Showing papers in "IEEE Transactions on Intelligent Transportation Systems in 2007"
TL;DR: An automatic road-sign detection and recognition system based on support vector machines that is able to detect and recognize circular, rectangular, triangular, and octagonal signs and, hence, covers all existing Spanish traffic-sign shapes.
Abstract: This paper presents an automatic road-sign detection and recognition system based on support vector machines (SVMs). In automatic traffic-sign maintenance and in a visual driver-assistance system, road-sign detection and recognition are two of the most important functions. Our system is able to detect and recognize circular, rectangular, triangular, and octagonal signs and, hence, covers all existing Spanish traffic-sign shapes. Road signs provide drivers important information and help them to drive more safely and more easily by guiding and warning them and thus regulating their actions. The proposed recognition system is based on the generalization properties of SVMs. The system consists of three stages: 1) segmentation according to the color of the pixel; 2) traffic-sign detection by shape classification using linear SVMs; and 3) content recognition based on Gaussian-kernel SVMs. Because of the used segmentation stage by red, blue, yellow, white, or combinations of these colors, all traffic signs can be detected, and some of them can be detected by several colors. Results show a high success rate and a very low amount of false positives in the final recognition stage. From these results, we can conclude that the proposed algorithm is invariant to translation, rotation, scale, and, in many situations, even to partial occlusions
687 citations
TL;DR: A comprehensive review of research efforts underway dealing with pedestrian safety and collision avoidance is presented, including research dealing with probabilistic modeling of pedestrian behavior for predicting collisions between pedestrians and vehicles.
Abstract: This paper describes the recent research on the enhancement of pedestrian safety to help develop a better understanding of the nature, issues, approaches, and challenges surrounding the problem. It presents a comprehensive review of research efforts underway dealing with pedestrian safety and collision avoidance. The importance of pedestrian protection is emphasized in a global context, discussing the research programs and efforts in various countries. Pedestrian safety measures, including infrastructure enhancements and passive safety features in vehicles, are described, followed by a systematic description of active safety systems based on pedestrian detection using sensors in vehicle and infrastructure. The pedestrian detection approaches are classified according to various criteria such as the type and configuration of sensors, as well as the video cues and classifiers used in detection algorithms. It is noted that collision avoidance not only requires detection of pedestrians but also requires collision prediction using pedestrian dynamics and behavior analysis. Hence, this paper includes research dealing with probabilistic modeling of pedestrian behavior for predicting collisions between pedestrians and vehicles.
540 citations
TL;DR: In this article, a real-time approach for detecting cognitive distraction using drivers' eye movements and driving performance data was proposed. But the results showed that the SVM models were able to detect driver distraction with an average accuracy of 81.1%, outperforming more traditional logistic regression models.
Abstract: As use of in-vehicle information systems (IVISs) such as cell phones, navigation systems, and satellite radios has increased, driver distraction has become an important and growing safety concern. A promising way to overcome this problem is to detect driver distraction and adapt in-vehicle systems accordingly to mitigate such distractions. To realize this strategy, this paper applied support vector machines (SVMs), which is a data mining method, to develop a real-time approach for detecting cognitive distraction using drivers' eye movements and driving performance data. Data were collected in a simulator experiment in which ten participants interacted with an IVIS while driving. The data were used to train and test both SVM and logistic regression models, and three different model characteristics were investigated: how distraction was defined, which data were input to the model, and how the input data were summarized. The results show that the SVM models were able to detect driver distraction with an average accuracy of 81.1%, outperforming more traditional logistic regression models. The best performing model (96.1% accuracy) resulted when distraction was defined using experimental conditions (i.e., IVIS drive or baseline drive), the input data were comprised of eye movement and driving measures, and these data were summarized over a 40-s window with 95% overlap of windows. These results demonstrate that eye movements and simple measures of driving performance can be used to detect driver distraction in real time. Potential applications of this paper include the design of adaptive in-vehicle systems and the evaluation of driver distraction
439 citations
TL;DR: In this article, a system-oriented framework for developing computer-vision technology for safer automobiles is presented, which considers three main components of the system: environment, vehicle, and driver.
