VTechWorks Repository :: Browsing by Author "Eskandarian, Azim"

Browsing by Author "Eskandarian, Azim"

Now showing 1 - 20 of 25

Analysis of Transient and Steady State Vehicle Handling with Torque Vectoring
Jose, Jobin (Virginia Tech, 2021-10-07)
Advanced Driver Assistance Systems (ADAS) and Autonomous Ground Vehicles (AGV) have the potential to increase road transportation safety, environmental gains, and passenger comfort. The advent of Electric Vehicles has also facilitated greater flexibility in powertrain architectures and control capabilities. Path Tracking controllers that provide steering input are used to execute lateral maneuvers or model the response of a vehicle during cornering. Direct Yaw Control using Torque Vectoring has the potential to improve vehicle's transient cornering stability and modify its steady state handling characteristics during lateral maneuvers. In the first part of this thesis, the transient dynamics of an existing baseline Path Tracking controller is improved using a transient Torque Vectoring algorithm. The existing baseline Path Tracking controller is evaluated, using a linearized system, for a range of vehicle and controller parameters. The effect of implementing transient Torque Vectoring along with the baseline Path Tracking controller is then studied for the same parameter range. The linear analysis shows, in both time and frequency domain, that the transient Torque Vectoring improves vehicle response and stability during cornering. A Torque Vectoring controller is developed in Linear Adaptive Model Predictive Control framework and it's performance is verified in simulation using Simulink and CarSim. The second part of the thesis analyzes the tradeoff enabled by steady state Torque Vectoring between improved limit handling capability through optimal tire force allocation and drivability demonstrated by understeer gradient. Optimal tire force allocation prescribes equal usage in all four tires during maneuvers. This is enabled using steering and Torque Vectoring. An analytical proof is presented which demonstrates that implementation of this optimal tire force allocation results in neutralsteering handling characteristics for the vehicle. The optimal tire force allocation strategy is formulated as a minimax optimization problem. A two-track vehicle model is simulated for this strategy, and it verified the analytical proof by displaying neutralsteering behavior.
Autonomous Mobile Robot Navigation in Dynamic Real-World Environments Without Maps With Zero-Shot Deep Reinforcement Learning
Sivashangaran, Shathushan (Virginia Tech, 2024-06-04)
Operation of Autonomous Mobile Robots (AMRs) of all forms that include wheeled ground vehicles, quadrupeds and humanoids in dynamically changing GPS denied environments without a-priori maps, exclusively using onboard sensors, is an unsolved problem that has potential to transform the economy, and vastly improve humanity's capabilities with improvements to agriculture, manufacturing, disaster response, military and space exploration. Conventional AMR automation approaches are modularized into perception, motion planning and control which is computationally inefficient, and requires explicit feature extraction and engineering, that inhibits generalization, and deployment at scale. Few works have focused on real-world end-to-end approaches that directly map sensor inputs to control outputs due to the large amount of well curated training data required for supervised Deep Learning (DL) which is time consuming and labor intensive to collect and label, and sample inefficiency and challenges to bridging the simulation to reality gap using Deep Reinforcement Learning (DRL). This dissertation presents a novel method to efficiently train DRL with significantly fewer samples in a constrained racetrack environment at physical limits in simulation, transferred zero-shot to the real-world for robust end-to-end AMR navigation. The representation learned in a compact parameter space with 2 fully connected layers with 64 nodes each is demonstrated to exhibit emergent behavior for Out-of-Distribution (OOD) generalization to navigation in new environments that include unstructured terrain without maps, dynamic obstacle avoidance, and navigation to objects of interest with vision input that encompass low light scenarios with the addition of a night vision camera. The learned policy outperforms conventional navigation algorithms while consuming a fraction of the computation resources, enabling execution on a range of AMR forms with varying embedded computer payloads.
Autonomous Vehicle Perception Quality Assessment
Zhang, Ce (Virginia Tech, 2023-06-29)
In recent years, the rapid development of autonomous vehicles (AVs) has necessitated the need for high-quality perception systems. Perception is a fundamental requirement for AVs, with cameras and LiDARs being commonly used sensors for environmental understanding and localization. However, there is a research gap in assessing the quality of AVs perception systems. To address this gap, this dissertation proposes a novel paradigm for evaluating AVs perception quality by studying the perception quality of cameras and LiDARs sensors. Our proposed paradigm aims to provide a comprehensive assessment of the quality of perception systems used in AVs.To achieve our research goals, we first validate the concept of surrounding environmental complexity through subjective experiments that rate complexity scores. In this study, we propose a neural network to classify complexity. Subsequently, we study image-based perception quality assessment by using image saliency and 2D object detection algorithms to create an image-based quality index. We then develop a neural network model to regress the proposed quality index score. Furthermore, we extend our research to LiDAR-based point cloud quality assessment by using the image-based saliency map as guidance to generate a point cloud quality index score. We then develop a neural network model to regress the score. Finally, we validate the proposed perception quality index with a novel designed AVs perception algorithm. In conclusion, this dissertation makes a significant contribution to the field of AVs perception by proposing a new paradigm for assessing perception quality. Our research findings can be used to improve the overall performance and safety of AVs, which has significant implications for the transportation industry and society as a whole.
