http://ieeexplore.ieee.org TOC Alert for Publication# 6979 2009 June 19 10 2 C1 C1 40 10 2 C2 C2 37 Although, in recent years, significant developments have been made in road safety, traffic statistics indicate that we still need significant improvements in the field. Since traffic accidents usually reflect human factors, in this paper, we focus on clarifying the understanding of driver behaviors under hazardous scenarios. Brake pedal signals or driver speech, or both, are utilized to detect incidents from a real-world driving database of 373 drivers. Results are then analyzed to address the individuality in driver behaviors, the multimodality of driver reactions, and the detection of potentially dangerous locations. All of the existing 25 potentially hazardous scenes in the database are hand labeled and categorized. Based on the joint histograms of behavioral signals and their time derivatives, a detection feature is proposed and satisfactorily applied to the indication of anomalies in driving behavior. Seventeen scenes, where a reaction utilizing the brake pedal was observed, are detected with a true positive (TP) rate of 100% and a false positive (FP) rate of 4.1%. We demonstrate the relevance of considering behavior individuality. During 11 scenes, the drivers verbally reacted. Scenes that included high-energy words are adequately detected by the speech-based method, which achieved a TP rate of 54% for an FP rate of 6.4%. The integration of different behavior modalities satisfactorily boosts the detection of the most subjectively hazardous situations, which suggests the importance of considering multimodal reactions. Finally, a strong relationship is presented between locations where potentially hazardous situations occurred and areas of frequent strong braking. ]]> 10 2 201 210 997 Recent news illustrates the frequent occurrence of pileup crashes on highways. A predominant reason for the occurrence of such crashes is that current vehicles (including those equipped with an automatic cruise control system) do not provide drivers with advance information of events occurring far ahead of them. The use of intervehicular communication to provide advance warnings to enhance automotive safety is therefore being actively discussed in the research community. In this paper, we investigate scenarios wherein only a subset of the vehicles in a multivehicle stream is equipped with such advance-warning capabilities. These vehicles (which are equipped with the capability to receive far-ahead information) are arbitrarily distributed among other unequipped vehicles that are capable of receiving only local near-neighbor information. It is seen that there are conditions wherein even a partial equipage of the system can be beneficial to both equipped and unequipped vehicles in a mixed-vehicle stream. We demonstrate this through both simulations and a theoretical analysis. We also developed a prototype of an advance-warning system and conducted road tests to test the concept. These road tests have demonstrated the system's performance to be satisfactory, subject to good communication links, for the class of scenarios tested. ]]> 10 2 211 225 1982 This paper presents a method of block-layout design between successive stations for mass rapid transit systems (MRTSs). The aim is to save energy under the framework of the fixed-block signaling (FBS) system and the equi-block principle. Unlike past research regarding the energy savings of train operation, this paper proposes a combinatorial optimization model to reduce the computation time. In the presented approach, the problem of minimizing the energy consumption between successive stations is first formulated as a combinatorial optimization problem. Then, the train-speed trajectory for saving energy is optimized by a MAX–MIN ant system (MMAS) of ant colony optimization (ACO) algorithms. Finally, the block layout is designed in accordance with the shortest block length under the equi-block principle. It is shown that the method presents a significant improvement for the reduction of computational burden on the block-layout design. The feasibility and benefits are verified via simulation study. Analyses and discussions are also given. ]]> 10 2 226 235 453 This paper presents a multimode dynamic traffic assignment (DTA) model for the impact analysis of the bus exclusive lane. First, a multimode point-queue model is proposed to reflect the interactions of cars and buses under two scenarios: networks with and without bus exclusive lanes. To capture the travel behaviors of mode choices, departure time choices, and path choices, an integrated variational inequality (VI) formulation is proposed. Then, a heuristic algorithm is developed to solve the VI problem. Finally, based on the proposed measures of effectiveness (MOEs) of travel cost, bus passengers, and queue length, the comparison analyses in virtual networks with and without bus exclusive lanes are presented by numerical examples. ]]> 10 2 236 245 296 Existing time-series models that are used for short-term traffic condition forecasting are mostly univariate in nature. Generally, the extension of existing univariate time-series models to a multivariate regime involves huge computational complexities. A different class of time-series models called structural time-series model (STM) (in its multivariate form) has been introduced in this paper to develop a parsimonious and computationally simple multivariate short-term traffic condition forecasting algorithm. The different components of a time-series data set such as trend, seasonal, cyclical, and calendar variations can separately be modeled in STM methodology. A case study at the Dublin, Ireland, city center with serious traffic congestion is performed to illustrate the forecasting strategy. The results indicate that the proposed forecasting algorithm is an effective approach in predicting real-time traffic flow at multiple junctions within an urban transport network. ]]> 10 2 246 254 980 This paper examines a recently