Matching Items (13)
Filtering by
- All Subjects: Mechanical Engineering
- All Subjects: Information retrieval
- Genre: Academic theses
Description
K-Nearest-Neighbors (KNN) search is a fundamental problem in many application domains such as database and data mining, information retrieval, machine learning, pattern recognition and plagiarism detection. Locality sensitive hash (LSH) is so far the most practical approximate KNN search algorithm for high dimensional data. Algorithms such as Multi-Probe LSH and LSH-Forest improve upon the basic LSH algorithm by varying hash bucket size dynamically at query time, so these two algorithms can answer different KNN queries adaptively. However, these two algorithms need a data access post-processing step after candidates' collection in order to get the final answer to the KNN query. In this thesis, Multi-Probe LSH with data access post-processing (Multi-Probe LSH with DAPP) algorithm and LSH-Forest with data access post-processing (LSH-Forest with DAPP) algorithm are improved by replacing the costly data access post-processing (DAPP) step with a much faster histogram-based post-processing (HBPP). Two HBPP algorithms: LSH-Forest with HBPP and Multi- Probe LSH with HBPP are presented in this thesis, both of them achieve the three goals for KNN search in large scale high dimensional data set: high search quality, high time efficiency, high space efficiency. None of the previous KNN algorithms can achieve all three goals. More specifically, it is shown that HBPP algorithms can always achieve high search quality (as good as LSH-Forest with DAPP and Multi-Probe LSH with DAPP) with much less time cost (one to several orders of magnitude speedup) and same memory usage. It is also shown that with almost same time cost and memory usage, HBPP algorithms can always achieve better search quality than LSH-Forest with random pick (LSH-Forest with RP) and Multi-Probe LSH with random pick (Multi-Probe LSH with RP). Moreover, to achieve a very high search quality, Multi-Probe with HBPP is always a better choice than LSH-Forest with HBPP, regardless of the distribution, size and dimension number of the data set.
ContributorsYu, Renwei (Author) / Candan, Kasim S (Thesis advisor) / Sapino, Maria L (Committee member) / Chen, Yi (Committee member) / Sundaram, Hari (Committee member) / Arizona State University (Publisher)
Created2011
Description
In the development of autonomous ground vehicles (AGVs), how to guarantee vehicle lateral stability is one of the most critical aspects. Based on nonlinear vehicle lateral and tire dynamics, new driving requirements of AGVs demand further studies and analyses of vehicle lateral stability control strategies. To achieve comprehensive analyses and stability-guaranteed vehicle lateral driving control, this dissertation presents three main contributions.First, a new method is proposed to estimate and analyze vehicle lateral driving stability regions, which provide a direct and intuitive demonstration for stability control of AGVs. Based on a four-wheel vehicle model and a nonlinear 2D analytical LuGre tire model, a local linearization method is applied to estimate vehicle lateral driving stability regions by analyzing vehicle local stability at each operation point on a phase plane. The obtained stability regions are conservative because both vehicle and tire stability are simultaneously considered. Such a conservative feature is specifically important for characterizing the stability properties of AGVs.
Second, to analyze vehicle stability, two novel features of the estimated vehicle lateral driving stability regions are studied. First, a shifting vector is formulated to explicitly describe the shifting feature of the lateral stability regions with respect to the vehicle steering angles. Second, dynamic margins of the stability regions are formulated and applied to avoid the penetration of vehicle state trajectory with respect to the region boundaries. With these two features, the shiftable stability regions are feasible for real-time stability analysis.
Third, to keep the vehicle states (lateral velocity and yaw rate) always stay in the shiftable stability regions, different control methods are developed and evaluated. Based on different vehicle control configurations, two dynamic sliding mode controllers (SMC) are designed. To better control vehicle stability without suffering chattering issues in SMC, a non-overshooting model predictive control is proposed and applied. To further save computational burden for real-time implementation, time-varying control-dependent invariant sets and time-varying control-dependent barrier functions are proposed and adopted in a stability-guaranteed vehicle control problem.
Finally, to validate the correctness and effectiveness of the proposed theories, definitions, and control methods, illustrative simulations and experimental results are presented and discussed.
