Driving Safety Performance Assessment Metrics for ADS-Equipped Vehicles and Scenarios Testing

Data

Driving Safety Performance Assessment Metrics for ADS-Equipped Vehicles and Scenarios Testing

One of the biggest questions facing the safe deployment and commercialization of automated driving systems (ADS)-equipped vehicles ​(AVs) today is “What level of driving safety performance is required compared to

Exploratory Data and Root Cause Analysis for Semiconductor Testing

The aim of this research is to analyze the data from electrical tests performed on the components of transistors at the Flexible Electronics and Display Center of ASU. The purpose

Creative Frameworks: Leveraging Deep Learning and Data Analysis to Create Accessible Artistic Technologies

Generative adversarial networks are used to create visuals from textual inputs, allowing a user to create artwork with only a keyboard. GANs can be extended by recycling the output image

Creative Frameworks: Leveraging Deep Learning and Data Analysis to Create Accessible Artistic Technologies

Auditory analysis based on musical information and text lyrics, and flexible light controls through mediums such as keyboard input or motion capture can be used as input to an end-to-end

Secure Tracing With Dendrite Vision: Computer Vision Methods For Matching Dendritic Identifiers Within The Supply Chain

Dendrites are fascinating branching structures that exhibit randomness, yet they are unique, non-repeatable, and identifiable with the right algorithmic innovations. The question this research aims to answer is how can

Decentralized Multiagent Reinforcement Learning

With the rise of big data, Distributed Computing methods have become the backbone of large systems. Contextualizing problems in a multiagent paradigm enables one to capitalize on the high scalability

Design of Mixed-Signal Circuit Board for RRAM (Resistive Random-Access Memory) Crossbar Testing

Memristors are newly utilized devices that hold variable resistances based on input voltages. This unique characteristic allows for a faster, more power-efficient implementation of the dot-product computation compared to traditional

Optimal Task-Allocation Algorithms for Multi-Tethered (MuTheR) Robots: Traditional Versus Timing Formulation

This project compared two optimization-based formulations for solving multi-robot task allocation problems with tether constraints. The first method used the common multiple traveling salesman formulation and implemented an algorithm over

Voice Command Object Localization with Spatial Audio and IoT Devices

Delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach the

Characterization of Synaptic Electronic Devices for Brain-Inspired Computing Systems

The project seeks to address the research question: Is hexagonal boron nitride (h-BN), a layered two-dimensional (2D) material, a promising candidate to implement brain-inspired (neuromorphic) computing devices and circuits? To

Analyzing the Features and Efficacy of Classification Models for Physiological Stress Prediction

Stress prediction in law enforcement can serve to better prepare officers for the intensity of their work. To further understand the physiological triggers that induce stress, the use of machine

Development of URCHIN: An Autonomous Multi-Agent Framework for Extraterrestrial Exploration and Geological Sample Collection

Current surface exploration swarm vehicle concepts have been designed to navigate the environment specific to their proposed mission destination, resulting in a design that is too dependent on its use-case

A Decision Support System for Urban Canopy Selection

This project focuses on developing an interactive web interface that evaluates the effectiveness of various shade structures based on certain parameters. During this semester, the interface has been improved by

Raphael David poses at a farmer's market.

Optimizing Vendor Mix at the Downtown Phoenix Farmers Market

Farmers markets (FMs) serve an important role in local food economies. FMs are multi-scalar operations that involve a number of decision-makers: farmers, market managers, and local residents. FMs provide economic

Monocular 3D Object Detection for Traffic Analysis

Recognizing and localizing objects in the 3D space is crucial for a more accurate representation of the environment for various use cases. While significant progress has been achieved with expensive LIDAR systems,

Modeling Saffman-Taylor Instability to Guide Material Selection for Dendritic Identification Tags

Saffman-Taylor instability is a fluid dynamics phenomenon that can be used to create dendritic formations that are structurally unique. These dendrites can be used as identification tags, with their distinctive