Characterization of Structure-Borne Tire Noise Using Virtual Sensing
Nouri, Arash (Virginia Tech, 2021-01-27)
Various improvements which have been made to the vehicle (reduced engine noise, reducedaerodynamic related NVH), have resulted in tire road noise as the dominant source of thevehicle interior noise. Generally, vehicle interior noise has two main sources, 1) travellinglow frequency excitation below 800 Hz from road surface through a structure- borne pathand 2) the high frequency (above 800 Hz) air-borne noise that is caused by air- pumpingnoise caused by tread pattern.The structure-borne waves of the circumference of the tire are generated by excitation atthe contact patch due to the road surface texture and characteristics. These vibrations arethen transferred from the sidewalls of the tire to the rim and then are transmitted throughthe spindle-wheel interface, resulting in high frequency vibration of vehicle body panels andwindows.The focus of this study is to develop several statistical-based models for analyzing the roadsurface and using them to predict the tire-road noise structure-borne component. In order todo this, a new methodology for sensing the road characteristics, such as asperities and roadsurface condition, were developed using virtual sensing and intelligent tire technology. In ad-dition, the spindle forces were used as an indicator to the structure-borne noise of the vehicle.Several data mining and multivariate analysis-based methods were developed to extractfeatures and to develop an empirical model to predict the power of structure-borne noiseunder different operational and road conditions. Finally, multiple data driven models-basedmodels were developed to classify the road types, and conditions and use them for the noisefrequency spectrum prediction.
Characterizing and Comparing the ADS Maneuver Execution Subsystem Performance of Two Vehicles
Gopiao, Joseph Brandon Bueno (Virginia Tech, 2023-06-07)
Automated driving systems (ADS) are projected to bring a plethora of benefits to society, such as enhanced road safety and heightened quality of life. However, placing one's trust in the hands of an automated system is still a large concern to society. To facilitate the large-scale adoption of ADSs, they must be stringently tested and evaluated prior to their deployment on public roadways due to their direct impact on the safety of other motorists and vulnerable road users. Currently, no standardized method of quantifying ADS performance exists, so this research project contributes to the evaluation of ADSs by developing and demonstrating a test method that solely characterizes the motion control subsystem of an ADS. The developed test method involved generating representative driving scenarios that exercised both the longitudinal and lateral control elements of an ADS. This method was then demonstrated using two test vehicles with different control system architectures by (1) defining and injecting a ground truth trajectory into the ADS, (2) characterizing the motion control subsystem by quantifying its ability to follow the ground truth path under both nominal conditions and conditions where disturbances were introduced, and (3) analyzing the response of each vehicle to characterize their respective control systems as well as identify differences between the two control architectures. First, a set of representative driving scenarios was created to test the longitudinal and lateral control elements both in isolation and in tandem. Multiple unique design variations of each scenario were created by implementing various target speeds, accelerations, and turning radii that map to both standard and emergency maneuvers. The parameters were set to match naturalistic driving or regulatory requirements identified as part of a literature review. Next, a reference trajectory—the ground truth set of waypoints that define the position and speed of the ADS—was generated for each driving scenario. This reference trajectory was implemented using three methods: recording the waypoint trail of a human driver and creating a synthetic waypoint list mathematically or with CarMaker, a simulation platform for automobile testing (IPG Automotive 2021). Once this step was completed, the reference trajectory was inserted into the ADS to isolate the motion control system and facilitate a repeatable test input. When the test vehicle was under ADS control, the experimenter served as the designated fallback user so they could take control of the vehicle if necessary. Finally, a set of test metrics related to the operation of the ADS (lateral offset, heading error, speed error, longitudinal stop position error, and test completion percentage) were calculated using kinematic data to characterize each motion control system architecture. The analysis of the kinematic metrics for each test scenario demonstrated that the method could effectively evaluate the performance of ADS in various scenarios and highlight the strengths and weaknesses of each system. The control system of Vehicle A consistently lagged in throttle and brake actuation and rounded corners by turning early and with a larger cornering radius. This control system also could not exceed a lateral acceleration of 3.5 m/s2 when under ADS control and limited its yaw rate to keep the lateral acceleration below this level. Consequently, this limitation caused the vehicle to turn wide for radius and speed combinations with a lateral acceleration greater than 3.5 m/s2. On the other hand, the control system of Vehicle B consistently exhibited a small delay before turning and tended to overshoot lane changes at higher lateral accelerations. Regarding disturbances, only the road grade significantly affected the response of both vehicles.
