Salvador Dominguez, Bogdan Khomutenko, G. Garcia, P. Martinet
Self-driving car's navigation requires a very precise localization covering wide areas and long distances. Moreover, they have to do it at faster speeds than conventional mobile robots. This paper reports on an efficient technique to optimize the position of a sequence of maps along a journey. We take advantage of the short-term precision and reduced space on disk of the localization using 2D occupancy grid maps, from now on called sub-maps, as well as, the long-term global consistency of a Kalman filter that fuses odometry and GPS measurements. In our approach, horizontal planar LiDARs and odometry measurements are used to perform 2D-SLAM generating the sub-maps, and the EKF to generate the trajectory followed by the car in global coordinates. During the trip, after finishing each sub-map, a relaxation process is applied to a set of the last sub-maps to position them globally using both, global and map's local path. The importance of this method lies on its performance, expending low computing resources, so it can work in real time on a computer with conventional characteristics and on its robustness which makes it suitable for being used on a self-driving car as it doesn't depend excessively on the availability of GPS signal or the eventual appearance of moving objects around the car. Extensive testing has been performed in the suburbs and in the down-town of Nantes (France) covering a distance of 25 kilometers with different traffic conditions obtaining satisfactory results for autonomous driving.
{"title":"An Optimization Technique for Positioning Multiple Maps for Self-Driving Car's Autonomous Navigation","authors":"Salvador Dominguez, Bogdan Khomutenko, G. Garcia, P. Martinet","doi":"10.1109/ITSC.2015.433","DOIUrl":"https://doi.org/10.1109/ITSC.2015.433","url":null,"abstract":"Self-driving car's navigation requires a very precise localization covering wide areas and long distances. Moreover, they have to do it at faster speeds than conventional mobile robots. This paper reports on an efficient technique to optimize the position of a sequence of maps along a journey. We take advantage of the short-term precision and reduced space on disk of the localization using 2D occupancy grid maps, from now on called sub-maps, as well as, the long-term global consistency of a Kalman filter that fuses odometry and GPS measurements. In our approach, horizontal planar LiDARs and odometry measurements are used to perform 2D-SLAM generating the sub-maps, and the EKF to generate the trajectory followed by the car in global coordinates. During the trip, after finishing each sub-map, a relaxation process is applied to a set of the last sub-maps to position them globally using both, global and map's local path. The importance of this method lies on its performance, expending low computing resources, so it can work in real time on a computer with conventional characteristics and on its robustness which makes it suitable for being used on a self-driving car as it doesn't depend excessively on the availability of GPS signal or the eventual appearance of moving objects around the car. Extensive testing has been performed in the suburbs and in the down-town of Nantes (France) covering a distance of 25 kilometers with different traffic conditions obtaining satisfactory results for autonomous driving.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126038350","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}
E. Cipriani, Andrea del Giudice, Marialisa Nigro, F. Viti, Guido Cantelmo
This paper analyzes the effects of modeling errors when simulating the real route choice behavior on the solution of travel demand estimation. Firstly, several test networks have been adopted to address such issue, showing the sensitivity of the estimation accuracy to route choice parameters. Then, considering the real network case of Rome (Italy), the added value of using information on actual route choices as indirect measurements on the network (as mimicking OD travel times from e.g. Floating Car Data) has been demonstrated.
{"title":"The Impact of Route Choice Modeling on Dynamic OD Estimation","authors":"E. Cipriani, Andrea del Giudice, Marialisa Nigro, F. Viti, Guido Cantelmo","doi":"10.1109/ITSC.2015.242","DOIUrl":"https://doi.org/10.1109/ITSC.2015.242","url":null,"abstract":"This paper analyzes the effects of modeling errors when simulating the real route choice behavior on the solution of travel demand estimation. Firstly, several test networks have been adopted to address such issue, showing the sensitivity of the estimation accuracy to route choice parameters. Then, considering the real network case of Rome (Italy), the added value of using information on actual route choices as indirect measurements on the network (as mimicking OD travel times from e.g. Floating Car Data) has been demonstrated.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125341480","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}
D. Pham, Bao Hoang, S. N. Thành, H. Nguyen, V. Duong
Due to demographic and economic growth in recent developing countries such as Viet Nam, traffic activities increase continuously and the problem of traffic management is urgently required. Consequently, the complexity of collecting traffic data as well as the traffic coordination carried over a control center are exponential. An Intelligent Transportation System (ITS) nowadays becomes a solution for handling those complexities. ITSs were already considered in developed countries under different formations. However, they are rarely used in most developing countries because of the cost of developing, implementing and maintaining those systems. We are interested by the design of an adaptive ITS for crowded cities in developing countries where non-lane-based traffic is core. We develop a framework for two main goals: 1) Collecting and processing traffic data from various types of sources such as cameras, sensors, GPS on cars, buses, taxis, motorcycles, etc. or individual users via our Mobile Application, 2) Adapting several algorithms in transportation research to regulate the traffic and inform users via a control center. Our ITS is firstly deployed to Ho Chi Minh city in Viet Nam under the support of local authority.
