Mô tả

The world is changing! The technology is changing! The advent of automation in our societies is spreading faster than anyone could have anticipated. At the forefront of our technological progress is autonomy in systems. Self driving cars and other autonomous vehicles are likely to be part of our every day lives. How would you like to understand and be able design these autonomous vehicles? How would you like to understand Mathematics behind it?

Welcome! In this course, you will be exposed to one of the most POWERFUL techniques there are, that are able to guide and control systems precisely and reliably.

You are going to DESIGN, MASTER and APPLY:

  • mathematical models in the form of state-space systems and equations of motion

  • a PID controller to a simple magnetic train that needs to catch objects that randomly fall from the sky

  • a Model Predictive Controller (MPC) to an autonomous car in a simple lane changing maneuver on a straight road at a constant forward speed.

You will LEARN the fundamentals and the logic of Modelling, PID and MPC that will allow you to apply it to other systems you might encounter in the future.

You need 3 things when solving an Engineering problem: INTUITION, MATHEMATICS, CODING! You can't choose - you really need them all. After this course, you will master Modelling, PID and MPC in all these 3 ways. That's a promise!

I'm very excited to have you in my course and I can't wait to teach you what I know.

Let's get started!

Bạn sẽ học được gì

mathematical modelling of systems

reformulating models into state-space equations

applying a PID controller to systems (simple magnetic train catching objects)

applying Model Predictive Control (MPC) to systems (autonomous car: lane changing maneuvers)

Yêu cầu

  • Basic Calculus: Functions, Derivatives, Integrals
  • Vector-Matrix multiplication

Nội dung khoá học

8 sections

Intro to Control - PID controller

41 lectures
Course guide
03:58
Intro to Control - how to control systems with a controller 1
06:52
Intro to Control - how to control systems with a controller 2
06:34
Open VS Closed Loop System
06:36
Controlling the water tank in a Python simulation
02:52
Intro to a proportional controller
04:44
Modelling the water tank 1
01:45
Modelling the water tank 2
12:13
Numerical integration applied to the water tank model
09:52
Combining math with the control structure
07:07
Water tank simulation - proportional controller
02:28
Intro to a PID simulation
02:26
Follow up!
00:58
PID: Modelling the train with forces 1
06:27
PID: Modelling the train with forces 2
09:36
PID: Going from system input to system output using numerical integration
10:00
PID: Magnetic train simulation - proportional controller
01:59
PID: Proportional controller overshoot explanation 1
04:39
PID: Proportional controller overshoot explanation 2
06:28
PID: Proportional controller overshoot explanation 3
03:40
PID: Intro to Derivative Control
10:24
PID: Tuning the controller
06:11
PID: Proportional & Derivative controller & magnetic train simulation in Python
09:01
PID: Intro to Integral Control
04:35
PID: Python magnetic train simulation at an inclination angle
01:49
PID: Mathematical modelling of the train with the inclination angle 1
03:43
PID: Mathematical modelling of the train with the inclination angle 2
08:45
PID: Proportional, Derivative, Integral Control combined
16:03
PID: Magnetic train simulation (inclination angle & PID)
02:26
Test your PID fundamental understanding
1 question
Intro to (Linux & macOS Terminal) & (Windows Command Prompt)
12:54
Python installation instructions
00:51
Installing the Python environment and its libraries (Windows 10)
05:46
Installing the Python environment and its libraries (Linux Ubuntu)
04:43
Installing the Python environment and its libraries (macOS)
08:04
PID train code explanation 1
17:56
PID train code explanation 2
11:15
PID train code explanation 3
11:18
Short intro to Python animation tools
12:24
Quick code & animation explanation (water tanks)
28:29
Codes for the P & PID controllers (Python 3, Numpy & Matplotlib needed)
00:06

Fundamentals of forces, moments, mass moment of inertia and reference frames

11 lectures
PID VS Model Predictive Control (MPC) 1
02:42
Intro to MPC
01:10
Getting started with modelling a car
05:06
Fundamentals of forces and moments 1
12:10
Fundamentals of forces and moments 2
10:18
Setting stage for the car's lateral control 1
05:09
Setting stage for the car's lateral control 2
08:50
PID VS Model Predictive Control (MPC) 2
01:15
Setting stage for the car's lateral control 3
08:25
Setting stage for the car's lateral control 4
01:27
Moment calculation exercise
2 questions

Vehicle modelling for lateral control using equations of motion

19 lectures
Follow up!
00:58
The general control structure for the vehicle's lateral control
02:31
Car model VS simplified bicycle model 1
04:59
Car model VS simplified bicycle model 2
01:41
Car model VS simplified bicycle model 3
02:52
Ackerman Steering
01:52
Longitudinal & lateral velocities of the bicycle model 1
04:37
Longitudinal & lateral velocities of the bicycle model 2
03:32
Equations of motion in the lateral direction
03:15
Lateral & centripetal acceleration
05:28
Centripetal acceleration intuition & mathematical derivation 1
05:39
Centripetal acceleration intuition & mathematical derivation 2
08:58
Extra explanation on rotating frames
01:36
Centripetal acceleration intuition & mathematical derivation 3
20:51
Modelling the front wheel of the vehicle 1
03:41
Rewriting lateral forces in terms of front wheel angles
03:39
Modelling the front wheel of the vehicle 2
02:09
Modelling the front wheel of the vehicle 3
07:25
Modelling the front wheel of the vehicle 4
08:10