Statistical Analysis of Multiwalled Carbon Nanotube Network Properties in Low Weight Percentage Nanocomposite Materials

The network properties of multiwalled carbon nanotubes in low weight percentage nanocomposites have never been investigated before. Atomic Force Microscopy (AFM) based Peak Force Quantitative Nanomechanical Mapping (PFQNM) was employed

Virtual Testing Environment for Flexible Drone Flight Simulation and Design Analysis

The use of flexible drones has increased in recent years and testing these designs takes time and effort, because virtual testing environments are rarely available. This project aims to make

Assessing the Effect of Overparameterization in Quantum Neural Networks

Current quantum devices aim to leverage quantum mechanical features in tandem with classical computing resources to iteratively solve high-value problems even the best supercomputers would be incapable of. For instance,

Computer science major Benjamin Joseph L. Herrera (left) is developing VivyNet, a tool that lets anyone create music from poems with artificial intelligence, with Assistant Professor Yezhou Yang (left).

VivyNet: A New Approach to Creating AI-Generated Music

Advances in machine learning (ML) have allowed researchers to simulate human behaviors. One such behavior is content generation. This field of artificial media creation is difficult to perfect as there

Unintentional Costs of Vehicle Alert Modality for Driving Hazards

The current research aims to better understand how the modality of in-vehicle alerts affects attention allocation for identification and response to simultaneously occurring driving hazards. The research will use a

Automated Traffic Incident Detection and Driver Behavior Analysis

Nowadays, there are over 260 million registered vehicles in the United States (most of them are passenger vehicles), and as a result, road safety is an important issue for everyone.

Automated Traffic Incident Detection and Driver Behavior Analysis

Nowadays, there are over 260 million registered vehicles in the United States (most of them are passenger vehicles), and as a result, road safety is an important issue for everyone.

A Systematic Study on Quantifying Bias in GAN-Augmented Data

Generative Adversarial Networks (GANs) can be used to augment the amount of information in datasets. However, upon training on certain datasets, GANs can magnify already existing biases in them. In

Optimization of Uniaxial Testing Apparatus for Micro-Scale Material Systems

Common methods of testing mechanical properties of micro-scale systems need a collection of specialized parts that are costly and difficult to set up. A new uniaxial testing apparatus that has

Real-Time Object Detection Using Image and Lidar Data

Lidar and camera sensor data are utilized, along with an object detection model, to recognize vehicles and their distances from the sensor system. This research project would help drivers by

Inference of Brain Morphology From Spatial Gene Expression

The Allen Brain Atlas offers an atlas of gene expression across the whole mouse brain, but spatial transcriptomic datasets are beyond direct interpretation. Reducing dimensionality with principal component analysis (PCA)

Maya Muir (left) works with her mentor Assistant Professor Ariane Middel (right).

A Decision Support System for Urban Canopy Selection

As record heatwaves are being seen across the globe, new tools are needed to support urban planners when considering infrastructure additions. This project focuses on developing an interactive web interface

Determining an Optimal Task-Allocation Algorithm for Multi-Tethered Rover (MuTheR) Systems

Multi-tethered rover (MuTheR) systems present an improved way to explore the terrain in lunar and planetary missions by utilizing the teamwork and buddy-system advantages associated with robots physically connected together.

Unintentional Costs of Vehicle Warning Modality for Driving Hazards

The current research aims to better understand how the modality of in-vehicle alerts affects attention allocation for identification and response to simultaneously occurring driving hazards. The research will use a

Autonomous Vehicle Object Detection on LiDAR Point Cloud Using Deep Learning Model

In order to improve the current advanced driver assistant system, more accurate input information of the vehicle’s surround is required. The project serves to improve this input information as LiDAR

Data Offloading in 5G Wireless Networks

Implementation and testing of data offloading in 5G wireless networks can be accomplished using Software Defined Radio (SDR). Machine learning classification techniques can be applied to identify receiver locations, then