ContributorsHuang, Yiwen (Author) / Chen, Yan (Thesis advisor) / Lee, Hyunglae (Committee member) / Ren, Yi (Committee member) / Yong, Sze Zheng (Committee member) / Zhang, Wenlong (Committee member) / Arizona State University (Publisher)
Created2021
Description
The need for autonomous cars has never been more vital, and for a vehicle to be completely autonomous, multiple components must work together, one of which is the capacity to park at the end of a mission. This thesis project aims to design and execute an automated parking assist system (APAS). Traditional Automated parking assist systems (APAS) may not be effective in some constrained urban parking environments because of the parking space dimension. The thesis proposes a novel four-wheel steering (4-WS) vehicle for automated parallel parking to overcome this kind of challenge. Then, benefiting from the maneuverability enabled by the 4WS system, the feasible initial parking area is vastly expanded from those for the conventional 2WS vehicles. In addition, the expanded initial area is divided into four areas where different paths are planned correspondingly. In the proposed novel APAS first, a suitable parking space is identified through ultra-sonic sensors, which are mounted around the vehicle, and then depending upon the vehicle's initial position, various compact and smooth parallel parking paths are generated. An optimization function is built to get the smoothest (i.e., the smallest steering angle change and the shortest path) parallel parking path. With the full utilization of the 4WS system, the proposed path planning algorithm can allow a larger initial parking area that can be easily tracked by the 4WS vehicles. The proposed APAS for 4WS vehicles makes the automatic parking process in restricted spaces efficient. To verify the feasibility and effectiveness of the proposed APAS, a 4WS vehicle prototype is applied for validation through both simulation and experiment results.
ContributorsGujarathi, Kaushik Kumar (Author) / Chen, Yan (Thesis advisor) / Yong, Sze Zheng (Committee member) / Ren, Yi (Committee member) / Arizona State University (Publisher)
Created2022
Description
The introduction of assistive/autonomous features in cyber-physical systems, e.g., self-driving vehicles, have paved the way to a relatively new field of system analysis for safety-critical applications, along with the topic of controlling systems with performance and safety guarantees. The different works in this thesis explore and design methodologies that focus on the analysis of nonlinear dynamical systems via set-membership approximations, as well as the development of controllers and estimators that can give worst-case performance guarantees, especially when the sensor data containing information on system outputs is prone to data drops and delays. For analyzing the distinguishability of nonlinear systems, building upon the idea of set membership over-approximation of the nonlinear systems, a novel optimization-based method for multi-model affine abstraction (i.e., simultaneous set-membership over-approximation of multiple models) is designed. This work solves for the existence of set-membership over-approximations of a pair of different nonlinear models such that the different systems can be distinguished/discriminated within a guaranteed detection time under worst-case uncertainties and approximation errors. Specifically, by combining mesh-based affine abstraction methods with T-distinguishability analysis in the literature yields a bilevel bilinear optimization problem, whereby leveraging robust optimization techniques and a suitable change of variables result in a sufficient linear program that can obtain a tractable solution with T-distinguishability guarantees. Moreover, the thesis studied the designs of controllers and estimators with performance guarantees, and specifically, path-dependent feedback controllers and bounded-error estimators for time-varying affine systems are proposed that are subject to delayed observations or missing data. To model the delayed/missing data, two approaches are explored; a fixed-length language and an automaton-based model. Furthermore, controllers/estimators that satisfy the equalized recovery property (a weaker form of invariance with time-varying finite bounds) are synthesized whose feedback gains can be adapted based on the observed path, i.e., the history of observed data patterns up to the latest available time step. Finally, a robust kinodynamic motion planning algorithm is also developed with collision avoidance and probabilistic completeness guarantees. In particular, methods based on fixed and flexible invariant tubes are designed such that the planned motion/trajectories can reject bounded disturbances using noisy observations.
