A. Ohadi, Y. Rasekhipour,
Volume 1, Issue 2 (6-2011)
Abstract
T. Feyzi, M. Esfahanian, R. Tikani, S. Ziaei Rad,
Volume 1, Issue 2 (6-2011)
Abstract
Mrs Mina Zohoorian Yazdi, Dr. Mohsen Soryani,
Volume 9, Issue 3 (9-2019)
Abstract
Today most accidents are caused by drivers’ fatigue, drowsiness and losing attention on the road ahead. In this paper, a system is introduced, using RGB-D cameras to automatically identify drowsiness and give warning. In this system two important modules have been utilized simultaneously to identify the state of driver’s mouth and eyes for detecting drowsiness. At first, using the depth information, the mouth area and its state are identified. Then using CNN networks, to predict whether the eyes are open or closed, a semi-VGG architecture is used .The results of yawning and eyes states detection are integrated to decide whether an alarm should be issued. The results show an accuracy of about 90% which is encouraging.
Alireza Khodayari, Arya Yahyaei,
Volume 10, Issue 2 (6-2020)
Abstract
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.
Dr. Alireza Bosaghzadeh, Majid Nasiri Manjili,
Volume 10, Issue 3 (9-2020)
Abstract
Lane detection is a crucial step for any autonomous driving system to decrease car accidents and increase safety. In this paper, based on inverse perspective mapping and Probabilistic Hough Transform, we propose a lane detection system which works on city street images. First, by using inverse perspective mapping the top view of the street is obtained. Second, the lanes are rectified using a specifically designed filter which enhances the lanes and suppresses other elements. Then, by using Probabilistic Hough transform the location of the lanes is detected in the images. For the final refinement, lane candidates are mapped to the road image using perspective mapping and the lane intensity is analyzed to reduce false acceptance. We evaluate the performance of the proposed method on Caltech-lane dataset and the obtained results show that the proposed method is able to detect straight lanes.
Behzad Samani, Dr Amir Hossein Shamekhi,
Volume 11, Issue 1 (3-2021)
Abstract
In this paper, an adaptive cruise control system is designed that is controlled by a neural network model. This neural network model is trained with data resulting from the simulation of a multi-objective nonlinear predictive adaptive cruise control system. For this purpose, first, an adaptive cruise control system was designed using the concept of model predictive control based on a nonlinear model to maintain the desired speed of the driver, maintain a safe distance with the car in front, reducing fuel consumption and increasing ride comfort. Due to the time-consuming computations in predictive control systems and the consequent need for powerful and expensive hardware, it was decided to use the extracted data from the simulation of this designed cruise control system to train a neural network model and use this model to achieve control objectives instead of the predictive controller. Using the neural network model in the cruise control system, despite a significant reduction in computation time, the control objectives were well achieved, and in fact a combination of model predictive controller accuracy and neural network controller speed was used.
Hashem Ghariblu,
Volume 12, Issue 2 (6-2022)
Abstract
This paper introduces a trajectory planning algorithm for long-term freeway driving for autonomous vehicles including different modes of motion. In the autonomous driving in a freeway, different maneuvers are needed, including free flow, distance adaption, speed adaption, lane change and overtaking. This paper introduces an algorithm that provides all of these driving scenarios in the trajectory planning for an autonomous vehicle. All maneuvers are classified and proper formulation for each driving mode formulated. Then, an algorithm is introduced to show the procedure of decision making and switching between all driving modes. The relative distances and velocities of the other peripheral and front vehicle from autonomous vehicle are considered as the main factors for decision making during the travelling in the freeway. By the developed simulation programming, validity and effectiveness of the algorithm are verified, and pseudo code and flowchart for the simulation programming are introduced. Later in two simulation studies, different driving conditions are generated and results have been discussed and analyzed by detail.
Mr. Mohammad Yar-Ahmadi, Mr. Hamid Rahmanei, Prof. Ali Ghaffari,
Volume 13, Issue 1 (3-2023)
Abstract
The primary purpose of each autonomous exit parking system is to facilitate the process of exiting the vehicle, emphasizing the comfort and safety of driving in the absence of almost any human effort. In this paper, the problem of exit parking for autonomous vehicles is addressed. A nonlinear kinematic model is presented based on the geometric relationship of the vehicle velocities, and a linear time-varying discrete-time model of the vehicle is obtained for utilizing the optimal control strategy. The proposed path planning algorithm is based on the minimization of a geometric cost function. This algorithm works for ample space exit parking in Single-Maneuver and tight spaces in Multi-Maneuver exit parking. Finally, an optimal discrete-time linear quadratic control approach is hired to minimize a quadratic cost function. To evaluate the performance of the proposed algorithm, the control system is simulated by MATLAB/Simulink software. The results show that the optimal control strategy is well able to design and follow the desired path in each of the exit parking maneuvers.
