This paper focuses on the solution for conflict detection and resolution (CDR) of unmanned aerial vehicles (UAVs) by heading control. The cooperative method is proposed. First, the relationships between conflicts involved UAVs are described by the geometric method. The practical and potential conflicts are considered. Then, the CDR problem is formalized as a nonlinear optimization problem so as to minimize maneuver costs. Moreover, a two-layer strategy composed of stochastic parallel gradient descent (SPGD) and interior-point algorithm is designed to efficiently solve the non-convex optimization problem. Finally, our approach is demonstrated on several scenarios and the simulation results show that it can achieve high performance in obtaining near optimal maneuvers for UAVs CDR.
{"title":"Two-Layer Optimization to Cooperative Conflict Detection and Resolution for UAVs","authors":"Jian Yang, Dong Yin, Qiao Cheng, Xu Xie","doi":"10.1109/ITSC.2015.335","DOIUrl":"https://doi.org/10.1109/ITSC.2015.335","url":null,"abstract":"This paper focuses on the solution for conflict detection and resolution (CDR) of unmanned aerial vehicles (UAVs) by heading control. The cooperative method is proposed. First, the relationships between conflicts involved UAVs are described by the geometric method. The practical and potential conflicts are considered. Then, the CDR problem is formalized as a nonlinear optimization problem so as to minimize maneuver costs. Moreover, a two-layer strategy composed of stochastic parallel gradient descent (SPGD) and interior-point algorithm is designed to efficiently solve the non-convex optimization problem. Finally, our approach is demonstrated on several scenarios and the simulation results show that it can achieve high performance in obtaining near optimal maneuvers for UAVs CDR.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"49 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":"124949131","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}
A macroscopic model for predicting the evolution of traffic on medium-scale networks is proposed in this paper. The model takes into consideration the flows of vehicles which move from some origins to some destinations, and it is based on the LWR discrete-time/discrete-space vehicle conservation equation, which leads to quite simple models that can be employed within optimization and control schemes, aimed at regulating traffic and mitigating congestions at neighbourhood level. In the proposed model, vehicles are not constrained to stay in a link for at least one time interval, as they are allowed to enter a link and exit from it within the same interval. This feature requires a particular property (upstream dependence) of the digraph which represents the traffic network, in any case, a modified version of the dynamic model is also proposed in the paper, in order to deal with complex networks which do not have such a property.
{"title":"A Medium-Scale Network Model for Short-Term Traffic Prediction at Neighbourhood Level","authors":"D. Giglio","doi":"10.1109/ITSC.2015.228","DOIUrl":"https://doi.org/10.1109/ITSC.2015.228","url":null,"abstract":"A macroscopic model for predicting the evolution of traffic on medium-scale networks is proposed in this paper. The model takes into consideration the flows of vehicles which move from some origins to some destinations, and it is based on the LWR discrete-time/discrete-space vehicle conservation equation, which leads to quite simple models that can be employed within optimization and control schemes, aimed at regulating traffic and mitigating congestions at neighbourhood level. In the proposed model, vehicles are not constrained to stay in a link for at least one time interval, as they are allowed to enter a link and exit from it within the same interval. This feature requires a particular property (upstream dependence) of the digraph which represents the traffic network, in any case, a modified version of the dynamic model is also proposed in the paper, in order to deal with complex networks which do not have such a property.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"15 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":"116785310","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}
Recommender systems have radically changed the way people find products, services and information. They are a precious tool in e-commerce and other online services and have slowly been clawing their way into the real-world stage. Location is one of the variables that can be useful in this new situation. While this particular area has been the subject of some research, it can go even further with the exploration of mobility. In this work, we analyze the integration of mobility in a recommender system with real mobility data from a public transportation network. We developed an algorithm that incorporates location and frequency in a conventional recommender system. Our results show successful recommendations of items adapted to users' mobility patterns.