addressed practical variant of the capacitated vehicle routing problem (VRP) called the Capacitated Vehicle Routing Problem with 3-D Loading Constraints (3L-CVRP). This problem considers customer demand to be formed by 3-D rectangular items. Additional loading constraints often encountered in real-life applications of transportation logistics are imposed on the examined problem model. In addition to 3L-CVRP, we also introduce and solve a new practical problem version that was dictated by a transportation logistics company and covers cases in which transported items are manually unloaded from the loading spaces of the vehicles. Both problem versions are solved by a hybrid metaheuristic methodology that combines the strategies of tabu search (TS) and guided local search (GLS). The loading characteristics are tackled by employing a collection of packing heuristics. The proposed algorithm's robustness was tested for both problem versions, solving benchmark instances derived from the literature and new benchmark problems with diverse features in terms of customer set size and transported-item dimensions. It produced fine results, improving most of the best solutions that were previously reported. ]]> 10 2 255 271 871 Accurate and robust lane results are of great significance in any driving-assistance system. To achieve robustness and accuracy in difficult scenarios, probabilistic estimation techniques are needed to compensate for the errors in the detection of lane-delimiting features. This paper presents a solution for lane estimation in difficult scenarios based on the particle-filtering framework. The solution employs a novel technique for pitch detection based on the fusion of two stereovision-based cues, a novel method for particle measurement and weighing using multiple lane-delimiting cues extracted by grayscale and stereo data processing, and a novel method for deciding upon the validity of the lane-estimation results. Initialization samples are used for uniform handling of the road discontinuities, eliminating the need for explicit track initialization. The resulting solution has proven to be a reliable and fast lane detector for difficult scenarios. ]]> 10 2 272 282 989 Pedestrian detection is one of the most important components in driver-assistance systems. In this paper, we propose a monocular vision system for real-time pedestrian detection and tracking during nighttime driving with a near-infrared (NIR) camera. Three modules (region-of-interest (ROI) generation, object classification, and tracking) are integrated in a cascade, and each utilizes complementary visual features to distinguish the objects from the cluttered background in the range of 20–80 m. Based on the common fact that the objects appear brighter than the nearby background in nighttime NIR images, efficient ROI generation is done based on the dual-threshold segmentation algorithm. As there is large intraclass variability in the pedestrian class, a tree-structured, two-stage detector is proposed to tackle the problem through training separate classifiers on disjoint subsets of different image sizes and arranging the classifiers based on Haar-like and histogram-of-oriented-gradients (HOG) features in a coarse-to-fine manner. To suppress the false alarms and fill the detection gaps, template-matching-based tracking is adopted, and multiframe validation is used to obtain the final results. Results from extensive tests on both urban and suburban videos indicate that the algorithm can produce a detection rate of more than 90% at the cost of about 10 false alarms/h and perform as fast as the frame rate (30 frames/s) on a Pentium IV 3.0-GHz personal computer, which also demonstrates that the proposed system is feasible for practical applications and enjoys the advantage of low implementation cost. ]]> 10 2 283 298 2104 The safety of the planned paths of autonomous cars with respect to the movement of other traffic participants is considered. Therefore, the stochastic occupancy of the road by other vehicles is predicted. The prediction considers uncertainties originating from the measurements and the possible behaviors of other traffic participants. In addition, the interaction of traffic participants, as well as the limitation of driving maneuvers due to the road geometry, is considered. The result of the presented approach is the probability of a crash for a specific trajectory of the autonomous car. The presented approach is efficient as most of the intensive computations are performed offline, which results in a lean online algorithm for real-time application. ]]> 10 2 299 310 803 This paper presents the design and evaluation of an online passenger information system for delivering personalized multimodal trip planning services through the integration of wireless and web-based communication technologies. The goal of the system is to provide real-time travel information throughout the entire life cycle of an interurban trip. Before the full-scale deployment of this type of system, it is essential to assess its impact on the involved stakeholders through a pilot application. The proposed system (ENOSIS) has been implemented and evaluated for supporting travel decisions in Greece. An evaluation framework for assessing the impacts of the ENOSIS system is proposed, and the evaluation results of the ENOSIS pilot application are also reported. The evaluation results provide significant evidence of the technical and operational efficiency of the ENOSIS services, while it is shown that the proposed system is cost effective. ]]> 10 2 311 323 1070 In this paper, we present a new approach for detecting trucks transporting illicit radioactive materials using radiation data. The approach is motivated by the high number of false alarms that typically results when using radiation portal monitors. Our approach is a three-stage anomaly detection process that consists of transforming the radiation sensor data into wavelet coefficients, representing the transformed data in binary form, and detecting