Table of Content

28 January 2023, Volume 28 Issue 1 Previous Issue   
---
Intelligent Transportation Systems



For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Intelligent Transportation Systems

Select

Travel Intention of Electric Vehicle Sharing based on Theory of Multiple Motivations BAO Lewen (鲍乐雯), MIAO Rui, ∗ (苗 瑞), CHEN Zhihua (陈志华), ZHANG Bo (张 博), GUO Peng (郭 鹏), MA Yuze (马宇泽) 2023, 28 (1):  1-9.  doi: 10.1007/s12204-023-2563-5 Abstract ( 458 )   PDF (467KB) ( 152 )   Determining the travel intention of residents with shared electric vehicles (EVs) is significant for promoting the development of low-carbon transportation, considering that common problems such as high idle rate and lack of attractiveness still exist. To this end, a structural equation model (SEM) based on the theory of multiple motivations is proposed in this paper. First, the influencing motivations for EV sharing are divided into three categories: consumer-driven, program-driven, and enterprise-driven motivations. Then, the intentions of residents in Shanghai to travel with shared EVs are obtained through a survey questionnaire. Finally, an SEM is constructed to analyze quantitatively the impact of different motivations on the travel intention. The results show that consumer-driven motivations with impact weights from 0.14 to 0.63 have the overwhelming impact on travel intention, compared to program-driven motivations with impact weights from ?0.14 to 0.15 and enterprise-driven motivations with impact weights from 0.02 to 0.06. In terms of consumer-driven motivations, the weight of green travel awareness is the highest. The implications of these results on the policy to enable large-scale implementation of shared EVs are discussed from the perspectives of the resident, enterprise, and government. References | Related Articles | Metrics

Select

Intelligent Driving Assistance System for Safe Expressway Driving in Rainy and Foggy Weather based on IoT YAN Beirui (燕北瑞), FANG Cheng (方 成), QIU Hao (邱 昊), ZHU Wenfeng∗ (朱文峰) 2023, 28 (1):  10-19.  doi: 10.1007/s12204-023-2564-4 Abstract ( 330 )   PDF (2162KB) ( 52 )   The feature bends and tunnels of mountainous expressways are often affected by bad weather, specifically rain and fog, which significantly threaten expressway safety and traffic efficiency. In order to solve this problem, a vehicle–road coordination system based on the Internet of Things (IoT) is developed that can share vehicle–road information in real time, expand the environmental perception range of vehicles, and realize vehicle–road collaboration. It helps improve traffic safety and efficiency. Further, a vehicle–road cooperative driving assistance system model is introduced in this study, and it is based on IoT for improving the driving safety of mountainous expressways. Considering the influence of rain and fog on driving safety, the interaction between rainfall, water film, and adhesion coefficient is analyzed. An intelligent vehicle–road coordination assistance system is constructed that takes in information on weather, road parameters, and vehicle status, and takes the stopping sight distance model as well as rollover and sideslip model as boundary constraints. Tests conducted on a real expressway demonstrated that the assistance system model is helpful in bad weather conditions. This system could promote intelligent development of mountainous expressways. References | Related Articles | Metrics

Select

Action-aware Encoder-Decoder Network for Pedestrian Trajectory Prediction FU Jiawei∗ (傅家威), ZHAO Xu (赵 旭) 2023, 28 (1):  20-27.  doi: 10.1007/s12204-023-2565-3 Abstract ( 273 )   PDF (775KB) ( 88 )   Accurate pedestrian trajectory predictions are critical in self-driving systems, as they are fundamental to the response- and decision-making of ego vehicles. In this study, we focus on the problem of predicting the future trajectory of pedestrians from a first-person perspective. Most existing trajectory prediction methods from the first-person view copy the bird’s-eye view, neglecting the differences between the two. To this end, we clarify the differences between the two views and highlight the importance of action-aware trajectory prediction in the first-person view. We propose a new action-aware network based on an encoder-decoder framework with an action prediction and a goal estimation branch at the end of the encoder. In the decoder part, bidirectional long short-term memory (Bi-LSTM) blocks are adopted to generate the ultimate prediction of pedestrians’ future trajectories. Our method was evaluated on a public dataset and achieved a competitive performance, compared with other approaches. An ablation study demonstrates the effectiveness of the action prediction branch. References | Related Articles | Metrics

