Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917335
Sven Schoenberg, F. Dressler
Travelling long distances with electric vehicles is becoming more viable today. Nevertheless, recharging is still necessary on long trips. As of now, the charging infrastructure is not yet ubiquitous and can be very heterogeneous in terms of charging power. Thus, appropriate route planning is needed, which is still an open research problem. We present an approach to optimize the total travel time for electric vehicles by selecting charging stations and routes, respectively, between origin and destinaton and the charging stations. We also take the possibility into account that driving below the speed limit helps to save energy. In particular, we use a multi-criterion shortest-path search to find the best compromise between the fastest and most economic route. In our approach, we use a non-linear charging model that supports CC-CV and CP-CV charging protocols used for lithium-ion batteries. To achieve acceptable speed for the multi-criterion shortest-path search, we combine contraction hierarchies with precomputation of shortest-path trees. By exploiting the fact that most routes are queried between the known locations of the charging stations, we were able to accelerate these queries by about two orders of magnitude. We compare our proposed adaptive charging and routing strategy to other strategies often cited in the literature. Our results clearly show that we are able to achieve a lower total travel time.
{"title":"Planning Ahead for EV: Total Travel Time Optimization for Electric Vehicles","authors":"Sven Schoenberg, F. Dressler","doi":"10.1109/ITSC.2019.8917335","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917335","url":null,"abstract":"Travelling long distances with electric vehicles is becoming more viable today. Nevertheless, recharging is still necessary on long trips. As of now, the charging infrastructure is not yet ubiquitous and can be very heterogeneous in terms of charging power. Thus, appropriate route planning is needed, which is still an open research problem. We present an approach to optimize the total travel time for electric vehicles by selecting charging stations and routes, respectively, between origin and destinaton and the charging stations. We also take the possibility into account that driving below the speed limit helps to save energy. In particular, we use a multi-criterion shortest-path search to find the best compromise between the fastest and most economic route. In our approach, we use a non-linear charging model that supports CC-CV and CP-CV charging protocols used for lithium-ion batteries. To achieve acceptable speed for the multi-criterion shortest-path search, we combine contraction hierarchies with precomputation of shortest-path trees. By exploiting the fact that most routes are queried between the known locations of the charging stations, we were able to accelerate these queries by about two orders of magnitude. We compare our proposed adaptive charging and routing strategy to other strategies often cited in the literature. Our results clearly show that we are able to achieve a lower total travel time.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"39 1","pages":"3068-3075"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88678256","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.2019.8916915
Brandon Araki, Igor Gilitschenski, Tatum Ogata, Alex Wallar, Wilko Schwarting, Zareen Choudhury, S. Karaman, D. Rus
Accurate localization of other cars in scenarios such as intersection navigation, intention-aware planning, and guardian systems is a critical component of safety. Multi-robot cooperative localization (CL) provides a method to estimate the joint state of a network of cars by exchanging information between communicating agents. However, there are many challenges to implementing CL algorithms on physical systems, including network delays, unmodeled dynamics, and non-constant velocities. In this work, we present a novel experimental framework for range-based cooperative localization that enables the testing of CL algorithms in realistic conditions, and we perform experiments using up to five cars. For state estimation, we develop and compare a particle filter, an Unscented Kalman Filter, and an Extended Kalman Filter that are compatible with nonlinear dynamics and the asynchronous reception of messages. We also model the relative transform between two unicycle models and perform a nonlinear observability analysis on the system, giving us insight into the measurements required to estimate the system’s state. Our approach enables relative localization of multiple vehicles in the absence of any global reference frame or joint map, and we demonstrate the effectiveness of our system in real-world experiments. Our results show that the UKF is likely the best candidate to use for the CL task.
