Pub Date : 2018-11-01DOI: 10.1109/ITSC.2018.8569452
Daun Jeong, Minseok Kim, KyungTaek Kim, Tae-Won Kim, JiHun Jin, ChungSu Lee, Sejoon Lim
We propose a driver identification system that uses deep learning technology with controller area network (CAN) data obtained from a vehicle. The data are collected by sensors that are able to obtain the characteristics of drivers. A convolutional neural network (CNN) is used to learn and identify a driver. Various techniques such as CNN 1D, normalization, special section extracting, and post-processing are applied to improve the accuracy of the identification. The experimental results demonstrate that the proposed system achieves an average accuracy of 90% in an experiment with four drivers. In addition, we simulated real-time driver identification in an actual vehicle. In this experiment, we evaluated the time required to reach certain accuracy. For example, the time required to reach an accuracy of 80% was 4–5 min on average.
{"title":"Real-time Driver Identification using Vehicular Big Data and Deep Learning","authors":"Daun Jeong, Minseok Kim, KyungTaek Kim, Tae-Won Kim, JiHun Jin, ChungSu Lee, Sejoon Lim","doi":"10.1109/ITSC.2018.8569452","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569452","url":null,"abstract":"We propose a driver identification system that uses deep learning technology with controller area network (CAN) data obtained from a vehicle. The data are collected by sensors that are able to obtain the characteristics of drivers. A convolutional neural network (CNN) is used to learn and identify a driver. Various techniques such as CNN 1D, normalization, special section extracting, and post-processing are applied to improve the accuracy of the identification. The experimental results demonstrate that the proposed system achieves an average accuracy of 90% in an experiment with four drivers. In addition, we simulated real-time driver identification in an actual vehicle. In this experiment, we evaluated the time required to reach certain accuracy. For example, the time required to reach an accuracy of 80% was 4–5 min on average.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"89 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":"115599625","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.2018.8569898
Julia Nitsch, J. Aguilar, Juan I. Nieto, R. Siegwart, M. Schmidt, César Cadena
Autonomous driving applications must be provided with information about other road users and road side infrastructure by object detection modules. These modules often process point clouds sensed by light detection and ranging (LiDAR) sensors. Within the captured point cloud a large amount of points correspond to physical locations on the ground. These points do not hold information about road users, obstacles or road side infrastructure. Thus an important preprocessing step is identifying ground points to allow the object detection focusing on relevant measurements only. Within this paper we propose a ground point classification which relies on simple but effective geometric features. We evaluate the accuracy of the proposed algorithm on simulated data of different traffic scenarios. In addition, we evaluate the effectiveness of this preprocessing step based on the achieved speed up of an object detection algorithm on real world data.
{"title":"3D Ground Point Classification for Automotive Scenarios","authors":"Julia Nitsch, J. Aguilar, Juan I. Nieto, R. Siegwart, M. Schmidt, César Cadena","doi":"10.1109/ITSC.2018.8569898","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569898","url":null,"abstract":"Autonomous driving applications must be provided with information about other road users and road side infrastructure by object detection modules. These modules often process point clouds sensed by light detection and ranging (LiDAR) sensors. Within the captured point cloud a large amount of points correspond to physical locations on the ground. These points do not hold information about road users, obstacles or road side infrastructure. Thus an important preprocessing step is identifying ground points to allow the object detection focusing on relevant measurements only. Within this paper we propose a ground point classification which relies on simple but effective geometric features. We evaluate the accuracy of the proposed algorithm on simulated data of different traffic scenarios. In addition, we evaluate the effectiveness of this preprocessing step based on the achieved speed up of an object detection algorithm on real world data.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"11 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":"124390013","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.2018.8569456
H. Winter, Volker Willert, J. Adamy
Train-borne localization systems as a key component of future signalling systems are expected to offer huge economic and operational advances for the railway transportation sector. However, the reliable provision of a track-selective and constantly available location information is still unsolved and prevents the introduction of such systems so far. A contribution to overcome this issue is presented here. We show a recursive multistage filtering approach with an increased cross-track positioning accuracy, which is decisive to ensure track-selectivity. This is achieved by exploiting track-geometry constraints known in advance, as there are strict rules for the construction of railway tracks. Additionally, compact geometric track-maps can be extracted during the filtering process which are beneficial for existing train localization approaches. The filter was derived applying approximate Bayesian inference. The geometry constraints are directly incorporated in the filter design, utilizing an interacting multiple model (IMM) filter and extended Kalman filters (EKF). Throughout simulations the performance of the filter is analyzed and discussed thereafter.