Select

Electric vehicle charging situation awareness for charging station ultra-short-term load forecast SHI Yiwei1 (史一炜), LIU Zeyu1 (刘泽宇), FENG Donghan1∗ (冯冬涵), ZHOU Yun1∗ (周 云), ZHANG Kaiyu2 (张开宇), LI Hengjie3 (李恒杰) 2023, 28 (1):  28-38.  doi: 10.1007/s12204-023-2566-2 Abstract ( 242 )   PDF (1518KB) ( 984 )   Electric vehicles (EVs) are expected to be key nodes connecting transportation–electricity–communication networks. Advanced automotive electronics technologies enhance EVs’ perception, computing, and communication capacity, which in turn can boost the operational efficiency of intelligent transportation systems (ITSs). EVs couple the ITS to the power system, providing a promising solution to charging congestion and transformer overload via navigation and forecasting approaches. This study proposes a privacy-preserving EV charging situation awareness framework and method to forecast the ultra-short-term load of charging stations. The proposed method only relies on public information from commercial service providers. In the case study, data are powered by the Baidu LBS cloud and EV-SGCC platform, and the experiment is conducted within an area of Pudong New District in Shanghai. Based on the results, the charging load of charging stations can be adequately forecasted more than 1 min ahead with low communication and computing power requirements. This research provides the basis for further studies on operation optimization and electricity market transaction of charging stations. References | Related Articles | Metrics

Select

Research on Real-time Dynamic Evaluation of Highway Passenger Service Satisfaction Based on Internet LUO Jing1 (罗 京), ZHOU Dai1∗ (周 岱), TAN Yunlong2 (谭云龙), XIA Ganlin3 (夏甘霖), ZHAO Guohua4,5 (赵国华) 2023, 28 (1):  39-51.  doi: 10.1007/s12204-023-2568-0 Abstract ( 187 )   PDF (556KB) ( 38 )   The current method of evaluating passenger satisfaction primarily adopts the traditional static evaluation mode, which can hardly satisfy the dynamic regulatory requirements of highway passenger transport service quality set by industry management departments. In this paper, we summarize the characteristics of real-time dynamic evaluation under the requirements of hierarchical and classified evaluation and analyze the entire process of the one-time travel service of highway passenger transport. We focus on station waiting and in-vehicle services, extract the elements most concerned by passengers as evaluation indexes, and construct a three-level index system. Subsequently, a multi-indicator comprehensive evaluation method based on the analytic hierarchy process and fuzzy comprehensive evaluation is selected to construct a comprehensive evaluation model. By combining with the development level of electronic ticket purchasing and the requirements of satisfaction evaluation, we propose three data collection methods and compare and analyze their strengths and weaknesses. Finally, based on actual survey data, the effectiveness of the model is verified. The verification results show that the real-time dynamic evaluation index system based on the Internet can better satisfy evaluation requirements. References | Related Articles | Metrics

Select

Spatial Temporal Correlation 3D Vehicle Detection and Tracking System with Multiple Surveillance Cameras XUE Weipeng (薛炜彭), WU Minghu (吴明虎), WANG Lin∗ (王 琳) 2023, 28 (1):  52-60.  doi: 10.1007/s12204-023-2567-1 Abstract ( 173 )   PDF (1375KB) ( 50 )   Compared to 3D object detection using a single camera, multiple cameras can overcome some limitations on field-of-view, occlusion, and low detection confidence. This study employs multiple surveillance cameras and develops a cooperative 3D object detection and tracking framework by incorporating temporal and spatial information. The framework consists of a 3D vehicle detection model, cooperatively spatial-temporal relation scheme, and heuristic camera constellation method. Specifically, the proposed cross-camera association scheme combines the geometric relationship between multiple cameras and objects in corresponding detections. The spatial-temporal method is designed to associate vehicles between different points of view at a single timestamp and fulfill vehicle tracking in the time aspect. The proposed framework is evaluated based on a synthetic cooperative dataset and shows high reliability, where the cooperative perception can recall more than 66% of the trajectory instead of 11% for single-point sensing. This could contribute to full-range surveillance for intelligent transportation systems. References | Related Articles | Metrics

