Learning Enhanced Dynamic Target Tracking and Information Fusion

Abstract

The project is to develop theories and algorithms for learning enhanced target tracking, including data driven automatic tuning of tracking filters, learning based context-aware target tracking, feature learning aided data association, and sparse polynomial chaos expansion (PCE) learning for target tracking. The goal is to automatically tune the tracking filter by learning its optimal parameters, such as the process noise and measurement noise covariance matrices, from past target trajectory data. Machine learning techniques, such as the backpropagation through time, will be applied to find the best parameters for various nonlinear filters and a multi-model filer for target tracking.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 21, 2022
Source ID
FA95502210038XX0

Entities

People

  • Ruixin Niu

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • Virginia Commonwealth University

Tags

Fields of Study

  • Engineering

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Neural Network Machine Learning.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks