Skip to main content

Robotics Summer Internships

The U.S. Department of Energy (DOE) Office of Energy Efficiency & Renewable Energy (EERE) Robotics Internship Program provides opportunities for students and recent graduates to intern at DOE national laboratories. Internships will last for 10 consecutive weeks from May to September at a DOE national laboratory. You will be mentored by and research alongside DOE scientists and subject matter experts, developing long-term relationships between yourself, researchers and others at your hosting laboratory.

Project Assignments

Project assignments will involve technologies used to develop machines that can substitute for humans and replicate human actions automatically. Examples of potential project assignments include:

  • Programming for a system that has sensing, acting, and/or communicating.
  • Designing and/or fabricating structural aspects of a robotic system or improvements to one.
  • Integrating sensors or exploring the integration of sensors to a system so that it can be made more robotic or smart.
  • Adding actuation or functional capability to a system so that it can improve its ability level of action.
  • Enhancing the human/machine interface to improve the communication with a system employing robotic technologies.
  • Designing experiments that involve robotic technologies at some level of sophistication.
  • Exploring ways to make traditionally “dumb” systems more “smart” with robotic characteristics. i.e. smart homes, smart buildings, smart products, etc.

EERE Robotics Internship Details

 

  • Application Cycle

    AMO Summer Internships are open for applications during the Fall/Winter of each year.

    2022 Application Year

    Online Applications Open  November-December 2021 Applicants will have the opportunity to review a project catalog of projects provided by hosting facilities to find a suitable match for their interests and educational discipline. Project catalogs can be found on the respective program page. 
    Application Deadline January-March 2022
    • Applicants should not contact research facilities/mentors after the application deadline
    • Applicants may contact mentors to ask questions about projects during the application period.
    Application Review February/March 2022
    Internship Notification March/April 2022 Candidates are notified of selections and receive offer letter to accept or decline internship
    Internship Period May - September 2022

    Candidates accept their internship offer and begin their ORISE internship.

    • Interns must complete 10-weeks of internship
    • In most cases, interns will have the opportunity to collaborate with their hosting laboratory to ensure internship dates work best for the intern and mentor. However, some hosting laboratories have separate requirements for summer internship periods.

  • Application Review and Selection

    In the application process, you will review available projects for your ORISE summer internship and provide your preference for which project and mentor you want to intern with for the summer. Mentors will review complete applications and project preferences to determine their ORISE intern selections and best match for their projects. Mentors may contact you directly or schedule interviews with you as part of the review process, and we encourage you to engage with them to determine the best fit for you and your potential mentor.

    However, mentor selection is only one part of the review process. Mentor selection of your application does not guarantee you will be selected to participate in an internship program.

    After mentors have submitted their selections, ORISE, who manages the summer internship programs for EERE AMO, will review selected applications for eligibility and completeness, and provide detailed information to EERE AMO representatives. EERE AMO will make final selections based on reviewer results.

    Once selections are finalized by EERE AMO, ORISE will notify you and your mentor if you are selected for an internship program. Formal offers will be sent through Zintellect, the ORISE application and participant tracking system.

  • Eligibility

    The EERE Robotics Internship Program is open to all students and recent graduates who meet the following qualifications:

    • Be a U.S. citizen.
    • Be at least 18 years old by May 1 of the internship year
    • Meet one of the following conditions:
      • Recent graduate: Have earned an associate, undergraduate or graduate degree in the past two years in a field related to robotics, manufacturing, or engineering.
      • Student: Be enrolled as a full-time student pursuing a degree related to robotics, manufacturing, or engineering. Proof of enrollment during spring semester must be submitted to ORISE at the time the appointment is accepted.
      • High school seniors, undergraduate students, graduate students, and postgraduates, earning a degree in the past two years, are eligible to apply. 

