Center for Undergraduate Research in Viterbi Engineering (CURVE) Fellowship

Established in 2018, the mission of the lab is to address problems associated with the simulation, design, and behavior of high-performance composites and structures. The scope includes the training of graduate and undergraduate students from aerospace, mechanical, and materials engineering through teaching and sponsored research projects.

• Principal Investigator: Bo Jin
• Website: https://sites.usc.edu/acsl/
• Projects
  • Additive Manufacturing of Structures with High Compressive Strength
    • Project Description: We are designing structures for high compressive strength and they are all 3D printed. The strength may reach/beyond 10k lb compressive force. The structure will need to be as tall/light as possible. I will explain more details in the Zoom meeting sessions. I will support with multiple advanced 3D printers (with large print-bed and bed-heating functions for shape/warping compensations) and unlimited printing materials for the project. Satisfying structures will attend the annual SAMPE AMC additive manufacturing contest. We just won a national 3rd from last year's. Great honor and a large plus to your resume.
    • Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
    • Student Responsibilities: With help of faculty and veteran students, conduct meetings and the design of your structures. Design the CAD models using whichever software you are familiar with, or trained by veteran students. Print the structure use the lab printers, maintain successful printing processes.
    • Preferred Majors: Aerospace & Mechanical Engineering, Astronautical Engineering, Civil & Environmental Engineering, Industrial & Systems Engineering
    • Preferred Skillsets: Basic CAD skills is a plus but not a must.

Established in 1995 and endowed with a generous gift from M.C. Gill in 2002, the mission of the Center is to address problems associated with the manufacture and behavior of composites and composite structures. The scope includes the training of graduate and undergraduate students from chemical, mechanical and materials engineering through sponsored research projects. Personnel within the Center provide a range of expertise that includes postdoctoral associates and research professors with specialized skills in mechanics, polymer science, and manufacturing technology. Center personnel work closely with industrial sponsors.

• Principal Investigator: Steven Nutt
• Website: https://composites.usc.edu/
• Projects
  • Fast Sintering of Ceramics and Ceramic Composites
    • Project Description: Synthesize high-termperature ceramics, measure/analyze products using microscopy to determine porosity and grain size and functions of sintering time and temperature.
    • Open to: CURVE Continuing Researchers
    • Student Responsibilities: Synthesize ceramics, prepare polished sections, perform quantitative microscopy, analyze products.
    • Preferred Majors: Aerospace & Mechanical Engineering,Chemical Engineering
    • Preferred Skillsets: Operating lab equipment, familiarity with stereological analysis techniques.

• Liquid Molding of Vitrimer Composites
  • Project Description: Development of recyclable fiber composites using vitrimer resin. The project goal is to demonstrate feasibility of formulating vitrimer resin suitable for RTM of carbon fiber composites, and ability to reuse constituents for remanufacture of second generation composites.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Perform resin transfer molding (RTM) experiments with vitrimer formulations and fiber preforms. Analyze product microstructure, perform mechanical tests.
  • Preferred Majors: Aerospace & Mechanical Engineering,Chemical Engineering
  • Preferred Skillsets: Operation of microscopes, sectioning saws, data acquisition (DAC) systems, and load frames.

We are researchers that focus on understanding the behavior of materials and devices by developing and applying novel electron microscopy techniques. We combine imaging, diffraction, spectroscopy, and machine learning approaches to probe structural, chemical, electronic properties, and topological textures at the atomic scale.

• Principal Investigator: Yu-Tsun Shao
• Website: https://sites.google.com/usc.edu/shao-emlab/
• Projects
  • Developing multi-modal scanning electron microscopy methods for materials characterization
    • Project Description: Electron microscopes are powerful tools that enable us to look at the microscopic details of the materials, hence provide insights into the fundamental structure-property relations. This applies to all materials -- including energy materials, quantum materials, etc. Thus, developing new imaging modes is analogous to putting on a new pair of glasses that allows us to see things that weren't possible before, including the crystal symmetry, strain, polarity, electric or magnetic fields within the materials.
    • Through this project, we will develop new imaging modes by combining hands on experimental and data mining/machine learning efforts, to explore the materials microstructures down to the nanometer scale.
    • Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
    • Student Responsibilities: Students will have hands on experiments on the scanning electron microscopy, read about the principles of electron scattering and interactions with the materials, as well as learn some programming for data analysis.
    • Preferred Majors: Aerospace & Mechanical Engineering, Astronautical Engineering, Chemical Engineering, Computer Science, Electrical & Computer Engineering
    • Preferred Skillsets: Courses: MASC 110 or 310 Materials Science; EE 238 Engineering Nano-systems
    • Skillsets: python programming, experience with electronic circuits for automated control