Characterizing Human Driving Behavior Through an Analysis of Naturalistic Driving Data
Ali, Gibran (Virginia Tech, 2023-01-23)
Reducing the number of motor vehicle crashes is one of the major challenges of our times. Current strategies to reduce crash rates can be divided into two groups: identifying risky driving behavior prior to crashes to proactively reduce risk and automating some or all human driving tasks using intelligent vehicle systems such as Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS). For successful implementation of either strategy, a deeper understanding of human driving behavior is essential. This dissertation characterizes human driving behavior through an analysis of a large naturalistic driving study and offers four major contributions to the field. First, it describes the creation of the Surface Accelerations Reference, a catalog of all longitudinal and lateral surface accelerations found in the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS). SHRP 2 NDS is the largest naturalistic driving study in the world with 34.5 million miles of data collected from over 3,500 participants driving in six separate locations across the United States. An algorithm was developed to detect each acceleration epoch and summarize key parameters, such as the mean and maxima of the magnitude, roadway properties, and driver inputs. A statistical profile was then created for each participant describing their acceleration behavior in terms of rates, percentiles, and the magnitude of the strongest event in a distance threshold. The second major contribution is quantifying the effect of several factors that influence acceleration behavior. The rate of mild to harsh acceleration epochs was modeled using negative binomial distribution-based generalized linear mixed effect models. Roadway speed category, driver age, driver gender, vehicle class, and location were used as fixed effects, and a unique participant identifier was as the random effect. Subcategories of each fixed effect were compared using incident rate ratios. Roadway speed category was found to have the largest effect on acceleration behavior, followed by driver age, vehicle class, and location. This methodology accounts for the major influences while simultaneously ensuring that the comparisons are meaningful and not driven by coincidences of data collection. The third major contribution is the extraction of acceleration-based long-term driving styles and determining their relationship to crash risk. Rates of acceleration epochs experienced on ≤ 30 mph roadways were used to cluster the participants into four groups. The metrics to cluster the participants were chosen so that they represent long-term driving style and not short-term driving behavior being influenced by transient traffic and environmental conditions. The driving style was also correlated to driving risk by comparing the crash rates, near-crash rates, and speeding behavior of the participants. Finally, the fourth major contribution is the creation of a set of interactive analytics tools that facilitate quick characterization of human driving during regular as well as safety-critical driving events. These tools enable users to answer a large and open-ended set of research questions that aid in the development of ADAS and ADS components. These analytics tools facilitate the exploration of queries such as how often do certain scenarios occur in naturalistic driving, what is the distribution of key metrics during a particular scenario, or what is the relative composition of various crash datasets? Novel visual analytics principles such as video on demand have been implemented to accelerate the sense-making loop for the user.
Cooperative Adaptive Cruise Control With Adaptive Kalman Filter Subject to Temporary Communication Loss
Wu, Chaoxian; Lin, Yuan; Eskandarian, Azim (IEEE, 2019)
Cooperative adaptive cruise control (CACC) communicates the relevant preceding vehicle state data to the follower (ego) vehicle to improve the vehicle following capabilities. In general, the CACC utilizes the preceding vehicle's desired acceleration from wireless communication as a feedforward term in the controller of the ego vehicle, which dominantly determines the total control input. However, communication loss would degrade CACC to adaptive cruise control (ACC), where the lack of the feedforward term during communication loss would increase the inter-vehicular distance or, otherwise, may lead to collision during vehicle emergency braking. This paper proposes a control algorithm with an adaptive Kalman filter estimating the acceleration of a preceding vehicle, and the estimated acceleration is implemented as a feedforward signal in the ego-vehicle CACC controller in case of communication loss. The proposed control algorithm is evaluated by the experiments using mobile robots that emulate driving. In addition, the simulations of real vehicles are also conducted. The results of simulations and robot experiments show that the performance of implementing the adaptive Kalman filter during communication loss is better than fallback to ACC and the normal Kalman filter based on the Singer model.
