Matching Items (121)
Filtering by
- Genre: Masters Thesis
- Creators: Yang, Yezhou
- Creators: Berman, Spring
- Resource Type: Text
- Status: Published
Description
This study focuses on state estimation of nonlinear discrete time systems with constraints. Physical processes have inherent in them, constraints on inputs, outputs, states and disturbances. These constraints can provide additional information to the estimator in estimating states from the measured output. Recursive filters such as Kalman Filters or Extended Kalman Filters are commonly used in state estimation; however, they do not allow inclusion of constraints in their formulation. On the other hand, computational complexity of full information estimation (using all measurements) grows with iteration and becomes intractable. One way of formulating the recursive state estimation problem with constraints is the Moving Horizon Estimation (MHE) approximation. Estimates of states are calculated from the solution of a constrained optimization problem of fixed size. Detailed formulation of this strategy is studied and properties of this estimation algorithm are discussed in this work. The problem with the MHE formulation is solving an optimization problem in each iteration which is computationally intensive. State estimation with constraints can be formulated as Extended Kalman Filter (EKF) with a projection applied to estimates. The states are estimated from the measurements using standard Extended Kalman Filter (EKF) algorithm and the estimated states are projected on to a constrained set. Detailed formulation of this estimation strategy is studied and the properties associated with this algorithm are discussed. Both these state estimation strategies (MHE and EKF with projection) are tested with examples from the literature. The average estimation time and the sum of square estimation error are used to compare performance of these estimators. Results of the case studies are analyzed and trade-offs are discussed.
ContributorsJoshi, Rakesh (Author) / Tsakalis, Konstantinos (Thesis advisor) / Rodriguez, Armando (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2013
Description
Solar power generation is the most promising technology to transfer energy consumption reliance from fossil fuel to renewable sources. Concentrated solar power generation is a method to concentrate the sunlight from a bigger area to a smaller area. The collected sunlight is converted more efficiently through two types of technologies: concentrated solar photovoltaics (CSPV) and concentrated solar thermal power (CSTP) generation. In this thesis, these two technologies were evaluated in terms of system construction, performance characteristics, design considerations, cost benefit analysis and their field experience. The two concentrated solar power generation systems were implemented with similar solar concentrators and solar tracking systems but with different energy collecting and conversion components: the CSPV system uses high efficiency multi-junction solar cell modules, while the CSTP system uses a boiler -turbine-generator setup. The performances are calibrated via the experiments and evaluation analysis.
ContributorsJin, Zhilei (Author) / Hui, Yu (Thesis advisor) / Ayyanar, Raja (Committee member) / Rodriguez, Armando (Committee member) / Arizona State University (Publisher)
Created2013
Description
Humans have an inherent capability of performing highly dexterous and skillful tasks with their arms, involving maintaining posture, movement and interacting with the environment. The latter requires for them to control the dynamic characteristics of the upper limb musculoskeletal system. Inertia, damping and stiffness, a measure of mechanical impedance, gives a strong representation of these characteristics. Many previous studies have shown that the arm posture is a dominant factor for determining the end point impedance in a horizontal plane (transverse plane). The objective of this thesis is to characterize end point impedance of the human arm in the three dimensional (3D) space. Moreover, it investigates and models the control of the arm impedance due to increasing levels of muscle co-contraction. The characterization is done through experimental trials where human subjects maintained arm posture, while perturbed by a robot arm. Moreover, the subjects were asked to control the level of their arm muscles' co-contraction, using visual feedback of their muscles' activation, in order to investigate the effect of the muscle co-contraction on the arm impedance. The results of this study showed a very interesting, anisotropic increase of the arm stiffness due to muscle co-contraction. This can lead to very useful conclusions about the arm biomechanics as well as many implications for human motor control and more specifically the control of arm impedance through muscle co-contraction. The study finds implications for the EMG-based control of robots that physically interact with humans.
ContributorsPatel, Harshil Naresh (Author) / Artemiadis, Panagiotis (Thesis advisor) / Berman, Spring (Committee member) / Helms Tillery, Stephen (Committee member) / Arizona State University (Publisher)
Created2013
Description
A systematic top down approach to minimize risk and maximize the profits of an investment over a given period of time is proposed. Macroeconomic factors such as Gross Domestic Product (GDP), Consumer Price Index (CPI), Outstanding Consumer Credit, Industrial Production Index, Money Supply (MS), Unemployment Rate, and Ten-Year Treasury are used to predict/estimate asset (sector ETF`s) returns. Fundamental ratios of individual stocks are used to predict the stock returns. An a priori known cash-flow sequence is assumed available for investment. Given the importance of sector performance on stock performance, sector based Exchange Traded Funds (ETFs) for the S&P; and Dow Jones are considered and wealth is allocated. Mean variance optimization with risk and return constraints are used to distribute the wealth in individual sectors among the selected stocks. The results presented should be viewed as providing an outer control/decision loop generating sector target allocations that will ultimately drive an inner control/decision loop focusing on stock selection. Receding horizon control (RHC) ideas are exploited to pose and solve two relevant constrained optimization problems. First, the classic problem of wealth maximization subject to risk constraints (as measured by a metric on the covariance matrices) is considered. Special consideration is given to an optimization problem that attempts to minimize the peak risk over the prediction horizon, while trying to track a wealth objective. It is concluded that this approach may be particularly beneficial during downturns - appreciably limiting downside during downturns while providing most of the upside during upturns. Investment in stocks during upturns and in sector ETF`s during downturns is profitable.
