Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917350
Kallirroi N. Porfyri, Areti Kotsi, E. Mitsakis
Cooperative Intelligent Transportation Systems (C-ITS) rely on the use of communication technologies to enable vehicles to exchange information with other vehicles, roadside infrastructure, back-end centres and mobile devices. Verification or testing is required for C-ITS applications, in order to assess their impact on traffic operation. Microsimulation appears to be a robust tool that allows to gain insights into the implementation and performance of such systems. In this work, a microscopic traffic simulation approach is used, to evaluate the impact of Vehicle-to-Infrastructure (V2I) technologies in the context of a road traffic accident. Specifically, the methodology is implemented to study a Road Hazard Warning (RHW) system, using the open source microscopic traffic simulator SUMO. The approach explicitly models vehicles collisions, RHW, Emergency Electronic Brake Light (EEBL) warnings and the resulting driver behavior. Moreover, a new gap control mechanism is adopted, to improve safety by advising vehicles in hazard lane to increase their headways with respect to their preceding vehicle, so that they can avoid a collision. Perfect communication links to all vehicles are assumed. The study findings indicate that the proposed V2I hazard warning strategy has a positive impact on traffic flow safety and efficiency.
{"title":"A microsimulation approach for the impact assessment of a Vehicle-to-Infrastructure based Road Hazard Warning system","authors":"Kallirroi N. Porfyri, Areti Kotsi, E. Mitsakis","doi":"10.1109/ITSC.2019.8917350","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917350","url":null,"abstract":"Cooperative Intelligent Transportation Systems (C-ITS) rely on the use of communication technologies to enable vehicles to exchange information with other vehicles, roadside infrastructure, back-end centres and mobile devices. Verification or testing is required for C-ITS applications, in order to assess their impact on traffic operation. Microsimulation appears to be a robust tool that allows to gain insights into the implementation and performance of such systems. In this work, a microscopic traffic simulation approach is used, to evaluate the impact of Vehicle-to-Infrastructure (V2I) technologies in the context of a road traffic accident. Specifically, the methodology is implemented to study a Road Hazard Warning (RHW) system, using the open source microscopic traffic simulator SUMO. The approach explicitly models vehicles collisions, RHW, Emergency Electronic Brake Light (EEBL) warnings and the resulting driver behavior. Moreover, a new gap control mechanism is adopted, to improve safety by advising vehicles in hazard lane to increase their headways with respect to their preceding vehicle, so that they can avoid a collision. Perfect communication links to all vehicles are assumed. The study findings indicate that the proposed V2I hazard warning strategy has a positive impact on traffic flow safety and efficiency.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"101 1","pages":"4443-4448"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79352092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917457
Naren Bao, Dongfang Yang, Alexander Carballo, Ü. Özgüner, K. Takeda
We propose a data-driven control framework for autonomous driving which combines learning-based risk assessment with personalized, safety-focused, predictive control. Different control strategies are used depending on the detected risk level of the driving situation (risky vs. non-risky). This requires a model which can understand the context of the driving situation. In addition, autonomous driving should also be able to provide various safe and comfortable driving styles customized for various users, which requires a modeling method that can capture individual driving preferences. To achieve this, we propose a novel vehicle control framework in which Model Predictive Control (MPC) is combined with a learning-based risk assessment model. Random Forest (RF) methods are trained to classify driving scenes as risky or not risky, while at the same time capturing individually preferred travel velocities. If driving scenes are classified as risky, then the Safety-focused Model Predictive Control (SMPC) system will be launched to generate control commands satisfying predetermined safety constraints, otherwise, Personalized Model Predictive Control (PMPC) is used instead to track the driver’s individually preferred velocity. We demonstrate experimentally our control framework.
