Automotive Science and Engineering

---

Car-following models, as the most popular microscopic traffic flow modeling, is increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. A number of factors including individual differences of age, gender, and risk-taking behavior, have been found to influence car-following behavior. This paper presents a novel idea to calculate the Driver-Vehicle Unit (DVU) instantaneous reaction delay of DVU as the human effects. Unlike previous works, where the reaction delay is considered to be fixed, considering the proposed idea, three input-output models are developed to estimate FV acceleration based on soft computing approaches. The models are developed based on the reaction delay as an input. In these modeling, the inputs and outputs are chosen with respect to this feature to design the soft computing models. The performance of models is evaluated based on field data and compared to a number of existing car-following models. The results show that new soft computing models based on instantaneous reaction delay outperformed the other car-following models. The proposed models can be recruited in driver assistant devices, safe distance keeping observers, collision prevention systems and other ITS applications.

---

The lane change maneuver is among the most popular driving behaviors. It is also the basic element of important maneuvers like overtaking maneuver. Therefore, it is chosen as the focus of this study and novel multi-input multi-output adaptive neuro-fuzzy inference system models (MANFIS) are proposed for this behavior. These models are able to simulate and predict the future behavior of a Driver-Vehicle-Unit in the lane change maneuver for various time delays. To design these models, the lane change maneuvers are extracted from the real traffic datasets. But, before extracting these maneuvers, several conditions are defined which assure the extraction of only those lane change maneuvers that have a smooth and uniform trajectory. Using the field data, the outputs of the MANFIS models are validated and compared with the real traffic data. In addition, the result of these models is compared with the result of other trajectory models. This comparison provides a better chance to analyze the performance of these models. The simulation results show that these models have a very close compatibility with the field data and reflect the situation of the traffic flow in a more realistic way.

---

Overtaking a slow lead vehicle is a complex maneuver because of the variety of overtaking conditions and driver behavior. In this study, two novel prediction models for overtaking behavior are proposed. These models are derived based on multi-input multi-output adaptive neuro-fuzzy inference system (MANFIS). They are validated at microscopic level and are able to simulate and predict the future behavior of the overtaking vehicle in real traffic flow. In these models, the kinematic features of Driver-Vehicle-Units (DVUs) such as distance, velocity, and acceleration are used. Unlike the previous models, where some variables of the two involved vehicles are considered to be constant, in this paper, instantaneous values of the variables are considered. The first model predicts the future value of the longitudinal acceleration and the movement angle of the overtaking vehicle. The other model predicts the overtaking trajectory for the overtaking vehicle. The second model is designed for two different vehicle classes: motorcycles and autos. Also, the result of the trajectory prediction model is compared with the result of other models. This comparison provides a better chance to analyze the performance of this model. Using the field data, the outputs of the MANFIS models are validated and compared with the real traffic dataset. The simulation results show that these two MANFIS models have a very close compatibility with the field data and reflect the situation of the traffic flow in a more realistic way. These models can be used for all types of drivers and vehicles and also in other roads and are not limited to certain types of situations. The proposed models can be employed in ITS applications and the like.

---

In this paper a control system has been designed to improve traffic conditions in car following maneuver. There are different methods to design a control system. In this paper design approach is based on the Fuzzy sliding mode control (FSMC) system. The aim of designing FSMC system is to achieve safe and desire longitudinal distance and less lateral displacement. In order to control and obtain desired longitudinal and lateral movements, suitable values of composite torque and steering angle is generated. At first to design of FSMC system, a nonlinear dynamics model of vehicle with three degrees of freedom is presented and validated with real traffic data. Then, the performance of the FSMC system has been evaluated by real car following data. At the end, the simulation results of FSMC are compared with the first and second order sliding mode control. Simulation result shows that performance of FSMC is better than sliding mode control. Also by comparing between FSMC and real driver, it is shown that FSMC is much safer than a real human driver in keeping the longitudinal distance and also the FSMC produces less lateral displacement in the lateral movement too.

---

Due to the increasing demand for traveling in public transportation systems and increasing traffic of vehicles, nowadays vehicles are getting to be intelligent to increase safety, reduce the probability of accident and also financial costs. Therefore, today, most vehicles are equipped with multiple safety control and vehicle navigation systems. In the process of developing such systems, simulation has become a cost-effective chance for the fast evolution of computational modeling techniques. The most popular microscopic traffic flow model is car following models which are increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. The control of car following is essential to its safety and its operational efficiency. This paper presents a car-following control system that was developed using a fuzzy model predictive control (FMPC). This system was used to simulate and predict the future behavior of a Driver-Vehicle-Unit (DVU) and was developed based on a new idea to calculate and estimate the instantaneous reaction of a DVU. At the end, for experimental evaluation, the FMPC system was used along with a human driver in a driving simulator. The results showed that the FMPC has better performance in keeping the safe distance in comparison with real data of human drivers behaviors. The proposed model can be recruited in driver assistant devices, safe distance keeping observers, collision prevention systems and other ITS applications.

