为满足自动驾驶系统的高效、准确感知的需求,如果仅依靠相机很难实现高精度和鲁棒的3D目标检测。解决这一问题的有效方法是将相机与经济型毫米波雷达传感器相结合,实现更可靠的多模态三维目标检测。融合两者的检测方式不仅提升了环境感...为满足自动驾驶系统的高效、准确感知的需求,如果仅依靠相机很难实现高精度和鲁棒的3D目标检测。解决这一问题的有效方法是将相机与经济型毫米波雷达传感器相结合,实现更可靠的多模态三维目标检测。融合两者的检测方式不仅提升了环境感知的准确性,还增强了系统的鲁棒性和安全性。本文提出了一种基于毫米波雷达和相机融合的自动驾驶感知算法HPR-Det(historical pillar of ray camera-radar fusion bird ’s eye view for 3D object detection)。具体而言,首先设计了雷达BEV特征提取Radar-PRANet(radar point RCS attention net),由双流雷达主干提取具有两种表征维度的雷达特征和RCS感知的BEV编码器组成,根据雷达特定的RCS特征将雷达特征分散到BEV中。其次,采用历史多帧预测范式HrOP(historical radar of object prediction),设计了长期解码器和短期解码器,同时只在训练期间执行,在推理过程中不引入额外的开销,同时由于本网络输入数据的稀疏性,引入了多模态的历史多帧输入,引导更准确的BEV特征学习。最后,提出了毫米波优化的射线去噪方法,通过将毫米波雷达点云的信息作为先验信息,使用当前帧的毫米波点云特征辅助生成提议,增强对于相机的查询特征表征。本文所提出的算法在大规模公开数据集nuScenes上进行模型训练和实验验证,在骨干为Resnet50的基础上NDS达到56.7%。展开更多
The development of chassis active safety control technology has improved vehicle stability under extreme conditions.However,its cross-system and multi-functional characteristics make the controller difficult to achiev...The development of chassis active safety control technology has improved vehicle stability under extreme conditions.However,its cross-system and multi-functional characteristics make the controller difficult to achieve cooperative goals.In addition,the chassis system,which has high complexity,numerous subsystems,and strong coupling,will also lead to low computing efficiency and poor control effect of the controller.Therefore,this paper proposes a scenario-driven hybrid distributed model predictive control algorithm with variable control topology.This algorithm divides multiple stability regions based on the vehicle’s β−γ phase plane,forming a mapping relationship between the control structure and the vehicle’s state.A control input fusion mechanism within the transition domain is designed to mitigate the problems of system state oscillation and control input jitter caused by switching control structures.Then,a distributed state-space equation with state coupling and input coupling characteristics is constructed,and a weighted local agent cost function in quadratic programming is derived.Through cost coupling,local agents can coordinate global performance goals.Finally,through Simulink/CarSim joint simulation and hardware-in-the-loop(HIL)test,the proposed algorithm is validated to improve vehicle stability while ensuring trajectory tracking accuracy and has good applicability for multi-objective coordinated control.This paper combines the advantages of distributed MPC and decentralized MPC,achieving a balance between approximating the global optimal results and the solution’s efficiency.展开更多
Due to the bus characteristics of large quality,high center of gravity and narrow wheelbase,the research of its yaw stability control(YSC)system has become the focus in the field of vehicle system dynamics.However,the...Due to the bus characteristics of large quality,high center of gravity and narrow wheelbase,the research of its yaw stability control(YSC)system has become the focus in the field of vehicle system dynamics.However,the tire nonlinear mechanical properties and the effectiveness of the YSC control system are not considered carefully in the current research.In this paper,a novel adaptive nonsingular fast terminal sliding mode(ANFTSM)control scheme for YSC is proposed to improve the bus curve driving stability and safety on slippery roads.Firstly,the STI(Systems Technologies Inc.)tire model,which can effectively reflect the nonlinear coupling relationship between the tire longitudinal force and lateral force,is established based on experimental data and firstly adopted in the bus YSC system design.On this basis,a more accurate bus lateral dynamics model is built and a novel YSC strategy based on ANFTSM,which has the merits of fast transient response,finite time convergence and high robustness against uncertainties and external disturbances,is designed.Thirdly,to solve the optimal allocation problem of the tire forces,whose objective is to achieve the desired direct yaw moment through the effective distribution of the brake force of each tire,the robust least-squares allocation method is adopted.To verify the feasibility,effectiveness and practicality of the proposed bus YSC approach,the TruckSim-Simulink co-simulation results are finally provided.The co-simulation results show that the lateral stability of bus under special driving conditions has been significantly improved.This research proposes a more effective design method for bus YSC system based on a more accurate tire model.展开更多
Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,...Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,Radars relative to Lidars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution.In order to compensate for the low detection accuracy,incomplete target attributes and poor environmental adaptability of single sensors such as Radar and LiDAR,in this paper,an effective method for high-precision detection and tracking of surrounding targets of autonomous vehicles.By employing the Unscented Kalman Filter,Radar and LiDAR information is effectively fused to achieve high-precision detection of the position and speed information of targets around the autonomous vehicle.Finally,the real vehicle test under various driving environment scenarios is carried out.The experimental results show that the proposed sensor fusion method can effectively detect and track the vehicle peripheral targets with high accuracy.Compared with a single sensor,it has obvious advantages and can improve the intelligence level of autonomous cars.展开更多