{"title":"Personalized Safety-focused Control by Minimizing Subjective Risk","authors":"Naren Bao, Dongfang Yang, Alexander Carballo, Ü. Özgüner, K. Takeda","doi":"10.1109/ITSC.2019.8917457","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917457","url":null,"abstract":"We propose a data-driven control framework for autonomous driving which combines learning-based risk assessment with personalized, safety-focused, predictive control. Different control strategies are used depending on the detected risk level of the driving situation (risky vs. non-risky). This requires a model which can understand the context of the driving situation. In addition, autonomous driving should also be able to provide various safe and comfortable driving styles customized for various users, which requires a modeling method that can capture individual driving preferences. To achieve this, we propose a novel vehicle control framework in which Model Predictive Control (MPC) is combined with a learning-based risk assessment model. Random Forest (RF) methods are trained to classify driving scenes as risky or not risky, while at the same time capturing individually preferred travel velocities. If driving scenes are classified as risky, then the Safety-focused Model Predictive Control (SMPC) system will be launched to generate control commands satisfying predetermined safety constraints, otherwise, Personalized Model Predictive Control (PMPC) is used instead to track the driver’s individually preferred velocity. We demonstrate experimentally our control framework.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"92 1","pages":"3853-3858"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81617406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917304
Wei Yuan, Ming Yang, Yuesheng He, Chunxiang Wang, B. Wang
A safe and efficient driving policy is essential for the future autonomous highway driving. However, driving policies are hard for modeling because of the diversity of scenes and uncertainties of the interaction with surrounding vehicles. The state-of-the-art deep reinforcement learning method is unable to learn good domain knowledge for highway driving policies using single reward architecture. This paper proposes a Multi-Reward Architecture (MRA) based reinforcement learning for highway driving policies. A single reward function is decomposed to multi-reward functions for better representation of multi-dimensional driving policies. Besides the big penalty for collision, the overall reward is decomposed to three dimensional rewards: the reward for speed, the reward for overtake, and the reward for lane-change. Then, each reward trains a branch of Q-network for corresponding domain knowledge. The Q-network is divided into two parts: low-level network is shared by three branches of high-level networks, which approximate the corresponding Q-value for the different reward functions respectively. The agent car chooses the action based on the sum of Q vectors from three branches. Experiments are conducted in a simulation platform, which performs the highway driving process and the agent car is able to provide the commonly used sensor data: the image and the point cloud. Experiment results show that the proposed method performs better than the DQN method on single reward architecture with three evaluations: higher speed, lower frequency of lane-change, more quantity of overtaking, which is more efficient and safer for the future autonomous highway driving.
{"title":"Multi-Reward Architecture based Reinforcement Learning for Highway Driving Policies","authors":"Wei Yuan, Ming Yang, Yuesheng He, Chunxiang Wang, B. Wang","doi":"10.1109/ITSC.2019.8917304","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917304","url":null,"abstract":"A safe and efficient driving policy is essential for the future autonomous highway driving. However, driving policies are hard for modeling because of the diversity of scenes and uncertainties of the interaction with surrounding vehicles. The state-of-the-art deep reinforcement learning method is unable to learn good domain knowledge for highway driving policies using single reward architecture. This paper proposes a Multi-Reward Architecture (MRA) based reinforcement learning for highway driving policies. A single reward function is decomposed to multi-reward functions for better representation of multi-dimensional driving policies. Besides the big penalty for collision, the overall reward is decomposed to three dimensional rewards: the reward for speed, the reward for overtake, and the reward for lane-change. Then, each reward trains a branch of Q-network for corresponding domain knowledge. The Q-network is divided into two parts: low-level network is shared by three branches of high-level networks, which approximate the corresponding Q-value for the different reward functions respectively. The agent car chooses the action based on the sum of Q vectors from three branches. Experiments are conducted in a simulation platform, which performs the highway driving process and the agent car is able to provide the commonly used sensor data: the image and the point cloud. Experiment results show that the proposed method performs better than the DQN method on single reward architecture with three evaluations: higher speed, lower frequency of lane-change, more quantity of overtaking, which is more efficient and safer for the future autonomous highway driving.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"24 1","pages":"3810-3815"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81618661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917320
