Pub Date : 2018-11-01DOI: 10.1109/ITSC.2018.8569952
L. Taccari, Francesco Sambo, L. Bravi, Samuele Salti, L. Sarti, Matteo Simoncini, A. Lori
The identification of dangerous events from sensor data is a fundamental sub-task in domains such as autonomous vehicles and intelligent transportation systems. In this work, we tackle the problem of classifying crash and near-crash events from dashcam videos and telematics data. We propose a method that uses a combination of state-of-the-art approaches in computer vision and machine learning. We use an object detector based on convolutional neural networks to extract semantic information about the road scene, and generate video and telematics features that are fed to a random forest classifier. Computational experiments on the SHRP2 dataset show that our approach reaches more than 0.87 of accuracy on the binary problem of distinguishing dangerous from safe events, and 0.85 on the 3-class problem of discriminating between crash, near-crash, and safe events.
{"title":"Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics","authors":"L. Taccari, Francesco Sambo, L. Bravi, Samuele Salti, L. Sarti, Matteo Simoncini, A. Lori","doi":"10.1109/ITSC.2018.8569952","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569952","url":null,"abstract":"The identification of dangerous events from sensor data is a fundamental sub-task in domains such as autonomous vehicles and intelligent transportation systems. In this work, we tackle the problem of classifying crash and near-crash events from dashcam videos and telematics data. We propose a method that uses a combination of state-of-the-art approaches in computer vision and machine learning. We use an object detector based on convolutional neural networks to extract semantic information about the road scene, and generate video and telematics features that are fed to a random forest classifier. Computational experiments on the SHRP2 dataset show that our approach reaches more than 0.87 of accuracy on the binary problem of distinguishing dangerous from safe events, and 0.85 on the 3-class problem of discriminating between crash, near-crash, and safe events.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"30 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":"114244857","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569933
Fasil Sagir, S. Ukkusuri
Automated vehicle (AV) technologies are rapidly maturing, and time line for their wider deployment is currently uncertain. Despite uncertainty these technologies are expected to bring about numerous societal benefits, such as enhanced traffic safety, improved mobility and reduced fuel emissions. In this paper, we propose a novel bottom-up approach to model various SAE levels on VISSIM in a two lane highway environment featuring an on-ramp. Our results indicate that mobility in SAE level 1 always exceeds that of SAE level 0, because the former has a consistently higher acceleration for given conditions. SAE level 2 provides more lateral stability and therefore less implied accidents than level 1 or 0 due to lower lateral deviations. For level 3, key consideration is to model the transition between human and system control. In SAE level 4 we model the operation of autonomous vehicles in Operational Design Domain (ODD) and transition to minimal risk conditions outside ODD. SAE level 5 overcomes impact of these transitions and hence has a better mobility than lower SAE levels. The models can help policymakers to understand the impact of autonomous vehicles on mobility and guide them in making critical policy decisions.
{"title":"Mobility Impacts of Autonomous Vehicle Systems","authors":"Fasil Sagir, S. Ukkusuri","doi":"10.1109/ITSC.2018.8569933","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569933","url":null,"abstract":"Automated vehicle (AV) technologies are rapidly maturing, and time line for their wider deployment is currently uncertain. Despite uncertainty these technologies are expected to bring about numerous societal benefits, such as enhanced traffic safety, improved mobility and reduced fuel emissions. In this paper, we propose a novel bottom-up approach to model various SAE levels on VISSIM in a two lane highway environment featuring an on-ramp. Our results indicate that mobility in SAE level 1 always exceeds that of SAE level 0, because the former has a consistently higher acceleration for given conditions. SAE level 2 provides more lateral stability and therefore less implied accidents than level 1 or 0 due to lower lateral deviations. For level 3, key consideration is to model the transition between human and system control. In SAE level 4 we model the operation of autonomous vehicles in Operational Design Domain (ODD) and transition to minimal risk conditions outside ODD. SAE level 5 overcomes impact of these transitions and hence has a better mobility than lower SAE levels. The models can help policymakers to understand the impact of autonomous vehicles on mobility and guide them in making critical policy decisions.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"357 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":"114840140","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569694
Jordan Ivanchev, S. Litescu, D. Zehe, M. Lees, Heiko Aydt, A. Knoll
Recent advances in Intelligent Transportation Systems, navigation tools and personal smart devices enable the development of effective mechanisms for improvement of traffic conditions. We present an information dissemination technique, which provides minimal but the right context to a population and steers the traffic system into a more efficient operational state. Selfish routing in large cities leads to a small group of roads being congested, while the rest of the road network remains underutilized [1], [2]. A routing steering mechanism is suggested, where we homogenize the traffic distribution by selectively disseminating information about the unavailability of certain roads, based on simulated outcomes of their closing. We demonstrate that the full removal of some road segments from the network can redistribute traffic in a socially beneficial way. We identify the most harmful roads and quantify their negative effect on the system. Furthermore, we introduce the concept of soft closing. Instead of informing the whole population to avoid a certain road, we inform only a portion of the drivers, further improving the network utilization. We use the city of Singapore as a case study for our traffic assignment model which we calibrate and validate using both survey and GPS tracking devices data.
