IEEE JRACS Seminar on An [almost] invisible controller for the unexpected unexpected!


An [almost] invisible controller for the unexpected unexpected!

by By Dr. Farbod Fahimi

Assistant Professor, Mechanical and Aerospace Engineering

University of Alabama Huntsville

Please register no later than Tuesday April 14, 2015, COB

  Date and Time




  • Date: 17 Apr 2015
  • Time: 11:30 AM to 01:00 PM
  • All times are (GMT-06:00) US/Central
  • Add_To_Calendar_icon Add Event to Calendar
  • 1004 Explorer Blvd
  • Huntsville, Alabama
  • United States 35806
  • Building: Dynetics, Inc., Solutions Complex
  • Room Number: Main Conference Room
  • Click here for Map

  • Leandro G. Barajas, Ph.D., PMP, IEEE SM 
    Chapter Chair, IEEE Joint Robotics and Automation - Controls Systems (JRACS) Society 
    IEEE Huntsville Section, Huntsville, AL
    +1 (248)705-8192

  • Co-sponsored by Dynetics, Inc.
  • Starts 29 March 2015 04:20 PM
  • Ends 15 April 2015 08:15 AM
  • All times are (GMT-06:00) US/Central
  • No Admission Charge
  • Menu: Non-US Citizen, US Citizen/Permanent Resident


Dr. Farbod Fahimi Dr. Farbod Fahimi of Mechanical and Aerospace Engineering, University of Alabama Huntsville (UAH)


An [almost] invisible controller for the unexpected unexpected!

Model-Free Online Reinforcement Learning (MFORL) controllers learn how to control a system only by interacting with it in real-time, the same way humans learn how to control machines. MFORL controllers have great potentials when it comes to control design for complex nonlinear systems, where the model-based methods fall short due to impracticality of formulating a mathematical model for the system. With availability of the MFORL control, unmodeled complex systems can be automated. Even if a model could be formulated, MFORL control derivation is extremely more economical for two major reasons. First, the need for lengthy process of system modeling, identification, and verification is eliminated. Second, once an MFORL controller is found for a dynamic system, it can be easily used for any system whose governing differential equation resembles that of the original dynamic system. In addition, MFORL controllers can relearn a completely new control law rapidly if the system dynamics suddenly changes due to an "unexpected" component break down. So, MFORL controllers can successfully deal with unexpected unexpected (situations that cannot be foreseen at the design stage) whereas robust/adaptive controllers can only deal with expected unexpected at best (known ranges of change in system parameters). In this talk, the theory behind MFORL controllers is discussed, and some sample benchmark applications are presented.


Dr. Fahimi has over 10 years of research experience in dynamic modeling, system identification, linear and nonlinear controls, with applications to robotic system and autonomous vehicles. He received a PhD degree in Mechanical Engineering on dynamic modeling of flexible multi-body systems in 1999. He has graduated 8 Masters students, and has offered several senior design projects. He is currently supervising several full time and part time graduate students. He has taught several undergraduate and graduate level courses such as Dynamics, Vibrations, System Dynamics, Elasticity, Finite Element Method, Introduction to Robotics, and Advanced Robotics. He has authored a graduate level text book titles: Autonomous Robots; Modeling, Path Planning, and Control.

Research Expertise

  • Linear and Nonlinear Controls
  • System Identification
  • Applied Control
  • Dynamics and Robotics
  • Autonomous Vehicles (Ground, Marine, Aerial)


Address:Technology Hall N264, , Huntsville, Alabama, United States, 35899

Dr. Farbod Fahimi of Mechanical and Aerospace Engineering, University of Alabama Huntsville (UAH)


An [almost] invisible controller for the unexpected unexpected!



Address:Huntsville, Alabama, United States


11:30am - 11:45am Meet & Greet

11:30am - 11:45am Lunch

11:45am - 12:00pm Announcements & Speaker Introduction

12:00pm - 12:45pm Talk

12:45pm - 1:00pm Q&A & Adjourn