Select

Infrastructure-Based Vehicle Localization System for Indoor Parking Lot Using RGB-D Cameras CAO Bingquan1,2,3 (曹炳全), HE Yuesheng1,2,3∗ (贺越生), ZHUANG Hanyang4 (庄瀚洋), YANG Ming1,2,3 (杨 明) 2023, 28 (1):  61-69.  doi: 10.1007/s12204-023-2569-z Abstract ( 223 )   PDF (1606KB) ( 33 )   Accurate vehicle localization is a key technology for autonomous driving tasks in indoor parking lots, such as automated valet parking. Additionally, infrastructure-based cooperative driving systems have become a means to realizing intelligent driving. In this paper, we propose a novel and practical vehicle localization system using infrastructure-based RGB-D cameras for indoor parking lots. In the proposed system, we design a depth data preprocessing method with both simplicity and efficiency to reduce the computational burden resulting from a large amount of data. Meanwhile, the hardware synchronization for all cameras in the sensor network is not implemented owing to the disadvantage that it is extremely cumbersome and would significantly reduce the scalability of our system in mass deployments. Hence, to address the problem of data distortion accompanying vehicle motion, we propose a vehicle localization method by performing template point cloud registration in distributed depth data. Finally, a complete hardware system was built to verify the feasibility of our solution in a real-world environment. Experiments in an indoor parking lot demonstrated the effectiveness and accuracy of the proposed vehicle localization system, with a maximum root mean squared error of 5 cm at 15 Hz compared with the ground truth. References | Related Articles | Metrics

Select

Lidar-Visual-Inertial Odometry with Online Extrinsic Calibration MAO Tianyang (茅天阳), ZHAO Wentao (赵文韬), WANG Jingchuan∗ (王景川), CHEN Weidong (陈卫东) 2023, 28 (1):  70-76.  doi: 10.1007/s12204-023-2570-6 Abstract ( 245 )   PDF (988KB) ( 59 )   To achieve precise localization, autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile platform. Calibration is a time-consuming process, and mechanical distortion will cause extrinsic calibration errors. Therefore, we propose a lidar-visual-inertial odometry, which is combined with an adapted sliding window mechanism and allows for online nonlinear optimization and extrinsic calibration. In the adapted sliding window mechanism, spatial-temporal alignment is performed to manage measurements arriving at different frequencies. In nonlinear optimization with online calibration, visual features, cloud features, and inertial measurement unit (IMU) measurements are used to estimate the ego-motion and perform extrinsic calibration. Extensive experiments were carried out on both public datasets and real-world scenarios. Results indicate that the proposed system outperforms state-of-the-art open-source methods when facing challenging sensor-degenerating conditions. References | Related Articles | Metrics

Select

Indoor Vehicle Positioning Based on Multi-Sensor Data Fusion WANG Mingyang (王明阳), SHI Liangren∗ (时良仁), LI Yuanlong (李元龙) 2023, 28 (1):  77-85.  doi: 10.1007/s12204-023-2571-5 Abstract ( 239 )   PDF (705KB) ( 43 )   This study proposes a Kalman filter-based indoor vehicle positioning method for cases in which the steering angle and rotation speed of the vehicle’s wheels are unknown. By fusing the position and velocity data from the ultra-wideband sensors and acceleration and orientation data from the inertial measurement unit, we developed two algorithms to estimate the real-time position of the vehicle based on a linear Kalman filter and extended Kalman filter, respectively. We then conducted simulations and experiments to examine the performances of the algorithms. In the experiment, the Kalman filtering hyperparameters are configured, and we then ran the two algorithms to determine the positioning precision and accuracy with the ground truth produced via LiDAR. We verified that our method can improve precision and accuracy compared with the raw positioning data and can achieve desirable effects for indoor vehicle positioning when vehicles travel at low speeds. References | Related Articles | Metrics