{"title":"Hard and Soft Closing of Roads Towards Socially Optimal Routing","authors":"Jordan Ivanchev, S. Litescu, D. Zehe, M. Lees, Heiko Aydt, A. Knoll","doi":"10.1109/ITSC.2018.8569694","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569694","url":null,"abstract":"Recent advances in Intelligent Transportation Systems, navigation tools and personal smart devices enable the development of effective mechanisms for improvement of traffic conditions. We present an information dissemination technique, which provides minimal but the right context to a population and steers the traffic system into a more efficient operational state. Selfish routing in large cities leads to a small group of roads being congested, while the rest of the road network remains underutilized [1], [2]. A routing steering mechanism is suggested, where we homogenize the traffic distribution by selectively disseminating information about the unavailability of certain roads, based on simulated outcomes of their closing. We demonstrate that the full removal of some road segments from the network can redistribute traffic in a socially beneficial way. We identify the most harmful roads and quantify their negative effect on the system. Furthermore, we introduce the concept of soft closing. Instead of informing the whole population to avoid a certain road, we inform only a portion of the drivers, further improving the network utilization. We use the city of Singapore as a case study for our traffic assignment model which we calibrate and validate using both survey and GPS tracking devices data.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"40 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":"116674602","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569256
M. Cocca, Danilo Giordano, M. Mellia, L. Vassio
Free Floating Car Sharing (FFCS) is a transport paradigm where customers are free to rent and drop cars of a fleet within city limits. In this work we consider the design of a FFCS system based on Electric Vehicles (EVs), We face the problem of finding the minimum number of charging stations and their placement, given the battery constraints of electric cars, the cost of installing the charging network, and the time-varying car usage patterns of customers. Differently from other studies, we base our solution on actual rentals collected from traditional combustion FFCS systems currently in use in two cities. We use about 450 000 actual rentals to characterize the system utilization. We propose a user-behavior model and system policies for the charging events. Then we evaluate via accurate trace driven simulations the performance with different charging station placement policies. We first present greedy solutions, and then perform a local optimization with a meta-heuristic that 1) guarantee system operativeness, i.e., car batteries never get depleted, and 2) minimize users' discomfort, i.e., users are only seldom forced to drop cars in a far-away charging station. Results show that it is possible to guarantee service continuity by installing charging stations in just 6 % of city areas, while 15% of equipped zones guarantee limited impact on users' discomfort.
{"title":"Data Driven Optimization of Charging Station Placement for EV Free Floating Car Sharing","authors":"M. Cocca, Danilo Giordano, M. Mellia, L. Vassio","doi":"10.1109/ITSC.2018.8569256","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569256","url":null,"abstract":"Free Floating Car Sharing (FFCS) is a transport paradigm where customers are free to rent and drop cars of a fleet within city limits. In this work we consider the design of a FFCS system based on Electric Vehicles (EVs), We face the problem of finding the minimum number of charging stations and their placement, given the battery constraints of electric cars, the cost of installing the charging network, and the time-varying car usage patterns of customers. Differently from other studies, we base our solution on actual rentals collected from traditional combustion FFCS systems currently in use in two cities. We use about 450 000 actual rentals to characterize the system utilization. We propose a user-behavior model and system policies for the charging events. Then we evaluate via accurate trace driven simulations the performance with different charging station placement policies. We first present greedy solutions, and then perform a local optimization with a meta-heuristic that 1) guarantee system operativeness, i.e., car batteries never get depleted, and 2) minimize users' discomfort, i.e., users are only seldom forced to drop cars in a far-away charging station. Results show that it is possible to guarantee service continuity by installing charging stations in just 6 % of city areas, while 15% of equipped zones guarantee limited impact on users' discomfort.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"24 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":"114982566","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569309
A. Nakamura, N. Shimada, M. Itami
Currently, the measures to traffic accident are advanced with the spread of the automobile. This paper discusses the pedestrian positioning system based on UWB(Ultra-Wide Band) ranging. In this system, base stations to receive UWB signal that is transmitted from pedestrians are attached to a traffic light for pedestrians. Positions of pedestrians are estimated by LSM(Least Square Method) using the ranging value that is estimated by UWB ranging scheme. The slotted ALOHA scheme is adopted for multiple access to access control. UWB positioning estimation system can detect positions with the error of 40cm. However, detailed characteristics of UWB positioning estimation system is not analyzed. In this paper, positioning error and PSR(Positioning Successful Rate) of estimation system are evaluated and analyzed by computer simulations. Also, positioning error and PSR are depended on the number of base stations. Thus, the effect of increasing the number of base stations is evaluated and analyzed. As the results of computer simulations, it is shown that the position of the pedestrian can be accurately estimated by using UWB positioning system.