{"title":"Increasing Accuracy in Train Localization Exploiting Track-Geometry Constraints","authors":"H. Winter, Volker Willert, J. Adamy","doi":"10.1109/ITSC.2018.8569456","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569456","url":null,"abstract":"Train-borne localization systems as a key component of future signalling systems are expected to offer huge economic and operational advances for the railway transportation sector. However, the reliable provision of a track-selective and constantly available location information is still unsolved and prevents the introduction of such systems so far. A contribution to overcome this issue is presented here. We show a recursive multistage filtering approach with an increased cross-track positioning accuracy, which is decisive to ensure track-selectivity. This is achieved by exploiting track-geometry constraints known in advance, as there are strict rules for the construction of railway tracks. Additionally, compact geometric track-maps can be extracted during the filtering process which are beneficial for existing train localization approaches. The filter was derived applying approximate Bayesian inference. The geometry constraints are directly incorporated in the filter design, utilizing an interacting multiple model (IMM) filter and extended Kalman filters (EKF). Throughout simulations the performance of the filter is analyzed and discussed thereafter.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"186 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":"117161704","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.2018.8569322
J. Yu, R. Jayakrishnan
Humans, as indispensable components in any transportation systems, have been very challenging to model and predict, especially in hypothetical scenarios. Adding further complexity is the increasingly important role of artificial intelligence and rapidly changing technologies and business models. We propose a modeling framework, CognAgent, which unifies the modeling approach of different types of autonomous entities from the perspective of cognition rather than revealed behaviors. This approach improves model flexibility, interpretability, and computational efficiency. Heterogeneous agents inherit from a single blueprint agent and interact with one another within the Physical Interaction module, the output of which is fed into the module of Space of Observables for agents to sense and perceive through noisy media of information transmission. Combining with prior knowledge, preprogrammed routines, emotions, and habits, agents make decisions on how to act in the Physical Interaction module. In CognAgent, information is a result of the change of perceived uncertainty, and therefore, consistent with the Information Theory. Owing to this explicitness of agents' cognition, the derived models become extendable to new technology and business models. Equity analysis related to cognitive limitations such as vision and hearing loss becomes also natural. The numerical example models explicitly humans and autonomous vehicles with heterogeneous information transmission, perception, and risk preference.
{"title":"A Cognitive Framework for Unifying Human and Artificial Intelligence in Transportation Systems Modeling","authors":"J. Yu, R. Jayakrishnan","doi":"10.1109/ITSC.2018.8569322","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569322","url":null,"abstract":"Humans, as indispensable components in any transportation systems, have been very challenging to model and predict, especially in hypothetical scenarios. Adding further complexity is the increasingly important role of artificial intelligence and rapidly changing technologies and business models. We propose a modeling framework, CognAgent, which unifies the modeling approach of different types of autonomous entities from the perspective of cognition rather than revealed behaviors. This approach improves model flexibility, interpretability, and computational efficiency. Heterogeneous agents inherit from a single blueprint agent and interact with one another within the Physical Interaction module, the output of which is fed into the module of Space of Observables for agents to sense and perceive through noisy media of information transmission. Combining with prior knowledge, preprogrammed routines, emotions, and habits, agents make decisions on how to act in the Physical Interaction module. In CognAgent, information is a result of the change of perceived uncertainty, and therefore, consistent with the Information Theory. Owing to this explicitness of agents' cognition, the derived models become extendable to new technology and business models. Equity analysis related to cognitive limitations such as vision and hearing loss becomes also natural. The numerical example models explicitly humans and autonomous vehicles with heterogeneous information transmission, perception, and risk preference.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"43 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":"117173492","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.2018.8569565
J. Meguro, T. Arakawa, Syunsuke Mizutani, Aoki Takanose
In this paper, we proposed a novel technique to realize accurate and robust position and pose estimation in a dense urban area. The technique make the best use of averaging effect to optimize long time (over several tens of seconds) series sensor data. Our proposed scheme uses just a low-cost GNSS receiver, a MEMS IMU, and a speed sensor. Evaluation tests in a Japanese urban area showed that our proposed scheme can realize robust lane-level absolute positioning results (2DRMS, 0.9 m). In addition, the standard deviation of the heading is 0.4°, and that of the pitch angle is 0.6°. Evaluation tests showed that the accuracy of our proposed scheme almost reached levels of the survey level mapping system, which is equipped with high-cost sensors. On the other hands, the total sensor cost for our prototype was only several hundreds of dollars. We believe that our proposed position and pose estimation scheme enables enhanced vehicle application to systems such as driver assistance systems, autonomous vehicle, and mapping systems.