{"title":"Discovering MARS: A Mobility Aware Recommender System","authors":"Ricardo Leal, P. Costa, Teresa Galvão","doi":"10.1109/ITSC.2015.8","DOIUrl":"https://doi.org/10.1109/ITSC.2015.8","url":null,"abstract":"Recommender systems have radically changed the way people find products, services and information. They are a precious tool in e-commerce and other online services and have slowly been clawing their way into the real-world stage. Location is one of the variables that can be useful in this new situation. While this particular area has been the subject of some research, it can go even further with the exploration of mobility. In this work, we analyze the integration of mobility in a recommender system with real mobility data from a public transportation network. We developed an algorithm that incorporates location and frequency in a conventional recommender system. Our results show successful recommendations of items adapted to users' mobility patterns.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"159 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":"123021691","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}
M. Magrini, D. Moroni, G. Palazzese, G. Pieri, G. Leone, O. Salvetti
Capillary monitoring of traffic in urban environment is key to a more sustainable mobility in smart cities. In this context, the use of low cost technologies is mandatory to avoid scalability issues that would prevent the adoption of monitoring solutions at the full city scale. In this paper, we introduce a low power and low cost sensor equipped with embedded vision logics that can be used for building Smart Camera Networks (SCN) for applications in Intelligent Transportation System (ITS), in particular, we describe an ad hoc computer vision algorithm for estimation of traffic flow and discuss the findings obtained through an actual field test.
{"title":"Computer Vision on Embedded Sensors for Traffic Flow Monitoring","authors":"M. Magrini, D. Moroni, G. Palazzese, G. Pieri, G. Leone, O. Salvetti","doi":"10.1109/ITSC.2015.35","DOIUrl":"https://doi.org/10.1109/ITSC.2015.35","url":null,"abstract":"Capillary monitoring of traffic in urban environment is key to a more sustainable mobility in smart cities. In this context, the use of low cost technologies is mandatory to avoid scalability issues that would prevent the adoption of monitoring solutions at the full city scale. In this paper, we introduce a low power and low cost sensor equipped with embedded vision logics that can be used for building Smart Camera Networks (SCN) for applications in Intelligent Transportation System (ITS), in particular, we describe an ad hoc computer vision algorithm for estimation of traffic flow and discuss the findings obtained through an actual field test.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"63 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":"131131833","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}
The data association algorithm plays the vital role of forming an appropriate and valid set of tracks from the available tracks at the fusion center, which are delivered by different sensor's local tracking systems. The architecture of the data association module has to be designed taking into account the fusion strategy of the sensor fusion system, the granularity and the quality of the data provided by the sensors. The current generation environment perception sensors used for automotive sensor fusion are capable of providing estimated kinematic and as well as non-kinematic information on the observed targets. This paper focuses on integrating the kinematic and non-kinematic information in a track-to-track association (T2TA) procedure. A scalable framework called Combi-Tor is introduced here that is designed to calculate the association decision using likelihood ratio tests based on the available kinematic and non-kinematic information on the targets, which are tracked and classified by different sensors. The calculation of the association decision includes the uncertainty in the sensor's local tracking and classification modules. The required sufficient statistical derivations are discussed. The performance of this T2TA framework and the traditional T2TA scheme considering only the kinematic information are evaluated using Monte-Carlo simulation. The initial results obtained using the real world sensor data is presented.
{"title":"Combi-Tor: Track-to-Track Association Framework for Automotive Sensor Fusion","authors":"B. Duraisamy, T. Schwarz","doi":"10.1109/ITSC.2015.263","DOIUrl":"https://doi.org/10.1109/ITSC.2015.263","url":null,"abstract":"The data association algorithm plays the vital role of forming an appropriate and valid set of tracks from the available tracks at the fusion center, which are delivered by different sensor's local tracking systems. The architecture of the data association module has to be designed taking into account the fusion strategy of the sensor fusion system, the granularity and the quality of the data provided by the sensors. The current generation environment perception sensors used for automotive sensor fusion are capable of providing estimated kinematic and as well as non-kinematic information on the observed targets. This paper focuses on integrating the kinematic and non-kinematic information in a track-to-track association (T2TA) procedure. A scalable framework called Combi-Tor is introduced here that is designed to calculate the association decision using likelihood ratio tests based on the available kinematic and non-kinematic information on the targets, which are tracked and classified by different sensors. The calculation of the association decision includes the uncertainty in the sensor's local tracking and classification modules. The required sufficient statistical derivations are discussed. The performance of this T2TA framework and the traditional T2TA scheme considering only the kinematic information are evaluated using Monte-Carlo simulation. The initial results obtained using the real world sensor data is presented.","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":"131542755","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 autonomous driving, road markings are an essential element for high-precision mapping, trajectory planning and can provide important information for localization. This paper presents an approach to detect, classify and approximate a great variety of road markings using a stereoscopic camera system. We present an algorithm that is able to classify characters and arrows as well as stop-lines, pedestrian crossings, dashed and straight lines, etc. The classification is independent of orientation, position or the exact shape. This is achieved using a histogram of the marking width as main part of the feature vector for line-shaped markings and Optical Character Recognition (OCR) for characters. Classification is done by an Artificial Neural Network (ANN). We have evaluated our approach over a 10.5 km drive through an urban area.