{"title":"Performance Analysis of UWB Positioning System at the Crossing","authors":"A. Nakamura, N. Shimada, M. Itami","doi":"10.1109/ITSC.2018.8569309","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569309","url":null,"abstract":"Currently, the measures to traffic accident are advanced with the spread of the automobile. This paper discusses the pedestrian positioning system based on UWB(Ultra-Wide Band) ranging. In this system, base stations to receive UWB signal that is transmitted from pedestrians are attached to a traffic light for pedestrians. Positions of pedestrians are estimated by LSM(Least Square Method) using the ranging value that is estimated by UWB ranging scheme. The slotted ALOHA scheme is adopted for multiple access to access control. UWB positioning estimation system can detect positions with the error of 40cm. However, detailed characteristics of UWB positioning estimation system is not analyzed. In this paper, positioning error and PSR(Positioning Successful Rate) of estimation system are evaluated and analyzed by computer simulations. Also, positioning error and PSR are depended on the number of base stations. Thus, the effect of increasing the number of base stations is evaluated and analyzed. As the results of computer simulations, it is shown that the position of the pedestrian can be accurately estimated by using UWB positioning system.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"206 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":"115463984","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569951
Farouk Ghallabi, F. Nashashibi, Ghayath El-Haj-Shhade, M. Mittet
Accurate self-vehicle localization is an important task for autonomous driving and ADAS. Current GNSS-based solutions do not provide better than 2–3 m in open-sky environments [1]. Moreover, map-based localization using HD maps became an interesting source of information for intelligent vehicles. In this paper, a Map-based localization using a multi-layer LIDAR is proposed. Our method mainly relies on road lane markings and an HD map to achieve lane-level accuracy. At first, road points are segmented by analysing the geometric structure of each returned layer points. Secondly, thanks to LIDAR reflectivity data, road marking points are projected onto a 2D image and then detected using Hough Transform. Detected lane markings are then matched to our HD map using Particle Filter (PF) framework. Experiments are conducted on a Highway-like test track using GPS/INS with RTK correction as ground truth. Our method is capable of providing a lane-level localization with a 22 cm cross-track accuracy.
{"title":"LIDAR-Based Lane Marking Detection For Vehicle Positioning in an HD Map","authors":"Farouk Ghallabi, F. Nashashibi, Ghayath El-Haj-Shhade, M. Mittet","doi":"10.1109/ITSC.2018.8569951","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569951","url":null,"abstract":"Accurate self-vehicle localization is an important task for autonomous driving and ADAS. Current GNSS-based solutions do not provide better than 2–3 m in open-sky environments [1]. Moreover, map-based localization using HD maps became an interesting source of information for intelligent vehicles. In this paper, a Map-based localization using a multi-layer LIDAR is proposed. Our method mainly relies on road lane markings and an HD map to achieve lane-level accuracy. At first, road points are segmented by analysing the geometric structure of each returned layer points. Secondly, thanks to LIDAR reflectivity data, road marking points are projected onto a 2D image and then detected using Hough Transform. Detected lane markings are then matched to our HD map using Particle Filter (PF) framework. Experiments are conducted on a Highway-like test track using GPS/INS with RTK correction as ground truth. Our method is capable of providing a lane-level localization with a 22 cm cross-track accuracy.","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":"123222505","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569758
Théophile Cabannes, Frank Shyu, Emily Porter, Shuai Yao, Yexin Wang, Marco Antonio Sangiovanni Vincentelli, Stefanus Hinardi, M. Zhao, A. Bayen
This article is focused on measuring the impact of navigational apps on road traffic patterns. We first define the marginal regret, which characterizes the difference between the travel time experienced on the most optimal path and the path of interest between the same origin destination pair. We then introduce a new metric, the average marginal regret, which is the average of marginal regret, taken over all possible OD pairs in the network. We evaluate the average marginal regret in simulations with varying proportions of app and non-app users (information vs. no information) using the microsimulation software Aimsun. We conduct experiments on a benchmark network as well as a calibrated corridor model of the I–210 in Los Angeles for which OD demand data is gathered from several sensing sources as well as actual signal timing plans. In both cases (i.e. the benchmark and I–210) experiments demonstrate that the use of apps leads to a system-wide convergence towards Nash equilibrium.
