How to build an autonomous anything

Similar documents
How to build an autonomous anything

Transformation to Artificial Intelligence with MATLAB Roy Lurie, PhD Vice President of Engineering MATLAB Products

Software Computer Vision - Driver Assistance

Sensing, Computing, Communication

Symposium: Urban Energy innovation

Das virtuelle Walzwerk Weg zum Cyber-Physical System

VSI Labs The Build Up of Automated Driving

23270: AUGMENTED REALITY FOR NAVIGATION AND INFORMATIONAL ADAS. Sergii Bykov Technical Lead Machine Learning 12 Oct 2017

Getting to Smart Paul Barnard Design Automation

Jim Mangione June, 2017

Robotics in Oil and Gas. Matt Ondler President / CEO

SHAPING THE FUTURE OF IOT: PLATFORMS FOR CO-CREATION, RAPID PROTOTYPING AND SUCCESSFUL INDUSTRIALIZATION

Simulationbased Development of ADAS and Automated Driving with the Help of Machine Learning

Energy autonomous wireless sensors: InterSync Project. FIMA Autumn Conference 2011, Nov 23 rd, 2011, Tampere Vesa Pentikäinen VTT

IT and Systems Science Transformational Impact on Technology, Society, Work, Life, Education, Training

Outline. Agents and environments Rationality PEAS (Performance measure, Environment, Actuators, Sensors) Environment types Agent types

Pramod Kumar Naik Senior Application Engineer MathWorks Products

Distributed Robotics From Science to Systems

The Key to the Internet-of-Things: Conquering Complexity One Step at a Time

INDUSTRY 4.0. Modern massive Data Analysis for Industry 4.0 Industry 4.0 at VŠB-TUO

Modeling and Simulation Made Easy with Simulink Carlos Osorio Principal Application Engineer MathWorks Natick, MA

Vision & Industry 4.0: Towards smarter sensors. Dr. Amina Chebira Vision Embedded Systems, CSEM SA October 4 th, 2016

Horizon 2020 ICT Robotics Work Programme (draft - Publication: 20 October 2015)

Metrology in Industry 4.0. Metromeet

John Magee Rob Harwood (RH) John Magee (JM)

Sensing, Computing, Communication

Sensing, Computing, Communication

A Review of Related Work on Machine Learning in Semiconductor Manufacturing and Assembly Lines

Agent. Pengju Ren. Institute of Artificial Intelligence and Robotics

Making Representations: From Sensation to Perception

Fundamentals of Industrial Control

Control Design Made Easy By Ryan Gordon

Automotive Applications ofartificial Intelligence

Last Time: Acting Humanly: The Full Turing Test

5G R&D at Huawei: An Insider Look

Using FMI/ SSP for Development of Autonomous Driving

CALL FOR PAPERS. embedded world Conference. -Embedded Intelligence- embedded world Conference Nürnberg, Germany

Digital Transformation. A Game Changer. How Does the Digital Transformation Affect Informatics as a Scientific Discipline?

Asia Conference Singapore

THE ARDUINO ENGINEERING KIT INFORMATION GUIDE ARDUINO.CC/EDUCATION

Real-Time Testing Made Easy with Simulink Real-Time

Framework Programme 7

Professor in Charge Topic Short description Project available for students Student needs good knowledge in the following fields

interactive IP: Perception platform and modules

INTERNET OF THINGS (IoT) PRESENTED BY: Wafaa Rizin Ameer

AI Application Processing Requirements

Exploring the value of emerging technology in the lean enterprise

Industry 4.0: the new challenge for the Italian textile machinery industry

A simple embedded stereoscopic vision system for an autonomous rover

Digitalization in Aker BP

Introduction to Computational Intelligence in Healthcare

Faurecia : Smart Life on board An innovative company

Artificial Intelligence for Social Impact. February 8, 2018 Dr. Cara LaPointe Senior Fellow Georgetown University

ADAS Development using Advanced Real-Time All-in-the-Loop Simulators. Roberto De Vecchi VI-grade Enrico Busto - AddFor

