying the current position information output of the laser odometry as the initial position information. The paper conducts effective experiments on the KITTI urban road data- set. The results prove that the map creation method based on the fusion of laser odometry and IMU can effectively reduce map drift, improve map resolution, and its output of the driving trajectory information is more accurate.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"126 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":"132779964","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

A Control Method for Improving Ride Comfort in Braking 一种提高制动平顺性的控制方法

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661232

B. Shi, L. Xiong, Zhuoping Yu

{"title":"A Control Method for Improving Ride Comfort in Braking","authors":"B. Shi, L. Xiong, Zhuoping Yu","doi":"10.1109/CVCI54083.2021.9661232","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661232","url":null,"abstract":"Under conditions where the vehicle brakes at a certain acceleration until the vehicle speed drops to zero, which is common in daily driving, after the vehicle stops, the vehicle speed remains at zero and the acceleration will change from a certain non-zero value to zero. As a result, a large jerk (i.e. derivative of acceleration) is generated instantly, which seriously affects the ride comfort of passengers. For the above mentioned condition, this paper proposes a method to improve the braking comfort based on an integrated electro-hydraulic brake system. The proposed method includes target acceleration generation, target acceleration revise and acceleration tracking control. The target acceleration generation is used to generate an ideal target acceleration that can ensure the braking comfort based on mathematical analysis. Target acceleration revise is used to reduce the influence of acceleration tracking error on braking comfort control. Acceleration tracking control includes feedforward control and feedback control, which is used to track the target acceleration. Real vehicle tests show that the proposed method can significantly improve the ride comfort in braking.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"154 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":"133118002","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 Platoon Agent Controller Based on Twin Delayed Deep Deterministic Policy Gradient Algorithm* 基于双延迟深度确定性策略梯度算法的排代理控制器研究*

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661225

Xiaofan Ma, Shuming Shi, Nan Lin, Yang Li

{"title":"Research on Platoon Agent Controller Based on Twin Delayed Deep Deterministic Policy Gradient Algorithm*","authors":"Xiaofan Ma, Shuming Shi, Nan Lin, Yang Li","doi":"10.1109/CVCI54083.2021.9661225","DOIUrl":"https://doi.org/10.1109/CVCI54083.2021.9661225","url":null,"abstract":"At present, in the research of platoon controller, most of it is based on Model Predictive Control, PID and other control algorithms under the condition of considering communication delay, topology structure and string stability. With the development of Deep Reinforcement Learning, agents can decide the controlled variable according to the state, which is very beneficial to the control of complex systems. Therefore, Twin Delayed Deep Deterministic policy gradient algorithm is used to control the agent platoon, and regards the information interaction within the platoon as a decision process with Markov properties. Matlab and Sumo are used to build a training platform, so as to train the function approximator that maps the state quantity to the action. In the design of the reward function, the state quantity involved in the string stability is given different weights to achieve the string stability from various aspects. Compared with the linear dynamic model, we use the 5-Degree of Freedom nonlinear dynamic model to make the dynamic characteristics of the vehicle more real. The simulation results show that the platoon agent trained by the Twin Delayed Deep Deterministic policy gradient algorithm can guarantee a certain string stability.","PeriodicalId":419836,"journal":{"name":"2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)","volume":"24 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":"117165983","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

Maximum Efficiency Point Calculation For Multiple Electric Vehicles of Wireless Power Transfer System With LCC-LCC Compensation Topology 基于LCC-LCC补偿拓扑的多辆电动汽车无线电力传输系统最大效率点计算

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661186

Jiaxu Meng, Guang Liu, Shuai Zhao, Yang Zhai, Shuo Chen, Yindong Wang

引用次数: 0

Trajectory Tracking Control Combined with Steering and Torque Vector Control based on Holistic MPC 基于整体MPC的轨迹跟踪控制与转向和转矩矢量控制相结合

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661138

Guodong Wang, Li Liu, Yu Meng, Qing Gu, Lei Zhou, B. Zhou

引用次数: 1

Electronic Differential Control for Distributed Electric Vehicles Based on Optimum Ackermann Steering Model 基于最优Ackermann转向模型的分布式电动汽车电子差速控制

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI) Pub Date : 2021-10-29 DOI: 10.1109/CVCI54083.2021.9661256

Pingshu Ge, Lie Guo, Junjie Chen

引用次数: 2