Driving with AI: The Future of Mobility and Transportation Harsha - - PowerPoint PPT Presentation

driving with ai the future of mobility and transportation
SMART_READER_LITE
LIVE PREVIEW

Driving with AI: The Future of Mobility and Transportation Harsha - - PowerPoint PPT Presentation

Driving with AI: The Future of Mobility and Transportation Harsha Badarinarayan , Ph.D. Director and Laboratory Manager Global Center for Social Innovation North America, Hitachi America, Ltd. Overview Hitachi Leaders in Digital


slide-1
SLIDE 1

Driving with AI: The Future of Mobility and Transportation

Harsha Badarinarayan, Ph.D.

Director and Laboratory Manager Global Center for Social Innovation – North America,

Hitachi America, Ltd.

slide-2
SLIDE 2

Overview § Hitachi – Leaders in Digital Innovation § Mobility Use Cases i. Connected Powertrain ii. Ride Comfort Control using AI

  • iii. Predictive Maintenance
  • iv. Vehicle Occupant Health and Safety

Analytics § Inspiring the Next…..

slide-3
SLIDE 3

Hitachi – a digital innovation company

As a global technology leader, digital innovation is at the heart of everything we do.

Hitachi is investing $2.8B over 3 years to build a global leadership in IoT

* As of March 31, 2016

Award winning

culture

$3.5B

annual R&D*

$2.8B

3-year IoT R&D*

$88.8B

consolidated revenue*

$5.4B

IoT revenue* 15,000+ global customers

1,400+

strategic alliances Industrial and IT Leader

#79

  • n Fortune 500

Heritage of innovation

119,000

global patents

11,000

IoT patents Thomson Reuters

Top 100

Global Innovators

15,000

global partners

110+ years

technology and product development

1,000+

subsidiaries

335,000

employees

slide-4
SLIDE 4

The Era of Digital Disruption

Presenting existential threats and transformative opportunities for Fortune 500

Creating new markets; breaking down industry boundaries; and disrupting value chains

IoT 3D Printing Cloud AI Blockchain Big Video Automation

Technical Innovation

Peer-to-peer As-a-Service Automated Shared Connected

Social Innovation

Global Mega Trends

Globalisation Aging Populations Mass Migration Urbanisation Sustainability Terrorism Cyber Crime

Rail Manufacturing and Industry Public Service Energy Automotive Financial Service

Society 5.0

slide-5
SLIDE 5

Major Trends Disrupting the Automotive Industry

Combustion engine advancements Fuel Cells Start-up OEMs New Retail – Direct to Customer Light-weighting Shared Mobility Low cost brands Electrification Intelligent and Automated Vehicles Alternative Fuels Shift to Asia Connectivity & AI Non-traditional entrants Digital Experience

Source: Roland Berger

Big Data/ Analytics

Short-term trends Mid-term trends Long-term trends

slide-6
SLIDE 6

Future of Mobility…

Source: Roland Berger

slide-7
SLIDE 7

i. Connected Powertrain

slide-8
SLIDE 8

Fuel Economy Improvement with Connected Powertrain

Synergy to create eco-friendly propulsion systems

AD/ADAS Technologies Powertrain Control

×

AD/ADAS Features

Autonomous Driving for highway Lane keep system (lane recognition) ACC/AEB (Preceding vehicle recognition)

AD: Autonomous Driving ADAS: Advanced Driver Assistance System ACC: Adaptive Cruise Control AEB: Autonomous Emergency Braking Powertrain Control Opportunity for Start & Stop

E.g. Start & Stop control

Sailing stop Coasting stop

Idling stop

Vehicle Speed VSP

Driving Cycle (Acceleration suppression) HEV control (Regeneration)

Realize eco-friendly propulsion system by creating synergy between powertrain technology AD/ADAS and Connectivity for safety and comfort

slide-9
SLIDE 9

Connected Powertrain Architecture

HD LDM + V2X + Traffic Estimating accurate position via HD Map Information Weather- robust Vision System and Sensor Fusion Architecture RADAR/LiDAR

Car as a Sensor Connected Controls

Engine Map Real World Driving

Connected Vehicle

Road Grade, Weather, Traffic Drive Cycle

slide-10
SLIDE 10

AI Neural Network Can Reduce Average Fuel Consumption by 10%

Input layer Extract Features + Live Traffic

Training Neural Net Drive Cycle Estimation

Feature Extraction

  • Trip Time
  • Avg. Speed
  • Congestion Level
  • Road Type

Output layer

min (𝐺 𝑦, 𝑣 = 𝑛𝑗𝑜 . 𝑔𝑣𝑓𝑚_𝑠𝑏𝑢𝑓(𝑄

789, ω789|𝑄<=>?7=_=7@)

  • Predicted Drive Cycle

Vehicle Speed (mph)

Optimize Supervisory Control

Time (Secs)

Outcomes

§ Emission reduction § CAFÉ Improvements § Gas Savings § Comfort Ride

slide-11
SLIDE 11

Traffic & Connected Powertrain Co-simulation

§ Perform large scale traffic simulation using Real World Driving data § Evaluate benefit of ‘look-ahead’ controls & calibration for powertrain

Multiple co-simulation platform

Speed (mph)

Free Flow Traffic Speed

Throttle Control Brake Control Predicted Traffic Speed (mph)