Cooperative Perception for Connected Vehicles
Mehr, Goodarz (Virginia Tech, 2024-05-31)
Cooperative Perception in Autonomous Ground Vehicles using a Mobile Robot Testbed
Sridhar, Srivatsan (Virginia Tech, 2017-10-03)
With connected and autonomous vehicles, no optimal standard or framework currently exists, outlining the right level of information sharing for cooperative autonomous driving. Cooperative Perception is proposed among vehicles, where every vehicle is transformed into a moving sensor platform that is capable of sharing information collected using its on-board sensors. This helps extend the line of sight and field of view of autonomous vehicles, which otherwise suffer from blind spots and occlusions. This increase in situational awareness promotes safe driving over a short range and improves traffic flow efficiency over a long range. This thesis proposes a methodology for cooperative perception for autonomous vehicles over a short range. The problem of cooperative perception is broken down into sub-tasks of cooperative relative localization and map merging. Cooperative relative localization is achieved using visual and inertial sensors, where a computer-vision based camera relative pose estimation technique, augmented with position information, is used to provide a pose-fix that is subsequently updated by dead reckoning using an inertial sensor. Prior to map merging, a technique for object localization using a monocular camera is proposed that is based on the Inverse Perspective Mapping technique. A mobile multi-robot testbed was developed to emulate autonomous vehicles and the proposed method was implemented on the testbed to detect pedestrians and also to respond to the perceived hazard. Potential traffic scenarios where cooperative perception could prove crucial were tested and the results are presented in this thesis.
Cooperative Perception of Connected Vehicles for Safety
Eskandarian, Azim; Ghorai, Prasenjit; Nayak, Anshul (Safe-D National UTC, 2023-04)
In cooperative perception, reliably detecting surrounding objects and communicating the information between vehicles is necessary for safety. However, vehicle-to-vehicle transmission of huge datasets or images can be computationally expensive and often not feasible in real time. A robust approach to ensure cooperation involves relative pose estimation between two vehicles sharing a common field of view. Detecting the object and transferring its location information in real time is necessary when the object is not in the ego vehicle’s field of view. In such scenarios, reliable and robust pose recovery of the object at each instant ensures the ego vehicle accurately estimates its trajectory. Once pose recovery is established, the object’s location information can be obtained for future trajectory prediction. Deterministic predictions provide only point estimates of future states which is not trustworthy under dynamic traffic scenarios. Estimating the uncertainty associated with the predicted states with a certain level of confidence can lead to robust path planning. This study proposed quantifying 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 predictions between the probabilistic neural network models were compared 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. The study has been extended to multiple datasets, providing a comprehensive comparison for each model.
Cooperative Prediction and Planning Under Uncertainty for Autonomous Robots
Nayak, Anshul Abhijit (Virginia Tech, 2024-10-11)
Autonomous robots are set to become ubiquitous in the future, with applications ranging from autonomous cars to assistive household robots. These systems must operate in close proximity of dynamic and static objects, including humans and other non-autonomous systems, adding complexity to their decision-making processes. The behaviour of such objects is often stochastic and hard to predict. Making robust decisions under such uncertain scenarios can be challenging for these autonomous robots. In the past, researchers have used deterministic approach to predict the motion of surrounding objects. However, these approaches can be over-confident and do not capture the stochastic behaviour of surrounding objects necessary for safe decision-making. In this dissertation, we show the importance of probabilistic prediction of surrounding dynamic objects and their incorporation into planning for safety-critical decision making. We utilise Bayesian inference models such as Monte Carlo dropout and deep ensemble to probabilistically predict the motion of surrounding objects. Our probabilistic trajectory forecasting model showed improvement over standard deterministic approaches and could handle adverse scenarios such as sensor noise and occlusion during prediction. The uncertainty-inclusive prediction of surrounding objects has been incorporated into planning. The inclusion of predicted states of surrounding objects with associated uncertainty enables the robot make proactive decisions while avoiding collisions.
Development and analysis of a small-scale controlled dataset with various weather conditions, lighting, and route types for autonomous driving
Du, Xuelai (Virginia Tech, 2024-07-24)
This study addresses the limitations of existing autonomous vehicle datasets, particularly the need for greater specificity of weather conditions and road types. We utilized X-CAR to highlight the challenges of extreme weather and non-urban road conditions on autonomous driving systems. Our dataset comprises recordings under seven distinct weather and lighting conditions across four road types. Notably, our research focuses on differentiating between various lighting and weather conditions and road types, which often need improvement in many existing datasets. We used the X-CAR platform to collect 360-degree image information and LiDAR point clouds at 10Hz. Due to the constraints of time and resources, we used algorithmic prediction to generate ground truth data via the Co-DETR 2D prediction algorithm. We validated the accuracy of the Co-DETR algorithm through partial manual annotation. However, it is undeniable that in some extreme conditions, the algorithm-generated ground truth can lead to results deviating from expectations and real-world situations. Therefore, we conducted a scaled manual annotation and controlled experiments, ensuring the highest level of accuracy. After the manual annotation, we validated our initial conclusions and trained a model based on YOLOv8x, focusing on weak environmental conditions. The final model underwent multiple iterations and achieved satisfactory accuracy. The enhanced model demonstrated a significant increase in detection accuracy compared to the original YOLOv8x model. At the same time, our analysis identifies weather conditions that markedly reduce detection accuracy, providing focal points for future dataset enhancements.
