Roadside cameras play a crucial role in road traffic, serving as an indispensable part of integrated vehicle-road-cloud systems due to their extensive visibility and monitoring capabilities. Nevertheless, these cameras face challenges in continuously tracking targets across perception domains. To address the issue of tracking vehicles across nonoverlapping perception domains between cameras, we propose a cross-camera vehicle tracking method within a Vehicle-Road-Cloud system that integrates visual and spatiotemporal information. A Gaussian model with microlevel traffic features is trained using vehicle information obtained through online tracking. Finally, the association of vehicle targets is achieved through the Gaussian model combining time and visual feature information. The experimental results indicate that the proposed system demonstrates excellent performance.
{"title":"Roadside Cross-Camera Vehicle Tracking Combining Visual and Spatial-Temporal Information for a Cloud Control System","authors":"Bolin Gao;Zhuxin Li;Dong Zhang;Yanwei Liu;Jiaxing Chen;Ziyuan Lv","doi":"10.26599/JICV.2023.9210034","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210034","url":null,"abstract":"Roadside cameras play a crucial role in road traffic, serving as an indispensable part of integrated vehicle-road-cloud systems due to their extensive visibility and monitoring capabilities. Nevertheless, these cameras face challenges in continuously tracking targets across perception domains. To address the issue of tracking vehicles across nonoverlapping perception domains between cameras, we propose a cross-camera vehicle tracking method within a Vehicle-Road-Cloud system that integrates visual and spatiotemporal information. A Gaussian model with microlevel traffic features is trained using vehicle information obtained through online tracking. Finally, the association of vehicle targets is achieved through the Gaussian model combining time and visual feature information. The experimental results indicate that the proposed system demonstrates excellent performance.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 2","pages":"129-137"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10586907","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141544049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-22DOI: 10.26599/JICV.2023.9210028
Ali Matin;Hussein Dia
This study investigates the attitudes and concerns of the Australian public toward connected and autonomous vehicles (CAVs), and the factors influencing their willingness to adopt this technology. Through a comprehensive survey, a diverse group of respondents provided valuable insights toward various CAV scenarios such as riding in a vehicle with no driver, self-driving public transport, self-driving taxis, and heavy vehicles without drivers. The results highlight the significant impact of safety concerns about automated vehicles on individuals' attitudes across all scenarios. Higher levels of concern were associated with more negative attitudes, and a strong correlation between concerns and opposition underlines the necessity of addressing these apprehensions to build public trust and promote CAV adoption. Interestingly, nearly 70% of respondents felt uncomfortable driving next to a CAV, but they displayed more confidence in adopting automated public transport in the near future. Additionally, around 40% of participants indicated a strong willingness to purchase a CAV, primarily driven by the desire to reduce their carbon footprint and safety considerations. Notably, respondents with health conditions or disability exhibited heightened interest (almost double those without health conditions) in CAV technology. Gender differences emerged in attitudes and preferences toward CAVs, with women expressing a greater level of concern and perceiving higher barriers to CAV deployment. This emphasizes the importance of employing targeted approaches to address the specific concerns of different demographics. The study also underscores the role of trust in technology as a significant barrier to CAV deployment, ranking high among respondents' concerns. To overcome these challenges and facilitate successful CAV deployment, various strategies are suggested, including live demonstrations, dedicated routes for automated public transport, adoption incentives, and addressing liability concerns. The findings from this study offer valuable insights for government agencies, vehicle manufacturers, and stakeholders in promoting the successful implementation of CAVs. By understanding societal acceptance and addressing concerns, decision-makers can devise effective interventions and policies to ensure the safe and widespread adoption of CAVs in Australia. Moreover, vehicle manufacturers can leverage these results to consider design aspects that align with passenger preferences, thereby facilitating the broader acceptance and adoption of CAVs in the future. Finally, this research provides a significant contribution to the understanding of public perception and acceptance of CAVs in the Australian context. By guiding decision-making and informing strategies, the study lays the foundation for a safer and more effective integration of CAVs into the country's transportation landscape.
