Matching Items (118)
Filtering by
- Genre: Doctoral Dissertation
- Creators: Papandreou-Suppappola, Antonia
- Member of: Theses and Dissertations
Description
Multi-segment manipulators and mobile robot collectives are examples of multi-agent robotic systems, in which each segment or robot can be considered an agent. Fundamental motion control problems for such systems include the stabilization of one or more agents to target configurations or trajectories while preventing inter-agent collisions, agent collisions with obstacles, and deadlocks. Despite extensive research on these control problems, there are still challenges in designing controllers that (1) are scalable with the number of agents; (2) have theoretical guarantees on collision-free agent navigation; and (3) can be used when the states of the agents and the environment are only partially observable. Existing centralized and distributed control architectures have limited scalability due to their computational complexity and communication requirements, while decentralized control architectures are often effective only under impractical assumptions that do not hold in real-world implementations. The main objective of this dissertation is to develop and evaluate decentralized approaches for multi-agent motion control that enable agents to use their onboard sensors and computational resources to decide how to move through their environment, with limited or absent inter-agent communication and external supervision. Specifically, control approaches are designed for multi-segment manipulators and mobile robot collectives to achieve position and pose (position and orientation) stabilization, trajectory tracking, and collision and deadlock avoidance. These control approaches are validated in both simulations and physical experiments to show that they can be implemented in real-time while remaining computationally tractable. First, kinematic controllers are proposed for position stabilization and trajectory tracking control of two- or three-dimensional hyper-redundant multi-segment manipulators. Next, robust and gradient-based feedback controllers are presented for individual holonomic and nonholonomic mobile robots that achieve position stabilization, trajectory tracking control, and obstacle avoidance. Then, nonlinear Model Predictive Control methods are developed for collision-free, deadlock-free pose stabilization and trajectory tracking control of multiple nonholonomic mobile robots in known and unknown environments with obstacles, both static and dynamic. Finally, a feedforward proportional-derivative controller is defined for collision-free velocity tracking of a moving ground target by multiple unmanned aerial vehicles.
ContributorsSalimi Lafmejani, Amir (Author) / Berman, Spring (Thesis advisor) / Tsakalis, Konstantinos (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Marvi, Hamidreza (Committee member) / Arizona State University (Publisher)
Created2022
Description
Microstructure refinement and alloy additions are considered potential routes to increase high temperature performance of existing metallic superalloys used under extreme conditions. Nanocrystalline (NC) Cu-10at%Ta exhibits such improvements over microstructurally unstable NC metals, leading to enhanced creep behavior compared to its coarse-grained (CG) counterparts. However, the low melting point of Cu compared to other FCC metals, e.g., Ni, might lead to an early onset of diffusional creep mechanisms. Thus, this research seeks to study the thermo-mechanical behavior and stability of hierarchical (prepared using arc-melting) and NC (prepared by collaborators through powder pressing and annealing) Ni-Y-Zr alloys where Zr is expected to provide solid solution and grain boundary strengthening in hierarchical and NC alloys, respectively, while Ni-Y and Ni-Zr intermetallic precipitates (IMCs) would provide kinetic stability. Hierarchical alloys had microstructures stable up to 1100 °C with ultrafine eutectic of ~300 nm, dendritic arm spacing of ~10 μm, and grain size ~1-2 mm. Room temperature hardness tests along with uniaxial compression performed at 25 and 600 °C revealed that microhardness and yield strength of hierarchical alloys with small amounts of Y (0.5-1wt%) and Zr (1.5-3 wt%) were comparable to Ni-superalloys, due to the hierarchical microstructure and potential presence of nanoscale IMCs. In contrast, NC alloys of the same composition were found to be twice as hard as the hierarchical alloys. Creep tests at 0.5 homologous temperature showed active Coble creep mechanisms in hierarchical alloys at low stresses with creep rates slower than Fe-based superalloys and dislocation creep mechanisms at higher stresses. Creep in NC alloys at lower stresses was only 20 times faster than hierarchical alloys, with the difference in grain size ranging from 10^3 to 10^6 times at the same temperature. These NC alloys showed enhanced creep properties over other NC metals and are expected to have rates equal to or improved over the CG hierarchical alloys with ECAP processing techniques. Lastly, the in-situ wide-angle x-ray scattering (WAXS) measurements during quasi-static and creep tests implied stresses being carried mostly by the matrix before yielding and in the primary creep stage, respectively, while relaxation was observed in Ni5Zr for both hierarchical and NC alloys. Beyond yielding and in the secondary creep stage, lattice strains reached a steady state, thereby, an equilibrium between plastic strain rates was achieved across different phases, so that deformation reaches a saturation state where strain hardening effects are compensated by recovery mechanisms.
