Pub Date : 2024-12-31DOI: 10.1109/OJITS.2024.3522969
Tianyi Li;Mingfeng Shang;Shian Wang;Raphael Stern
With the emergence of vehicles featuring advanced driver-assistance systems like adaptive cruise control (ACC) and additional automated driving functionalities, there has arisen a heightened potential for cyberattacks targeting these automated vehicles (AVs). While overt attacks that lead to collisions are more conspicuous, subtle attacks that slightly modify driving behaviors can cause widespread impacts, including increased congestion, fuel consumption, and crash risks without being easily detected. To address the detection of such attacks, we first present a traffic modeling framework for three types of potential cyberattacks: malicious manipulation of vehicle control commands, data poison attacks, and denial-of-service (DoS) attacks. Subsequently, we examine the consequences of these attacks on both singular vehicle dynamics (micro) and broader traffic flow patterns (macro). We introduce a new anomaly detection model based on generative adversarial networks (GAN) designed for the real-time pinpointing of such attacks using vehicle trajectory data. Numerical results are presented to show the effectiveness of our machine learning strategy in identifying cyberattacks on vehicles equipped with ACC. The proposed approach is observed to outperform contemporary neural network models in detecting irregular driving patterns of ACC vehicles.
{"title":"Detecting Subtle Cyberattacks on Adaptive Cruise Control Vehicles: A Machine Learning Approach","authors":"Tianyi Li;Mingfeng Shang;Shian Wang;Raphael Stern","doi":"10.1109/OJITS.2024.3522969","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3522969","url":null,"abstract":"With the emergence of vehicles featuring advanced driver-assistance systems like adaptive cruise control (ACC) and additional automated driving functionalities, there has arisen a heightened potential for cyberattacks targeting these automated vehicles (AVs). While overt attacks that lead to collisions are more conspicuous, subtle attacks that slightly modify driving behaviors can cause widespread impacts, including increased congestion, fuel consumption, and crash risks without being easily detected. To address the detection of such attacks, we first present a traffic modeling framework for three types of potential cyberattacks: malicious manipulation of vehicle control commands, data poison attacks, and denial-of-service (DoS) attacks. Subsequently, we examine the consequences of these attacks on both singular vehicle dynamics (micro) and broader traffic flow patterns (macro). We introduce a new anomaly detection model based on generative adversarial networks (GAN) designed for the real-time pinpointing of such attacks using vehicle trajectory data. Numerical results are presented to show the effectiveness of our machine learning strategy in identifying cyberattacks on vehicles equipped with ACC. The proposed approach is observed to outperform contemporary neural network models in detecting irregular driving patterns of ACC vehicles.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"11-23"},"PeriodicalIF":4.6,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10819009","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993036","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 : 2024-12-25DOI: 10.1109/OJITS.2024.3521449
José Manuel Gaspar Sánchez;Leonard Bruns;Jana Tumova;Patric Jensfelt;Martin Törngren
Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor noise. These challenges become more evident in highly dynamic environments. This work proposes a probabilistic framework to jointly infer which parts of an environment are statically and which parts are dynamically occupied. We formulate the problem as a Bayesian network and introduce minimal assumptions that significantly reduce the complexity of the problem. Based on those, we derive Transitional Grid Maps (TGMs), an efficient analytical solution. Using real data, we demonstrate how this approach produces better maps than the state-of-the-art by keeping track of both static and dynamic elements and, as a side effect, can help improve existing SLAM algorithms.