ContributorsHassaan, Syed Muhammad (Author) / Yong, Sze Zheng (Thesis advisor) / Rivera, Daniel (Committee member) / Marvi, Hamidreza (Committee member) / Lee, Hyunglae (Committee member) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2023
Description
The construction industry is very mundane and tiring for workers without the assistance of machines. This challenge has changed the trend of construction industry tremendously by motivating the development of robots that can replace human workers. This thesis presents a computed torque controller that is designed to produce movements by a small-scale, 5 degree-of-freedom (DOF) robotic arm that are useful for construction operations, specifically bricklaying. A software framework for the robotic arm with motion and path planning features and different control capabilities has also been developed using the Robot Operating System (ROS).
First, a literature review of bricklaying construction activity and existing robots’ performance is discussed. After describing an overview of the required robot structure, a mathematical model is presented for the 5-DOF robotic arm. A model-based computed torque controller is designed for the nonlinear dynamic robotic arm, taking into consideration the dynamic and kinematic properties of the arm. For sustainable growth of this technology so that it is affordable to the masses, it is important that the energy consumption by the robot is optimized. In this thesis, the trajectory of the robotic arm is optimized using sequential quadratic programming. The results of the energy optimization procedure are also analyzed for different possible trajectories.
A construction testbed setup is simulated in the ROS platform to validate the designed controllers and optimized robot trajectories on different experimental scenarios. A commercially available 5-DOF robotic arm is modeled in the ROS simulators Gazebo and Rviz. The path and motion planning is performed using the Moveit-ROS interface and also implemented on a physical small-scale robotic arm. A Matlab-ROS framework for execution of different controllers on the physical robot is described. Finally, the results of the controller simulation and experiments are discussed in detail.
First, a literature review of bricklaying construction activity and existing robots’ performance is discussed. After describing an overview of the required robot structure, a mathematical model is presented for the 5-DOF robotic arm. A model-based computed torque controller is designed for the nonlinear dynamic robotic arm, taking into consideration the dynamic and kinematic properties of the arm. For sustainable growth of this technology so that it is affordable to the masses, it is important that the energy consumption by the robot is optimized. In this thesis, the trajectory of the robotic arm is optimized using sequential quadratic programming. The results of the energy optimization procedure are also analyzed for different possible trajectories.
A construction testbed setup is simulated in the ROS platform to validate the designed controllers and optimized robot trajectories on different experimental scenarios. A commercially available 5-DOF robotic arm is modeled in the ROS simulators Gazebo and Rviz. The path and motion planning is performed using the Moveit-ROS interface and also implemented on a physical small-scale robotic arm. A Matlab-ROS framework for execution of different controllers on the physical robot is described. Finally, the results of the controller simulation and experiments are discussed in detail.
ContributorsGandhi, Sushrut (Author) / Berman, Spring (Thesis advisor) / Marvi, Hamidreza (Committee member) / Yong, Sze Zheng (Committee member) / Arizona State University (Publisher)
Created2019
Description
Online health forums provide a convenient channel for patients, caregivers, and medical professionals to share their experience, support and encourage each other, and form health communities. The fast growing content in health forums provides a large repository for people to seek valuable information. A forum user can issue a keyword query to search health forums regarding to some specific questions, e.g., what treatments are effective for a disease symptom? A medical researcher can discover medical knowledge in a timely and large-scale fashion by automatically aggregating the latest evidences emerging in health forums.
This dissertation studies how to effectively discover information in health forums. Several challenges have been identified. First, the existing work relies on the syntactic information unit, such as a sentence, a post, or a thread, to bind different pieces of information in a forum. However, most of information discovery tasks should be based on the semantic information unit, a patient. For instance, given a keyword query that involves the relationship between a treatment and side effects, it is expected that the matched keywords refer to the same patient. In this work, patient-centered mining is proposed to mine patient semantic information units. In a patient information unit, the health information, such as diseases, symptoms, treatments, effects, and etc., is connected by the corresponding patient.
Second, the information published in health forums has varying degree of quality. Some information includes patient-reported personal health experience, while others can be hearsay. In this work, a context-aware experience extraction framework is proposed to mine patient-reported personal health experience, which can be used for evidence-based knowledge discovery or finding patients with similar experience.
