Engineering Commons^™

Al-Driven Interfacial Gap Prediction In Overlapped Al/Cu Laser Weld Joint For Battery Applications, Hyeonhee Kim, Sanghoon Kang, Cheolhee Kim, Yong Hoon Jang, Minjung Kang

Mechanical and Materials Engineering Faculty Publications and Presentations

The battery tab-to-busbar welding process forms the primary electrical path in battery packs and is directly linked to both performance and safety. Variations in jig alignment, material tolerance, and forming quality can cause small interfacial gaps that lead to weak welds. An artificial intelligence (AI)-driven method was proposed in this study for predicting interfacial gaps in aluminum-copper overlap joints by integrating deep learning with multi-sensor data. A charge-coupled device (CCD) camera, spectrometer, and optical coherence tomography (OCT) sensors were employed to develop and validate deep learning models under varying gap conditions. The results revealed that the variation in melt-pool dimensions, …

Characterization Of Sediment Loads And Size Distribution In Nebraska Roadway Runoff, Pavel Shrestha

Department of Civil and Environmental Engineering: Dissertations, Theses, and Student Research

The Nebraska Department of Transportation (NDOT) must manage sediment and pollutant loads from roadway runoff to meet stormwater regulations for discharges into impaired waters. The SAFL Baffle, a hydrodynamic separator used by NDOT, depends on accurate estimates of total suspended solids (TSS) and particle size distribution (PSD). However, existing studies show large variability in these characteristics, limiting their relevance to Nebraska roadways.

This study monitored stormwater runoff for 1.5 years at four NDOT-maintained sites—two in Lincoln and two in Beatrice—that received runoff from areas outside the roadway right-of-way. The SAFL Baffle was evaluated using the SHSAM (Sizing Hydrodynamic Separators and …

Coupling The Parflow Integrated Hydrology Model Within The Nasa Land Information System: A Case Study Over The Upper Colorado River Basin, P.Eyman Abbaszadeh, Fadji Zaouna Maina, Chen Yang, Dan Rosen, Sujay Kumar, Matthew Rodell, Reed Maxwell

Civil and Environmental Engineering Faculty Publications and Presentations

Understanding, observing, and simulating Earth's water cycle is imperative for effective water resource management in the face of a changing climate. While NASA's Land Information System (LIS)/Noah-MP is widely used for land surface modeling, its ability to represent groundwater processes is limited. In contrast, the ParFlow hydrologic model explicitly simulates subsurface water movement. This study explores the effectiveness and usefulness of the newly coupled modeling framework, ParFlow-LIS/Noah-MP (PF-LIS/Noah-MP) over the Upper Colorado River Basin (UCRB). The framework integrates the strengths of both models to provide a physically based representation of surface and subsurface processes and their interactions. Unlike standalone LIS/Noah-MP, …

Systems Intelligence Manager: Warfighter Dominance 2025 Technical Review Key Program, Daniel Hornberger

Space Dynamics Laboratory Publications

Objective & Background

• Objective
• Provide a governing network framework that reduces network congestion and improves connectivity, stability, and resilience
• Provide a single point for systems to connect to on varied networks, which also federates data to required entities
• Manage complex military CONOPs, controlling one or many heterogeneous unmanned platforms while coordinating collection efforts of varying sensor suites on each platform

Atomistic Insights Into Dual Mechanisms For Nacl-Driven Dissolution And Polymerization Of Tricalcium Silicate, Wei Zhang, Jia Sun, Juntao Dang, Bo Tao Huang, Biqin Dong, Hongyan Ma, Dongshuai Hou

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

In this study, experimental characterization and reactive molecular dynamics simulations were integrated to reveal the effects of NaCl on the early hydration of tricalcium silicate (C3S). The results demonstrate that NaCl significantly accelerates the early hydration of C3S by promoting Ca dissolution and silicate tetrahedra polymerization. Specifically, Cl^–ions coordinate with surface Ca, weakening the Ca–O bonds in C3S and reducing the energy barrier for Ca dissolution. Meanwhile, Na⁺ions compete with Ca²⁺for the O atoms, creating localized charge imbalance and attracting protons, which destabilize Si–O bonds and facilitate the polymerization of silicate tetrahedra. These effects …

Experimental Investigation Of 3d Printed Tpu Triboelectric Composites For Biomechanical Energy Conversion In Knee Implants, Osama Abdalla, Milad Azami, Amir Ameli, Emre Salman, Milutin Stanacevic, Ryan Willing, Shahrzad Towfighian