{"title":"Public Perception of Connected and Automated Vehicles: Benefits, Concerns, and Barriers from an Australian Perspective","authors":"Ali Matin;Hussein Dia","doi":"10.26599/JICV.2023.9210028","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210028","url":null,"abstract":"This study investigates the attitudes and concerns of the Australian public toward connected and autonomous vehicles (CAVs), and the factors influencing their willingness to adopt this technology. Through a comprehensive survey, a diverse group of respondents provided valuable insights toward various CAV scenarios such as riding in a vehicle with no driver, self-driving public transport, self-driving taxis, and heavy vehicles without drivers. The results highlight the significant impact of safety concerns about automated vehicles on individuals' attitudes across all scenarios. Higher levels of concern were associated with more negative attitudes, and a strong correlation between concerns and opposition underlines the necessity of addressing these apprehensions to build public trust and promote CAV adoption. Interestingly, nearly 70% of respondents felt uncomfortable driving next to a CAV, but they displayed more confidence in adopting automated public transport in the near future. Additionally, around 40% of participants indicated a strong willingness to purchase a CAV, primarily driven by the desire to reduce their carbon footprint and safety considerations. Notably, respondents with health conditions or disability exhibited heightened interest (almost double those without health conditions) in CAV technology. Gender differences emerged in attitudes and preferences toward CAVs, with women expressing a greater level of concern and perceiving higher barriers to CAV deployment. This emphasizes the importance of employing targeted approaches to address the specific concerns of different demographics. The study also underscores the role of trust in technology as a significant barrier to CAV deployment, ranking high among respondents' concerns. To overcome these challenges and facilitate successful CAV deployment, various strategies are suggested, including live demonstrations, dedicated routes for automated public transport, adoption incentives, and addressing liability concerns. The findings from this study offer valuable insights for government agencies, vehicle manufacturers, and stakeholders in promoting the successful implementation of CAVs. By understanding societal acceptance and addressing concerns, decision-makers can devise effective interventions and policies to ensure the safe and widespread adoption of CAVs in Australia. Moreover, vehicle manufacturers can leverage these results to consider design aspects that align with passenger preferences, thereby facilitating the broader acceptance and adoption of CAVs in the future. Finally, this research provides a significant contribution to the understanding of public perception and acceptance of CAVs in the Australian context. By guiding decision-making and informing strategies, the study lays the foundation for a safer and more effective integration of CAVs into the country's transportation landscape.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 2","pages":"108-128"},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10537112","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141543908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.26599/JICV.2023.9210031
Amandeep Singh;Sarah Yahoodik;Yovela Murzello;Samuel Petkac;Yusuke Yamani;Siby Samuel
The present study examined the impact of aging on ethical decision-making in simulated critical driving scenarios. 204 participants from North America, grouped into two age groups (18–30 years and 65 years and above), were asked to decide whether their simulated automated vehicle should stay in or change from the current lane in scenarios mimicking the Trolley Problem. Each participant viewed a video clip rendered by the driving simulator at Old Dominion University and pressed the space-bar if they decided to intervene in the control of the simulated automated vehicle in an online experiment. Bayesian hierarchical models were used to analyze participants' responses, response time, and acceptability of utilitarian ethical decision-making. The results showed significant pedestrian placement, age, and time-to-collision (TTC) effects on participants' ethical decisions. When pedestrians were in the right lane, participants were more likely to switch lanes, indicating a utilitarian approach prioritizing pedestrian safety. Younger participants were more likely to switch lanes in general compared to older participants. The results imply that older drivers can maintain their ability to respond to ethically fraught scenarios with their tendency to switch lanes more frequently than younger counterparts, even when the tasks interacting with an automated driving system. The current findings may inform the development of decision algorithms for intelligent and connected vehicles by considering potential ethical dilemmas faced by human drivers across different age groups.