Drone Cellular Networks: Fundamentals, Modeling, and Analysis
Banagar, Morteza (Virginia Tech, 2022-06-23)
With the increasing maturity of unmanned aerial vehicles (UAVs), also known as drones, wireless ecosystem is experiencing an unprecedented paradigm shift. These aerial platforms are specifically appealing for a variety of applications due to their rapid and flexible deployment, cost-effectiveness, and high chance of forming line-of-sight (LoS) links to the ground nodes. As with any new technology, the benefits of incorporating UAVs in existing cellular networks cannot be characterized without completely exploring the underlying trade space. This requires a detailed system-level analysis of drone cellular networks by taking the unique features of UAVs into account, which is the main objective of this dissertation. We first focus on a static setup and characterize the performance of a three-dimensional (3D) two-hop cellular network in which terrestrial base stations (BSs) coexist with UAVs to serve a set of ground user equipment (UE). In particular, a UE connects either directly to its serving terrestrial BS by an access link or connects first to its serving UAV which is then wirelessly backhauled to a terrestrial BS (joint access and backhaul). We consider realistic antenna radiation patterns for both BSs and UAVs using practical models developed by the third generation partnership project (3GPP). We assume a probabilistic channel model for the air-to-ground transmission, which incorporates both LoS and non-LoS links. Assuming the max-power association policy, we study the performance of the network in both amplify-and-forward (AF) and decode-and-forward (DF) relaying protocols. Using tools from stochastic geometry, we analyze the joint distribution of distance and zenith angle of the closest (and serving) UAV to the origin in a 3D setting. Further, we identify and extensively study key mathematical constructs as the building blocks of characterizing the received signal-to-interference-plus-noise ratio (SINR) distribution. Using these results, we obtain exact mathematical expressions for the coverage probability in both AF and DF relaying protocols. Furthermore, considering the fact that backhaul links could be quite weak because of the downtilted antennas at the BSs, we propose and analyze the addition of a directional uptilted antenna at the BS that is solely used for backhaul purposes. The superiority of having directional antennas with wirelessly backhauled UAVs is further demonstrated via extensive simulations. Second, we turn our attention to a mobile setup and characterize the performance of several canonical mobility models in a drone cellular network in which UAV base stations serve UEs on the ground. In particular, we consider the following four mobility models: (i) straight line (SL), (ii) random stop (RS), (iii) random walk (RW), and (iv) random waypoint (RWP), among which the SL mobility model is inspired by the simulation models used by the 3GPP for the placement and trajectory of UAVs, while the other three are well-known canonical models (or their variants) that offer a useful balance between realism and tractability. Assuming the nearest-neighbor association policy, we consider two service models for the UEs: (i) UE independent model (UIM), and (ii) UE dependent model (UDM). While the serving UAV follows the same mobility model as the other UAVs in the UIM, it is assumed to fly towards the UE of interest in the UDM and hover above its location after reaching there. We then present a unified approach to characterize the point process of UAVs for all the mobility and service models. Using this, we provide exact mathematical expressions for the average received rate and the session rate as seen by the typical UE. Further, using tools from the calculus of variations, we concretely demonstrate that the simple SL mobility model provides a lower bound on the performance of other general mobility models (including the ones in which UAVs follow curved trajectories) as long as the movement of each UAV in these models is independent and identically distributed (i.i.d.). Continuing our analysis on mobile setups, we analyze the handover probability in a drone cellular network, where the initial positions of the UAVs serving the ground UEs are modeled by a homogeneous Poisson point process (PPP). Inspired by the mobility model considered in the 3GPP studies, we assume that all the UAVs follow the SL mobility model, i.e., move along straight lines in random directions. We further consider two different scenarios for the UAV speeds: (i) same speed model (SSM), and (ii) different speed model (DSM). Assuming nearest-neighbor association policy, we characterize the handover probability of this network for both mobility scenarios. For the SSM, we compute the exact handover probability by establishing equivalence with a single-tier terrestrial cellular network, in which the BSs are static while the UEs are mobile. We then derive a lower bound for the handover probability in the DSM by characterizing the