At last, the proposed patient-centered and experience-aware mining framework is used to build a patient health information database for effectively discovering adverse drug reactions (ADRs) from health forums. ADRs have become a serious health problem and even a leading cause of death in the United States. Health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. Empirical evaluation shows the effectiveness of the proposed approach.
This dissertation studies how to effectively discover information in health forums. Several challenges have been identified. First, the existing work relies on the syntactic information unit, such as a sentence, a post, or a thread, to bind different pieces of information in a forum. However, most of information discovery tasks should be based on the semantic information unit, a patient. For instance, given a keyword query that involves the relationship between a treatment and side effects, it is expected that the matched keywords refer to the same patient. In this work, patient-centered mining is proposed to mine patient semantic information units. In a patient information unit, the health information, such as diseases, symptoms, treatments, effects, and etc., is connected by the corresponding patient.
Second, the information published in health forums has varying degree of quality. Some information includes patient-reported personal health experience, while others can be hearsay. In this work, a context-aware experience extraction framework is proposed to mine patient-reported personal health experience, which can be used for evidence-based knowledge discovery or finding patients with similar experience.
At last, the proposed patient-centered and experience-aware mining framework is used to build a patient health information database for effectively discovering adverse drug reactions (ADRs) from health forums. ADRs have become a serious health problem and even a leading cause of death in the United States. Health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. Empirical evaluation shows the effectiveness of the proposed approach.
ContributorsLiu, Yunzhong (Author) / Chen, Yi (Thesis advisor) / Liu, Huan (Thesis advisor) / Li, Baoxin (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2016
Description
Recent efforts in data cleaning have focused mostly on problems like data deduplication, record matching, and data standardization; few of these focus on fixing incorrect attribute values in tuples. Correcting values in tuples is typically performed by a minimum cost repair of tuples that violate static constraints like CFDs (which have to be provided by domain experts, or learned from a clean sample of the database). In this thesis, I provide a method for correcting individual attribute values in a structured database using a Bayesian generative model and a statistical error model learned from the noisy database directly. I thus avoid the necessity for a domain expert or master data. I also show how to efficiently perform consistent query answering using this model over a dirty database, in case write permissions to the database are unavailable. A Map-Reduce architecture to perform this computation in a distributed manner is also shown. I evaluate these methods over both synthetic and real data.
ContributorsDe, Sushovan (Author) / Kambhampati, Subbarao (Thesis advisor) / Chen, Yi (Committee member) / Candan, K. Selcuk (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2014
Description
Soft Poly-Limb (SPL) is a pneumatically driven, wearable, soft continuum robotic arm designed to aid humans with medical conditions, such as cerebral palsy, paraplegia, cervical spondylotic myelopathy, perform activities of daily living. To support user's tasks, the SPL acts as an additional limb extending from the human body which can be controlled to perform safe and compliant mobile manipulation in three-dimensional space. The SPL is inspired by invertebrate limbs, such as the elephant trunk and the arms of the octopus. In this work, various geometrical and physical parameters of the SPL are identified, and behavior of the actuators that comprise it are studied by varying their parameters through novel quasi-static computational models. As a result, this study provides a set of engineering design rules to create soft actuators for continuum soft robotic arms by understanding how varying parameters affect the actuator's motion as a function of the input pressure. A prototype of the SPL is fabricated to analyze the accuracy of these computational models by performing linear expansion, bending and arbitrary pose tests. Furthermore, combinations of the parameters based on the application of the SPL are determined to affect the weight, payload capacity, and stiffness of the arm. Experimental results demonstrate the accuracy of the proposed computational models and help in understanding the behavior of soft compliant actuators. Finally, based on the set functional requirements for the assistance of impaired users, results show the effectiveness of the SPL in performing tasks for activities of daily living.
