VTechWorks Repository :: Browsing by Author "Kochersberger, Kevin B."

Browsing by Author "Kochersberger, Kevin B."

Now showing 1 - 20 of 93

3-D Point Cloud Generation from Rigid and Flexible Stereo Vision Systems
Short, Nathaniel Jackson (Virginia Tech, 2009-12-04)
When considering the operation of an Unmanned Aerial Vehicle (UAV) or an Unmanned Ground Vehicle (UGV), such problems as landing site estimation or robot path planning become a concern. Deciding if an area of terrain has a level enough slope and a wide enough area to land a Vertical Take Off and Landing (VTOL) UAV or if an area of terrain is traversable by a ground robot is reliant on data gathered from sensors, such as cameras. 3-D models, which can be built from data extracted from digital cameras, can help facilitate decision making for such tasks by providing a virtual model of the surrounding environment the system is in. A stereo vision system utilizes two or more cameras, which capture images of a scene from two or more viewpoints, to create 3-D point clouds. A point cloud is a set of un-gridded 3-D points corresponding to a 2-D image, and is used to build gridded surface models. Designing a stereo system for distant terrain modeling requires an extended baseline, or distance between the two cameras, in order to obtain a reasonable depth resolution. As the width of the baseline increases, so does the flexibility of the system, causing the orientation of the cameras to deviate from their original state. A set of tools have been developed to generate 3-D point clouds from rigid and flexible stereo systems, along with a method for applying corrections to a flexible system to regain distance accuracy in a flexible system.
A*-Based Path Planning for an Unmanned Aerial and Ground Vehicle Team in a Radio Repeating Operation
Krawiec, Bryan Michael (Virginia Tech, 2012-05-02)
In the event of a disaster, first responders must rapidly gain situational awareness about the environment in order to plan effective response operations. Unmanned ground vehicles are well suited for this task but often require a strong communication link to a remote ground station to effectively relay information. When considering an obstacle-rich environment, non-line-of-sight conditions and naive navigation strategies can cause substantial degradations in radio link quality. Therefore, this thesis incorporates an unmanned aerial vehicle as a radio repeating node and presents a path planning strategy to cooperatively navigate the vehicle team so that radio link health is maintained. This navigation technique is formulated as an A*-based search and this thesis presents the formulation of this path planner as well as an investigation into strategies that provide computational efficiency to the search process. The path planner uses predictions of radio signal health at different vehicle configurations to effectively navigate the vehicles and simulations have shown that the path planner produces favorable results in comparison to several conceivable naive radio repeating variants. The results also show that the radio repeating path planner has outperformed the naive variants in both simulated environments and in field testing where a Yamaha RMAX unmanned helicopter and a ground vehicle were used as the vehicle team. Since A* is a general search process, this thesis also presents a roadway detection algorithm using A* and edge detection image processing techniques. This algorithm can supplement unmanned vehicle operations and has shown favorable performance for images with well-defined roadways.
Advanced Linear Model Predictive Control For Helicopter Shipboard Maneuvers
Greer, William Bryce (Virginia Tech, 2019-10-22)
This dissertation focuses on implementing and analyzing advanced methods of model predictive control to control helicopters into stable flight near a ship and perform a soft touchdown from that state. A shrinking horizon model predictive control method is presented which can target specific states at specific times and take into account several important factors during landing. This controller is then used in simulation to perform a touchdown maneuver on a ship for a helicopter by targeting a landed state at a specific time. Increasing levels of fidelity are considered in the simulations. Computational power required reduces the closer the helicopter starts to the landing pad. An infinite horizon model predictive controller which allows simultaneous cost on state tracking, control energy, and control rates and allows tracking of an arbitrary equilibrium to infinity is then presented. It is applied in simulation to control a helicopter initially in a random flight condition far from a ship to slowly transition to stable flight near the ship, holding an arbitrary rough position relative to the ship indefinitely at the end. Three different target positions are simulated. This infinite horizon control method can be used to prepare for landing procedures that desire starting with the helicopter in some specific position in close proximity to the landing pad, such as the finite horizon method of landing control described previously which should start with the helicopter close to the ship to reduce computation power required. A method of constructing a landing envelope is then presented and used to construct a landing envelope for the finite horizon landing controller. A pre-existing method of combining linear controllers to account for nonlinearity is then slightly modified and used on implementations of the finite horizon landing controller to make a control that takes into account some of the nonlinearity of the problem. This control is tested in simulation.