{"title":"A Universal Approach to Detect and Classify Road Surface Markings","authors":"Fabian Poggenhans, M. Schreiber, C. Stiller","doi":"10.1109/ITSC.2015.310","DOIUrl":"https://doi.org/10.1109/ITSC.2015.310","url":null,"abstract":"In autonomous driving, road markings are an essential element for high-precision mapping, trajectory planning and can provide important information for localization. This paper presents an approach to detect, classify and approximate a great variety of road markings using a stereoscopic camera system. We present an algorithm that is able to classify characters and arrows as well as stop-lines, pedestrian crossings, dashed and straight lines, etc. The classification is independent of orientation, position or the exact shape. This is achieved using a histogram of the marking width as main part of the feature vector for line-shaped markings and Optical Character Recognition (OCR) for characters. Classification is done by an Artificial Neural Network (ANN). We have evaluated our approach over a 10.5 km drive through an urban area.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"22 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":"131758701","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}
A. Styler, A. Sauer, I. Nourbakhsh, H. Rottengruber
Each year, hybrid vehicles command a larger portion of total vehicles on the road. These vehicles combine multiple sources of energy, such as batteries and gasoline, which have different strengths and weaknesses. Active management of these energy sources can increase vehicle efficiency, longevity, or performance. Optimizing energy management is highly sensitive to upcoming power loads on the vehicle, but conventional control policies only react to the present state. Furthermore, these policies are computed at design-time and do not adapt to individual drivers. Advancements in cheap sensing and computation have enabled on-board learning and optimization that was previously impossible. In this work, we developed and implemented a real-time controller that exploits predictions computed from a dataset collected from other drivers. This data-driven controller manages a range-extender in a series gas-electric hybrid vehicle, optimizing fuel use, noise, and ignition frequency. The algorithm is scalable to large amounts of source data, and performance improves with prediction accuracy. We tested the algorithm in simulation and on a modified vehicle with direct programmatic control of the range extender. The experimental results on the vehicle reflected those observed in simulation, achieving fuel savings up to 12% and a noise-cost reduction of 73%.
{"title":"Learned Optimal Control of a Range Extender in a Series Hybrid Vehicle","authors":"A. Styler, A. Sauer, I. Nourbakhsh, H. Rottengruber","doi":"10.1109/ITSC.2015.420","DOIUrl":"https://doi.org/10.1109/ITSC.2015.420","url":null,"abstract":"Each year, hybrid vehicles command a larger portion of total vehicles on the road. These vehicles combine multiple sources of energy, such as batteries and gasoline, which have different strengths and weaknesses. Active management of these energy sources can increase vehicle efficiency, longevity, or performance. Optimizing energy management is highly sensitive to upcoming power loads on the vehicle, but conventional control policies only react to the present state. Furthermore, these policies are computed at design-time and do not adapt to individual drivers. Advancements in cheap sensing and computation have enabled on-board learning and optimization that was previously impossible. In this work, we developed and implemented a real-time controller that exploits predictions computed from a dataset collected from other drivers. This data-driven controller manages a range-extender in a series gas-electric hybrid vehicle, optimizing fuel use, noise, and ignition frequency. The algorithm is scalable to large amounts of source data, and performance improves with prediction accuracy. We tested the algorithm in simulation and on a modified vehicle with direct programmatic control of the range extender. The experimental results on the vehicle reflected those observed in simulation, achieving fuel savings up to 12% and a noise-cost reduction of 73%.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"2013 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":"133572014","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}
Konrad Stahl, Klaus-Dieter Leimbach, Ansgar Meroth, R. Zöllner
In this paper the modeling and simulation of a six degree of freedom hexapod platform simulator is presented. The simulator is used for vehicle driving simulations. Washout algorithms are used for the control of the platform. Components of the washout algorithms are low pass filters and high pass filters, as well as a tilt coordination algorithm. A test with realistic input acceleration data of a vehicle maneuver is performed to verify the model.