    For more detailed information about eligibility, refer to the Zintellect opportunity announcement

  • Appointment Details

    • Appointments will be for 10 consecutive weeks during the months of May-September. Factors such as class schedules, housing availability, and laboratory schedules may be taken into consideration when determining appointment start and end dates.
    • An appointment involves a full-time commitment at the host laboratory with the intern in residence on-site at the specified location.
    • Interns are required to have health insurance coverage during the appointment period and to provide proof of this coverage prior to the start of the appointment.
  • Stipend and Other Benefits

    • Stipend: Based on academic level at the start of your internship appointment.
      • High school senior, undergraduate students, and post- bachelors receive $700 per week
      • Masters students or post- masters receive $900 per week
      • Doctoral students and postdoctoral receive $1000 per week
    • Travel: Travel reimbursement for inbound and outbound expenses up to a combined maximum of $2,000 if you live more than fifty miles, one-way, from your assigned hosting laboratory.
    • Housing Allowance: A housing stipend starting at $150 per week. Additional housing stipend may be provided to offset high cost of living in certain locations.
    • Training/Research Allowance: Up to $250 to offset relevant costs, such as fees for submitting research for publication, access to relevant training, etc.

Project Catalog for the Robotics Summer Internships

Applicants submitting an application to the EERE Robotics Summer Internships Program are required to select one to three projects. Review the list below to determine which projects you are most interested in for your internship. Submit your project preferences in the relevant section in your Zintellect application.

This project catalog will be updated throughout the application period. If you do not see any projects of interest to you, check back often for updates throughout the application period. All available projects will be finalized 2 weeks prior to the application deadline.

For technical assistance with navigating Zintellect, contact Zintellect Support at Zintellect@orau.org.

The Summer 2022 Project Catalog will be updated starting in November 2021. Please check back regularly for updates.

 

Project Title Citizenship Required Reference Code Posted Date Posted Datetime Hosting Site Internship Location Description

Yes ANL-Plathottam1 12/1/2021 1638334800000 Argonne National Laboratory Batavia, IL

U.S. Citizenship is a requirement for this internship

Project Description:

In this project, the intern will develop a surrogate model for a Power Electronic inverter using Physics Informed Neural Networks (PINN). This project will support the Department of Energy Office of Electricity’s, Advanced Grid Modeling program as well as support Office of Science’s focus on Scientific Machine learning. For this project, we want to extend the capability of models used in large-scale power grid simulations.

The primary focus of our project is applying artificial intelligence (AI) and scientific machine learning (SciML) for developing high-performance models of inverter-based resources (e.g. Solar PV system, Battery storage system). One application of these models is to simulate power grids with high renewable energy penetration much faster than what is possible with existing first principle models. The internship project will focus on taking an existing inverter model with its dynamics defined by a system of ordinary differential equations (ODEs) and using them to train a Physics informed neural network model of the inverter.

TASKS
Under the guidance of the PI, the student will perform the following tasks:
• Review relevant literature on scientific machine learning with a focus on Physics Informed Neural Networks.
• Review state-of-the-art open-source packages (in Python or Julia) which can be used for SciML.
• Design a workflow for converting a system of ODEs into a Physics Informed Neural Network model.
• Implement the workflow and train a surrogate model for at least one type of power electronic inverter.
• Maintain the code related to the project in a public repository (GitHub).

STUDENT REQUIREMENTS
• Computer Science, Engineering, or Mathematics background.
• Proficiency in Python.
• Familiarity with Machine learning or dynamic modeling using ODEs.
• At least 3.0 GPA on a 4.0 scale.
• A desire to participate in a dynamic work environment with competing deadlines.
• Ability to be highly motivated and self-starting.

Hosting Site:

Argonne National Laboratory

Internship location: Batavia, IL

Mentor:

  • Siby Jose Plathottam
    splathottam@anl.gov
    (630) 252-6516

Internship Coordinator:

  • Lindsay Buettner
    lcullen@anl.gov

Yes ANL-Stutenberg1 12/1/2021 1638334800000 Argonne National Laboratory Batavia, IL

U.S. Citizenship is a requirement for this internship

Project Description:

The goal of this project will be to support the development and analysis of a system for capturing on-road data of connected and automated vehicle technologies. The participant will gain direct experience with development of components of the autonomous system and test vehicles, interpreting and processing corresponding datasets, and continued system refinement. Additional areas for experience will include integration of the simulated environments with vehicles in a laboratory of a chassis dynamometer.