T. Bandaragoda, Daswin De Silva, D. Kleyko, Evgeny Osipov, U. Wiklund, D. Alahakoon
Road traffic congestion in urban environments poses an increasingly complex challenge of detection, profiling and prediction. Although public policy promotes transport alternatives and new infrastructure, traffic congestion is highly prevalent and continues to be the lead cause for numerous social, economic and environmental issues. Although a significant volume of research has been reported on road traffic prediction, profiling of traffic has received much less attention. In this paper we address two key problems in traffic profiling by proposing a novel unsupervised incremental learning approach for road traffic congestion detection and profiling, dynamically over time. This approach uses (a) hyperdimensional computing to enable capture variable-length trajectories of commuter trips represented as vehicular movement across intersections, and (b) transforms these into feature vectors that can be incrementally learned over time by the Incremental Knowledge Acquiring Self-Learning (IKASL) algorithm. The proposed approach was tested and evaluated on a dataset consisting of approximately 190 million vehicular movement records obtained from 1,400 Bluetooth identifiers placed at the intersections of the arterial road network in the State of Victoria, Australia.
{"title":"Trajectory clustering of road traffic in urban environments using incremental machine learning in combination with hyperdimensional computing","authors":"T. Bandaragoda, Daswin De Silva, D. Kleyko, Evgeny Osipov, U. Wiklund, D. Alahakoon","doi":"10.1109/ITSC.2019.8917320","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917320","url":null,"abstract":"Road traffic congestion in urban environments poses an increasingly complex challenge of detection, profiling and prediction. Although public policy promotes transport alternatives and new infrastructure, traffic congestion is highly prevalent and continues to be the lead cause for numerous social, economic and environmental issues. Although a significant volume of research has been reported on road traffic prediction, profiling of traffic has received much less attention. In this paper we address two key problems in traffic profiling by proposing a novel unsupervised incremental learning approach for road traffic congestion detection and profiling, dynamically over time. This approach uses (a) hyperdimensional computing to enable capture variable-length trajectories of commuter trips represented as vehicular movement across intersections, and (b) transforms these into feature vectors that can be incrementally learned over time by the Incremental Knowledge Acquiring Self-Learning (IKASL) algorithm. The proposed approach was tested and evaluated on a dataset consisting of approximately 190 million vehicular movement records obtained from 1,400 Bluetooth identifiers placed at the intersections of the arterial road network in the State of Victoria, Australia.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"12 1","pages":"1664-1670"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81883260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917035
Kehang Chen, J. Lv, Jia Huang, Haonan Guo, S. Su, T. Tang
The Automatic Train Operation System (ATO) is an important part in the Communication Based Train Control System (CBTC). It is important to verify the correctness and safety of its control logic functions. In this paper, a timed automata online conformance testing framework based on UPPAAL-TRON has been introduced to test the ATO software. The conformance of the real ATO software and its time automata specification model has been tested. Thus the safety control logic functions are verified according to the mutation analysis, which mainly focuses on the typical faults in the real ATO software, such as the wrong safety distance, inconsistent static speed constraint, functional logic failure and the loss of command, etc. The experimental results show that the online conformance testing framework can detect the inconsistency between the real ATO software and its specification model, which can effectively improve the error detection capability of the functional testing on ATO.
