arXiv subjects

Azim Eskandarian

Publications and source records attributed to Azim Eskandarian.

34 records · Page 2Linked to original sources

arXiv2023

EEG-Fest: Few-shot based Attention Network for Driver's Vigilance Estimation with EEG Signals

A lack of driver's vigilance is the main cause of most vehicle crashes. Electroencephalography(EEG) has been reliable and efficient tool for drivers' drowsiness estimation. Even though previous studies have developed accurate and robust driver's vigilance detection algorithms, these methods are still facing challenges on following areas: (a) small sample size training, (b) anomaly signal detection, and (c) subject-independent classification. In this paper, we propose a generalized few-shot model, namely EEG-Fest, to improve aforementioned drawbacks. The EEG-Fest model can (a) classify the query sample's drowsiness with a few samples, (b) identify whether a query sample is anomaly signals or not, and (c) achieve subject independent classification. The proposed algorithm achieves state-of-the-art results on the SEED-VIG dataset and the SADT dataset. The accuracy of the drowsy class achieves 92% and 94% for 1-shot and 5-shot support samples in the SEED-VIG dataset, and 62% and 78% for 1-shot and 5-shot support samples in the SADT dataset.

cs.LG↗

arXiv2023

Emergency Collision Avoidance and Mitigation Using Model Predictive Control and Artificial Potential Function

Although extensive research in emergency collision avoidance has been carried out for straight or curved roads in a highway scenario, a general method that could be implemented for all road environments has not been thoroughly explored. Moreover, most current algorithms don't consider collision mitigation in an emergency. This functionality is essential since the problem may have no feasible solution. We propose a safe controller using model predictive control and artificial potential function to address these problems. A new artificial potential function inspired by line charge is proposed as the cost function for our model predictive controller. The vehicle dynamics and actuator limitations are set as constraints. The new artificial potential function considers the shape of all objects. In particular, the artificial potential function we proposed has the flexibility to fit the shape of the road structures, such as the intersection. We could also realize collision mitigation for a specific part of the vehicle by increasing the charge quantity at the corresponding place. We have tested our methods in 192 cases from 8 different scenarios in simulation with two different models. The simulation results show that the success rate of the proposed safe controller is 20% higher than using HJ-reachability with system decomposition by using a unicycle model. It could also decrease 43% of collision that happens at the pre-assigned part. The method is further validated in a dynamic bicycle model.

cs.RO↗

arXiv2022

X-CAR: An Experimental Vehicle Platform for Connected Autonomy Research Powered by CARMA

Autonomous vehicles promise a future with a safer, cleaner, more efficient, and more reliable transportation system. However, the current approach to autonomy has focused on building small, disparate intelligences that are closed off to the rest of the world. Vehicle connectivity has been proposed as a solution, relying on a vision of the future where a mix of connected autonomous and human-driven vehicles populate the road. Developed by the U.S. Department of Transportation Federal Highway Administration as a reusable, extensible platform for controlling connected autonomous vehicles, the CARMA Platform is one of the technologies enabling this connected future. Nevertheless, the adoption of the CARMA Platform has been slow, with a contributing factor being the limited, expensive, and relatively old vehicle configurations that are officially supported. To alleviate this problem, we propose X-CAR (eXperimental vehicle platform for Connected Autonomy Research). By implementing the CARMA Platform on more affordable, high quality hardware, X-CAR aims to increase the versatility of the CARMA Platform and facilitate its adoption for research and development of connected driving automation.

cs.RO↗

arXiv2022

Uncertainty estimation of pedestrian future trajectory using Bayesian approximation

Past research on pedestrian trajectory forecasting mainly focused on deterministic predictions which provide only point estimates of future states. These future estimates can help an autonomous vehicle plan its trajectory and avoid collision. However, under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy. Rather, estimating the uncertainty associated with the predicted states with a certain level of confidence can lead to robust path planning. Hence, the authors propose to quantify this uncertainty during forecasting using stochastic approximation which deterministic approaches fail to capture. The current method is simple and applies Bayesian approximation during inference to standard neural network architectures for estimating uncertainty. The authors compared the predictions between the probabilistic neural network (NN) models with the standard deterministic models. The results indicate that the mean predicted path of probabilistic models was closer to the ground truth when compared with the deterministic prediction. Further, the effect of stochastic dropout of weights and long-term prediction on future state uncertainty has been studied. It was found that the probabilistic models produced better performance metrics like average displacement error (ADE) and final displacement error (FDE). Finally, the study has been extended to multiple datasets providing a comprehensive comparison for each model.

cs.LG↗

arXiv2021

Sentinel: An Onboard Lane Change Advisory System for Intelligent Vehicles to Reduce Traffic Delay during Freeway Incidents