Abstract: This paper presents investigations into the role of computer-vision technology in developing safer automobiles. We consider vision systems, which cannot only look out of the vehicle to detect and track roads and avoid hitting obstacles or pedestrians but simultaneously look inside the vehicle to monitor the attentiveness of the driver and even predict her intentions. In this paper, a systems-oriented framework for developing computer-vision technology for safer automobiles is presented. We will consider three main components of the system: environment, vehicle, and driver. We will discuss various issues and ideas for developing models for these main components as well as activities associated with the complex task of safe driving. This paper includes a discussion of novel sensory systems and algorithms for capturing not only the dynamic surround information of the vehicle but also the state, intent, and activity patterns of drivers
320 citations
TL;DR: Good performance can be achieved with the lowest information case, with a time-invariant controller that is optimized to the environment, and a predictive controller based on information supplied by the vehicle-navigation system and traffic-flow-information systems that can come very close to the minimal attainable fuel consumption are shown.
Abstract: The potential for reduced fuel consumption of hybrid electric vehicles by the use of predictive powertrain control was assessed on measured-drive data from an urban route with varying topography. The assessment was done by evaluating the fuel consumption using three optimal controllers, each with a different level of information access to the driven route. The lowest information case represents that the vehicle knows that it is being driven in a certain environment, e.g., city driving, and that the controller has been optimized for that type of environment. The second highest information level represents a vehicle equipped with a GPS combined with a traffic-flow information system. In the highest information level, the future power demand is completely known to the control system, hence, the corresponding optimal controller results in the minimal attainable fuel consumption. This paper showed that good performance (1%-3% from the minimal attainable fuel consumption) can be achieved with the lowest information case, with a time-invariant controller that is optimized to the environment. The second highest information level results in less than 0.2% higher consumption than the minimal attainable on the studied route. This means that it is possible to design a predictive controller based on information supplied by the vehicle-navigation system and traffic-flow-information systems that can come very close to the minimal attainable fuel consumption. A novel algorithm that uses information supplied by the vehicle-navigation system was presented. The proposed algorithm results in a consumption only 0.3% from the minimal attainable consumption on the studied route
280 citations
TL;DR: The history of the founding of PATH and of the national ITS program in the U.S. is reviewed, providing perspective on the changes that have occurred during the past 20 years.
Abstract: The California partners for advanced transit and highways (PATH) program was founded in 1986, as the first research program in North America focused on the subject now known as intelligent transportation systems (ITS). This paper reviews the history of the founding of PATH and of the national ITS program in the U.S., providing perspective on the changes that have occurred during the past 20 years.
238 citations
TL;DR: A driver intent inference system (DIIS) based on lane positional information, vehicle parameters, and driver head motion, which is evaluated on real-world data collected in a modular intelligent vehicle test-bed using a sparse Bayesian learning methodology.
Abstract: In this paper, we demonstrate a driver intent inference system that is based on lane positional information, vehicle parameters, and driver head motion. We present robust computer vision methods for identifying and tracking freeway lanes and driver head motion. These algorithms are then applied and evaluated on real-world data that are collected in a modular intelligent vehicle test bed. Analysis of the data for lane change intent is performed using a sparse Bayesian learning methodology. Finally, the system as a whole is evaluated using a novel metric and real-world data of vehicle parameters, lane position, and driver head motion.
236 citations
TL;DR: In this article, a vehicle detection system fusing radar and vision data is described, where the radar data is used to locate areas of interest on images and vehicle search in these areas is mainly based on vertical symmetry.
