Alireza Khodayari

Bio: Alireza Khodayari is an academic researcher from Islamic Azad University. The author has contributed to research in topics: SMA* & Control theory. The author has an hindex of 12, co-authored 58 publications receiving 627 citations. Previous affiliations of Alireza Khodayari include K.N.Toosi University of Technology & University of Tehran.

A Modified Car-Following Model Based on a Neural Network Model of the Human Driver Effects

Abstract: Nowadays, among the microscopic traffic flow modeling approaches, the car-following models are increasingly used by transportation experts to utilize appropriate intelligent transportation systems. Unlike previous works, where the reaction delay is considered to be fixed, in this paper, a modified neural network approach is proposed to simulate and predict the car-following behavior based on the instantaneous reaction delay of the driver-vehicle unit as the human effects. This reaction delay is calculated based on a proposed idea, and the model is developed based on this feature as an input. In this modeling, the inputs and outputs are chosen with respect to the reaction delay to train the neural network model. Using the field data, the performance of the model is calculated and compared with the responses of some existing neural network car-following models. Considering the difference between the responses of the actual plant and the predicted model as the error, comparison shows that the error in the proposed model is significantly smaller than that that in the other models.

A historical review on lateral and longitudinal control of autonomous vehicle motions

Abstract: In this research, brief survey of literature on current developments in the field of lateral and longitudinal control of autonomous vehicle motions. The paper categorizes the motions of vehicle to: car following, lane keeping, lane changing, subsequently, longitudinal control (brake and throttle), lateral control (steering) and integration of these controls for autonomous vehicles was investigated. Also different equipment and approaches to control of motions in each field was proposed.

ANFIS based modeling and prediction car following behavior in real traffic flow based on instantaneous reaction delay

Abstract: Nowadays, car following models, as the most popular microscopic traffic flow modeling, are increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. This paper presents a car-following model that was developed using an adaptive neuro fuzzy inference system (ANFIS) to simulate and predict the future behavior of a Driver-Vehicle-Unit (DVU). This model was developed based on new idea for calculate and estimate the instantaneous reaction of DVU. This idea was used in selection of inputs and outputs in train of ANFIS model. Integration of the driver's reaction time delay and omission of the necessity of regime classification are considered while developing the model. The model's performance was evaluated based on field data and compared to a number of existing car following models. The results showed that new model based on instantaneous reaction delay outperformed the other car-following models. The model was validated at the microscopic level, and the results showed very close agreement between field data and model outputs. The proposed model can be recruited in Drier Assistant devices, Safe Distance Keeping Observers, Collision Prevention systems and other ITS applications.

Design of an improved fuzzy logic based model for prediction of car following behavior

Abstract: Nowadays, car following models, as the most popular microscopic traffic flow modeling, are increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. This paper presents a car following model that was developed using a fuzzy inference system (FIS) to simulate and predict the future behavior of a Driver-Vehicle- Unit (DVU). This model was developed based on a new idea for estimating the instantaneous reaction of DVU, as an input of fuzzy model. The model's performance was evaluated based on field data. The results showed that fuzzy model based on instantaneous reaction delay outperformed the other car following models. The proposed model can be used in Driver Assistant Devices, Safe Distance Keeping Observers, Collision Prevention Systems and other ITS applications.

Software defined networking-based vehicular Adhoc Network with Fog Computing

Abstract: Vehicular Adhoc Networks (VANETs) have been attracted a lot of research recent years. Although VANETs are deployed in reality offering several services, the current architecture has been facing many difficulties in deployment and management because of poor connectivity, less scalability, less flexibility and less intelligence. We propose a new VANET architecture called FSDN which combines two emergent computing and network paradigm Software Defined Networking (SDN) and Fog Computing as a prospective solution. SDN-based architecture provides flexibility, scalability, programmability and global knowledge while Fog Computing offers delay-sensitive and location-awareness services which could be satisfy the demands of future VANETs scenarios. We figure out all the SDN-based VANET components as well as their functionality in the system. We also consider the system basic operations in which Fog Computing are leveraged to support surveillance services by taking into account resource manager and Fog orchestration models. The proposed architecture could resolve the main challenges in VANETs by augmenting Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), Vehicle-to-Base Station communications and SDN centralized control while optimizing resources utility and reducing latency by integrating Fog Computing. Two use-cases for non-safety service (data streaming) and safety service (Lane-change assistance) are also presented to illustrate the benefits of our proposed architecture.