Mechanical Engineering Faculty Scholarship

Although total knee replacements have an insignificant impact on patients’ mobility and quality of life, real-time performance monitoring remains a challenge. Monitoring the load over time can improve surgery outcomes and early detection of mechanical imbalances. Triboelectric nanogenerators (TENGs) present a promising approach as a self-powered sensor for load monitoring in TKR. A TENG was fabricated with dielectric layers consisting of Kapton tape and 3D-printed thermoplastic polyurethane (TPU) matrix incorporating CNT and BTO fillers, separated by an air gap and sandwiched between two copper electrodes. The sensor performance was optimized by varying the concentrations of BTO and CNT to study …

Vertical Sorting Of Bed Material In Gravel-Bed Streams-- Insights From Long-Term Observations In East Creek, British Columbia, Marwan A. Hassan, Tianqi Xing, Conor Mcdowell, Kevin J. Pierce, Mike Turley, Sol Leader-Cole, Enrica Viparelli

Faculty Publications

The vertical sorting of streambed grains is a key control on river channel stability and sediment transport rates. In this study, we report on burial depths and mobility characteristics of coarse sediment in a small gravel-bed stream using an extensive data set of nearly 1,500 magnetically tagged tracer grains, deployed and annually surveyed between 2004 and 2018. We observe that sediment burial correlates with grain size and event magnitude, and we identify correlations between the burial depths of coarse grains and their mobility, residence time, and travel distance characteristics. A particularly large event in 2007 produced significant vertical sorting which …

An Integrated Decision Support System For Bim Level 3 Implementation, Lama Abumoeilak, Salwa Beheiry, Serter Atabay

Civil and Environmental Engineering Faculty Publications

The Architecture, Engineering, and Construction (AEC) sector accounts for 39% of greenhouse gas emissions, 40% of solid waste, and 12% of potablewater usage globally, underscoring the need for sustainable, efficient practices. Building Information Modeling (BIM) offers a digital framework to address these challenges through lifecycle management, collaboration, and efficiency gains. However, most organizations remain at BIM Level 2 maturity, which limits their potential for full integration. This study proposes a comprehensive Decision Support System (DSS) to facilitate the adoption of BIM Level 3, with an emphasis on collaboration, sustainability, and data interoperability. The DSS integrates Structural Equation Modeling (SEM), Analytical …

Development And Validation Of A Composite Digital Balance Score For Spinocerebellar Ataxia: A Prospective Study., James Mcnames, Vrutangkumar V. Shah, Hannah L. Casey, Kristen L. Sowalsky, Mahmoud El-Gohary, Delaram Safarpour, Patricia Carlson-Kuhta, Jeremy D. Schmahmann, Liana S. Rosenthal, Susan Perlman, Multiple Additional Authors

Electrical and Computer Engineering Faculty Publications and Presentations

Clinical trials in spinocerebellar ataxia are currently limited by the large sample sizes required by available clinical endpoints. We aimed to devise a digital composite measure of standing and walking balance using wearable inertial sensors that would require smaller sample sizes. The new score is called the Score of Integrated Balance in Ataxia (SIBA).

Reliability Targeted Snow Loads And Winter Wind Parameters For Locations Outside Of The Conterminous United States, Brennan L. Bean, Nicholas Brimhall, Bikram Bhusal, Marc Maguire, Maha Moussa

Browse all Datasets

The national building standard ASCE 7 moved to reliability-targeted snow loads (RTSLs) in the 2022 version. This necessitates the development of RTSLs for international locations. This repository contains the data and code needed to produce RTSLs and Winter Wind Parameters for locations outside of the Conterminous United States (OCONUS). It relies on annual maximum snow loads provided in a separate data release (see Brimhall et al. 2025).

Insights On Ai-Supported Uncrewed And Autonomous Systems Education, Brent A. Terwilliger Ph. D, John Faraca

Publications

Artificial Intelligence (AI) related technology is reshaping the educational experience in programs focused on uncrewed and autonomous systems, aviation, robotics, and aerospace, with growing implications for workforce readiness and cross-sector innovation. Early survey data, capturing student, educator, and employer perspectives, reveals that AI-supported tools are notably changing student engagement, communication, and skills development. Initial indications underscores the importance of AI proficiency and technological familiarity in hiring and workforce development, particularly in technical and operational roles. Key areas of focus include the use of AI to strengthen outreach and interactivity; enrich instruction through intelligent simulations; inform curricular improvements using data analytics; …