Inference of Brain Morphology from Spatial Gene Expression

The Allen Brain Atlas offers an atlas of gene expression across the whole mouse brain, but spatial transcriptomic datasets are beyond direct interpretation. Reducing dimensionality with principal component analysis (PCA)

Enabling Circular Economies of Recyclable Materials Through Matrix Completion

An integral part in improving our recycling process is the development of circular economies. One of the major hindrances to the development of circular economies is the incompleteness of commodity

Learning Complex Behaviors from Simple Behaviors: An Analysis of Behavior-Based Modular Design for RL Agents

In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by subsumption

A Systematic Study on Quantifying Bias in GAN-Augmented Headshot Data

Generative Adversarial Networks (GANs) can be used to augment the amount of information in datasets. However, upon training on certain datasets, GANs can magnify already existing biases in them. In

Perspective Variant Preference-Based Learning with Quadcopter Swarms

Preference-based learning allows for non-expert users to interact with reinforcement learning agents in a way that they can shape their behaviors. This work intends to push the current implementations of

Understanding Machine vs Human Generated Text in News Articles

The aim of this research is to create a model that can take a text input to classify the content of the message into two categories, Machine Generated and Human

Development and Validation of a Custom Soft-Body FEA Simulator for Rapid Prototyping

This study focuses on the development of a soft-bodied finite element analysis (FEA) simulator for the purpose of early phase prototyping. This simulator facilitates rapid generation of design concepts in

Understanding the Impact of the Tempo of Distractions on Cognitive Ability

In order to provide students with the best education, it is critical to understand what distractors may affect their cognitive abilities. The research focuses on understanding whether patterned or randomly

Alternative Promoter Usage Using Transcription Start Sites

With relatively small genomes, many species have evolved mechanisms for diversifying their transcriptome (set of messenger mRNA transcripts in a given cell). One of the mechanisms to do so is

Evaluating How Empathy Optimizes Transparency and Trust in pHRI

This research investigates how a robot’s empathy, the ability to allow humans to misunderstand a robot’s intent, optimizes the transparency and trust in the Human-Robot Interaction (HRI). The robot is

Prototyping of a 5G Ad-Hoc Cellular System on Hardware Kits

This research focuses on the development of a self-correcting 5G ad-hoc cellular network that will connect both fixed and wireless users, regardless of location. A localization proof-of-concept will be prototyped

A Novel Approach to Perform Rank-One Updates in Machine Learning

The fact that ML algorithms can suffer from significant rounding errors and affect their output has received little attention. Moreover, techniques for avoiding rounding errors tend to be computationally expensive.

Employing Deep Learning and GPS Outdoor Positioning for Vision-Aided mmWave Beam Prediction

This project is aimed at utilizing machine learning frameworks to develop an optimized beam training model, capable of predicting the optimal direction of mmWave signal at a considerable success probability,

Parth Khopkar and Heni Ben Amor

Control and Coordination of Multi-Robot Swarm Systems

Robot swarms show great promise in performing complex tasks in areas ranging from search and rescue to interplanetary exploration and yet controlling the behaviors of these swarms effectively is an

Auto-generation of Spatial SQL Queries

In the recent past, there has been an increase in AI-based systems built to make human database interactions seamless, but they rely on interaction sessions that are extremely small. The

Traffic Analysis with Drone Videos

Recent advances in drones for consumer and professional applications have enabled a wide range of video-based analysis tasks in the air, including urban landscape survey, farmland area counting, and crop

Analysis of Biomolecules Using a Novel Sapphire-Supported Nanopore

Solid-state nanopores are a revolutionary technology first devised in the early 1990s that allow researchers to conduct biomolecule analysis, with a potential for fast and low-cost diagnostics. Conventional solid-state nanopores

Data Offloading in 5G Wireless Networks

Implementation and testing of data offloading in 5G wireless networks can be accomplished using Software Defined Radio (SDR). Developing a working system through SDR requires overcoming inherent challenges, including compensating

CUR Decomposition Method for Dimensionality Reduction of High Dimensional Alloy Data

