Announcements

Author: Yekanth Ram Chalumuri

Title of dissertation: TOWARDS AUTOMATION OF HEMORRHAGE DIAGNOSTICS AND THERAPEUTICS

Date/time:  April 10th, 2024 at 12pm

Location:  ERF 1207 (IREAP Building)

Committee members:

Dr. Jin-Oh Hahn, Advisor and Chair

Dr. Yang Tao, Dean’s Representative

Dr. Hosam Fathy

Dr. Mark Fuge

Dr. Yancy Diaz-Mercado

Dr. Andrew Reisner

Abstract:

This thesis primarily focuses on developing algorithms and methodologies to achieve the broader aim of advancing the care in hemorrhage diagnostics and therapeutics, especially in low resource settings. The first goal of this thesis is to develop algorithms that can detect hemorrhage using non-invasive physiological signals. Our results showed that our machine learning algorithm can successfully classify various types of hypovolemia. We also developed a physics-based approach to detect and estimate internal hemorrhage even when the body is being compensated by fluid resuscitation using continuous non-invasive hemoglobin measurements. We evaluated the model in silico and determined the maximum acceptable measurement noise that can make these algorithms effective.

The second objective is to advance the regulatory aspects of physiological closed-loop control systems in maintaining blood pressure at a desired value during hemorrhage. Physiological closed-loop control systems offer an exciting opportunity to treat hemorrhage in low resource settings but often face regulatory challenges due to safety concerns. A physics-based model with rigorous validation can improve regulatory aspects of such systems but current validation techniques are very naïve. We developed a physics-based model that can predict blood pressure, heart rate, cardiac output, and hematocrit during hemorrhage and resuscitation and validated using a validation framework that uses sampled digital twins for validation along with more rigorous validation metrics. Overall, the goal of this research is to improve the care and outcomes of patients with hemorrhagic shock by utilizing machine learning, inference, and modeling approaches for early detection and treatment.

Author: Sidney Molnar

Title of dissertation: Metareasoning Strategies to Correct Navigation Failures of Autonomous Ground Robots

Date/time: April 8th, 2024 at 10:00am

Zoom: https://umd.zoom.us/j/9892794999?omn=94673990602

Location: 2164 DeWALT Conference Room, Glenn L. Martin Hall.

Committee members:

• Dr. Jeffrey Herrmann, Advisor and Chair
• Dr. Michael Otte
• Dr. Shapour Azarm

Abstract: Due to the complexity of autonomous systems, theoretically perfect path planning algorithms sometimes fail because of unexpected behaviors that occur when these systems interact with various sub-processes like perception, mapping, and goal planning. These failures can prevent the success of a mission, especially in complex and unexplored environments. Metareasoning, or “thinking about thinking,” is one approach to mitigate these planning failures. This project introduces a novel metareasoning approach that employs various methods of monitoring and control to identify and address path planning irregularities that lead to failures. All methods were integrated into the ARL ground autonomy stack, which utilizes both global and local path planning ROS nodes. The monitoring methods proposed include listening to messages from the planning algorithms, assessing the environmental context of the robot, expected progress methods that evaluate the robot’s progress based on its movement capabilities from a milestone checkpoint, and fixed radius methods that use parameters selected based on mission objectives to assess progress from a milestone checkpoint. The control policies introduced are metric-based sequential policies which select new planner combinations based on benchmark robot performance metrics, context-based pairs policies that assess the effects of switching between two planner combinations, and a restart policy that relaunches a new instance of the same planner combination. The study evaluated which combinations of monitoring and control policies improved or degraded navigation performance by assessing how close the robot could get to the final mission goal. Additionally, this thesis suggests areas for further research to determine the conditions under which metareasoning can improve navigation.

Author: Christina Nikiforidou

Title of dissertation: Locomotion on Granular Media: Reduced-Order Models

Date/time:  April 3rd, 2024 at 9:30am

Location: 2164 DeWALT Conference Room, Glenn L. Martin Hall.