Select

Ant Colony Algorithm Path Planning Based on Grid Feature Point Extraction LI Erchao∗ (李二超), QI Kuankuan (齐款款) 2023, 28 (1):  86-99.  doi: 10.1007/s12204-023-2572-4 Abstract ( 228 )   PDF (1196KB) ( 114 )   Aimed at the problems of a traditional ant colony algorithm, such as the path search direction and field of view, an inability to find the shortest path, a propensity toward deadlock and an unsmooth path, an ant colony algorithm for use in a new environment is proposed. First, the feature points of an obstacle are extracted to preprocess the grid map environment, which can avoid entering a trap and solve the deadlock problem. Second, these feature points are used as pathfinding access nodes to reduce the node access, with more moving directions to be selected, and the locations of the feature points to be selected determine the range of the pathfinding field of view. Then, based on the feature points, an unequal distribution of pheromones and a two-way parallel path search are used to improve the construction efficiency of the solution, an improved heuristic function is used to enhance the guiding role of the path search, and the pheromone volatilization coefficient is dynamically adjusted to avoid a premature convergence of the algorithm. Third, a Bezier curve is used to smooth the shortest path obtained. Finally, using grid maps with a different complexity and different scales, a simulation comparing the results of the proposed algorithm with those of traditional and other improved ant colony algorithms verifies its feasibility and superiority. References | Related Articles | Metrics

Select

Birds-Eye-View Semantic Segmentation and Voxels Semantic Segmentation Based on Frustum Voxels Modeling and Monocular Camera QIN Chao1 (秦 超), WANG Yafei1 (王亚飞), ZHANG Yuchao2 (张宇超), YIN Chengliang1∗ (殷承良) 2023, 28 (1):  100-113.  doi: 10.1007/s12204-023-2573-3 Abstract ( 213 )   PDF (3885KB) ( 57 )   The semantic segmentation of a bird’s-eye view (BEV) is crucial for environment perception in autonomous driving, which includes the static elements of the scene, such as drivable areas, and dynamic elements such as cars. This paper proposes an end-to-end deep learning architecture based on 3D convolution to predict the semantic segmentation of a BEV, as well as voxel semantic segmentation, from monocular images. The voxelization of scenes and feature transformation from the perspective space to camera space are the key approaches of this model to boost the prediction accuracy. The effectiveness of the proposed method was demonstrated by training and evaluating the model on the NuScenes dataset. A comparison with other state-of-the-art methods showed that the proposed approach outperformed other approaches in the semantic segmentation of a BEV. It also implements voxel semantic segmentation, which cannot be achieved by the state-of-the-art methods. References | Related Articles | Metrics

Select

Cascade Optimization Control of Unmanned Vehicle Path Tracking under Harsh Driving Conditions HUANG Yinggang1 (黄迎港), LUO Wenguang1∗ (罗文广), HUANG Dan2 (黄 丹), LAN Hongli1 (蓝红莉) 2023, 28 (1):  114-125.  doi: 10.1007/s12204-023-2574-2 Abstract ( 168 )   PDF (2166KB) ( 35 )   Under ultra-high-speed and harsh conditions, conventional control methods struggle to ensure the path tracking accuracy and driving stability of unmanned vehicles during the turning process. Therefore, this study proposes a cascade control to solve this problem. Based on the new vehicle error model that considers vehicle tire sideslip and road curvature, the feedforward-parametric adaptive linear quadratic regulator (LQR) and proportional integral control-based speed-keeping controllers are used to compose the path-tracking cascade optimization controller for unmanned vehicles. To improve the adaptability of the unmanned vehicle path-tracking control under harsh driving conditions, the LQR controller parameters are automatically adjusted using a backpropagation neural network, in which the initial weights and thresholds are optimized using the improved grey wolf optimization algorithm according to the driving conditions. The speed-keeping controller reduces the impact on the curve-tracking accuracy under nonlinear vehicle speed variations. Finally, a joint model of MATLAB/Simulink and CarSim was established, and simulations show that the proposed control method can achieve stable entry and exit curves at ultra-high speeds for unmanned vehicles. Under strong wind and ice road conditions, the method exhibits a higher tracking accuracy and is more adaptive and robust to external interference in driving and variable curvature roads than methods such as the feedforward-LQR, preview and pure pursuit controls. References | Related Articles | Metrics