{"title":"Ethical Decision-Making in Older Drivers During Critical Driving Situations: An Online Experiment","authors":"Amandeep Singh;Sarah Yahoodik;Yovela Murzello;Samuel Petkac;Yusuke Yamani;Siby Samuel","doi":"10.26599/JICV.2023.9210031","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210031","url":null,"abstract":"The present study examined the impact of aging on ethical decision-making in simulated critical driving scenarios. 204 participants from North America, grouped into two age groups (18–30 years and 65 years and above), were asked to decide whether their simulated automated vehicle should stay in or change from the current lane in scenarios mimicking the Trolley Problem. Each participant viewed a video clip rendered by the driving simulator at Old Dominion University and pressed the space-bar if they decided to intervene in the control of the simulated automated vehicle in an online experiment. Bayesian hierarchical models were used to analyze participants' responses, response time, and acceptability of utilitarian ethical decision-making. The results showed significant pedestrian placement, age, and time-to-collision (TTC) effects on participants' ethical decisions. When pedestrians were in the right lane, participants were more likely to switch lanes, indicating a utilitarian approach prioritizing pedestrian safety. Younger participants were more likely to switch lanes in general compared to older participants. The results imply that older drivers can maintain their ability to respond to ethically fraught scenarios with their tendency to switch lanes more frequently than younger counterparts, even when the tasks interacting with an automated driving system. The current findings may inform the development of decision algorithms for intelligent and connected vehicles by considering potential ethical dilemmas faced by human drivers across different age groups.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"30-37"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10506787","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.26599/JICV.2023.9210019
Changxi Ma;Fansong Xue
With the increasing number of vehicles, there has been an unprecedented pressure on the operation and maintenance of intelligent transportation systems and transportation infrastructure. In order to achieve faster and more accurate identification of traffic vehicles, computer vision and deep learning technology play a vital role and have made significant advancements. This study summarizes the current research status, latest findings, and future development trends of traditional detection algorithms and deep learning-based detection algorithms. Among the detection algorithms based on deep learning, this study focuses on the representative convolutional neural network models. Specifically, it examines the two-stage and one-stage detection algorithms, which have been extensively utilized in the field of intelligent transportation systems. Compared to traditional detection algorithms, deep learning-based detection algorithms can achieve higher accuracy and efficiency. The single-stage detection algorithm is more efficient for real-time detection, while the two-stage detection algorithm is more accurate than the single-stage detection algorithm. In the follow-up research, it is important to consider the balance between detection efficiency and detection accuracy. Additionally, vehicle missed detection and false detection in complex scenes, such as bad weather and vehicle overlap, should be taken into account. This will ensure better application of the research findings in engineering practice.
{"title":"A Review of Vehicle Detection Methods Based on Computer Vision","authors":"Changxi Ma;Fansong Xue","doi":"10.26599/JICV.2023.9210019","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210019","url":null,"abstract":"With the increasing number of vehicles, there has been an unprecedented pressure on the operation and maintenance of intelligent transportation systems and transportation infrastructure. In order to achieve faster and more accurate identification of traffic vehicles, computer vision and deep learning technology play a vital role and have made significant advancements. This study summarizes the current research status, latest findings, and future development trends of traditional detection algorithms and deep learning-based detection algorithms. Among the detection algorithms based on deep learning, this study focuses on the representative convolutional neural network models. Specifically, it examines the two-stage and one-stage detection algorithms, which have been extensively utilized in the field of intelligent transportation systems. Compared to traditional detection algorithms, deep learning-based detection algorithms can achieve higher accuracy and efficiency. The single-stage detection algorithm is more efficient for real-time detection, while the two-stage detection algorithm is more accurate than the single-stage detection algorithm. In the follow-up research, it is important to consider the balance between detection efficiency and detection accuracy. Additionally, vehicle missed detection and false detection in complex scenes, such as bad weather and vehicle overlap, should be taken into account. This will ensure better application of the research findings in engineering practice.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"1-18"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520219","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.26599/JICV.2023.9210033
Lingshu Zhong;Ho Sheau En;Mingyang Pei;Jingwen Xiong;Tao Wang
As the adoption of Electric Vehicles (EVs) intensifies, two primary challenges emerge: limited range due to battery constraints and extended charging times. The traditional charging stations, particularly those near highways, exacerbate these issues with necessary detours, inconsistent service levels, and unpredictable waiting durations. The emerging technology of dynamic wireless charging lanes (DWCLs) may alleviate range anxiety and eliminate long charging stops; however, the driving speed on DWCL significantly affects charging efficiency and effective charging time. Meanwhile, the existing research has addressed load balancing optimization on Dynamic Wireless Charging (DWC) systems to a limited extent. To address this critical issue, this study introduces an innovative eco-driving speed control strategy, providing a novel solution to the multi-objective optimization problem of speed control on DWCL. We utilize mathematical programming methods and incorporate the longitudinal dynamics of vehicles to provide an accurate physical model of EVs. Three objective functions are formulated to tackle the challenges at hand: reducing travel time, increasing charging efficiency, and achieving load balancing on DWCL, which corresponds to four control strategies. The results of numerical tests indicate that a comprehensive control strategy, which considers all objectives, achieves a minor sacrifice in travel time reduction while significantly improving energy efficiency and load balancing. Furthermore, by defining the energy demand and speed range through an upper operation limit, a relatively superior speed control strategy can be selected. This work contributes to the discourse on DWCL integration into modern transportation systems, enhancing the EV driving experience on major roads.