Vehicle's state-space & Linear Time Invariant (LTI) model for lateral control

14 lectures
From equations of motion to state-space equations 1
01:26
From equations of motion to state-space equations 2
07:25
From equations of motion to state-space equations 3
07:17
The meaning of states
08:36
Adding extra states to the system
08:28
Computing new states in the open loop system 1
10:29
Computing new states in the open loop system 2
08:57
Computing new states in the open loop system 3
04:53
Simplifying systems with small angle assumptions
07:29
Nonlinear VS Linear Time Invariant (LTI) models
10:47
Connecting LTI matrices with the vehicle's inputs
04:41
Getting LTI model using small angle approximation 1
03:59
Getting LTI model using small angle approximation 2
06:00
Getting LTI model using small angle approximation 3 + Recap
06:51

Model Predictive Control - Intuition - Rocket example

15 lectures
The objective of this section
00:24
Model Predictive Control - Intro
07:05
Model Predictive Control - Thrust levels
06:15
Model Predictive Control - Cost function
12:28
Model Predictive Control - Cost function having several variables 1
13:28
Model Predictive Control - Cost function having several variables 2
04:26
Model Predictive Control - Cost function weights
06:51
Model Predictive Control - Horizon period
10:30
Model Predictive Control - measured VS predicted outputs (Kalman Filter)
09:20
Recommended reading: Great article about Kalman Filters
00:10
Model Predictive Control - Quadratic VS other cost functions 1
05:26
Model Predictive Control - Quadratic VS other cost functions 2
05:08
Model Predictive Control - Quadratic VS other cost functions 3
06:57
Model Predictive Control - Quadratic VS other cost functions 4
06:35
MPC in a nutshell
02:02

Model Predictive Control - Mathematical Derivation - autonomous vehicle example

28 lectures
MPC 1 - continuous VS discrete state space equations
11:16
MPC 2 - deriving discrete state space equations
05:38
MPC 3 - discrete form (extra information)
00:10
MPC 4 - predicting future states 1
12:34
MPC 5 - predicting future states 2
18:04
MPC 6 - reformulating the cost function 1
11:34
MPC 7 - reformulating the cost function 2
07:42
MPC 8 - adding extra state to the system (augmentation) 1
07:51
MPC 9 - adding extra state to the system (augmentation) 2
09:24
MPC 10 - reason for why only the first input is chosen
10:04
MPC 11 -rewriting the error term in form of reference minus output
02:19
MPC 12 - expanding the cost function terms 1
08:21
MPC 13 - expanding the cost function terms 2
15:00
MPC 14 - expanding the cost function terms 3
04:54
MPC 15 - expanding the cost function terms 4
13:40
MPC 16 - reformulating the cost function from polynomial to matrix vector form 1
03:51
MPC 17 - reformulating the cost function from polynomial to matrix vector form 2
07:47
MPC 18 - predicting future states (assuming system augmentation)
11:04
MPC 19 - cost function reformulation 1
05:35
MPC 20 - cost function reformulation 2
07:43
MPC 21 - obtaining the gradient of the cost function to get the inputs 1
06:24
MPC 22 - obtaining the gradient of the cost function to get the inputs 2
09:02
Derivation of the gradient of a quadratic vector-matrix form 1
08:55
Derivation of the gradient of a quadratic vector-matrix form 2
04:34
Derivation of the gradient of a quadratic vector-matrix form 3
05:46
Derivation of the gradient of a quadratic vector-matrix form 4
08:52
Derivation of the gradient of a quadratic vector-matrix form 5
10:45
Why is H double bar (Hdb) matrix symmetric?
1 question

Model Predictive Control - Python Simulation - autonomous vehicle

23 lectures
Intro to (Linux & macOS Terminal) & (Windows Command Prompt)
12:54
Python Simulation Intro
01:02
Python installation instructions - Windows 10
05:46
Python installation instructions - Ubuntu
04:43
Python installation instructions - macOS
08:04
Intro to the simulator
09:17
Recap of the course
06:15
Code explanation 1 - general overview
09:49
Code explanation 2 - a function for storing the initial variables
14:01
Code explanation 3 - a function for generating trajectories
18:31
Code explanation 4 - a function for discrete state space matrices
06:01
Code explanation 5 - a function for generating the MPC cost function matrices
16:23
Code explanation 6 - a function for calculating new states
16:44
Code explanation 7 - the MAIN file 1
15:47
Code explanation 8 - the MAIN file 2
10:55
Code explanation 9 - the MAIN file 3
11:37
Code explanation 10 - the MAIN file 4
03:44
Basic intro to Python animations tools
19:00
Discussing the simulation results
10:57
Aligning yourself with a fixed reference line SMOOTHLY
1 question
PID VS Model Predictive Control (MPC) 3
09:22
The summary material
00:38
The Simulation codes - Model Predictive Control
01:08

Last Words

1 lectures
Well done! You did it! But don't stop here! Keep going forward!
00:49

Đánh giá của học viên

Chưa có đánh giá
Course Rating
5
0%
4
0%
3
0%
2
0%
1
0%

Bình luận khách hàng

Viết Bình Luận

Bạn đánh giá khoá học này thế nào?

image

Đăng ký get khoá học Udemy - Unica - Gitiho giá chỉ 50k!

Get khoá học giá rẻ ngay trước khi bị fix.