ContributorsSharma, Shruti (Author) / Peralta, Pedro (Thesis advisor) / Alford, Terry (Committee member) / Jiao, Yang (Committee member) / Solanki, Kiran (Committee member) / Arizona State University (Publisher)
Created2022
Description
Complex perovskite materials, including Ba(Zn1/3Ta2/3)O3 (BZT), are commonly used to make resonators and filters in communication systems because of their low dielectric loss and high-quality factors (Q). Transition metal additives are introduced (i.e., Ni2+, Co2+, Mn2+) to act as sintering agents and tune their temperature coefficient to zero or near-zero. However, losses in these commercial dielectric materials at cryogenic temperatures increase markedly due to spin-excitation resulting from the presence of paramagnetic defects. Applying a large magnetic field (e.g., 5 Tesla) quenches these losses and has allowed the study of other loss mechanisms present at low temperatures. Work was performed on Fe3+ doped LaAlO3. At high magnetic fields, the residual losses versus temperature plots exhibit Debye peaks at ~40 K, ~75 K, and ~215 K temperature and can be tentatively associated with defect reactions O_i^x+V_O^x→O_i^'+V_O^•, Fe_Al^x+V_Al^"→Fe_Al^'+V_Al^' and Al_i^x+Al_i^(••)→〖2Al〗_i^•, respectively. Peaks in the loss tangent versus temperature graph of Zn-deficient BZT indicate a higher concentration of defects and appear to result from conduction losses.Guided by the knowledge gained from this study, a systematic study to develop high-performance microwave materials for ultra-high performance at cryogenic temperatures was performed. To this end, the production and characterization of perovskite materials that were either undoped or contained non-paramagnetic additives were carried out. Synthesis of BZT ceramic with over 98% theoretical density was obtained using B2O3 or BaZrO3 additives. At 4 K, the highest Q x f product of 283,000 GHz was recorded for 5% BaZrO3 doped BZT.
A portable, inexpensive open-air spectrometer was designed, built, and tested to make the electron paramagnetic resonance (EPR) technique more accessible for high-school and university lab instruction. In this design, the sample is placed near a dielectric resonator and does not need to be enclosed in a cavity, as is used in commercial EPR spectrometers. Permanent magnets used produce fields up to 1500 G, enabling EPR measurements up to 3 GHz.
ContributorsGajare, Siddhesh Girish (Author) / Newman, Nathan (Thesis advisor) / Alford, Terry (Committee member) / Tongay, Sefaattin (Committee member) / Chamberlin, Ralph (Committee member) / Arizona State University (Publisher)
Created2022
Description
The advancement and marked increase in the use of computing devices in health care for large scale and personal medical use has transformed the field of medicine and health care into a data rich domain. This surge in the availability of data has allowed domain experts to investigate, study and discover inherent patterns in diseases from new perspectives and in turn, further the field of medicine. Storage and analysis of this data in real time aids in enhancing the response time and efficiency of doctors and health care specialists. However, due to the time critical nature of most life- threatening diseases, there is a growing need to make informed decisions prior to the occurrence of any fatal outcome. Alongside time sensitivity, analyzing data specific to diseases and their effects on an individual basis leads to more efficient prognosis and rapid deployment of cures. The primary challenge in addressing both of these issues arises from the time varying and time sensitive nature of the data being studied and in the ability to successfully predict anomalous events using only observed data.This dissertation introduces adaptive machine learning algorithms that aid in the prediction of anomalous situations arising due to abnormalities present in patients diagnosed with certain types of diseases. Emphasis is given to the adaptation and development of algorithms based on an individual basis to further the accuracy of all predictions made. The main objectives are to learn the underlying representation of the data using empirical methods and enhance it using domain knowledge. The learned model is then utilized as a guide for statistical machine learning methods to predict the occurrence of anomalous events in the near future. Further enhancement of the learned model is achieved by means of tuning the objective function of the algorithm to incorporate domain knowledge. Along with anomaly forecasting using multi-modal data, this dissertation also investigates the use of univariate time series data towards the prediction of onset of diseases using Bayesian nonparametrics.
