Query：
学者姓名：黄炜
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
从控制架构与驾驶权决策出发,阐述了人机共驾的研究现状以及发展趋势;在控制架构方面,分析了切换控制架构和共享控制架构的特点和应用范围,并提出了混杂控制架构概念;在驾驶权决策方面,讨论了不同驾驶权决策方法对不同来源、不同性质信息的使用方式,概括了执行驾驶权分配时直接和间接共享控制方式所涉及的方法,梳理了策略层决策与执行层决策的研究角度与方法.研究结果表明:针对高阶自动驾驶上路运行安全问题,发展混杂控制架构对安全员干预场景下的系统动态进行描述有利于避免模型失配,从而为控制性能优化和稳定性设计提供了基础;通过融合全息态势感知与数据智能的方式收集和整合多个信息源的数据,能够更加全面地理解人机共驾系统中诸多要素的动态变化并做出最优驾驶权决策;相较于直接共享控制,间接共享控制能避免人机控制流直接对抗,但是其动态驾驶权分配执行层面不仅需要考虑人机之间的冲突反馈,还需要确保合理的交互体验以体现间接共享控制的优势;基于智能体的策略层决策方法并不依赖于数学模型精度,能够自适应环境的动态变化;基于博弈论的执行层决策方法通过建模人机交互过程能够增强驾驶权决策系统的可控性和可解释性;未来的人机共驾系统设计应进一步优化交互体验,关注发展平等共融的人机关系,并提高控制系统的鲁棒性以及驾驶权决策的可解释性和适应性.
Keyword ：
交互协同 交互协同 人机共驾 人机共驾 博弈论 博弈论 强化学习 强化学习 混杂控制 混杂控制 驾驶权 驾驶权
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黄炜 , 黄起鹏 . 人机共驾控制架构与驾驶权决策研究综述 [J]. | 交通运输工程学报 , 2025 , 25 (1) : 48-65 . |
| MLA | 黄炜 等. "人机共驾控制架构与驾驶权决策研究综述" . | 交通运输工程学报 25 . 1 (2025) : 48-65 . |
| APA | 黄炜 , 黄起鹏 . 人机共驾控制架构与驾驶权决策研究综述 . | 交通运输工程学报 , 2025 , 25 (1) , 48-65 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为更好解决基于同步定位与地图构建(SLAM)地图无人车的长期定位问题,提出一种基于语义图相似匹配与候选帧的语义扫描上下文描述符,通过粗、细两步定位实现对点云场景的重定位.首先,提取点云语义和几何特征,剔除移动、可移动类对象,通过融合语义信息和拓扑关系构建语义图,以图相似度计算实现快速重定位粗匹配;其次,通过全局语义迭代最近点(ICP)方法计算点云之间的相对偏航角和水平位移,为点云配准提供良好的初始值;最后,通过语义扫描上下文生成全局语义描述符,通过对比描述符判别点云相似性,完成精准重定位.实验结果表明:所提方法相较基于语义图的地点识别方法在地点识别精度、遮挡场景和视角变化场景下精度分别提升20.10%、20.90%和20.47%.
Keyword ：
同步定位与地图构建 同步定位与地图构建 点云配准 点云配准 语义图 语义图 语义扫描上下文 语义扫描上下文 重定位 重定位
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黄孝鸿 , 彭育辉 , 黄炜 . 基于语义图和语义扫描上下文的激光点云两步重定位方法 [J]. | 激光与光电子学进展 , 2024 , 61 (18) : 189-196 . |
| MLA | 黄孝鸿 等. "基于语义图和语义扫描上下文的激光点云两步重定位方法" . | 激光与光电子学进展 61 . 18 (2024) : 189-196 . |
| APA | 黄孝鸿 , 彭育辉 , 黄炜 . 基于语义图和语义扫描上下文的激光点云两步重定位方法 . | 激光与光电子学进展 , 2024 , 61 (18) , 189-196 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Trajectory following is an important function of autonomous vehicles. To enable a four-wheel independent drive electric vehicle to precisely follow a predefined or real-time generated trajectory with good lateral stability and ride comfort at high velocity, a model predictive control (MPC) scheme with feedback compensation considering model mismatch is proposed in this paper to coordinate the direct yaw-moment control and active front steering. The system input signal computed by model predictive control is corrected by the feedback compensation to cope with the model mismatch existing between the controlled vehicle and the nominal model. Moreover, co-simulation is carried out between the software MATLAB/Simulink and Carsim to verify the proposed method. In comparison, the integration of the direct yaw-moment control and active front steering through model predictive control can overcome the non-smooth problem of vehicle dynamics while implementing the active front steering only. However, the value of the external yaw moment computed by the model predictive controller might be too large due to the predictive error in extreme situations, which could endanger the vehicle. The results reveal that the proposed model predictive control scheme with feedback compensation can effectively compensate the front steering angle and enhance the control effect. Therefore, it can significantly improve the trajectory following accuracy and yaw stability.