High Entropy Alloys have potential for application in structural and aerospace industries due to their desirable material properties. These alloys consist of five or more elements, leading to a large

Flux Balance Analysis of Synechocystis sp. PCC 6803 for the Production of D-lactate

Flux Balance Analysis (FBA) is a computational approach to simulate the flux of metabolic pathways in genome-scale metabolic networks in organisms such as cyanobacteria. COBRA toolbox is used to predict

Online Prediction for Vision-based Active Pursuit using a Domain Agnostic Offline Motion Model

The use of a Long Short-Term Memory Network-based domain-agnostic predictive pursuit agent is proposed as an alternative to conventional methods such as Kalman Filtering. The empirical results from the pursuit-evasion

FPGA Powered Infrared Imaging of Hypersonic Missiles

This research project explores the applicability of low-altitude hypersonic missile detection using artificial intelligence (AI) implemented on a field-programmable gate array (FPGA). The ability to defend against hypersonic missiles depends

A Systematic Study of Pooled Testing Procedures for SARS-CoV-2

Testing is an invaluable method used to monitor and limit the spread of COVID-19. However, global shortages of reagents and instruments make it difficult to perform routine high-volume testing. Studies

Designing a Low-Cost and Power-Efficient DC-Biasing System for Reconfigurable Reflective Surfaces in the Terahertz Spectrum

The motivation behind the group’s research is to fabricate the physical structures for implementing a new type of frontier in wireless sensing and communication. To achieve this, a rugged yet

Weight and Moment Estimations for Small Fixed-Wing UAVs

Currently the weight of small UAVs cannot be accurately estimated by the commonly used empirical equations that were derived for full-sized aircraft. As weight and their related moments of inertia

Modeling the Complexity of Sankey Diagrams

In this project, the team is developing a model to quantify the complexity of Sankey diagrams, which are a type of visualization technique that shows flow between groups. To do

Implementing creative ways of generating SQL Queries in a Data Exploration Session

The objective of this research is to develop creative ways of generating SQL queries during a Data Exploration session. This research aims to develop  efficient methods of collecting human interactions

Aircraft Performance Data Acquisition

Considering the applications and popularity of electric fixed-wing UAVs are growing, it is critical to quickly obtain performance data on aircraft platforms to verify and optimize design. Research is conducted

Study of the Effects of Polydispersity on Vortex Tubes

This study explores polydispersity as a method of mitigating vortical flows. A cluster of particles with ranging sizes will be dispersed in the core of a vortex to observe the

Development and Validation of a Custom Soft-Body FEA Simulator for Rapid Prototyping

This study focuses on the development of a soft-bodied finite element analysis (FEA) simulator for the purpose of early phase prototyping. This simulator facilitates the rapid generation of design concepts

Visualizing Spatio-Temporal Data

The research question is “How can Spatio-temporal data be visualized on a graphical plot within the Lampy project of the DataSystems’ Lab?” By using high-level Python libraries and data set

Environmental Perception Based Human Intent Inference in Autonomous Cars

Social Value Orientation (SVO) is a measure of ones’ preference to allocate rewards between themselves and another person.  Previous research in human modeling for autonomous driving has incorporated SVO estimation

A Novel Use of GAN’s to Efficiently Simulate Fracture in Polymer Composites

Can a neural network be used to speed up finite element analysis in certain material simulations? The researchers built a pipeline to generate thousands of finite element analysis maps and

Evaluating Collective Intelligence Strategies for Visual Detection

This work investigates how different methods of soliciting and aggregating input from multiple people best inform visual detection tasks. A crowdsourced experiment is developed which asks hundreds of study participants

Ligament Breakup in a Sheer Flow

The goal of this research is to create a database of how a string of fluid, or ligament, breaks up into droplets due to an external flow. With this database,

Neural ODE Modeling for Many-Body Interactions

Neural Ordinary Differential Equations (ODEs) present a new pathway for the reversible modeling of many-body systems, including those for the predictive analysis of particle interactions. Such modeling can determine destination