Abstract: This paper describes a vehicle detection system fusing radar and vision data. Radar data are used to locate areas of interest on images. Vehicle search in these areas is mainly based on vertical symmetry. All the vehicles found in different image areas are mixed together, and a series of filters is applied in order to delete false detections. In order to speed up and improve system performance, guard rail detection and a method to manage overlapping areas are also included. Both methods are explained and justified in this paper. The current algorithm analyzes images on a frame-by-frame basis without any temporal correlation. Two different statistics, namely: 1) frame based and 2) event based, are computed to evaluate vehicle detection efficiency, while guard rail detection efficiency is computed in terms of time savings and correct detection rates. Results and problems are discussed, and directions for future enhancements are provided
224 citations
TL;DR: An automated dispatching system provides better solutions in terms of delay minimization when compared to dispatching rules that can be adopted by a human traffic controller.
Abstract: During rail operations, unforeseen events may cause timetable perturbations, which ask for the capability of traffic management systems to reschedule trains and to restore the timetable feasibility. Based on an accurate monitoring of train positions and speeds, potential conflicting routes can be predicted in advance and resolved in real time. The adjusted targets (location-time-speed) would be then communicated to the relevant trains by which drivers should be able to anticipate the changed traffic circumstances and adjust the train's speed accordingly. We adopt a detailed alternative graph model for the train dispatching problem. Conflicts between different trains are effectively detected and solved. Adopting the blocking time model, we ascertain whether a safe distance headway between trains is respected, and we also consider speed coordination issues among consecutive trains. An iterative rescheduling procedure provides an acceptable speed profile for each train over the intended time horizon. After a finite number of iterations, the final solution is a conflict-free schedule that respects the signaling and safety constraints. A computational study based on a hourly cyclical timetable of the Schiphol railway network has been carried out. Our automated dispatching system provides better solutions in terms of delay minimization when compared to dispatching rules that can be adopted by a human traffic controller
217 citations
TL;DR: A set of tests performed in controlled and real scenarios proves the suitability of the proposed IMM-EKF implementation as compared with low-cost GNSS-based solutions, dead reckoning systems, single-model EKF, and other filtering approaches of the current literature.
Abstract: User requirements for the performance of Global Navigation Satellite System (GNSS)-based road applications have been significantly increasing in recent years. Safety systems based on vehicle localization, electronic fee-collection systems, and traveler information services are just a few examples of interesting applications requiring onboard equipment (OBE) capable of offering a high available accurate position, even in unfriendly environments with low satellite visibility such as built-up areas or tunnels and at low cost. In addition to that, users and service providers demand from the OBEs not only accurate continuous positioning but integrity information of the reliability of this position as well. Specifically, in life-critical applications, high-integrity monitored positioning is absolutely required. This paper presents a solution based on the fusion of GNSS and inertial sensors (a Global Positioning System/satellite-based augmentation system/inertial navigation system integrated system) running an extended Kalman filter combined with an interactive multimodel method (IMM-EKF). The solution developed in this paper supplies continuous positioning in marketable conditions and a meaningful trust level of the given solution. A set of tests performed in controlled and real scenarios proves the suitability of the proposed IMM-EKF implementation as compared with low-cost GNSS-based solutions, dead reckoning systems, single-model EKF, and other filtering approaches of the current literature.
193 citations
TL;DR: This contribution points out the main requirements for pedestrian-navigation technologies and presents an approach to identify pedestrian flows and to imply landmark information into navigation services for pedestrians.
Abstract: Pedestrian-navigation services enable people to retrieve precise instructions to reach a specific location. However, the development of mobile spatial-information technologies for pedestrians is still at the beginning and faces several difficulties. As the spatial behavior of people on foot differs in many ways from the driver's performance, common concepts for car-navigation services are not suitable for pedestrian navigation. Particularly, the usage of landmarks is vitally important in human navigation. This contribution points out the main requirements for pedestrian-navigation technologies and presents an approach to identify pedestrian flows and to imply landmark information into navigation services for pedestrians
TL;DR: A components-based learning approach is proposed in order to better deal with pedestrian variability, illumination conditions, partial occlusions, and rotations and suggest a combination of feature extraction methods as an essential clue for enhanced detection performance.