{"title":"Transitional Grid Maps: Joint Modeling of Static and Dynamic Occupancy","authors":"José Manuel Gaspar Sánchez;Leonard Bruns;Jana Tumova;Patric Jensfelt;Martin Törngren","doi":"10.1109/OJITS.2024.3521449","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3521449","url":null,"abstract":"Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor noise. These challenges become more evident in highly dynamic environments. This work proposes a probabilistic framework to jointly infer which parts of an environment are statically and which parts are dynamically occupied. We formulate the problem as a Bayesian network and introduce minimal assumptions that significantly reduce the complexity of the problem. Based on those, we derive Transitional Grid Maps (TGMs), an efficient analytical solution. Using real data, we demonstrate how this approach produces better maps than the state-of-the-art by keeping track of both static and dynamic elements and, as a side effect, can help improve existing SLAM algorithms.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"1-10"},"PeriodicalIF":4.6,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10813430","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993035","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 : 2024-12-11DOI: 10.1109/OJITS.2024.3515270
Giovanni Lucente;Mikkel Skov Maarssoe;Sanath Himasekhar Konthala;Anas Abulehia;Reza Dariani;Julian Schindler
Trajectory planning for automated vehicles in traffic has been a challenging task and a hot topic in recent research. The need for flexibility, transparency, interpretability and predictability poses challenges in deploying data-driven approaches in this safety-critical application. This paper proposes DeepGame-TP, a game-theoretical trajectory planner that uses deep learning to model each agent’s cost function and adjust it based on observed behavior. In particular, a LSTM network predicts each agent’s desired speed, forming a penalizing term that reflects aggressiveness in the cost function. Experiments demonstrated significant advantages of this innovative framework, highlighting the adaptability of DeepGame-TP in intersection, overtaking, car following and merging scenarios. It effectively avoids dangerous situations that could arise from incorrect cost function estimates. The approach is suitable for real-time applications, solving the Generalized Nash Equilibrium Problem (GNEP) in scenarios with up to four vehicles in under 100 milliseconds on average.
{"title":"DeepGame-TP: Integrating Dynamic Game Theory and Deep Learning for Trajectory Planning","authors":"Giovanni Lucente;Mikkel Skov Maarssoe;Sanath Himasekhar Konthala;Anas Abulehia;Reza Dariani;Julian Schindler","doi":"10.1109/OJITS.2024.3515270","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3515270","url":null,"abstract":"Trajectory planning for automated vehicles in traffic has been a challenging task and a hot topic in recent research. The need for flexibility, transparency, interpretability and predictability poses challenges in deploying data-driven approaches in this safety-critical application. This paper proposes DeepGame-TP, a game-theoretical trajectory planner that uses deep learning to model each agent’s cost function and adjust it based on observed behavior. In particular, a LSTM network predicts each agent’s desired speed, forming a penalizing term that reflects aggressiveness in the cost function. Experiments demonstrated significant advantages of this innovative framework, highlighting the adaptability of DeepGame-TP in intersection, overtaking, car following and merging scenarios. It effectively avoids dangerous situations that could arise from incorrect cost function estimates. The approach is suitable for real-time applications, solving the Generalized Nash Equilibrium Problem (GNEP) in scenarios with up to four vehicles in under 100 milliseconds on average.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"873-888"},"PeriodicalIF":4.6,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10793110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925364","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}
In the realm of Emergency Medical Services (EMS), the integration of Machine Learning (ML) techniques has emerged as a catalyst for revolutionizing ambulance operations. ML algorithms could play a pivotal role in dynamically allocating resources, devising efficient routes, and predicting demand patterns. By thoroughly reviewing the existing literature and methodologies, this paper provides a comprehensive overview of the approaches used in ambulance allocation, routing, demand estimation and simulation models. We discuss the challenges faced by these methods, emphasizing the need for innovative solutions that can adapt to real-time data and changing emergency patterns. Through this survey, we aim to offer valuable insights into the current state of research and practices, shedding light on potential areas for future exploration and development. The findings presented in this paper serve as a foundation for researchers and practitioners working towards enhancing the efficiency of ambulance deployment in EMS.