{"title":"Optimized Speed Control for Electric Vehicles on Dynamic Wireless Charging Lanes: An Eco-Driving Approach","authors":"Lingshu Zhong;Ho Sheau En;Mingyang Pei;Jingwen Xiong;Tao Wang","doi":"10.26599/JICV.2023.9210033","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210033","url":null,"abstract":"As the adoption of Electric Vehicles (EVs) intensifies, two primary challenges emerge: limited range due to battery constraints and extended charging times. The traditional charging stations, particularly those near highways, exacerbate these issues with necessary detours, inconsistent service levels, and unpredictable waiting durations. The emerging technology of dynamic wireless charging lanes (DWCLs) may alleviate range anxiety and eliminate long charging stops; however, the driving speed on DWCL significantly affects charging efficiency and effective charging time. Meanwhile, the existing research has addressed load balancing optimization on Dynamic Wireless Charging (DWC) systems to a limited extent. To address this critical issue, this study introduces an innovative eco-driving speed control strategy, providing a novel solution to the multi-objective optimization problem of speed control on DWCL. We utilize mathematical programming methods and incorporate the longitudinal dynamics of vehicles to provide an accurate physical model of EVs. Three objective functions are formulated to tackle the challenges at hand: reducing travel time, increasing charging efficiency, and achieving load balancing on DWCL, which corresponds to four control strategies. The results of numerical tests indicate that a comprehensive control strategy, which considers all objectives, achieves a minor sacrifice in travel time reduction while significantly improving energy efficiency and load balancing. Furthermore, by defining the energy demand and speed range through an upper operation limit, a relatively superior speed control strategy can be selected. This work contributes to the discourse on DWCL integration into modern transportation systems, enhancing the EV driving experience on major roads.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"52-63"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10499223","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.26599/JICV.2023.9210032
Jia Shi;Yugong Luo;Pengfei Li;Jiawei Wang;Keqiang Li
The on-ramp merging in multi-lane highway scenarios presents challenges due to the complexity of coordinating vehicles' merging and lane-changing behaviors, while ensuring safety and optimizing traffic flow. However, there are few studies that have addressed the merging problem of ramp vehicles and the cooperative lane-change problem of mainline vehicles within a unified framework and proposed corresponding optimization strategies. To tackle this issue, this study adopts a cyber-physical integration perspective and proposes a graph-based solution approach. First, the information of vehicle groups in the physical plane is mapped to the cyber plane, and a dynamic conflict graph is introduced in the cyber space to describe the conflict relationships among vehicle groups. Subsequently, graph decomposition and search strategies are employed to obtain the optimal solution, including the set of mainline vehicles changing lanes, passing sequences for each route, and corresponding trajectories. Finally, the proposed dynamic conflict graph-based algorithm is validated through simulations in continuous traffic with various densities, and its performance is compared with the default algorithm in SUMO. The results demonstrate the effectiveness of the proposed approach in improving vehicle safety and traffic efficiency, particularly in high traffic density scenarios, providing valuable insights for future research in multi-lane merging strategies.
