Pub Date : 2025-01-30DOI: 10.1109/OJITS.2025.3536469
Hiroya Tanaka;Keita Funayama
We demonstrate directional vehicular traffic using a two-dimensional honeycomb-shaped topological structure. We consider a hexagonal street network modeled with vertices and edges, and numerically simulate vehicular transport as a symmetric random walk between vertices. We show that two topologically protected modes lead to traffic flows in orthogonal directions. Additionally, we introduce a synthesized mode that combines topological edge modes. This synthesized mode enables traffic to flow in specific direction by adjusting the combined weights. Our investigation offers an approach for optimizing urban traffic management, enhancing traffic efficiency, and reducing congestion in urban environments.
{"title":"Designing Directional Traffic Flow With Edge Mode Combination in 2-D Topological Structures","authors":"Hiroya Tanaka;Keita Funayama","doi":"10.1109/OJITS.2025.3536469","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3536469","url":null,"abstract":"We demonstrate directional vehicular traffic using a two-dimensional honeycomb-shaped topological structure. We consider a hexagonal street network modeled with vertices and edges, and numerically simulate vehicular transport as a symmetric random walk between vertices. We show that two topologically protected modes lead to traffic flows in orthogonal directions. Additionally, we introduce a synthesized mode that combines topological edge modes. This synthesized mode enables traffic to flow in specific direction by adjusting the combined weights. Our investigation offers an approach for optimizing urban traffic management, enhancing traffic efficiency, and reducing congestion in urban environments.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"109-115"},"PeriodicalIF":4.6,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858188","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465602","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 : 2025-01-27DOI: 10.1109/OJITS.2025.3534516
{"title":"2024 Index IEEE Open Journal of Intelligent Transportation Systems Vol. 5","authors":"","doi":"10.1109/OJITS.2025.3534516","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3534516","url":null,"abstract":"","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"889-904"},"PeriodicalIF":4.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10854583","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143360882","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 : 2025-01-22DOI: 10.1109/OJITS.2025.3532777
Simon Speth;Maximilian Trien;Dominik Kufer;Alexander Pretschner
Robustness testing is crucial for verifying autonomous vehicles, especially for safety-critical deep learning components like light detection and ranging (LiDAR) object detectors. Metamorphic testing (MT) assesses the robustness by automatically generating test cases based on abstract system specifications known as metamorphic relations (MRs). However, a key challenge is ensuring a traceable safety argumentation for MRs that is in line with industry standards. To ensure this traceability, we derive seven traceable metamorphic transformations from defects identified through interviews with industry experts. Another challenge is prioritizing failures by safety criticality, as not all failing test cases, as evaluated by current intersection over union (IoU)-based metamorphic oracles, pose the same safety risk. We address this by introducing novel egocentric test oracles based on traffic participants’ bounding boxes shifted into or out of the ego vehicle’s expected lane. Testing five LiDAR object detection systems working on two datasets by executing half a million metamorphic test cases (MTCs) shows that the number of failures decreases from 48k using IoU metrics to 342 safety-critical failures with our novel test oracle “shift out of ego lane.” This reduction enables testers to stay within the test analysis budget and, hence, manually analyze each failed MTC by prioritizing safety-critical test failures.
{"title":"Safety-Critical Oracles for Metamorphic Testing of Deep Learning LiDAR Point Cloud Object Detectors","authors":"Simon Speth;Maximilian Trien;Dominik Kufer;Alexander Pretschner","doi":"10.1109/OJITS.2025.3532777","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3532777","url":null,"abstract":"Robustness testing is crucial for verifying autonomous vehicles, especially for safety-critical deep learning components like light detection and ranging (LiDAR) object detectors. Metamorphic testing (MT) assesses the robustness by automatically generating test cases based on abstract system specifications known as metamorphic relations (MRs). However, a key challenge is ensuring a traceable safety argumentation for MRs that is in line with industry standards. To ensure this traceability, we derive seven traceable metamorphic transformations from defects identified through interviews with industry experts. Another challenge is prioritizing failures by safety criticality, as not all failing test cases, as evaluated by current intersection over union (IoU)-based metamorphic oracles, pose the same safety risk. We address this by introducing novel egocentric test oracles based on traffic participants’ bounding boxes shifted into or out of the ego vehicle’s expected lane. Testing five LiDAR object detection systems working on two datasets by executing half a million metamorphic test cases (MTCs) shows that the number of failures decreases from 48k using IoU metrics to 342 safety-critical failures with our novel test oracle “shift out of ego lane.” This reduction enables testers to stay within the test analysis budget and, hence, manually analyze each failed MTC by prioritizing safety-critical test failures.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"95-108"},"PeriodicalIF":4.6,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10849578","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361044","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 : 2025-01-21DOI: 10.1109/OJITS.2025.3532389
Viktoria Afxentiou;Tanya Vladimirova
