Browsing by Author "Koskie, Sarah"

Now showing 1 - 10 of 11
  • Thumbnail Image
    Item
    An Adaptive Eye Gaze Tracking System Without Calibration for Use in an Automobile
    (2011) Rajabather, Harikrishna K.; Koskie, Sarah; Chen, Yaobin; Christopher, Lauren
    One of the biggest hurdles to the development of an effective driver state monitor is the that there is no real-time eye-gaze detection. This is primarily due to the fact that such systems require calibration. In this thesis the various aspects that comprise an eye gaze tracker are investigated. From that we developed an eye gaze tracker for automobiles that does not require calibration. We used a monocular camera system with IR light sources placed in each of the three mirrors. The camera system created the bright-pupil effect for robust pupil detection and tracking. We developed an SVM based algorithm for initial eye candidate detection; after that the eyes were tracked using a hybrid Kalman/Mean-shift algorithm. From the tracked pupils, various features such as the location of the glints (reflections in the pupil from the IR light sources) were extracted. This information is then fed into a Generalized Regression Neural Network (GRNN). The GRNN then maps this information into one of thirteen gaze regions in the vehicle.
  • Thumbnail Image
    Item
    Alcohol intoxication progressively impairs drivers' capacity to detect important environmental stimuli
    (Elsevier, 2018) Plawecki, Martin Henry; Koskie, Sarah; Kosobud, Ann; Justiss, Michael D.; O'Connor, Sean; Psychiatry, School of Medicine
    Rationale Alcohol intoxication impairs driving skills, leading to an increased frequency of accidents and crash fatalities. Inebriation may specifically impair environmental vigilance, reducing the driver's capacity for attention to stimuli that are relevant to successful navigation. Objectives We examined the separate and interactive effects of breath alcohol concentration (BrAC) and simulated driving scenario on the capacity to correctly identify visual stimuli embedded in the environment. Methods Ten healthy young adult drivers (6 males; 4 females) each performed 4 driving scenarios at each of 3 steady breath alcohol concentration levels (0, 60 and 100 mg/dl). Scenarios were based on speed or distance keeping while navigating a rural 2-lane road in daytime or nighttime conditions. Drivers pressed a button on the steering wheel corresponding to the direction of an arrow (up or down) which appeared briefly on road signs embedded in the environment, either overhead or on the roadside. Results Increasing level of BrAC and subjective scenario difficulty manifested significant, separate, but not interactive influences in association with the number of arrows correctly identified. Significant impairments could be detected at a level of BrAC below the current American limit for legal operation of a motor vehicle. Conclusions Environmental vigilance is subject to impairment by either/both alcohol intoxication and driving conditions.
  • Thumbnail Image
    Item
    Automatic Modeling and Simulation of Networked Components
    (2011) Bruce, Nathaniel William; Koskie, Sarah; Chen, Yaobin; Li, Lingxi
    Testing and verification are essential to safe and consistent products. Simulation is a widely accepted method used for verification and testing of distributed components. Generally, one of the major hurdles in using simulation is the development of detailed and accurate models. Since there are time constraints on projects, fast and effective methods of simulation model creation emerge as essential for testing. This thesis proposes to solve these issues by presenting a method to automatically generate a simulation model and run a random walk simulation using that model. The method is automated so that a modeler spends as little time as possible creating a simulation model and the errors normally associated with manual modeling are eliminated. The simulation is automated to allow a human to focus attention on the device that should be tested. The communications transactions between two nodes on a network are recorded as a trace file. This trace file is used to automatically generate a finite state machine model. The model can be adjusted by a designer to add missing information and then simulated in real-time using a software-in-the-loop approach. The innovations in this thesis include adaptation of a synthesis method for use in simulation, introduction of a random simulation method, and introduction of a practical evaluation method for two finite state machines. Test results indicate that nodes can be adequately replaced by models generated automatically by these methods. In addition, model construction time is reduced when comparing to the from scratch model creation method.
  • Thumbnail Image
    Item
    Collision Avoidance for Automated Vehicles Using Occupancy Grid Map and Belief Theory
    (2021-08) Soltani, Reza; Li, Lingxi; Koskie, Sarah; Chen, Yaobin
    This thesis discusses occupancy grid map, collision avoidance system and belief theory, and propose some of the latest and the most effective method such as predictive occupancy grid map, risk evaluation model and OGM role in the belief function theory with the approach of decision uncertainty according to the environment perception with the degree of belief in the driving command acceptability. Finally, how the proposed models mitigate or prevent the occurrence of the collision.