ContributorsDas, Subhasish (Author) / Gupta, Sandeep K.S. (Thesis advisor) / Banerjee, Ayan (Committee member) / Indic, Premananda (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2022
Description
The recent proposal of two-way relaying has attracted much attention due to its promising features for many practical scenarios. Hereby, two users communicate simultaneously in both directions to exchange their messages with the help of a relay node. This doctoral study investigates various aspects of two-way relaying. Specifically, the issue of asynchronism, lack of channel knowledge, transmission of correlated sources and multi-way relaying techniques involving multiple users are explored.
With the motivation of developing enabling techniques for two-way relay (TWR) channels experiencing excessive synchronization errors, two conceptually-different schemes are proposed to accommodate any relative misalignment between the signals received at any node. By designing a practical transmission/detection mechanism based on orthogonal frequency division multiplexing (OFDM), the proposed schemes perform significantly better than existing competing solutions. In a related direction, differential modulation is implemented for asynchronous TWR systems that lack the channel state information (CSI) knowledge. The challenge in this problem compared to the conventional point-to-point counterpart arises not only from the asynchrony but also from the existence of an interfering signal. Extensive numerical examples, supported by analytical work, are given to demonstrate the advantages of the proposed schemes.
Other important issues considered in this dissertation are related to the extension of the two-way relaying scheme to the multiple-user case, known as the multi-way relaying. First, a distributed source coding solution based on Slepian-Wolf coding is proposed to compress correlated messages close to the information theoretical limits in the context of multi-way relay (MWR) channels. Specifically, the syndrome approach based on low-density parity-check (LDPC) codes is implemented. A number of relaying strategies are considered for this problem offering a tradeoff between performance and complexity. The proposed solutions have shown significant improvements compared to the existing ones in terms of the achievable compression rates. On a different front, a novel approach to channel coding is proposed for the MWR channel based on the implementation of nested codes in a distributed manner. This approach ensures that each node decodes the messages of the other users without requiring complex operations at the relay, and at the same time, providing substantial benefits compared to the traditional routing solution.
With the motivation of developing enabling techniques for two-way relay (TWR) channels experiencing excessive synchronization errors, two conceptually-different schemes are proposed to accommodate any relative misalignment between the signals received at any node. By designing a practical transmission/detection mechanism based on orthogonal frequency division multiplexing (OFDM), the proposed schemes perform significantly better than existing competing solutions. In a related direction, differential modulation is implemented for asynchronous TWR systems that lack the channel state information (CSI) knowledge. The challenge in this problem compared to the conventional point-to-point counterpart arises not only from the asynchrony but also from the existence of an interfering signal. Extensive numerical examples, supported by analytical work, are given to demonstrate the advantages of the proposed schemes.
Other important issues considered in this dissertation are related to the extension of the two-way relaying scheme to the multiple-user case, known as the multi-way relaying. First, a distributed source coding solution based on Slepian-Wolf coding is proposed to compress correlated messages close to the information theoretical limits in the context of multi-way relay (MWR) channels. Specifically, the syndrome approach based on low-density parity-check (LDPC) codes is implemented. A number of relaying strategies are considered for this problem offering a tradeoff between performance and complexity. The proposed solutions have shown significant improvements compared to the existing ones in terms of the achievable compression rates. On a different front, a novel approach to channel coding is proposed for the MWR channel based on the implementation of nested codes in a distributed manner. This approach ensures that each node decodes the messages of the other users without requiring complex operations at the relay, and at the same time, providing substantial benefits compared to the traditional routing solution.