The McCurry lab applies the tools of organic and analytical chemistry to solve environmental problems. We primarily work in the areas of wastewater reuse and drinking water treatment

• Principal Investigator: Daniel McCurry
• Website: https://mccurrylab.com 
• Projects
  • Enabling safe water reuse by developing new treatment technology and understanding transformation pathways of chemical contaminants
    • Project Description: Research activities in our lab focus on enabling safe water reuse by minimizing the presence of harmful contaminants in recycled wastewater. Our major research efforts include developing new chemical technologies for oxidation of trace organic contaminants, identifying the precursors and transformation pathways of disinfection byproducts formed during water treatment and wastewater reuse, and developing new analytical techniques for identification and quantification of chemical pollutants using mass spectrometry. Our research primarily takes place in the BHE Water Lab, and relies heavily on chemical analytical instrumentation, including an ion mobility QTOF mass spectrometer, a gas chromatograph/triple quadrupole mass spectrometer, and an inductively-coupled plasma mass spectrometer. These tools allow us to quantify chemicals at extremely low concentrations (e.g., parts per trillion) and to identify previously unknown compounds in water samples.
    • Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
    • Student Responsibilities: Assisting graduate students with experiments on water treatment, water reuse, and quantification of trace contaminants in water. Specific responsibilities will include preparing for and setting up batch water treatment experiments, sample preparation for mass spectrometry-based identification and quantification of pollutants, and analyzing data produced by analytical instruments. Especially dedicated students may eventually have the opportunity to advance to a fully-independent project advised directly by the PI.
    • Preferred Majors: Chemical Engineering,Civil & Environmental Engineering
    • Preferred Skillsets: General chemistry lab skills; Some exposure to analytical chemistry is helpful but not required; General chemistry coursework (e.g., CHEM105 here or AP equivalent) is useful

Our research team at USC explores topics at the intersection of physics-based modeling, data analytics and uncertainty quantification for applications in monitoring and design of civil structures. We are excited about the potential that data, in conjunction with mechanistic models, holds to help build the resilient and smart urban environments of tomorrow. The applicability of machine learning algorithms to scientific and in particular civil engineering problematics requires careful considerations of data scarcity and imbalance, inherent randomness and stochasticity of the driving systems inputs, and compliance with well-established physics principles. Our research team works on the development of advanced data analytics tools that embed physical knowledge and quantify uncertainties, allowing for reliable decision-making.

• Principal Investigator: Audrey Olivier
• Website: https://www.audreyolivier.com
• Projects
  • Bayesian nonlinear filtering for estimation of dynamical systems
    
    • Project Description: Bayesian filters aim at estimating the states (and parameters) of a system that evolves with time from sequential measurements. This project aims at implementing Bayesian filtering algorithms, in particular nonlinear Kalman filters such as the EKF/UKF and their variants, within the open source UQpy software.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Learning about Bayesian filtering and implementing code that agrees with the architecture of UQpy, starting with the linear Kalman filter. Student will also be responsible in creating appropriate documentation and code examples.
    • Preferred Majors: Aerospace & Mechanical Engineering, Civil & Environmental Engineering, Computer Science, Electrical & Computer Engineering
    • Preferred Skillsets: Python programming

We bring together natural language processing and robotics to connect language to the world (RoboNLP). Our lab is broadly interested in connecting language to agent perception and action, and lifelong learning through interaction.

• Principal Investigator: Jesse Thomason
• Website: https://glamor.rocks/
• Projects
  • An Accessible Machine Learning-Based ADRD Screening Tool for Families and Caregivers
    • Project Description: Approximately 50 million people worldwide are diagnosed with dementia and an estimated 6.2 million Americans, one in nine people 65 and older, are living with Alzheimer's Disease (AD), as of 2021. The majority of affected people do not obtain early screening toward a timely diagnosis. Consequently, there is a very large and rapidly growing need for low-cost, non-invasive, and accessible tools for dementia screening toward alerting families and caregivers and encouraging them to pursue medical evaluation for potential patients. The goal of this project is to develop a screening system capable of detecting early signs of AD using data from standard clinical AD diagnostics captured through an app. The app is intended for family members and caregivers, and will be designed to be easy to use and encourage regular screening. The app will enable convenient, early flagging of ADRD symptoms and facilitating data collection for research and clinical diagnosis.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Students will work on collecting data and processing the data for our Machine Learning algorithms. Moreover, the students will get familiar with our Tobii Pro Eyetracker Setup and SDK coding. Consequently, The students will also work on implementing machine learning models for multimodal purposes using this knowledge.
    • Preferred Majors: Computer Science,Electrical & Computer Engineering
    • Preferred Skillsets: Python, Pytorch

