Matching Items (9)
Filtering by
- Creators: Arizona State University
- Creators: Li, Baoxin
Description
The exponential rise in unmanned aerial vehicles has necessitated the need for accurate pose estimation under any extreme conditions. Visual Odometry (VO) is the estimation of position and orientation of a vehicle based on analysis of a sequence of images captured from a camera mounted on it. VO offers a cheap and relatively accurate alternative to conventional odometry techniques like wheel odometry, inertial measurement systems and global positioning system (GPS). This thesis implements and analyzes the performance of a two camera based VO called Stereo based visual odometry (SVO) in presence of various deterrent factors like shadows, extremely bright outdoors, wet conditions etc... To allow the implementation of VO on any generic vehicle, a discussion on porting of the VO algorithm to android handsets is presented too. The SVO is implemented in three steps. In the first step, a dense disparity map for a scene is computed. To achieve this we utilize sum of absolute differences technique for stereo matching on rectified and pre-filtered stereo frames. Epipolar geometry is used to simplify the matching problem. The second step involves feature detection and temporal matching. Feature detection is carried out by Harris corner detector. These features are matched between two consecutive frames using the Lucas-Kanade feature tracker. The 3D co-ordinates of these matched set of features are computed from the disparity map obtained from the first step and are mapped into each other by a translation and a rotation. The rotation and translation is computed using least squares minimization with the aid of Singular Value Decomposition. Random Sample Consensus (RANSAC) is used for outlier detection. This comprises the third step. The accuracy of the algorithm is quantified based on the final position error, which is the difference between the final position computed by the SVO algorithm and the final ground truth position as obtained from the GPS. The SVO showed an error of around 1% under normal conditions for a path length of 60 m and around 3% in bright conditions for a path length of 130 m. The algorithm suffered in presence of shadows and vibrations, with errors of around 15% and path lengths of 20 m and 100 m respectively.
ContributorsDhar, Anchit (Author) / Saripalli, Srikanth (Thesis advisor) / Li, Baoxin (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2010
Description
A Graph Neural Network (GNN) is a type of neural network architecture that operates on data consisting of objects and their relationships, which are represented by a graph. Within the graph, nodes represent objects and edges represent associations between those objects. The representation of relationships and correlations between data is unique to graph structures. GNNs exploit this feature of graphs by augmenting both forms of data, individual and relational, and have been designed to allow for communication and sharing of data within each neural network layer. These benefits allow each node to have an enriched perspective, or a better understanding, of its neighbouring nodes and its connections to those nodes. The ability of GNNs to efficiently process high-dimensional node data and multi-faceted relationships among nodes gives them advantages over neural network architectures such as Convolutional Neural Networks (CNNs) that do not implicitly handle relational data. These quintessential characteristics of GNN models make them suitable for solving problems in which the correspondences among input data are needed to produce an accurate and precise representation of these data. GNN frameworks may significantly improve existing communication and control techniques for multi-agent tasks by implicitly representing not only information associated with the individual agents, such as agent position, velocity, and camera data, but also their relationships with one another, such as distances between the agents and their ability to communicate with one another. One such task is a multi-agent navigation problem in which the agents must coordinate with one another in a decentralized manner, using proximity sensors only, to navigate safely to their intended goal positions in the environment without collisions or deadlocks. The contribution of this thesis is the design of an end-to-end decentralized control scheme for multi-agent navigation that utilizes GNNs to prevent inter-agent collisions and deadlocks. The contributions consist of the development, simulation and evaluation of the performance of an advantage actor-critic (A2C) reinforcement learning algorithm that employs actor and critic networks for training that simultaneously approximate the policy function and value function, respectively. These networks are implemented using GNN frameworks for navigation by groups of 3, 5, 10 and 15 agents in simulated two-dimensional environments. It is observed that in $40\%$ to $50\%$ of the simulation trials, between 70$\%$ to 80$\%$ of the agents reach their goal positions without colliding with other agents or becoming trapped in deadlocks. The model is also compared to a random run simulation, where actions are chosen randomly for the agents and observe that the model performs notably well for smaller groups of agents.