Hosting Site:

Argonne National Laboratory

Internship location: Batavia, IL

Mentor:

  • Kevin Stutenberg
    kstutenberg@anl.gov
    6086982019

Internship Coordinator:

  • Lindsay Buettner
    lcullen@anl.gov

Yes LLNL-Czyz1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

There is a growing concern that a terrorist may try to detonate a nuclear weapon.  We are looking for students interested in developing new analysis methods that can reduce the threat of such a devastating occurrence.  We are working on systems that can find nuclear threats being produced, being transported out of other countries, entering the U.S., and en route between facilities or to its destination.  Our focus is on improving the sensitivity of these systems to detect nuclear threat signatures, and to recognize benign radiation sources to avoid false alarms.  This is challenging because nuclear threat signatures are typically quite weak, and easily overwhelmed by the presences of the benign radioactive materials in our environment.  We are applying the most recent advances in detection technology, sensor networks, signal processing, multi-modal data fusion analysis, machine learning, and big-data analytics to this problem. Our solutions are providing new capabilities that are going into operations to help close some of the most urgent needs for improving our ability to detect nuclear threats. 

This position will focus on machine learning approaches for analysis of multi-modal measurements.  We are developing a measurement system that includes gamma-ray and neutron detectors along with LiDAR, video, magnetometer, geophone and RF sensors.  Knowledge about radiation detectors and these other sensors is not a requirement for this project (but if you collaborate on it you will know a lot about it by the end), your project will be to develop and optimize machine learning methods to provide data fusion and enhance the performance of this multi-modal measurement system. 

Ideal candidates will have programming experience and familiarity with Python or Matlab.  Proficiency in principles of object-oriented programming and software development best practices is a big plus, as is experience with Java or C++.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Steven Czyz
    czyz1@llnl.gov
    1-925-724-6098

Internship Coordinator:

  • Simon Labov
    labov1@llnl.gov
    925-423-3818

Yes ANL-Iloeje1 12/1/2021 1638334800000 Argonne National Laboratory Batavia, IL

U.S. Citizenship is a requirement for this internship

Project Description:

Argonne supports the Department of Energy, Advanced Manufacturing Office, on a multi-laboratory strategic analysis team. With researchers at LBNL, NREL, and ORNL, we evaluate the feasibility and life cycle impacts of sustainable manufacturing. For this project, we want to extend the capability of our tools for automated design of chemical process configurations, where artificial intelligence (AI) agents independently assemble, simulate and optimize process designs, given target specifications. This will primarily involve the design of a learning environment to allow an AI agent to interact with – and learn from – a simulation environment.

The primary focus of our project is applying artificial intelligence (AI) to manufacturing optimization. The idea is to substitute the human designer with a software agent that can learn by interacting with a virtual environment for process design and simulation. The internship project will focus on building a learning environment that serves as an interface between the AI agent and the simulation environment, implementing agent actions and returning rewards to facilitate reinforcement learning. Of course, the simulation environment can be replaced in the future with sensor data from a physical process, but that is not the stage we are at. The candidate will develop a learning environment to allow AI-agents to interact with the building blocks simulation framework to optimize the engineering process design. This project will contribute to a broader research program involving a multi-laboratory team focused on improving energy and sustainable manufacturing systems

TASKS
Under the guidance of the PI(s), the student will perform the following tasks:
•  Review relevant literature on learning environments for deep reinforcement learning (DRL) agents.
•  Critically study and assess existing codebase (in Python).
•  Formulate strategies to facilitate agent learning to accomplish design goals (e.g., through reward engineering).
•  Maintain, modify, and extend existing codebase in the public repository (GitHub).

STUDENT REQUIREMENTS
• Computer Science, Engineering or Mathematics background.
• Proficiency in Python.
• Familiarity with Get, reinforcement learning, and OpenAI  Gym is a plus
• At least 3.0 GPA on 4.0 scale.
• A desire to participate in a dynamic work environment with competing deadlines.
• Ability to be highly motivated and self-starting. For this project, the selected candidate will explore deep reinforcement learning for chemical process intensification. 

Hosting Site:

Argonne National Laboratory

Internship location: Batavia, IL

Mentor:

  • Nwike Iloeje
    ciloeje@anl.gov
    (630) 252-6878

Internship Coordinator:

  • Lindsay Buettner
    lcullen@anl.gov

Yes LLNL-Qin1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

Combining low-cost unmanned route and points optimized low-water solar-panel-cleaning ground robotic fleet with deep learning dirt detection aerial robotics carrier (1 aerial carrier served for 6-12 ground cleaning robots) to rescue dirty solar panel efficiency up to 30% per year (an analysis by the US National Renewable Energy Laboratory (NREL) that showed a potential 30% energy yield loss per year, if they are not cleaned monthly).

