LOCATION UPDATE to VIRTUAL

Gebhardt Distinguished Lecture

Using Machine Learning for Astrodynamics Applications

by

Hanspeter Schaub

Professor and Chair | University of Colorado Aerospace Engineering Sciences 

Thursday, September 26
3:30 - 4:30 p.m.
Microsoft Teams Need help?

Join the meeting now
Meeting ID: 215 621 345 416
Passcode: rgUiGw

Dial in by phone
+1 470-705-2566,,304575547# United States, Atlanta
Find a local number
Phone conference ID: 304 575 547#
 

About the Seminar: 
The use of machine learning and neural networks has become an enabling technology for spacecraft operations and mission development.  This talk discusses recent work in the Autonomous Vehicle Systems (AVS) lab at the Univeristy of Colorado to research means to schedule spacecraft tasking operations using a shielded neural network.  Both single and collaborative multi-satellite scenarios are discussed with Earth imaging mission scenarios.  The goal is to develop scalable scheduling solutions that can are efficient to compute on-board, robust to uncertainties in spacecraft and trajectory modeling, require minimal communication across satellites, and finally is robust to satellites being added or removed from operations.  In these studies the training is performed with the open-source physics-based Basilisk spacecraft simulation framework. Further, exciting results are presented on using machine learning and physics informed neural networks to model the complex gravity fields of celestial bodies.  The neural networks are storage efficient, accurate down to the surface of an asteroid without diverging (unlike spherical harmonics) and are very promising for on-orbit gravity field estimation applications.

About the Speaker: 
Dr. Schaub is a professor and chair of the University of Colorado aerospace engineering sciences department.  He holds the Schaden leadership chair.  He has over 28 years of research experience, of which 4 years are at Sandia National Laboratories. His research interests are in astrodynamics, relative motion dynamics, charged spacecraft motion as well as spacecraft autonomy.  This has led to about 208 journal and 326 conference publications, as well as a 4th edition textbook on analytical mechanics of space systems.  Dr. Schaub has been the ADCS lead in the CICERO mission, the ADCS algorithm lead on a Mars mission and supporting ADCS for a new asteroid mission. In 2023 he won the Hazel Barnes Price, the top award granted to faculty at the University of Colorado.  He has been awarded the H. Joseph Smead Faculty Fellowship, the Provost's Faculty Achievement Award, the faculty assembly award for excellence in teaching, as well as the Outstanding Faculty Advisor Award.  He is a fellow of AIAA and AAS, and has won the AIAA/ASEE Atwood Educator award, AIAA Mechanics and Control of Flight award, as well as the Collegiate Educator of the Year for the AIAA Rocky Mountain section.