3D vehicle dynamics

§ Traffic Flow § Vehicle Velocity

Large-scale traffic on Michigan road network

slide-12
SLIDE 12
  • ii. Ride Comfort Control using AI
slide-13
SLIDE 13

Value of an Autonomous car : Safety + Experience + Comfort

Safety Drive Experience Ride Comfort

Ex: Driver Assist Technology Ex: Configurable seats Ex: Semi-Active Dampers

Our AI based approach for Enhanced Ride Comfort Sensing Technology Fusion coupled with AI

Maps/Traffic Road Topology Road Profile Dynamic Localization AI – Machine Learning Safe, Smooth & Comfortable Ride

slide-14
SLIDE 14

Ride Comfort Solution:

Pitching – Acceleration/Deceleration Yaw / Roll – Turns & Curved Roads

Image: DSPORT Magazine

slide-15
SLIDE 15

Development of AI Platform

slide-16
SLIDE 16

System Architecture – Turn Prediction

Output Approach Input

GPS OBD Accel/ Gyro Feature Extraction Identify Driver Model Training/Test Drive Mode Calculate G-Force Speed Gyro_Z Predict Turn GPS Heading Polish Features Trained Model

slide-17
SLIDE 17

Road Tests – Drive Model & Turn Prediction

slide-18
SLIDE 18
  • iii. Predictive Maintenance
slide-19
SLIDE 19

Need for Predictive Maintenance – Background

Consumer/Commercial Vehicles Fleet Vehicles Warranty Costs as a Percentage of Annual Sales

Proactive and predictive maintenance approach are needed to minimize warranty and service related expense for next generation mobility: ‒ Reactive maintenance approach no longer relevant/applicable in this landscape ‒ Need Proactive and Predictive maintenance ‒ Use-case of a shock absorber to emphasize the predictive maintenance benefits for reducing warranty costs

Source: ELEMENT Source: WarrantyWeek

slide-20
SLIDE 20

Predictive Maintenance Architecture

IoT Architecture with Edge Analytics to Collect, Process, Analyze & enable Decision Making Capability through Cloud Infrastructure

slide-21
SLIDE 21

Results Visualization – Miles to Failure Prediction

Potential Reduction in Component Life

slide-22
SLIDE 22
  • iv. Vehicle Occupant Health and Safety Analytics
slide-23
SLIDE 23

Overview – Vehicle Occupant Health and Safety

Background and Value

v Market projections $7.74B by 2020 v Effective distraction monitoring v Remote health monitoring v Estimate driver fatigue level

Requirements and Challenges Our Key Differentiation

ü Breath Alcohol Detection ü Facial state recognition ü Fusion of physiological sensors and vision system ü On-going field trials in the US

Before Driving – Breath Alcohol Detection During Driving – Monitor Psychophysiological State

slide-24
SLIDE 24

Breath Alcohol Detection System

Drunk Driving Accounts for 30% of Total Deaths in USA ü Multi-gas Sensor ü 3X More Accurate ü Facial Recognition ü Abuse Prevention Features – Anywhere, Anytime, and Easy Measurement . Humidity and Multi-gas Sensor distinguish human breathe from artificial gas

6月1日 8: 30 2. 45 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月2日 8: 31 2. 14 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月3日 8: 32 1. 58 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月4日 8: 33 2. 16 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月5日 8: 34 2. 45 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月6日 8: 35 2. 14 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月7日 8: 36 1. 58 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月8日 8: 37 2. 16 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月9日 8: 38 2. 45 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月10日 8: 39 2. 14 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月11日 8: 40 1. 58 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月12日 8: 41 2. 16 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月13日 8: 42 2. 16 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○ 6月14日 8: 43 2. 16 ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ○

Data log sheet

A Driver Management System Could Improve Business Efficiency Especially for Transport Industry Utilizing Breathe Alcohol Detection System

slide-25
SLIDE 25

Occupant Psychophysiological State Monitoring

In-vehicle sensor fusion Cloud Platform Real-Time Data Usage by Service Provider Current System Architecture

slide-26
SLIDE 26

Field Tests – Occupant Psychophysiological State Monitoring

Camera

Pulse Sensor Breathing Sensor

Experimental Setup Real-Time Pulse & Respiration Monitoring Real-Time Driver’s Facial State Monitoring System Sample Experimental Results of Subjects Heart and Respiration Rate

slide-27
SLIDE 27

Inspiring the Next…

slide-28
SLIDE 28

Innovation and IoT are in our DNA

OT

107 YEARS

INDUSTRIAL CONSUMER BUSINESS CITY

IT

57 YEARS

APPLICATIONS ANALYTICS INFRASTRUCTURE BIG DATA CLOUD

IoT

Is in our DNA

slide-29
SLIDE 29

Hitachi’s Unique Value Proposition

OT asset IT asset

Human data Business data

Edge AI/Analytics Studio Core Foundry

Leap-frogging competitors through collaborative co-creation Embed Hitachi’s IT x OT Experience OT x Market Disruption

Machine data

×

Connectivity Security

slide-30
SLIDE 30

Inspiring the Digital Transformation

Unparalleled OT + IT + IoT Expertise Social Innovation Flexible Business Models

Accelerates time to value Solutions that benefit business and society Focused on delivering value

slide-31
SLIDE 31

Thank You!

slide-32
SLIDE 32

Visit us at the ‘Smart Transportation’ Exhibit…

slide-33
SLIDE 33

Questions….

slide-34
SLIDE 34