The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and ...The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and collisions occur more frequently on highways.However,existing studies lack analysis of L3-AV performance in highway maintenance areas.In this study,we investigated the traffic flow and maintenance situation of S68 highway in Zhenjiang City and simulated it in SUMO,then compared the L3-AV takeover details based on length and number of lanes of maintenance area,fitted the prediction of the conflict data using the CatBoost model,and interpreted the prediction results in terms of global and local features by the SHAP theory.The results show that the length of the maintenance area and the number of lanes influence both the initial takeover and the takeover frequency.The relative speed between the L3-AV and the surrounding vehicles plays an important role in the conflict likelihood during traveling in the maintenance area.The findings of this paper are important for optimizing highway maintenance area configurations and developing L3-AV conflict avoidance techniques in specific scenarios.展开更多
Traffic sign detection is a crucial task for autonomous driving systems.However,the performance of deep learning-based algorithms for traffic sign detection is highly affected by the illumination conditions of scenari...Traffic sign detection is a crucial task for autonomous driving systems.However,the performance of deep learning-based algorithms for traffic sign detection is highly affected by the illumination conditions of scenarios.While existing algo-rithms demonstrate high accuracy in well-lit environments,they suffer from low accuracy in low-light scenarios.This paper proposes an end-to-end framework,LLTH-YOLOv5,specifically tailored for traffic sign detection in low-light scenarios,which enhances the input images to improve the detection performance.The proposed framework comproses two stages:the low-light enhancement stage and the object detection stage.In the low-light enhancement stage,a lightweight low-light enhancement network is designed,which uses multiple non-reference loss functions for parameter learning,and enhances the image by pixel-level adjustment of the input image with high-order curves.In the object detection stage,BIFPN is introduced to replace the PANet of YOLOv5,while designing a transformer-based detection head to improve the accuracy of small target detection.Moreover,GhostDarkNet53 is utilized based on Ghost module to replace the backbone network of YOLOv5,thereby improving the real-time performance of the model.The experimental results show that the proposed method significantly improves the accuracy of traffic sign detection in low-light scenarios,while satisfying the real-time requirements of autonomous driving.展开更多
Nowadays,the deep learning for object detection has become more popular and is widely adopted in many fields.This paper focuses on the research of LiDAR and camera sensor fusion technology for vehicle detection to ens...Nowadays,the deep learning for object detection has become more popular and is widely adopted in many fields.This paper focuses on the research of LiDAR and camera sensor fusion technology for vehicle detection to ensure extremely high detection accuracy.The proposed network architecture takes full advantage of the deep information of both the LiDAR point cloud and RGB image in object detection.First,the LiDAR point cloud and RGB image are fed into the system.Then a high-resolution feature map is used to generate a reliable 3D object proposal for both the LiDAR point cloud and RGB image.Finally,3D box regression is performed to predict the extent and orientation of vehicles in 3D space.Experiments on the challenging KITTI benchmark show that the proposed approach obtains ideal detection results and the detection time of each frame is about 0.12 s.This approach could establish a basis for further research in autonomous vehicles.展开更多
文摘为满足自动驾驶系统的高效、准确感知的需求,如果仅依靠相机很难实现高精度和鲁棒的3D目标检测。解决这一问题的有效方法是将相机与经济型毫米波雷达传感器相结合,实现更可靠的多模态三维目标检测。融合两者的检测方式不仅提升了环境感知的准确性,还增强了系统的鲁棒性和安全性。本文提出了一种基于毫米波雷达和相机融合的自动驾驶感知算法HPR-Det(historical pillar of ray camera-radar fusion bird ’s eye view for 3D object detection)。具体而言,首先设计了雷达BEV特征提取Radar-PRANet(radar point RCS attention net),由双流雷达主干提取具有两种表征维度的雷达特征和RCS感知的BEV编码器组成,根据雷达特定的RCS特征将雷达特征分散到BEV中。其次,采用历史多帧预测范式HrOP(historical radar of object prediction),设计了长期解码器和短期解码器,同时只在训练期间执行,在推理过程中不引入额外的开销,同时由于本网络输入数据的稀疏性,引入了多模态的历史多帧输入,引导更准确的BEV特征学习。最后,提出了毫米波优化的射线去噪方法,通过将毫米波雷达点云的信息作为先验信息,使用当前帧的毫米波点云特征辅助生成提议,增强对于相机的查询特征表征。本文所提出的算法在大规模公开数据集nuScenes上进行模型训练和实验验证,在骨干为Resnet50的基础上NDS达到56.7%。
基金Supported by National Natural Science Foundation of China(Grant Nos.52225212,52272418,U22A20100)National Key Research and Development Program of China(Grant No.2022YFB2503302).