evolution of the spatial distribution of the UAVs over time. After performing these system-level analyses on UAV networks, we focus our attention on the air-to-ground wireless channel and attempt to understand its unique features. For that, we first study the impact of UAV wobbling on the coherence time of the wireless channel between UAVs and a ground UE, using a Rician multi-path channel model. We consider two different scenarios for the number of UAVs: (i) single UAV scenario (SUS), and (ii) multiple UAV scenario (MUS). For each scenario, we model UAV wobbling by two random processes, i.e., the Wiener and sinusoidal processes, and characterize the channel autocorrelation function (ACF) which is then used to derive the coherence time of the channel. For the MUS, we further show that the UAV-UE channels for different UAVs are uncorrelated from each other. One key observation that is revealed from our analysis is that even for small UAV wobbling, the coherence time of the channel may degrade quickly, which may make it difficult to track the channel and establish a reliable communication link. Finally, we develop an impairments-aware air-to-ground unified channel model that incorporates the effect of both wobbling and hardware impairments, where the former is caused by random physical fluctuations of UAVs, and the latter by intrinsic radio frequency (RF) nonidealities at both the transmitter and receiver, such as phase noise, in-phase/quadrature (I/Q) imbalance, and power amplifier (PA) nonlinearity. The impact of UAV wobbling is modeled by two stochastic processes, i.e., the canonical Wiener process and the more realistic sinusoidal process. On the other hand, the aggregate impact of all hardware impairments is modeled as two multiplicative and additive distortion noise processes, which is a well-accepted model. For the sake of generality, we consider both wide-sense stationary (WSS) and nonstationary processes for the distortion noises. We then rigorously characterize the ACF of the wireless channel, using which we provide a comprehensive analysis of four key channel-related metrics: (i) power delay profile (PDP), (ii) coherence time, (iii) coherence bandwidth, and (iv) power spectral density (PSD) of the distortion-plus-noise process. Furthermore, we evaluate these metrics with reasonable UAV wobbling and hardware impairment models to obtain useful insights. Similar to our observation above, this work again demonstrates that the coherence time severely degrades at high frequencies even for small UAV wobbling, which renders air-to-ground channel estimation very difficult at these frequencies.
Effectiveness and Acceptance of Adaptive Intelligent Speed Adaptation Systems
Arhin, Stephen; Eskandarian, Azim; Blum, Jeremy; Delaigue, Pierre; Soudbakhsh, Damoon (The National Academies of Sciences, Engineering, and Medicine, 2008)
Intelligent speed adaptation (ISA) systems face significant consumer acceptance hurdles that limit the likelihood of widespread adoption, particularly in the United States. However, if these systems are designed as speed management systems rather than speed limiting systems, with adaptability to individual driving behavior, they may be more likely to meet with consumer acceptance. The results of a fixed-based driving simulator experiment that tested the acceptance and effectiveness of a new type of ISA, called an Advanced Vehicular Speed Adaptation System (AVSAS), are reported. The results of the experiment showed that AVSAS resulted in reductions in driver speeds across a range of roadway types. AVSAS is a speed management system that adapts to an individual driver’s speed behavior and the current driving situation. AVSAS resulted in an average reduction of 5% of the maximum speeds and 3% of the average speeds of the drivers on four road segments. As expected, AVSAS did not reduce driver speeds as much as the mandatory control ISA system, and the experiment confirmed the results of tests conducted on ISA systems largely in Europe. Conversely, the results revealed that more participants were willing to purchase AVSAS compared with the information or mandatory ISAs. Although these results show the promise of a trade-off between system effectiveness and acceptability that has been missing in mandatory and information ISA research, AVSAS suggests that a range of ISA system design requirements could encourage the adoption of ISA systems in the United States.
A method for propulsion nozzle design
Eskandarian, Azim (Virginia Polytechnic Institute and State University, 1983)
An inverse method for the design of exhaust nozzles with a specified transonic pressure distribution is presented. A problem of mixed Neumann and Dirichlet boundary condition is solved. A successive line relaxation process is used to solve the array of velocity potentials in the entire flow field. The streamlines are then displaced to produce boundaries which match a desired pressure distribution. Various cases are tested to verify the reliability of the method. The design calculation proves to be efficient and accurate.