{"title":"Low-cost Lane-level Positioning in Urban Area Using Optimized Long Time Series GNSS and IMU Data","authors":"J. Meguro, T. Arakawa, Syunsuke Mizutani, Aoki Takanose","doi":"10.1109/ITSC.2018.8569565","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569565","url":null,"abstract":"In this paper, we proposed a novel technique to realize accurate and robust position and pose estimation in a dense urban area. The technique make the best use of averaging effect to optimize long time (over several tens of seconds) series sensor data. Our proposed scheme uses just a low-cost GNSS receiver, a MEMS IMU, and a speed sensor. Evaluation tests in a Japanese urban area showed that our proposed scheme can realize robust lane-level absolute positioning results (2DRMS, 0.9 m). In addition, the standard deviation of the heading is 0.4°, and that of the pitch angle is 0.6°. Evaluation tests showed that the accuracy of our proposed scheme almost reached levels of the survey level mapping system, which is equipped with high-cost sensors. On the other hands, the total sensor cost for our prototype was only several hundreds of dollars. We believe that our proposed position and pose estimation scheme enables enhanced vehicle application to systems such as driver assistance systems, autonomous vehicle, and mapping systems.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"115 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":"127307115","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.2018.8569735
M. Almannaa, Mohammed Elhenawy, F. Guo, H. Rakha
Bike sharing systems (BSSs) have become a convenient and environmentally friendly transportation mode, but may suffer from logistical issues such as bike shortages at stations. Predicting bike counts would help mitigate imbalances in the system. Research has focused on global prediction techniques but has neglected the role of user incentives. We adopted two computational techniques to capture BSS dynamics: mini-batch gradient descent for the linear regression (MBGDLR) and locally weighted regression (LWR). The two approaches used incremental learning based only on the previous status of the station with neither weather nor time information. The models were applied to a BSS data set for one year (2014–2015) in the San Francisco Bay Area for different prediction windows. Both models gave comparable results. LWR performed slightly better than MBGDLR for all prediction windows. The smallest prediction error for LWR was 0.31 bikes/station (4% prediction error) for a 15-minute prediction window and 0.32 bikes/station for MBGDLR. The 120-minute prediction window had the largest prediction error of 1.1 bikes/station and 1.2 bikes/station for LWR and MBGDLR, respectively. Computationally, MBGDLR was 55 times faster than LWR and proved to be faster than other machine learning and time series algorithms.