ContributorsAyalasomayajula, Manaswini (Author) / Berman, Spring (Thesis advisor) / Mian, Sami (Committee member) / Pavlic, Theodore (Committee member) / Arizona State University (Publisher)
Created2022
Description
Pollinator populations globally have declined at concerning rates in recent years, which is problematic given that roughly a third of all food production depends on them. Managed honey bee colony losses in particular have alarmed beekeepers and scientists, especially in the United States. Widespread agrochemical use has been implicated as one of the major causes of these colony losses. While the lethal effects of agrochemicals often receive the most attention, sublethal effects can occur at lower doses and can substantially weaken colonies over time. Impaired associative learning ability is a sublethal effect of a number of agrochemicals, and is particularly concerning, as it may hinder the abilities of bees to forage for food or find their way back to the colony. Here, I focus on the fungicide Pristine® (active ingredients: 25.2% boscalid, 12.8% pyraclostrobin), which is sprayed on honey bee-pollinated crops during bloom and is known to poison bee mitochondria at ppm levels. First, I show that Pristine® impairs performance on an associative learning assay in the laboratory. Next, I show that Pristine® alters carbohydrate absorption in honey bees, providing a possible mechanism underlying this impaired learning performance. Finally, I demonstrate that Pristine® interacts with high temperatures to induce homing failure in exposed bees. My results raise concerns that this common fungicide may not be safe for pollinators and will be relevant to policymakers as they make decisions surrounding the regulation of fungicide use in agriculture.
ContributorsDesJardins, Nicole (Author) / Harrison, Jon F (Thesis advisor) / Smith, Brian H (Thesis advisor) / DeGrandi-Hoffman, Gloria (Committee member) / DeNardo, Dale (Committee member) / Pratt, Stephen (Committee member) / Arizona State University (Publisher)
Created2023
Description
Autonomous Robots have a tremendous potential to assist humans in environmental monitoring tasks. In order to generate meaningful data for humans to analyze, the robots need to collect accurate data and develop reliable representation of the environment. This is achieved by employing scalable and robust navigation and mapping algorithms that facilitate acquiring and understanding data collected from the array of on-board sensors. To this end, this thesis presents navigation and mapping algorithms for autonomous robots that can enable robot navigation in complexenvironments and develop real time semantic map of the environment respectively. The first part of the thesis presents a novel navigation algorithm for an autonomous underwater vehicle that can maintain a fixed distance from the coral terrain while following a human diver. Following a human diver ensures that the robot would visit all important sites in the coral reef while maintaining a constant distance from the terrain reduces heterscedasticity in the measurements. This algorithm was tested on three different synthetic terrains including a real model of a coral reef in Hawaii. The second part of the thesis presents a dense semantic surfel mapping technique based on top of a popular surfel mapping algorithm that can generate meaningful maps in real time. A semantic mask from a depth aligned RGB-D camera was used to assign labels
to the surfels which were then probabilistically updated with multiple measurements. The mapping algorithm was tested with simulated data from an RGB-D camera and the results were analyzed.