{"title":"Collaborative Multi-Lane on-Ramp Merging Strategy for Connected and Automated Vehicles Using Dynamic Conflict Graph","authors":"Jia Shi;Yugong Luo;Pengfei Li;Jiawei Wang;Keqiang Li","doi":"10.26599/JICV.2023.9210032","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210032","url":null,"abstract":"The on-ramp merging in multi-lane highway scenarios presents challenges due to the complexity of coordinating vehicles' merging and lane-changing behaviors, while ensuring safety and optimizing traffic flow. However, there are few studies that have addressed the merging problem of ramp vehicles and the cooperative lane-change problem of mainline vehicles within a unified framework and proposed corresponding optimization strategies. To tackle this issue, this study adopts a cyber-physical integration perspective and proposes a graph-based solution approach. First, the information of vehicle groups in the physical plane is mapped to the cyber plane, and a dynamic conflict graph is introduced in the cyber space to describe the conflict relationships among vehicle groups. Subsequently, graph decomposition and search strategies are employed to obtain the optimal solution, including the set of mainline vehicles changing lanes, passing sequences for each route, and corresponding trajectories. Finally, the proposed dynamic conflict graph-based algorithm is validated through simulations in continuous traffic with various densities, and its performance is compared with the default algorithm in SUMO. The results demonstrate the effectiveness of the proposed approach in improving vehicle safety and traffic efficiency, particularly in high traffic density scenarios, providing valuable insights for future research in multi-lane merging strategies.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"38-51"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10499221","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As the proliferation and development of automated container terminal continue, the issues of efficiency and safety become increasingly significant. The container yard is one of the most crucial cargo distribution centers in a terminal. Automated Guided Vehicles (AGVs) that carry materials of varying hazard levels through these yards without compromising on the safe transportation of hazardous materials, while also maximizing efficiency, is a complex challenge. This research introduces an algorithm that integrates Long Short-Term Memory (LSTM) neural network with reinforcement learning techniques, specifically Deep Q-Network (DQN), for routing an AGV carrying hazardous materials within a container yard. The objective is to ensure that the AGV carrying hazardous materials efficiently reaches its destination while effectively avoiding AGVs carrying non-hazardous materials. Utilizing real data from the Meishan Port in Ningbo, Zhejiang, China, the actual yard is first abstracted into an undirected graph. Since LSTM neural network can efficiently conveys and represents information in long time sequences and do not causes useful information before long time to be ignored, a two-layer LSTM neural network with 64 neurons per layer was constructed for predicting the motion trajectory of AGVs carrying non-hazardous materials, which are incorporated into the map as background AGVs. Subsequently, DQN is employed to plan the route for an AGV transporting hazardous materials, aiming to reach its destination swiftly while avoiding encounters with other AGVs. Experimental tests have shown that the route planning algorithm proposed in this study improves the level of avoidance of hazardous material AGV in relation to non-hazardous material AGVs. Compared to the method where hazardous material AGV follow the shortest path to their destination, the avoidance efficiency was enhanced by 3.11%. This improvement demonstrates potential strategies for balancing efficiency and safety in automated terminals. Additionally, it provides insights for designing avoidance schemes for autonomous driving AGVs, offering solutions for complex operational environments where safety and efficient navigation are paramount.
{"title":"Enhancing Safety and Efficiency in Automated Container Terminals: Route Planning for Hazardous Material AGV Using LSTM Neural Network and Deep Q-Network","authors":"Fei Li;Junchi Cheng;Zhiqi Mao;Yuhao Wang;Pingfa Feng","doi":"10.26599/JICV.2023.9210041","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210041","url":null,"abstract":"As the proliferation and development of automated container terminal continue, the issues of efficiency and safety become increasingly significant. The container yard is one of the most crucial cargo distribution centers in a terminal. Automated Guided Vehicles (AGVs) that carry materials of varying hazard levels through these yards without compromising on the safe transportation of hazardous materials, while also maximizing efficiency, is a complex challenge. This research introduces an algorithm that integrates Long Short-Term Memory (LSTM) neural network with reinforcement learning techniques, specifically Deep Q-Network (DQN), for routing an AGV carrying hazardous materials within a container yard. The objective is to ensure that the AGV carrying hazardous materials efficiently reaches its destination while effectively avoiding AGVs carrying non-hazardous materials. Utilizing real data from the Meishan Port in Ningbo, Zhejiang, China, the actual yard is first abstracted into an undirected graph. Since LSTM neural network can efficiently conveys and represents information in long time sequences and do not causes useful information before long time to be ignored, a two-layer LSTM neural network with 64 neurons per layer was constructed for predicting the motion trajectory of AGVs carrying non-hazardous materials, which are incorporated into the map as background AGVs. Subsequently, DQN is employed to plan the route for an AGV transporting hazardous materials, aiming to reach its destination swiftly while avoiding encounters with other AGVs. Experimental tests have shown that the route planning algorithm proposed in this study improves the level of avoidance of hazardous material AGV in relation to non-hazardous material AGVs. Compared to the method where hazardous material AGV follow the shortest path to their destination, the avoidance efficiency was enhanced by 3.11%. This improvement demonstrates potential strategies for balancing efficiency and safety in automated terminals. Additionally, it provides insights for designing avoidance schemes for autonomous driving AGVs, offering solutions for complex operational environments where safety and efficient navigation are paramount.