{"title":"Range-based Cooperative Localization with Nonlinear Observability Analysis","authors":"Brandon Araki, Igor Gilitschenski, Tatum Ogata, Alex Wallar, Wilko Schwarting, Zareen Choudhury, S. Karaman, D. Rus","doi":"10.1109/ITSC.2019.8916915","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8916915","url":null,"abstract":"Accurate localization of other cars in scenarios such as intersection navigation, intention-aware planning, and guardian systems is a critical component of safety. Multi-robot cooperative localization (CL) provides a method to estimate the joint state of a network of cars by exchanging information between communicating agents. However, there are many challenges to implementing CL algorithms on physical systems, including network delays, unmodeled dynamics, and non-constant velocities. In this work, we present a novel experimental framework for range-based cooperative localization that enables the testing of CL algorithms in realistic conditions, and we perform experiments using up to five cars. For state estimation, we develop and compare a particle filter, an Unscented Kalman Filter, and an Extended Kalman Filter that are compatible with nonlinear dynamics and the asynchronous reception of messages. We also model the relative transform between two unicycle models and perform a nonlinear observability analysis on the system, giving us insight into the measurements required to estimate the system’s state. Our approach enables relative localization of multiple vehicles in the absence of any global reference frame or joint map, and we demonstrate the effectiveness of our system in real-world experiments. Our results show that the UKF is likely the best candidate to use for the CL task.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"148 1","pages":"1864-1870"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86654873","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.2019.8917513
Lingzhou Shu, Jia Wu, Ziyan Li
Centralized traffic control in a large-scale grid is quite challenging due to the large search space of the policy. To deal with this problem, we propose a hierarchical regional control framework that can learn more quickly and efficiently, based on prior knowledge. Specifically, the traffic at intersections is controlled by local controller based on well-adjusted policies. The coordination of the local controllers is decided by a master controller that is trained by using reinforcement learning. The control of the whole grid is handled solely by learning a master policy. The master controller continuously observes the state of the traffic network and predicts the best possible traffic control strategy for the current state. In this way, the dimension of the action space is dramatically decreased, and it is much easier to explore the optimal policy. We verify our method by implementing a series of experiments in SUMO. The numerical experiments demonstrate that our method outperforms the traditional methods and the new control methods based on deep reinforcement learning in various typical scenarios. We also demonstrate that our method is easy to train and operates robustly.
{"title":"Hierarchical Regional Control for Traffic Grid Signal Optimization","authors":"Lingzhou Shu, Jia Wu, Ziyan Li","doi":"10.1109/ITSC.2019.8917513","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917513","url":null,"abstract":"Centralized traffic control in a large-scale grid is quite challenging due to the large search space of the policy. To deal with this problem, we propose a hierarchical regional control framework that can learn more quickly and efficiently, based on prior knowledge. Specifically, the traffic at intersections is controlled by local controller based on well-adjusted policies. The coordination of the local controllers is decided by a master controller that is trained by using reinforcement learning. The control of the whole grid is handled solely by learning a master policy. The master controller continuously observes the state of the traffic network and predicts the best possible traffic control strategy for the current state. In this way, the dimension of the action space is dramatically decreased, and it is much easier to explore the optimal policy. We verify our method by implementing a series of experiments in SUMO. The numerical experiments demonstrate that our method outperforms the traditional methods and the new control methods based on deep reinforcement learning in various typical scenarios. We also demonstrate that our method is easy to train and operates robustly.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"7 1","pages":"3547-3552"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91050271","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.2019.8917072
Stefan Jesenski, J. Stellet, Wolfgang Branz, Johann Marius Zöllner
The release of highly automated driving functions requires a thorough validation of safety. In this paper, the recently introduced 3-circles model is recapitulated. Based on the 3-circles model, the possible areas of application of simulations to the validation procedure are analyzed and possible challenges and limitations of simulation-based methods are given and discussed. An overview and classification of current simulation concepts is presented. Afterwards, recent research on the implementation details of simulations is discussed.
{"title":"Simulation-Based Methods for Validation of Automated Driving: A Model-Based Analysis and an Overview about Methods for Implementation","authors":"Stefan Jesenski, J. Stellet, Wolfgang Branz, Johann Marius Zöllner","doi":"10.1109/ITSC.2019.8917072","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917072","url":null,"abstract":"The release of highly automated driving functions requires a thorough validation of safety. In this paper, the recently introduced 3-circles model is recapitulated. Based on the 3-circles model, the possible areas of application of simulations to the validation procedure are analyzed and possible challenges and limitations of simulation-based methods are given and discussed. An overview and classification of current simulation concepts is presented. Afterwards, recent research on the implementation details of simulations is discussed.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"27 1","pages":"1914-1921"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89905388","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.2019.8917200
Philip Schörner, J. Doll, Maximilian Galm, Johann Marius Zöllner
We propose an online motion planning approach for a pseudo omnidirectional vehicle based on particle swarm optimization. Therefore, we first describe the principles behind the optimization process. Afterwards we derive representations for the vehicle’s movement based on the description of the position of the instantaneous center of motion. Then, the mathematical operators used in the optimization process for the trajectories are described with regard to the previously derived representations. The costfunction is explained with focus on the new opportunities in the movement of the vehicle like e.g. driving sideways. However, the extra degree of freedom not only brings benefits, but also complicates the generation of trajectories for the initial particle swarm. Therefore we describe how to efficiently sample omnidirectional trajectories and also trajectories for certain well known gaits like Ackermann driving. Finally, the approach is evaluated in simulation showing the full maneuverability of the vehicle.