Aerodynamic and Electromechanical Design, Modeling and Implementation Of Piezocomposite Airfoils
Bilgen, Onur (Virginia Tech, 2010-08-02)
Piezoelectrics offer high actuation authority and sensing over a wide range of frequencies. A Macro-Fiber Composite is a type of piezoelectric device that offers structural flexibility and high actuation authority. A challenge with piezoelectric actuators is that they require high voltage input; however the low power consumption allows for relatively lightweight electronic components. Another challenge, for piezoelectric actuated aerodynamic surfaces, is found in operating a relatively compliant, thin structure (desirable for piezoceramic actuators) in situations where there are relatively high external (aerodynamic) forces. Establishing an aeroelastic configuration that is stiff enough to prevent flutter and divergence, but compliant enough to allow the range of available motion is the central challenge in developing a piezocomposite airfoil. The research proposed here is to analyze and implement novel electronic circuits and structural concepts that address these two challenges. Here, a detailed theoretical and experimental analysis of the aerodynamic and electromechanical systems that are necessary for a practical implementation of a piezocomposite airfoil is presented. First, the electromechanical response of Macro-Fiber Composite based unimorph and bimorph structures is analyzed. A distributed parameter electromechanical model is presented for interdigitated piezocomposite unimorph actuators. Necessary structural features that result in large electrically induced deformations are identified theoretically and verified experimentally. A novel, lightweight electrical circuitry is proposed and implemented to enable the peak-to-peak actuation of Macro-Fiber Composite bimorph devices with asymmetric voltage range. Next, two novel concepts of supporting the piezoelectric material are proposed to form two types of variable-camber aerodynamic surfaces. The first concept, a simply-supported thin bimorph airfoil, can take advantage of aerodynamic loads to reduce control input moments and increase control effectiveness. The structural boundary conditions of the design are optimized by solving a coupled fluid-structure interaction problem by using a structural finite element method and a panel method based on the potential flow theory for fluids. The second concept is a variable-camber thick airfoil with two cascading bimorphs and a compliant box mechanism. Using the structural and aerodynamic theoretical analysis, both variable-camber airfoil concepts are fabricated and successfully implemented on an experimental ducted-fan vehicle. A custom, fully automated low-speed wind tunnel and a load balance is designed and fabricated for experimental validation. The airfoils are evaluated in the wind tunnel for their two-dimensional lift and drag coefficients at low Reynolds number flow. The effects of piezoelectric hysteresis are identified. In addition to the shape control application, low Reynolds number flow control is examined using the cascading bimorph variable-camber airfoil. Unimorph type actuators are proposed for flow control in two unique concepts. Several electromechanical excitation modes are identified that result in the delay of laminar separation bubble and improvement of lift. Periodic excitation to the flow near the leading edge of the airfoil is used as the flow control method. The effects of amplitude, frequency and spanwise distribution of excitation are determined experimentally using the wind tunnel setup. Finally, the effects of piezoelectric hysteresis nonlinearity are identified for Macro-Fiber Composite bimorphs. The hysteresis is modeled for open-loop response using a phenomenological classical Preisach model. The classical Preisach model is capable of predicting the hysteresis observed in 1) two cantilevered bimorph beams, 2) the simply-supported thin airfoil, and 3) the cascading bimorph thick airfoil.