A Novel Approach to Perform Rank-one Updates in Machine Learning

Data proliferation has made Machine Learning (ML) algorithms ubiquitous. However, the fact that ML algorithms can suffer from significant rounding errors and affect their output has received little attention. Moreover,

Control and Coordination of Multi-Robot Swarm Systems

Robot swarms show great promise in performing complex tasks in areas ranging from search and rescue to interplanetary exploration and yet controlling the behaviors of these swarms effectively is an

Simulation Framework for Driving Data Collection and Object Detection Algorithms to Aid Autonomous Vehicle Emulation of Human Driving Styles

Identifying objects and estimating the volume enclosed by these objects is a critical index in determining the viability of autonomous vehicles (AVs) and is crucial for inculcating safety measures. Including

Low-Cost and Power-Efficient Terahertz Reconfigurable Reflective Surfaces for Imaging and Wireless Communications

The motivation behind the group’s research is to fabricate the physical structures for implementing a new type of frontier in wireless sensing and communication. While several aspects of the design

A Benchmarking Framework for Data-Driven Compressive Sensing

The objective of the research is to develop a benchmarking framework with a unified API and benchmarks to allow researchers in this field to quantitatively evaluate new algorithms. To achieve

Improvement of Uniaxial Testing Apparatus for Micro-Scale Material Systems

Common methods of testing mechanical properties of micro-scale systems need a collection of specialized parts that are costly and difficult to set up. A new uniaxial testing apparatus that has

How Center of Gravity Location and the Sizing of Control Surfaces Affect Aircraft Stability

The motivation behind this project is to investigate how to size an aircraft’s control surface in relation to the center of gravity for aircraft stability. Finding a working balance between

Multi-Modal Communication Between Human and Robots through Virtual and Augmented Reality

The goal of this project is to enable multi-modal communication with human-robot teams. This study will demonstrate a way to incorporate spatial and temporal cues to enhance human-robot communication with

Leveraging on Deep Learning to Predict the Optimal Beam Index Using Wireless Sensing Localization

The demand for communication networks with high capacity rate will be fulfilled with the recent developments of 5G technology. But then this technology utilizes mmWave systems, which has the following

A Novel Use of GAN’s to Efficiently Simulate Fracture in Polymer Composites

Can a neural network be used to speed up finite element analysis in certain material simulations? The researchers have built a pipeline to generate thousands of finite element analysis maps

Study of the Interaction of Vortex Tubes with Suspended Dust Particles

Vortex stability is a key area of interest. Vortical flows over aircraft wings at high angle of attack can enable the aircraft to perform maneuvers that are impossible otherwise. On

Target Detection Using Algorithmic Matter

Synth cells are micro-scale robots with limited computation power and memory, but can work together to perform complex tasks. It has been shown that synth cells can converge to a

Learning and Sampling from the Causal Graph of Multi Categorical Distributions Via the Generative Adversarial Network

Machine learning is being used to solve many problems, trying to generate multi categorical data is one of the challenges the researchers faced. The researcher team has proposed a new

A Benchmarking Framework for Data-Driven Compressive Sensing

The objective of the research is to develop a benchmarking framework with a unified API to allow researchers to quantitatively evaluate new compressive sensing algorithms.To achieve fair and extensive comparisons,all

Ligament Breakup in a Sheer Flow

The goal of this research is to create a database of how a ligament, or a string of fluid, breaks up into droplets from an external flow. To create a

Object Detection With Sensor Fusion and Embedded Systems

As the technology available for autonomous vehicles advances, car manufacturers are looking for ways to implement Advanced Driver-Assistance Systems (ADAS) economically. Both in terms of cost and energy used. This

Real Time Multimodal Classification for Social Media Notifications

Aim of this research is to create a model that can take either image, text or both to classify the content of the message into different categories in real time.