This paper introduces Sentinel, an onboard system for intelligent vehicles that guides their lane changing behavior during a freeway incident with the goal of reducing traffic congestion, capacity drop, and delay. When an incident blocking the lanes ahead is detected, Sentinel calculates the probability of leaving the blocked lane(s) before reaching the incident point at each time step. It advises the vehicle to leave the blocked lane(s) when that probability drops below a certain threshold, as the vehicle nears the congestion boundary. By doing this, Sentinel reduces the number of late-stage lane changes of vehicles in the blocked lane(s) trying to move to other lanes, and distributes those maneuvers upstream of the incident point. A simulation case study is conducted in which one lane of a four-lane section of the I-66 interstate highway in the U.S. is temporarily blocked due to an incident, to understand how Sentinel impacts traffic flow and how different parameters - traffic flow, system penetration rate, and incident duration - affect Sentinel's performance. The results show that Sentinel has a positive impact on traffic flow, reducing average delay by up to 37%, particularly when it has a considerable penetration rate. Working alongside Traffic Incident Management Systems (TIMS), Sentinel can be a valuable asset for reducing traffic delay and potentially saving billions of dollars annually in costs associated with congestion caused by freeway incidents.

cs.RO↗

arXiv2021

Attention-based Neural Network for Driving Environment Complexity Perception

Environment perception is crucial for autonomous vehicle (AV) safety. Most existing AV perception algorithms have not studied the surrounding environment complexity and failed to include the environment complexity parameter. This paper proposes a novel attention-based neural network model to predict the complexity level of the surrounding driving environment. The proposed model takes naturalistic driving videos and corresponding vehicle dynamics parameters as input. It consists of a Yolo-v3 object detection algorithm, a heat map generation algorithm, CNN-based feature extractors, and attention-based feature extractors for both video and time-series vehicle dynamics data inputs to extract features. The output from the proposed algorithm is a surrounding environment complexity parameter. The Berkeley DeepDrive dataset (BDD Dataset) and subjectively labeled surrounding environment complexity levels are used for model training and validation to evaluate the algorithm. The proposed attention-based network achieves 91.22% average classification accuracy to classify the surrounding environment complexity. It proves that the environment complexity level can be accurately predicted and applied for future AVs' environment perception studies.

cs.LG↗

arXiv2021

EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification

Classification of EEG-based motor imagery (MI) is a crucial non-invasive application in brain-computer interface (BCI) research. This paper proposes a novel convolutional neural network (CNN) architecture for accurate and robust EEG-based MI classification that outperforms the state-of-the-art methods. The proposed CNN model, namely EEG-Inception, is built on the backbone of the Inception-Time network, which showed to be highly efficient and accurate for time-series classification. Also, the proposed network is an end-to-end classification, as it takes the raw EEG signals as the input and does not require complex EEG signal-preprocessing. Furthermore, this paper proposes a novel data augmentation method for EEG signals to enhance the accuracy, at least by 3%, and reduce overfitting with limited BCI datasets. The proposed model outperforms all the state-of-the-art methods by achieving the average accuracy of 88.4% and 88.6% on the 2008 BCI Competition IV 2a (four-classes) and 2b datasets (binary-classes), respectively. Furthermore, it takes less than 0.025 seconds to test a sample suitable for real-time processing. Moreover, the classification standard deviation for nine different subjects achieves the lowest value of 5.5 for the 2b dataset and 7.1 for the 2a dataset, which validates that the proposed method is highly robust. From the experiment results, it can be inferred that the EEG-Inception network exhibits a strong potential as a subject-independent classifier for EEG-based MI tasks.

eess.SP↗

arXiv2021

Estimating the Probability that a Vehicle Reaches a Near-Term Goal State Using Multiple Lane Changes

This paper proposes a model to estimate the probability of a vehicle reaching a near-term goal state using one or multiple lane changes based on parameters corresponding to traffic conditions and driving behavior. The proposed model not only has broad application in path planning and autonomous vehicle navigation, it can also be incorporated in advance warning systems to reduce traffic delay during recurrent and non-recurrent congestion. The model is first formulated for a two-lane road segment through systemic reduction of the number of parameters and transforming the problem into an abstract statistical form, for which the probability can be calculated numerically. It is then extended to cases with a higher number of lanes using the law of total probability. VISSIM simulations are used to validate the predictions of the model and study the effect of different parameters on the probability. For most cases, simulation results are within 4% of model predictions, and the effect of different parameters such as driving behavior and traffic density on the probability match our expectation. The model can be implemented with near real-time performance, with computation time increasing linearly with the number of lanes.

