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.

---

Vehicular ad-hoc network (VANET) is an important component of intelligent transportation systems, in which vehicles are equipped with on-board computing and communication devices which enable vehicle-to-vehicle communication. Consequently, with regard to larger communication due to the greater number of vehicles, stability of connectivity would be a challenging problem. Clustering technique as one of the most important data mining techniques is a possible method that can improve the stability of connectivity in VANET. Stable communication within a VANET leads to enhanced driver safety and better traffic management. Therefore, this paper presented a novel clustering algorithm based on ant system-based algorithm called IASC in order to provide a fast clustering algorithm with high accuracy and improve the stability of VANET topology. A comparative study was proposed to analogize the results of the proposed algorithm with six VANET clustering algorithms in the literature which were taken as benchmarks. Results revealed improvement in stability and overhead on VANET.

---

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.

---

Accurate and correct performance of controller in cruise control systems is important. Hence, in such systems, controller should optimize itself against noise and probable changes in system dynamic. As a matter of fact, in this article three approaches have been conducted to-ward this purpose: MIT, direct estimation and indirect estimation. These approaches are used as controllers to track reference signal. First the performance of each of these three controllers is checked. comparison of performances indicated better behavior for indirect estimation than others. Also, it has less sensitivity against external noise. Finally, by using indirect estimation method as an adaptive control approach, two parallel separate controllers are designed for two inputs, gas and braking, and their performances are compared with recent studies. It shows improvement in performance of adaptive cruise control system to track reference signal.