Application of Computer Vision Techniques for Railroad Inspection using UAVs
Harekoppa, Pooja Puttaswamygowda (Virginia Tech, 2016-08-16)
The task of railroad inspection is a tedious one. It requires a lot of skilled experts and long hours of frequent on-field inspection. Automated ground equipment systems that have been developed to address this problem have the drawback of blocking the rail service during inspection process. As an alternative, using aerial imagery from a UAV, Computer Vision and Machine Learning based techniques were developed in this thesis to analyze two kinds of defects on the rail tracks. The defects targeted were missing spikes on tie plates and cracks on ties. In order to perform this inspection, the rail region was identified in the image and then the tie plate and tie regions on the track were detected. These steps were performed using morphological operations, filtering and intensity analysis. Once the tie plate was localized, the regions of interest on the plate were used to train a machine learning model to recognize missing spikes. Classification using SVM resulted in an accuracy of around 96% and varied greatly based on the tie plate illumination and ROI alignment for Lampasas and Chickasha subdivision datasets. Also, many other different classifiers were used for training and testing and an ensemble method with majority vote scheme was also explored for classification. The second category of learning model used was a multi-layered neural network. The major drawback of this method was, it required a lot of images for training. However, it performed better than feature based classifiers with availability of larger training dataset. As a second kind of defect, tie conditions were analyzed. From the localized tie region, the tie cracks were detected using thresholding and morphological operations. A machine learning classifier was developed to predict the condition of a tie based on training examples of images with extracted features. The multi-class classification accuracy obtained was around 83% and there were no misclassifications seen between two extreme classes of tie condition on the test data.
Automated Landing Site Evaluation for Semi-Autonomous Unmanned Aerial Vehicles
Klomparens, Dylan (Virginia Tech, 2008-08-20)
A system is described for identifying obstacle-free landing sites for a vertical-takeoff-and-landing (VTOL) semi-autonomous unmanned aerial vehicle (UAV) from point cloud data obtained from a stereo vision system. The relatively inexpensive, commercially available Bumblebee stereo vision camera was selected for this study. A "point cloud viewer" computer program was written to analyze point cloud data obtained from 2D images transmitted from the UAV to a remote ground station. The program divides the point cloud data into segments, identifies the best-fit plane through the data for each segment, and performs an independent analysis on each segment to assess the feasibility of landing in that area. The program also rapidly presents the stereo vision information and analysis to the remote mission supervisor who can make quick, reliable decisions about where to safely land the UAV. The features of the program and the methods used to identify suitable landing sites are presented in this thesis. Also presented are the results of a user study that compares the abilities of humans and computer-supported point cloud analysis in certain aspects of landing site assessment. The study demonstrates that the computer-supported evaluation of potential landing sites provides an immense benefit to the UAV supervisor.
Automatic Dynamic Tracking of Horse Head Facial Features in Video Using Image Processing Techniques
Doyle, Jason Emory (Virginia Tech, 2019-02-11)
The wellbeing of horses is very important to their care takers, trainers, veterinarians, and owners. This thesis describes the development of a non-invasive image processing technique that allows for automatic detection and tracking of horse head and ear motion, respectively, in videos or camera feed, both of which may provide indications of horse pain, stress, or well-being. The algorithm developed here can automatically detect and track head motion and ear motion, respectively, in videos of a standing horse. Results demonstrating the technique for nine different horses are presented, where the data from the algorithm is utilized to plot absolute motion vs. time, velocity vs. time, and acceleration vs. time for the head and ear motion, respectively, of a variety of horses and ponies. Two-dimensional plotting of x and y motion over time is also presented. Additionally, results of pilot work in eye detection in light colored horses is also presented. Detection of pain in horses is particularly difficult because they are prey animals and have mechanisms to disguise their pain, and these instincts may be particularly strong in the presence of an unknown human, such as a veterinarian. Current state-of-the art for detecting pain in horses primarily involves invasive methods, such as heart rate monitors around the body, drawing blood for cortisol levels, and pressing on painful areas to elicit a response, although some work has been done for humans to sort and score photographs subjectively in terms of a "horse grimace scale." The algorithms developed in this thesis are the first that the author is aware for exploiting proven image processing approaches from other applications for development of an automatic tool for detection and tracking of horse facial indicators. The algorithms were done in common open source programs Python and OpenCV, and standard image processing approaches including Canny Edge detection Hue, Saturation, Value color filtering, and contour tracking were utilized in algorithm development. The work in this thesis provides the foundational development of a non -invasive and automatic detection and tracking program for horse head and ear motion, including demonstration of the viability of this approach using videos of standing horses. This approach lays the groundwork for robust tool development for monitoring horses non-invasively and without the required presence of humans in such applications as post-operative monitoring, foaling, evaluation of performance horses in competition and/or training, as well as for providing data for research on animal welfare, among other scenarios.