Joint Open Lab and PHD proposal

The 3xD Simulator for Intelligent Vehicles Professor Paul Jennings. 20 th October 2016

Available theses (October 2011) MERLIN Group

The future of work. Artificial Intelligence series

Teleoperation. History and applications

Embracing Complexity. Gavin Walker Development Manager

CISC 1600 Lecture 3.4 Agent-based programming

If Bridges Could Talk

Marine Robotics. Alfredo Martins. Unmanned Autonomous Vehicles in Air Land and Sea. Politecnico Milano June 2016

Building Spatial Experiences in the Automotive Industry

Trends that are shaping the future of process automation

HUMAN-ROBOT COLLABORATION TNO, THE NETHERLANDS. 6 th SAF RA Symposium Sustainable Safety 2030 June 14, 2018 Mr. Johan van Middelaar

David Howarth. Business Development Manager Americas

HeroX - Untethered VR Training in Sync'ed Physical Spaces

Railway Maintenance Trends in Technology and management. Uday Kumar Luleå University of Technology LULEÅ-SWEDEN

DENSO www. densocorp-na.com

Issues in Information Systems Volume 16, Issue IV, pp , 2015

Regionaal Platform. 19 oktober 2016

Industry 4.0 The Future of Innovation

Digitalisation as day-to-day-business

EU regulatory system for robots

Intelligent Buildings Remote Monitoring Using PI System at the VSB - Technical University of Ostrava Jan Vanus

Dr. Charles Watt. Educational Advancement & Innovation

Sparking a New Economy. Canada s Advanced Manufacturing Supercluster

ARMY RDT&E BUDGET ITEM JUSTIFICATION (R2 Exhibit)

UNIT 2 TOPICS IN COMPUTER SCIENCE. Emerging Technologies and Society

CATALOGUE. HBRP Publication

MLAB - Matlab: Fundamentals And/Or Applications

Introduction to Systems Engineering

Jane Li. Assistant Professor Mechanical Engineering Department, Robotic Engineering Program Worcester Polytechnic Institute

Presentation Title By Author

Adopting Standards For a Changing Health Environment

Web of Things for Connected Vehicles. Soumya Kanti Datta Communication Systems Department

Eleonora Escalante, MBA - MEng Strategic Corporate Advisory Services Creating Corporate Integral Value (CIV)

CS277 - Experimental Haptics Lecture 2. Haptic Rendering

Model-Based Design for Sensor Systems

Robotic Technology for Port and Maritime Automation

Ant? Bird? Dog? Human -SURE

MATLAB - Matlab. Fundamentals And/Or Applications

3D Virtual Training Systems Architecture

Smart Government The Potential of Intelligent Networking in Government and Public Administration

Glossary of terms. Short explanation

Technology trends in the digitalization era. ANSYS Innovation Conference Bologna, Italy June 13, 2018 Michele Frascaroli Technical Director, CRIT Srl

Introduction. digitalsupercluster.ca

Predictive Diagnostics for Pump Seals: Field Trial Learnings. Matthew Miller, John Crane

Advances and Perspectives in Health Information Standards

Transcription:

How to build an autonomous anything Jim Tung jim@mathworks.com 2015 The MathWorks, Inc. 1

2

3

4

5

6

7

Autonomous Technology 8

Autonomy Having the power for self-governance 9

Autonomous Technology Provides the ability of a system to act independently of direct human control under unrehearsed conditions 10

11

Capabilities of an Autonomous System Sense 12

Capabilities of an Autonomous System Sense Perceive 13

Capabilities of an Autonomous System Sense Perceive Decide & Plan Learning Algorithms Optimization 14

Capabilities of an Autonomous System Sense Perceive Decide & Plan Act Control Algorithms 15

Responsibility Autonomous Technology Transfers Responsibility to Computers Computer Human Degree of Autonomy 16

Bazille s Studio Frederic Bazille (Paris, 1870) Shuffleton s Barbershop Norman Rockwell (Vermont, 1950) 17

