Matching Items (13)
Filtering by
- All Subjects: artificial intelligence
- Creators: Berman, Spring
- Resource Type: Text
Description
The use of electromyography (EMG) signals to characterize muscle fatigue has been widely accepted. Initial work on characterizing muscle fatigue during isometric contractions demonstrated that its frequency decreases while its amplitude increases with the onset of fatigue. More recent work concentrated on developing techniques to characterize dynamic contractions for use in clinical and training applications. Studies demonstrated that as fatigue progresses, the EMG signal undergoes a shift in frequency, and different physiological mechanisms on the possible cause of the shift were considered. Time-frequency processing, using the Wigner distribution or spectrogram, is one of the techniques used to estimate the instantaneous mean frequency and instantaneous median frequency of the EMG signal using a variety of techniques. However, these time-frequency methods suffer either from cross-term interference when processing signals with multiple components or time-frequency resolution due to the use of windowing. This study proposes the use of the matching pursuit decomposition (MPD) with a Gaussian dictionary to process EMG signals produced during both isometric and dynamic contractions. In particular, the MPD obtains unique time-frequency features that represent the EMG signal time-frequency dependence without suffering from cross-terms or loss in time-frequency resolution. As the MPD does not depend on an analysis window like the spectrogram, it is more robust in applying the timefrequency features to identify the spectral time-variation of the EGM signal.
ContributorsAustin, Hiroko (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Kovvali, Narayan (Committee member) / Muthuswamy, Jitendran (Committee member) / Arizona State University (Publisher)
Created2012
Description
Myoelectric control is lled with potential to signicantly change human-robot interaction.
Humans desire compliant robots to safely interact in dynamic environments
associated with daily activities. As surface electromyography non-invasively measures
limb motion intent and correlates with joint stiness during co-contractions,
it has been identied as a candidate for naturally controlling such robots. However,
state-of-the-art myoelectric interfaces have struggled to achieve both enhanced
functionality and long-term reliability. As demands in myoelectric interfaces trend
toward simultaneous and proportional control of compliant robots, robust processing
of multi-muscle coordinations, or synergies, plays a larger role in the success of the
control scheme. This dissertation presents a framework enhancing the utility of myoelectric
interfaces by exploiting motor skill learning and
exible muscle synergies for
reliable long-term simultaneous and proportional control of multifunctional compliant
robots. The interface is learned as a new motor skill specic to the controller,
providing long-term performance enhancements without requiring any retraining or
recalibration of the system. Moreover, the framework oers control of both motion
and stiness simultaneously for intuitive and compliant human-robot interaction. The
framework is validated through a series of experiments characterizing motor learning
properties and demonstrating control capabilities not seen previously in the literature.
The results validate the approach as a viable option to remove the trade-o
between functionality and reliability that have hindered state-of-the-art myoelectric
interfaces. Thus, this research contributes to the expansion and enhancement of myoelectric
controlled applications beyond commonly perceived anthropomorphic and
\intuitive control" constraints and into more advanced robotic systems designed for
everyday tasks.
Humans desire compliant robots to safely interact in dynamic environments
associated with daily activities. As surface electromyography non-invasively measures
limb motion intent and correlates with joint stiness during co-contractions,
it has been identied as a candidate for naturally controlling such robots. However,
state-of-the-art myoelectric interfaces have struggled to achieve both enhanced
functionality and long-term reliability. As demands in myoelectric interfaces trend
toward simultaneous and proportional control of compliant robots, robust processing
of multi-muscle coordinations, or synergies, plays a larger role in the success of the
control scheme. This dissertation presents a framework enhancing the utility of myoelectric
interfaces by exploiting motor skill learning and
exible muscle synergies for
reliable long-term simultaneous and proportional control of multifunctional compliant
robots. The interface is learned as a new motor skill specic to the controller,
providing long-term performance enhancements without requiring any retraining or
recalibration of the system. Moreover, the framework oers control of both motion
and stiness simultaneously for intuitive and compliant human-robot interaction. The
framework is validated through a series of experiments characterizing motor learning
properties and demonstrating control capabilities not seen previously in the literature.