Abstract: This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a support-vector-machine-based classifier. This poses the problem of pedestrian detection in real cluttered road images. Candidate pedestrians are located using a subtractive clustering attention mechanism based on stereo vision. A components-based learning approach is proposed in order to better deal with pedestrian variability, illumination conditions, partial occlusions, and rotations. Extensive comparisons have been carried out using different feature extraction methods as a key to image understanding in real traffic conditions. A database containing thousands of pedestrian samples extracted from real traffic images has been created for learning purposes at either daytime or nighttime. The results achieved to date show interesting conclusions that suggest a combination of feature extraction methods as an essential clue for enhanced detection performance
TL;DR: The proposed approach is a hierarchical-structured algorithm that fuses traffic environment data with car dynamics in order to accurately predict the trajectory of the ego-vehicle, allowing the active safety system to inform, warn the driver, or intervene when critical situations occur.
Abstract: Path prediction is the only way that an active safety system can predict a driver's intention. In this paper, a model-based description of the traffic environment is presented - both vehicles and infrastructure - in order to provide, in real time, sufficient information for an accurate prediction of the ego-vehicle's path. The proposed approach is a hierarchical-structured algorithm that fuses traffic environment data with car dynamics in order to accurately predict the trajectory of the ego-vehicle, allowing the active safety system to inform, warn the driver, or intervene when critical situations occur. The algorithms are tested with real data, under normal conditions, for collision warning (CW) and vision-enhancement applications. The results clearly show that this approach allows a dynamic situation and threat assessment and can enhance the capabilities of adaptive cruise control and CW functions by reducing the false alarm rate.
TL;DR: An online calibration approach that jointly estimates demand and supply parameters of dynamic traffic assignment (DTA) systems is presented and empirically validated through an extensive application.
Abstract: An online calibration approach that jointly estimates demand and supply parameters of dynamic traffic assignment (DTA) systems is presented and empirically validated through an extensive application The problem can be formulated as a nonlinear state-space model Because of its nonlinear nature, the resulting model cannot be solved by the Kalman filter, and therefore, nonlinear extensions need to be considered The following three extensions to the Kalman filtering algorithm are presented: 1) the extended Kalman filter (EKF); 2) the limiting EKF (LimEKF); and 3) the unscented Kalman filter The solution algorithms are applied to the on-line calibration of the state-of-the-art DynaMIT DTA model, and their use is demonstrated in a freeway network in Southampton, UK The LimEKF shows accuracy that is comparable to that of the best algorithm but with vastly superior computational performance The robustness of the approach to varying weather conditions is demonstrated, and practical aspects are discussed
TL;DR: A vision-based traffic accident detection algorithm and system for automatically detecting, recording, and reporting traffic accidents at intersections and makes decisions on the traffic accident based on the extracted features.
Abstract: In this paper, we suggested a vision-based traffic accident detection algorithm and developed a system for automatically detecting, recording, and reporting traffic accidents at intersections. A system with these properties would be beneficial in determining the cause of accidents and the features of an intersection that impact safety. This model first extracts the vehicles from the video image of the charge-couple-device camera, tracks the moving vehicles (MVs), and extracts features such as the variation rate of the velocity, position, area, and direction of MVs. The model then makes decisions on the traffic accident based on the extracted features. In a field test, the suggested model achieved a correct detection rate (CDR) of 50% and a detection rate of 60%. Considering that a sound-based accident detection system showed a CDR of 1% and a DR of 66.1%, our result is a remarkable achievement
TL;DR: An evaluation of a candidate VSLS system for an urban freeway in Toronto, ON, Canada is presented using a microscopic simulation model combined with a categorical crash potential model for estimating safety impacts.
Abstract: Variable-speed limit sign (VSLS) systems enable transportation managers to dynamically change the posted speed limit in response to prevailing traffic and/or weather conditions. Although VSLSs have been implemented in a limited number of jurisdictions throughout the world, there is currently very limited documentation that describes quantitative safety and operational impacts. Furthermore, the impacts reported are primarily from systems in Europe and may not be directly transferable to other jurisdictions such as North America. This paper presents the results of an evaluation of a candidate VSLS system for an urban freeway in Toronto, ON, Canada. The evaluation was conducted using a microscopic simulation model combined with a categorical crash potential model for estimating safety impacts.