cs.RO↗

arXiv2021

A Probabilistic Approach to Driver Assistance for Delay Reduction at Congested Highway Lane Drops

This paper proposes an onboard advance warning system based on a probabilistic prediction model that advises vehicles on when to change lanes for an upcoming lane drop. Using several traffic- and driver-related parameters such as the distribution of inter-vehicle headway distances, the prediction model calculates the likelihood of utilizing one or multiple lane changes to successfully reach a target position on the road. When approaching a lane drop, the onboard system projects current vehicle conditions into the future and uses the model to continuously estimate the success probability of changing lanes before reaching the lane-end, and advises the driver or autonomous vehicle to start a lane changing maneuver when that probability drops below a certain threshold. In a simulation case study, the proposed system was used on a segment of the I-81 interstate highway with two lane drops - transitioning from four lanes to two lanes - to advise vehicles on avoiding the lane drops. The results indicate that the proposed system can reduce average delay by up to 50% and maximum delay by up to 33%, depending on traffic flow and the ratio of vehicles equipped with the advance warning system.

eess.SY↗

arXiv2020

Traffic Delay Reduction at Highway Diverges Using an Advance Warning System Based on a Probabilistic Prediction Model

This paper presents an on-board advance warning system for vehicles based on a probabilistic prediction model that advises them on when to change lanes to reach a highway diverge on time. The system is based on a model that estimates the probability of reaching a goal state on the road using one or multiple lane changes. This estimate is based on several traffic-related parameters such as the distribution of inter-vehicle headway distances as well as driver-related parameters like lane change duration. For an upcoming diverge, the advance warning system uses the model to continuously calculate the probability of reaching it and advise the driver to change lanes when the probability dips below a certain threshold. To evaluate the performance of the proposed system in reducing traffic delay at highway diverges, it was used on a segment of a four-lane highway to advise vehicles taking an off-ramp on when to change lanes. Results show that using the proposed system reduces average delay up to 6% and maximum delay up to 16%, depending on traffic flow and the ratio of vehicles taking the off-ramp.

eess.SY↗

arXiv2020

A Survey and Tutorial of EEG-Based Brain Monitoring for Driver State Analysis

Drivers cognitive and physiological states affect their ability to control their vehicles. Thus, these driver states are important to the safety of automobiles. The design of advanced driver assistance systems (ADAS) or autonomous vehicles will depend on their ability to interact effectively with the driver. A deeper understanding of the driver state is, therefore, paramount. EEG is proven to be one of the most effective methods for driver state monitoring and human error detection. This paper discusses EEG-based driver state detection systems and their corresponding analysis algorithms over the last three decades. First, the commonly used EEG system setup for driver state studies is introduced. Then, the EEG signal preprocessing, feature extraction, and classification algorithms for driver state detection are reviewed. Finally, EEG-based driver state monitoring research is reviewed in-depth, and its future development is discussed. It is concluded that the current EEG-based driver state monitoring algorithms are promising for safety applications. However, many improvements are still required in EEG artifact reduction, real-time processing, and between-subject classification accuracy.

eess.SP↗

arXiv2020

A Computationally Efficient Multiclass Time-Frequency Common Spatial Pattern Analysis on EEG Motor Imagery

Common spatial pattern (CSP) is a popular feature extraction method for electroencephalogram (EEG) motor imagery (MI). This study modifies the conventional CSP algorithm to improve the multi-class MI classification accuracy and ensure the computation process is efficient. The EEG MI data is gathered from the Brain-Computer Interface (BCI) Competition IV. At first, a bandpass filter and a time-frequency analysis are performed for each experiment trial. Then, the optimal EEG signals for every experiment trials are selected based on the signal energy for CSP feature extraction. In the end, the extracted features are classified by three classifiers, linear discriminant analysis (LDA), naïve Bayes (NVB), and support vector machine (SVM), in parallel for classification accuracy comparison. The experiment results show the proposed algorithm average computation time is 37.22% less than the FBCSP (1st winner in the BCI Competition IV) and 4.98% longer than the conventional CSP method. For the classification rate, the proposed algorithm kappa value achieved 2nd highest compared with the top 3 winners in BCI Competition IV.

eess.SP↗

arXiv2020

Automatic LiDAR Extrinsic Calibration System using Photodetector and Planar Board for Large-scale Applications

This paper presents a novel automatic calibration system to estimate the extrinsic parameters of LiDAR mounted on a mobile platform for sensor misalignment inspection in the large-scale production of highly automated vehicles. To obtain subdegree and subcentimeter accuracy levels of extrinsic calibration, this study proposed a new concept of a target board with embedded photodetector arrays, named the PD-target system, to find the precise position of the correspondence laser beams on the target surface. Furthermore, the proposed system requires only the simple design of the target board at the fixed pose in a close range to be readily applicable in the automobile manufacturing environment. The experimental evaluation of the proposed system on low-resolution LiDAR showed that the LiDAR offset pose can be estimated within 0.1 degree and 3 mm levels of precision. The high accuracy and simplicity of the proposed calibration system make it practical for large-scale applications for the reliability and safety of autonomous systems.

