Logo
ORAU

Resource Constraint adaptive computing: Algorithm and optimization for ARL Auton

ORAU, Aberdeen, Maryland, United States, 21001

Save Job

Resource Constraint adaptive computing: Algorithm and optimization for ARL Autonomy Stack Overview: There is an internship opportunity from Army Research Laboratory at Aberdeen Proving Ground for graduate students with US citizenship or green card holder. The ARL team focuses on optimizing computationally expensive perception algorithms of the Autonomy stack. Autonomous vehicles use sensors such as RGB camera and LiDAR to sense the environment and build the world map for autonomous maneuver. ARL autonomy stack has many perception algorithms including object detection, semantic segmentation, image classification, etc. These sensors collect large amounts of data that have to be processed by multiple perception algorithms sharing the limited computing resource in real-time. Army SWaP (Size, Weight, and Power) requirements which significantly limit the computing and communication resources of autonomous vehicles and also limit the battery size. Therefore, ARL team will develop and apply different approaches to optimize the perception algorithms to fit in tactical unmanned vehicles (UGVs) with limited computing resources to achieve real-time operation and accomplish the mission. The student will closely work with ARL researchers in optimizing and integrating containerized ML algorithms to UGVs and evaluating the model's performance in the lab and field tests.

Organization DEVCOM Army Research Laboratory

Description About the Research

There is an internship opportunity from Army Research Laboratory at Aberdeen Proving Ground for graduate students with US citizenship or green card holder. The ARL team is mainly focused on optimizing computationally expensive perception algorithms of Autonomy stack. Autonomous vehicles use various sensors such as RGB camera and LiDAR to sense the environment and build the world map for autonomous maneuver. ARL autonomy stack has many perception algorithms including object detection, semantic segmentation, image classification etc. These sensors collect large amount of data that have to be processed by multiple perception algorithms sharing the limited computing resource in real-time. At the same time, the Army has SWaP (Size, Weight, and Power) requirements which significantly limit the computing and communication resources of autonomous vehicles and also limit the battery size. Therefore, ARL team will develop and apply different approaches to optimize the perception algorithms to fit in tactical unmanned vehicles (UGVs) with limited computing resources to achieve real-time operation and accomplish the mission. The student will closely work with ARL researcher in optimizing and integrating containerized ML algorithms to UGVs and evaluating the model's performance in the lab and field tests.

Position will include

Using Python, C++, and software repositories

Optimizing deep learning perception algorithms

Using containerization technologies such as Docker to create docker image for perception algorithms to be evaluated in ROS environment.

Deploying machine learning algorithms in a ROS environment on UGV

Documenting and publishing the results in technical reports or conference papers

The candidate does not need to have all skills right now but must be willing to learn new technology.

ARL Advisors: Peng Wang, Billy Geerhart

ARL Advisor Email: peng.wang2.civ@army.mil, billy.e.geerhart2.civ@army.mil

Keywords: Deep Learning Perception model; model optimization; ROS

About Army Research Directorate (ARD) ARL’s Army Research Directorate (ARD) focuses on exploiting concept development, discovery, technology development, and transition of the most promising disruptive science and technology to deliver to the Army fundamentally advantageous science-based capabilities through laboratory’s 11 research competencies. This intramural research directorate also manages the laboratory’s essential research programs, which are flagship research efforts focused on delivering defined outcomes.

About Network Cyber & Computational Sciences (NCCS) Sciences to enable and ensure secure resilient communication networks for distributed analytics in Multi-Domain Operations.

About ARL-RAP The Army Research Laboratory Research Associateship Program (ARL-RAP) is designed to significantly increase the involvement of creative and highly trained scientists and engineers from academia and industry in scientific and technical areas of interest and relevance to the Army. Scientists and Engineers at the CCDC Army Research Laboratory (ARL) help shape and execute the Army's program for meeting the challenge of developing technologies that will support Army forces in meeting future operational needs by pursuing scientific research and technological developments in diverse fields such as: applied mathematics, atmospheric characterization, simulation and human modeling, digital/optical signal processing, nanotechnology, material science and technology, multifunctional technology, propulsion and flight physics, communication and networking, and computational and information sciences.

A complete application includes

Curriculum Vitae or Resume

Three References Forms

Transcripts

Transcript verifying receipt of degree must be submitted with the application. Student/unofficial copy is acceptable

If selected by an advisor the participant will also be required to write a research proposal to submit to the ARL-RAP review panel for :

Research topic should relate to a specific opportunity at ARL

The objective of the research topic should be clear and have a defined outcome

Explain the direction you plan to pursue

Include expected period for completing the study

Include a brief background such as preparation and motivation for the research

References of published efforts may be used to improve the proposal

A link to upload the proposal will be provided to the applicant once the advisor has made their selection.

Questions about this opportunity? Please email ARLFellowship@orau.org.

Eligibility Requirements

Degree: Currently pursuing a Master's Degree or Doctoral Degree.

Academic Level(s): Any academic level.

Discipline(s):

Computer, Information, and Data Sciences

Artificial Intelligence (including Robotics, Computer Vision, and Human Language Processing)

Computer Architecture and Grids

Computer Science - Languages and Systems

Computer Science - Theoretical Foundations

Computer Science (general)

Computer Systems Analysis

Computer Systems Design (including Signal Processing)

Data Science

Databases, Information Retrieval, and Web Search

Graphics and Visualization

Human Computer Interaction

Information Science and Technology

Information Security and Assurance

Networks and Communications

Operating Systems and Middleware

Scientific Computing and Informatics

Software Engineering

Engineering (3 )

Seniority level Internship

Employment type Full-time

Job function Management and Manufacturing

Industries Government Administration

#J-18808-Ljbffr