TL;DR: This modeling approach not only successfully models the mental workload measured by the six National Aeronautic and Space Administration Task Load Index workload scales in terms of subnetwork utilization but also simulates the driving performance, reflecting mental workload from both subjective- and performance-based measurements.
Abstract: Drivers overloaded with information significantly increase the chance of vehicle collisions. Driver workload, which is a multidimensional variable, is measured by both performance-based and subjective measurements and affected by driver age differences. Few existing computational models are able to cover these major properties of driver workload or simulate subjective mental workload and human performance at the same time. We describe a new computational approach in modeling driver performance and workload-a queuing network approach based on the queuing network theory of human performance and neuroscience discoveries. This modeling approach not only successfully models the mental workload measured by the six National Aeronautic and Space Administration Task Load Index workload scales in terms of subnetwork utilization but also simulates the driving performance, reflecting mental workload from both subjective- and performance-based measurements. In addition, it models age differences in workload and performance and allows us to visualize driver mental workload in real time. Further usage and implementation of the model in designing intelligent and adaptive in-vehicle systems are discussed.
TL;DR: A scheme that allows vehicles to estimate the local density and distinguish between the free-flow and the congested traffic phases is proposed and the density estimate is used to develop a dynamic transmission-range-assignment (DTRA) algorithm that sets a vehicle transmission range dynamically according to the local traffic conditions.
Abstract: Vehicular ad hoc networks have several characteristics that distinguish them from other ad hoc networks. Among those is the rapid change in topology due to traffic jams, which also disturbs the homogeneous distribution of vehicles on the road. For this reason, a dynamic transmission range is more effective in maintaining the connectivity while minimizing the adverse effects of a high transmission power. This paper proposes a scheme that allows vehicles to estimate the local density and distinguish between the free-flow and the congested traffic phases. The density estimate is used to develop a dynamic transmission-range-assignment (DTRA) algorithm that sets a vehicle transmission range dynamically according to the local traffic conditions. Simulations of several road configurations validate the quality of the local density estimation and show that the DTRA algorithm is successful in maintaining the connectivity in highly dynamic networks.
TL;DR: This paper demonstrates that the 1.0-s 85th-percentile PRT that is recommended in traffic-signal-design procedures is valid and consistent with the field observations, and demonstrates that either a lognormal or a beta distribution is sufficient to model the stochastic nature of the brake PRT.
Abstract: This paper involves a field test on 60 test participants to characterize driver behavior (perception-reaction time (PRT) and stopping/running decisions) at the onset of a yellow phase. Driver behavior is analyzed for five trigger distances that are measured from the vehicle position at the start of the yellow indication to the stop bar. This paper demonstrates that the 1.0-s 85th-percentile PRT that is recommended in traffic-signal-design procedures is valid and consistent with the field observations. Furthermore, this paper clearly shows that brake PRTs are impacted by the vehicle's time to intersection (TTI) at the onset of a yellow-indication introduction. This paper also demonstrates that either a lognormal or a beta distribution is sufficient to model the stochastic nature of the brake PRT. In terms of stopping decisions, this paper demonstrates that the probability of stopping varies from 100% at a TTI of 5.5 s to 9% at a TTI of 1.6 s. This paper also indicates a decrease in the probability of stopping for male drivers when compared with female drivers. Furthermore, this study suggests that drivers 65 years of age and older are significantly less likely to clear the intersection at short yellow-indication trigger distances when compared with other age groups. The dilemma zone for the less than 40 year old group is found to range from 3.9 to 1.85 s, whereas the dilemma zone for the greater than 70 year old group is found to range from 3.2 to 1.5 s.