Automatic Positioning and Design of a Variable Baseline Stereo Boom
Fanto, Peter Louis (Virginia Tech, 2012-07-17)
Conventional stereo vision systems rely on two spatially fixed cameras to gather depth information about a scene. The cameras typically have a fixed distance between them, known as the baseline. As the baseline increases, the estimated 3D information becomes more accurate, which makes it advantageous to have as large a baseline as possible. However, large baselines have problems whenever objects approach the cameras. The objects begin to leave the field of view of the cameras, making it impossible to determine where they are located in 3D space. This becomes especially important if an object of interest must be actuated upon and is approached by a vehicle. In an attempt to overcome this limitation, this thesis introduces a variable baseline stereo system that can adjust its baseline automatically based on the location of an object of interest. This allows accurate depth information to be gathered when an object is both near and far. The system was designed to operate under, and automatically move to a large range of different baselines. This thesis presents the mechanical design of the stereo boom. This is followed by a derivation of a control scheme that adjusts the baseline based on an estimate object location, which is gathered from stereo vision. This algorithm ensures that a certain incident angle on an object of interest is never surpassed. This maximum angle is determined by where a stereo correspondence algorithm, Semi-Global Block Matching, fails to create full reconstructions.
Autonomous Aerial Localization of Radioactive Point Sources via Recursive Bayesian Estimation and Contour Analysis
Towler, Jerry Alwynne (Virginia Tech, 2011-06-16)
The rapid, accurate determination of the positions and strengths of sources of dangerous radioactivity takes high priority after a catastrophic event to ensure the safety of personnel, civilians, and emergency responders. This thesis presents approaches and algorithms to autonomously investigate radioactive material using an unmanned aerial vehicle. Performing this autonomous analysis comprises five major steps: ingress from a base of operations to the danger zone, initial detection of radioactive material, measurement of the strength of radioactive emissions, analysis of the data to provide position and intensity estimates, and finally egress from the area of interest back to the launch site. In all five steps, time is of critical importance: faster responses promise potentially saved lives. A time-optimal ingress and egress path planning method solves the first and last steps. Vehicle capabilities and instrument sensitivity inform the development of an efficient search path within the area of interest. Two algorithms—a grid-based recursive Bayesian estimator and a novel radiation contour analysis method—are presented to estimate the position of radioactive sources using simple gross gamma ray event count data from a nondirectional radiation detector. The latter procedure also correctly estimates the number of sources present and their intensities. Ultimately, a complete unsupervised mission is developed, requiring minimal initial operator interaction, that provides accurate characterization of the radiation environment of an area of interest as quickly as reasonably possible.