anomalies among data sets using a proximity-based method. The approach is evaluated using simulated radiation data, and the results are encouraging. From a transportation security perspective, our results indicate that the concomitant use of gross count and spectroscopy radiation data improves identification of trucks transporting illicit radioactive materials. The results also suggest that the use of additional heterogeneous data with radiation data may enhance the reliability of the detection process. Further testing with real radiation data and mixture of cargo is needed to fully validate the results. ]]> 10 2 324 334 761 Automated vehicle control systems are a key technology for intelligent vehicle highway systems (IVHSs). This paper presents an automated vehicle control algorithm for combined longitudinal and lateral motion control of highway vehicles, with special emphasis on front-wheel-steered four-wheel road vehicles. The controller is synthesized using an online neural-estimator-based control law that works in combination with a lateral velocity observer. The online adaptive neural-estimator-based design approach enables the controller to counteract for inherent model discrepancies, strong nonlinearities, and coupling effects. The neurocontrol approach can guarantee the uniform ultimate bounds (UUBs) of the tracking and observer errors and the bounds of the neural weights. The key design features are 1) inherent coupling effects will be taken into account as a result of combining of the two control issues, viz., lateral and longitudinal control; 2) rather ad hoc numerical approximations of lateral velocity will be avoided via a combined controller–observer design; and 3) closed-loop stability issues of the overall system will be established. The algorithm is validated via a formative mathematical analysis based on a Lyapunov approach and numerical simulations in the presence of parametric uncertainties, as well as severe and adverse driving conditions. ]]> 10 2 335 345 310 In this paper, a decentralized sliding-mode control approach is applied to the control tasks of vehicles in platoons. Using the well-known bicycle model, a robust nonlinear observer is introduced to facilitate the controller design, which needs full-state measurements. The vehicles in platoons can be treated as an interconnected system with a special form. Observer gain and controller gain are properly designed. In addition, appropriate linear matrix inequality (LMI) stability conditions by the Lyapunov method are derived to ensure the stability of the system. The main advantages can be summarized as follows: 1) The linear approximation of the nonlinear vehicle model enables various advanced robust control possibilities. 2) The proposed robust control approach with the nonlinear observer ensures the convergence of the whole interconnected system, given that the system is operated within the stable region of linearization. 3) Stability conditions in the form of LMIs for both observer and controller are rigorously derived. Finally, simulation results for three identical vehicles based on the relative bicycle model are demonstrated to show the performance of the approach. ]]> 10 2 346 354 271 Classically, fundamental diagrams are estimated from aggregated data at a specific location. Such a measurement method may lead to inconsistency, which mainly explains the current controversy about their shape. This paper proposes a new estimation method based on passing rate measurements along moving observer paths. Under specific assumptions, it can be proved that in congestion, the passing rate is independent of the traffic flow states. This property allows 1) proof that a linear fundamental diagram is suitable to represent traffic flow behavior involved in the Next Generation Simulation (NGSim) data set and 2) fitting of its two parameters, i.e., the congested wave speed and the jam density. ]]> 10 2 355 359 335 The purpose of this paper is to develop rear-end collision warning thresholds with appropriate values of parameters for busses driving on freeways. Based on a bus-driving simulator, we design a simulation scenario of car following with emergency braking on freeways. Bus drivers working with a bus company are recruited to manipulate the simulation. The perception–reaction time, braking deceleration rate, and buffer of bus drivers' responses to a lead vehicle suddenly braking are collected and analyzed as parameters. Results indicate that not all the subjects have the same value in each parameter. Hence, the values of parameters in the bus rear-end collision warning threshold equations should be differentiated from various bus-driving characteristics. This paper further uses a fuzzy set theory to develop the safety membership function of each parameter and deduces 27 warning threshold equations. By these threshold equations, a rear-end collision warning algorithm for busses driving on freeways is also recommended. ]]> 10 2 360 365 352 Overtaking is a complex and hazardous driving maneuver for intelligent vehicles. When to initiate overtaking and how to complete overtaking are critical issues for an overtaking intelligent vehicle. We propose an overtaking control method based on the estimation of the conflict probability. This method uses the conflict probability as the safety indicator and completes overtaking by tracking a safe conflict probability. The conflict probability is estimated by the future relative position of intelligent vehicles, and the future relative position is estimated by using the dynamics models of the intelligent vehicles. The proposed method uses model predictive control to track a desired safe conflict probability and synthesizes decision making and control of the overtaking maneuver. The effectiveness of this method has been validated in different experimental configurations, and the effects of some parameters in this control method have also been investigated. ]]> 10 2 366 370 232 10 2 371 371 139 10 2 372 372 453 10 2 C3 C3 28 10 2 C4 C4 37