Weather image classification is a critical component of the vision systems in autonomous driving systems (ADSs), facilitating accurate decision-making across diverse driving conditions. Adverse weather conditions (AWCs) can significantly impair sensor data quality, diminishing the ADSs’ ability to interpret the surrounding environment. It is, therefore, essential for ADSs to effectively perceive and adapt to AWCs, ensuring enhanced performance and safety. This paper introduces a novel evaluation methodology for classifying AWC images using Convolutional Neural Network (CNN) models, with the goal of assessing their effectiveness for use in ADSs. The methodology provides a structured process for evaluating CNN models, taking into account key factors such as architectural designs, model sizes, diverse datasets, AWC scenarios, and real-time performance. A bespoke design framework is developed to guide the experimental modelling work, incorporating a range of representative CNN-based classification approaches and a variety of AWCs datasets and weather scenarios. This is followed by a comprehensive comparative performance analysis for both single-label and multi-label classification of AWCs images, which is grounded in an extensive experimental modelling effort and serves the purpose of validating the proposed novel evaluation methodology. The analysis systematically evaluates the performance of the targeted CNN approaches under consistent conditions, utilizing the same datasets and weather scenarios to provide a thorough and reliable comparison. Additionally, it includes performance testing on a small-scale embedded computing platform to examine real-time applicability. The findings and insights from this study aim to help researchers identify the most suitable CNN-based weather image classification approaches for their ADS application, ensuring alignment with their performance and operational requirements.
{"title":"Evaluation of CNN-Based Approaches to Adverse Weather Image Classification for Autonomous Driving Systems","authors":"Viktoria Afxentiou;Tanya Vladimirova","doi":"10.1109/OJITS.2025.3532389","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3532389","url":null,"abstract":"Weather image classification is a critical component of the vision systems in autonomous driving systems (ADSs), facilitating accurate decision-making across diverse driving conditions. Adverse weather conditions (AWCs) can significantly impair sensor data quality, diminishing the ADSs’ ability to interpret the surrounding environment. It is, therefore, essential for ADSs to effectively perceive and adapt to AWCs, ensuring enhanced performance and safety. This paper introduces a novel evaluation methodology for classifying AWC images using Convolutional Neural Network (CNN) models, with the goal of assessing their effectiveness for use in ADSs. The methodology provides a structured process for evaluating CNN models, taking into account key factors such as architectural designs, model sizes, diverse datasets, AWC scenarios, and real-time performance. A bespoke design framework is developed to guide the experimental modelling work, incorporating a range of representative CNN-based classification approaches and a variety of AWCs datasets and weather scenarios. This is followed by a comprehensive comparative performance analysis for both single-label and multi-label classification of AWCs images, which is grounded in an extensive experimental modelling effort and serves the purpose of validating the proposed novel evaluation methodology. The analysis systematically evaluates the performance of the targeted CNN approaches under consistent conditions, utilizing the same datasets and weather scenarios to provide a thorough and reliable comparison. Additionally, it includes performance testing on a small-scale embedded computing platform to examine real-time applicability. The findings and insights from this study aim to help researchers identify the most suitable CNN-based weather image classification approaches for their ADS application, ensuring alignment with their performance and operational requirements.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"204-229"},"PeriodicalIF":4.6,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10848144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570887","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 : 2025-01-20DOI: 10.1109/OJITS.2025.3525887
{"title":"IEEE OPEN JOURNAL OF THE INTELLIGENT TRANSPORTATION SYSTEMS SOCIETY","authors":"","doi":"10.1109/OJITS.2025.3525887","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3525887","url":null,"abstract":"","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"C2-C2"},"PeriodicalIF":4.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10847636","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993034","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 : 2025-01-20DOI: 10.1109/OJITS.2025.3531363
S. Shahkar
GNSS-independent localization is one of the most prominent research problems in aerial autonomous systems navigation, especially in certain applications where Simultaneous Localization and Mapping (SLAM) methods are inapplicable due to the complexity of the environment, or in open-air spaces where a flock of Autonomous Aerial Vehicles (AAVs) navigate in a GNSS-independent fashion. This paper introduces a filter through which AAVs form a multi-agent Cellular Vehicle-to-Everything (C-V2X) network to exchange their estimated positions, and eventually achieve a group consensus over the true position of each vehicle. The localization error correction takes place in the filter with reference to the AAV’s relative range from neighbouring vehicles, that is measured by onboard ranging devices. It is shown that in ideal situations where rangefinder errors can be neglected, cooperative localization yields perfect localization, if the network is sufficiently large and sufficiently connected. It is also shown that the accuracy of cooperative localization is superior to the existing least-mean-square-error based techniques, where a centralized controller augments the positioning accuracy of the flock. Cooperative localization is also favourable due to the fact that the process is computationally affordable and fully distributed. Theoretical derivations and results have been validated through case studies and Monte Carlo simulations, and suggest cooperative localization as a complementary navigation technique to odometery, and other advanced solutions that are available in the literature.