Committee members:

Dr. Balakumar Balachandran, Advisor and Chair

Dr. Peter Chung 

Dr. Teng Li

Abstract: (attached)

Author: Gurtajbir Herr

Title of dissertation:  ON DATA-BASED MAPPING AND NAVIGATION OF UNMANNED GROUND VEHICLES

Date/time:  April 3rd, 2024 at 12:00pm

Location: AVW 1146 (ISR seminar room)

Committee members:

Dr. Nikhil Chopra, Advisor and Chair

Dr. Anubhav Datta, Dean’s Representative

Dr. Balakumar Balachandran

Dr. Miao Yu

Dr. Yancy Diaz-Mercado

Abstract:

Unmanned ground vehicles (UGVs) have seen tremendous advancement in their capabilities and applications in the past two decades. With several key algorithmic and hardware breakthroughs and advancements in deep learning, UGVs are quickly becoming ubiquitous, finding applications as self-driving cars, in remote site inspections, in hospitals and shopping malls, among several others. Motivated by their large-scale adoption, this dissertation aims to enable the navigation of UGVs in complex environments. In this dissertation, we develop a supervised learning-based navigation algorithm that utilizes model predictive control (MPC)  for providing training data. Improving MPC performance by data-based modelling of complex vehicle dynamics is then addressed. Finally, this dissertation deals with detecting and registering transparent objects that may deteriorate navigation performance.

Navigation in dynamic environments poses unique challenges, particularly due to the limited knowledge of the decisions made by other agents and their objectives. In this dissertation, we propose a solution that utilizes an MPC-based planner as an expert to generate high-quality motion commands for a car-like robot operating in a simulated dynamic environment. These commands are then used to train a deep neural network, which learns to navigate. The deep learning-based planner is further enhanced with safety margins to improve its effectiveness in collision avoidance. We then evaluate the performance of our method through simulations and real-world experiments, demonstrating its superior performance in terms of obstacle avoidance and successful mission completion. This research has practical implications for the development of safer and more efficient autonomous vehicles.

Many real-world applications rely on MPC to control UGVs due to its safety guarantees and constraint satisfaction properties. However, the performance of such MPC-based solutions is heavily reliant on the accuracy of the motion model. This dissertation addresses this challenge by exploring a data-based approach to discovering vehicle dynamics. Unlike existing physics-based models that require extensive testing setups and manual tuning for new platforms and driving surfaces, our approach leverages the universal differential equations (UDEs) framework to identify unknown dynamics from vehicle data. This innovative approach, which does not make assumptions about the unknown dynamics terms and directly models the vector field, is then deployed to showcase its efficacy. This research opens up new possibilities for more accurate and adaptable motion models for UGVs. 
With the increasing adoption of glass and other transparent materials, UGVs must be able to detect and register them for reliable navigation. Unfortunately, such objects are not easily detected by LiDARs and cameras. In this dissertation, we study algorithms for detecting and including glass objects in a Graph SLAM framework. We use a simple and computationally inexpensive glass detection scheme to detect glass objects. We present the methodology to incorporate the identified objects into the occupancy grid maintained by such a framework. We also address the issue of drift accumulation that can affect mapping performance when operating in large environments.

Author: Weidi Yin

Title of dissertation:  De-conflicting Management of Fluid Resuscitation and Intravenous Medication Infusion

Date/time:  April 4th, 2024 at 12:15pm

Location: 2164 DeWALT Conference Room, Glenn L. Martin Hall.

Committee members:

Dr. Jin-Oh Hahn, Advisor and Chair

Dr. Robert M. Sanner, Dean’s Representative

Dr. Hosam Fathy

Dr. Nikhil Chopra

Dr. Yancy Diaz-Mercado

Abstract: (attached)

Author: Sangeeth Balakrishnan

Title of dissertation: MACHINE LEARNING IN SCARCE DATA REGIME FOR DESIGN AND DISCOVERY OF MATERIALS

Date/time: March 29th, 2024 at 10am

Location: 2164 DeWALT Conference Room, Glenn L. Martin Hall.