The results validate the approach as a viable option to remove the trade-o
between functionality and reliability that have hindered state-of-the-art myoelectric
interfaces. Thus, this research contributes to the expansion and enhancement of myoelectric
controlled applications beyond commonly perceived anthropomorphic and
\intuitive control" constraints and into more advanced robotic systems designed for
everyday tasks.
ContributorsIson, Mark (Author) / Artemiadis, Panagiotis (Thesis advisor) / Santello, Marco (Committee member) / Greger, Bradley (Committee member) / Berman, Spring (Committee member) / Sugar, Thomas (Committee member) / Fainekos, Georgios (Committee member) / Arizona State University (Publisher)
Created2015
Description
Bioscience High School, a small magnet high school located in Downtown Phoenix and a STEAM (Science, Technology, Engineering, Arts, Math) focused school, has been pushing to establish a computer science curriculum for all of their students from freshman to senior year. The school's Mision (Mission and Vision) is to: "..provide a rigorous, collaborative, and relevant academic program emphasizing an innovative, problem-based curriculum that develops literacy in the sciences, mathematics, and the arts, thus cultivating critical thinkers, creative problem-solvers, and compassionate citizens, who are able to thrive in our increasingly complex and technological communities." Computational thinking is an important part in developing a future problem solver Bioscience High School is looking to produce. Bioscience High School is unique in the fact that every student has a computer available for him or her to use. Therefore, it makes complete sense for the school to add computer science to their curriculum because one of the school's goals is to be able to utilize their resources to their full potential. However, the school's attempt at computer science integration falls short due to the lack of expertise amongst the math and science teachers. The lack of training and support has postponed the development of the program and they are desperately in need of someone with expertise in the field to help reboot the program. As a result, I've decided to create a course that is focused on teaching students the concepts of computational thinking and its application through Scratch and Arduino programming.
ContributorsLiu, Deming (Author) / Meuth, Ryan (Thesis director) / Nakamura, Mutsumi (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Electromyography (EMG) and Electroencephalography (EEG) are techniques used to detect electrical activity produced by the human body. EMG detects electrical activity in the skeletal muscles, while EEG detects electrical activity from the scalp. The purpose of this study is to capture different types of EMG and EEG signals and to determine if the signals can be distinguished between each other and processed into output signals to trigger events in prosthetics. Results from the study suggest that the PSD estimates can be used to compare signals that have significant differences such as the wrist, scalp, and fingers, but it cannot fully distinguish between signals that are closely related, such as two different fingers. The signals that were identified were able to be translated into the physical output simulated on the Arduino circuit.
ContributorsJanis, William Edward (Author) / LaBelle, Jeffrey (Thesis director) / Santello, Marco (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2013-12
Description
In this thesis work, a novel learning approach to solving the problem of controllinga quadcopter (drone) swarm is explored. To deal with large sizes, swarm control is
often achieved in a distributed fashion by combining different behaviors such that
each behavior implements some desired swarm characteristics, such as avoiding ob-
stacles and staying close to neighbors. One common approach in distributed swarm
control uses potential fields. A limitation of this approach is that the potential fields
often depend statically on a set of control parameters that are manually specified a
priori. This paper introduces Dynamic Potential Fields for flexible swarm control.
These potential fields are modulated by a set of dynamic control parameters (DCPs)
that can change under different environment situations. Since the focus is only on
these DCPs, it simplifies the learning problem and makes it feasible for practical use.
This approach uses soft actor critic (SAC) where the actor only determines how to
modify DCPs in the current situation, resulting in more flexible swarm control. In
the results, this work will show that the DCP approach allows for the drones to bet-
ter traverse environments with obstacles compared to several state-of-the-art swarm
control methods with a fixed set of control parameters. This approach also obtained
a higher safety score commonly used to assess swarm behavior. A basic reinforce-
ment learning approach is compared to demonstrate faster convergence. Finally, an
ablation study is conducted to validate the design of this approach.