Treating Low-Concentration Methane Emissions Via A Methanotroph-Based Biotrickling Filter: Techno-Economic And Life Cycle Assessment, Waaseyaaban Landgren, Robert Handler, David Shonnard, Mary E. Lidstrom

Michigan Tech Publications

Methane, a greenhouse gas which has a global warming potential 80 times greater than carbon dioxide on a 20-year time scale, greatly contributes to global warming. Removing 1 Gt of atmospheric methane by 2050 would limit global temperature increase from reaching 1.5 °C. Currently, biotrickling filter systems for removing atmospheric methane via methanotrophs exist, but not for very low methane concentrations (< 1 v%). Recent work at the University of Washington to isolate and improve a microbial strain which thrives at 500 ppmv CH4 has removed one obstacle in making this technology feasible. In this study, techno-economic and environmental life cycle assessment analyses conducted on this process have assessed its economic feasibility, greenhouse gas reduction potential, and possible areas of improvement. Study results show that at 500 ppmv CH4, this process could remove atmospheric methane at a cost of USD 3992–5224/tCH4. The best-performing case also produces annual net reductions in warming potential by 276–311 tCO2e/120 m3 process unit deployed. Many opportunities exist to improve the outcomes of the baseline analysis even further, especially related to reducing the transport distance of media and harvested biomass.

Intrinsic Defects (Vacancies And Antisites) In Neutron Irradiated Cdsip2 Crystals, Timothy D. Gustafson, Elizabeth M. Scherrer, Nancy C. Giles, Kevin T. Zawilski, Peter G. Schunemann, Jonathan E. Slagle, Kent L. Averett, Larry E. Halliburton

Faculty Publications

Cadmium silicon phosphide (CdSiP₂) is a nonlinear optical material widely used in optical parametric oscillators. Intrinsic defects (vacancies and antisites) are responsible for unwanted broad optical absorption bands in these crystals that degrade the performance of the devices. In the present work, optical absorption and electron paramagnetic resonance (EPR) spectra are acquired (at room temperature and 12 K, respectively) from a neutron-irradiated CdSiP₂ crystal. After the irradiation, the crystal is highly absorbing from the band edge near 600 nm to beyond 1.3 μm because of overlapping defect-related absorption bands. Heating to 550 °C removes nearly all the …

Halogenated Flame Retardants In The Sediments Of The Lower Great Lakes And Region-Wide Discoveries, Tian Lin, Shanshan Zhou, Huan He, Jiehong Guo, Neil C. Sturchio, Karl J. Rockne, John P. Giesy, An Li

Michigan Tech Publications

This work aims to provide updated information and insights on the contamination by halogenated flame retardants (HFRs) of the Great Lakes sediments. Thirty HFRs, including polybrominated diphenyl ethers (PBDEs), dechlorane plus (DPs), and other chlorinated (CFRs) or brominated (BFRs) chemicals, were measured in 400 sediment surface grab and core segment samples from Lakes Erie and Ontario. The data were combined with those from Lakes Superior, Michigan, and Huron to provide a comprehensive region-wide analysis. Together, the target HFRs in the Great Lakes sediment amount to approximately 420 tonnes. Among the five lakes, Lake Ontario had the highest concentrations of CFRs, …

Tacscope: A Miniaturized Vision-Based Tactile Sensor For Surgical Applications, Md Rakibul Islam Prince, Sheeraz Athar, Pokuang Zhou, Yu She

School of Industrial Engineering Faculty Publications

The lack of tactile feedback in robot-assisted minimally invasive surgery (RMIS) limits surgeons’ ability to palpate tissues, a critical technique for locating abnormalities such as tumors. To address this challenge, we introduce TacScope, a novel, vision-based tactile sensor leveraging the magnification properties of a spherical-surface elastomer to provide tactile feedback for advanced clinical applications. TacScope features a robust, low-cost, and easyly fabricate design, enabling seamless integration into surgical robotic setups. It reconstructs high-resolution 3D geometry from variations in particle-density distribution across its elastomer surface, requiring only a single image for calibration. The curved elastomer membrane alters particle-density distribution under …

A Comprehensive Assessment And Benchmark Studyof Large Atomistic Foundation Models For Phonons, Md Zaibul Anam, Ogheneyoma Aghoghovbia, Mohammed Al-Fahdi, Lingyu Kong, Victor Fung, Ming Hu