Modified Kernel Principal Component Analysis and Autoencoder Approaches to Unsupervised Anomaly Detection
Merrill, Nicholas Swede (Virginia Tech, 2020-06-01)
Unsupervised anomaly detection is the task of identifying examples that differ from the normal or expected pattern without the use of labeled training data. Our research addresses shortcomings in two existing anomaly detection algorithms, Kernel Principal Component Analysis (KPCA) and Autoencoders (AE), and proposes novel solutions to improve both of their performances in the unsupervised settings. Anomaly detection has several useful applications, such as intrusion detection, fault monitoring, and vision processing. More specifically, anomaly detection can be used in autonomous driving to identify obscured signage or to monitor intersections. Kernel techniques are desirable because of their ability to model highly non-linear patterns, but they are limited in the unsupervised setting due to their sensitivity of parameter choices and the absence of a validation step. Additionally, conventionally KPCA suffers from a quadratic time and memory complexity in the construction of the gram matrix and a cubic time complexity in its eigendecomposition. The problem of tuning the Gaussian kernel parameter, $sigma$, is solved using the mini-batch stochastic gradient descent (SGD) optimization of a loss function that maximizes the dispersion of the kernel matrix entries. Secondly, the computational time is greatly reduced, while still maintaining high accuracy by using an ensemble of small, textit{skeleton} models and combining their scores. The performance of traditional machine learning approaches to anomaly detection plateaus as the volume and complexity of data increases. Deep anomaly detection (DAD) involves the applications of multilayer artificial neural networks to identify anomalous examples. AEs are fundamental to most DAD approaches. Conventional AEs rely on the assumption that a trained network will learn to reconstruct normal examples better than anomalous ones. In practice however, given sufficient capacity and training time, an AE will generalize to reconstruct even very rare examples. Three methods are introduced to more reliably train AEs for unsupervised anomaly detection: Cumulative Error Scoring (CES) leverages the entire history of training errors to minimize the importance of early stopping and Percentile Loss (PL) training aims to prevent anomalous examples from contributing to parameter updates. Lastly, early stopping via Knee detection aims to limit the risk of over training. Ultimately, the two new modified proposed methods of this research, Unsupervised Ensemble KPCA (UE-KPCA) and the modified training and scoring AE (MTS-AE), demonstrates improved detection performance and reliability compared to many baseline algorithms across a number of benchmark datasets.
Motion Planning For Autonomous Vehicles In Non-Signalized Intersections
Patel, Darshit Satishkumar (Virginia Tech, 2023-07-25)
Real-time path generation, including collision checks, is vital in critical driving scenarios such as navigating non-signalized intersections. These intersections lack organized traffic flow, which raises the risk of accidents. Rapidly Exploring Random Trees (RRT) is a widely adopted algorithm in robotics for motion planning due to its simplicity and probabilistic completeness. Over the years, researchers have made modifications to the basic RRT algorithm to improve its performance in dynamic environments, making it a favored planning algorithm for autonomous driving. Among these variants, probabilistic RRT (pRRT) demonstrates promising capabilities for efficient online replanning. The first part of the thesis thoroughly studies the pRRT algorithm and compares its performance to the standard RRT and RRT* algorithms through Python simulations. The pRRT algorithm outperformed the RRT and RRT* algorithms in terms of success rate and time to find a safe trajectory. The algorithm was implemented experimentally on scaled cars for the validation of its feasibility. The experimental results show good sim-to-real transfer for this algorithm. The second part of the thesis proposes a novel algorithm for path planning. The algorithm outperforms the standard RRT and pRRT techniques in terms of optimality and conformance to human instincts. The generated paths are much smoother and easier for the controller to track. The AV implementation combines the probabilistic RRT with the RRT-Connect algorithm to mitigate the problem of parameter tuning of the standard pRRT algorithm. The idea is to generate intermediate critical points around the obstacles to grow multiple trees between these points, which are then eventually connected if a safe trajectory is found. The algorithm was tested in simulation and showed comparatively better performance in handling obstacles.
Practical Algorithms and Analysis for Next-Generation Decentralized Vehicular Networks
Dayal, Avik (Virginia Tech, 2021-11-19)
The development of autonomous ground and aerial vehicles has driven the requirement for radio access technologies (RATs) to support low latency applications. While onboard sensors such as Light Detection and Ranging (LIDAR), Radio Detection and Ranging (RADAR), and cameras can sense and assess the immediate space around the vehicle, RATs are crucial for the exchange of information on critical events, such as accidents and changes in trajectory, with other vehicles and surrounding infrastructure in a timely manner. Simulations and analytical models are critical in modelling and designing efficient networks. In this dissertation, we focus on (a) proposing and developing algorithms to improve the performance of decentralized vehicular communications in safety critical situations and (b) supporting these proposals with simulation and analysis of the two most popular RAT standards, the Dedicated Short Range Communications (DSRC) standard, and the Cellular vehicle-to-everything (C-V2X) standard. In our first contribution, we propose a risk based protocol for vehicles using the DSRC standard. The protocol allows a higher beacon transmission rate for vehicles that are at a higher risk of collision. We verify the benefits