  • Thumbnail Image
    Item
    Concurrent topology optimization of structures and materials
    (2013-12-11) Liu, Kai; Tovar, Andrés; Nematollahi, Khosrow; Koskie, Sarah; Anwar, Sohel
    Topology optimization allows designers to obtain lightweight structures considering the binary distribution of a solid material. The introduction of cellular material models in topology optimization allows designers to achieve significant weight reductions in structural applications. However, the traditional topology optimization method is challenged by the use of cellular materials. Furthermore, increased material savings and performance can be achieved if the material and the structure topologies are concurrently designed. Hence, multi-scale topology optimization methodologies are introduced to fulfill this goal. The objective of this investigation is to discuss and compare the design methodologies to obtaining optimal macro-scale structures and the corresponding optimal meso-scale material designs in continuum design domains. These approaches make use of homogenization theory to establish communication bridges between both material and structural scales. The periodicity constraint makes such cellular materials manufacturable while relaxing the periodicity constraint to achieve major improvements of structural performance. Penalization methods are used to obtain binary solutions in both scales. The proposed methodologies are demonstrated in the design of stiff structure and compliant mechanism synthesis. The multiscale results are compared with the traditional structural-level designs in the context of Pareto solutions, demonstrating benefits of ultra-lightweight configurations. Errors involved in the mult-scale topology optimization procedure are also discussed. Errors are mainly classified as mesh refinement errors and homogenization errors. Comparisons between the multi-level designs and uni-level designs of solid structures, structures using periodic cellular materials and non-periodic cellular materials are provided. Error quantifications also indicate the superiority of using non-periodic cellular materials rather than periodic cellular materials.
  • Thumbnail Image
    Item
    Evaluation of model predictive control method for collision avoidance of automated vehicles
    (2020-08) Ozdemir, Hikmet D.; Li, Lingxi; Koskie, Sarah; King, Brian
    Collision avoidance design plays an essential role in autonomous vehicle technology. It's an attractive research area that will need much experimentation in the future. This research area is very important for providing the maximum safety to automated vehicles, which have to be tested several times under diFFerent circumstances for safety before use in real life. This thesis proposes a method for designing and presenting a collision avoidance maneuver by using a model predictive controller with a moving obstacle for automated vehicles. It consists of a plant model, an adaptive MPC controller, and a reference trajectory. The proposed strategy applies a dynamic bicycle model as the plant model, adaptive model predictive controller for the lateral control, and a custom reference trajectory for the scenario design. The model was developed using the Model Predictive Control Toolbox and Automated Driving Toolbox in Matlab. Builtin tools available in Matlab/Simulink were used to verify the modeling approach and analyze the performance of the system. The major contribution of this thesis work was implementing a novel dynamic obstacle avoidance control method for automated vehicles. The study used validated parameters obtained from previous research. The novelty of this research was performing the studies using a MPC based controller instead of a sliding mode controller, that was primarily used in other studies. The results obtained from the study are compared with the validated models. The comparisons consisted of the lateral overlap, lateral error, and steering angle simulation results between the models. Additionally, this study also included outcomes for the yaw angle. The comparisons and other outcomes obtained in this study indicated that the developed control model produced reasonably acceptable results and recommendations for future studies.
  • Thumbnail Image
    Item
    Lane departure avoidance system
    (2011-08) Mukhopadhyay, Mousumi; Koskie, Sarah; Chen, Yaobin; Lee, John
    Traffic accidents cause millions of injuries and tens of thousands of fatalities per year worldwide. This thesis briefly reviews different types of active safety systems designed to reduce the number of accidents. Focusing on lane departure, a leading cause of crashes involving fatalities, we examine a lane-keeping system proposed by Minoiu Enache et al.They proposed a switched linear feedback (LMI) controller and provided two switching laws, which limit driver torque and displacement of the front wheels from the center of the lane. In this thesis, a state feedback (LQR) controller has been designed. Also, a new switching logic has been proposed which is based on driver's torque, lateral offset of the vehicle from the center of the lane and relative yaw angle. The controller activates assistance torque when the driver is deemed inattentive. It is deactivated when the driver regains control. Matlab/Simulink modeling and simulation environment is used to verify the results of the controller. In comparison to the earlier switching strategies, the maximum values of the state variables lie very close to the set of bounds for normal driving zone. Also, analysis of the controller’s root locus shows an improvement in the damping factor, implying better system response.