Faculty Publications

The rapid development of universal machine learning potentials (uMLPs) has enabled efficient, accurate predictions of diverse material properties across broad chemical spaces. While their capability for modeling phonon properties is emerging, systematic benchmarking across chemically diverse systems remains limited. We evaluate six recent uMLPs—EquiformerV2, MatterSim, MACE, and CHGNet—on 2429 crystalline materials from the Open Quantum Materials Database. Models were used to compute atomic forces in displaced supercells, derive interatomic force constants (IFCs), and predict phonon properties including lattice thermal conductivity (LTC), compared with density functional theory and experimental data. The EquiformerV2 pretrained model trained on the OMat24 dataset exhibits strong …

Evaluating Platinum, Gold, Glassy Carbon, And Graphite Anodes For Chlorine Evolution In Molten Calcium Chloride Salt, Cameron Vann, Shelssie Klvacek, Carlos Mejia, Devin Rappleye

Faculty Publications

The chlorine evolution reaction (CER) in molten CaCl₂ plays a critical role in high-temperature electrochemical processes, including chlorination, metal refining, and used nuclear fuel treatment. This study evaluates the performance of gold (Au), platinum (Pt), glassy carbon (GC), and graphite anodes for the CER under consistent electrochemical conditions. Anode performance was assessed based on chlorine (Cl₂) gas evolution, material robustness, and kinetic parameters. Cl₂ generation was directly confirmed using quadrupole mass spectrometry for Pt, GC, and graphite anodes. GC and graphite demonstrated stable and sustained CER activity. Pt and Au were shown to have significant mass …

Scalable Biosynthesis And Recovery Of Poly-3-Hydroxybutyrate Produced From Cotton-Derived Glucose By Cupriavidus Necator, Ashley M. Clark, Lucia E. Gargano, Gabriella M. Fioravanti, Hannah M. Schapiro, Ron G. Kander

School of Design and Engineering Papers

To combat the growing issue of petroleum plastic waste, alternative bio-based polymers are being developed. Many of these biopolymers are made from bio-derived materials, or are biodegradable, but the most promising polymers fall in both categories. Polyhydroxyalkanoates (PHAs) are one such class of polymers, and poly-3-hydroxybutyrate (P3HB), the most popular PHA, has shown great potential. This study utilized two types of cotton-derived glucose, alongside commercial glucose, as a feedstock for the biosynthesis of P3HB by Cupriavidus necator (also known as Ralstonia eutropha). The fermentation took place in a 2-L bioreactor, showing potential for scale-up. A single-solvent extraction method was …

Insights From A Simple Mathematical Model Of Autism Spectrum Disorders, Charles F. Babbs

Weldon School of Biomedical Engineering Faculty Working Papers

This preliminary report explores insights about mechanisms of autism spectrum disorders (ASDs) gained from a mathematical model of interconnected clusters of excitatory neurons. This local, integrate-and-fire, spiking neural network is subjected to random noise from other populations of excitatory and inhibitory neurons outside the network. Its emergent behavior in response to different ratios of inhibitory to excitatory noise mimics several aspects of ASDs. The spiking neural network functions according to rules of classical neurophysiology, involving resting membrane potential, threshold potential, excitatory or inhibitory post-synaptic potentials, action potential, and refractory period. Key parameters include the incremental change in membrane potential, p …

Assessing Riparian Evapotranspiration Dynamics In A Water Conflict Region In Nebraska, Usa, Ivo Z. Gonçalves, Burdette Barker, Christopher M. U. Neale, Derrel L. Martin, Sammy Z. Akasheh

Civil and Environmental Engineering Faculty Publications

The escalating pressure on water resources in agricultural regions has become a catalyst for water conflicts. The adoption of innovative approaches to estimate actual evapotranspiration (ETa) offers potential solutions to mitigate conflicts related to water usage. This research presents the application of a remote sensing-based methodology for estimating actual evapotranspiration (ETa) based on a two-source energy balance model (TSEB) for riparian vegetation in Nebraska, US using the Spatial EvapoTranspiration Modeling Interface (SETMI). Estimated results through SETMI and field data using the eddy covariance system (EC) considering the period 2008–2013 were used to validate the energy balance components and ETa. Modeled …

Calving As A Source Of Acute And Persistent Kinetic Energy To Enhance Submarine Melting Of Tidewater Glaciers, M. F. Shaya, J. D. Nash, E. C. Pettit, J. M. Amundson, R. H. Jackson, D. A. Sutherland, Dylan Winters