TL;DR: A parameter estimation algorithm for the SS-ARX model with multiple measured input-output sequences is developed based on the expectation-maximization algorithm by extending the parameter estimation technique for the conventional hidden Markov model.
Abstract: This paper presents the development of the modeling and recognition of human driving behavior based on a stochastic switched autoregressive exogenous (SS-ARX) model. First, a parameter estimation algorithm for the SS-ARX model with multiple measured input-output sequences is developed based on the expectation-maximization algorithm. This can be achieved by extending the parameter estimation technique for the conventional hidden Markov model. Second, the developed parameter estimation algorithm is applied to driving data with the focus being on driver's collision avoidance behavior. The driving data were collected using a driving simulator based on the cave automatic virtual environment, which is a stereoscopic immersive virtual reality system. Then, the parameter set for each driver is obtained, and certain driving characteristics are identified from the viewpoint of switched control mechanism. Finally, the performance of the SS-ARX model as a behavior recognizer is examined. The results show that the SS-ARX model holds remarkable potential to function as a behavior recognizer.
TL;DR: Emergency Lane Assist is a new automotive safety function that combines conventional lane guidance systems with a threat assessment module that tries to activate the lane guidance interventions according to the actual risk level of lane departure.
Abstract: This paper presents a new automotive safety function called Emergency Lane Assist (ELA). ELA combines conventional lane guidance systems with a threat assessment module that tries to activate the lane guidance interventions according to the actual risk level of lane departure. The goal is to only prevent dangerous lane departure maneuvers. The ELA safety function is based on a statistical method that evaluates a list of safety concepts and tries to maximize the impact on accident statistics while minimizing development and hardware component costs. ELA runs in a demonstrator and successfully intervenes during lane changes that are likely to result in a collision and is also able to take control of the vehicle and return it to a safe position in the original lane. It has also been tested on 2000 km of roads in traffic without giving any false interventions
TL;DR: In this paper, a car-following model that was developed using a neural network approach for mapping perceptions to actions has been presented, which has a similar formulation to the desired spacing models that do not consider reaction time or attempt to explain the behavioral aspects of car following.
Abstract: This paper presents a car-following model that was developed using a neural network approach for mapping perceptions to actions The model has a similar formulation to the desired spacing models that do not consider reaction time or attempt to explain the behavioral aspects of car following The model's performance was evaluated based on field data and compared to a number of existing car-following models The results showed that neural network models outperformed the Gipps and psychophysical family of car-following models A qualitative drift behavior analysis also confirmed the findings The model was validated at the microscopic and macroscopic levels, and the results showed very close agreement between field data and model outputs Local and asymptotic stability analysis results also demonstrated the robustness of the model under mild and severe traffic disturbances
TL;DR: This paper designs a four-camera experimental testbed consisting of two color and two infrared cameras for capturing and analyzing various configuration permutations for pedestrian detection and proposes a multimodal trifocal framework consisting of a stereo pair of color cameras coupled with an infrared camera.
Abstract: This paper presents an analysis of color-, infrared-, and multimodal-stereo approaches to pedestrian detection. We design a four-camera experimental testbed consisting of two color and two infrared cameras for capturing and analyzing various configuration permutations for pedestrian detection. We incorporate this four-camera system in a test vehicle and conduct comparative experiments of stereo-based approaches to obstacle detection using unimodal color and infrared imageries. A detailed analysis of the color and infrared features used to classify detected obstacles into pedestrian regions is used to motivate the development of a multimodal solution to pedestrian detection. We propose a multimodal trifocal framework consisting of a stereo pair of color cameras coupled with an infrared camera. We use this framework to combine multimodal-image features for pedestrian detection and to demonstrate that the detection performance is significantly higher when color, disparity, and infrared features are used together. This result motivates experiments and discussion toward achieving multimodal-feature combination using a single color and a single infrared camera arranged in a cross-spectral stereo pair. We demonstrate an approach to registering multiple objects across modalities and provide an experimental analysis that highlights issues and challenges of pursuing the cross-spectral approach to multimodal and multiperspective pedestrian analysis.