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Yining Qin
    qin3@llnl.gov
    9254228695

Yes ANL-Lee1 12/1/2021 1638334800000 Argonne National Laboratory Batavia, IL

U.S. Citizenship is a requirement for this internship

Project Description:

X-ray beamlines at the nation’s most powerful synchrotron, the Advanced Photon Source (APS) at the Argonne National Laboratory (ANL), have been developing autonomous experimental data acquisition and using robot arms to load/unload samples as well as to prepare samples. This project includes programming a UR robot and CCD cameras for molecular biology experiments at an x-ray beamline of APS. The student will participate in the development of robotic operation in mixed-reality environment incorporating virtual-reality simulation as well as hardware robot operation assisted by artificial intelligence (AI). Particularly, AI will be used to analyze the camera feed in recognizing situations around the robot arm and making a decision, for example, whether the sample loading was done properly or needs a new loading. The student can also be mentored by an AI expert at ANL.

Hosting Site:

Argonne National Laboratory

Internship location: Batavia, IL

Mentor:

  • Byeongdu Lee
    blee@anl.gov
    630-252-0395

Internship Coordinator:

  • Lindsay Buettner
    lcullen@anl.gov

Yes LLNL-McFerran1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

There is a growing concern that a terrorist may try to detonate a nuclear weapon.  We are looking for students interested in developing new analysis methods that can reduce the threat of such a devastating occurrence.  We are working on systems that can find nuclear threats being produced, being transported out of other countries, entering the U.S., and en route between facilities or to its destination.  Our focus is on improving the sensitivity of these systems to detect nuclear threat signatures, and to recognize benign radiation sources to avoid false alarms.  We are applying the most recent advances in detection technology, sensor networks, signal processing, multi-modal data fusion analysis, machine learning, and big-data analytics to this problem. Our solutions are providing new capabilities that are going into operations to help close some of the most urgent needs for improving our ability to detect nuclear threats. 

This position will focus on machine learning approach to uncertainty quantification of uranium enrichment measurements.  We have lots of measurements of tanks filled with uranium, and we need to know how accurately we can determine the enrichment.  We are using machine learning to combine radiation measurements with non-radiation measurements and contextual information to estimate enrichment and the uncertainty in enrichment.  Knowledge about uranium enrichment is not a requirement for this project (but if you work on it you will know a lot at the end), your job will be to help figure out if enrichment is happening more than expected: false positives are bad as we don’t want to blame someone for doing something wrong if they are not, and false negatives are bad as we don’t want to miss anything.

Applicants need to have programming experience and familiarity with Python or Matlab.  Proficiency in principles of object-oriented programming and software development best practices is a big plus, as is experience with Java or C++.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Noah McFerran
    mcferran4@llnl.gov
    510-432-9986

Internship Coordinator:

  • Simon Labov
    labov1@llnl.gov
    9257843689

Yes LLNL-Monterial1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

There is a growing concern that a terrorist may try to detonate a nuclear weapon.  We are looking for students interested in developing new analysis methods that can reduce the threat of such a devastating occurrence.  We are working on systems that can find nuclear threats being produced, being transported out of other countries, entering the U.S., and en route between facilities or to its destination.  Our focus is on improving the sensitivity of these systems to detect nuclear threat signatures, and to recognize benign radiation sources to avoid false alarms.  This is challenging because nuclear threat signatures are typically quite weak, and easily overwhelmed by the presences of the benign radioactive materials in our environment.  We are applying the most recent advances in detection technology, sensor networks, signal processing, multi-modal data fusion analysis, machine learning, and big-data analytics to this problem. Our solutions are providing new capabilities that are going into operations to help close some of the most urgent needs for improving our ability to detect nuclear threats. 

This position will focus on machine learning approaches for analyzing gamma-ray spectral measurements.  We have developed several methods to determine the composition of the radiation source from their gamma-ray emissions, some of these use machine learning, and others can be enhanced by using their outputs as features that are analyzed using machine learning.  Knowledge about gamma-ray spectroscopy is not a requirement for this project (but if you work on it you will know a lot about it by the end), your job will be to develop and optimize machine learning methods enhancing the capabilities of the physics-based codes already in place. 