{"title":"A Survey of Machine Learning Innovations in Ambulance Services: Allocation, Routing, and Demand Estimation","authors":"Reem Tluli;Ahmed Badawy;Saeed Salem;Mahmoud Barhamgi;Amr Mohamed","doi":"10.1109/OJITS.2024.3514871","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3514871","url":null,"abstract":"In the realm of Emergency Medical Services (EMS), the integration of Machine Learning (ML) techniques has emerged as a catalyst for revolutionizing ambulance operations. ML algorithms could play a pivotal role in dynamically allocating resources, devising efficient routes, and predicting demand patterns. By thoroughly reviewing the existing literature and methodologies, this paper provides a comprehensive overview of the approaches used in ambulance allocation, routing, demand estimation and simulation models. We discuss the challenges faced by these methods, emphasizing the need for innovative solutions that can adapt to real-time data and changing emergency patterns. Through this survey, we aim to offer valuable insights into the current state of research and practices, shedding light on potential areas for future exploration and development. The findings presented in this paper serve as a foundation for researchers and practitioners working towards enhancing the efficiency of ambulance deployment in EMS.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"842-872"},"PeriodicalIF":4.6,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10787208","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858865","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 : 2024-12-09DOI: 10.1109/OJITS.2024.3514536
Pushkin Kachroo;Shaurya Agarwal;Kaan Ozbay
This paper presents the theory and analysis related to the aggregated macroscopic fundamental diagram and presents specific implications for traffic control. The paper presents the aggregation results for the three fundamental variables, traffic density, speed, and traffic flow, and the relationship among the aggregated versions of these for the Greenshields’ model and a piecewise affine model. The development of the algebraic relationships is followed by stochastic analysis to obtain aggregation results in the limiting sense. The dynamics of the aggregated variables are studied, and the idea of dynamic region for aggregation in terms of dynamic reachability is utilized. We also provide an analysis of the error bounds that can be utilized during perimeter control design using MFDs. Finally, the implications of this new analysis are studied in terms of traffic control for an aggregated region, followed by traffic control simulations. Two separate control problems are formulated and studied, which include a) MFD-based control strategy on freeways and b) MFD-based modeling and control of urban sub-networks. Control methodologies used for the two problems include conservation law-based direct control design and feedback linearization control, respectively.
{"title":"Macroscopic Fundamental Diagram: Alternative Theoretical Analysis and Implications for Traffic Control","authors":"Pushkin Kachroo;Shaurya Agarwal;Kaan Ozbay","doi":"10.1109/OJITS.2024.3514536","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3514536","url":null,"abstract":"This paper presents the theory and analysis related to the aggregated macroscopic fundamental diagram and presents specific implications for traffic control. The paper presents the aggregation results for the three fundamental variables, traffic density, speed, and traffic flow, and the relationship among the aggregated versions of these for the Greenshields’ model and a piecewise affine model. The development of the algebraic relationships is followed by stochastic analysis to obtain aggregation results in the limiting sense. The dynamics of the aggregated variables are studied, and the idea of dynamic region for aggregation in terms of dynamic reachability is utilized. We also provide an analysis of the error bounds that can be utilized during perimeter control design using MFDs. Finally, the implications of this new analysis are studied in terms of traffic control for an aggregated region, followed by traffic control simulations. Two separate control problems are formulated and studied, which include a) MFD-based control strategy on freeways and b) MFD-based modeling and control of urban sub-networks. Control methodologies used for the two problems include conservation law-based direct control design and feedback linearization control, respectively.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"826-841"},"PeriodicalIF":4.6,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10787029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858864","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}
Lane changing present a significant challenge for autonomous vehicles, as they must maintain safe driving and optimize time efficiency. This process is strongly affected by traffic environment and driver characteristics. This paper proposed a lane changing control method based on Stackelberg game theory, integrating lane changing decision and trajectory planning while comprehensively considering the driver’s characteristics and the traffic environment. Firstly, considering the common characteristics of lane changing decision and trajectory planning, the two stages are integrated using the leader-follower game theory, enhancing the accuracy of lane changing decisions. Secondly, the cooperative game theory model is employed to design an adaptive weight adjustment strategy for the trajectory tracking controller. The weight coefficients for vehicle stability and path tracking accuracy are dynamically adjusted within the model predictive control method to adapt to the vehicle’s stability state. Simulation results indicate a 24% improvement in decision-making accuracy with the proposed leader-follower game decision method over the rule-based lane changing model. The average relative error in lateral displacement, comparing the vehicle’s actual trajectory to the planned one, is reduced by 6%. Additionally, the variable-weight trajectory tracking control enhances overall tracking performance by over 30% in scenarios involving high speeds and low adhesion. These findings verify the proposed vehicle lane changing method notably improves lane changing safety, stability, and precision.