ContributorsAntervedi, Lakshmi Gana Prasad (Author) / Das, Jnaneshwar (Thesis advisor) / Martin, Roberta E (Committee member) / Marvi, Hamid (Committee member) / Arizona State University (Publisher)
Created2021
Description
A lot of strides have been made in enabling technologies to aid individuals with visual impairment live an independent life. The advent of smart devices and participatory web has especially facilitated the possibility of new interactions to aide everyday tasks. Current systems however tend to be complex and require multiple cumbersome devices which invariably come with steep learning curves. Building new cyber-human systems with simple integrated interfaces while keeping in mind the specific requirements of the target users would help alleviate their mundane yet significant daily needs. Navigation is one such significant need that forms an integral part of everyday life and is one of the areas where individuals with visual impairment face the most discomfort. There is little technology out there to help travelers with navigating new routes. A number of research prototypes have been proposed but none of them are available to the general population. This may be due to the need for special equipment that needs expertise before deployment, or trained professionals needing to calibrate devices or because of the fact that the systems are just not scalable. Another area that needs assistance is the field of education. Lot of the classroom material and textbook material is not readily available in alternate formats for use. Another such area that requires attention is information delivery in the age of web 2.0. Popular websites like Facebook, Amazon, etc are designed with sighted people as target audience. While the mobile editions with their pared down versions make it easier to navigate with screen readers, the truth remains that there is still a long way to go in making such websites truly accessible.
ContributorsPaladugu, Devi Archana (Author) / Li, Baoxin (Thesis advisor) / Hedgpeth, Terri (Committee member) / Atkinson, Robert (Committee member) / Walker, Erin (Committee member) / Arizona State University (Publisher)
Created2016
Description
As a promising solution to the problem of acquiring and storing large amounts of image and video data, spatial-multiplexing camera architectures have received lot of attention in the recent past. Such architectures have the attractive feature of combining a two-step process of acquisition and compression of pixel measurements in a conventional camera, into a single step. A popular variant is the single-pixel camera that obtains measurements of the scene using a pseudo-random measurement matrix. Advances in compressive sensing (CS) theory in the past decade have supplied the tools that, in theory, allow near-perfect reconstruction of an image from these measurements even for sub-Nyquist sampling rates. However, current state-of-the-art reconstruction algorithms suffer from two drawbacks -- They are (1) computationally very expensive and (2) incapable of yielding high fidelity reconstructions for high compression ratios. In computer vision, the final goal is usually to perform an inference task using the images acquired and not signal recovery. With this motivation, this thesis considers the possibility of inference directly from compressed measurements, thereby obviating the need to use expensive reconstruction algorithms. It is often the case that non-linear features are used for inference tasks in computer vision. However, currently, it is unclear how to extract such features from compressed measurements. Instead, using the theoretical basis provided by the Johnson-Lindenstrauss lemma, discriminative features using smashed correlation filters are derived and it is shown that it is indeed possible to perform reconstruction-free inference at high compression ratios with only a marginal loss in accuracy. As a specific inference problem in computer vision, face recognition is considered, mainly beyond the visible spectrum such as in the short wave infra-red region (SWIR), where sensors are expensive.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2015
Description
The physical environment influences the physiology, psychology, and the societal interactions of those who experience it. The environment can also influence human behavior. Critical care nurses are in constant interaction with the physical environment surrounding their patients. High acuity ICU patients are vulnerable and at risk for harm, infection, and poor outcomes while the physical and cognitive workload of nurses presents a demanding and continuous challenge.
The goal of this qualitative study was to explore and understand the way critical care nurses navigate within the patient room and interact with its features. The study of critical care nurses interacting with the patient room environment was conducted in five critical care units at three tertiary care institutions in the Eastern United States, along with another unit in the pilot study at a community hospital in the Southwest United States. Nurses were observed in their typical work environment as they performed normal tasks and patient care activities for entire day and night shifts. The study involved ethnographic field observations, individual semi-structured participant interviews, and examination of photographs and floor plans.
The exploratory study resulted in a comprehensive model for nurse navigation that includes both cognitive and action components, along with a conceptual framework for nurse behavioral activity. Repetitive patterns of nurse movement were identified and named. The findings produced recommendations for nurses’ effective use of space and architectural design of ICU patient rooms to improve patient outcomes.
The goal of this qualitative study was to explore and understand the way critical care nurses navigate within the patient room and interact with its features. The study of critical care nurses interacting with the patient room environment was conducted in five critical care units at three tertiary care institutions in the Eastern United States, along with another unit in the pilot study at a community hospital in the Southwest United States. Nurses were observed in their typical work environment as they performed normal tasks and patient care activities for entire day and night shifts. The study involved ethnographic field observations, individual semi-structured participant interviews, and examination of photographs and floor plans.