{"title":"Cooperative Localization of Multi-Agent Autonomous Aerial Vehicle (AAV) Networks in Intelligent Transportation Systems","authors":"S. Shahkar","doi":"10.1109/OJITS.2025.3531363","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3531363","url":null,"abstract":"GNSS-independent localization is one of the most prominent research problems in aerial autonomous systems navigation, especially in certain applications where Simultaneous Localization and Mapping (SLAM) methods are inapplicable due to the complexity of the environment, or in open-air spaces where a flock of Autonomous Aerial Vehicles (AAVs) navigate in a GNSS-independent fashion. This paper introduces a filter through which AAVs form a multi-agent Cellular Vehicle-to-Everything (C-V2X) network to exchange their estimated positions, and eventually achieve a group consensus over the true position of each vehicle. The localization error correction takes place in the filter with reference to the AAV’s relative range from neighbouring vehicles, that is measured by onboard ranging devices. It is shown that in ideal situations where rangefinder errors can be neglected, cooperative localization yields perfect localization, if the network is sufficiently large and sufficiently connected. It is also shown that the accuracy of cooperative localization is superior to the existing least-mean-square-error based techniques, where a centralized controller augments the positioning accuracy of the flock. Cooperative localization is also favourable due to the fact that the process is computationally affordable and fully distributed. Theoretical derivations and results have been validated through case studies and Monte Carlo simulations, and suggest cooperative localization as a complementary navigation technique to odometery, and other advanced solutions that are available in the literature.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"49-66"},"PeriodicalIF":4.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10845814","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184134","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 : 2025-01-20DOI: 10.1109/OJITS.2025.3525889
{"title":"IEEE Open Journal of Intelligent Transportation Systems Instructions for Authors","authors":"","doi":"10.1109/OJITS.2025.3525889","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3525889","url":null,"abstract":"","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"C3-C3"},"PeriodicalIF":4.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10847606","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993033","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 : 2025-01-20DOI: 10.1109/OJITS.2025.3531549
Jonas Vogt;Hans D. Schotten;Horst Wieker
For decades, systems in the mobility sector have been maintained as discrete entities. It is imperative that they collaborate in order to enhance traffic safety and efficiency, while simultaneously reducing environmental pollution. The protocols employed in the formally separated ecosystems demonstrate disparate behaviors and data representations. In order to facilitate connectivity between these ecosystems, we propose the introduction of the Intelligent Transportation System Protocol Interoperability Evaluation (ITS-PIE). The evaluation method allows system architects and developers to analyze existing protocols in a six-step process. The initial step is the assessment of interdependencies, which identifies any formal or informal correlation between two protocol specifications. The second step is the formal classification of the protocols’ informal and formal descriptions, which emphasizes the specification’s similarities and differences. The formal comparison calculates the consensual parallelisms between the formal specifications. The data evaluation defines tooling to describe the specifications in a way that an automated transition can be conducted. The protocols’ architecture context evaluation displays the framework conditions. The final step is a situation-dependent interpretation. Two illustrative examples are provided herein to illustrate the advantages of the evaluation and to highlight the principal challenges that arise during the process.
{"title":"Intelligent Transportation System Protocol Interoperability Evaluation","authors":"Jonas Vogt;Hans D. Schotten;Horst Wieker","doi":"10.1109/OJITS.2025.3531549","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3531549","url":null,"abstract":"For decades, systems in the mobility sector have been maintained as discrete entities. It is imperative that they collaborate in order to enhance traffic safety and efficiency, while simultaneously reducing environmental pollution. The protocols employed in the formally separated ecosystems demonstrate disparate behaviors and data representations. In order to facilitate connectivity between these ecosystems, we propose the introduction of the Intelligent Transportation System Protocol Interoperability Evaluation (ITS-PIE). The evaluation method allows system architects and developers to analyze existing protocols in a six-step process. The initial step is the assessment of interdependencies, which identifies any formal or informal correlation between two protocol specifications. The second step is the formal classification of the protocols’ informal and formal descriptions, which emphasizes the specification’s similarities and differences. The formal comparison calculates the consensual parallelisms between the formal specifications. The data evaluation defines tooling to describe the specifications in a way that an automated transition can be conducted. The protocols’ architecture context evaluation displays the framework conditions. The final step is a situation-dependent interpretation. Two illustrative examples are provided herein to illustrate the advantages of the evaluation and to highlight the principal challenges that arise during the process.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"67-94"},"PeriodicalIF":4.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10845830","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143107050","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 : 2025-01-16DOI: 10.1109/OJITS.2025.3530516
Călin Andrei Badea;Andrija Vidosavljević;Joost Ellerbroek;Jacco Hoekstra
Very-low-level (VLL) urban air operations have been extensively investigated as a solution for mitigating congestion in cities. However, the manner in which the management of such traffic should be performed is still actively investigated. One important component of such a system is the conflict detection and resolution (CD&R), mainly composed of the strategic and tactical CD&R module. While many approaches towards these have been studied, insufficient analysis has been conducted on their compatibility when functioning within a unified, hybrid system. Additionally, their robustness to operational uncertainties such as wind and departure delays is often overlooked. In this work, we investigate the performance of strategic planing methods when combined with tactical CD&R and subjected to a wide range of traffic demand levels and uncertainty conditions. Simulations indicate that the performance of the strategic deconfliction module is highly sensitive to the presence of wind and delay. This decline in performance is partially mitigated by the tactical deconfliction module. Thus, the results suggest that increased use of tactical CD&R could lessen the required level of detail of strategic deconfliction methods, leading to improved compatibility between the two modules.