Bazille s Studio Frederic Bazille (Paris, 1870) Shuffleton s Barbershop Norman Rockwell (Vermont, 1950) 18

Autonomous Artistic Style Classification Rutgers University Sense Machine Learning Classification Style Classifier (SVM) Style: Regionalism Perceive Decide & Plan Image Feature Extraction Visual Features Genre Classifier (SVM) Genre: Interior Act Artist Classifier (SVM) Artist: Rockwell 19

Where to add autonomy with perception? Analyze more data Reduce bias Reduce variability Save time Improve performance 20

Where to add autonomy with perception? Analyze more data Reduce bias Reduce variability Save time Improve performance 21

Cost of rig: >$1M Repair cost: $100,000 Cost of valve: $200 23

24

25

26

Autonomous Service for Predictive Maintenance Sense Which sensor values should they use? Vibration Timing Perceive Pressure Temperature Decide & Plan Act Other variables 27

Autonomous Service for Predictive Maintenance Sense Perceive Decide & Plan Act Normal Operation Monitor Closely Maintenance Needed 28

What are the best predictors? Data-driven Model-driven Jet Engine Monitoring 29

Autonomous Glucose Level Management 31

Autonomous Glucose Level Management Bigfoot Biomedical Sense + - Perceive Decide & Plan Target Glucose Level Insulin Pump Person Act Continuous Glucose Monitor 32

Autonomous Glucose Level Management Bigfoot Biomedical Sense + - Perceive Decide & Plan Target Glucose Level Insulin Pump Person + + Act Mobile App Continuous Glucose Monitor 33

Autonomous Glucose Level Management Bigfoot Biomedical Sense Simulink, Stateflow, Polyspace + - Perceive Decide & Plan Target Glucose Level Insulin Pump Person + + Act Mobile App Continuous Glucose Monitor 34

Autonomous Glucose Level Management Bigfoot Biomedical Sense + - Perceive Decide & Plan Target Glucose Level Insulin Pump Person + + Act Mobile App Continuous Glucose Monitor 35

Autonomous Glucose Level Management Bigfoot Biomedical Sense Virtual Clinic MATLAB, Toolboxes 2017 2018 + - Perceive Decide & Plan Target Glucose Level Insulin Pump Person + + Act Mobile App Continuous Glucose Monitor 36

Virtual Clinic Generating data through simulation 37

Virtual Clinic Scaling computations to simulate 50 million patients a day 38

39

Where will you get your data? Simulation Public repositories In the lab In the field Internet of Things (IoT) 40

CNH Develops Intelligent Filling System for Forage Harvesters 41

42

Autonomous Trailer Filling Sense Perceive Decide & Plan Act Control Algorithms 43

Autonomous Trailer Filling Sense Perceive Decide & Plan Act Control Algorithms 44

45

Autonomous Trailer Filling Sense 3D Cameras Perceive Actuators Decide & Plan CAN Act ECU Computer vision and controls algorithms 46

Autonomous Trailer Filling Sense 3D Cameras Vehicle Display Controller Driver Input Visualization Perceive Decide & Plan CAN Actuators Act Computer vision and controls algorithms ECU 47

Autonomous Trailer Filling Sense Perceive Decide & Plan 3D Cameras Embedded Coder Vehicle Display Controller CAN Driver Input Visualization Computer Vision Controls Actuators Act Computer vision and controls algorithms ECU 48

Autonomous Trailer Filling Sense Perceive Decide & Plan 3D Cameras Vehicle Display Controller CAN Driver Input Visualization Computer Vision Controls Actuators Act Monitoring ECU 49

How will you put it into production? System Architecture Embedded systems Enterprise systems HMIs 50

51

52

53

How to build an autonomous anything Focus on Perception Use the Best Predictors Get the Right Data Go to Production Look for autonomy in creative places Do more than manually possible 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 54

How to build an autonomous anything Sense Perceive Decide & Plan Act 55

What is your autonomous anything? 56

57