ContributorsSalīm, Aḥmad (Author) / Duman, Tolga M. (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Zhang, Junshan (Committee member) / Arizona State University (Publisher)
Created2015
Description
ABSTRACT
Large-pore metal-organic framework (MOF) membranes offer potential in a number of gas and liquid separations due to their wide and selective adsorption capacities. A key characteristic of a number of MOF and zeolitic imidazolate framework (ZIF) membranes is their highly selective adsorption capacities for CO2. These membranes offer very tangible potential to separate CO2 in a wide array of industrially relevant separation processes, such as the separation from CO2 in flue gas emissions, as well as the sweetening of methane.
By virtue of this, the purpose of this dissertation is to synthesize and characterize two linear large-pore MOF membranes, MOF-5 and ZIF-68, and to study their gas separation properties in binary mixtures of CO¬2/N2 and CO2/CH4. The three main objectives researched are as follows. The first is to study the pervaporation behavior and stability of MOF-5; this is imperative because although MOF-5 exhibits desirable adsorption and separation characteristics, it is very unstable in atmospheric conditions. In determining its stability and behavior in pervaporation, this material can be utilized in conditions wherein atmospheric levels of moisture can be avoided. The second objective is to synthesize, optimize and characterize a linear, more stable MOF membrane, ZIF-68. The final objective is to study in tandem the high-pressure gas separation behavior of MOF-5 and ZIF-68 in binary gas systems of both CO2/N2 and CO2/CH4.
Continuous ZIF-68 membranes were synthesized via the reactive seeding method and the modified reactive seeding method. These membranes, as with the MOF-5 membranes synthesized herein, both showed adherence to Knudsen diffusion, indicating limited defects. Organic solvent experiments indicated that MOF-5 and ZIF-68 were stable in a variety of organic solvents, but both showed reductions in permeation flux of the tested molecules. These reductions were attributed to fouling and found to be cumulative up until a saturation of available bonding sites for molecules was reached and stable pervaporation permeances were reached for both. Gas separation behavior for MOF-5 showed direct dependence on the CO2 partial pressure and the overall feed pressure, while ZIF-68 did not show similar behavior. Differences in separation behavior are attributable to orientation of the ZIF-68 membranes.
Large-pore metal-organic framework (MOF) membranes offer potential in a number of gas and liquid separations due to their wide and selective adsorption capacities. A key characteristic of a number of MOF and zeolitic imidazolate framework (ZIF) membranes is their highly selective adsorption capacities for CO2. These membranes offer very tangible potential to separate CO2 in a wide array of industrially relevant separation processes, such as the separation from CO2 in flue gas emissions, as well as the sweetening of methane.
By virtue of this, the purpose of this dissertation is to synthesize and characterize two linear large-pore MOF membranes, MOF-5 and ZIF-68, and to study their gas separation properties in binary mixtures of CO¬2/N2 and CO2/CH4. The three main objectives researched are as follows. The first is to study the pervaporation behavior and stability of MOF-5; this is imperative because although MOF-5 exhibits desirable adsorption and separation characteristics, it is very unstable in atmospheric conditions. In determining its stability and behavior in pervaporation, this material can be utilized in conditions wherein atmospheric levels of moisture can be avoided. The second objective is to synthesize, optimize and characterize a linear, more stable MOF membrane, ZIF-68. The final objective is to study in tandem the high-pressure gas separation behavior of MOF-5 and ZIF-68 in binary gas systems of both CO2/N2 and CO2/CH4.
