Planning and control
This lecture covers the concept of model predictive control and is a part of the Deep Learning Course at CDS, a course that covered the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. Prerequisites for this module include: Models 1-6 of this course and Introduction to Data Science or a Graduate Level Machine Learning.
Chapters:
00:00 – Background on the class creation
00:58 – Take a quiz!
01:33 – Planning and control
02:21 – Action plan (table of contents)
09:06 – State transition equations
31:22 – A few numerical examples (I), no action
34:44 – A few numerical examples (II), negative acceleration
36:24 – A few numerical examples (II), positive and negative steering
38:31 – PyTorch implementation of physical examples
46:26 – Kelley-Bryson algorithm (RNN recap and control)
56:29 – Control with final cost
59:13 – Control with cumulative cost
1:00:42 – PyTorch implementation of optimal control examples