  • Thumbnail Image
    Item
    Real-time road traffic events detection and geo-parsing
    (2018-08-08) Kumar, Saurabh; Koskie, Sarah
    In the 21st century, there is an increasing number of vehicles on the road as well as a limited road infrastructure. These aspects culminate in daily challenges for the average commuter due to congestion and slow moving traffic. In the United States alone, it costs an average US driver $1200 every year in the form of fuel and time. Some positive steps, including (a) introduction of the push notification system and (b) deploying more law enforcement troops, have been taken for better traffic management. However, these methods have limitations and require extensive planning. Another method to deal with traffic problems is to track the congested area in a city using social media. Next, law enforcement resources can be re-routed to these areas on a real-time basis. Given the ever-increasing number of smartphone devices, social media can be used as a source of information to track the traffic-related incidents. Social media sites allow users to share their opinions and information. Platforms like Twitter, Facebook, and Instagram are very popular among users. These platforms enable users to share whatever they want in the form of text and images. Facebook users generate millions of posts in a minute. On these platforms, abundant data, including news, trends, events, opinions, product reviews, etc. are generated on a daily basis. Worldwide, organizations are using social media for marketing purposes. This data can also be used to analyze the traffic-related events like congestion, construction work, slow-moving traffic etc. Thus the motivation behind this research is to use social media posts to extract information relevant to traffic, with effective and proactive traffic administration as the primary focus. I propose an intuitive two-step process to utilize Twitter users' posts to obtain for retrieving traffic-related information on a real-time basis. It uses a text classifier to filter out the data that contains only traffic information. This is followed by a Part-Of-Speech (POS) tagger to find the geolocation information. A prototype of the proposed system is implemented using distributed microservices architecture.
  • Thumbnail Image
    Item
    Road Accident Reconstruction and Simulation With and Without EDR Data
    (2011-08-23) Modak, Anagha Gurunath; Koskie, Sarah; Chen, Yaobin; Li, Lingxi
    Road accident reconstruction and simulation investigates the accident causes, suggests improvements in vehicle design and investigates failures in vehicle control and safety systems such as the anti-lock brake system (ABS) and air-bag deployment. This thesis focuses on analysis of crash data from vehicles not equipped with collision warning systems. Vehicle parameters before and during an accident can be recorded using an Event Data Recorder (EDR) which helps in reconstructing an accident. This tool, installed in the vehicle, records different crash parameters like vehicle speed, lateral and longitudinal acceleration, seat-belt status, and air-bag deployment over a period that spens the accident. This thesis focuses on accident reconstruction with and without EDR data. A simulation software tool called HVE is used to visually recreate the reconstructed accidents. HVE is a platform to execute different accident simulation methods which are used for specific types of simulations. Two such simulation methods, EDSMAC4 and EDHIS, are discussed in this thesis. The former is an important method for vehicle-to-vehicle collisions and the latter is used for analysis of human behavior involved in the accident. Three real-life accidents were chosen for reconstruction and simulation. They were Bus and Car accident, Three Vehicle accident and Intersection accident. These particular accidents were chosen to represent a diverse selection of accidents based on the following parameters: the locations of the accidents, the vehicles involved in each accident, and the data available. A qualitative analysis of vehicle occupant's behavior is also presented for one of the three accidents. The thesis discusses in detail the reconstruction of these three accidents. Throughout these simulations, the thesis illustrates the advantages and limitations of the EDR and HVE simulation software for accident reconstruction and simulation.
  • Thumbnail Image
    Item
    Transportation Active Safety Institute
    (Office of the Vice Chancellor for Research, 2010-04-09) Ainslie, Paul; Chen, Yaobin; Justiss, Michael; Koskie, Sarah; O’Connor, Sean
    Since its founding in February 2006, the mission of the Transportation Active Safety Institute (TASI) has been to advance the use of active safety systems to reduce vehicle crashes and save lives. TASI was one of 10 centers awarded IUPUI Signature Center funding in January, 2008. With core faculty drawn from ten departments representing eight schools, the Transportation Active Safety Institute (TASI) is a university-wide interdisciplinary center for advanced automotive-safety research and development on the IUPUI campus. Partnership with industry, government, and non-profit agencies ensures that university research activities complement existing technologies and address existing and future needs. TASI aims to provide a neutral forum for pre-competitive discussion and development of standards and test methodologies for establishing objective benefits of active-safety systems. TASI has established a driving simulator laboratory for research into driver behavior and for testing active-safety system performance. The state-of-the-art DriveSafety DS-600c Driving Simulator is providing a flexible and realistic driving environment for industry, government, and internally sponsored research. This reconfigurable platform allows TASI to test various sensors and driver interfaces, in order to determine effective and convenient solutions to challenges in enhancing safety. TASI held its third workshop, the International Workshop on Research in Active Safety Technology, August 10-11, 2009, in Indianapolis and is currently planning an international workshop on human factors for August 2010. TASI has established an active dialog with other vehicle safety centers around the world through our Global Academic Network for Active Safety.