{"title":"Spatio-Temporal Partitioning of Large Urban Networks for Travel Time Prediction","authors":"Matej Cebecauer, E. Jenelius, W. Burghout","doi":"10.1109/ITSC.2018.8569648","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569648","url":null,"abstract":"The paper explores the potential of spatiotemporal network partitioning for travel time prediction accuracy and computational costs in the context of large-scale urban road networks (including motorways/freeways, arterials and urban streets). Forecasting in this context is challenging due to the complexity, heterogeneity, noisy data, unexpected events and the size of the traffic network. The proposed spatio-temporal network partitioning methodology is versatile, and can be applied for any source of travel time data and multivariate travel time prediction method. A case study of Stockholm, Sweden considers a network exceeding 11,000 links and uses taxi probe data as the source of travel times data. To predict the travel times the Probabilistic Principal Component Analysis (PPCA) is used. Results show that the spatio-temporal network partitioning provides a more appropriate bias-variance tradeoff, and that prediction accuracy and computational costs are improved by considering the proper number of clusters towards robust large-scale travel time prediction.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115508011","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}
{"title":"Real-time Stereo Reconstruction Failure Detection and Correction using Deep Learning","authors":"Vlad-Cristian Miclea, L. Miclea, S. Nedevschi","doi":"10.1109/ITSC.2018.8569928","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569928","url":null,"abstract":"This paper introduces a stereo reconstruction method that besides producing accurate results in real-time, is capable to detect and conceal possible failures caused by one of the cameras. A classification of stereo camera sensor faults is initially introduced, the most common types of defects being highlighted. We next present a stereo camera failure detection method in which various additional checks are being introduced, with respect to the aforementioned error classification. Furthermore, we propose a novel error correction method based on CNNs (convolutional neural networks) that is capable of generating reliable disparity maps by using prior information provided by semantic segmentation in conjunction with the last available disparity. We highlight the efficiency of our approach by evaluating its performance in various driving scenarios and show that it produces accurate disparities on images from Kitti stereo and raw datasets while running in real-time on a regular GPU.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116048242","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}
{"title":"Dual-Mode Vehicle Routing in Mixed Autonomous and Non-Autonomous Zone Networks","authors":"B. Beirigo, Frederik Schulte, R. Negenborn","doi":"10.1109/ITSC.2018.8569344","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569344","url":null,"abstract":"Autonomous vehicles (AVs) are expected to widely re-define mobility in the future, transforming many solutions into autonomous services. Nonetheless, this development requires an expected transition phase of several decades in which some regions will provide sufficient infrastructure for AV movements, while others will not support AVs yet. In this work, we propose an operational planning model for mobility services operating in regions with AV-ready and not AV-ready zones. To this end, we model detailed automated driving areas and consider a heterogeneous fleet comprised of three vehicle types: autonomous, conventional, and dual-mode. While autonomous and conventional vehicles can only operate in their designated areas, dual-mode vehicles service zone-crossing demands in which both human and autonomous driving are required. For such a hybrid network, we introduce a new mathematical planning model based on a site-dependent variant of the heterogeneous dial-a-ride problem (HDARP). With a numerical study for the city of Delft, The Netherlands, we provide insights into how operational costs, service levels, and fleet utilization develop under 405 scenarios of multiple infrastructural settings and technology costs.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122627996","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}
Alvaro Cabrejas Egea, Peter De-Ford, C. Connaughton
{"title":"Estimating Baseline Travel Times for the UK Strategic Road Network","authors":"Alvaro Cabrejas Egea, Peter De-Ford, C. Connaughton","doi":"10.1109/ITSC.2018.8569924","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569924","url":null,"abstract":"We present a new method for long-term estimation of the expected travel time for links on highways and their variation with time. The approach is based on a time series analysis of travel time data from the UK's National Traffic Information Service (NTIS). Time series of travel times are characterised by a noisy background variation exhibiting the expected daily and weekly patterns punctuated by large spikes associated with congestion events. Some spikes are caused by peak hour congestion and some are caused by unforeseen events like accidents. Our algorithm uses thresholding to split the data into background and spike signals, each of which is analysed separately. The the background signal is extracted using spectral filtering. The periodic part of the spike signal is extracted using locally weighted regression (LWR). The final estimated travel time is obtained by recombining these two. We assess our method by cross-validating in several UK motorways. We use 8 weeks of training data and calculate the error of the resulting travel time estimates for a week of test data, repeating this process 4 times. We find that the error is significantly reduced compared to estimates obtained by simple segmentation of the data and compared to the estimates published by the NTIS system.