---

In recent years due to improvements of technology within automobile industry, design process of advanced driver assistance systems for collision avoidance and traffic management has been investigated in both academics and industrial levels. Detection of traffic signs is an effective method to reach the mentioned aims. In this paper a new intelligent driver assistance system based on traffic sign detection with Persian context is designed. The main goal of this system is to assist drivers to choose their path based on traffic signs more precisely. To reach this purpose, a new framework by using of fuzzy logic was used for detection of traffic signs in videos which have has been captured from a vehicle path in highways. Fuzzy logic increases inference and intelligent capabilities in smart systems to make correct decision making in online conditions. Then, the combination of Maximally Stable Extermal Regions (MSER) and Canny Edge Detector Algorithms are used to detect road sign’s texts detection. MSER algorithm is aimed at assists to detect regions in an image that differ in properties, for example in brightness or color, compared to surrounding regions. Also, canny edge detector uses a multi-stage algorithm to detect a wide range of edges in the images. Thereafter, morphological mask operator is used to join individual characters for final detection of texts in the traffic signs. Finally, MATLAB Optical Character Recognition (OCR) is employed to recognize the detected texts. This new framework gives an overall text detection and recognition rate of . .

---

The designing of advanced driver assistance systems and autonomous vehicles needs measurement of dynamical variations of vehicle, such as acceleration, velocity and yaw rate. Designed adaptive controllers to control lateral and longitudinal vehicle dynamics are based on the measured variables. Inertial MEMS-based sensors have some benefits including low price and low consumption that make them suitable choices to use in vehicle navigation problems. However, these sensors have some deterministic and stochastic error sources. These errors could diverge sensor outputs from the real values. Therefore, calibration of the inertial sensors is one of the most important processes that should be done in order to have the exact model of dynamical behaviors of the vehicle. In this paper, a new method, based on artificial neural network, is presented for the calibration of an inertial accelerometer applied in the vehicle navigation. Levenberg-Marquardt algorithm is used to train the designed neural network. This method has been tested in real driving scenarios and results show that the presented method reduces the root mean square error of the measured acceleration up to 96%. The presented method can be used in managing the traffic flow and designing collision avoidance systems.

---

Advanced Driver Assistance Systems (ADAS) benefit from current infrastructure to discern environmental information. Traffic signs are global guidelines which inform drivers from near characteristics of paths ahead. Traffic Sign Recognition (TSR) system is an ADAS that recognize traffic signs in images captured from road and show information as an adviser or transmit them to other ADASs. In this paper presents a novel machine vision algorithm for traffic sign recognition based on fuzzy sets. This algorithm is a pipeline consists of multiple fuzzy set that create a fuzzy space here called Super Fuzzy Set (SFS). SFS helped to design a flexible and fast algorithm for recognizing traffic signs in a real-time application. Designed algorithm was implemented in computer-based system and checked on a test car in real urban environment. 83.34% accuracy rate was obtained in real-time test.

---

The Global Positioning System (GPS) and an Inertial Navigation System (INS) are two basic navigation systems. Due to their complementary characters in many aspects, a GPS/INS integrated navigation system has been a hot research topic in the recent decade. The Micro Electrical Mechanical Sensors (MEMS) successfully solved the problems of price, size and weight with the traditional INS. Therefore they are commonly applied in GPS/INS integrated systems. The biggest problem of MEMS is the large sensor errors, which rapidly degrade the navigation performance in an exponential speed. Three levels of GPS/IMU integration structures, i.e. loose, tight and ultra tight GPS/IMU navigation, are proposed by researchers. The loose integration principles are given with detailed equations as well as the basic INS navigation principles. The Extended Kalman Filter (EKF) is introduced as the basic data fusion algorithm, which is also the core of the whole navigation system to be presented. The kinematic constraints of land vehicle navigation, i.e. velocity constraint and height constraint, are presented. A detailed implementation process of the GPS/IMU integration system is given. Based on the system model, we show the propagation of position standard errors with the tight integration structure under different scenarios. A real test with loose integration structure is carried out, and the EKF performances as well as the physical constraints are analyzed in detail.

---

In this paper, an intelligent system based on a novel algorithm for pulling out is designed and implemented. Through processing images of the surroundings of a vehicle, this very algorithm detects the obstacles and objects which are likely to pose danger to the vehicle while pulling out.  Two different methods are integrated into this system to detect obstacles and objects.  The first method, which is called Support Vector Machine (SVM), detects a broad range of moving objects around the vehicle drawing on training datasets.  Whereas, in the second method, types of obstacles and objects are detected using the area of the moving object within range. The system in question is implemented using both methods whose performance are compared in terms of computation and image processing speed; SVM and object area methods detected 93% and 96% of vehicles respectively. The utilization of this algorithm can contribute to the safety of vehicles while executing pullout maneuver and decreased the probability of crashing into fixed and moving obstacles in the surroundings.  Results of this research will be available to be used in the design and development of parking control systems.