eess.IV↗

arXiv2020

Accurate Alignment Inspection System for Low-resolution Automotive and Mobility LiDAR

A misalignment of LiDAR as low as a few degrees could cause a significant error in obstacle detection and mapping that could cause safety and quality issues. In this paper, an accurate inspection system is proposed for estimating a LiDAR alignment error after sensor attachment on a mobility system such as a vehicle or robot. The proposed method uses only a single target board at the fixed position to estimate the three orientations (roll, tilt, and yaw) and the horizontal position of the LiDAR attachment with sub-degree and millimeter level accuracy. After the proposed preprocessing steps, the feature beam points that are the closest to each target corner are extracted and used to calculate the sensor attachment pose with respect to the target board frame using a nonlinear optimization method and with a low computational cost. The performance of the proposed method is evaluated using a test bench that can control the reference yaw and horizontal translation of LiDAR within ranges of 3 degrees and 30 millimeters, respectively. The experimental results for a low-resolution 16 channel LiDAR (Velodyne VLP-16) confirmed that misalignment could be estimated with accuracy within 0.2 degrees and 4 mm. The high accuracy and simplicity of the proposed system make it practical for large-scale industrial applications such as automobile or robot manufacturing process that inspects the sensor attachment for the safety quality control.

eess.IV↗

arXiv2019

Integrating Inter-vehicular Communication, Vehicle Localization, and a Digital Map for Cooperative Adaptive Cruise Control with Target Detection Loss

Adaptive Cruise Control (ACC) is an Advanced Driver Assistance System (ADAS) that enables vehicle following with desired inter-vehicular distances. Cooperative Adaptive Cruise Control (CACC) is upgraded ACC that utilizes additional inter-vehicular wireless communication to share vehicle states such as acceleration to enable shorter gap following. Both ACC and CACC rely on range sensors such as radar to obtain the actual inter-vehicular distance for gap-keeping control. The range sensor may lose detection of the target, the preceding vehicle, on curvy roads or steep hills due to limited angle of view. Unfavourable weather conditions, target selection failure, or hardware issue may also result in target detection loss. During target detection loss, the vehicle following system usually falls back to Cruise Control (CC) wherein the follower vehicle maintains a constant speed. In this work, we propose an alternative way to obtain the inter-vehicular distance during target detection loss to continue vehicle following. The proposed algorithm integrates inter-vehicular communication, accurate vehicle localization, and a digital map with lane center information to approximate the inter-vehicular distance. In-lab robot following experiments demonstrated that the proposed algorithm provided desirable inter-vehicular distance approximation. Although the algorithm is intended for vehicle following application, it can also be used for other scenarios that demand vehicles' relative distance approximation. The work also showcases our in-lab development effort of robotic emulation of traffic for connected and automated vehicles.

cs.RO↗

arXiv2013

Concurrent multi-domain simulations in linear structural dynamics using multiple grid multiple time-scale (MGMT) method

Work presented in this paper describes a general algorithm and its finite element implementation for performing concurrent multiple sub-domain simulations in linear structural dynamics. Using this approach one can solve problems in which the domain under analysis can be selectively discretized spatially and temporally, hence allowing the user to obtain a desired level of accuracy in critical regions while improving computational efficiency globally. The mathematical background for this approach is largely based upon the fundamental principles of domain decomposition methods (DDM) and Lagrange multipliers, used to obtain coupled equations of motion for distinct regions of a continuous domain. These methods when combined together systematically yield constraint forces that not only ensure conservation of energy but also enforce continuity of velocities across sub-domain interfaces. Multiple grid (MG) connections between non-conforming sub-domains are modeled using mortar elements whereas coupled multiple time-scale (MT) equations are derived for the classical Newmark integration algorithm (and its constituents). Fully discretized equations of motion for component sub-domains, augmented with an interface condition are then solved using block elimination method and Crout factorization. A proof of stability is provided using Energy method and overall efficiency, accuracy and stability of multiple sub-domain coupling is evaluated using a series of numerical examples. Primary observations are made for the evolution and distribution of kinematic quantities and structural wave propagation across connecting sub-domain. Numerical stability is verified by ensuring energy balance at global as well as component sub-domain level. Discussed examples highlight the greatest advantage of MGMT method; which is high simulation speedups (at the cost of reasonably small errors).

math.NA↗