{"title":"A Constructive Intelligent Transportation System for Urban Traffic Network in Developing Countries via GPS Data from Multiple Transportation Modes","authors":"D. Pham, Bao Hoang, S. N. Thành, H. Nguyen, V. Duong","doi":"10.1109/ITSC.2015.281","DOIUrl":"https://doi.org/10.1109/ITSC.2015.281","url":null,"abstract":"Due to demographic and economic growth in recent developing countries such as Viet Nam, traffic activities increase continuously and the problem of traffic management is urgently required. Consequently, the complexity of collecting traffic data as well as the traffic coordination carried over a control center are exponential. An Intelligent Transportation System (ITS) nowadays becomes a solution for handling those complexities. ITSs were already considered in developed countries under different formations. However, they are rarely used in most developing countries because of the cost of developing, implementing and maintaining those systems. We are interested by the design of an adaptive ITS for crowded cities in developing countries where non-lane-based traffic is core. We develop a framework for two main goals: 1) Collecting and processing traffic data from various types of sources such as cameras, sensors, GPS on cars, buses, taxis, motorcycles, etc. or individual users via our Mobile Application, 2) Adapting several algorithms in transportation research to regulate the traffic and inform users via a control center. Our ITS is firstly deployed to Ho Chi Minh city in Viet Nam under the support of local authority.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125587450","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}
Y. Dupuis, Pierre Merriaux, P. Vasseur, X. Savatier
Estimating vehicle position on road maps is important for many ITS applications. Advanced Driver Assistance System (ADAS) may expect robust positioning invariant to day time, weather or simplifications induced by the topological representations of road maps. This paper describes a particle filter approach used to achieve vehicle positioning on freely available road maps. Anti-lock Braking System (ABS) and Electronic Stability Program (ESP) sensor data are used in the motion update model. Measurement updates solely rely on vehicle heading. As our results indicate, our approach is able to cope with the odometry error accumulation. We also found that our methodology is able to successfully localize and track a vehicle with a median error of 3.6m in a road network made of 380km of drivable roads with a performance comparable to a high-end INS unit.
{"title":"Vehicle Positioning in Road Networks without GPS","authors":"Y. Dupuis, Pierre Merriaux, P. Vasseur, X. Savatier","doi":"10.1109/ITSC.2015.293","DOIUrl":"https://doi.org/10.1109/ITSC.2015.293","url":null,"abstract":"Estimating vehicle position on road maps is important for many ITS applications. Advanced Driver Assistance System (ADAS) may expect robust positioning invariant to day time, weather or simplifications induced by the topological representations of road maps. This paper describes a particle filter approach used to achieve vehicle positioning on freely available road maps. Anti-lock Braking System (ABS) and Electronic Stability Program (ESP) sensor data are used in the motion update model. Measurement updates solely rely on vehicle heading. As our results indicate, our approach is able to cope with the odometry error accumulation. We also found that our methodology is able to successfully localize and track a vehicle with a median error of 3.6m in a road network made of 380km of drivable roads with a performance comparable to a high-end INS unit.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116069380","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}
Yun Shen, Honghui Dong, L. Jia, Yong Qin, Fei Su, Mingchao Wu, Kai Liu, Pan Li, Zhao Tian
The knowledge of the transportation mode, which is used by humans to complete the travels, especially the signal-mode segment directly related to travel behavior research, is critical for application such as travel behavior research, transport planning and traffic management. As application of GPS gradually increased, traffic managers obtain more and more travel data used by residents, which is more accurate, and problems by traditional survey can be avoided. However, the travel data cannot contain the transport mode and even a trip contains more than one mode. In this article, a new method for segmenting travel data into single-mode segments is presented. We analysis the position data of GPS area of Beijing, extracting the position journeys, then obtaining the segments and the segment points by splitting the position journeys with the interval time, extracting the features of the segments for calculating similarity measure distance of the adjacent segment based on Euclidean distance, analyzing the similarity distance, and last implement the traffic travel status segmentation-the transition point recognition. Our method can directly implement the transition point recognition before the transport modes classification. We have implemented the method and test it with the GPS data collected in Beijing. As a result, based on Euclidean distance for similarity measure and the interval time of 90s, we achieve that the precision and recall accuracy being greater than others, are 70%, 77.8%, respectively.