Continuous ZIF-68 membranes were synthesized via the reactive seeding method and the modified reactive seeding method. These membranes, as with the MOF-5 membranes synthesized herein, both showed adherence to Knudsen diffusion, indicating limited defects. Organic solvent experiments indicated that MOF-5 and ZIF-68 were stable in a variety of organic solvents, but both showed reductions in permeation flux of the tested molecules. These reductions were attributed to fouling and found to be cumulative up until a saturation of available bonding sites for molecules was reached and stable pervaporation permeances were reached for both. Gas separation behavior for MOF-5 showed direct dependence on the CO2 partial pressure and the overall feed pressure, while ZIF-68 did not show similar behavior. Differences in separation behavior are attributable to orientation of the ZIF-68 membranes.
ContributorsKasik, Alexandra Marie (Author) / Lin, Jerry (Thesis advisor) / Tasooji, Amaneh (Committee member) / Alford, Terry (Committee member) / Arizona State University (Publisher)
Created2015
Description
I propose a new communications scheme where signature signals are used to carry digital data by suitably modulating the signal parameters with information bits. One possible application for the proposed scheme is in underwater acoustic (UWA) communications; with this motivation, I demonstrate how it can be applied in UWA communications. In order to do that, I exploit existing parameterized models for mammalian sounds by using them as signature signals. Digital data is transmitted by mapping vectors of information bits to a carefully designed set of parameters with values obtained from the biomimetic signal models. To complete the overall system design, I develop appropriate receivers taking into account the specific UWA channel models. I present some numerical results from the analysis of data recorded during the Kauai Acomms MURI 2011 (KAM11) UWA communications experiment.
It is shown that the proposed communication scheme results in approximate channel models with amplitude-limited inputs and signal-dependent additive noise. Motivated by this observation, I study capacity of amplitude-limited channels under different transmission scenarios. Specifically, I consider fading channels, signal-dependent additive Gaussian noise channels, multiple-input multiple-output (MIMO) systems and parallel Gaussian channels under peak power constraints.
I also consider practical channel coding problems for channels with signal-dependent noise. I consider two specific models; signal-dependent additive Gaussian noise channels and Z-channels which serve as binary-input binary-output approximations to the Gaussian case. I propose a new upper bound on the probability of error, and utilize it for design of codes. I illustrate the tightness of the derived bounds and the performance of the designed codes via examples.
It is shown that the proposed communication scheme results in approximate channel models with amplitude-limited inputs and signal-dependent additive noise. Motivated by this observation, I study capacity of amplitude-limited channels under different transmission scenarios. Specifically, I consider fading channels, signal-dependent additive Gaussian noise channels, multiple-input multiple-output (MIMO) systems and parallel Gaussian channels under peak power constraints.
I also consider practical channel coding problems for channels with signal-dependent noise. I consider two specific models; signal-dependent additive Gaussian noise channels and Z-channels which serve as binary-input binary-output approximations to the Gaussian case. I propose a new upper bound on the probability of error, and utilize it for design of codes. I illustrate the tightness of the derived bounds and the performance of the designed codes via examples.
ContributorsElMoslimany, Ahmad (Author) / Duman, Tolga M. (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Kosut, Oliver (Committee member) / Arizona State University (Publisher)
Created2015
Description
Stress-related failure such as cracking are an important photovoltaic (PV) reliability issue since it accounts for a high percentage of power losses in the midlife-failure and wear-out failure regimes. Cell cracking can only be correlated with module degradation when cracks are of detectable size and detrimental to the performance. Several techniques have been explored to access the deflection and stress status on solar cell, but they have disadvantages such as high surface sensitivity.
This dissertation presents a new and non-destructive method for mapping the deflection on encapsulated solar cells using X-ray topography (XRT). This method is based on Bragg diffraction imaging, where only the areas that meet diffraction conditions will present contrast. By taking XRT images of the solar cell at various sample positions and applying an in-house developed algorithm framework, the cell‘s deflection map is obtained. Error analysis has demonstrated that the errors from the experiment and the data processing are below 4.4 and 3.3%.
Von Karman plate theory has been applied to access the stress state of the solar cells. Under the assumptions that the samples experience pure bending and plain stress conditions, the principal stresses are obtained from the cell deflection data. Results from a statistical analysis using a Weibull distribution suggest that 0.1% of the data points can contribute to critical failure. Both the soldering and lamination processes put large amounts of stress on solar cells. Even though glass/glass packaging symmetry is preferred over glass/backsheet, the solar cells inside the glass/glass packaging experience significantly more stress. Through a series of in-situ four-point bending test, the assumptions behind Von Karman theory are validated for cases where the neutral plane is displaced by the tensile and compressive stresses.