• Building robust visual programs
  • Project Description: Visual programs have emerged as a strong neuro-symbolic method for composing highly performant multimodal models to solve complex language queries (e.g. https://prior.allenai.org/projects/visprog). However, these methods are sensitive to uncertainty and errors in individual components, and these errors can propagate through the program. In this project, we will build methods that increase model robustness when tackling complex vision-language tasks.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: This project may be a little more open-ended than others, and will challenge students to identify and answer research questions with partial independence.
  • Preferred Majors: Computer Science
  • Preferred Skillsets: PyTorch and Python required

• Modeling Sign Language Morphology
  • Project Description: Signed languages contain morphemes, i.e. systematic mappings from visual appearance to meaning. While many spoken language morphemes take the form of a few characters appended to a word (e.g. "-tion"), sign language morphemes consist of certain hand locations, configurations, and/or movements (e.g. food related signs are usually produced near the mouth). This project will (a) survey linguistic research on sign language morphology and (b) implement a model which can identify morphemes in isolated signs.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Model implementation, regular meetings, willingness to learn across disciplines beyond CS
  • Preferred Majors: Computer Science
  • Preferred Skillsets: Python, Pytorch; familiarity with ASL is a plus but not required

• Task-aware Image Descriptions
  • Project Description: Image captioning models typically describe the literal content of an image at a granularity specific to the underlying dataset. Such models are not particularly helpful when an image description is needed for a particular /reason/, such as for identifying information helpful for telling a person how to get from where the image was taken to a location of interest within the image. For example, how to navigate across a room to a refrigerator while being aware of potential obstacles in the path. This project will investigate whether recent large scale pretrained models in both language and vision can be pipelined to provide task-aware language descriptions of images for particular use cases.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Implement models, conduct user studies
  • Preferred Majors: Computer Science
  • Preferred Skillsets: Python, Pytorch, and a willingness to engage with human-computer interaction research literature in a meaningful way, going beyond standard AI/ML literature and approaches.

The Haptics Robotics and Virtual Interaction (HaRVI) Laboratory explores how humans interact with our world, robots, and technology through touch. The goal of our research is to create natural and intuitive interactions that realistically mimic the touch sensations experienced during interactions with the physical world. We design novel haptic hardware and rendering algorithms to improve the usability of technology, increasing people’s social connectedness, ability to complete specific tasks, and immersiveness in virtual reality. Our research has a strong focus on integrating human perception into all steps of the design process.

• Principal Investigator: Heather Culbertson
• Website: https://sites.usc.edu/culbertson/
• Projects
  • User Preferences for Haptic Feedback in Mobile Devices
    • Project Description: We are working on a project to investigate the preferences and impact of haptic feedback in a game like environment. The project involve experimenting with various haptic feedback patterns and gauging player reactions and optimizing haptic experiences in line with player preferences.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities:
    • Preferred Majors: Computer Science
    • Preferred Skillsets: A strong understanding of mobile gaming environments, user experience testing, and haptic technology is required for this project. Skills we are looking for is human participatory research skills, CITI training, and a preferably a CSBA background.

• Open Source Haptic Device Design
  • Project Description: This project focuses on making haptics research accessible to a broader range of developers through a programmable motor controller running Raspberry Pi RP2040. A researcher on this team will be responsible for designing a schematic for the board and producing a manufacturable final product, then iterating on this process multiple times while adding features throughout the year.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities:
  • Preferred Majors: Computer Science
  • Preferred Skillsets: Skills necessary for this position include knowledge of motor controllers and EDA software (Altium, KiCad, Eagle).