{"title":"Incremental Learning Models of Bike Counts at Bike Sharing Systems","authors":"M. Almannaa, Mohammed Elhenawy, F. Guo, H. Rakha","doi":"10.1109/ITSC.2018.8569735","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569735","url":null,"abstract":"Bike sharing systems (BSSs) have become a convenient and environmentally friendly transportation mode, but may suffer from logistical issues such as bike shortages at stations. Predicting bike counts would help mitigate imbalances in the system. Research has focused on global prediction techniques but has neglected the role of user incentives. We adopted two computational techniques to capture BSS dynamics: mini-batch gradient descent for the linear regression (MBGDLR) and locally weighted regression (LWR). The two approaches used incremental learning based only on the previous status of the station with neither weather nor time information. The models were applied to a BSS data set for one year (2014–2015) in the San Francisco Bay Area for different prediction windows. Both models gave comparable results. LWR performed slightly better than MBGDLR for all prediction windows. The smallest prediction error for LWR was 0.31 bikes/station (4% prediction error) for a 15-minute prediction window and 0.32 bikes/station for MBGDLR. The 120-minute prediction window had the largest prediction error of 1.1 bikes/station and 1.2 bikes/station for LWR and MBGDLR, respectively. Computationally, MBGDLR was 55 times faster than LWR and proved to be faster than other machine learning and time series algorithms.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"42 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":"127532915","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.2018.8569485
Abdul Rahman Kreidieh, Cathy Wu, A. Bayen
This article demonstrates the ability for model-free reinforcement learning (RL) techniques to generate traffic control strategies for connected and automated vehicles (CAVs) in various network geometries. This method is demonstrated to achieve near complete wave dissipation in a straight open road network with only 10% CAV penetration, while penetration rates as low as 2.5% are revealed to contribute greatly to reductions in the frequency and magnitude of formed waves. Moreover, a study of controllers generated in closed network scenarios exhibiting otherwise similar densities and perturbing behaviors confirms that closed network policies generalize to open network tasks, and presents the potential role of transfer learning in fine-tuning the parameters of these policies. Videos of the results are available at: https://sites.google.com/view/itsc-dissipating-waves.
{"title":"Dissipating stop-and-go waves in closed and open networks via deep reinforcement learning","authors":"Abdul Rahman Kreidieh, Cathy Wu, A. Bayen","doi":"10.1109/ITSC.2018.8569485","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569485","url":null,"abstract":"This article demonstrates the ability for model-free reinforcement learning (RL) techniques to generate traffic control strategies for connected and automated vehicles (CAVs) in various network geometries. This method is demonstrated to achieve near complete wave dissipation in a straight open road network with only 10% CAV penetration, while penetration rates as low as 2.5% are revealed to contribute greatly to reductions in the frequency and magnitude of formed waves. Moreover, a study of controllers generated in closed network scenarios exhibiting otherwise similar densities and perturbing behaviors confirms that closed network policies generalize to open network tasks, and presents the potential role of transfer learning in fine-tuning the parameters of these policies. Videos of the results are available at: https://sites.google.com/view/itsc-dissipating-waves.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"82 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":"124851883","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.2018.8569286
Xin Li, Yifan Dang, Tefang Chen
Recently, with the rapid development of autonomous vehicles and connected vehicles, the demands of vehicular computing keep continuously growing. We notice a constant and limited onboard computational ability can hardly keep up with the rising requirements of the vehicular system and software application during their long-term lifetime, and also at the same time, the vehicles onboard computation causes an increasingly higher vehicular energy consumption. Therefore, we suppose to build a vehicular edge cloud computing (VECC) framework to resolve such a vehicular computing dilemma. In this framework, potential vehicular computing tasks can be executed remotely in an edge cloud within their time latency constraints. Simultaneously, an effective wireless network resources allocation scheme is one of the essential and fundamental factors for the QoS (quality of Service) on the VECC. In this paper, we adopted a stochastic fair allocation (SFA) algorithm to randomly allocate minimum required resource blocks to admitted vehicular users. The numerical results show a great effectiveness of energy efficiency in VECC.