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114451189","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}
{"title":"Connections between classical car following models and artificial neural networks","authors":"Fangyu Wu, D. Work","doi":"10.1109/ITSC.2018.8569333","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569333","url":null,"abstract":"This article considers the problem of traffic modeling via modeling at the microscopic (i.e., vehicle) scale. It provides a connection between classical ordinary differential equation based models and data driven artificial neural network (ANN) based models by showing an example of a car following model which can be exactly expressed as an ANN. In a set of numerical experiments, four ANN models (ranging in structure from a model that is able to exactly capture a classical car following model, to a generic neural network model) are proposed and then trained from data and their resulting accuracy is assessed. It is shown that by adding structure into the neural network (i.e., via the architecture and the activation functions), it is possible to outperform generic ANN models to emergent phenomena such as stop and go waves.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114544741","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}
Marika Strano, Fabricio Novak, Shelly Walbert, B. Palmeiro, Sonia Morales, Ignacio J. Alvarez
{"title":"“Peace of Mind”, An Experiential Safety Framework for Automated Driving Technology Interactions","authors":"Marika Strano, Fabricio Novak, Shelly Walbert, B. Palmeiro, Sonia Morales, Ignacio J. Alvarez","doi":"10.1109/ITSC.2018.8569686","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569686","url":null,"abstract":"Current automated driving systems assume drivers continuously monitor the vehicle. Meanwhile, fully automated vehicles aim at not requiring human intervention for their safely operation. The industry is currently debating how these novel systems can be certified under functional safety standards. In this paper, we argue that the current safety picture is not comprehensive enough, since it alienates users. We propose experiential safety as a complement to existing functional safety and to develop a framework for experiential safety interactions between the user and automation in automated driving environments. To support the experiential safety design model, we provide an overview of the user-centered research on experiential automation safety, which includes results from online surveys, personal interviews, and gamified group workshops. We explore current user behaviors by focusing on what makes them feel safe as drivers and passengers, and how unexpected events and automation responses might impact their perception of safety. Among the highlighted results, we show how mismatched expectations and unexpected behaviors from autonomous vehicles can lead to frustration and compromised trust. We also show how automation feedback to the user can generate stress and anxiety if not properly configured and how a cooperative relationship between automation and the driver leads to more satisfying driving experiences. Finally, we present guidelines for the experiential safety to be applied by automotive engineers and designers in their development of automated driving technologies.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122061628","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}
{"title":"Eco-driving at Signalized Intersections: What is Possible in the Real-World?","authors":"Geunseob Oh, H. Peng","doi":"10.1109/ITSC.2018.8569588","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569588","url":null,"abstract":"A significant amount of fuel is wasted at signalized intersections due to unnecessary braking and idling. Connected Vehicle technologies make future signal phasing and timing (SPaT) information available to drivers. Recent research which utilized SPaT on eco-driving has verified its potential to reduce fuel consumption in simulations and controlled lab tests. In this paper, we propose an eco-driving algorithm and use realworld driving data of 609 human-driven trips undertaken in Ann Arbor, MI. The proposed eco-driving method shows potential fuel savings of 40–50 % while matching human travel time. Results were formulated under the assumption that the vehicle is operating in free-flow traffic, utilizing SPaT of the two consecutive signalized intersections, and equipped with a continuously variable transmission and an internal combustion engine. For each human-driven trip recorded, the proposed method uses Dynamic Programming to determine globally optimal trajectories of three different eco-driving policies: fuel-optimal policy, time-optimal policy, and balanced eco-driving policy. Given the same initial and the final conditions as those of human-driven trips, comparisons are made to demonstrate the real-world benefits of the eco-driving policies. These results can serve as an upper bound of fuel and travel time saving potential of the eco-driving in the vicinity of signalized intersections.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630499","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}