• Affective Communication
  • Project Description: The student will be immersed in an exploration of the haptics research, with a special emphasis on social touch. Engaged in acquiring essential knowledge about the fundamental hardware, software, and algorithms that shape wearable systems which aimed to create touch illusions, the student will apply this knowledge in real-world situations.
  • Open to: CURVE First-Time Researcher
  • Student Responsibilities: Student is expected to gain hands-on coding experience, display a keen interest in developing the technical skills (3D Printing, Electrical Design, Signal Design and Algorithms) required to design, implement, and troubleshoot haptic systems. The student's comprehensive approach to learning, combined with a deep curiosity for haptics and wearable technology, forms the foundation for future academic pursue in haptics.
  • Preferred Majors: Aerospace & Mechanical Engineering,Computer Science
  • Preferred Skillsets: Student is expected to gain hands-on coding experience, display a keen interest in developing the technical skills (3D Printing, Electrical Design, Signal Design and Algorithms) required to design, implement, and troubleshoot haptic systems. The student's

• Facial Skin Stretch for Emotion Expression
  • Project Description: This project is studies the perception of facial skin stretch. Specifically, we are interested in determining how differences in facial skin stretch perception between neurodivergent and neurotypical individuals affects their ability to make and recognize facial expressions. The project involves the mechanical design and control of a head-mounted system for applying controlled amounts of skin stretch to key points on the face.
  • Open to: CURVE Continuing Researchers
  • Student Responsibilities: Key skills include CAD, programming (C++), embedded computing (Arduino), 3D printing, and electronics.

The Interaction Lab focuses on developing computational principles, techniques, models, and interventions to enable socially assistive human-robot interaction that supports human health and wellness. Socially Assistive Robotics (SAR) uses non-contact social interaction interventions involving social, emotional, cognitive, and physical abilities of users, toward improved wellness, communication, learning, and autonomy. The Interaction Lab conducts research in an interdisciplinary SAR arena that uses computing, engineering, and human user studies to characterize, model, and understand complex human behavior. Our projects aim to contribute insights and individualized tools toward mitigating pervasive societal challenges—including skill training for autism, anxiety, and depression coping, rehabilitation, and healthy aging —that require sustained personalized support that supplement the efforts of caregivers, clinicians, parents, and educators.

• Principal Investigator: Maja Mataric
• Website: https://uscinteractionlab.web.app/ 
• Projects
  • Socially Assistive Robot Administered Cognitive Behavioral Therapy
    • Project Description: Cognitive Behavioral Therapy (CBT) is a widely used clinically validated therapy method based on the premise that “psychological problems are based, in part, on faulty or unhelpful ways of thinking…and learned patterns of unhelpful behavior” and that people can learn better ways to cope, enabling them to be more effective in their lives. CBT treatment guides individuals to recognize and address cognitive distortions and alter thinking patterns. CBT interventions empower people to learn to recognize and address their distortions and implement therapeutic lessons as a daily practice. Thus a major component of CBT interventions involves “homework,” such as filling out worksheets or journaling, designed by therapists to encourage applying CBT skills to day-to-day lives between therapy sessions. However, many studies have demonstrated that adherence with CBT homework is low despite their importance in improving clinical outcomes. This work aims to investigate the use of new technologies for CBT homework. Students on this project will have the opportunity to analyze data from a recent study and assess the performance of the various CBT  homework technologies
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Students will assist with design and implementation of user studies and annotation of collected participant data. They will also have the opportunity to learn how to use machine learning tools to develop affect models and gain familiarity with fundamental robotics software tools.
    • Preferred Majors: Computer Science
    • Preferred Skillsets: Requirements: Prior coding experience with python. Bonus: experience with machine learning projects or prior coursework.

• An Accessible Machine Learning-Based ADRD Screening Tool for Families and Caregivers
  • Project Description: Approximately 50 million people worldwide are diagnosed with dementia and an estimated 6.2 million Americans, one in nine people 65 and older, are living with Alzheimer's Disease (AD), as of 2021. The majority of affected people do not obtain early screening toward a timely diagnosis. Consequently, there is a very large and rapidly growing need for low-cost, non-invasive, and accessible tools for dementia screening toward alerting families and caregivers and encouraging them to pursue medical evaluation for potential patients. The goal of this project is to develop a screening system capable of detecting early signs of AD using data from standard clinical AD diagnostics captured through an app. The app is intended for family members and caregivers, and will be designed to be easy to use and encourage regular screening. The app will enable convenient, early flagging of ADRD symptoms and facilitating data collection for research and clinical diagnosis.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Students will work on collecting data and processing the data for our Machine Learning algorithms. Moreover, the students will get familiar with our Tobii Pro Eyetracker Setup and SDK
    coding. Consequently, The students will also work on implementing machine learning models for multimodal purposes using this knowledge.
  • Preferred Majors: Computer Science
  • Preferred Skillsets: Python, Pytorch