Applicants need to have programming experience and familiarity with Python or Matlab.  Proficiency in principles of object-oriented programming and software development best practices is a big plus, as is experience with Java or C++.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Mateusz Monterial
    monterial1@llnl.gov
    1-925-961-4730

Internship Coordinator:

  • Simon Labov
    labov1@llnl.gov
    9257843689

Yes LLNL-Albin1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

There is a growing concern that a terrorist may try to detonate a nuclear weapon.  We are looking for students interested in developing new analysis methods that can reduce the threat of such a devastating occurrence.  We are working on systems that can find nuclear threats being produced, being transported out of other countries, entering the U.S., and en route between facilities or to its destination.  Our focus is on improving the sensitivity of these systems to detect nuclear threat signatures, and to recognize benign radiation sources to avoid false alarms.  We are applying the most recent advances in detection technology, sensor networks, signal processing, multi-modal data fusion analysis, machine learning, and big-data analytics to this problem. Our solutions are providing new capabilities that are going into operations to help close some of the most urgent needs for improving our ability to detect nuclear threats. 

This position will focus on nuclear threat detection using sensor networks with machine learning.  A single radiation measurement is often insufficient to find nuclear threats without excessive false alarms.  Combining multiple measurements, often taken at different times, with different instruments is difficult. We are using machine learning to enhance threat detection from heterogeneous sensors.  We already have tools that can process the data producing threat scores, so knowledge about nuclear threat detection is not a requirement (but you will learn a lot about it if you work on this project).  Your job will be to help explore machine learning approaches to combining the information to improve detection and reduce false alarms.

Applicants need to have programming experience and familiarity with Python or Matlab.  Proficiency in principles of object-oriented programming and software development best practices is a big plus, as is experience with Java or C++.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Eric Albin
    albin3@llnl.gov
    9257247362

Internship Coordinator:

  • Simon Labov
    labov1@llnl.gov
    9257843689

Yes LLNL-Swanberg1 12/1/2021 1638334800000 Lawrence Livermore National Laboratory Livermore, CA

U.S. Citizenship is a requirement for this internship

Project Description:

There is a growing concern that a terrorist may try to detonate a nuclear weapon.  We are looking for students interested in developing new analysis methods that can reduce the threat of such a devastating occurrence.  We are working on systems that can find nuclear threats being produced, being transported out of other countries, entering the U.S., and en route between facilities or to its destination.  Our focus is on improving the sensitivity of these systems to detect nuclear threat signatures, and to recognize benign radiation sources to avoid false alarms.  This is challenging because nuclear threat signatures are typically quite weak, and easily overwhelmed by the presences of the benign radioactive materials in our environment.  We are applying the most recent advances in detection technology, sensor networks, signal processing, multi-modal data fusion analysis, machine learning, and big-data analytics to this problem. Our solutions are providing new capabilities that are going into operations to help close some of the most urgent needs for improving our ability to detect nuclear threats. 

This position will focus on machine learning approaches for analysis of multi-modal vehicle sensors.  We are developing a measurement system that includes magnetometer, geophone and RF sensors that measure many different attributes of passing vehicles.  Your job will be to develop and optimize feature extraction and machine learning methods to determine as much information about passing vehicles as possible including speed, distance, vehicle type, vehicle weight and if this same vehicle was measured previously. 

Applicants need to have programming experience and familiarity with Python or Matlab.  Proficiency in principles of object-oriented programming and software development best practices is a big plus, as is experience with Java or C++.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Livermore, CA

Mentor:

  • Erik Swanberg
    swanberg3@llnl.gov
    925 724 6902

Internship Coordinator:

  • 925 724 6902
    labov1@llnl.gov
    9254233818

No NREL-Nichols1 12/7/2021 1638853200000 National Renewable Energy Laboratory Golden, CO

Project Description:

Project Description:
Commercial wind blades continue to get longer every year with offshore wind blades exceeding 100 meters in length. There are major opportunities in improving the manufacturing methods of wind blades by solving issues with safety, repeatability, and cost. Developments in factory automation with robotics provides solutions to safely manufacture large offshore wind blades that can lower wind energy costs, improve wind energy reliability, and enable viable options for domestic manufacturing.