Mr. Hamid Rahmanei, Dr. Abbas Aliabadi, Prof. Ali Ghaffari, Prof. Shahram Azadi,
Volume 13, Issue 2 (6-2023)
Abstract
The coordinated control of autonomous electric vehicles with in-wheel motors is classified as over-actuated control problems requiring a precise control allocation strategy. This paper addresses the trajectory tracking problem of autonomous electric vehicles equipped with four independent in-wheel motors and active front steering. Unlike other available methods presenting optimization formulation to handle the redundancy, in this paper, the constraints have been applied directly using the kinematic relations of each wheel. Four separate sliding mode controllers are designed in such a way that they ensure the convergence of tracking errors, in addition to incorporating the parametric and modeling uncertainties. The lateral controller is also designed to determine the front steering angles to eliminate lateral tracking errors. To appraise the performance of the proposed control strategy, a co-simulation is carried out in MATLAB/Simulink and Carsim software. The results show that the proposed control strategy has enabled the vehicle to follow the reference path and has converged the errors of longitudinal and lateral positions, velocity, heading angle, and yaw rate. Furthermore, the proposed control system shows promising results in the presence of uncertainties including the mass and moment of inertia, friction coefficient, and the wind disturbances.
Dr Hossein Chehardoli,
Volume 13, Issue 3 (9-2023)
Abstract
In this article, the optimal robust H2 / H∞ control of self-driving car platoons (SDCPs) under external disturbance is investigated. By considering the engine dynamics and the effects of external disturbance, a linear dynamical model is presented to define the motion of each self-driving car (SDC). Each following SDC is in direct communication with the leader. By utilizing the relative position of following SDCs and the leader, the error dynamics of each SDC is calculated. The particle swarm optimization (PSO) method is utilized to find the optimal control gains. To this aim, a cost function which is a linear combination of H2 and H∞ norms of the transfer function between disturbance and target variables is constructed. By employing the PSO method, the cost function will be minimized and therefore, the robustness of the controller against external disturbance is guaranteed. It will be proved that under the presented robust control method, the negative effects of disturbance on system performance will significantly reduce. Therefore, the SDCP is internally stable and subsequently, each SDC tracks the motion of the leader. In order to validate the proposed method, simulation examples will be presented and analyzed.
Hossein Ghanbari, Mostafa Shabani, Dr Emran Mohammadi,
Volume 13, Issue 4 (12-2023)
Abstract
Portfolio optimization is the process of distributing a specific amount of wealth across various available assets, with the aim of achieving the highest possible returns while minimizing investment risks. There are a large number of studies on portfolio optimization in various cases, covering numerous applications; however, none have focused exclusively on the automotive industry as one of the largest manufacturing sectors in the global economy. Since the economic activity of this industry has a coherent pattern with that of the global economy, the automotive industry is very sensitive to the booms and busts of business cycles. Due to the volatile global economic environment and significant inter-industry implications, providing an appropriate approach to investing in this sector is essential. Thus, this paper aims to provide an appropriate approach to investing in this sector. In this study, an extended Conditional Drawdown at Risk (CDaR) model with cardinality and threshold constraints for portfolio optimization problems is proposed, which is highly beneficial in practical portfolio management. The feature of this risk management technique is that it admits the formulation of a portfolio optimization model as a linear programming problem. The CDaR risk functions family also enables a risk manager to control the worst ( 1-α)×100% 
drawdowns. In order to demonstrate the effectiveness of the proposed model, a real-world empirical case study from the annual financial statements of automotive companies and their suppliers in the Tehran Stock Exchange (TSE) database is utilized.
Mr Seyed Amir Mohammad Managheb, Mr Hamid Rahmanei, Dr Ali Ghaffari,
Volume 14, Issue 1 (3-2024)
Abstract
The turn-around task is one of the challenging maneuvers in automated driving which requires intricate decision making, planning and control, concomitantly. During automatic turn-around maneuver, the path curvature is too large which makes the constraints of the system severely restrain the path tracking performance. This paper highlights the path planning and control design for single and multi-point turn of autonomous vehicles. The preliminaries of the turn-around task including environment, vehicle modeling, and equipment are described. Then, a predictive approach is proposed for planning and control of the vehicle. In this approach, by taking the observation of the road and vehicle conditions into account and considering the actuator constraints in cost function, a decision is made regarding the minimum number of steering to execute turn-around. The constraints are imposed on the speed, steering angle, and their rates. Moreover, the collision avoidance with road boundaries is developed based on the GJK algorithm. According to the simulation results, the proposed system adopts the minimum number of appropriate steering commands while incorporating the constraints of the actuators and avoiding collisions. The findings demonstrate the good performance of the proposed approach in both path design and tracking for single- and multi-point turns.