文摘The development of chassis active safety control technology has improved vehicle stability under extreme conditions.However,its cross-system and multi-functional characteristics make the controller difficult to achieve cooperative goals.In addition,the chassis system,which has high complexity,numerous subsystems,and strong coupling,will also lead to low computing efficiency and poor control effect of the controller.Therefore,this paper proposes a scenario-driven hybrid distributed model predictive control algorithm with variable control topology.This algorithm divides multiple stability regions based on the vehicle’s β−γ phase plane,forming a mapping relationship between the control structure and the vehicle’s state.A control input fusion mechanism within the transition domain is designed to mitigate the problems of system state oscillation and control input jitter caused by switching control structures.Then,a distributed state-space equation with state coupling and input coupling characteristics is constructed,and a weighted local agent cost function in quadratic programming is derived.Through cost coupling,local agents can coordinate global performance goals.Finally,through Simulink/CarSim joint simulation and hardware-in-the-loop(HIL)test,the proposed algorithm is validated to improve vehicle stability while ensuring trajectory tracking accuracy and has good applicability for multi-objective coordinated control.This paper combines the advantages of distributed MPC and decentralized MPC,achieving a balance between approximating the global optimal results and the solution’s efficiency.
基金Supported by National Natural Science Foundation of China(Grant Nos.52072161,U20A20331)China Postdoctoral Science Foundation(Grant No.2019T120398)+2 种基金State Key Laboratory of Automotive Safety and Energy of China(Grant No.KF2016)Vehicle Measurement Control and Safety Key Laboratory of Sichuan Province(Grant No.QCCK2019-002)Young Elite Scientists Sponsorship Program by CAST(Grant No.2018QNRC 001).
文摘Due to the bus characteristics of large quality,high center of gravity and narrow wheelbase,the research of its yaw stability control(YSC)system has become the focus in the field of vehicle system dynamics.However,the tire nonlinear mechanical properties and the effectiveness of the YSC control system are not considered carefully in the current research.In this paper,a novel adaptive nonsingular fast terminal sliding mode(ANFTSM)control scheme for YSC is proposed to improve the bus curve driving stability and safety on slippery roads.Firstly,the STI(Systems Technologies Inc.)tire model,which can effectively reflect the nonlinear coupling relationship between the tire longitudinal force and lateral force,is established based on experimental data and firstly adopted in the bus YSC system design.On this basis,a more accurate bus lateral dynamics model is built and a novel YSC strategy based on ANFTSM,which has the merits of fast transient response,finite time convergence and high robustness against uncertainties and external disturbances,is designed.Thirdly,to solve the optimal allocation problem of the tire forces,whose objective is to achieve the desired direct yaw moment through the effective distribution of the brake force of each tire,the robust least-squares allocation method is adopted.To verify the feasibility,effectiveness and practicality of the proposed bus YSC approach,the TruckSim-Simulink co-simulation results are finally provided.The co-simulation results show that the lateral stability of bus under special driving conditions has been significantly improved.This research proposes a more effective design method for bus YSC system based on a more accurate tire model.
