Machine Vision and Learning for eXplainable AI (XAI)

Organization
National Aeronautics and Space Administration (NASA)
Reference Code
0017-NPP-JUL23-LRC-AeroEng
Application Deadline
7/1/2023 6:00:00 PM Eastern Time Zone
Description

NASA Langley Research Center is seeking a postdoctoral researcher with expertise in computer vision to develop learning methods (including deep learning) using electro-optical sensors to explore novel applications of autonomous systems, with an emphasis on small Unmanned Aerial Systems (sUAS). The successful candidate should hold a doctoral degree in a field related to computer vision and machine learning (e.g., electrical engineering, computer science, applied mathematics) and will perform cutting-edge research as a team member in the project ATTRACTOR: Autonomy Teaming & TRAnsparency for Complex Trusted Operational Reliability. The objective of ATTRACTOR is to develop approaches to imbue Verification & Validation (V&V) into mission planning and execution via AI explainability (XAI) in training, decision-making, and object recognition; analyzable trajectories; natural interaction for human-machine teaming; and persistent modeling and simulation for engendering justifiable trust in autonomous systems. This requires enhanced neural network-based object classifiers that provide sub-object descriptions of the resulting classification in an effort to develop explainability. This position will involve the development of neural networks that rely on electro-optical and other sensor modalities for autonomous applications within the ATTRACTOR project goals, especially V&V and uncertainty quantification in object recognition, and should lead to publication(s) in top tier journals and conferences (e.g., CVPR, RSS, ICRA, AIAA, IEEE). Possible candidate tasks include: rapid training, tuning, and testing of neural networks, object tracking, scene classification, contextual learning, multi-modal learning, stereo vision, pose estimation, and collision avoidance. All developed methods and products must be accompanied by uncertainty quantification in support of approaches to V&V for autonomous systems. The candidate should include a list of publications related to deep learning (and preferably pre-prints for articles that may be under review). Demonstrated strong software skills applied to solving Machine Learning and/or Computer Vision problems is a pre-requisite. Experience developing on NVIDIA Jetson products, ROS, CAFFE, OpenCV, or participating in machine learning challenges are pluses.

 

Location:
Langley Research Center
Hampton, Virginia

Field of Science:Aeronautics, Aeronautical or Other Engineering

Advisors:
Bonnie Allen
danette.allen@nasa.gov
757-864-7364

 

 

 

Eligibility is currently open to:

  • U.S. Citizens;
  • U.S. Lawful Permanent Residents (LPR);
  • Foreign Nationals eligible for an Exchange Visitor J-1 visa status; and,
  • Applicants for LPR, asylees, or refugees in the U.S. at the time of application with 1) a valid EAD card and 2) I-485 or I-589 forms in pending status
Eligibility Requirements
  • Degree: Doctoral Degree.
NPP
ORISE ORAU Pathfinder
ORISE

Whether you are just starting your career or already at a senior level, ORAU offers internships, fellowships, research opportunities, and contract positions that can provide you with invaluable experience. Download the ORAU Pathfinder mobile app and find the right opportunity to propel you along your career path!