{"title":"Measuring Regret in Routing: Assessing the Impact of Increased App Usage","authors":"Théophile Cabannes, Frank Shyu, Emily Porter, Shuai Yao, Yexin Wang, Marco Antonio Sangiovanni Vincentelli, Stefanus Hinardi, M. Zhao, A. Bayen","doi":"10.1109/ITSC.2018.8569758","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569758","url":null,"abstract":"This article is focused on measuring the impact of navigational apps on road traffic patterns. We first define the marginal regret, which characterizes the difference between the travel time experienced on the most optimal path and the path of interest between the same origin destination pair. We then introduce a new metric, the average marginal regret, which is the average of marginal regret, taken over all possible OD pairs in the network. We evaluate the average marginal regret in simulations with varying proportions of app and non-app users (information vs. no information) using the microsimulation software Aimsun. We conduct experiments on a benchmark network as well as a calibrated corridor model of the I–210 in Los Angeles for which OD demand data is gathered from several sensing sources as well as actual signal timing plans. In both cases (i.e. the benchmark and I–210) experiments demonstrate that the use of apps leads to a system-wide convergence towards Nash equilibrium.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"134 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":"123222624","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8570015
Pallavi Mitra, Apratirn Choudhury, V. R. Aparow, Giridharan Kulandaivelu, J. Dauwels
Detection and tracking of dynamic traffic objects such as pedestrians, cyclists, and surrounding ground vehicles is an important part of the perception of Autonomous Vehicle (AV). In practice, the presence of noise corrupts sensors' ideal performance, causing detection and state estimation of moving objects to be erroneous. These detection errors propagate through the overall system and potentially compromise the reliability and safety of the AV. To get an assurance that the vehicle will operate safely, any simulation platform for an AV must include a realistic representation of the fallacies in vehicle's perception. In this study, the perception error for a vision based detection algorithm of the camera sensor is modeled by applying auto-regressive moving average (ARMA) and nonlinear autoregressive (NAR) method. It will enable statistical error values to be injected into ideal values obtained from simulation models. The proposed approach is evaluated based on several test case scenarios using various environmental and traffic information. A comparative analysis of the behavior of the AV with and without perception error model for the imperfection of camera sensor has been undertaken using the CarMaker platform. The investigation of the impact on the behavior of the AV by the variation of the state (distance, brake-torque) clearly depict the effectiveness of incorporating the error model at detection level in CarMaker.
{"title":"Towards Modeling of Perception Errors in Autonomous Vehicles","authors":"Pallavi Mitra, Apratirn Choudhury, V. R. Aparow, Giridharan Kulandaivelu, J. Dauwels","doi":"10.1109/ITSC.2018.8570015","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8570015","url":null,"abstract":"Detection and tracking of dynamic traffic objects such as pedestrians, cyclists, and surrounding ground vehicles is an important part of the perception of Autonomous Vehicle (AV). In practice, the presence of noise corrupts sensors' ideal performance, causing detection and state estimation of moving objects to be erroneous. These detection errors propagate through the overall system and potentially compromise the reliability and safety of the AV. To get an assurance that the vehicle will operate safely, any simulation platform for an AV must include a realistic representation of the fallacies in vehicle's perception. In this study, the perception error for a vision based detection algorithm of the camera sensor is modeled by applying auto-regressive moving average (ARMA) and nonlinear autoregressive (NAR) method. It will enable statistical error values to be injected into ideal values obtained from simulation models. The proposed approach is evaluated based on several test case scenarios using various environmental and traffic information. A comparative analysis of the behavior of the AV with and without perception error model for the imperfection of camera sensor has been undertaken using the CarMaker platform. The investigation of the impact on the behavior of the AV by the variation of the state (distance, brake-torque) clearly depict the effectiveness of incorporating the error model at detection level in CarMaker.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"38 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":"123429154","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569323
Stefan Luthardt, Volker Willert, J. Adamy
The precise localization of vehicles is an important requirement for autonomous driving or advanced driver assistance systems. Using common GNSS the ego position can be measured but not with the reliability and precision necessary. An alternative approach to achieve precise localization is the usage of visual landmarks observed by a camera mounted in the vehicle. However, this raises the necessity of reliable visual landmarks that are easily recognizable and persistent. We propose a novel SLAM algorithm that focuses on learning and mapping such visual long-term landmarks (LLamas). The algorithm therefore processes stereo image streams from several recording sessions in the same spatial area. The key part within LLama-SLAM is the assessment of the landmarks with quality values that are inferred as viewpoint dependent probabilities from observation statistics. By adding solely landmarks of high quality to the final LLama Map, it can be kept compact while still allowing reliable localization. Due to the long-term evaluation of the GNSS measurement during the sessions, the landmarks can be positioned precisely in a global referenced coordinate system. For a first assessment of the algorithm's capabilities, we present some experimental results from the mapping process combining three sessions recorded over two months on the same route.