{"title":"Online Conformance Testing of CBTC On-board ATO Functions Based on UPPAAL-TRON Framework","authors":"Kehang Chen, J. Lv, Jia Huang, Haonan Guo, S. Su, T. Tang","doi":"10.1109/ITSC.2019.8917035","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917035","url":null,"abstract":"The Automatic Train Operation System (ATO) is an important part in the Communication Based Train Control System (CBTC). It is important to verify the correctness and safety of its control logic functions. In this paper, a timed automata online conformance testing framework based on UPPAAL-TRON has been introduced to test the ATO software. The conformance of the real ATO software and its time automata specification model has been tested. Thus the safety control logic functions are verified according to the mutation analysis, which mainly focuses on the typical faults in the real ATO software, such as the wrong safety distance, inconsistent static speed constraint, functional logic failure and the loss of command, etc. The experimental results show that the online conformance testing framework can detect the inconsistency between the real ATO software and its specification model, which can effectively improve the error detection capability of the functional testing on ATO.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"15 1","pages":"3334-3339"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81914043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917293
Marc Sons, Christian Kinzig, Dominic Zanker, C. Stiller
Matching keypoints between images showing the same scene under different conditions is a fundamental step for a variety of applications. Recent approaches based on convolutional neural networks show superior results in terms of discriminability compared to well established descriptors like SIFT or ORB. However, there is less previous work which brings the CNNs to automated driving applications like SLAM and analyze the performance in terms of accuracy and runtime. In this work, we take state-of-the-art patch comparison CNNs, train them from scratch and analyze the performance on the KITTI odometry benchmark. For that, we replace the ORBfrontend within the publicly available ORB-SLAM2 framework through our trained CNN variants and compare both. We show that it is necessary to downsize the complexity of the original architectures to achieve real-time capability. Furthermore, our evaluation shows that the downsized models achieve significantly higher matching performance than the ORB descriptor. Moreover, we achieve slightly better results on the KITTI odometry benchmark compared to ORB-SLAM2 while using a CNN-based feature descriptor, which can easily be adapted to different environments.
{"title":"An Approach for CNN-Based Feature Matching Towards Real-Time SLAM","authors":"Marc Sons, Christian Kinzig, Dominic Zanker, C. Stiller","doi":"10.1109/ITSC.2019.8917293","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917293","url":null,"abstract":"Matching keypoints between images showing the same scene under different conditions is a fundamental step for a variety of applications. Recent approaches based on convolutional neural networks show superior results in terms of discriminability compared to well established descriptors like SIFT or ORB. However, there is less previous work which brings the CNNs to automated driving applications like SLAM and analyze the performance in terms of accuracy and runtime. In this work, we take state-of-the-art patch comparison CNNs, train them from scratch and analyze the performance on the KITTI odometry benchmark. For that, we replace the ORBfrontend within the publicly available ORB-SLAM2 framework through our trained CNN variants and compare both. We show that it is necessary to downsize the complexity of the original architectures to achieve real-time capability. Furthermore, our evaluation shows that the downsized models achieve significantly higher matching performance than the ORB descriptor. Moreover, we achieve slightly better results on the KITTI odometry benchmark compared to ORB-SLAM2 while using a CNN-based feature descriptor, which can easily be adapted to different environments.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"88 1","pages":"1305-1310"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79440736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917219
Yu Wang, Yicheng Zhang, Hai-Heng Ng, Bing Zhao, W. Ng
To validate traffic signal control algorithm’s performance, a setup of microscopic traffic simulation platform with realistic traffic demand is necessary. Traditionally, a bilevel framework of Origin-Destination (OD) calibration and trip assignment, is setup to estimate OD so that realistic traffic demand can be emulated in simulation platform. However, with this approach, we may mislead the calibration process by introducing insufficient green time allocation, as vehicles are likely to be stopped by red signals and thus vehicle throughput will never reach the real traffic demand. While this happens occasionally in unsaturated traffic condition, it is very prevalent in the saturated condition scenario. This paper introduces a trilevel problem formulation with consideration of traffic signal schedules during the OD estimation process. The first level uses an iterative algorithm (LSQR) to generate OD traffic demand with certain constraints based on real loop count data at junctions. Second level applies the traffic demand into a simulation platform to generate the trips between OD points. Dynamic User Equilibrium (DUE) will be satisfied iteratively so that the trip assignment is reasonable. Finally, the third level applies Iterative Tuning (IT) signal controller to tune signal schedules iteratively, such that sufficient green time can be allocated to allow vehicles drive through intersections. Via OD calibrations in corridor and area networks, we show that the trilevel OD estimation approach can achieve better performance as compared to the bi-level approach.