{"title":"Trajectory Planning for a Pseudo Omnidirectional Vehicle using Particle Swarm Optimization","authors":"Philip Schörner, J. Doll, Maximilian Galm, Johann Marius Zöllner","doi":"10.1109/ITSC.2019.8917200","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917200","url":null,"abstract":"We propose an online motion planning approach for a pseudo omnidirectional vehicle based on particle swarm optimization. Therefore, we first describe the principles behind the optimization process. Afterwards we derive representations for the vehicle’s movement based on the description of the position of the instantaneous center of motion. Then, the mathematical operators used in the optimization process for the trajectories are described with regard to the previously derived representations. The costfunction is explained with focus on the new opportunities in the movement of the vehicle like e.g. driving sideways. However, the extra degree of freedom not only brings benefits, but also complicates the generation of trajectories for the initial particle swarm. Therefore we describe how to efficiently sample omnidirectional trajectories and also trajectories for certain well known gaits like Ackermann driving. Finally, the approach is evaluated in simulation showing the full maneuverability of the vehicle.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"18 1","pages":"1454-1461"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89531277","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.2019.8917314
M. Garzón, A. Spalanzani
This paper presents a game theoretic decision making process for autonomous vehicles. Its goal is to provide a solution for a very challenging task: the merge manoeuvre in high traffic scenarios. Unlike previous approaches, the proposed solution does not rely on vehicle-to-vehicle communication or any specific coordination, moreover, it is capable of anticipating both the actions of other players and their reactions to the autonomous vehicle’s movements.
{"title":"Game theoretic decision making for autonomous vehicles’ merge manoeuvre in high traffic scenarios","authors":"M. Garzón, A. Spalanzani","doi":"10.1109/ITSC.2019.8917314","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917314","url":null,"abstract":"This paper presents a game theoretic decision making process for autonomous vehicles. Its goal is to provide a solution for a very challenging task: the merge manoeuvre in high traffic scenarios. Unlike previous approaches, the proposed solution does not rely on vehicle-to-vehicle communication or any specific coordination, moreover, it is capable of anticipating both the actions of other players and their reactions to the autonomous vehicle’s movements.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"26 1","pages":"3448-3453"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89580141","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.2019.8917372
Siru Chen, Pengfei Zhu, W. Yan, Konglin Zhu, Lin Zhang
Vehicle platoon service is considered as a promising framework for Intelligent Transportation System (ITS) to reduce energy cost, and meanwhile enhance driving safety and comfortability. In platoon service, platoon head takes the crucial role for the quality of service. The secure and trustworthy platoon heads with good driving skills will provide a better service than untrusted ones. How to motivate secure platoon heads for the platoon service becomes an interesting problem. In this paper, we formulate the trust platoon heads selection as a platoon utility maximization (PUM) problem. Then we employ game-theoretical approach showing that the PUM game is a potential game, and thus exists a Nash Equilibrium. Furthermore, we propose a cyber-physical-social approach to motivate vehicles to become platoon heads and at the same time maximize the platoon utility by seeking for the Nash Equilibrium. The extensive evaluation results show that the proposed platoon heads selection approach effectively stimulate more trustworthy users to be platoon heads and gains up to 60% more platoon utility compared with baseline methods.
{"title":"Cyber-Physical-Social Motivated Collaborative Platoon Heads Selection for Intelligent and Connected Vehicles","authors":"Siru Chen, Pengfei Zhu, W. Yan, Konglin Zhu, Lin Zhang","doi":"10.1109/ITSC.2019.8917372","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917372","url":null,"abstract":"Vehicle platoon service is considered as a promising framework for Intelligent Transportation System (ITS) to reduce energy cost, and meanwhile enhance driving safety and comfortability. In platoon service, platoon head takes the crucial role for the quality of service. The secure and trustworthy platoon heads with good driving skills will provide a better service than untrusted ones. How to motivate secure platoon heads for the platoon service becomes an interesting problem. In this paper, we formulate the trust platoon heads selection as a platoon utility maximization (PUM) problem. Then we employ game-theoretical approach showing that the PUM game is a potential game, and thus exists a Nash Equilibrium. Furthermore, we propose a cyber-physical-social approach to motivate vehicles to become platoon heads and at the same time maximize the platoon utility by seeking for the Nash Equilibrium. The extensive evaluation results show that the proposed platoon heads selection approach effectively stimulate more trustworthy users to be platoon heads and gains up to 60% more platoon utility compared with baseline methods.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"1 1","pages":"1173-1177"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89723152","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.2019.8917391
M. Sabry, Abdulla Al-Kaff, A. Hussein, Slim Abdennadher
Technology advances in the field of Intelligent Transportation Systems are rapidly increasing to obtain higher autonomy levels, and improve the robustness and reliability of autonomous driving. One of the challenges related to autonomous vehicles is the localization systems especially in GPS-denied environments. This paper presents an enhancement in the monocular visual odometry by exploring the use of one external sensor (encoder); in order to obtain the vehicle speed with computer vision techniques to provide a reliable and real time localization system. The proposed algorithm has been validated by performing real experiments, and the obtained results show the improvement in accuracy comparing to existing stereo visual odometry algorithm, with lower error in translation and rotation of the path points.