{"title":"A Method of Traffic Travel Status Segmentation Based on Position Trajectories","authors":"Yun Shen, Honghui Dong, L. Jia, Yong Qin, Fei Su, Mingchao Wu, Kai Liu, Pan Li, Zhao Tian","doi":"10.1109/ITSC.2015.462","DOIUrl":"https://doi.org/10.1109/ITSC.2015.462","url":null,"abstract":"The knowledge of the transportation mode, which is used by humans to complete the travels, especially the signal-mode segment directly related to travel behavior research, is critical for application such as travel behavior research, transport planning and traffic management. As application of GPS gradually increased, traffic managers obtain more and more travel data used by residents, which is more accurate, and problems by traditional survey can be avoided. However, the travel data cannot contain the transport mode and even a trip contains more than one mode. In this article, a new method for segmenting travel data into single-mode segments is presented. We analysis the position data of GPS area of Beijing, extracting the position journeys, then obtaining the segments and the segment points by splitting the position journeys with the interval time, extracting the features of the segments for calculating similarity measure distance of the adjacent segment based on Euclidean distance, analyzing the similarity distance, and last implement the traffic travel status segmentation-the transition point recognition. Our method can directly implement the transition point recognition before the transport modes classification. We have implemented the method and test it with the GPS data collected in Beijing. As a result, based on Euclidean distance for similarity measure and the interval time of 90s, we achieve that the precision and recall accuracy being greater than others, are 70%, 77.8%, respectively.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116421031","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}
S. Hallmark, Nicole Oneyear, Bo Wang, Samantha Tyner, C. Carney, D. McGehee
The object of this research was to use naturalistic driving study data (NDS) to determine where drivers begin reacting to the presence of a curve. Understanding where drivers begin to react to the curve is important for optimal placement of traffic control devices, such as advance curve warning signs, as well as other countermeasures. Time series data were modeled using regression analysis. Results indicate that, depending on radius of curve, drivers begin reacting to the curve 164 to 180 meters (538.1 to 590.6 feet) upstream of the point of curvature. This was compared against sign placement guidelines in the 2009 Manual on Uniform Traffic Control Devices, and it was determined these guidelines are appropriately set based on where drivers actually react to the curve. The analysis found that drivers begin reacting to the curve sooner for curves with larger radii than for curves with smaller radii. Drivers may not be able to gauge the sharpness of the curve, or sight distance issues may be a concern for sharper curves. It should be noted that the model only identified where drivers reacted to the curve. This research question did not attempt to answer whether the reaction point was sufficient for drivers to successfully negotiate the curve. It is also noted that sample sizes are small. Due to resource and data constraints it was not possible to model a large number of drivers over large variation of different curve types. Consequently, the results provide useful information but should be used within the context of the study limitations.