基金Supported by National Natural Science Foundation of China(Grant Nos.U20A20333,61906076,51875255,U1764257,U1762264),Jiangsu Provincial Natural Science Foundation of China(Grant Nos.BK20180100,BK20190853)Six Talent Peaks Project of Jiangsu Province(Grant No.2018-TD-GDZB-022)+1 种基金China Postdoctoral Science Foundation(Grant No.2020T130258)Jiangsu Provincial Key Research and Development Program of China(Grant No.BE2020083-2).
文摘Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,Radars relative to Lidars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution.In order to compensate for the low detection accuracy,incomplete target attributes and poor environmental adaptability of single sensors such as Radar and LiDAR,in this paper,an effective method for high-precision detection and tracking of surrounding targets of autonomous vehicles.By employing the Unscented Kalman Filter,Radar and LiDAR information is effectively fused to achieve high-precision detection of the position and speed information of targets around the autonomous vehicle.Finally,the real vehicle test under various driving environment scenarios is carried out.The experimental results show that the proposed sensor fusion method can effectively detect and track the vehicle peripheral targets with high accuracy.Compared with a single sensor,it has obvious advantages and can improve the intelligence level of autonomous cars.
基金supported by the National Key R&D Program of China(2023YFB2504400)National Natural Science Foundation of China(52372413,U20A20333,U20A20331,52225212,51905223)。
文摘The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and collisions occur more frequently on highways.However,existing studies lack analysis of L3-AV performance in highway maintenance areas.In this study,we investigated the traffic flow and maintenance situation of S68 highway in Zhenjiang City and simulated it in SUMO,then compared the L3-AV takeover details based on length and number of lanes of maintenance area,fitted the prediction of the conflict data using the CatBoost model,and interpreted the prediction results in terms of global and local features by the SHAP theory.The results show that the length of the maintenance area and the number of lanes influence both the initial takeover and the takeover frequency.The relative speed between the L3-AV and the surrounding vehicles plays an important role in the conflict likelihood during traveling in the maintenance area.The findings of this paper are important for optimizing highway maintenance area configurations and developing L3-AV conflict avoidance techniques in specific scenarios.
基金National Natural Science Foundation of China,U20A20331,Long Chen.
文摘Traffic sign detection is a crucial task for autonomous driving systems.However,the performance of deep learning-based algorithms for traffic sign detection is highly affected by the illumination conditions of scenarios.While existing algo-rithms demonstrate high accuracy in well-lit environments,they suffer from low accuracy in low-light scenarios.This paper proposes an end-to-end framework,LLTH-YOLOv5,specifically tailored for traffic sign detection in low-light scenarios,which enhances the input images to improve the detection performance.The proposed framework comproses two stages:the low-light enhancement stage and the object detection stage.In the low-light enhancement stage,a lightweight low-light enhancement network is designed,which uses multiple non-reference loss functions for parameter learning,and enhances the image by pixel-level adjustment of the input image with high-order curves.In the object detection stage,BIFPN is introduced to replace the PANet of YOLOv5,while designing a transformer-based detection head to improve the accuracy of small target detection.Moreover,GhostDarkNet53 is utilized based on Ghost module to replace the backbone network of YOLOv5,thereby improving the real-time performance of the model.The experimental results show that the proposed method significantly improves the accuracy of traffic sign detection in low-light scenarios,while satisfying the real-time requirements of autonomous driving.
基金This work was supported by the National Key Research and Development Program of China(2017YFB0102603,2018YFB0105003)the National Natural Science Foundation of China(51875255,61601203,61773184,U1564201,U1664258,U1764257,U1762264)+3 种基金the Natural Science Foundation of Jiangsu Province(BK20180100)the Six Talent Peaks Project of Jiangsu Province(2018-TD-GDZB-022)the Key Project for the Development of Strategic Emerging Industries of Jiangsu Province(2016-1094)the Key Research and Development Program of Zhenjiang City(GY2017006).
文摘Nowadays,the deep learning for object detection has become more popular and is widely adopted in many fields.This paper focuses on the research of LiDAR and camera sensor fusion technology for vehicle detection to ensure extremely high detection accuracy.The proposed network architecture takes full advantage of the deep information of both the LiDAR point cloud and RGB image in object detection.First,the LiDAR point cloud and RGB image are fed into the system.Then a high-resolution feature map is used to generate a reliable 3D object proposal for both the LiDAR point cloud and RGB image.Finally,3D box regression is performed to predict the extent and orientation of vehicles in 3D space.Experiments on the challenging KITTI benchmark show that the proposed approach obtains ideal detection results and the detection time of each frame is about 0.12 s.This approach could establish a basis for further research in autonomous vehicles.