of the risk based protocol over conventional DSRC using ns-3 simulations. Two risk based beacon rate protocols are evaluated in our ns-3 simulator, one that adapts the beacon rate between 1 and 10 Hz, and another between 1 and 20 Hz. Our results show that both protocols improve the packet delivery ratio (PDR) performance by up to 45% in congested environments using the 1-10 Hz adaptive beacon rate protocol and by 38% using the 1-20 Hz adaptive scheme. The two adaptive beacon rate protocol simulation results also show that the likelihood of a vehicle collision due to missed packets decreases by up to 41% and 77% respectively, in a three lane dense highway scenario with 160 vehicles operating at different speeds. In our second contribution, we study the performance of a distance based transmission protocol for vehicular ad hoc network (VANET) using tools from stochastic geometry. We consider a risk based transmission protocol where vehicles transmit more frequently depending on the distance to adjacent vehicles. We evaluate two transmission policies, a listen more policy, in which the transmission rate of vehicles decreases as the inter-vehicular distance decreases, and a talk more policy, in which the transmission rate of vehicles increases as the distance to the vehicle ahead of it decreases. We model the layout of a highway using a 1-D Poisson Point process (PPP) and analyze the performance of a typical receiver in this highway setting. We characterize the success probability of a typical link assuming slotted ALOHA as the channel access scheme. We study the trends in success probability as a function of system parameters. Our third contribution includes improvements to the 3rd Generation Partnership Project (3GPP) Release 14 C-V2X standard, evaluated using a modified collision framework. In C-V2X basic safety messages (BSMs) are transmitted through Mode-4 communications, introduced in Release 14. Mode-4 communications operate under the principle of sensing-based semi-persistent scheduling (SPS), where vehicles sense and schedule transmissions without a base station present. We propose an improved adaptive semi-persistent scheduling, termed Ch-RRI SPS, for Mode-4 C-V2X networks. Specifically, Ch-RRI SPS allows each vehicle to dynamically adjust in real-time the BSM rate, referred to in the LTE standard as the resource reservation interval (RRI). Our study based on system level simulations demonstrates that Ch-RRI SPS greatly outperforms SPS in terms of both on-road safety performance, measured as collision risk, and network performance, measured as packet delivery ratio, in all considered C-V2X scenarios. In high density scenarios, e.g., 80 vehicles/km, Ch-RRI SPS shows a collision risk reduction of 51.27%, 51.20% and 75.41% when compared with SPS with 20 ms, 50 ms, and 100 ms RRI respectively. In our fourth and final contribution, we look at the tracking error and age-of-information (AoI) of the latest 3GPP Release 16 NR-V2X standard, which includes enhancements to the 3GPP Release 14 C-V2X standard. The successor to Mode-4 C-V2X, known as Mode-2a NR-V2X, makes slight changes to sensing-based semi-persistent scheduling (SPS), though vehicles can still sense and schedule transmissions without a base station present. We use AoI and tracking error, which is the freshness of the information at the receiver and the difference in estimated vs actual location of a transmitting vehicle respectively, to measure the impact of lost and outdated BSMs on a vehicle's ability to localize neighboring vehicles. In this work, we again show that such BSM scheduling (with a fixed RRI) suffers from severe under- and over- utilization of radio resources, which severely compromises timely dissemination of BSMs and increases the system AoI and tracking error. To address this, we propose an RRI selection algorithm that measures the age or freshness of messages from neighboring vehicles to select an RRI, termed Age of Information (AoI)-aware RRI (AoI-RRI) selection. Specifically, AoI-aware SPS (i) measures the neighborhood AoI (as opposed to channel availability) to select an age-optimal RRI and (ii) uses a modified SPS procedure with the chosen RRI to select BSM transmission opportunities that minimize the overall system AoI. We compare AoI-RRI SPS to Ch-RRI SPS and fixed RRI SPS for NR-V2X. Our experiments based on the Mode-2a NR-V2X standard implemented using system level simulations show both Ch-RRI SPS and AoI-RRI SPS outperform SPS in high density scenarios in terms of tracking error and age-of-information.
Predictive Path Planning For Vehicles at Non-signalized Intersections
Wu, Xihui (Virginia Tech, 2020-09-23)
In the context of path planning, the non-signalized intersections are always a challenging scenario due to the mixture of traffic flow. Most path planning algorithms use the information at the current time instance to generate an optimal path. Because of the dynamics of the non-signalized intersections, iteratively generating a path in a high frequency is necessary, resulting in an enormous waste of computational resources. Rapidly-exploring Random Tree (RRT) as an effective local path planning methodology can determine a feasible path in the static environment. Few improvements are proposed to adopt the RRT to the non-signalized intersections. Gaussian Processes Regression (GPR) is used to predict the other vehicles' future location. The location information in the current and future time instance is used to generate a probability position map. The map not only avoids useless sampling procedures but also increases the speed of generating a path. The optimal steering strategy is deployed to guarantee the trajectory is collision-free in both current and future time frames. Overall, the proposed probabilistic RRT algorithm can select a collision-free path in the non-signalized intersections by combining the GPR, probability position map, and optimal-steering.
A probabilistic approach to driver assistance for delay reduction at congested highway lane drops
Mehr, Goodarz; Eskandarian, Azim (Elsevier, 2021-12-01)
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.

Browsing by Author "Eskandarian, Azim"

Results Per Page

Sort Options