ContributorsFerraro, Calvin Shores (Author) / Zhang, Yu (Thesis advisor) / Ben Amor, Hani (Committee member) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2022
Description
Despite the rapid adoption of robotics and machine learning in industry, their application to scientific studies remains under-explored. Combining industry-driven advances with scientific exploration provides new perspectives and a greater understanding of the planet and its environmental processes. Focusing on rock detection, mapping, and dynamics analysis, I present technical approaches and scientific results of developing robotics and machine learning technologies for geomorphology and seismic hazard analysis. I demonstrate an interdisciplinary research direction to push the frontiers of both robotics and geosciences, with potential translational contributions to commercial applications for hazard monitoring and prospecting. To understand the effects of rocky fault scarp development on rock trait distributions, I present a data-processing pipeline that utilizes unpiloted aerial vehicles (UAVs) and deep learning to segment densely distributed rocks in several orders of magnitude. Quantification and correlation analysis of rock trait distributions demonstrate a statistical approach for geomorphology studies. Fragile geological features such as precariously balanced rocks (PBRs) provide upper-bound ground motion constraints for hazard analysis. I develop an offboard method and onboard method as complementary to each other for PBR searching and mapping. Using deep learning, the offboard method segments PBRs in point clouds reconstructed from UAV surveys. The onboard method equips a UAV with edge-computing devices and stereo cameras, enabling onboard machine learning for real-time PBR search, detection, and mapping during surveillance. The offboard method provides an efficient solution to find PBR candidates in existing point clouds, which is useful for field reconnaissance. The onboard method emphasizes mapping individual PBRs for their complete visible surface features, such as basal contacts with pedestals–critical geometry to analyze fragility. After PBRs are mapped, I investigate PBR dynamics by building a virtual shake robot (VSR) that simulates ground motions to test PBR overturning. The VSR demonstrates that ground motion directions and niches are important factors determining PBR fragility, which were rarely considered in previous studies. The VSR also enables PBR large-displacement studies by tracking a toppled-PBR trajectory, presenting novel methods of rockfall hazard zoning. I build a real mini shake robot providing a reverse method to validate simulation experiments in the VSR.
ContributorsChen, Zhiang (Author) / Arrowsmith, Ramon (Thesis advisor) / Das, Jnaneshwar (Thesis advisor) / Bell, James (Committee member) / Berman, Spring (Committee member) / Christensen, Philip (Committee member) / Whipple, Kelin (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
For a system of autonomous vehicles functioning together in a traffic scene, 3Dunderstanding of participants in the field of view or surrounding is very essential for
assessing the safety operation of the involved. This problem can be decomposed into online
pose and shape estimation, which has been a core research area of computer vision for over
a decade now. This work is an add-on to support and improve the joint estimate of the pose
and shape of vehicles from monocular cameras. The objective of jointly estimating the
vehicle pose and shape online is enabled by what is called an offline reconstruction
pipeline. In the offline reconstruction step, an approach to obtain the vehicle 3D shape with
keypoints labeled is formulated.
This work proposes a multi-view reconstruction pipeline using images and masks
which can create an approximate shape of vehicles and can be used as a shape prior. Then
a 3D model-fitting optimization approach to refine the shape prior using high quality
computer-aided design (CAD) models of vehicles is developed. A dataset of such 3D
vehicles with 20 keypoints annotated is prepared and call it the AvaCAR dataset. The
AvaCAR dataset can be used to estimate the vehicle shape and pose, without having the
need to collect significant amounts of data needed for adequate training of a neural
network. The online reconstruction can use this synthesis dataset to generate novel
viewpoints and simultaneously train a neural network for pose and shape estimation. Most
methods in the current literature using deep neural networks, that are trained to estimate
pose of the object from a single image, are inherently biased to the viewpoint of the images
used. This approach aims at addressing these existing limitations in the current method by
delivering the online estimation a shape prior which can generate novel views to account
for the bias due to viewpoint. The dataset is provided with ground truth extrinsic parameters
and the compact vector based shape representations which along with the multi-view
dataset can be used to efficiently trained neural networks for vehicle pose and shape
estimation. The vehicles in this library are evaluated with some standard metrics to assure
they are capable of aiding online estimation and model based tracking.