{"title":"Lane Changing Control of Autonomous Vehicle With Integrated Trajectory Planning Based on Stackelberg Game","authors":"Dongmei Wu;Zhen Li;Changqing Du;Changsheng Liu;Yang Li;Xin Xu","doi":"10.1109/OJITS.2024.3509462","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3509462","url":null,"abstract":"Lane changing present a significant challenge for autonomous vehicles, as they must maintain safe driving and optimize time efficiency. This process is strongly affected by traffic environment and driver characteristics. This paper proposed a lane changing control method based on Stackelberg game theory, integrating lane changing decision and trajectory planning while comprehensively considering the driver’s characteristics and the traffic environment. Firstly, considering the common characteristics of lane changing decision and trajectory planning, the two stages are integrated using the leader-follower game theory, enhancing the accuracy of lane changing decisions. Secondly, the cooperative game theory model is employed to design an adaptive weight adjustment strategy for the trajectory tracking controller. The weight coefficients for vehicle stability and path tracking accuracy are dynamically adjusted within the model predictive control method to adapt to the vehicle’s stability state. Simulation results indicate a 24% improvement in decision-making accuracy with the proposed leader-follower game decision method over the rule-based lane changing model. The average relative error in lateral displacement, comparing the vehicle’s actual trajectory to the planned one, is reduced by 6%. Additionally, the variable-weight trajectory tracking control enhances overall tracking performance by over 30% in scenarios involving high speeds and low adhesion. These findings verify the proposed vehicle lane changing method notably improves lane changing safety, stability, and precision.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"810-825"},"PeriodicalIF":4.6,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10772001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858868","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 : 2024-11-27DOI: 10.1109/OJITS.2024.3507917
Masato Okuda;Kota Yoshida;Takeshi Fujino
In recent intelligent transportation systems (ITS), it is important to recognize pedestrians and avoid collisions. Various sensors are used to detect pedestrians, and some research on pedestrian detection uses a visible light (RGB) camera and a far-infrared (FIR) camera. FIR cameras are significantly affected by ambient temperatures such as summer and winter. However, few studies have focused on this property when evaluating pedestrian detection accuracy. Therefore, this paper investigates the effect of temperature change in real-time multispectral pedestrian detection. We created an original dataset with three subsets, Hot, Intermediate, and Cold, and evaluated temperature effects by changing the subsets during training and testing. We first evaluated YOLOv8s-4ch, which simply extended the input layer of YOLOv8 from 3 channels of RGB to 4 channels of RGB-FIR. To further improve detection performance, we built a new model called YOLOv8s-2stream. This model has two backbones for RGB and FIR, and fuses their feature maps in each resolution. We found that the model trained on a specific temperature subset dropped the test accuracy in other subsets. On the other hand, when training using a Mix set covering all temperature sets (Hot, Inter., Cold), the model achieved the highest accuracy through all conditions. Moreover, our YOLOv8s-2stream has improved by 3.9 points of accuracy (AP@0.5:0.95) compared to YOLOv8s-4ch, and achieved 73 FPS inference speed on Jetson.
{"title":"Realtime Multispectral Pedestrian Detection With Visible and Far-Infrared Under Ambient Temperature Changing","authors":"Masato Okuda;Kota Yoshida;Takeshi Fujino","doi":"10.1109/OJITS.2024.3507917","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3507917","url":null,"abstract":"In recent intelligent transportation systems (ITS), it is important to recognize pedestrians and avoid collisions. Various sensors are used to detect pedestrians, and some research on pedestrian detection uses a visible light (RGB) camera and a far-infrared (FIR) camera. FIR cameras are significantly affected by ambient temperatures such as summer and winter. However, few studies have focused on this property when evaluating pedestrian detection accuracy. Therefore, this paper investigates the effect of temperature change in real-time multispectral pedestrian detection. We created an original dataset with three subsets, Hot, Intermediate, and Cold, and evaluated temperature effects by changing the subsets during training and testing. We first evaluated YOLOv8s-4ch, which simply extended the input layer of YOLOv8 from 3 channels of RGB to 4 channels of RGB-FIR. To further improve detection performance, we built a new model called YOLOv8s-2stream. This model has two backbones for RGB and FIR, and fuses their feature maps in each resolution. We found that the model trained on a specific temperature subset dropped the test accuracy in other subsets. On the other hand, when training using a Mix set covering all temperature sets (Hot, Inter., Cold), the model achieved the highest accuracy through all conditions. Moreover, our YOLOv8s-2stream has improved by 3.9 points of accuracy (AP@0.5:0.95) compared to YOLOv8s-4ch, and achieved 73 FPS inference speed on Jetson.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"797-809"},"PeriodicalIF":4.6,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10770282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844534","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 : 2024-11-07DOI: 10.1109/OJITS.2024.3493461