Keyword ：
Autonomous vehicle Autonomous vehicle direct yaw-moment control direct yaw-moment control feedback compensation feedback compensation model predictive control model predictive control trajectory following trajectory following
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Xingyu , Zhu, Shaopeng , Ao, Di et al. Nonlinear model predictive trajectory following control with feedback compensation for autonomous four-wheel independent drive electric vehicles [J]. | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2024 , 238 (2-3) : 478-490 . |
| MLA | Ye, Xingyu et al. "Nonlinear model predictive trajectory following control with feedback compensation for autonomous four-wheel independent drive electric vehicles" . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING 238 . 2-3 (2024) : 478-490 . |
| APA | Ye, Xingyu , Zhu, Shaopeng , Ao, Di , Huang, Wei . Nonlinear model predictive trajectory following control with feedback compensation for autonomous four-wheel independent drive electric vehicles . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2024 , 238 (2-3) , 478-490 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为提高自动泊车成功率，建立车位环境复杂度量化评价模型.以车位类型、车位线属性等7个指标建立车位环境复杂度评价指标体系，并提出相应的量化表征方法.针对主客观组合赋权法无法正确计算单个样本临界指标权重的问题，在层次分析法基础上，提出基于平方和归一化的权重二次分配方法.运用模糊综合评价求解车位环境复杂度，通过设计仿真测试来验证所提模型.结果表明：与层次分析法、熵权法相比，所提赋权方法能够正确对临界决定性指标赋予较大权重，避免无效权重赋予；所提模型能够正确反映车位环境复杂度变化，对泊车成功率有较大提升，为泊车位的自动选择提供一种可行的新路径.
Keyword ：
层次分析法 层次分析法 智能交通 智能交通 模糊综合评价 模糊综合评价 自动泊车系统 自动泊车系统 车位主动选择 车位主动选择
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈泽辉 , 彭育辉 , 黄炜 et al. 环境复杂度量化评价下的车位选择方法 [J]. | 福州大学学报(自然科学版) , 2024 , 52 (01) : 61-68 . |
| MLA | 陈泽辉 et al. "环境复杂度量化评价下的车位选择方法" . | 福州大学学报(自然科学版) 52 . 01 (2024) : 61-68 . |
| APA | 陈泽辉 , 彭育辉 , 黄炜 , 姚宇捷 , 吴庆 , 何维堃 . 环境复杂度量化评价下的车位选择方法 . | 福州大学学报(自然科学版) , 2024 , 52 (01) , 61-68 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper concerns with the development of computationally efficient lane keeping control method for the autonomous vehicles. To obtain autonomous lane keeping, model predictive control (MPC) scheme was intensively investigated in the previous studies owing to its inherent advantage of dealing with constrained multivariable systems. However, the tradeoff problem between the good tracking performance and the low computational complexity is inevitably raised in developing of MPC-based lane keeping technology. To alleviate the conflict between performance and cost, an on-board MPC with fuzzy preview distance is designed in this study. A linear system dynamics model is used in the MPC design to reduce the computational cost, and a fuzzy logic algorithm is developed to select an appropriate preview distance for enhancing the MPC performance. Further, hardware-in-the-loop test is adopted to explore the effectiveness and efficiency of the proposed control method. In comparison to the proportional-integral controller, the experimental results show that the MPC is more sensitive to the selective value of fixed preview distance. Since the significant impact of preview distance selection on the MPC-based lane keeping performance, the fuzzy logic algorithm is of the essence in terms of selecting the appropriate preview distance for MPC enhancement under different vehicle speed and road curvature. Eventually, experimental results validate that the proposed fuzzy preview distance algorithm can effectively improve the MPC-based lane keeping performance for autonomous vehicles subject to limited computational resource.