• A Haptic Feedback Device for Guided Mindfulness Exercises with a Socially Assistive Robot
  • Project Description: Prior studies have explored the applications of both physical feedback devices and socially assistive robots (SARs) to aid users during mindfulness exercises, but no study has explored the potential of combining these two modalities during mindfulness practice. This work aims to design a physical device that gives appropriate haptic feedback through motor movements to guide users through a mindfulness exercise led by a socially assistive robot. Students working on this project will generate and prototype designs for the device that meet the following goals: low-cost and easily fabricated by non-expert users, cohesive with the design of the SAR Blossom, and easily synced to different mindfulness exercises.
  • Open to: CURVE First-Time Researcher
  • Student Responsibilities: Students will use an arduino microcontroller and various electronic components to build and program the device. They will explore existing haptic mindfulness devices and design a device for the Blossom robot. They may use different fabrication techniques to build the device such as 3d printing, laser cutting, or crochet.
  • Preferred Majors: Aerospace & Mechanical Engineering, Computer Science
  • Preferred Skillsets: Arduino or other microcontrollers, CAD modeling (especially Fusion 360), 3d printing

• Using Affective Computing to Predict Persistent and Momentary Emotional Labor of Mothers with Infants
  • Project Description: Using machine learning techniques, this project attempts to understand the types of emotional labor mothers of infants must go through. We have videos of mothers and infants interacting, along with mental health screening scores. This project will use these resources in an attempt to answer three questions. (1) What are the differences in emotional labor between mothers of 6 month and 12 month infants? (2) Can we use freeplay interaction videos to capture persistent mental health issues? (3) Can we use freeplay interaction videos to capture momentary emotional labor? Using multimodal affective learning techniques, this project will answer these questions in order to develop potential in-the-moment interventions in the future.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Students will assist with design and implementation of user studies and annotation of collected participant data. They will also have the opportunity to learn how to use machine learning tools to develop affect models.
  • Preferred Majors: Computer Science, Statistics
  • Preferred Skill Sets: Requirements: Prior coding experience with python. Bonus: Experience with machine learning projects or prior coursework. Experience with machine learning statistical interpretation.

The Integrated Media Systems Center (IMSC) blends the unique resources available across the University of Southern California and Los Angeles to create a world-class, multidisciplinary hub for exploration and discovery. We engage a diverse faculty with expertise in fundamental research areas critical to every aspect of data science and are closely connected to the domain experts applying these tools through our affiliated schools and organizations. IMSC is built to deliver next-generation, custom-built data platforms based on bleeding-edge basic and applied research. These end-to-end solutions span the entire data pipeline, from the acquisition of real data to the application of mined insights, and are created for partners facing real-world problems across the globe.

• Principal Investigator: Cyrus Shahabi
• Website: https://imsc.usc.edu/
• Projects
  • Location Trajectory Analysis
    
    • Project Description: We have access to millions of location trajectories from regular people. These are timestamped (latitude, longitude) pairs. We use this data for several of our research projects, but we don’t understand some important characteristics of the data. For instance, does a person’s anonymous ID change over time? Are people’s home locations missing in the data? The goal of this project is to become our local expert on this data, so we can turn to you with our questions. It will involve writing code to thoroughly understand the data.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Develop a Python framework to understand our trajectory data. Begin by answering some basic questions and then prepare to respond to new questions.
    • Preferred Majors: Computer Science
    • Preferred Skillsets: Python, handling large datasets

Founded in 2002, our laboratory conducts research on the design and implementation of a wide range of networked computing systems.

• Principal Investigator: Ramesh Govindan
• Website: https://nsl.usc.edu
• Projects
  • AR Localization with NeRF
    
    • Project Description: To build a system that use NeRF as the map for the outdoor AR applications.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities:
      • Perform analysis on NeRF software
      • Write code in C++/Python that train and infer NeRF
      • Work with Ph.D. students on an existing codebase to integrate the above algorithms.
      • Read existing literature in related areas
    • Preferred Majors: Computer Science
    • Preferred Skillsets: C++/Python, NeRF, computer graphics

Our research is dedicated to understanding and designing Cyber Physical Systems. CPS is a highly interdisciplinary area and our group works on a variety of topics. In general, we are interested in the fundamental and applied questions relating to the structure and dynamics of networks.