{"title":"A Washout and a Tilt Coordination Algorithm for a Hexapod Platform","authors":"Konrad Stahl, Klaus-Dieter Leimbach, Ansgar Meroth, R. Zöllner","doi":"10.1109/ITSC.2015.197","DOIUrl":"https://doi.org/10.1109/ITSC.2015.197","url":null,"abstract":"In this paper the modeling and simulation of a six degree of freedom hexapod platform simulator is presented. The simulator is used for vehicle driving simulations. Washout algorithms are used for the control of the platform. Components of the washout algorithms are low pass filters and high pass filters, as well as a tilt coordination algorithm. A test with realistic input acceleration data of a vehicle maneuver is performed to verify the model.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"157 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":"133516640","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}
The knowledge of traffic light parameters, such as cycle plan or future signal phase and timing information (SPaT) of traffic lights is the base for a vast number of use scenarios. A few examples are traffic signal adaptive routing, green light optimal speed control, red light duration advisory or efficient start-stop control. The basis for all these functionalities is the knowledge on the correct traffic light cycle time, i.e. the periodicity of the traffic light's signaling sequence. With a correct cycle time given, green start and end times can be derived from periodically reoccurring movement patterns. In this paper, we propose a method to reconstruct a traffic light's cycle plan through the interpretation of the recorded information on a vehicle's movement pattern (trajectory) in the intersection area. The recorded trajectories are temporarily sparse and and the cycle plan changes frequently. Therefore, we propose a model that focuses on the performance on very limited available trajectory data and yet is robust with regard to estimation errors. We show that our approach is able to detect the correct cycle time with already 30 trajectories at an accuracy of 99%.
{"title":"Learning Traffic Light Parameters with Floating Car Data","authors":"Valentin Protschky, Christian Ruhhammer, S. Feit","doi":"10.1109/ITSC.2015.393","DOIUrl":"https://doi.org/10.1109/ITSC.2015.393","url":null,"abstract":"The knowledge of traffic light parameters, such as cycle plan or future signal phase and timing information (SPaT) of traffic lights is the base for a vast number of use scenarios. A few examples are traffic signal adaptive routing, green light optimal speed control, red light duration advisory or efficient start-stop control. The basis for all these functionalities is the knowledge on the correct traffic light cycle time, i.e. the periodicity of the traffic light's signaling sequence. With a correct cycle time given, green start and end times can be derived from periodically reoccurring movement patterns. In this paper, we propose a method to reconstruct a traffic light's cycle plan through the interpretation of the recorded information on a vehicle's movement pattern (trajectory) in the intersection area. The recorded trajectories are temporarily sparse and and the cycle plan changes frequently. Therefore, we propose a model that focuses on the performance on very limited available trajectory data and yet is robust with regard to estimation errors. We show that our approach is able to detect the correct cycle time with already 30 trajectories at an accuracy of 99%.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"111 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":"132219953","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}
Shuai Di, Honggang Zhang, Xue Mei, D. Prokhorov, Haibin Ling
Parsing road scene images taken from vehicle mounted cameras provides important information for high level tasks in automated on-road vehicles. In this paper we adopt the nonparametric framework for this problem and present a simple yet effective strategy to integrate spatial prior into the framework. Unlike natural scene images, road scene images in our problem typically have very stable scene layout, which motivates us to explore such layout for improving scene labeling. In particular, the spatial distribution of each semantic category is obtained from a set of previously observed data. Then, such distributions, in the form of histograms, are integrated into the nonparametric labeling framework to guide scene parsing. Compared with previous approaches, our solution is very efficient in both computation and memory usage, since there is no complicated semantic training involved. For evaluation, we collected three video datasets on three different trips and ran the proposed algorithm on all of them, both within each trip or cross trip. The experimental results show advantages of our algorithm.
{"title":"Spatial Prior for Nonparametric Road Scene Parsing","authors":"Shuai Di, Honggang Zhang, Xue Mei, D. Prokhorov, Haibin Ling","doi":"10.1109/ITSC.2015.199","DOIUrl":"https://doi.org/10.1109/ITSC.2015.199","url":null,"abstract":"Parsing road scene images taken from vehicle mounted cameras provides important information for high level tasks in automated on-road vehicles. In this paper we adopt the nonparametric framework for this problem and present a simple yet effective strategy to integrate spatial prior into the framework. Unlike natural scene images, road scene images in our problem typically have very stable scene layout, which motivates us to explore such layout for improving scene labeling. In particular, the spatial distribution of each semantic category is obtained from a set of previously observed data. Then, such distributions, in the form of histograms, are integrated into the nonparametric labeling framework to guide scene parsing. Compared with previous approaches, our solution is very efficient in both computation and memory usage, since there is no complicated semantic training involved. For evaluation, we collected three video datasets on three different trips and ran the proposed algorithm on all of them, both within each trip or cross trip. The experimental results show advantages of our algorithm.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"133 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":"134287862","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：