Keyword ：
autonomous vehicle autonomous vehicle fuzzy logic fuzzy logic Lane keeping Lane keeping model predictive control model predictive control preview distance preview distance
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huang, Wei , Xia, Wei , Wu, Zhengxiao et al. On-board model predictive control for autonomous lane keeping with fuzzy preview distance: Design and experiment [J]. | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2024 . |
| MLA | Huang, Wei et al. "On-board model predictive control for autonomous lane keeping with fuzzy preview distance: Design and experiment" . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING (2024) . |
| APA | Huang, Wei , Xia, Wei , Wu, Zhengxiao , Liu, Xinjie , Shi, Tianhua , Peng, Yuhui et al. On-board model predictive control for autonomous lane keeping with fuzzy preview distance: Design and experiment . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
A novel hierarchical direct yaw moment controller is designed to enhance the lateral stability of the four-wheel-drive electric vehicle. The adaptive sliding mode control (ASMC) technique in the upper-layer controller is employed to compute an additional yaw moment. The lower-layer controller distributes this yaw moment into each independent wheel by utilizing model predictive control allocation (MPCA). The proposed MPCA aims to mitigate the performance deterioration induced by in-wheel motor dynamics and optimize the power consumption stemming from the additional yaw moment. Co-simulation and hardware-in-the-loop (HIL) test is conducted to verify the performance of the proposed controller. Validation results show that the proposed hierarchical ASMC-MPCA controller outperforms the sliding mode control MPCA (SMC-MPCA) and the integrated nonlinear model predictive control (NMPC) with the lowest root-mean-square errors ( RMSE s ) of yaw rate, sideslip angle, lateral deviation, and lowest power consumption. Additionally, the chattering phenomenon in SMC-MPCA can be suppressed effectively by adaptively estimating the parameter uncertainties. The proposed ASMC-MPCA controller also consumes less computational resources than the NMPC and SMC-MPCA, which indicates that the ASMC-MPCA is more suitable for an automotive onboard controller. The comparison between hierarchical and integrated controller frameworks also shows that the hierarchical framework is more suitable for production vehicles under non-powerful vehicle control units.
Keyword ：
Adaptive sliding mode control Adaptive sliding mode control direct yaw moment direct yaw moment four-wheel driving electric vehicle four-wheel driving electric vehicle lateral stability lateral stability model predictive control allocation model predictive control allocation power consumption power consumption
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ao, Di , Wong, Pak Kin , Huang, Wei . Model predictive control allocation based on adaptive sliding mode control strategy for enhancing the lateral stability of four-wheel-drive electric vehicles [J]. | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2023 , 238 (6) : 1514-1534 . |
| MLA | Ao, Di et al. "Model predictive control allocation based on adaptive sliding mode control strategy for enhancing the lateral stability of four-wheel-drive electric vehicles" . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING 238 . 6 (2023) : 1514-1534 . |
| APA | Ao, Di , Wong, Pak Kin , Huang, Wei . Model predictive control allocation based on adaptive sliding mode control strategy for enhancing the lateral stability of four-wheel-drive electric vehicles . | PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING , 2023 , 238 (6) , 1514-1534 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为提高复杂环境下自动垂直泊车的安全性和成功率,提出一种基于多项式曲线优化的垂直泊车路径规划方法和跟踪控制策略.首先,基于直线-圆弧路径下逆向泊车的方法,计算垂直泊车可行起始点范围.其次,综合考虑车辆位置结构和道路边界约束,以多项式为基函数、泊车终点姿态角最小为目标,建立多约束非线性规划路径函数模型,利用粒子群算法求解垂直泊车路径.最后,结合模糊神经网络控制方法,设计路径跟踪控制器.构建Simulink/CarSim仿真模型,对所提路径规划方法和跟踪策略进行仿真,结果验证了所提泊车路径规划和跟踪控制策略的可行性和有效性.
Keyword ：
垂直泊车 垂直泊车 多项式曲线 多项式曲线 跟踪控制 跟踪控制 路径规划 路径规划
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 江铭 , 彭育辉 , 黄炜 et al. 多项式曲线优化的垂直泊车路径规划与跟踪 [J]. | 福州大学学报（自然科学版） , 2023 , 51 (1) : 76-82 . |
| MLA | 江铭 et al. "多项式曲线优化的垂直泊车路径规划与跟踪" . | 福州大学学报（自然科学版） 51 . 1 (2023) : 76-82 . |
| APA | 江铭 , 彭育辉 , 黄炜 , 徐德强 . 多项式曲线优化的垂直泊车路径规划与跟踪 . | 福州大学学报（自然科学版） , 2023 , 51 (1) , 76-82 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
For the problems of unsatisfactory detection accuracy and weak real-time performance in the complicated illumination scenes in the existing deep learning target detection algorithms，an anti-illumination target detection network model YOLO-RLG based on the YOLO algorithm is proposed. Firstly，the RGB data of the input model is converted into HSV data，and the S channel with powerful anti-illumination capability is separated from the HSV data and fused with the RGB data to generate RGBS data so that the input data has anti-illumination capability. Secondly，the backbone network of YOLOV4 is replaced with Ghostnet network，with the model assignment ratio between ordinary convolution and cheap convolution modified to improve the detection efficiency while ensuring the detection accuracy. Finally，the loss function of the model is improved by replacing CIoU with EIoU，which enhances the target detection accuracy and algorithm robustness. The experimental results based on KITTI and VOC datasets indicate that，compared with the original network model，the FPS improves by 22.54 and 17.84 f/s，with the model reduced by 210.3 M，the accuracy（AP）improved by 0.83% and 1.31%，and the algorithm′s anti-illumination performance significantly enhanced. © 2023 SAE-China. All rights reserved.