Violin Vibrato Video Imaging: A Novel Method to Generate Frequency Iterations Using Convolutional Neural Networks

The violin vibrato is an artistic modulation of a violin’s pitch that gives the tone of the instrument a desired aesthetic effect. Using computer vision techniques, the purpose of this

Multi-modal Communication Between Human and Robots through Virtual and Augmented Reality

The goal of this project is to enable multi-modal communication with human-robot teams. This study will demonstrate a way to incorporate spatial and temporal cues to enhance human-robot communication with virtual

Investigating the Impact of Environmental Features on Multi-Agent Communication

Traditional reinforcement learning methods have been challenging to apply to multi-agent settings, thanks to the nonstationarity of the environment, until recently. This project aims to employ such multi-agent RL methods

Effect of Particle and Environmental Variables on Flowability of Granular Materials

The purpose of this research is to attempt to design a set of characterization tools to relate granular material physical properties to their performance properties. Different forms of organic materials

Visual and Output-Based Improvements of a MATLAB Program for Dynamic Light Scattering Applications

The research motivation was to improve a MATLAB program that provided correlation coefficient and size distribution outputs for a sample run through a DLS (Dynamic Light Scattering) machine. Research methods

Assessment of Injury Induced Blood Brain Barrier Disruption and Necroptosis via Development of Rapid Data Analysis Pipeline

The goal of the project completed by the researcher was to establish a Java program that aids in the efficiency and accuracy of traumatic brain injury (TBI) scan analysis. Current

Socially Attentive Autonomous Vehicles

The computational cost of determining the action sequence in high traffic areas such as changing lanes on a highway or merging into lanes can be computationally costly. Rather than computing

Ant-Inspired Control Strategies for Collective Transport by Dynamic Teams with Temporary Leaders

Ant groups often work together to transport food and materials back to their nests. In some cases, the group exhibits leader-follower behaviors where a single ant guides the entire group

Learning Deep Neural Interaction Policy for ExoSkeleton Control

The purpose of this research is to develop a deep-learning-based approach to control a custom-built hip exoskeleton. A key component is to leverage learning-based techniques to adapt across different walking

Target Detection Using Algorithmic Matter

Synth cells are micro-scale robots with limited computation power and memory, but can work together to perform complex tasks. It has been shown that synth cells can converge to a

Vector Tiles in Geospatial Mapping

The research question is “How can vector tiles and maps be used in DataSys lab’s creation, the GeoSpark software, to provide the most user-friendly interface possible?” In order to determine

Utilizing PVAD Algorithm for Detecting Network Anomalies

Detecting network anomalies is a critical part of maintaining security and reliability within computer networks. The goal of this experiment is to investigate the multivariate data characteristics of normal, anomalous,

Input-elicitation Methods for Crowdsourced Human Computation

“Collecting human data from crowdsourcing is problematic due to cognitive biases, varying worker expertise, and varying levels of subjective scales. In this work, we investigate the effectiveness of input-elicitation systems

Complementary Wireless Vision Test Bed

The next generation of high frequency 5G wireless communications will allow high data rate communication. However, operating at these frequencies poses challenges such as (i) the sensitivity to blockages which

Robot Artist

The research question states how we can extract data on an artist’s artwork – mark-making methodology, in order to recreate the original art using a robot. The researcher studied digital

Raman Spectrometry Conclusions as an Example of Intuitive Software

There is a lack of accessibility in Raman spectrometry (used to detect the presence of compounds in provided samples). It was determined that by creating a software which aided in

Propulsion Data Acquisition

The research team’s interest in this project is prompted by the lack of knowledge on electric aircraft performance. Research is conducted via the development of instruments onboard a miniature electric

Learning Unknown Physics Behind Cellular Dynamics Using Time-Variant Neural Network

The objective of the research is to develop a modified Hamiltonian ordinary differential equation neural network (MHODE) that models the dynamics of a multi body system with non-conservative energy. This

Is Artificial Intelligence a Burden in a Changing Environment

Although there have been many recent advancements in artificial intelligence (A.I.) learning, the capacity to make assumptions is necessary to reduce the time, data, and error it takes in order