{"title":"Understanding Tourist Destination Choices from Geo-tagged Tweets","authors":"M. Hasnat, Samiul Hasan","doi":"10.1109/ITSC.2018.8569237","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569237","url":null,"abstract":"Tourism related travels have significant impacts on transportation infrastructures, especially in large tourist attractions such as Florida. It is very expensive to collect individual travel data of a reasonable number of tourists traveling over a large region. Ubiquitous use of social media allows us to collect tourist travel data at a large scale in a cost effective way. This paper presents an analysis of tourist destination choices with longitudinal travel data collected from Twitter. From a collection of geo-tagged tweets, we have filtered out a reliable sample and identified tourists using a data mining approach. Then we find the tourists' destinations inside Florida. We have created a sequence of visited locations and applied a Conditional Random Field (CRF) model to predict the type of a tourists' next destination. The proposed model utilizes the features extracted from tweet posted time and location types. The feature set can be expanded by incorporating content-based features without violating the assumptions of CRF. The data collection steps and results derived from this study will be significantly useful for building an individual-level travel behavior model for tourists using social media data.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128964702","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}
{"title":"Connected Vehicle Enhanced Vehicle Routing with Intersection Turning Cost Estimation","authors":"Hao Yang, K. Oguchi","doi":"10.1109/ITSC.2018.8569246","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569246","url":null,"abstract":"On arterial corridors, due to traffic signals and vehicle demands at all different approaches, traffic conditions can be very different across lanes. Vehicular queues and average speed at different lanes, especially lane groups with different turns, can be extremely different even under the same road segment. This paper develops an innovative vehicle routing system with the consideration of vehicle queues and delays as the turning costs to search for the optimal routes for individual vehicles. The algorithm applies connected vehicles to estimate turning costs and dynamically updates vehicle routes with the prediction of the costs at each intersection along the routes. The system is incorporated in the INTEGRATION microscopic traffic simulator to conduct a comprehensive evaluation. The results indicate that the proposed algorithm can reduce the average travel time of connected vehicles and entire networks by up to 49% at one congested grid network. The impact of market penetration rates of connected vehicles is also investigated in this paper.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124712234","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}
{"title":"A Two-stage Method to Optimise Driving Strategy and Timetable for High-speed Trains","authors":"Sheng Zhao, B. Cai, W. Shangguan","doi":"10.1109/ITSC.2018.8569734","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569734","url":null,"abstract":"Nowadays one of the major priorities for highspeed railways and operators is the reduction of energy consumption, considering the contradiction between limited resources and environmental pollution. Energy-efficient driving strategy and timetable optimization are two effective methods to minimize the energy consumption of high-speed railways. This paper combines driving strategy and timetable integrally to optimise train operation in successive sections. Primarily, the optimization model is established with the crucial objectives of energy consumption and trip time of each section. Then a two-stage approach is designed to solve the problem. First the quantum evolutionary algorithm (QEA) is implemented in order to find the optimal Pareto set of each section quickly and efficiently, and the corresponding Pareto curve can be obtained by fitting. In the second stage, the optimal trip time of each section and optimal operation strategy can be acquired based on internal penalty function (IPF). Finally, the algorithm is implemented in MATLAB with a case study on the regional train operating in four sections from Nanjing South station to Kunshan South station in China to verify the effectiveness of our proposed approaches.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130654851","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}