The deflection and stress mapping method is applied to two next generation PV concepts named Flex-circuit and PVMirror. The Flex-circuit module concept replaces traditional metal ribbons with Al foils for electrical contact and PVMirror concept utilizes a curved PV module design with a dichroic film for thermal storage and electrical output. The XRT framework proposed in this dissertation successfully characterized the impact of various novel interconnection and packaging solutions.
This dissertation presents a new and non-destructive method for mapping the deflection on encapsulated solar cells using X-ray topography (XRT). This method is based on Bragg diffraction imaging, where only the areas that meet diffraction conditions will present contrast. By taking XRT images of the solar cell at various sample positions and applying an in-house developed algorithm framework, the cell‘s deflection map is obtained. Error analysis has demonstrated that the errors from the experiment and the data processing are below 4.4 and 3.3%.
Von Karman plate theory has been applied to access the stress state of the solar cells. Under the assumptions that the samples experience pure bending and plain stress conditions, the principal stresses are obtained from the cell deflection data. Results from a statistical analysis using a Weibull distribution suggest that 0.1% of the data points can contribute to critical failure. Both the soldering and lamination processes put large amounts of stress on solar cells. Even though glass/glass packaging symmetry is preferred over glass/backsheet, the solar cells inside the glass/glass packaging experience significantly more stress. Through a series of in-situ four-point bending test, the assumptions behind Von Karman theory are validated for cases where the neutral plane is displaced by the tensile and compressive stresses.
The deflection and stress mapping method is applied to two next generation PV concepts named Flex-circuit and PVMirror. The Flex-circuit module concept replaces traditional metal ribbons with Al foils for electrical contact and PVMirror concept utilizes a curved PV module design with a dichroic film for thermal storage and electrical output. The XRT framework proposed in this dissertation successfully characterized the impact of various novel interconnection and packaging solutions.
ContributorsMeng, Xiaodong (Author) / Bertoni, Marian I (Thesis advisor) / Meier, Rico (Committee member) / Holman, Zachary C (Committee member) / Alford, Terry (Committee member) / Arizona State University (Publisher)
Created2019
Description
The marked increase in the inflow of remotely sensed data from satellites have trans- formed the Earth and Space Sciences to a data rich domain creating a rich repository for domain experts to analyze. These observations shed light on a diverse array of disciplines ranging from monitoring Earth system components to planetary explo- ration by highlighting the expected trend and patterns in the data. However, the complexity of these patterns from local to global scales, coupled with the volume of this ever-growing repository necessitates advanced techniques to sequentially process the datasets to determine the underlying trends. Such techniques essentially model the observations to learn characteristic parameters of data-generating processes and highlight anomalous planetary surface observations to help domain scientists for making informed decisions. The primary challenge in defining such models arises due to the spatio-temporal variability of these processes.
This dissertation introduces models of multispectral satellite observations that sequentially learn the expected trend from the data by extracting salient features of planetary surface observations. The main objectives are to learn the temporal variability for modeling dynamic processes and to build representations of features of interest that is learned over the lifespan of an instrument. The estimated model parameters are then exploited in detecting anomalies due to changes in land surface reflectance as well as novelties in planetary surface landforms. A model switching approach is proposed that allows the selection of the best matched representation given the observations that is designed to account for rate of time-variability in land surface. The estimated parameters are exploited to design a change detector, analyze the separability of change events, and form an expert-guided representation of planetary landforms for prioritizing the retrieval of scientifically relevant observations with both onboard and post-downlink applications.