Amirhossein Samii;Nikolaos Bekiaris-Liberis
We develop a predictor-based cooperative adaptive cruise control (CACC) design for platoons with heterogeneous vehicles, whose dynamics are described by a third-order linear system subject to actuators delays, which are distinct for each individual vehicle. The design achieves individual vehicle stability, string stability, and zero, steady-state speed/spacing tracking errors, relying on a nominal, constant time headway (CTH)-type CACC design that achieves these specifications when all actuators’ delays are zero. This is achieved owing to the delay-compensating mechanism, of the CACC law introduced, for long delays and despite the fact that each vehicle’s dynamics are subject to different input delays, which makes the available predictor-feedback CACC designs inapplicable. The proofs of individual vehicle stability, string stability, and regulation rely on employment of an input-output approach on the frequency domain. We present consistent simulation results, including an example in which we employ real traffic data for the trajectory of the leading vehicle and an example via which we compare the performance of our design with the existing, predictor-feedback CACC and predictor-based ACC laws. In addition, we study numerically the robustness properties with respect to string stability of our predictor-based CACC design to (uncertain) communication delays. Thus, our numerical results validate the performance of the design in realistic scenarios and as compared with related, existing control laws.
{"title":"Predictor-Based CACC Design for Heterogeneous Vehicles With Distinct Input Delays","authors":"Amirhossein Samii;Nikolaos Bekiaris-Liberis","doi":"10.1109/OJITS.2024.3493461","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3493461","url":null,"abstract":"We develop a predictor-based cooperative adaptive cruise control (CACC) design for platoons with heterogeneous vehicles, whose dynamics are described by a third-order linear system subject to actuators delays, which are distinct for each individual vehicle. The design achieves individual vehicle stability, string stability, and zero, steady-state speed/spacing tracking errors, relying on a nominal, constant time headway (CTH)-type CACC design that achieves these specifications when all actuators’ delays are zero. This is achieved owing to the delay-compensating mechanism, of the CACC law introduced, for long delays and despite the fact that each vehicle’s dynamics are subject to different input delays, which makes the available predictor-feedback CACC designs inapplicable. The proofs of individual vehicle stability, string stability, and regulation rely on employment of an input-output approach on the frequency domain. We present consistent simulation results, including an example in which we employ real traffic data for the trajectory of the leading vehicle and an example via which we compare the performance of our design with the existing, predictor-feedback CACC and predictor-based ACC laws. In addition, we study numerically the robustness properties with respect to string stability of our predictor-based CACC design to (uncertain) communication delays. Thus, our numerical results validate the performance of the design in realistic scenarios and as compared with related, existing control laws.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"783-796"},"PeriodicalIF":4.6,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10746502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713821","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 : 2024-11-06DOI: 10.1109/OJITS.2024.3492211
Lantao Li;Wenqi Zhang;Xiaoxue Wang;Tao Cui;Chen Sun
Multi-agent multi-sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the occluded zone of individual vehicular perception system and further enhancing the overall safety of autonomous driving system. This technique relies heavily on the reliability and availability of vehicle-to-everything (V2X) communication. In practical cooperative perception application scenarios, the non-line-of-sight (NLOS) issue causes occluded zones for not only the perception system but also V2X direct communication, especially for busy traffic scenarios. Cooperative perception can address the NLOS issue for vehicular perception systems once. However, to ensure effective real-world implementation, we must also solve the NLOS challenge a second time for the communication systems that support cooperative perception, NLOS “dies” twice. To counteract underlying communication issues, we introduce an abstract perception matrix matching method for quick sensor fusion matching procedures and mobility-height hybrid relay determination procedures, proactively improving the efficiency and performance of V2X communication to serve the upper layer application fusion requirements. To demonstrate the effectiveness of our solution, a new simulation framework is designed to consider autonomous driving, cooperative perception and V2X communication in general, paving the way for end-to-end performance evaluation and further solution derivation.