• Principal Investigator: Paul Bogdan
• Website: https://cps.usc.edu/
• Projects
  • Brain Age Prediction
    • Project Description: The phenotypic age of the human brain, as revealed via deep learning of anatomic magnetic resonance images, reflects patterns of structural change related to cognitive decline. Our interpretable deep learning estimates that the brain ages more accurately than any other approaches to date. Furthermore, compared to chronological age, our inferred brain ages are significantly more strongly associated with early signs of Alzheimer's disease. Maps conveying the importance of each brain region for estimating brain age reveal differences in patterns of neurological aging between males and females and between persons with and without cognitive impairment. These findings provide insight into early identification of persons at high risk of Alzheimer's disease.
    • Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
    • Preferred Majors: Computer Science,Electrical & Computer Engineering

The FPGA/Parallel Computing Lab is focused on solving data, compute and memory intensive problems in the intersection of high speed network processing, data-intensive computing, and high performance computing.

• Principal Investigator: Viktor Prasanna
• Website: fpga.usc.edu
• Projects
  • Accelerating graph machine learning
    • Project Description: Develop parallelization strategies on CPU, GPU, FPGAs.
    • Open to: CURVE Continuing Researchers
    • Student Responsibilities: Code development, testing, interface with advanced PhD students in the group.
    • Preferred Majors: Computer Science, Electrical & Computer Engineering
    • Preferred Skillsets: Coding
    • EE 451 EE 457

Animals -- lizards, snakes, insects -- often exhibit novel strategies in effectively interacting with their physical environments and generating desired responses for locomotion. In our lab, we are interested in creating robots that can do the same. Our approach integrates engineering, physics, and biology to discover the general principles governing the interactions between bio-inspired robots and their locomotion environments. For example, how do legged animals and robots use solid-like and fluid-like responses from soft sand and mud to produce effective movement? How can insect-like and snake-like robots take advantage of obstacle collisions to navigate within cluttered environments? We use these principles to create novel sensing and control strategies that can allow robots to perceive and intelligently elicit environment responses to achieve desired motion, even from traditional-considered "undesired" environments such as flowing sand, yielding mud, and cluttered obstacle fields.

• Principal Investigator: Feifei Qian
• Website: https://sites.usc.edu/qian/
• Projects
  • Robot-assisted earth and planetary exploration
    • Project Description: This project focuses on developing robots that can use their legs as terrain sensor to help geoscientists and planetary scientists collect and interpret information at high spatial and temporal resolution. To achieve this, we will build robot legs that can sensitively “feel” the responses of desert sand or near-shore mud. We will design different interaction-based sensing protocols for the robot legs, and test these protocols in lab experiments. Once the sensing capabilities are developed and tested, we will take the robots to field trips, where the robots work alongside human scientists and learn how human make sampling decisions and adapt exploration strategies based on dynamic incoming measurements. Going forward, these understandings will help enable our robots with cognitive reasoning capabilities to flexibly support human teammates' scientific objectives during collaborative exploration missions.
    • Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
    • Student Responsibilities: Selected candidate(s) will assist in the development of robotic platforms (mechanical design and fabrication, control, and programming), perform sensing and locomotion experiment data collection (e.g., force measurements, motion capture tracking) and analysis (MATLAB or Python)
    • Preferred Majors: Aerospace & Mechanical Engineering, Astronautical Engineering, Electrical & Computer Engineering
    • Preferred Skillsets: Mechanical design (e.g., Solidworks) and fabrication (e.g., power tools, CNC, laser cutting), programming in Python and C++

Our current research interests are focused on the theory of graph signal processing (GSP) and its applications, including 3D point clouds, image and video compression, sensor networks and machine learning. The main goal of GSP is to extend conventional signal processing operations such as filtering and sampling to data associated with graphs. In some cases, graphs can represent physical networks (the Internet, sensor networks, electrical grids or the brain) or information networks (the world wide web, Wikipedia or online social networks). We are also interested in applications where there is no graph and one has to be selected first. Examples include image, video and 3D point cloud processing (graph nodes are pixels), as well as machine learning (each node is a data point in a data set).

• Principal Investigator: Antonio Ortega
• Website: https://sites.google.com/usc.edu/stac-lab/home
• Projects
  • Acquisition and processing of 3D point clouds
    • Project Description: Point clouds can be acquired with short-range (e.g., Kinect cameras) and long-range (e.g., LiDaR) sensors. Areas of interest in this project include 1) point cloud acquisition using a state-of-the-art experimental mid-range camera prototype, 2) denoising of point-cloud geometry and attributes, and 3) compression of point cloud datasets.
    • Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
    • Student Responsibilities: Develop, implement, and test, individually or in collaboration with graduate students, new algorithms to solve some of the problems encountered in point cloud processing and acquisition. I expect students to take the initiative and define their own project directions with support from faculty and PhD mentors.
    • Preferred Majors: Electrical & Computer Engineering
    • Preferred Skillsets: 1) Independence, curiosity, and critical thinking; 2) Programming experience at a basic level (Matlab or Python); 3) Linear algebra (EE 141L or equivalent).