Electrical and Computer Engineering Faculty Publications and Presentations

Calving icebergs at tidewater glaciers release large amounts of potential energy. This energy—in principle—could be a source for submarine melting, which scales with near‐terminus water temperature and velocity. Because near‐terminus currents are challenging to observe or predict, submarine melt remains a key uncertainty in projecting tidewater glacier retreat and sea level rise. Here, we study one submarine calving event at Xeitl Sít’ (LeConte Glacier), Alaska, to explore the effect of calving on ice melt, using a suite of autonomously deployed instruments beneath, around, and downstream of the calving iceberg. Our measurements captured flows exceeding 5 m/s and demonstrate how potential …

Improved Streamflow Forecasting Through Swe-Augmented Spatio-Temporal Graph Neural Networks, Akhila Akkala, Soukaina Filali Boubrahimi, Shah Muhammad Hamdi, Pouya Hosseinzadeh, Ayman Nassar

Computer Science Student Research

Streamflow forecasting in snowmelt-dominated basins is essential for water resource planning, flood mitigation, and ecological sustainability. This study presents a comparative evaluation of statistical, machine learning (Random Forest), and deep learning models (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Spatio-Temporal Graph Neural Network (STGNN)) using 30 years of data from 20 monitoring stations across the Upper Colorado River Basin (UCRB). We assess the impact of integrating meteorological variables—particularly, the Snow Water Equivalent (SWE)—and spatial dependencies on predictive performance. Among all models, the Spatio-Temporal Graph Neural Network (STGNN) achieved the highest accuracy, with a Nash–Sutcliffe Efficiency (NSE) of 0.84 …

Evaluation Of An In Situ Forming Composite Hydrogel Based On Gelatin–Sodium Alginate– Polyethylene Oxide For Biomedical Applications: Effect Of Incorporated Sophora Japonica On Hydrogel Performance, Samar A. Salim

Nanotechnology Research Centre

Hydrogels are ideal candidates for biomedical applications such as wound healing, tissue engineering, and bone regeneration due to their porosity and similarity to the extracellular matrix of humans. A gelatin/ sodium alginate (SA) hydrogel with the inclusion of polyethylene oxide (PEO) was utilized to achieve enhanced mechanical strength. Hydrogels were prepared at different ratios of polymer solutions to select the hydrogel that exhibited an optimal gelation time. Sophora japonica, a plant leaf extract (SJLE) rich in flavonoids and isoflavonoids, was added to the hydrogel to enhance tissue repair. The developed hydrogels were extensively characterized for their morphology, porosity, and swelling …

Microstructural Evolution And Magnetic Properties Of Spark Plasma Sintered Smco5 And Smco5-Fe Composites, Farhan Ishrak, Michael Lastovich, Fu-Yun Tsai, Charles Perkins Iv, Henri Baldino, Alex Helmer, Sean Rego, Sanoj Karki, Daniel Hedlund, Rajeev Gupta, Tushar Borkar

Mechanical Engineering Faculty Publications

Optimizing SmCo(5-)based nanocomposites for high-temperature magnetic applications requires balancing coercivity and saturation magnetization, properties often compromised by grain coarsening, oxidation, and secondary phase formation during conventional sintering. This study investigates the microstructural evolution and magnetic properties of SmCo5 and SmCo5-Fe composites processed via high-energy ball milling followed by spark plasma sintering at 900 degrees C and 1000 degrees C, a route designed to retain the nanostructure while enabling rapid densification compared to conventional sintering. A suite of characterization techniques, including electron microscopy, X-ray diffraction, magnetometry, Magneto-optical Kerr effect, and magnetic force microscopy, reveals the extent of consolidation, phase composition, and …

Incorporating The Influence Of Vehicle Mix On Crash Frequency And Severity, Shahrior Pervaz, Manmohan Joshi, Tanmoy Bhowmik, Dewan Ashraful Parvez, Kai Wang, John N. Ivan, Naveen Eluru

Civil and Environmental Engineering Faculty Publications and Presentations

The current approaches for crash frequency and severity prediction in the Highway Safety Manual (HSM) do not employ vehicle mix information. In this research effort, we build advanced alternatives to HSM methods while incorporating vehicle mix information. Two model systems—(a) multivariate Poisson-lognormal model and (b) negative binomial-ordered probit fractional split model—are estimated by incorporating vehicle mix variables. The developed model systems can also capture the influence of observed and unobserved heterogeneity of different independent variables including vehicle mix variables. We estimate the models for three facility types including Urban Arterial 4-Lane Divided segments, Rural 3-Leg STOP-Controlled and Rural 4-Leg STOP-Controlled …