Select

Safety Evaluation of Commercial Vehicle Driving Behavior Based on AHP-CRITIC Algorithm PANG Na1 (庞 娜), LUO Wenguang1∗ (罗文广), WU Ruoyuan1 (吴若园), LAN Hongli1 (蓝红莉), QIN Yongxin1 (覃永新), SU Qi2 (苏 琦) 2023, 28 (1):  126-135.  doi: 10.1007/s12204-023-2575-1 Abstract ( 208 )   PDF (421KB) ( 42 )   To prevent and reduce road traffic accidents and improve driver safety awareness and bad driving behaviors, we propose a safety evaluation method for commercial vehicle driving behavior. Three driving style classification indexes were extracted using driving data from commercial vehicles and four primary and ten secondary safety evaluation indicators. Based on the stability of commercial vehicles transporting goods, the acceleration index is divided into three levels according to the statistical third quartile, and the evaluation expression of the safety index evaluation is established. Drivers were divided into conservative, moderate, and radical using Kmeans++. The weights corresponding to each index were calculated using a combination of the analytic hierarchy process (AHP) and criteria importance through intercriteria correlation (CRITIC), and the driving behavior scores of various drivers were calculated according to the safety index score standard. The established AHP–CRITIC safety evaluation model was verified using the actual driving behavior data of commercial vehicle drivers. The calculation results show that the proposed evaluation model can clearly distinguish between the types of drivers with different driving styles, verifying its rationality and validity. The evaluation results can provide a reference for transportation management departments and enterprises. References | Related Articles | Metrics

Select

Robust Charging Demand Prediction and Charging Network Planning for Heterogeneous Behavior of Electric Vehicles ZHANG Yilun1‡ (张轶伦), XU Sikun2‡ (徐思坤), XU Jie1 (徐 捷), ZENG Xueqi3 (曾学奇), LI Zheng4 (李 铮), XIE Chi5∗ (谢 驰) 2023, 28 (1):  136-149.  doi: 10.1007/s12204-023-2576-0 Abstract ( 175 )   PDF (1054KB) ( 40 )   This study addresses a new charging station network planning problem for smart connected electric vehicles. We embed a charging station choice model into a charging network planning model that explicitly considers the heterogeneity of the charging behavior in a data-driven manner. To cope with the deficiencies from a small size and sparse behavioral data, we propose a robust charging demand prediction method that can significantly reduce the impact of sample errors and missing data. On the basis of these two building blocks, we form and solve a new optimal charging station location and capacity problem by minimizing the construction and charging costs while considering the charging service level, construction budget, and limit to the number of chargers. We use a case study of planning charging stations in Shanghai to validate our contributions and provide managerial insight in this area. References | Related Articles | Metrics

Select

Straight-Going Priority in Hierarchical Control Framework for Right-Turning Vehicle Merging Based on Cooperative Game YANG Jingwena (杨静文), ZHANG Libina (张立彬), WANG Pinga (王 萍), YAO Junfengb∗ (姚俊峰), ZHAO Xiangmob (赵祥模) 2023, 28 (1):  150-160.  doi: 10.1007/s12204-023-2577-z Abstract ( 163 )   PDF (997KB) ( 53 )   With the development of connected and automated vehicles (CAVs), forming strategies could extend from the typically used first-come-first-served rules. It is necessary to consider passing priorities when crossing intersections to prevent conflicts. In this study, a hierarchical strategy based on a cooperative game was developed to improve safety and efficiency during right-turning merging. A right-turn merging conflict model was established to analyze the right-turning vehicle characteristics of the traffic flow. The proposed three-layered hierarchical strategy includes a decision-making layer, a task layer, and an operation layer. A decision-making-layer cooperative game strategy was used to determine the merging priority of straight-going traffic and right-turning flows. In addition, a task-layer cooperative game strategy was designed for the merging sequence. A modified consensus algorithm was utilized to optimize the speed of vehicles in the virtual platoon of the operation layer. Traffic simulations were performed on the PYTHON-SUMO integrated platform to verify the proposed strategy. The simulation results show that, compared with other methods, the proposed hierarchical strategy has the shortest travel time and loss time and performs better than other methods when the straight-going traffic flow increases during right-turning merging at the intersection. The proposed method shows superiority under a significant traffic flow with a threshold of 900 vehicle/(h · lane). This satisfactory application of right-turning merging might be extended to ramps, lane-changing, and other scenarios in the future. References | Related Articles | Metrics