ContributorsChitturi, Divakar (Author) / Rodriguez, Armando (Thesis advisor) / Tsakalis, Konstantinos S (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2010
Description
Feature embeddings differ from raw features in the sense that the former obey certain properties like notion of similarity/dissimilarity in it's embedding space. word2vec is a preeminent example in this direction, where the similarity in the embedding space is measured in terms of the cosine similarity. Such language embedding models have seen numerous applications in both language and vision community as they capture the information in the modality (English language) efficiently. Inspired by these language models, this work focuses on learning embedding spaces for two visual computing tasks, 1. Image Hashing 2. Zero Shot Learning. The training set was used to learn embedding spaces over which similarity/dissimilarity is measured using several distance metrics like hamming / euclidean / cosine distances. While the above-mentioned language models learn generic word embeddings, in this work task specific embeddings were learnt which can be used for Image Retrieval and Classification separately.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
ContributorsGattupalli, Jaya Vijetha (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2019
Description
Building and optimizing a design for deformable media can be extremely costly. However, granular scaling laws enable the ability to predict system velocity and mobility
power consumption by testing at a smaller scale in the same environment. The validity of
the granular scaling laws for arbitrarily shaped wheels and screws were evaluated in
materials like silica sand and BP-1, a lunar simulant. Different wheel geometries, such as
non-grousered and straight and bihelically grousered wheels were created and tested
using 3D printed technologies. Using the granular scaling laws and the empirical data
from initial experiments, power and velocity were predicted for a larger scaled version
then experimentally validated on a dynamic mobility platform. Working with granular
media has high variability in material properties depending on initial environmental
conditions, so particular emphasis was placed on consistency in the testing methodology.
Through experiments, these scaling laws have been validated with defined use cases and
limitations.
ContributorsMcbryan, Teresa (Author) / Marvi, Hamidreza (Thesis advisor) / Berman, Spring (Committee member) / Lee, Hyunglae (Committee member) / Arizona State University (Publisher)
Created2022
Description
Chemical Reaction Networks (CRNs) provide a useful framework for modeling andcontrolling large numbers of agents that undergo stochastic transitions between a set of states
in a manner similar to chemical compounds. By utilizing CRN models to design agent control
policies, some of the computational challenges in the coordination of multi-agent systems can
be overcome. In this thesis, a CRN model is developed that defines agent control policies for a
multi-agent construction task. The use of surface CRNs to overcome the tradeoff between
speed and accuracy of task performance is explained. The computational difficulties involved
in coordinating multiple agents to complete collective construction tasks is then discussed. A
method for stochastic task and motion planning (TAMP) is proposed to explain how a TAMP
solver can be applied with CRNs to coordinate multiple agents.
This work defines a collective construction scenario in which a group of noncommunicating agents must rearrange blocks on a discrete domain with obstacles into a
predefined target distribution. Four different construction tasks are considered with 10, 20,
30, or 40 blocks, and a simulation of each scenario with 2, 4, 6, or 8 agents is performed. As the
number of blocks increases, the construction problem becomes more complex, and a given
population of agents requires more time to complete the task. Populations of fewer than 8
agents are unable to solve the 30-block and 40-block problems in the allotted simulation time,
suggesting an inflection point for computational feasibility, implying that beyond that point
the solution times for fewer than 8 agents would be expected to increase significantly. For a
group of 8 agents, the time to complete the task generally increases as the number of blocks
increases, except for the 30-block problem, which has specifications that make the task slightly
easier for the agents to complete compared to the 20-block problem. For the 10-block and 20-
block problems, the time to complete the task decreases as the number of agents increases;
however, the marginal effect of each additional two agents on this time decreases. This can be
explained through the pigeonhole principle: since there area finite number of states, when the
number of agents is greater than the number of available spaces, deadlocks start to occur and
the expectation is that the overall solution time to tend to infinity.
ContributorsKamojjhala, Pranav (Author) / Berman, Spring (Thesis advisor) / Fainekos, Gergios E (Thesis advisor) / Pavlic, Theodore P (Committee member) / Arizona State University (Publisher)
Created2022
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
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Machine learning models can pick up biases and spurious correlations from training data and projects and amplify these biases during inference, thus posing significant challenges in real-world settings. One approach to mitigating this is a class of methods that can identify filter out bias-inducing samples from the training datasets to force models to avoid being exposed to biases. However, the filtering leads to a considerable wastage of resources as most of the dataset created is discarded as biased. This work deals with avoiding the wastage of resources by identifying and quantifying the biases. I further elaborate on the implications of dataset filtering on robustness (to adversarial attacks) and generalization (to out-of-distribution samples). The findings suggest that while dataset filtering does help to improve OOD(Out-Of-Distribution) generalization, it has a significant negative impact on robustness to adversarial attacks. It also shows that transforming bias-inducing samples into adversarial samples (instead of eliminating them from the dataset) can significantly boost robustness without sacrificing generalization.
ContributorsSachdeva, Bhavdeep Singh (Author) / Baral, Chitta (Thesis advisor) / Liu, Huan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021