{"title":"Evaluating the Synergy of Conflict Detection and Resolution Services for Constrained Urban Airspace","authors":"Călin Andrei Badea;Andrija Vidosavljević;Joost Ellerbroek;Jacco Hoekstra","doi":"10.1109/OJITS.2025.3530516","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3530516","url":null,"abstract":"Very-low-level (VLL) urban air operations have been extensively investigated as a solution for mitigating congestion in cities. However, the manner in which the management of such traffic should be performed is still actively investigated. One important component of such a system is the conflict detection and resolution (CD&R), mainly composed of the strategic and tactical CD&R module. While many approaches towards these have been studied, insufficient analysis has been conducted on their compatibility when functioning within a unified, hybrid system. Additionally, their robustness to operational uncertainties such as wind and departure delays is often overlooked. In this work, we investigate the performance of strategic planing methods when combined with tactical CD&R and subjected to a wide range of traffic demand levels and uncertainty conditions. Simulations indicate that the performance of the strategic deconfliction module is highly sensitive to the presence of wind and delay. This decline in performance is partially mitigated by the tactical deconfliction module. Thus, the results suggest that increased use of tactical CD&R could lessen the required level of detail of strategic deconfliction methods, leading to improved compatibility between the two modules.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"24-36"},"PeriodicalIF":4.6,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10843729","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143107049","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 : 2025-01-16DOI: 10.1109/OJITS.2025.3530268
Yuxiang Feng;Qiming Ye;Eduardo Candela;Jose Javier Escribano-Macias;Bo Hu;Yiannis Demiris;Panagiotis Angeloudis
Autonomous vehicles need to continuously analyse the driving context and establish a comprehensive understanding of the dynamic traffic environment. To ensure the safety and efficiency of their operations, it would be beneficial to have accurate predictions of surrounding vehicles’ future trajectories. AVs can adjust their motions proactively to improve road safety and comfort with such information. This paper proposes a novel approach to predict the future trajectories of interacting vehicles, through a model of potential spatial-temporal interactions. A unique kernel function that emphasises risk-awareness was developed to extract spatial dependencies. The established model was trained and evaluated with the publicly available Highway Drone Dataset and Intersection Drone Dataset. The performance of the developed model was assessed with eight state-of-the-art methods. An ablation study and safety analysis were also conducted to evaluate the proposed risk-awareness kernel function. Results show that the proposed model’s inference speed is over eight times faster than the commonly used LSTM-based models. It also achieves an improvement of over 8% in prediction accuracy when compared with the state-of-the-art model.
{"title":"Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling","authors":"Yuxiang Feng;Qiming Ye;Eduardo Candela;Jose Javier Escribano-Macias;Bo Hu;Yiannis Demiris;Panagiotis Angeloudis","doi":"10.1109/OJITS.2025.3530268","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3530268","url":null,"abstract":"Autonomous vehicles need to continuously analyse the driving context and establish a comprehensive understanding of the dynamic traffic environment. To ensure the safety and efficiency of their operations, it would be beneficial to have accurate predictions of surrounding vehicles’ future trajectories. AVs can adjust their motions proactively to improve road safety and comfort with such information. This paper proposes a novel approach to predict the future trajectories of interacting vehicles, through a model of potential spatial-temporal interactions. A unique kernel function that emphasises risk-awareness was developed to extract spatial dependencies. The established model was trained and evaluated with the publicly available Highway Drone Dataset and Intersection Drone Dataset. The performance of the developed model was assessed with eight state-of-the-art methods. An ablation study and safety analysis were also conducted to evaluate the proposed risk-awareness kernel function. Results show that the proposed model’s inference speed is over eight times faster than the commonly used LSTM-based models. It also achieves an improvement of over 8% in prediction accuracy when compared with the state-of-the-art model.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"37-48"},"PeriodicalIF":4.6,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10843350","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143107051","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：