{"title":"LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization","authors":"Stefan Luthardt, Volker Willert, J. Adamy","doi":"10.1109/ITSC.2018.8569323","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569323","url":null,"abstract":"The precise localization of vehicles is an important requirement for autonomous driving or advanced driver assistance systems. Using common GNSS the ego position can be measured but not with the reliability and precision necessary. An alternative approach to achieve precise localization is the usage of visual landmarks observed by a camera mounted in the vehicle. However, this raises the necessity of reliable visual landmarks that are easily recognizable and persistent. We propose a novel SLAM algorithm that focuses on learning and mapping such visual long-term landmarks (LLamas). The algorithm therefore processes stereo image streams from several recording sessions in the same spatial area. The key part within LLama-SLAM is the assessment of the landmarks with quality values that are inferred as viewpoint dependent probabilities from observation statistics. By adding solely landmarks of high quality to the final LLama Map, it can be kept compact while still allowing reliable localization. Due to the long-term evaluation of the GNSS measurement during the sessions, the landmarks can be positioned precisely in a global referenced coordinate system. For a first assessment of the algorithm's capabilities, we present some experimental results from the mapping process combining three sessions recorded over two months on the same route.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"18 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":"124728329","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 : 2018-11-01DOI: 10.1109/ITSC.2018.8569608
Maxime Guériau, Ivana Dusparic
Shared mobility-on-demand systems can improve the efficiency of urban mobility through reduced vehicle ownership and parking demand. However, some issues in their implementations remain open, most notably the issue of rebalancing non-occupied vehicles to meet geographically uneven demand, as is, for example, the case during the rush hour. This is somewhat alleviated by the prospect of autonomous mobility-on-demand systems, where autonomous vehicles can relocate themselves; however, the proposed relocation strategies are still centralized and assume all vehicles are a part of the same fleet. Furthermore, ride-sharing is not considered, which also has an impact on rebalancing, as already occupied vehicles can also potentially be available to serve new requests simultaneously. In this paper we propose a reinforcement learning-based decentralized approach to vehicle relocation as well as ride request assignment in shared mobility-on-demand systems. Each vehicle autonomously learns its behaviour, which includes both rebalancing and selecting which requests to serve, based on its local current and observed historical demand. We evaluate the approach using data on taxi use in New York City, first serving a single request by a vehicle at a time, and then introduce ride-sharing to evaluate its impact on the learnt rebalancing and assignment behaviour.
{"title":"SAMoD: Shared Autonomous Mobility-on-Demand using Decentralized Reinforcement Learning","authors":"Maxime Guériau, Ivana Dusparic","doi":"10.1109/ITSC.2018.8569608","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569608","url":null,"abstract":"Shared mobility-on-demand systems can improve the efficiency of urban mobility through reduced vehicle ownership and parking demand. However, some issues in their implementations remain open, most notably the issue of rebalancing non-occupied vehicles to meet geographically uneven demand, as is, for example, the case during the rush hour. This is somewhat alleviated by the prospect of autonomous mobility-on-demand systems, where autonomous vehicles can relocate themselves; however, the proposed relocation strategies are still centralized and assume all vehicles are a part of the same fleet. Furthermore, ride-sharing is not considered, which also has an impact on rebalancing, as already occupied vehicles can also potentially be available to serve new requests simultaneously. In this paper we propose a reinforcement learning-based decentralized approach to vehicle relocation as well as ride request assignment in shared mobility-on-demand systems. Each vehicle autonomously learns its behaviour, which includes both rebalancing and selecting which requests to serve, based on its local current and observed historical demand. We evaluate the approach using data on taxi use in New York City, first serving a single request by a vehicle at a time, and then introduce ride-sharing to evaluate its impact on the learnt rebalancing and assignment behaviour.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"12 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":"124915860","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：