TL;DR: A novel method to enhance license plate numbers of moving vehicles in real traffic videos is proposed by fusing the information derived from multiple, subpixel shifted, and noisy low-resolution observations to obtain a high-resolution image of the number plate.
Abstract: In this paper, a novel method to enhance license plate numbers of moving vehicles in real traffic videos is proposed. A high-resolution image of the number plate is obtained by fusing the information derived from multiple, subpixel shifted, and noisy low-resolution observations. The image to be superresolved is modeled as a Markov random field and is estimated from the observations by a graduated nonconvexity optimization procedure. A discontinuity adaptive regularizer is used to preserve the edges in the reconstructed number plate for improved readability. Experimental results are given on several traffic sequences to demonstrate the robustness of the proposed method to potential errors in motion and blur estimates. The method is computationally efficient as all operations can be implemented locally in the image domain
TL;DR: A development framework and novel algorithms for road situation analysis based on driving action behavior, where the safety situation is analyzed by simulating real driving action behaviors and the experimental results show that the approach is efficient forRoad situation evaluation and prediction.
Abstract: Road situation analysis in Interactive Intelligent Driver-Assistance and Safety Warning (I2DASW) systems involves estimation and prediction of the position and size of various on-road obstacles. Real-time processing, given incomplete and uncertain information, is a challenge for current object detection and tracking technologies. This paper proposed a development framework and novel algorithms for road situation analysis based on driving action behavior, where the safety situation is analyzed by simulating real driving action behaviors. First, we review recent development and trends in road situation analysis to provide perspective for the related research. Second, we introduce a road situation analysis framework, where onboard sensors provide information about drivers, traffic environment, and vehicles. Finally, on the basis of the previous frameworks, we proposed multiple-obstacle detection and tracking algorithms using multiple sensors including radar, lidar, and a camera, where a decentralized track-to-track fusion approach is introduced to fuse these sensors. In order to reduce the effect of obstacle shape and appearance, we cluster lidar data and then classify obstacles into two categories: static and moving objects. Future collisions are assessed by computation of local tracks of moving obstacles using extended Kalman filter, maximum likelihood estimation to fuse distributed local tracks into global tracks, and finally, computation of future collision distribution from the global tracks. Our experimental results show that our approach is efficient for road situation evaluation and prediction
TL;DR: In this article, the adaptive space division multiplexing (ASDM) protocol is proposed for safety-related intervehicle communication (IVC) networks, which requires no control messages and provides message delivery guarantees.
Abstract: Current link-layer protocols for safety-related intervehicle communication (IVC) networks suffer from significant scalability and security challenges. Carrier sense multiple-access approaches produce excessive transmission collisions at high vehicle densities and are vulnerable to a variety of denial of service (DoS) attacks. Explicit time slot allocation approaches tend to be limited by the need for a fixed infrastructure, a high number of control messages, or poor bandwidth utilization, particularly in low-density traffic. This paper presents a novel adaptation of the explicit time slot allocation protocols for IVC networks. The protocol adaptive space-division multiplexing (ASDM) requires no control messages, provides protection against a range of DoS attacks, significantly improves bandwidth utilization, and automatically adjusts the time slot allocation in response to changes in vehicle densities. This paper demonstrates the need for and the effectiveness of this new protocol. The exposures of the current proposals to attacks on availability and integrity, as well as the improvements effected by ASDM, are analytically evaluated. Furthermore, through simulation studies, ASDM's ability to provide message delivery guarantees is contrasted with the inability of the current IVC proposals to do the same
TL;DR: An integrated approach combining offline precomputation of optimal candidate paths with online path retrieval and dynamic adaptation is proposed for a dynamic navigation system in a centralized system architecture based on a static traffic data file.