Committee members:

Dr. Peter Chung, Advisor and Chair

Dr. Mark Fuge, Co-chair

Dr. Yifei Mo, Dean’s Representative

Dr. Nikhil Chopra

Dr. Hugh Bruck

Dr. Brian Barnes

Abstract:

In recent years, data-driven approaches based on machine learning have emerged as a promising method for rapid and efficient estimation of the structure-property-performance relationships, leading to the discovery of advanced materials. However, the cost and time required to obtain relevant data have limited application of these methods to only a few classes of materials where extensive property data are available. Moreover, the material property prediction poses its own unique set of challenges, in part, due to: 1) the complex non-linear response of materials in different space and time domains, 2) inherent variability in material in terms of composition and processing conditions from the atomic to the macroscopic scales, and 3) the need for accurate, rapid and less expensive predictive models for accelerated material discovery. This dissertation aims to develop three novel machine learning frameworks for constructing targeted learning frameworks and discovering novel materials when dealing with limited available data. The dissertation also highlights the future directions and challenges of such approaches.

In the first approach, we develop data-driven methods to estimate the material properties under shock compression. A novel featurization approach combining synthetic and physical features was developed showing substantial improvements in the machine learning model performance. The effects of feature engineering, model choices, and uncertainty in the experimental data were investigated. In the second approach, we develop a novel joint embedding framework that enables transfer learning, with the target of locally optimizing the shock wave properties of nitrogen-rich molecules. This work is motivated by a need to overcome challenges associated with the translation of machine learning approaches to domains where there is a relative lack of domain-specific data. However, the properties studied in the second approach do not consider factors needed to assemble a complete material system. Therefore, in the third and final approach, we investigate material systems whose properties at system level are determined by various upstream design factors, such as the composition of raw materials, manufacturing variability, and considerations involved while assembling the system. We propose a stacked ensemble learning framework to make statistical inferences about the system properties.

Title of dissertation: ANALYSIS OF THE LIFE-CYCLE COST AND CAPABILITY TRADEOFFS ASSOCIATED WITH THE PROCUREMENT AND SUSTAINMENT OF OPEN SYSTEMS

Date/time: March 19th at 9:00 AM

Location: 2164 DeWALT Conference Room, Glenn L. Martin Hall.

Zoom link: https://umd.zoom.us/j/6254630014?omn=99524160244

Committee members:
Professor Peter A. Sandborn, Chair
Professor Bilal M. Ayyub, Dean’s Representative
Professor Katrina Groth
Professor Jeffrey Herrmann
Professor William Lucyshyn

Author: Samuel Gigioli

Date: November 13th, 2023 at 10:00AM

Location: IREAP 1207

Committee Members:

Dr. Ashwani Gupta, Chair
Dr. Bao Yang
Dr. Kenneth

Title: DISSECTION AND MODELING OF AEDC WIND TUNNEL 9 CONTROL LAW AND FACILITY DURING BLOW PHASE

Abstract:

This work presents the progress towards a mathematical modeling of the Arnold
Engineering Development Complex (AEDC) Wind Tunnel 9 control law during the blow
phase of a given tunnel run, composing of electrical analog physics, ideal gas control
volume physics, incompressible fluid mechanics, and force balance kinematics. Tunnel 9
does not currently have a well-defined process for developing control law parameters for a
new tunnel condition. The modeled control law is developed based on electrical schematics
and theoretical analog circuitry. The model is further refined by analyzing historical data
through a two-factor interaction analysis of several run-condition factors. The primary goal
of this work is to provide enhanced support to the Tunnel 9 engineers with the ability to
model different run conditions. Key facility measurements can be estimated, aiding in the
determination if proposed non-standard run conditions will meet or maintain the facility
capabilities, and if the facility can be operated under safe operating limits. The secondary
goal of this model is to progress toward a digitally controlled valve system to replace the
current analog system. Such changes may enable considerably more advantages in facility
(1) performance, (2) health monitoring, (3) maintainability, and (4) sustainment.

