What do you want to learn today?

Underactuated Robotics 6.832 MIT

Online Free Online Course by  World Mentoring Academy
Online / Free Online Course

Details

Robots today move far too conservatively, using control systems that attempt to maintain full control authority at all times. Humans and animals move much more aggressively by routinely executing motions which involve a loss of instantaneous control authority. Controlling nonlinear systems without complete control authority requires methods that can reason about and exploit the natural dynamics of our machines. This course discusses nonlinear dynamics and control of underactuated mechanical systems, with an emphasis on machine learning methods. Topics include nonlinear dynamics of passive robots (walkers, swimmers, flyers), motion planning, partial feedback linearization, energy-shaping control, analytical optimal control, reinforcement learning/approximate optimal control, and the influence of mechanical design on control. Discussions include examples from biology and applications to legged locomotion, compliant manipulation, underwater robots, and flying machines.

Language: English

Units: 23

Lesson content
  • Lec 1 Introduction  
  • Lec 2 The Simple Pendulum  
  • Lec 3 Optimal control of the double integrator  
  • Lec 4 Optimal control of the double integrator (continued)  
  • Lec 5 Numerical optimal control (dynamic programming)  
  • Lec 6 Acrobot and cart-pole  
  • Lec 7 Swing-up control of acrobot and cart-pole systems  
  • Lec 8 Dynamic programming (DP) and policy search  
  • Lec 9 Trajectory optimization  
  • Lec 10 Trajectory stabilization and iterative linear quadratic regulator (iLQR)  
  • Lec 11 Walking  
  • Lec 12 Walking (continued)  
  • Lec 13 Running  
  • Lec 14 Feasible motion planning  
  • Lec 15 Global policies from local policies  
  • Lec 16 Introducing stochastic optimal control  
  • Lec 17 Stochastic Gradient Descent  
  • Lec 18 Stochastic Gradient Descent 2  
  • Lec 19 Temporal difference learning  
  • Lec 20 Temporal difference learning with function approximation  
  • Lec 21 Policy improvement  
  • Lec 22 Actor-Critic methods  
  • Lec 23 Case studies in computational underactuated control  
Reviews
Be the first to write a review about this event.
Write a Review
World Mentoring Academy is offering FREE Open Courseware. Setup a free user account & select courses with video lectures, Syllabus, Free textbooks when avail., assignments/homework, testing from MIT, Harvard, UC Berkeley, Stanford, U of Mich, Yale along with many of the World's finest University's (700+courses/24-48+ Lectures)
Sending Message
Please wait...
× × Speedycourse.com uses cookies to deliver our services. By continuing to use the site, you are agreeing to our use of cookies, Privacy Policy, and our Terms & Conditions.