Autonomous Fire Suppression Using Feedback Control for Robotic Firefighting
McNeil, Joshua G. (Virginia Tech, 2016-02-04)
There is an increasing demand for robotics in dangerous and extreme conditions to limit human exposure and risk. An area in which robots are being considered as a support tool is in firefighting operations to reduce the number of firefighter injuries and deaths. One such application is to increase firefighting performance through localized fire suppression. This research focused on developing an autonomous suppression system for use on a mobile robotic platform. This included a real-time close proximity fire suppression approach, appropriate feature selection and probabilistic classification of water leaks and sprays, real-time trajectory estimation, and a feedback controller for error correction in longer-range firefighting. The close proximity suppression algorithm uses IR fire detection IR stereo processing to localize a fire. Feedback of the fire size and fire target was used to manipulate the nozzle for effective placement of the suppressant onto the fire and experimentally validated with tests in high and low visibility environments. To improve performance of autonomous suppression and for inspection tasks, identification of water sprays and leaks is a critical component. Bayesian classification was used to identify the features associated with water leaks and sprays in thermal images. Appropriate first and second order features were selected by using a multi-objective genetic algorithm optimization. Four textural features were selected as a method of discriminating water sprays and leaks from other non-water, high motion objects. Water classification was implemented into a real-time suppression system as a method of determining the yaw and pitch angle of a water nozzle. Estimation of the angle orientation provided an error estimate between the current path and desired nozzle orientation. A proportional-integral (PI) controller was used to correct for forced errors in fire targeting and performance and response was shown through indoor and outdoor suppression tests with wood-crib fires. The autonomous suppression algorithm was demonstrated through fire testing to be at least three times faster compared with suppression by an operator using tele-operation.
Autonomous Localization of 1/R² Sources Using an Aerial Platform
Brewer, Eric Thomas (Virginia Tech, 2009-12-09)
Unmanned vehicles are often used in time-critical missions such as reconnaissance or search and rescue. To this end, this thesis provides autonomous localization and mapping tools for 1/R² sources. A "1/R²" source is one in which the received intensity of the source is inversely proportional to the square of the distance from the source. An autonomous localization algorithm is developed which utilizes a particle swarm particle ltering method to recursively estimate the location of a source. To implement the localization algorithm experimentally, a command interface with Virginia Tech's autonomous helicopter was developed. The interface accepts state information from the helicopter, and returns command inputs to drive the helicopter autonomously to the source. To make the use of the system more intuitive, a graphical user interface was developed which provides localization functionality as well as a waypoint navigation outer-loop controller for the helicopter. This assists in positioning the helicopter and returning it home after the the algorithm is completed. An autonomous mapping mission with a radioactive source is presented, along with a localization experiment utilizing simulated sensor readings. This work is the rst phase of an on-going project at the Unmanned Systems Lab. Accordingly, this thesis also provides a framework for its continuation in the next phase of the project.
Autonomous Navigation, Perception and Probabilistic Fire Location for an Intelligent Firefighting Robot
Kim, Jong Hwan (Virginia Tech, 2014-10-09)
Firefighting robots are actively being researched to reduce firefighter injuries and deaths as well as increase their effectiveness on performing tasks. There has been difficulty in developing firefighting robots that autonomously locate a fire inside of a structure that is not in the direct robot field of view. The commonly used sensors for robots cannot properly function in fire smoke-filled environments where high temperature and zero visibility are present. Also, the existing obstacle avoidance methods have limitations calculating safe trajectories and solving local minimum problem while avoiding obstacles in real time under cluttered and dynamic environments. In addition, research for characterizing fire environments to provide firefighting robots with proper headings that lead the robots to ultimately find the fire is incomplete. For use on intelligent firefighting robots, this research developed a real-time local obstacle avoidance method, local dynamic goal-based fire location, appropriate feature selection for fire environment assessment, and probabilistic classification of fire, smoke and their thermal reflections. The real-time local obstacle avoidance method called the weighted vector method is developed to perceive the local environment through vectors, identify suitable obstacle avoidance modes by applying a decision tree, use weighting functions to select necessary vectors and geometrically compute a safe heading. This method also solves local obstacle avoidance problems by integrating global and local goals to reach the final goal. To locate a fire outside of the robot field of view, a local dynamic goal-based 'Seek-and-Find' fire algorithm was developed by fusing long wave infrared camera images, ultraviolet radiation sensor and Lidar. The weighted vector method was applied to avoid complex static and unexpected dynamic obstacles while moving toward the fire. This algorithm was successfully validated for a firefighting robot to autonomously navigate to find a fire outside the field of view. An improved 'Seek-and-Find' fire algorithm was developed using Bayesian classifiers to identify fire features using thermal images. This algorithm was able to discriminate fire and smoke from thermal reflections and other hot objects, allowing the prediction of a more robust heading for the robot. To develop this algorithm, appropriate motion and texture features that can accurately identify fire and smoke from their reflections were analyzed and selected by using multi-objective genetic algorithm optimization. As a result, mean and variance of intensity, entropy and inverse difference moment in the first and second order statistical texture features were determined to probabilistically classify fire, smoke, their thermal reflections and other hot objects simultaneously. This classification performance was measured to be 93.2% accuracy based on validation using the test dataset not included in the original training dataset. In addition, the precision, recall, F-measure, and G-measure were 93.5 - 99.9% for classifying fire and smoke using the test dataset.