Imitating driver behavior with generative adversarial networks

Abstract: The ability to accurately predict and simulate human driving behavior is critical for the development of intelligent transportation systems. Traditional modeling methods have employed simple parametric models and behavioral cloning. This paper adopts a method for overcoming the problem of cascading errors inherent in prior approaches, resulting in realistic behavior that is robust to trajectory perturbations. We extend Generative Adversarial Imitation Learning to the training of recurrent policies, and we demonstrate that our model rivals rule-based controllers and maximum likelihood models in realistic highway simulations. Our model both reproduces emergent behavior of human drivers, such as lane change rate, while maintaining realistic control over long time horizons.

Human-like autonomous car-following model with deep reinforcement learning

Abstract: This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates from the empirical data. Through these interactions, an optimal policy, or car-following model that maps in a human-like way from speed, relative speed between a lead and following vehicle, and inter-vehicle spacing to acceleration of a following vehicle is finally obtained. The model can be continuously updated when more data are fed in. Two thousand car-following periods extracted from the 2015 Shanghai Naturalistic Driving Study were used to train the model and compare its performance with that of traditional and recent data-driven car-following models. As shown by this study’s results, a deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1 s, denoted as DDPGvRT, can reproduce human-like car-following behavior with higher accuracy than traditional and recent data-driven car-following models. Specifically, the DDPGvRT model has a spacing validation error of 18% and speed validation error of 5%, which are less than those of other models, including the intelligent driver model, models based on locally weighted regression, and conventional neural network-based models. Moreover, the DDPGvRT demonstrates good capability of generalization to various driving situations and can adapt to different drivers by continuously learning. This study demonstrates that reinforcement learning methodology can offer insight into driver behavior and can contribute to the development of human-like autonomous driving algorithms and traffic-flow models.

Driver modeling based on driving behavior and its evaluation in driver identification : Analysis of car-pedal use and car-following habits may allow the help offered by intelligent driver assistance systems to be customized for individual drivers

Abstract: | All drivers have habits behind the wheel. Different drivers vary in how they hit the gas and brake pedals, how they turn the steering wheel, and how much following distance they keep to follow a vehicle safely and comfortably. In this paper, we model such driving behaviors as car-following and pedal operation patterns. The relationship between following distance and velocity mapped into a two-dimensional space is modeled for each driver with an optimal velocity model approximated by a nonlinear function or with a statistical method of a Gaussian mixture model (GMM). Pedal operation patterns are also modeled with GMMs that represent the distributions of raw pedal operation signals or spectral features extracted through spectral analysis of the raw pedal operation signals. The driver models are evaluated in driver identification experiments using driving signals collected in a driving simulator and in a real vehicle. Experimental results show that the driver model based on the spectral features of pedal operation signals efficiently models driver individual differences and achieves an identification rate of 76.8% for a field test with 276 drivers, resulting in a relative error reduction of 55% over driver models that use raw pedal operation signals without spectral analysis.

Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior

Abstract: The validity of any traffic simulation model depends on its ability to generate representative driver acceleration profiles. This paper studies the effectiveness of recurrent neural networks in predicting the acceleration distributions for car following on highways. The long short-term memory recurrent networks are trained and used to propagate the simulated vehicle trajectories over 10-s horizons. On the basis of several performance metrics, the recurrent networks are shown to generally match or outperform baseline methods in replicating driver behavior, including smoothness and oscillatory characteristics present in real trajectories. This paper reveals that the strong performance is due to the ability of the recurrent network to identify recent trends in the ego-vehicle's state, and recurrent networks are shown to perform as, well as feedforward networks with longer histories as inputs.