Day-Night Shifts In Water-Soluble Ions Of Size-Resolved Aerosols Before And After The Covid-19 Lockdown In A Coastal Megacity: Metro Manila, Philippines, Grace Betito, Paola Angela Bañaga, Rachel A. Braun, Maria Obiminda Cambaliza, Melliza Templonuevo Cruz, Alexander B. Macdonald, James Bernard Simpas, Connor Stahl, Armin Sooroshian

SOSE Affiliate: Manila Observatory

The COVID-19 pandemic-driven lockdowns offer a unique opportunity to examine how reductions in anthropogenic emissions impacted atmospheric aerosol composition in urban environments. This study investigates the day-night variability of size-resolved water-soluble ions in ambient particulate matter (PM) collected in Metro Manila before (November 2019–February 2020) and after (November 2020–February 2021) lockdown implementation. Using tandem Micro-Orifice Uniform Deposit Impactors (MOUDIs), aerosol samples were collected during daytime (06:00–18:00) and nighttime (18:00–06:00) periods and analyzed for key ionic species (sulfate, ammonium, nitrate, oxalate, sodium, chloride, calcium, and magnesium) via ion chromatography. Submicrometer water-soluble mass declined post-lockdown, particularly during daytime, reflecting suppressed secondary formation …

Using Serial Open Circuit Potentiometry To Study Ce And Gd Deposition In Molten Licl-Kcl Eutectic, Ranon G. Fuller, Guy L. Fredrickson, Devin Rappleye

Faculty Publications

The ability to electrochemically separate individual species in a pyrochemical reprocessing salt relies on first being able to detect a separation in their reaction potentials. This requires the ability to measure reaction potentials with extreme precision. In this work, we introduce a novel technique called serial open circuit potentiometry (SOCP) and demonstrate its effectiveness at precisely measuring metal deposition reaction potentials. SOCP has several advantages over traditional open circuit potentiometry, including its abilities to quantify the error of measured equilibrium potentials by averaging many individual OCP measurements, determine overpotential deposition nucleation potentials to instrument precision, and simultaneously determine the nucleation …

Resilience Oriented Distribution System Service Restoration Considering Overhead Power Lines Affected By Hurricanes, Kehkashan Fatima, Hussain Shareef, Flavio Costa

Michigan Tech Publications

In recent years, there has been an increase in the frequency of severe weather events (like hurricanes). These events are responsible for most power outages in power distribution systems (PDSs). Particularly susceptible to storms are overhead PDSs. In this study, the dynamic Bayesian network (DBN)-based failure model was developed for different hurricane scenarios to predict the line failure of overhead lines. Based on the outcomes of the DBN model, a service restoration model was formulated to maximize restored loads and minimize power losses using Particle Swarm Optimization (PSO)-based distributed generation (DG) integration and system reconfiguration. Three different case studies based …

Synthetically Expressive: Evaluating Gesture And Voice For Emotion And Empathy In Vr And 2d Scenarios, Haoyang Du, Kiran Chhatre, Christopher Peters, Brian Keegan, Rachel Mcdonnell, Cathy Ennis

Conference papers

The creation of virtual humans increasingly leverages automated synthesis of speech and gestures, enabling expressive, adaptable agents that effectively engage users. However, the independent development of voice and gesture generation technologies, alongside the growing popularity of virtual reality (VR), presents significant questions about the integration of these signals and their ability to convey emotional detail in immersive environments. In this paper, we evaluate the influence of real and synthetic gestures and speech, alongside varying levels of immersion (VR vs. 2D displays) and emotional contexts (positive, neutral, negative) on user perceptions. We investigate how immersion affects the perceived match between gestures …

Trustworthy Navigation With Variational Policy In Deep Reinforcement Learning, Karla Bockrath, Liam Ernst, Rohaan Nadeem, Bryan Joseph Pedraza, Dimah Dera

Electrical and Computer Engineering Faculty Publications

Introduction: Developing a reliable and trustworthy navigation policy in deep reinforcement learning (DRL) for mobile robots is extremely challenging, particularly in real-world, highly dynamic environments. Particularly, exploring and navigating unknown environments without prior knowledge, while avoiding obstacles and collisions, is very cumbersome for mobile robots.

Methods: This study introduces a novel trustworthy navigation framework that utilizes variational policy learning to quantify uncertainty in the estimation of the robot’s action, localization, and map representation. Trust-Nav employs the Bayesian variational approximation of the posterior distribution over the policy-based neural network’s parameters. Policy-based and value-based learning are combined to guide the robot’s actions …