Autonomous Sample Collection Using Image-Based 3D Reconstructions
Torok, Matthew M. (Virginia Tech, 2012-04-26)
Sample collection is a common task for mobile robots and there are a variety of manipulators available to perform this operation. This thesis presents a novel scoop sample collection system design which is able to both collect and contain a sample using the same hardware. To ease the operator burden during sampling the scoop system is paired with new semi-autonomous and fully autonomous collection techniques. These are derived from data provided by colored 3D point clouds produced via image-based 3D reconstructions. A custom robotic mobility platform, the Scoopbot, is introduced to perform completely automated imaging of the sampling area and also to pick up the desired sample. The Scoopbot is wirelessly controlled by a base station computer which runs software to create and analyze the 3D point cloud models. Relevant sample parameters, such as dimensions and volume, are calculated from the reconstruction and reported to the operator. During tests of the system in full (48 images) and fast (6-8 images) modes the Scoopbot was able to identify and retrieve a sample without any human intervention. Finally, a new building crack detection algorithm (CDA) is created to use the 3D point cloud outputs from image sets gathered by a mobile robot. The CDA was shown to successfully identify and color-code several cracks in a full-scale concrete building element.
Autonomous Source Localization
Peterson, John Ryan (Virginia Tech, 2020-05-01)
This work discusses the algorithms and implementation of a multi-robot system for locating radioactive sources. The estimation algorithm presented in this work is able to fuse measurements collected by γ-ray spectrometers carried by an unmanned aerial and unmanned ground vehicle into a single consistent estimate of the probability distribution over the position of a point source in an environment. By constructing a set of hypotheses on the position of the point source, this method converts a non-linear problem into many independent linear ones. Since the underlying model is probabilistic, candidate paths may be evaluated by their expected reduction in uncertainty, allowing the algorithm to select good paths for vehicles to take. An initial hardware test conducted at Savannah River National Laboratory served as a proof of concept and demonstrated that the algorithm successfully locates a radioactive source in the environment, and moves the vehicle to that location. This approach also demonstrated the capability to utilize radiation data collected from an unmanned aerial vehicle to aid the ground vehicle’s exploration. Subsequent numerical experiments characterized the performance of several reward functions and different exploration algorithms in scenarios covering a range of source strengths and region sizes. These experiments demonstrated the improved performance of planning-based algorithms over the myopic method initially tested in the hardware experiments.