{"title":"Identifying Curve Reaction Point Using NDS Data","authors":"S. Hallmark, Nicole Oneyear, Bo Wang, Samantha Tyner, C. Carney, D. McGehee","doi":"10.1109/ITSC.2015.361","DOIUrl":"https://doi.org/10.1109/ITSC.2015.361","url":null,"abstract":"The object of this research was to use naturalistic driving study data (NDS) to determine where drivers begin reacting to the presence of a curve. Understanding where drivers begin to react to the curve is important for optimal placement of traffic control devices, such as advance curve warning signs, as well as other countermeasures. Time series data were modeled using regression analysis. Results indicate that, depending on radius of curve, drivers begin reacting to the curve 164 to 180 meters (538.1 to 590.6 feet) upstream of the point of curvature. This was compared against sign placement guidelines in the 2009 Manual on Uniform Traffic Control Devices, and it was determined these guidelines are appropriately set based on where drivers actually react to the curve. The analysis found that drivers begin reacting to the curve sooner for curves with larger radii than for curves with smaller radii. Drivers may not be able to gauge the sharpness of the curve, or sight distance issues may be a concern for sharper curves. It should be noted that the model only identified where drivers reacted to the curve. This research question did not attempt to answer whether the reaction point was sufficient for drivers to successfully negotiate the curve. It is also noted that sample sizes are small. Due to resource and data constraints it was not possible to model a large number of drivers over large variation of different curve types. Consequently, the results provide useful information but should be used within the context of the study limitations.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122511600","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}
Based on the fact that new vehicles bring new technologies into the traffic step by step, the research presented in this paper is focused on the impact of mixed traffic stream in urban environment with different percentage rates of adaptive stop&go cruise control equipped vehicles on the traffic flow, travel time, energy demand and emission. A model of a mixed traffic stream comprised of conventional and advanced vehicles was built upon a microscopic single lane urban traffic simulator that we have previously developed, calibrated and validated. Through number of parallel simulations of real and mixed traffic stream and analysis of the obtained results, we have evaluated the impact that certain presence rates of adaptive stop&go cruise control equipped vehicles in the mixed traffic stream have on the traffic flow, travel time, energy demand and emission. Furthermore, the comparison of the results leads towards some interesting conclusions which may serve as a base for further tuning of several aspects related to mixed traffic in urban environment.
{"title":"Impact of Mixed Traffic in Urban Environment with Different Percentage Rates of Adaptive stop&go Cruise Control Equipped Vehicles on the Traffic Flow, Travel Time, Energy Demand and Emission","authors":"A. Kostikj, M. Kjosevski, Ljupcho Kocarev","doi":"10.1109/ITSC.2015.261","DOIUrl":"https://doi.org/10.1109/ITSC.2015.261","url":null,"abstract":"Based on the fact that new vehicles bring new technologies into the traffic step by step, the research presented in this paper is focused on the impact of mixed traffic stream in urban environment with different percentage rates of adaptive stop&go cruise control equipped vehicles on the traffic flow, travel time, energy demand and emission. A model of a mixed traffic stream comprised of conventional and advanced vehicles was built upon a microscopic single lane urban traffic simulator that we have previously developed, calibrated and validated. Through number of parallel simulations of real and mixed traffic stream and analysis of the obtained results, we have evaluated the impact that certain presence rates of adaptive stop&go cruise control equipped vehicles in the mixed traffic stream have on the traffic flow, travel time, energy demand and emission. Furthermore, the comparison of the results leads towards some interesting conclusions which may serve as a base for further tuning of several aspects related to mixed traffic in urban environment.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122595107","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}
Piotr Smietanka, K. Szczypiorski, F. Viti, M. Seredynski
The efficiency of Public Transport (PT) has significantly improved thanks to Automatic Vehicle Location (AVL) systems. They are used by several applications, such as realtime passenger information systems, transit signal priority, and control schemes designed to reduce the negative effects of bus bunching. Currently, these applications rely on a centralised architecture, i.e. buses equipped with communication and location detection technologies constantly send their positions to the AVL centre. In this paper, we demonstrate how a distributed AVL system can be designed on the basis of Connected Vehicle (CV) technology, i.e. information about bus location is exchanged in the PT network via buses equipped with the technology. Using computation experiments based on microscopic traffic simulations we demonstrate that CV-based AVL works efficiently when it comes to providing a bus with information about locations of buses ahead of it. However, information about buses behind is far less reliable, and requires additional support in message dissemination (e.g. by private vehicles).
