MATLAB & Simulink for Cyber Physical Systems

1© 2017 The MathWorks, Inc.

MATLAB & Simulink for Cyber Physical Systems

Sumit Tandon – Senior Customer Success Manager, MathWorks

2

Agenda

▪ Intro to MATLAB and Simulink

– What, where, who, how, quick demos

▪ Intro to Automated Driving System Toolbox

– What, where, why, quick demos

▪ Resources

▪ Q & A

3

What is MATLAB?

▪ High-level language

▪ Interactive development

environment

▪ Used for:

– Numerical computation

– Data analysis and visualization

– Algorithm development and

programming

– Application development and

deployment

4

Data Analysis Workflow

Reporting and

Documentation

Outputs for Design

Deployment

ShareExplore & Discover

Data Analysis

& Modeling

Algorithm

Development

Application

Development

Files

Software

Hardware

Access

Code & Applications

Automate

5

Demo: Fuel Economy Analysis

▪ Goal:

– Study the relationships between fuel economy,

horsepower, and type of vehicle

▪ Approach:

– Import data from spreadsheet

– Interactively visualize

and explore trends

– Create a model

– Document results

6

Simulink

▪ Block-diagram environment

▪ Model, simulate and analyze multidomain systems

▪ Accurately design, implement, and test:– Control systems– Signal processing systems– Communications systems– And other dynamic systems

▪ Platform for Model-Based Design

The leading environment for modeling, simulating, and implementing dynamic and embedded systems

7

System Design Process

8

Demo: Wing Landing Gear System

9

What people do in industry:

Mars Rovers – NASA Jet Propulsion Lab

Artist's rendition of Mars rover.

Graphics courtesy of NASA/JPL/Cornell

MATLAB is used for:

Entry, Descent, and Landing System Design, Navigation, and Data Analysis…

10

What people do in industry:

Motion-Stereo Parking – BMW

Vehicle equipped with side-view camera. As the vehicle moves, the side-view camera acquires

images that are used to measure depth.

MATLAB is use for:

Motion-Stereo Systems, Object Detection, Computer Vision, Real-Time Control…

11

What people do in industry:

Prosthetic Arm – Applied Physics LabMATLAB is use for:

Simulation in Virtual Environment, Machine Learning, Real-Time Controller Design,

and Clinical Application…

12

Automated Driving System Toolbox

13

Some common questions from automated driving engineers

How can I

visualize vehicle

data?

How can I

detect objects in

images?

How can I

fuse multiple

detections?

vehicle

1011010101010100101001

0101010100100001010101

0010101001010100101010

0101010100101010101001

0101010010100010101010

0010100010100101010101

0100101010101010010101

0100101010010110000101

0100101010101010010010

1010011101010100101010

1

2F

14

Some common questions from automated driving engineers

How can I

visualize vehicle

data?

How can I

detect objects in

images?

How can I

fuse multiple

detections?

vehicle

1011010101010100101001

0101010100100001010101

0010101001010100101010

0101010100101010101001

0101010010100010101010

0010100010100101010101

0100101010101010010101

0100101010010110000101

0100101010101010010010

1010011101010100101010

1

2F

15

Visualize sensor data

16

Visualize differences in sensor detections

17

Learn more about visualizing vehicle databy exploring examples in the Automated Driving System Toolbox

▪ Transform between

vehicle and image

coordinates

▪ Plot lidar point cloud▪ Plot object detectors

in vehicle coordinates– Vision & radar detector

– Lane detectors

– Detector coverage areas

18

Some common questions from automated driving engineers

How can I

visualize vehicle

data?

How can I

detect objects in

images?

How can I

fuse multiple

detections?

vehicle

1011010101010100101001

0101010100100001010101

0010101001010100101010

0101010100101010101001

0101010010100010101010

0010100010100101010101

0100101010101010010101

0100101010010110000101

0100101010101010010010

1010011101010100101010

1

2F

19

Classification

Left

Bottom

Width

Height

How can I detect objects in images?

Object

detector

Classification

Left

Bottom

Width

Height

20

Train object detectors based on ground truth

ImagesObject

detector

Train

detector

Ground Truth

Classification

Left

Bottom

Width

Height

Classification

Left

Bottom

Width

Height

21

Train object detectors based on ground truth

Object

detector

Train

detector

Design object detectors with the Computer Vision System Toolbox

Machine

Learning

Aggregate Channel Feature trainACFObjectDetector

Cascade trainCascadeObjectDetector

Deep

Learning

R-CNN(Regions with Convolutional Neural Networks)

trainRCNNObjectDetector

Fast R-CNN trainFastRCNNObjectDetector

Faster R-CNN trainFasterRCNNObjectDetector

Images

Ground Truth

22

How can I create

ground truth?

Specify ground truth to train detector

Object

detector

Train

detector

Ground Truth

Images

23

Specify ground truth to train detector

Ground Truth

Object

detector

Train

detectorGround Truth

Labeler App

Video

24

Specify ground truth to evaluate detectors

Video Set 2Object

detector Evaluate

detections

Specify ground truth to train detectors

Ground truthGround Truth

Labeler App

Detections

Ground Truth

Object

detector

Train

detectorGround Truth

Labeler App

Video Set 1

25

Learn more about detecting objects in imagesby exploring examples in the Automated Driving System Toolbox

▪ Add automation algorithm

for lane tracking

▪ Extend connectivity of

Ground Truth Labeler App

▪ Label detections with

Ground Truth Labeler App

26

Learn more about detecting objects in imagesby exploring examples in the Automated Driving System Toolbox

▪ Explore pre-trained

pedestrian detector

▪ Explore lane detector

using coordinate

transforms for mono-

camera sensor model

▪ Train object detector

using deep learning and

machine learning

techniques

27

Some common questions from automated driving engineers

How can I

detect objects in

images?

How can I

fuse multiple

detections?

vehicle

1

2F

How can I

visualize vehicle

data?

1011010101010100101001

0101010100100001010101

0010101001010100101010

0101010100101010101001

0101010010100010101010

0010100010100101010101

0100101010101010010101

0100101010010110000101

0100101010101010010010

1010011101010100101010

28

Learn more about sensor fusionby exploring examples in the Automated Driving System Toolbox

▪ Design

multi-object tracker

based on logged

vehicle data

▪ Synthesize

driving scenario

to test

multi-object tracker

▪ Generate C/C++

code from algorithm

which includes a

multi-object tracker

29

Upcoming Webinar:

Introduction to Automated Driving System Toolbox

www.mathworks.com > Events > Upcoming Webinars

https://www.mathworks.com/company/events/webinars/upcoming/introduction-to-automated-driving-system-toolbox-

2355969.html

Date Time

25 Jan 2018 1:30 AM PST

25 Jan 2018 6:00 AM PST

25 Jan 2018 11:00 AM PST

30

Resources

31

Q & A