• Human activity analysis using skeleton graphs
  • Project Description: Newly developed commercial cameras can extract the position of joints in the human body in real time. Rather than working with video, it is possible to analyze human motion by tracking the position of those joints, which together form a skeleton. This is useful for applications where privacy is important. In this project, we developed offline methods based on graph signal processing (GSP) to analyze skeleton motion. We plan to extend these ideas to a more realistic setting, where live skeleton data captured by a camera is analyzed in real time.
  • Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
  • Student Responsibilities: Develop, implement, and test new algorithms to solve some of the problems encountered in human activity analysis from skeleton data, individually or in collaboration with graduate students. I expect students to take the initiative and define their project directions with support from faculty and Ph.D. mentors.
  • Preferred Majors: Electrical & Computer Engineering
  • Preferred Skillsets: 1) Independence, curiosity, and critical thinking; 2) Programming experience at a basic level (Matlab or Python); 3) Linear algebra (EE 141L or equivalent).

• Graph-based analysis of EEG data
  • Project Description: EEGs are widely used to diagnose and treat various conditions (e.g., epilepsy or traumatic brain injuries). We are developing methods to estimate the spatial correlation between observations made at different electrodes. We start by estimating the similarity between EEG signals at any pair of sensors, and we next construct a sparse graph where only the most important similarities are preserved. Our goal is to explore different parameters in this system (temporal window, similarity metric, etc.) to identify those more promising in detecting medically significant events from EEG data.
  • Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
  • Student Responsibilities: Develop, implement, and test new algorithms to solve problems encountered in EEG data analysis, individually or in collaboration with graduate students. I expect students to take the initiative and define their project directions with support from faculty and Ph.D. mentors.
  • Preferred Majors: Biomedical Engineering,Electrical & Computer Engineering
  • Preferred Skillsets: 1) Independence, curiosity, and critical thinking; 2) Programming experience at a basic level (Matlab or Python); 3) Linear algebra (EE 141L or equivalent).

Our lab is nicknamed SCIP (Super Computing In Pocket). SCIP Research Areas:

1. Energy efficiency through heterogeneous computing
2. Reliability of high performance computing
3. Bandwidth efficient big data computing
4. Runtime systems design to enable dispersed computing
5. Hardware-assisted secure and private machine learning
6. Building innovative sensor data collection platforms to improve human performance

• Principal Investigator: Murali Annavaram
• Website: https://scip-lab.usc.edu
• Projects
  • Privacy-Preserving Large Language Models
    
    • Project Description: Large Language Models (LLMs) are proliferating in society, but securely preserving the privacy of user data used to train these models is an increasingly important issue. A mathematical framework called Differential Privacy (DP) allows us to rigorously quantify the privacy leakage occurring by these models. Although DP has been deployed by big organizations, such as Apple, Google, Microsoft, applying DP in LLMs is still relatively nascent. Our work aims for an optimal balance between privacy and model performance by designing algorithms that maximize utility while guaranteeing DP. Based on the student’s preference, we can either focus on the theoretical dimensions of this work, such as algorithmic design, or more applied work such as privacy evaluation of LLMs.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities:
      • Paper readings and discussion
      • Designing and implementing DP algorithms in Python
      • Experimental evaluation of DP algorithms on benchmarks
      • Attend weekly research meetings
    • Preferred Majors: Computer Science, Electrical & Computer Engineering
    • Preferred Skillsets:
      • Some mathematical background in Linear Algebra, Probability Theory, Algorithms
      • Programming experience in Python

• Principal Investigator: Andreas Molisch
• Website: https://usc.edu
• Projects
  • Mechanical design of reliable structures for channel sounders
    • Project Description: The student would be in charge of designing, modelling, and 3D printing different types of contraptions/structures to increase the reliability and repeatability of our sounding measurement campaigns. Additionally, the students will participate in measurement campaigns, when necessary. The student will be led by one or more PhD students from WiDeS lab in designing the parts and contraptions to meet mechanical and thermal requirements.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Designing, CAD modelling, and 3D printing of parts. Student will also check with vendors in case off-the-shelf components are needed.
    • Preferred Majors: Aerospace & Mechanical Engineering
    • Preferred Skillsets: Student should feel comfortable in any 3D CAD modelling software that allows easy export to 3D printing software. Previous experience with 3D printing and design of rotational structures is desirable.