Author: Gabriel Smith

Date: October 26, 2023 at 2pm EST

Location: EGR-2164, Martin Hall

Committee Members:

• Professor Sarah Bergbreiter, Advisor
• Professor Ryan Sochol, Chair
• Professor Don DeVoe
• Professor Hugh Bruck
• Professor Jeffrey Shultz, Dean’s Representative

Title: DIRECT LASER WRITE PROCESSES FOR SPIDER-INSPIRED MICROHYDRAULICS AND MULTI-SCALE LIQUID METAL DEVICES

Abstract: 

Direct Laser Write (DLW) through two-photon polymerization (2PP) empowers us to delve into the realm of genuine three-dimensional design complexity for microsystems, enabling features smaller than a single micrometer. This dissertation develops two novel fabrication processes that leverage DLW for functional fluidic microsystems. In the first process, we are inspired by arachnids that use internal hemolymph pressure to actuate extension in one or more of their leg joints. The inherent large foot displacement to body length ratio that arachnids can achieve through hydraulics relative to muscle-based actuators is both energy and volumetrically efficient. Until recent advances in nano/microscale 3-D printing with 2PP, the physical realization of synthetic complex ‘soft’ joints would have been impossible to replicate and fill with hydraulic fluid into a sealed sub-millimeter system. This dissertation demonstrates the smallest scale 3D-printed hydraulic actuator 4.9 × 10⁻⁴ mm^{^3} by more than an order of magnitude. The use of stiff 2PP polymers with micron-scale dimensions enables compliant membranes similar to exoskeletons seen in nature without the requirement for low-modulus materials. The bio-inspired system is designed to mimic similar hydraulic pressure-activated mechanisms in arachnid joints utilized for large displacement motions relative to body length. Using variations on this actuator design, we demonstrate the ability to transmit forces with relatively large magnitudes (milliNewtons) in 3D space, as well as the ability to direct motion that is useful towards microrobotics and medical applications. Microscale hydraulic actuation provides a promising approach to the transmission of large forces and 3D motions at small scales, previously unattainable in wafer-level 2D micro-electromechanical systems (MEMS).

The second fabrication process focuses on incorporating functionality through the use of liquid metals in 3D DLW structures. Room temperature eutectic Gallium Indium (eGaIn)-based liquid metal devices with stretchable, conductive, and reconfigurable behavior show great promise across many areas of technology, including robotics, communications, and medicine. Microfluidics provide one means of creating eGaIn devices and circuits, but these devices are typically limited to larger feature sizes. Developments in 3D printing via DLW have enabled sub-100 µm complex microfluidic devices, though interfacing microfluidic devices manufactured with DLW to larger millimeter-scale systems is difficult. The reduced channel diameter creates challenges for removing resist from the channels, filling microchannels with eGaIn, and electrically integrating them to larger channels or other circuitry. These challenges have prevented microscale liquid metal devices from being used more widely. In this dissertation, we demonstrate a facile, low-cost multiscale process for printing DLW microchannels and devices onto centimeter-scale custom fluidic channel substrates fabricated via stereolithography (SLA). This work demonstrates a robust interface between the two independently printed materials and greatly simplifies the filling of eGaIn microfluidic channels down to 50 µm in diameter, with the potential to achieve even smaller feature sizes of liquid metals. This work also demonstrates eGaIn coils with resistance of 43-770 mΩ and inductance of 2-4 nH. As a result, this process empowers us to manufacture interfaces that are not only low-temperature but also conductive and flexible. These interfaces find their application in connecting with sensors, actuators, and integrated circuits, thereby opening new avenues in the field of 3D electronics. Furthermore, our approach extends the lower limits of size-dependent properties for passive electronic components like resistors, capacitors, and inductors crafted from liquid metal, expanding the frontiers of possibilities in miniature electronic design.