Matlab and development of autonomous systems

1. 1© 2015 The MathWorks, Inc.
How to build an
autonomous anything
Chris Hayhurst

2. 2

3. 3

4. 4

5. 5

6. 6

7. 7

8. 8
Autonomous Technology
Provides the ability of a system to act
independently of direct human control
under unrehearsed conditions

9. 9

10. 10
Capabilities of an Autonomous System
Sense

11. 11
Capabilities of an Autonomous System
Sense
Perceive

12. 12
Capabilities of an Autonomous System
Learning Algorithms
Optimization
Sense
Perceive
Decide
& Plan

13. 13
Capabilities of an Autonomous System
Control Algorithms
Sense
Perceive
Decide
& Plan
Act

14. 14
Autonomous Technology Transfers Responsibility to Computers
Human
Computer
Responsibility
Degree of Autonomy

15. 15
Bazille’s Studio
Bazille 1870
Shuffleton’s Barbershop
Rockwell 1950

16. 16
Autonomous Artistic Style Classification
Rutgers University
Image
Feature
Extraction
Visual Features
Genre
Classifier
(SVM)
Artist
Classifier
(SVM)
Style
Classifier
(SVM)
Style:
Regionalism
Genre:
Interior
Artist:
Rockwell
Machine
Learning
Classification
Sense
Perceive
Decide
& Plan
Act

17. 17
Where to add autonomy with perception?
 Analyze more data
 Reduce bias
 Reduce variability
 Save time
 Improve performance
Determine
Loudspeaker
Quality
Virtual Semiconductor
Manufacturing Calibration

18. 18

19. 19

20. 20
Autonomous Service for Predictive Maintenance
Which sensor values should they use?
Decide
& Plan
Act
Perceive
Sense
Pressure
Other
variables
Vibration Timing
Temperature

21. 21
Normal Operation Maintenance NeededMonitor Closely
Autonomous Service for Predictive Maintenance
Sense
Act
Perceive
Decide
& Plan

22. 22
What are the best predictors?
 Data
 Models
Name of Presenter

23. 23
Autonomous Glucose Level Management

24. 24
Autonomous Glucose Level Management
Bigfoot Biomedical
Continuous
Glucose Monitor
Target
Glucose
Level
+ -
Insulin Pump
+ +
Mobile App
Person
Perceive
Decide
& Plan
Act
Sense
Virtual Clinic
MATLAB, Toolboxes

25. 25
Virtual Clinic
Generating data through simulation

26. 26
Virtual Clinic
Scaling computations to simulate 50 million patients a day

27. 27
Where will you get your data?
 Simulation
 Public repositories
 In the lab
 In the field
 Internet of Things (IoT)

28. 28
CNH Develops Intelligent Filling System for Forage Harvesters

29. 29

30. 30
Autonomous Trailer Filling
Control Algorithms
Perceive
Act
Sense
Decide
& Plan

31. 31
Autonomous Trailer Filling
Control Algorithms
Act
Decide
& Plan
Perceive
Sense

32. 32

33. 33
Autonomous Trailer Filling
Control Algorithms
Monitoring
CANEmbedded Coder
3D Camera
Actuators
ECU
• User Input
• Visualization
• Computer
Vision
• Controls
Embedded Platform
MPC5121e
Act
Perceive
Decide
& Plan
Sense

34. 34
How will you put it into production?
 Embedded Systems
 IT Systems
 Desktop Apps

35. 35

36. 36

37. 37

38. 38
How to build an autonomous anything
Focus on Perception
• Data-driven
• Model-driven
• Reduce to actionable data
• Take advantage of Big Data
• Use simulation to supplement available data
• Address the architecture
• Leverage Model-Based Design for embedded
• Automate integration with enterprise IT systems
• Look for autonomy in creative places
• Do more than manually possible
Use the Best Predictors
Get the Right Data
Flow to Production

39. 39
What is your
autonomous anything?