ContributorsDUTTA, PRABAL BIJOY (Author) / Yang, Yezhou (Thesis advisor) / Berman, Spring (Committee member) / Lu, Duo (Committee member) / Arizona State University (Publisher)
Created2022
Description
This work has improved the quality of the solution to the sparse rewards problemby combining reinforcement learning (RL) with knowledge-rich planning. Classical
methods for coping with sparse rewards during reinforcement learning modify the
reward landscape so as to better guide the learner. In contrast, this work combines
RL with a planner in order to utilize other information about the environment. As
the scope for representing environmental information is limited in RL, this work has
conflated a model-free learning algorithm – temporal difference (TD) learning – with
a Hierarchical Task Network (HTN) planner to accommodate rich environmental
information in the algorithm. In the perpetual sparse rewards problem, rewards
reemerge after being collected within a fixed interval of time, culminating in a lack of a
well-defined goal state as an exit condition to the problem. Incorporating planning in
the learning algorithm not only improves the quality of the solution, but the algorithm
also avoids the ambiguity of incorporating a goal of maximizing profit while using
only a planning algorithm to solve this problem. Upon occasionally using the HTN
planner, this algorithm provides the necessary tweak toward the optimal solution. In
this work, I have demonstrated an on-policy algorithm that has improved the quality
of the solution over vanilla reinforcement learning. The objective of this work has
been to observe the capacity of the synthesized algorithm in finding optimal policies to
maximize rewards, awareness of the environment, and the awareness of the presence
of other agents in the vicinity.
ContributorsNandan, Swastik (Author) / Pavlic, Theodore (Thesis advisor) / Das, Jnaneshwar (Thesis advisor) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2022
Description
In this work, I propose to bridge the gap between human users and adaptive control of robotic systems. The goal is to enable robots to consider user feedback and adjust their behaviors. A critical challenge with designing such systems is that users are often non-experts, with limited knowledge about the robot's hardware and dynamics. In the domain of human-robot interaction, there exist different modalities of conveying information regarding the desired behavior of the robot, most commonly used are demonstrations, and preferences. While it is challenging for non-experts to provide demonstrations of robot behavior, works that consider preferences expressed as trajectory rankings lead to users providing noisy and possibly conflicting information, leading to slow adaptation or system failures. The end user can be expected to be familiar with the dynamics and how they relate to their desired objectives through repeated interactions with the system. However, due to inadequate knowledge about the system dynamics, it is expected that the user would find it challenging to provide feedback on all dimension's of the system's behavior at all times. Thus, the key innovation of this work is to enable users to provide partial instead of completely specified preferences as with traditional methods that learn from user preferences. In particular, I consider partial preferences in the form of preferences over plant dynamic parameters, for which I propose Adaptive User Control (AUC) of robotic systems. I leverage the correlations between the observed and hidden parameter preferences to deal with incompleteness. I use a sparse Gaussian Process Latent Variable Model formulation to learn hidden variables that represent the relationships between the observed and hidden preferences over the system parameters. This model is trained using Stochastic Variational Inference with a distributed loss formulation. I evaluate AUC in a custom drone-swarm environment and several domains from DeepMind control suite. I compare AUC with the state-of-the-art preference-based reinforcement learning methods that are utilized with user preferences. Results show that AUC outperforms the baselines substantially in terms of sample and feedback complexity.
ContributorsBiswas, Upasana (Author) / Zhang, Yu (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Berman, Spring (Committee member) / Liu, Lantao (Committee member) / Arizona State University (Publisher)
Created2023