The exploratory study resulted in a comprehensive model for nurse navigation that includes both cognitive and action components, along with a conceptual framework for nurse behavioral activity. Repetitive patterns of nurse movement were identified and named. The findings produced recommendations for nurses’ effective use of space and architectural design of ICU patient rooms to improve patient outcomes.
ContributorsHamilton, D. Kirk (Author) / Lamb, Gerri (Thesis advisor) / Fleury, Julie (Committee member) / Gurses, Ayse (Committee member) / Arizona State University (Publisher)
Created2017
Description
Limited spectral access motivates technologies that adapt to diminishing resources and increasingly cluttered environments. A joint positioning-communications system is designed and implemented on \acf{COTS} hardware. This system enables simultaneous positioning of, and communications between, nodes in a distributed network of base-stations and unmanned aerial systems (UASs). This technology offers extreme ranging precision ($<$ 5 cm) with minimal bandwidth (10 MHz), a secure communications link to protect against cyberattacks, a small form factor that enables integration into numerous platforms, and minimal resource consumption which supports high-density networks. The positioning and communications tasks are performed simultaneously with a single, co-use waveform, which efficiently utilizes limited resources and supports higher user densities. The positioning task uses a cooperative, point-to-point synchronization protocol to estimate the relative position and orientation of all users within the network. The communications task distributes positioning information between users and secures the positioning task against cyberattacks. This high-performance system is enabled by advanced time-of-arrival estimation techniques and a modern phase-accurate distributed coherence synchronization algorithm. This technology may be installed in ground-stations, ground vehicles, unmanned aerial systems, and airborne vehicles, enabling a highly-mobile, re-configurable network with numerous applications.
ContributorsHerschfelt, Andrew (Author) / Bliss, Daniel W (Thesis advisor) / Cochran, Douglas (Committee member) / Richmond, Christ (Committee member) / Alkhateeb, Ahmed (Committee member) / Arizona State University (Publisher)
Created2019
Description
Unmanned aerial systems (UASs) have recently enabled novel applications such as passenger transport and package delivery, but are increasingly vulnerable to cyberattack and therefore difficult to certify. Legacy systems such as GPS provide these capabilities extremely well, but are sensitive to spoofing and hijacking. An alternative intelligent transport system (ITS) was developed that provides highly secure communications, positioning, and timing synchronization services to networks of cooperative RF users, termed Communications and High-Precision Positioning (CHP2) system. This technology was implemented on consumer-off-the-shelf (COTS) hardware and it offers rapid (<100 ms) and precise (<5 cm) positioning capabilities in over-the-air experiments using flexible ground stations and UAS platforms using limited bandwidth (10 MHz). In this study, CHP2 is considered in the context of safety-critical and resource limited transport applications and urban air mobility. The two-way ranging (TWR) protocol over a joint positioning-communications waveform enables distributed coherence and time-of-flight(ToF) estimation. In a multi-antenna setup, the cross-platform ranging on participating nodes in the network translate to precise target location and orientation. In the current form, CHP2 necessitates a cooperative timing exchange at regular intervals. Dynamic resource management supports higher user densities by constantly renegotiating spectral access depending on need and opportunity. With these novel contributions to the field of integrated positioning and communications, CHP2 is a suitable candidate to provide both communications, navigation, and surveillance (CNS) and alternative positioning, navigation, and timing (APNT) services for high density safety-critical transport applications on a variety of vehicular platforms.
ContributorsSrinivas, Sharanya (Author) / Bliss, Daniel W. (Thesis advisor) / Richmond, Christ D. (Committee member) / Chakrabarti, Chaitali (Committee member) / Alkhateeb, Ahmed (Committee member) / Arizona State University (Publisher)
Created2020