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"64-77"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520170","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study aims to propose a decision-making method based on artificial potential fields (APFs) and finite state machines (FSMs) in emergency conditions. This study presents a decision-making method based on APFs and FSMs for emergency conditions. By modeling the longitudinal and lateral potential energy fields of the vehicle, the driving state is identified, and the trigger conditions are provided for path planning during lane changing. In addition, this study also designed the state transition rules based on the longitudinal and lateral virtual forces. It established the vehicle decision-making model based on the finite state machine to ensure driving safety in emergency situations. To illustrate the performance of the decision-making model by considering APFs and finite state machines. The version of the model in the co-simulation platform of MATLAB and CarSim shows that the developed decision model in this study accurately generates driving behaviors of the vehicle at different time intervals. The contributions of this study are two-fold. A hierarchical vehicle state machine decision model is proposed to enhance driving safety in emergency scenarios. Mathematical models for determining the transition thresholds of lateral and longitudinal vehicle states are established based on the vehicle potential field model, leading to the formulation of transition rules between different states of autonomous vehicles (AVs).
{"title":"Intelligent Decision-Making Method for Vehicles in Emergency Conditions Based on Artificial Potential Fields and Finite State Machines","authors":"Xunjia Zheng;Huilan Li;Qiang Zhang;Yonggang Liu;Xing Chen;Hui Liu;Tianhong Luo;Jianjie Gao;Lihong Xia","doi":"10.26599/JICV.2023.9210025","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210025","url":null,"abstract":"This study aims to propose a decision-making method based on artificial potential fields (APFs) and finite state machines (FSMs) in emergency conditions. This study presents a decision-making method based on APFs and FSMs for emergency conditions. By modeling the longitudinal and lateral potential energy fields of the vehicle, the driving state is identified, and the trigger conditions are provided for path planning during lane changing. In addition, this study also designed the state transition rules based on the longitudinal and lateral virtual forces. It established the vehicle decision-making model based on the finite state machine to ensure driving safety in emergency situations. To illustrate the performance of the decision-making model by considering APFs and finite state machines. The version of the model in the co-simulation platform of MATLAB and CarSim shows that the developed decision model in this study accurately generates driving behaviors of the vehicle at different time intervals. The contributions of this study are two-fold. A hierarchical vehicle state machine decision model is proposed to enhance driving safety in emergency scenarios. Mathematical models for determining the transition thresholds of lateral and longitudinal vehicle states are established based on the vehicle potential field model, leading to the formulation of transition rules between different states of autonomous vehicles (AVs).","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 1","pages":"19-29"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10506788","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-19DOI: 10.26599/JICV.2023.9210029
Chunlei Zheng;Yiping Yan;Yang Liu
Throughout much of human history, the vast majority of people lived in small communities. However, in the last few centuries, and particularly in recent decades, there has been a dramatic shift. A massive migration has moved populations from rural to urban areas. United Nations reports state that over 4.3 billion individuals now inhabit urban regions, which accounts for more than half (55% as of 2017) of the global population. In most high-income nations, including Western Europe, the Americas, Australia, Japan, and the Middle East, over 80% of people live in urban areas. This figure ranges from 50% to 80% in upper-middle-income countries like Eastern Europe, East Asia, North Africa, South Africa, and South America (United Nations, Department of Economic and Social Affairs, Population Division, 2019). The urban population is anticipated to rise across all countries in the coming decades, albeit at different rates. By 2050, the global population is expected to reach approximately 9.8 billion, with about 6.7 billion residing in cities and 3.1 billion in rural areas. Despite this rapid urbanization, only around 1% of the Earth's land is allocated for urban and infrastructure development. While urbanization has spurred socio-economic growth, it has also led to significant challenges such as traffic congestion and air pollution. In China, the swift growth of cities has notably expanded urban areas and extended the commuting times of residents. The “2022 Commuting Monitoring Report of Major Chinese Cities” reveals that in 2022, over 14 million people in 44 major Chinese cities experienced extreme commuting, with upwards of 13% spending over an hour in transit (Baidu Maps, 2023). Beijing recorded the highest rate, where 26% of commuters faced this issue.