• Coding and digitizer hardware for wireless channel sounders
  • Project Description: The student would be in charge of configuring, testing and troubleshooting sounding equipment and participate in measurement campaigns. The student will be led by one or more PhD students or Postdocs from WiDeS lab in configuring and testing high-speed digitizers and RF equipment.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Programming, testing and troubleshooting of digitizing equipment in Labview/Python/C or Matlab
  • Preferred Majors: Electrical & Computer Engineering
  • Preferred Skillsets: Student should feel comfortable with programming, working with RF equipment, excellent coding skills. Previous experience with Labview, Matlab and Python is desirable.

• Machine-learning based investigation of wireless channel features
  • Project Description: The student would be working on understanding wireless channels and identifying key features that may help improve modeling results with machine learning algorithms. The student will be led by one or more Postdocs from WiDeS lab in signal processing and ML investigations.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Programming, implementation of machine learning algorithms in Python or Matlab
  • Preferred Majors: Computer Science,Electrical & Computer Engineering
  • Preferred Skillsets: Student should feel comfortable with programming and learning signal processing as well as wireless fundamentals. Previous experience with Matlab and Python is desirable.

• Use of software-defined radios to measure millimeter-wave (5G) propagation channels
  • Project Description: The students would be in charge of configuring RF parameters towards the experiment execution scripts, including drafting, testing, and debugging the file with related devices from the COSMOS testbed. Moreover, the students are required to proceed data sanity check and post-processing evaluation before and after each necessary measurement campaign.
  • Open to: CURVE Continuing Researchers
  • Student Responsibilities: RF configuration, coding with C++ and Python, test and debug the script connected with devices, signal processing.
  • Preferred Majors: Electrical & Computer Engineering
  • Preferred Skillsets: Student should have solid background of wireless communication knowledge and be aware of RF equipment. Student should also be familiar with Fourier theory and signal processing.

• Ray tracing for high frequency
  • Project Description: This project aims to create a ray tracer that can emulate the behavior of wireless propagation channels at very high (e.g., Terahertz) propagation channels.
  • Open to: CURVE Continuing Researchers
  • Student Responsibilities: Students will be using tools from computer graphics (ray tracing, edge detection, etc.) to preprocess point-cloud databases of environments of interest (inside and outside of buildings), and develop methods for fast simulation of how rays of Terahertz radiation propagate from the transmitter to the receiver.
  • Preferred Majors: Computer Science,Electrical & Computer Engineering
  • Preferred Skillsets: Excellent knowledge in computer graphics is key. Strong programming skills (Python, C++) are a major plus.

• Location Tracking Using Microcontrollers
  • Project Description: Student will be in charge of maintaining and modifying existing Arduino code that logs the information coming from a sensor. Student will develop new code that adds information from additional sensors to the log file.
  • Open to: CURVE First-Time Researchers
  • Student Responsibilities: Create, maintain, modify Arduino microcontroller code bases. Suggest solutions to sensor logging problems.
  • Preferred Majors: Electrical Engineering, Electronics Engineering, Mechatronics Engineering, Mechanical Engineering
  • Preferred Skillsets: Student should be proficient in the use of Arduino microcontrollers and basic sensor electronics. Knowledge in STM32 microcontrollers desirable, but not needed.

Our research focuses on understanding and tracking human behaviors, social signals and emotions. To this end, we perform multimodal machine learning to analyze verbal and nonverbal behaviors. Our ongoing research include multimodal machine learning, human-agent interaction, mental health assessment, facial expression analysis and computational understanding of motivations and emotions.

• Principal Investigator: Mohammad Soleymani
• Website: https://ihp-lab.org/
• Projects
  • Socially Intelligent Agents
    • Project Description: This project aims to develop novel social capabilities for robots and virtual agents interacting with humans. Nonverbal behaviors are important indicators of active engagement in a social interaction and agents and robots should be able to naturally respond to users' verbal and nonverbal behaviors. In this project, we aim to build machine learning models that can augment heuristic and rule-based tools for generating and realizing compelling listening behaviors, e.g., head nods, voice back channels, etc. The resulting agent and robot will be better able to build rapport and trust with its users.
    • Open to: CURVE First-Time Researchers
    • Student Responsibilities: Students will develop and deploy automated rule-based and machine learning models for generating social behaviors. This project will involve hands-on programming and experimentation with social robots and virtual agents, available in the lab.
    • Preferred Majors: Computer Science
    • Preferred Skillsets: Python, Experience with .Net is a plus