{"title":"Dynamic Origin-Destination Estimation Framework with Iterative Traffic Signal Tuning for Microscopic Traffic Simulation","authors":"Yu Wang, Yicheng Zhang, Hai-Heng Ng, Bing Zhao, W. Ng","doi":"10.1109/ITSC.2019.8917219","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917219","url":null,"abstract":"To validate traffic signal control algorithm’s performance, a setup of microscopic traffic simulation platform with realistic traffic demand is necessary. Traditionally, a bilevel framework of Origin-Destination (OD) calibration and trip assignment, is setup to estimate OD so that realistic traffic demand can be emulated in simulation platform. However, with this approach, we may mislead the calibration process by introducing insufficient green time allocation, as vehicles are likely to be stopped by red signals and thus vehicle throughput will never reach the real traffic demand. While this happens occasionally in unsaturated traffic condition, it is very prevalent in the saturated condition scenario. This paper introduces a trilevel problem formulation with consideration of traffic signal schedules during the OD estimation process. The first level uses an iterative algorithm (LSQR) to generate OD traffic demand with certain constraints based on real loop count data at junctions. Second level applies the traffic demand into a simulation platform to generate the trips between OD points. Dynamic User Equilibrium (DUE) will be satisfied iteratively so that the trip assignment is reasonable. Finally, the third level applies Iterative Tuning (IT) signal controller to tune signal schedules iteratively, such that sufficient green time can be allocated to allow vehicles drive through intersections. Via OD calibrations in corridor and area networks, we show that the trilevel OD estimation approach can achieve better performance as compared to the bi-level approach.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"1 1","pages":"2201-2206"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79779659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917146
S. Ifqir, D. Ichalal, N. A. Oufroukh, S. Mammar
This paper presents a new methodology for guaranteed and robust estimation of vehicle lateral tire forces with respect to cornering stiffness variations resulting from changes in tire-road friction and/or driving conditions. A Switched interval observer is designed and provides the set of admissible vehicle state values. Sufficient conditions for the existence of such an observer are provided using Multiple Quadratic ISS-Lyapunov function and Linear Matrix Inequalities (LMIs) formulation. Using an interval relaxation tire model, the upper and lower bounds of lateral tire forces are estimated algebraically. Performance of the proposed algorithm is evaluated through field data acquired using a prototype vehicle. Simulation results show that the proposed estimation scheme succeeds to accurately estimate the upper and lower bounds of vehicle lateral tire forces.
{"title":"An Interval Algebraic Approach for vehicle lateral tire forces estimation","authors":"S. Ifqir, D. Ichalal, N. A. Oufroukh, S. Mammar","doi":"10.1109/ITSC.2019.8917146","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917146","url":null,"abstract":"This paper presents a new methodology for guaranteed and robust estimation of vehicle lateral tire forces with respect to cornering stiffness variations resulting from changes in tire-road friction and/or driving conditions. A Switched interval observer is designed and provides the set of admissible vehicle state values. Sufficient conditions for the existence of such an observer are provided using Multiple Quadratic ISS-Lyapunov function and Linear Matrix Inequalities (LMIs) formulation. Using an interval relaxation tire model, the upper and lower bounds of lateral tire forces are estimated algebraically. Performance of the proposed algorithm is evaluated through field data acquired using a prototype vehicle. Simulation results show that the proposed estimation scheme succeeds to accurately estimate the upper and lower bounds of vehicle lateral tire forces.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"44 1","pages":"3601-3606"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84127959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917188
Keno Garlichs, Alexander Willecke, M. Wegner, L. Wolf
Platooning is able to improve fuel efficiency and reduce road congestion. But to maximize the concept’s impact, platoons need to be created dynamically whenever feasible. Therefore, vehicles have to cooperate with unknown and possibly malicious partners, creating new safety hazards. Hence, vehicles need to be able to determine the trustworthiness of their cooperators. This paper proposes TriP, a trust model which rates platoon members by the divergence of their reported to their actual behavior. The proposed model is evaluated against attacks from literature. The evaluation demonstrates that TriP detects all attacks and prevents harm by deploying countermeasures thus mitigating safety hazards.