{"title":"NLOS Dies Twice: Challenges and Solutions of V2X for Cooperative Perception","authors":"Lantao Li;Wenqi Zhang;Xiaoxue Wang;Tao Cui;Chen Sun","doi":"10.1109/OJITS.2024.3492211","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3492211","url":null,"abstract":"Multi-agent multi-sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the occluded zone of individual vehicular perception system and further enhancing the overall safety of autonomous driving system. This technique relies heavily on the reliability and availability of vehicle-to-everything (V2X) communication. In practical cooperative perception application scenarios, the non-line-of-sight (NLOS) issue causes occluded zones for not only the perception system but also V2X direct communication, especially for busy traffic scenarios. Cooperative perception can address the NLOS issue for vehicular perception systems once. However, to ensure effective real-world implementation, we must also solve the NLOS challenge a second time for the communication systems that support cooperative perception, NLOS “dies” twice. To counteract underlying communication issues, we introduce an abstract perception matrix matching method for quick sensor fusion matching procedures and mobility-height hybrid relay determination procedures, proactively improving the efficiency and performance of V2X communication to serve the upper layer application fusion requirements. To demonstrate the effectiveness of our solution, a new simulation framework is designed to consider autonomous driving, cooperative perception and V2X communication in general, paving the way for end-to-end performance evaluation and further solution derivation.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"774-782"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10745605","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713822","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 : 2024-11-05DOI: 10.1109/OJITS.2024.3492115
Alexander Seiffer;Michael Frey;Frank Gauterin
Wheel-selective drives on the steered axle of a vehicle with Ackermann steering allow for the generation of steering torque without the use of a steering actuator. If different drive torques are applied to the left and right driven wheels, their effect on the steering torque is not balanced, and a resulting steering torque remains (differential steering). Thus, the function of a steering actuator can be replaced, e.g., in case of a failure. Previous studies have demonstrated the effectiveness of controlling a vehicle using differential steering. However, the vehicle dynamics during the failure-induced transition from actuator-based to differential steering control have not been thoroughly investigated. In this work, we utilize a cascaded vehicle dynamics control approach with control allocation to distribute the total drive and steering torques to the available actuators in an overactuated chassis system. Based on both simulation studies and validation experiments with a demonstrator vehicle, we investigate the vehicle dynamics immediately following actuator failures. Our cascaded approach ensures precise vehicle guidance in both nominal and redundancy mode via differential steering. After a sudden actuator failure, vehicle guidance is reliably maintained, even in dynamic driving conditions, as the approach also considers the effect of drive torque distribution on the total yaw torque (torque vectoring). The analyses conducted using the proposed approach demonstrate that a safe transition to cross-actuator functional redundancy after an actuator failure is achievable. Consequently, differential steering can be evaluated as a suitable basis for cross-actuator functional redundancy concepts to enable fault-tolerant operation of steer-by-wire systems.
{"title":"Control Allocation Approach Using Differential Steering to Compensate for Steering Actuator Failure","authors":"Alexander Seiffer;Michael Frey;Frank Gauterin","doi":"10.1109/OJITS.2024.3492115","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3492115","url":null,"abstract":"Wheel-selective drives on the steered axle of a vehicle with Ackermann steering allow for the generation of steering torque without the use of a steering actuator. If different drive torques are applied to the left and right driven wheels, their effect on the steering torque is not balanced, and a resulting steering torque remains (differential steering). Thus, the function of a steering actuator can be replaced, e.g., in case of a failure. Previous studies have demonstrated the effectiveness of controlling a vehicle using differential steering. However, the vehicle dynamics during the failure-induced transition from actuator-based to differential steering control have not been thoroughly investigated. In this work, we utilize a cascaded vehicle dynamics control approach with control allocation to distribute the total drive and steering torques to the available actuators in an overactuated chassis system. Based on both simulation studies and validation experiments with a demonstrator vehicle, we investigate the vehicle dynamics immediately following actuator failures. Our cascaded approach ensures precise vehicle guidance in both nominal and redundancy mode via differential steering. After a sudden actuator failure, vehicle guidance is reliably maintained, even in dynamic driving conditions, as the approach also considers the effect of drive torque distribution on the total yaw torque (torque vectoring). The analyses conducted using the proposed approach demonstrate that a safe transition to cross-actuator functional redundancy after an actuator failure is achievable. Consequently, differential steering can be evaluated as a suitable basis for cross-actuator functional redundancy concepts to enable fault-tolerant operation of steer-by-wire systems.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"756-773"},"PeriodicalIF":4.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10742943","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713878","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：