{"title":"Prospects of eVTOL and Modular Flying Cars in China Urban Settings","authors":"Chunlei Zheng;Yiping Yan;Yang Liu","doi":"10.26599/JICV.2023.9210029","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210029","url":null,"abstract":"Throughout much of human history, the vast majority of people lived in small communities. However, in the last few centuries, and particularly in recent decades, there has been a dramatic shift. A massive migration has moved populations from rural to urban areas. United Nations reports state that over 4.3 billion individuals now inhabit urban regions, which accounts for more than half (55% as of 2017) of the global population. In most high-income nations, including Western Europe, the Americas, Australia, Japan, and the Middle East, over 80% of people live in urban areas. This figure ranges from 50% to 80% in upper-middle-income countries like Eastern Europe, East Asia, North Africa, South Africa, and South America (United Nations, Department of Economic and Social Affairs, Population Division, 2019). The urban population is anticipated to rise across all countries in the coming decades, albeit at different rates. By 2050, the global population is expected to reach approximately 9.8 billion, with about 6.7 billion residing in cities and 3.1 billion in rural areas. Despite this rapid urbanization, only around 1% of the Earth's land is allocated for urban and infrastructure development. While urbanization has spurred socio-economic growth, it has also led to significant challenges such as traffic congestion and air pollution. In China, the swift growth of cities has notably expanded urban areas and extended the commuting times of residents. The “2022 Commuting Monitoring Report of Major Chinese Cities” reveals that in 2022, over 14 million people in 44 major Chinese cities experienced extreme commuting, with upwards of 13% spending over an hour in transit (Baidu Maps, 2023). Beijing recorded the highest rate, where 26% of commuters faced this issue.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"187-189"},"PeriodicalIF":0.0,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10365716","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210010
Changxi Ma;Yuanping Li;Wei Meng
Currently, traffic problems in urban road traffic environments remain severe, traffic pollution and congestion have not been effectively improved, and traffic accidents are still frequent. Traditional traffic signal control methods have little effect on these problems. With the continuous improvement of communication technology and network connections, vehicle speed guidance provides a new idea for solving the above problems and has gradually become a popular topic in academic research. However, its generalization has shortcomings. Therefore, this paper summarizes the research on vehicle speed control strategies in urban road environments and provides suggestions for future research. In this paper, we summarize the existing research in four parts. First, we categorize existing research based on vehicle type. Second, the vehicle speed guidance problem is divided according to the problem research scene. Third, we summarize the existing literature regarding vehicle speed. Finally, we summarize the methods used for speed guidance. Through an analysis of the existing literature, it is concluded that there is a deficiency in the existing research, and suggestions for the future of vehicle speed guidance research are suggested.
{"title":"A Review of Vehicle Speed Control Strategies","authors":"Changxi Ma;Yuanping Li;Wei Meng","doi":"10.26599/JICV.2023.9210010","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210010","url":null,"abstract":"Currently, traffic problems in urban road traffic environments remain severe, traffic pollution and congestion have not been effectively improved, and traffic accidents are still frequent. Traditional traffic signal control methods have little effect on these problems. With the continuous improvement of communication technology and network connections, vehicle speed guidance provides a new idea for solving the above problems and has gradually become a popular topic in academic research. However, its generalization has shortcomings. Therefore, this paper summarizes the research on vehicle speed control strategies in urban road environments and provides suggestions for future research. In this paper, we summarize the existing research in four parts. First, we categorize existing research based on vehicle type. Second, the vehicle speed guidance problem is divided according to the problem research scene. Third, we summarize the existing literature regarding vehicle speed. Finally, we summarize the methods used for speed guidance. Through an analysis of the existing literature, it is concluded that there is a deficiency in the existing research, and suggestions for the future of vehicle speed guidance research are suggested.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"190-201"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409227","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：