{"title":"TriP: Misbehavior Detection for Dynamic Platoons using Trust","authors":"Keno Garlichs, Alexander Willecke, M. Wegner, L. Wolf","doi":"10.1109/ITSC.2019.8917188","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917188","url":null,"abstract":"Platooning is able to improve fuel efficiency and reduce road congestion. But to maximize the concept’s impact, platoons need to be created dynamically whenever feasible. Therefore, vehicles have to cooperate with unknown and possibly malicious partners, creating new safety hazards. Hence, vehicles need to be able to determine the trustworthiness of their cooperators. This paper proposes TriP, a trust model which rates platoon members by the divergence of their reported to their actual behavior. The proposed model is evaluated against attacks from literature. The evaluation demonstrates that TriP detects all attacks and prevents harm by deploying countermeasures thus mitigating safety hazards.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"15 1","pages":"455-460"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84394820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917198
Yuning Qiu, Teruhisa Misu, C. Busso
As a driver prepares to complete a maneuver, his/her internal cognitive state triggers physiological responses that are manifested, for example, in changes in heart rate (HR), breath rate (BR), and electrodermal activity (EDA). This process opens opportunities to understand driving events by observing the physiological data of the driver. In particular, this work studies the relation between driver maneuvers and physiological signals during naturalistic driving recordings. It presents both feature and discriminant analysis to investigate how physiological data can signal driver’s responses for planning, preparation, and execution of driving maneuvers. We study recordings with extreme values in the physiological data (high and low values in HR, BR, and EDA). The analysis indicates that most of these events are associated with driving events. We evaluate the values obtained from physiological signals as the driver complete specific maneuvers. We observe deviations from typical physiological responses during normal driving recordings that are statistically significant. These results are validated with binary classification problems, where the task is to recognize between a driving maneuver and a normal driving condition (e.g., left turn versus normal). The average F1-score of these classifiers is 72.8%, demonstrating the discriminative power of features extracted from physiological signals.
{"title":"Analysis of the Relationship Between Physiological Signals and Vehicle Maneuvers During a Naturalistic Driving Study","authors":"Yuning Qiu, Teruhisa Misu, C. Busso","doi":"10.1109/ITSC.2019.8917198","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917198","url":null,"abstract":"As a driver prepares to complete a maneuver, his/her internal cognitive state triggers physiological responses that are manifested, for example, in changes in heart rate (HR), breath rate (BR), and electrodermal activity (EDA). This process opens opportunities to understand driving events by observing the physiological data of the driver. In particular, this work studies the relation between driver maneuvers and physiological signals during naturalistic driving recordings. It presents both feature and discriminant analysis to investigate how physiological data can signal driver’s responses for planning, preparation, and execution of driving maneuvers. We study recordings with extreme values in the physiological data (high and low values in HR, BR, and EDA). The analysis indicates that most of these events are associated with driving events. We evaluate the values obtained from physiological signals as the driver complete specific maneuvers. We observe deviations from typical physiological responses during normal driving recordings that are statistically significant. These results are validated with binary classification problems, where the task is to recognize between a driving maneuver and a normal driving condition (e.g., left turn versus normal). The average F1-score of these classifiers is 72.8%, demonstrating the discriminative power of features extracted from physiological signals.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"38 1","pages":"3230-3235"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85327136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：