Improving Data Rate for 5G Systems using USRP Kits

In this research project, machine learning is utilized for channel estimation. Channel gains can be manually estimated, but the downside of manually calculating estimating the channels is that it is

A Probabilistic and Confidence-Driven Approach to Theory of Mind Models in Autonomous Agents

By nature, humans can be very unpredictable with their actions, which makes it difficult to create a perfect Theory of Mind (ToM) model to attempt to predict those actions. Having

Bicycle Rider Pose Estimation from Physical Human-Robot Interaction Forces

Riding a bicycle requires simultaneous balance and navigation, which may be difficult or even impossible for persons with disabilities. This may be partly alleviated by providing active balance and steering

Combined Interfacial and Solvothermal Synthesis to Study the MOF Growth Process

Solvothermal synthesis is a method of producing chemical compounds and is commonly applied to synthesize metal-organic frameworks (MOFs). MOFs are a class of crystalline porous materials with the traits of

Machine Learning and Dimensionality Reduction to Accelerate DFT Simulations of Material Properties and Enable Computational Material Design

This research is focused on applying machine learning to create an alternative to computationally expensive DFT and MD simulations of material properties. We specifically investigate the utility of graph neural

Drone Swarms in Search and Rescue Operations

The last decade has seen an increase in research of autonomous vehicles. This research tries to tackle autonomy in Unmanned Aerial Vehicles (UAV) by specifically designing decentralized controllers for platooning.

An Investigation of the Different Approaches of Autonomous Traversal

The objective of this research is to design an algorithm that helps a mobile robot navigate in unmapped terrain through the aid of computer vision, GPS coordinates and path planning.

Blame All vs. Blame Me in AVs

Due to the increasing desire to make the roads safer with the innovation in autonomous vehicles (AVs), it is imperative to understand what information should go into a vehicle’s control

Analyzing Sensor Quantization of RAW Images for Visual SLAM

Visual simultaneous localization and mapping (SLAM) is an emerging technology that enables low-power devices with a single camera to perform robotic navigation. Most visual SLAM algorithms are tuned for images

Ankle Flexion Data as a Differentiative Measure in Orthotic Device Prescription for Stroke Survivors

Gait and balance impairments are well-known consequences of a stroke that causes nearly half of the 6.5 million stroke survivors in the U.S. to fall. Ankle Foot Orthoses (AFOs) are

Neural ODE Modeling for Many-Body Interactions

Neural Ordinary Differential Equations (ODEs) present a new pathway for the reversible modeling of many-body systems, including those for the predictive analysis of particle interactions. Such modeling can determine destination

Effect of Particle and Environmental Variables on Flowability of Granular Materials

The purpose of this research is to attempt to design a novel set of characterization tools to relate granular material physical properties to their performance in handling and conversion operations.

Connecting the Dots: Towards Automated Dataset and Visualization Recommendation from News Articles

In this project, the team is investigating the efficacy of automatically recommending data visualizations to accompany a news story, even when there is no explicit data provided. To do this,

Computational and Experimental Studies of Imidazolium-Based Ionic Liquids in Organic Solutions for MET Sensor Devices

This research focuses on further understanding on how molecular dynamic interactions affect the chemical properties of ionic liquid solutions for the optimization of a molecular electronic transducer-based seismometer for low-temperature

Efficient Policy Iteration Architecture for Learning Rollout Policy in POMDP

The research project considers an infinite horizon discounted dynamic programming problem with finite state and control space under partial observability. These problems are hard due to the curse of dimensionality.

Experimental Analysis on the Effect of Human Learning on Physical Human-robot Interaction

To develop robots that effectively interact with humans, it is important to understand how humans teach and learn in different scenarios. The research aims to collect data for pairs of

FURI Totals

TotalStudents

0

FacultyMentors

0

OnlineSymposia

0

FocusAreas

0

FURIProjects

0

MOREProjects

0

KEENProjects

0

GCSPProjects

0