ContributorsNuthi, Sai Gautham (Author) / Polygerinos, Panagiotis (Thesis advisor) / Lee, Hyunglae (Committee member) / Yong, Sze Zheng (Committee member) / Arizona State University (Publisher)
Created2018
Description
Autonomous vehicle technology has been evolving for years since the Automated Highway System Project. However, this technology has been under increased scrutiny ever since an autonomous vehicle killed Elaine Herzberg, who was crossing the street in Tempe, Arizona in March 2018. Recent tests of autonomous vehicles on public roads have faced opposition from nearby residents. Before these vehicles are widely deployed, it is imperative that the general public trusts them. For this, the vehicles must be able to identify objects in their surroundings and demonstrate the ability to follow traffic rules while making decisions with human-like moral integrity when confronted with an ethical dilemma, such as an unavoidable crash that will injure either a pedestrian or the passenger.
Testing autonomous vehicles in real-world scenarios would pose a threat to people and property alike. A safe alternative is to simulate these scenarios and test to ensure that the resulting programs can work in real-world scenarios. Moreover, in order to detect a moral dilemma situation quickly, the vehicle should be able to identify objects in real-time while driving. Toward this end, this thesis investigates the use of cross-platform training for neural networks that perform visual identification of common objects in driving scenarios. Here, the object detection algorithm Faster R-CNN is used. The hypothesis is that it is possible to train a neural network model to detect objects from two different domains, simulated or physical, using transfer learning. As a proof of concept, an object detection model is trained on image datasets extracted from CARLA, a virtual driving environment, via transfer learning. After bringing the total loss factor to 0.4, the model is evaluated with an IoU metric. It is determined that the model has a precision of 100% and 75% for vehicles and traffic lights respectively. The recall is found to be 84.62% and 75% for the same. It is also shown that this model can detect the same classes of objects from other virtual environments and real-world images. Further modifications to the algorithm that may be required to improve performance are discussed as future work.
Testing autonomous vehicles in real-world scenarios would pose a threat to people and property alike. A safe alternative is to simulate these scenarios and test to ensure that the resulting programs can work in real-world scenarios. Moreover, in order to detect a moral dilemma situation quickly, the vehicle should be able to identify objects in real-time while driving. Toward this end, this thesis investigates the use of cross-platform training for neural networks that perform visual identification of common objects in driving scenarios. Here, the object detection algorithm Faster R-CNN is used. The hypothesis is that it is possible to train a neural network model to detect objects from two different domains, simulated or physical, using transfer learning. As a proof of concept, an object detection model is trained on image datasets extracted from CARLA, a virtual driving environment, via transfer learning. After bringing the total loss factor to 0.4, the model is evaluated with an IoU metric. It is determined that the model has a precision of 100% and 75% for vehicles and traffic lights respectively. The recall is found to be 84.62% and 75% for the same. It is also shown that this model can detect the same classes of objects from other virtual environments and real-world images. Further modifications to the algorithm that may be required to improve performance are discussed as future work.
ContributorsSankaramangalam Ulhas, Sangeet (Author) / Berman, Spring (Thesis advisor) / Johnson, Kathryn (Committee member) / Yong, Sze Zheng (Committee member) / Arizona State University (Publisher)
Created2019
Description
Bicycle stabilization has become a popular topic because of its complex dynamic behavior and the large body of bicycle modeling research. Riding a bicycle requires accurately performing several tasks, such as balancing and navigation which may be difficult for disabled people. Their problems could be partially reduced by providing steering assistance. For stabilization of these highly maneuverable and efficient machines, many control techniques have been applied – achieving interesting results, but with some limitations which includes strict environmental requirements. This thesis expands on the work of Randlov and Alstrom, using reinforcement learning for bicycle self-stabilization with robotic steering. This thesis applies the deep deterministic policy gradient algorithm, which can handle continuous action spaces which is not possible for Q-learning technique. The research involved algorithm training on virtual environments followed by simulations to assess its results. Furthermore, hardware testing was also conducted on Arizona State University’s RISE lab Smart bicycle platform for testing its self-balancing performance. Detailed analysis of the bicycle trial runs are presented. Validation of testing was done by plotting the real-time states and actions collected during the outdoor testing which included the roll angle of bicycle. Further improvements in regard to model training and hardware testing are also presented.
ContributorsTurakhia, Shubham (Author) / Zhang, Wenlong (Thesis advisor) / Yong, Sze Zheng (Committee member) / Ren, Yi (Committee member) / Arizona State University (Publisher)
Created2020