Keyword ：
anti-illumination image processing anti-illumination image processing Ghostnet network Ghostnet network loss function loss function machine vision machine vision
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yao, Y. , Peng, Y. , Chen, Z. et al. An Improved YOLO Algorithm Supporting Anti-illumination Target Detection; [支持抗光照目标检测的改进 YOLO 算法] [J]. | Automotive Engineering , 2023 , 45 (5) : 777-785 . |
| MLA | Yao, Y. et al. "An Improved YOLO Algorithm Supporting Anti-illumination Target Detection; [支持抗光照目标检测的改进 YOLO 算法]" . | Automotive Engineering 45 . 5 (2023) : 777-785 . |
| APA | Yao, Y. , Peng, Y. , Chen, Z. , He, W. , Wu, Q. , Huang, W. et al. An Improved YOLO Algorithm Supporting Anti-illumination Target Detection; [支持抗光照目标检测的改进 YOLO 算法] . | Automotive Engineering , 2023 , 45 (5) , 777-785 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为了提高汽车对外界环境信息的感知能力和对动态车辆目标行为的预测能力，采用YOLOX作为前端检测器，结合优化的DeepSort跟踪算法开展动态车辆多目标跟踪方法研究。在车辆特征匹配过程中，提取Haar-like特征对车辆的明暗变化信息进行匹配，提高物体匹配精度；基于DeepSort重识别网络，采用改进的ResNet13作为特征提取的骨干网络，加入SENet调整不同通道维度的特征权重。使用实际道路驾驶采集的视频数据对改进算法与传统算法进行对比，结果表明：相较于传统DeepSort算法，改进算法的多目标跟踪精度（MOTA）提高了1.4百分点，平均数比率（IDF1）提升了7.7百分点。
Keyword ：
DeepSort DeepSort Haar-like Haar-like SENet SENet 多目标跟踪 多目标跟踪 自动驾驶 自动驾驶
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 何维堃 , 彭育辉 , 黄炜 et al. 基于DeepSort的动态车辆多目标跟踪方法研究 [J]. | 汽车技术 , 2023 , 7 (11) : 27-33 . |
| MLA | 何维堃 et al. "基于DeepSort的动态车辆多目标跟踪方法研究" . | 汽车技术 7 . 11 (2023) : 27-33 . |
| APA | 何维堃 , 彭育辉 , 黄炜 , 姚宇捷 , 陈泽辉 . 基于DeepSort的动态车辆多目标跟踪方法研究 . | 汽车技术 , 2023 , 7 (11) , 27-33 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对现有的深度学习目标检测算法中存在的复杂光照场景下检测精度不高、实时性差等问题，提出了一种基于YOLO算法的抗光照目标检测网络模型YOLO-RLG。首先，将输入模型的RGB数据转换为HSV数据，从HSV数据分离出抗光照能力强的S通道，并与RGB数据合并生成RGBS数据，使输入数据具备抗光照能力；其次，将YOLOV4的主干网络替换成Ghostnet网络，并对其在普通卷积与廉价卷积的模型分配比例上进行调整，在保证检测精度的同时提高检测速度；最后，用EIoU替换CIoU改进模型的损失函数，提高了目标检测精度和算法鲁棒性。基于KITTI与VOC数据集的实验结果表明，与原网络模型比较，FPS提高了22.54与17.84 f/s，模型降低了210.3 M，精确度（AP）提升了0.83%与1.31%，且算法的抗光照能力得到显著增强。
Keyword ：
Ghostnet网络 Ghostnet网络 抗光照图像处理 抗光照图像处理 损失函数 损失函数 机器视觉 机器视觉
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 姚宇捷 , 彭育辉 , 陈泽辉 et al. 支持抗光照目标检测的改进YOLO算法 [J]. | 汽车工程 , 2023 , 45 (05) : 777-785 . |
| MLA | 姚宇捷 et al. "支持抗光照目标检测的改进YOLO算法" . | 汽车工程 45 . 05 (2023) : 777-785 . |
| APA | 姚宇捷 , 彭育辉 , 陈泽辉 , 何维堃 , 吴庆 , 黄炜 et al. 支持抗光照目标检测的改进YOLO算法 . | 汽车工程 , 2023 , 45 (05) , 777-785 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