{"title":"Ground Vehicle Monocular Visual Odometry","authors":"M. Sabry, Abdulla Al-Kaff, A. Hussein, Slim Abdennadher","doi":"10.1109/ITSC.2019.8917391","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917391","url":null,"abstract":"Technology advances in the field of Intelligent Transportation Systems are rapidly increasing to obtain higher autonomy levels, and improve the robustness and reliability of autonomous driving. One of the challenges related to autonomous vehicles is the localization systems especially in GPS-denied environments. This paper presents an enhancement in the monocular visual odometry by exploring the use of one external sensor (encoder); in order to obtain the vehicle speed with computer vision techniques to provide a reliable and real time localization system. The proposed algorithm has been validated by performing real experiments, and the obtained results show the improvement in accuracy comparing to existing stereo visual odometry algorithm, with lower error in translation and rotation of the path points.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"55 1","pages":"3587-3592"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78130179","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.2019.8917413
Kaiqiang Xie, Lu Ma, Hui Xiong, Shasha Wu
As a significant factor in urban planning and traffic forecasting, human mobility draws intensive attentions in recent years with the emergence of geo-related data. In this paper, we build models for human mobility with regards to individuals’ largest daily displacement using Extreme Value Theory (EVT) based on nearly 40 million individuals’ trajectories. It is found that the largest daily displacement can be well fitted by the Generalized Pareto Distribution (GPD) and is not heavy tailed compared to the exponential distribution. Besides, we also explored differences in distribution of the largest daily displacement according to gender and weekday. The analysis results indicate that male tend to have a larger displacement and individuals tend to travel longer on weekends.
{"title":"Modeling Individuals' Largest Daily Trip Displacement using Extreme Value Theory","authors":"Kaiqiang Xie, Lu Ma, Hui Xiong, Shasha Wu","doi":"10.1109/ITSC.2019.8917413","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917413","url":null,"abstract":"As a significant factor in urban planning and traffic forecasting, human mobility draws intensive attentions in recent years with the emergence of geo-related data. In this paper, we build models for human mobility with regards to individuals’ largest daily displacement using Extreme Value Theory (EVT) based on nearly 40 million individuals’ trajectories. It is found that the largest daily displacement can be well fitted by the Generalized Pareto Distribution (GPD) and is not heavy tailed compared to the exponential distribution. Besides, we also explored differences in distribution of the largest daily displacement according to gender and weekday. The analysis results indicate that male tend to have a larger displacement and individuals tend to travel longer on weekends.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"1 1","pages":"2665-2668"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78392607","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.2019.8917459
Malte Schmidt, N. Weik, Stephan Zieger, A. Schmeink, Nils Nießen
The paper presents a stochastic, infrastructure centered modeling approach for capacity analysis applications in long term planning of railway stations. A formal modeling approach of train operations using generalized stochastic Petri nets is proposed. The model is analyzed based on the embedded Markov chain, which allows for quality based performance metrics including utilization, blocking probabilities and waiting times. The model is validated and tested against simulation in an application scenario for a medium size railway station. In addition, model extensions to large-scale systems are discussed.
{"title":"A Generalized Stochastic Petri Net Model for Performance Analysis of Trackside Infrastructure in Railway Station Areas under Uncertainty *","authors":"Malte Schmidt, N. Weik, Stephan Zieger, A. Schmeink, Nils Nießen","doi":"10.1109/ITSC.2019.8917459","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917459","url":null,"abstract":"The paper presents a stochastic, infrastructure centered modeling approach for capacity analysis applications in long term planning of railway stations. A formal modeling approach of train operations using generalized stochastic Petri nets is proposed. The model is analyzed based on the embedded Markov chain, which allows for quality based performance metrics including utilization, blocking probabilities and waiting times. The model is validated and tested against simulation in an application scenario for a medium size railway station. In addition, model extensions to large-scale systems are discussed.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"32 1","pages":"3732-3737"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75071865","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：