This dissertation introduces models of multispectral satellite observations that sequentially learn the expected trend from the data by extracting salient features of planetary surface observations. The main objectives are to learn the temporal variability for modeling dynamic processes and to build representations of features of interest that is learned over the lifespan of an instrument. The estimated model parameters are then exploited in detecting anomalies due to changes in land surface reflectance as well as novelties in planetary surface landforms. A model switching approach is proposed that allows the selection of the best matched representation given the observations that is designed to account for rate of time-variability in land surface. The estimated parameters are exploited to design a change detector, analyze the separability of change events, and form an expert-guided representation of planetary landforms for prioritizing the retrieval of scientifically relevant observations with both onboard and post-downlink applications.
ContributorsChakraborty, Srija (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Christensen, Philip R. (Philip Russel) (Thesis advisor) / Richmond, Christ (Committee member) / Maurer, Alexander (Committee member) / Arizona State University (Publisher)
Created2019
Description
Robotic lower limb prostheses provide new opportunities to help transfemoral amputees regain mobility. However, their application is impeded by that the impedance control parameters need to be tuned and optimized manually by prosthetists for each individual user in different task environments. Reinforcement learning (RL) is capable of automatically learning from interacting with the environment. It becomes a natural candidate to replace human prosthetists to customize the control parameters. However, neither traditional RL approaches nor the popular deep RL approaches are readily suitable for learning with limited number of samples and samples with large variations. This dissertation aims to explore new RL based adaptive solutions that are data-efficient for controlling robotic prostheses.
This dissertation begins by proposing a new flexible policy iteration (FPI) framework. To improve sample efficiency, FPI can utilize either on-policy or off-policy learning strategy, can learn from either online or offline data, and can even adopt exiting knowledge of an external critic. Approximate convergence to Bellman optimal solutions are guaranteed under mild conditions. Simulation studies validated that FPI was data efficient compared to several established RL methods. Furthermore, a simplified version of FPI was implemented to learn from offline data, and then the learned policy was successfully tested for tuning the control parameters online on a human subject.
Next, the dissertation discusses RL control with information transfer (RL-IT), or knowledge-guided RL (KG-RL), which is motivated to benefit from transferring knowledge acquired from one subject to another. To explore its feasibility, knowledge was extracted from data measurements of able-bodied (AB) subjects, and transferred to guide Q-learning control for an amputee in OpenSim simulations. This result again demonstrated that data and time efficiency were improved using previous knowledge.
While the present study is new and promising, there are still many open questions to be addressed in future research. To account for human adaption, the learning control objective function may be designed to incorporate human-prosthesis performance feedback such as symmetry, user comfort level and satisfaction, and user energy consumption. To make the RL based control parameter tuning practical in real life, it should be further developed and tested in different use environments, such as from level ground walking to stair ascending or descending, and from walking to running.
This dissertation begins by proposing a new flexible policy iteration (FPI) framework. To improve sample efficiency, FPI can utilize either on-policy or off-policy learning strategy, can learn from either online or offline data, and can even adopt exiting knowledge of an external critic. Approximate convergence to Bellman optimal solutions are guaranteed under mild conditions. Simulation studies validated that FPI was data efficient compared to several established RL methods. Furthermore, a simplified version of FPI was implemented to learn from offline data, and then the learned policy was successfully tested for tuning the control parameters online on a human subject.
Next, the dissertation discusses RL control with information transfer (RL-IT), or knowledge-guided RL (KG-RL), which is motivated to benefit from transferring knowledge acquired from one subject to another. To explore its feasibility, knowledge was extracted from data measurements of able-bodied (AB) subjects, and transferred to guide Q-learning control for an amputee in OpenSim simulations. This result again demonstrated that data and time efficiency were improved using previous knowledge.
While the present study is new and promising, there are still many open questions to be addressed in future research. To account for human adaption, the learning control objective function may be designed to incorporate human-prosthesis performance feedback such as symmetry, user comfort level and satisfaction, and user energy consumption. To make the RL based control parameter tuning practical in real life, it should be further developed and tested in different use environments, such as from level ground walking to stair ascending or descending, and from walking to running.
ContributorsGao, Xiang (Author) / Si, Jennie (Thesis advisor) / Huang, He Helen (Committee member) / Santello, Marco (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2020