The NREL team will lead this research based on recent project experience with robotics in wind blade manufacturing and leveraging the new Kuka industrial robot platform in the CoMET. This system is a 7-axis advanced industrial robot with a 300-kg payload rating, 2.5-meters arm reach, and a track with more than 6-meters stroke. This Kuka robotics platform as a tool for the team of researchers in blade automation will enable the research and development of automation hardware and software that will scale for manufacturing large offshore wind blades. The robotics to be developed through this program will be capable of safely working at the heights necessary in a blade factory for manufacturing large offshore wind blades while keeping operators safely on the ground.

The NREL team is seeking a EERE Robotics Intern to assist in these research efforts. The intern will gain experience designing, implementing and optimizing industrial robot software and hardware to achieve the desired results in blade safety, reliability and cost. This may include opportunities exploring:

  • Robot toolpath programming with Python, Matlab or LabVIEW
  • Blade finishing end effector design, prototyping or optimization
  • Computer vision to develop innovative toolpath generation algorithms
  • Machine learning to improve robot toolpath generation quality
  • Robot mobilization within blade manufacturing facilities
  • Laboratory testing of blade manufacturing technologies

Hosting Site:

National Renewable Energy Laboratory

Internship location: Golden, CO

Mentor:

  • Casey Nichols
    casey.nichols@nrel.gov
    720-539-1493

Internship Coordinator:

  • Ryan Beach
    ryan.beach@nrel.gov

No LLNL-Qin 12/7/2021 1638853200000 Lawrence Livermore National Laboratory Berkeley, CA

Project Description:

Combining low-cost unmanned route and points optimized low-water solar-panel-cleaning ground robotic fleet with deep learning dirt detection aerial robotics carrier (1 aerial carrier served for 6-12 ground cleaning robots) to rescue dirty solar panel efficiency up to 30% per year (an analysis by the US National Renewable Energy Laboratory (NREL) that showed a potential 30% energy yield loss per year, if they are not cleaned monthly).

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Berkeley, CA

Mentor:

  • Yining Qin
    qin3@llnl.gov
    9254228695

No ANL-Park1 12/7/2021 1638853200000 Argonne National Laboratory Lemont, IL

Project Description:

A recent report by the current administration recommends innovations in intelligent manufacturing and advanced materials as the future direction in manufacturing. To this end a new breed of intelligent robots, namely co-robots, is emerging which can work in collaboration with humans. In this regard, the objective of this project is to develop a new human-robot interface (HRI) for collaborative robotic systems which can render safe and intuitive collaboration. The performance of the technology will be tested on a collaborative robot for human-robot collaborative tasks. The development will encompass the design and prototyping of haptic sensor, and development of human-robot interaction control algorithm. The development will utilize the 3D printing, microcontroller, and software infrastructure based on robot operating system (ROS) in the lab.

Hosting Site:

Argonne National Laboratory

Internship location: Lemont, IL

Mentor:

  • Young Soo Park
    ypark@anl.gov
    (630) 639-2149

Internship Coordinator:

  • Lindsay Cullen
    lcullen@anl.gov

No LLNL-Goldhahn 12/7/2021 1638853200000 Lawrence Livermore National Laboratory Berkeley, CA

Project Description:

Coming soon.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Berkeley, CA

Mentor:

  • Ryan Goldhahn
    goldhahn1@llnl.gov
    925-961-6605

No ANL-Park2 12/7/2021 1638853200000 Argonne National Laboratory Lemont, IL

Project Description:

Materials are an essential element in the future of advanced energy technology and industry. However, the discovery of new materials is a lengthy and costly process, which also requires the knowledge and experience of highly trained experts. However, development of new materials is a lengthy and costly process, which also requires expert help. To this end, there is a great opportunity to scale-up and speed up the materials discovery process by incorporating robotics and artificial intelligence (AI). Such robotics systems are expected to bring about enhancements in all phases of next generation material discovery processes- process design, synthesis, characterization, and feedback optimization. However, the current state of the scientific robotic systems lacks the performance and flexibility to accommodate leading edge technologies for next generation materials discovery process. To this end, this project addresses the development of a new modular robotic platform that can simulate and execute automation and autonomous materials discovery process. The development will entail integration Argonne’s technology basis on 3D virtual-reality simulation, sensor-based augmented-reality, teleoperation, and machine learning for the development of a digital robotics platform that facilitates hardware-in-the-loop simulation of materials synthesis process. The project task will entail both hardware (3D printing and assembly) and software development.