{"title":"Distributed Automated Vehicle Location (AVL) System Based on Connected Vehicle Technology","authors":"Piotr Smietanka, K. Szczypiorski, F. Viti, M. Seredynski","doi":"10.1109/ITSC.2015.315","DOIUrl":"https://doi.org/10.1109/ITSC.2015.315","url":null,"abstract":"The efficiency of Public Transport (PT) has significantly improved thanks to Automatic Vehicle Location (AVL) systems. They are used by several applications, such as realtime passenger information systems, transit signal priority, and control schemes designed to reduce the negative effects of bus bunching. Currently, these applications rely on a centralised architecture, i.e. buses equipped with communication and location detection technologies constantly send their positions to the AVL centre. In this paper, we demonstrate how a distributed AVL system can be designed on the basis of Connected Vehicle (CV) technology, i.e. information about bus location is exchanged in the PT network via buses equipped with the technology. Using computation experiments based on microscopic traffic simulations we demonstrate that CV-based AVL works efficiently when it comes to providing a bus with information about locations of buses ahead of it. However, information about buses behind is far less reliable, and requires additional support in message dissemination (e.g. by private vehicles).","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116998940","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}
Yeona Kim, J. Ryu, Min Baek, Hwan Lee, Cheol Mun, Kyunbyoung Ko
In this paper, we propose bicycle collision avoidance (BCA) algorithms and analyze their performance. As typical type accidents related with bicycles, we consider both intersection collision and rear crash. Then, the rear crash avoidance (RCA) algorithm and the intersection collision avoidance (ICA) algorithm are respectively developed by utilizing 'PreScan' and 'MATLAB'. The derived analytical approach can explain the condition and effect of bicycle collisions. Furthermore, proposed algorithms are verified from simulations. Consequently, the BCA developing methodology is confirmed to be used as a general solution tool to reduce the cost and the time consumption required for commercialization of safety services under IEEE 802.11p/WAVE wireless networks.
{"title":"Development and Performance Analysis of Bicycle Collision Avoidance (BCA) Algorithms by Using PreScan and MATLAB","authors":"Yeona Kim, J. Ryu, Min Baek, Hwan Lee, Cheol Mun, Kyunbyoung Ko","doi":"10.1109/ITSC.2015.246","DOIUrl":"https://doi.org/10.1109/ITSC.2015.246","url":null,"abstract":"In this paper, we propose bicycle collision avoidance (BCA) algorithms and analyze their performance. As typical type accidents related with bicycles, we consider both intersection collision and rear crash. Then, the rear crash avoidance (RCA) algorithm and the intersection collision avoidance (ICA) algorithm are respectively developed by utilizing 'PreScan' and 'MATLAB'. The derived analytical approach can explain the condition and effect of bicycle collisions. Furthermore, proposed algorithms are verified from simulations. Consequently, the BCA developing methodology is confirmed to be used as a general solution tool to reduce the cost and the time consumption required for commercialization of safety services under IEEE 802.11p/WAVE wireless networks.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129863083","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}
In order to improve the effectiveness of information provided to travelers of a transit network, the new generation of trip planners should give recommendations taking into account several factors, such as network unreliability and presence of diversion nodes where path decision can be made according to the occurrences of random events. In this context, travelers have not to rely on a single selected path, but they have to use a strategy, i.e. set of rules that allow travelers to reach the destination maximizing their expected utility. The availability of real-time predictive information requires the traditional optimal hyper-path approaches to be overcame and new ones to be developed. Further, as the values of path attributes forecasted are random variables and therefore, also with an information system, the uncertainty is not completely overcome. This paper explores some aspects of providing path recommendations in unreliable network, proposing a methodology for defining real-time optimal strategies, that combine predictive and expected values of path attributes.
{"title":"Transit Trip Planners: Real-Time Strategy-Based Path Recommendation","authors":"A. Nuzzolo, A. Comi","doi":"10.1109/ITSC.2015.41","DOIUrl":"https://doi.org/10.1109/ITSC.2015.41","url":null,"abstract":"In order to improve the effectiveness of information provided to travelers of a transit network, the new generation of trip planners should give recommendations taking into account several factors, such as network unreliability and presence of diversion nodes where path decision can be made according to the occurrences of random events. In this context, travelers have not to rely on a single selected path, but they have to use a strategy, i.e. set of rules that allow travelers to reach the destination maximizing their expected utility. The availability of real-time predictive information requires the traditional optimal hyper-path approaches to be overcame and new ones to be developed. Further, as the values of path attributes forecasted are random variables and therefore, also with an information system, the uncertainty is not completely overcome. This paper explores some aspects of providing path recommendations in unreliable network, proposing a methodology for defining real-time optimal strategies, that combine predictive and expected values of path attributes.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128208688","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：