Abstract: In this paper, an integrated approach combining offline precomputation of optimal candidate paths with online path retrieval and dynamic adaptation is proposed for a dynamic navigation system in a centralized system architecture. Based on a static traffic data file, a partially disjoint candidate path set is constructed prior to the trip using a heuristic link weight increment method. This method satisfies reasonable path constraints that meet the drivers' preferences, as well as alternative path constraints, that limit the joint failure probability for candidate paths. The characteristics of the proposed algorithm are the following: 1) The response time for online navigation demand is nearly linear with network size and less dependent on system load; 2) the veracity of the pretrip route plan based on the static data file is improved by taking travel time reliability into account; and 3) system optimization can be approximated without sacrificing driver preferences. The algorithm is tested on randomly generated road networks, and the numerical results show the efficiency of the approach
TL;DR: A planning and decision component to generalize vehicle following to situations with nonautomated interfering vehicles in mixed traffic by treating the path of the leader vehicle as an elastic band that is subjected to repelling forces of obstacles in the surroundings.
Abstract: The vehicle-following concept has been widely used in several intelligent-vehicle applications. Adaptive cruise control systems, platooning systems, and systems for stop-and-go traffic employ this concept: The ego vehicle follows a leader vehicle at a certain distance. The vehicle-following concept comes to its limitations when obstacles interfere with the path between the ego vehicle and the leader vehicle. We call such situations dynamic driving situations. This paper introduces a planning and decision component to generalize vehicle following to situations with nonautomated interfering vehicles in mixed traffic. As a demonstrator, we employ a car that is able to navigate autonomously through regular traffic that is longitudinally and laterally guided by actuators controlled by a computer. This paper focuses on and limits itself to lateral control for collision avoidance. Previously, this autonomous-driving capability was purely based on the vehicle-following concept using vision. The path of the leader vehicle was tracked. To extend this capability to dynamic driving situations, a dynamic path-planning component is introduced. Several driving situations are identified that necessitate responses to more than the leader vehicle. We borrow an idea from robotics to solve the problem. Treat the path of the leader vehicle as an elastic band that is subjected to repelling forces of obstacles in the surroundings. This elastic-band framework offers the necessary features to cover dynamic driving situations. Simulation results show the power of this approach. Real-world results obtained with our demonstrator validate the simulation results
TL;DR: A complex vision system, able to provide the two basic sensorial capabilities needed by autonomous vehicle navigation in extreme environments: obstacle detection and path detection, is presented.
Abstract: Autonomous driving in off-road environments requires an exceptionally capable sensor system, particularly given that the unstructured environment does not provide many of the cues available in on-road environments. This paper presents a complex vision system, which is able to provide the two basic sensorial capabilities needed by autonomous vehicle navigation in extreme environments: obstacle detection and path detection. A variable-width-baseline (up to 1.5 m) single-frame stereo system is used for pitch estimation and obstacle detection, whereas a decision-network approach is used to detect the drivable path by a monocular vision system. The system has been field tested on the TerraMax vehicle, which is one of the only five vehicles to complete the 2005 Defense Advanced Research Projects Agency (DARPA) Grand Challenge course.
TL;DR: In this paper, the authors examined the stages a passenger goes through when deciding to undertake a public transport trip and in what form they require information at each stage, defined these stages as "pre-trip to destination," "at-stop," "onboard," and "pretrip to origin" (this is the return journey).
Abstract: This paper focuses on the provision of public transport information in Dublin, Ireland. It examines both existing and potential methods of accessing information, with particular focus on the implementation of various intelligent transport systems applications. One of the main objectives of this paper is examining the stages a passenger goes through when deciding to undertake a public transport trip and in what form they require information at each stage. This paper defines these stages as "pre-trip to destination," "at-stop," "onboard," and "pre-trip to origin" (this is the return journey). Each of these four stages is examined in this paper. A web-based survey was used to collect data on passenger preferences and describes the methods of information delivery each passenger requires at each stage. This paper primarily deals with the respondents' stated preference for public transport information and does not examine revealed preferences. The survey also details results of passengers' opinions of the different information provision formats such as call centers, mobile phones, the Internet, and paper-based methods. This paper concludes with the results of this exploratory research