Hosting Site:

Argonne National Laboratory

Internship location: Lemont, IL

Mentor:

  • Young Soo Park
    ypark@anl.gov
    (630) 252-5094

Internship Coordinator:

  • Lindsay Cullen
    lcullen@anl.gov

No ANL-Park3 12/7/2021 1638853200000 Argonne National Laboratory Lemont, IL

Project Description:

After many years of proliferation of nuclear industry, the nation is indebted with enormous liability for nuclear waste cleanup and decontamination and decommissioning (D&D) of life-ended nuclear facilities. In this regard, deployment of robotic and remote systems is expected to perform tasks in the hazardous environments to keep the human workers out of the harm’s way. Many of such tasks require handling of heavy tools in contact with facility structures and equipment, thus required force sensitive robots. However, such robots with complex force sensors are unsuitable for remote deployment. What is required is a new robot manipulator which is simple and rugged robot system, and yet capable of dexterous force reflection. Recently a new bilateral control approach was developed for surgery robotics with essential vibration feedback. To this end, this project aims at developing a bilateral (force reflection) control system for D&D operation utilizing tactile feedback. In this teleoperation system, instead of force sensors, accelerometers will be used to capture high frequency tactile sensastion, which will be fed back to vibro-tactile operator interface. Since the high frequency vibro-tactile feedback will not affect the stability of the bilateral control, it will be possible to achieve effective contact manipulation with simple and rugged heavy manipulator. In this project the student will be participating in the provision of accelerometer on the slave robot, vibro-tactile feedback on the hand-controller, signal filtering, and implementation of bilateral telerobotic control system. The student is expected to have knowledge in computer programming language (C++, python) and electronics.

Hosting Site:

Argonne National Laboratory

Internship location: Lemont, IL

Mentor:

  • Young Soo Park
    ypark@anl.gov
    (630) 252-5094

Internship Coordinator:

  • Lindsay Cullen
    lcullen@anl.gov

No ANL-Park4 12/7/2021 1638853200000 Argonne National Laboratory Lemont, IL

Project Description:

The objective of the project is to develop a new telerobotic operation method, namely augmented teleautonomy, which enhances the efficiency and accuracy by integrating sensor based augmented reality and autonomous motion primitives via machine learning. In teleoperation, human operator operates a robot from a distance using visual-haptic human-robot interfaces. Augmented reality - the technology that can blend artificial entity with real world perception - can provide effective perceptual guidance to human operator in such operation. In addition, recent advances in machine learning technologies allow realization of complex and flexible autonomous robotic behaviors. The development will be built on previous development of 3D sensing and augmented-reality display technology basis, and to integrate onto the remote control system of a collaborative two-arm robot system, Baxter, for demonstration. The software development will be based on utilization of Robot Operating System (ROS) which is a Linux-based open-source distributed operating system. The outcome of the R&D is expected to have crosscutting contributions in the design and operation experience of various energy facilities, as well as social applications such as entertainment, healthcare, and everyday conveniences.

Hosting Site:

Argonne National Laboratory

Internship location: Lemont, IL

Mentor:

  • Young Soo Park
    ypark@anl.gov
    (630) 252-5094

Internship Coordinator:

  • Lindsay Cullen
    lcullen@anl.gov

No LLNL-Mitchell1 12/7/2021 1638853200000 Lawrence Livermore National Laboratory Berkeley, CA

Project Description:

LLNL is conducting research at the intersection of biology and materials science, specifically on biocompatible materials processing using “bio-electrospinning.” Students may research topics in materials such as electrospun fibers and polymer properties. Under the mentorship of a small group of scientists, interns will develop and/or characterize materials designed to stabilize biological media for division supported applications such as novel sensors and filters.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Berkeley, CA

Mentor:

  • Mark Mitchell
    mitchell36@llnl.gov
    (925) 422-8600

No LLNL-Mitchell2 12/7/2021 1638853200000 Lawrence Livermore National Laboratory Berkeley, CA

Project Description:

LLNL is conducting exciting research in 3D printing/additive manufacturing as well as research on porous membranes, sealants, ceramics, gas separations, and/or filtration. One research project poses interesting opportunities to research two different approaches to 3D printing. Students may research advanced materials processing including inorganic materials processing, thermal processing and thermodynamics of materials, and materials characterization.  Students will combine conventional ceramic processing techniques with additive manufacturing with the goal of creating filters with complex internal geometries that can meet and exceed requirements. This challenge requires a quantitative investigation of the capabilities of 3D printing of polymers for use as ceramic templates. The manufacturing limits of thermoplastic 3D printing, including accuracy and size, must be understood in relation to the design space of ceramic filters. This information will allow our group to develop novel filter designs that advance the state of the art. This research is directly applicable to improving safety. HEPA filtration is a critical component of safety systems in hospitals, manufacturing facilities, and nuclear facilities. The added demands of fire resistance, low pressure drop, and reusability have driven research efforts for more effective ceramic filtration technologies. Students may also research additional emerging technological areas with potentially different technical goals and include processing from powders of ceramics and metals. Additional examples of additive manufacturing opportunities include:

  1. Additive manufacturing of ceramics and metals capable of surviving high temperatures and harsh environments (e.g., ceramic heat exchangers for concentrated solar power plants and next-generation nuclear reactors; ceramic HEPA filters, effluent, and CO2 scrubbers; and ultra-high temperature ceramics [UHTCs]) can improve infrastructure resiliency and nuclear safety, as well as minimize releases of hazardous materials.
  2. Additive manufacturing of polymers (e.g., scintillators, thermoluminescent materials) can improve nuclear safety and increase understanding of doses after a nuclear accident.
  3. Additive manufacturing of innovative, magnetically attached radiation shielding (MARS) can reduce dose to maintenance personnel (e.g., during maintenance outages in nuclear reactors). 
  4. Magnetostrictive materials for advanced manufacturing of actuators and sensors to improve stability, reliability, and resiliency of the electrical grid while reducing the risk of wildfires

Education: Engineers or material scientists

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Berkeley, CA

Mentor:

  • Mark Mitchell
    mitchell36@llnl.gov
    (925) 422-8600

No LLNL-Mitchell3 12/7/2021 1638853200000 Lawrence Livermore National Laboratory Berkeley, CA

Project Description:

LLNL is conducting exciting research in organic and inorganic electrospun nanofibers.  Our goal is to develop robust and efficient methods for development, production, and integration of nanofibers for a broad range of applications, including sensors. The student will learn and participate in activities related to the processing of ceramic nanofibers as well as polymeric nanofibers. Students may research development of feedstock formulations, electrospinning optimization, structural characterization, forming, thermal processing, process scaling, device integration/prototype development, and performance testing. Students will combine conventional electrospun nanofiber processing techniques with innovative new approaches that can meet and exceed requirements. This challenge could help address America’s need for appropriate materials for N95 masks to prevent the spread of COVID-19. The manufacturing limits of electrospun nanofibers must be understood in relation to the design space of the application. This information will allow our group to develop novel nanofiber materials that advance the state of the art.  At present, nanofiber media prepared by LLNL are manipulated manually to create useable structures one-at-a-time in a very time and labor-intensive process. Thousands of these structures are required for scaling the process and testing prototypes that use these structures. Automating these rather delicate cutting, peeling, handling, heat sealing, and general mechanical manipulation processes can improve productivity to reduce time and labor requirements. Fundamentally different filter designs compared to conventional filters also require new metrics and in-line sensors for health monitoring of the filter.

Hosting Site:

Lawrence Livermore National Laboratory

Internship location: Berkeley, CA

Mentor:

  • Mark Mitchell
    mitchell36@llnl.gov
    (925) 422-8600

The name and contact information of the hosting site internship coordinator is provided for further assistance with questions regarding the hosting site; local housing availability, cost, or roommates; local transportation; security clearance requirements; internship start and end dates; and other administrative issues specific to that research facility. If you contact the internship coordinator, identify yourself as an applicant to the NSF Mathematical Sciences Graduate Internship (MSGI) Program.

Interns will not enter into an employee/employer relationship with the Hosting Site, ORAU/ORISE, EERE or DOE. No commitment with regard to later employment is implied or should be inferred.