{"title":"Vehicular Edge Cloud Computing: Depressurize the Intelligent Vehicles Onboard Computational Power","authors":"Xin Li, Yifan Dang, Tefang Chen","doi":"10.1109/ITSC.2018.8569286","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569286","url":null,"abstract":"Recently, with the rapid development of autonomous vehicles and connected vehicles, the demands of vehicular computing keep continuously growing. We notice a constant and limited onboard computational ability can hardly keep up with the rising requirements of the vehicular system and software application during their long-term lifetime, and also at the same time, the vehicles onboard computation causes an increasingly higher vehicular energy consumption. Therefore, we suppose to build a vehicular edge cloud computing (VECC) framework to resolve such a vehicular computing dilemma. In this framework, potential vehicular computing tasks can be executed remotely in an edge cloud within their time latency constraints. Simultaneously, an effective wireless network resources allocation scheme is one of the essential and fundamental factors for the QoS (quality of Service) on the VECC. In this paper, we adopted a stochastic fair allocation (SFA) algorithm to randomly allocate minimum required resource blocks to admitted vehicular users. The numerical results show a great effectiveness of energy efficiency in VECC.","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":"126129859","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.2018.8569425
Christian Pek, M. Althoff
Ensuring the safety of self-driving vehicles is a challenging task, especially if other traffic participants severely deviate from the predicted behavior. One solution is to ensure that the vehicle is able to execute a collision-free evasive trajectory at any time. However, a fast method to plan these socalled fail-safe trajectories does not yet exist. Our new approach plans fail-safe trajectories in arbitrary traffic scenarios by incorporating convex optimization techniques. By integrating safety verification in the planner, we are able to generate fail-safe trajectories in real-time, which are guaranteed to be safe. At the same time, we minimize jerk to provide enhanced comfort for passengers. The proposed benefits are demonstrated in different urban and highway scenarios using the CommonRoad benchmark suite and compared to a widely-used sampling-based planner.
{"title":"Computationally Efficient Fail-safe Trajectory Planning for Self-driving Vehicles Using Convex Optimization","authors":"Christian Pek, M. Althoff","doi":"10.1109/ITSC.2018.8569425","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569425","url":null,"abstract":"Ensuring the safety of self-driving vehicles is a challenging task, especially if other traffic participants severely deviate from the predicted behavior. One solution is to ensure that the vehicle is able to execute a collision-free evasive trajectory at any time. However, a fast method to plan these socalled fail-safe trajectories does not yet exist. Our new approach plans fail-safe trajectories in arbitrary traffic scenarios by incorporating convex optimization techniques. By integrating safety verification in the planner, we are able to generate fail-safe trajectories in real-time, which are guaranteed to be safe. At the same time, we minimize jerk to provide enhanced comfort for passengers. The proposed benefits are demonstrated in different urban and highway scenarios using the CommonRoad benchmark suite and compared to a widely-used sampling-based planner.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"29 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":"125289996","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.2018.8569809
Mohamed Hadded, Jean-Marc Lasgouttes, F. Nashashibi, Ilias Xydias
In this paper, we consider the problem of vehicle collection assisted by a fleet manager where parked vehicles are collected and guided by fleet managers. Each platoon follows a calculated and optimized route to collect and guide the parked vehicles to their final destinations. The Platoon Route Optimization for Picking up Automated Vehicles problem, called PROPAV, consists in minimizing the collection duration, the number of platoons and the total energy required by the platoon leaders. We propose a formal definition of PROPAV as an integer linear programming problem, and then we show how to use the Non-dominated Sorting Genetic Algorithm II (NSGA-II), to deal with this multi-criteria optimization problem. Results in various configurations are presented to demonstrate the capabilities of NSGA-II to provide well-distributed Pareto-front solutions.
{"title":"Platoon Route Optimization for Picking up Automated Vehicles in an Urban Network","authors":"Mohamed Hadded, Jean-Marc Lasgouttes, F. Nashashibi, Ilias Xydias","doi":"10.1109/ITSC.2018.8569809","DOIUrl":"https://doi.org/10.1109/ITSC.2018.8569809","url":null,"abstract":"In this paper, we consider the problem of vehicle collection assisted by a fleet manager where parked vehicles are collected and guided by fleet managers. Each platoon follows a calculated and optimized route to collect and guide the parked vehicles to their final destinations. The Platoon Route Optimization for Picking up Automated Vehicles problem, called PROPAV, consists in minimizing the collection duration, the number of platoons and the total energy required by the platoon leaders. We propose a formal definition of PROPAV as an integer linear programming problem, and then we show how to use the Non-dominated Sorting Genetic Algorithm II (NSGA-II), to deal with this multi-criteria optimization problem. Results in various configurations are presented to demonstrate the capabilities of NSGA-II to provide well-distributed Pareto-front solutions.","PeriodicalId":395239,"journal":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","volume":"42 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":"126901601","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：