Beyond LiDAR for Unmanned Aerial Event-Based Localization in GPS Denied Environments
Mayalu Jr, Alfred Kulua (Virginia Tech, 2021-06-23)
Finding lost persons, collecting information in disturbed communities, efficiently traversing urban areas after a blast or similar catastrophic events have motivated researchers to develop intelligent sensor frameworks to aid law enforcement, first responders, and military personnel with situational awareness. This dissertation consists of a two-part framework for providing situational awareness using both acoustic ground sensors and aerial sensing modalities. Ground sensors in the field of data-driven detection and classification approaches typically rely on computationally expensive inputs such as image or video-based methods [6, 91]. However, the information given by an acoustic signal offers several advantages, such as low computational needs and possible classification of occluded events including gunshots or explosions. Once an event is identified, responding to real-time events in urban areas is difficult using an Unmanned Aerial Vehicle (UAV) especially when GPS is unreliable due to coverage blackouts and/or GPS degradation [10]. Furthermore, if it is possible to deploy multiple in-situ static intelligent acoustic autonomous sensors that can identify anomalous sounds given context, then the sensors can communicate with an autonomous UAV that can navigate in a GPS-denied urban environment for investigation of the event; this could offer several advantages for time-critical and precise, localized response information necessary for life-saving decision-making. Thus, in order to implement a complete intelligent sensor framework, the need for both an intelligent static ground acoustic autonomous unattended sensors (AAUS) and improvements to GPS-degraded localization has become apparent for applications such as anomaly detection, public safety, as well as intelligence surveillance and reconnaissance (ISR) operations. Distributed AAUS networks could provide end-users with near real-time actionable information for large urban environments with limited resources. Complete ISR mission profiles require a UAV to fly in GPS challenging or denied environments such as natural or urban canyons, at least in a part of a mission. This dissertation addresses, 1) the development of intelligent sensor framework through the development of a static ground AAUS capable of machine learning for audio feature classification and 2) GPS impaired localization through a formal framework for trajectory-based flight navigation for unmanned aircraft systems (UAS) operating BVLOS in low-altitude urban airspace. Our AAUS sensor method utilizes monophonic sound event detection in which the sensor detects, records, and classifies each event utilizing supervised machine learning techniques [90]. We propose a simulated framework to enhance the performance of localization in GPS-denied environments. We do this by using a new representation of 3D geospatial data using planar features that efficiently capture the amount of information required for sensor-based GPS navigation in obstacle-rich environments. The results from this dissertation would impact both military and civilian areas of research with the ability to react to events and navigate in an urban environment.
Broadband World Modeling and Scene Reconstruction
Goldman, Benjamin Joseph (Virginia Tech, 2013-05-24)
Perception is a key feature in how any creature or autonomous system relates to its environment. While there are many types of perception, this thesis focuses on the improvement of the visual robotics perception systems. By implementing a broadband passive sensing system in conjunction with current perception algorithms, this thesis explores scene reconstruction and world modeling. The process involves two main steps. The first is stereo correspondence using block matching algorithms with filtering to improve the quality of this matching process. The disparity maps are then transformed into 3D point clouds. These point clouds are filtered again before the registration process is done. The registration uses a SAC-IA matching technique to align the point clouds with minimum error. The registered final cloud is then filtered again to smooth and down sample the large amount of data. This process was implemented through software architecture that utilizes Qt, OpenCV, and Point Cloud Library. It was tested using a variety of experiments on each of the components of the process. It shows promise for being able to replace or augment existing UGV perception systems in the future.
Characterization of Oscillatory Lift in MFC Airfoils
Lang Jr, Joseph Reagle (Virginia Tech, 2014-11-25)
The purpose of this research is to characterize the response of an airfoil with an oscillatory morphing, Macro-fiber composite (MFC) trailing edge. Correlation of the airfoil lift with the oscillatory input is presented. Modal analysis of the test airfoil and apparatus is used to determine the frequency response function. The effects of static MFC inputs on the FRF are presented and compared to the unactuated airfoil. The transfer function is then used to determine the lift component due to cambering and extract the inertial components from oscillating airfoil. Finally, empirical wind tunnel data is modeled and used to simulate the deflection of airfoil surfaces during dynamic testing conditions. This research serves to combine modal analysis, empirical modeling, and aerodynamic testing of MFC driven, oscillating lift to formulate a model of a dynamic, loaded morphing airfoil.
Classification of Faults in Railway Ties Using Computer Vision and Machine Learning
Kulkarni, Amruta Kiran (Virginia Tech, 2017-06-30)
This work focuses on automated classification of railway ties based on their condition using aerial imagery. Four approaches are explored and compared to achieve this goal - handcrafted features, HOG features, transfer learning and proposed CNN architecture. Mean test accuracy per class and Quadratic Weighted Kappa score are used as performance metrics, particularly suited for the ordered classification in this work. Transfer learning approach outperforms the handcrafted features and HOG features by a significant margin. The proposed CNN architecture caters to the unique nature of the railway tie images and their defects. The performance of this approach is superior to the handcrafted and HOG features. It also shows a significant reduction in the number of parameters as compared to the transfer learning approach. Data augmentation boosts the performance of all approaches. The problem of label noise is also analyzed. The techniques proposed in this work will help in reducing the time, cost and dependency on experts involved in traditional railway tie inspections and will facilitate efficient documentation and planning for maintenance of railway ties.
Collaborative Unmanned Air and Ground Vehicle Perception for Scene Understanding, Planning and GPS-denied Localization
Christie, Gordon A. (Virginia Tech, 2017-01-05)
Autonomous robot missions in unknown environments are challenging. In many cases, the systems involved are unable to use a priori information about the scene (e.g. road maps). This is especially true in disaster response scenarios, where existing maps are now out of date. Areas without GPS are another concern, especially when the involved systems are tasked with navigating a path planned by a remote base station. Scene understanding via robots' perception data (e.g. images) can greatly assist in overcoming these challenges. This dissertation makes three contributions that help overcome these challenges, where there is a focus on the application of autonomously searching for radiation sources with unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) in unknown and unstructured environments. The three main contributions of this dissertation are: (1) An approach to overcome the challenges associated with simultaneously trying to understand 2D and 3D information about the environment. (2) Algorithms and experiments involving scene understanding for real-world autonomous search tasks. The experiments involve a UAV and a UGV searching for potentially hazardous sources of radiation is an unknown environment. (3) An approach to the registration of a UGV in areas without GPS using 2D image data and 3D data, where localization is performed in an overhead map generated from imagery captured in the air.
A Collection of Computer Vision Algorithms Capable of Detecting Linear Infrastructure for the Purpose of UAV Control
Smith, Evan McLean (Virginia Tech, 2016-07-06)
One of the major application areas for UAVs is the automated traversing and inspection of infrastructure. Much of this infrastructure is linear, such as roads, pipelines, rivers, and railroads. Rather than hard coding all of the GPS coordinates along these linear components into a flight plan for the UAV to follow, one could take advantage of computer vision and machine learning techniques to detect and travel along them. With regards to roads and railroads, two separate algorithms were developed to detect the angle and distance offset of the UAV from these linear infrastructure components to serve as control inputs for a flight controller. The road algorithm relied on applying a Gaussian SVM to segment road pixels from rural farmland using color plane and texture data. This resulted in a classification accuracy of 96.6% across a 62 image dataset collected at Kentland Farm. A trajectory can then be generated by fitting the classified road pixels to polynomial curves. These trajectories can even be used to take specific turns at intersections based on a user defined turn direction and have been proven through hardware-in-the-loop simulation to produce a mean cross track error of only one road width. The combined segmentation and trajectory algorithm was then implemented on a PC (i7-4720HQ 2.6 GHz, 16 GB RAM) at 6.25 Hz and a myRIO 1900 at 1.5 Hz proving its capability for real time UAV control. As for the railroad algorithm, template matching was first used to detect railroad patterns. Upon detection, a region of interest around the matched pattern was used to guide a custom edge detector and Hough transform to detect the straight lines on the rails. This algorithm has been shown to detect rails correctly, and thus the angle and distance offset error, on all images related to the railroad pattern template and can run at 10 Hz on the aforementioned PC.

Browsing by Author "Kochersberger, Kevin B."

Results Per Page

Sort Options