Accelerating ADAS with Open Source Introduction Mikko Hurskainen - - PowerPoint PPT Presentation

▶

Dec 28, 2022 418 likes •610 views

Accelerating ADAS with Open Source Introduction Mikko Hurskainen - Technical leadership positions in Nokia, Notava, Nomovok, Suunto, Link Motion Now Technologist in Link Motion. Looking on

SLIDE 1

Accelerating ADAS with Open Source

SLIDE 2

Introduction

Mikko Hurskainen - ミッコ

フルスカイネン

Technical leadership positions

in Nokia, Notava, Nomovok, Suunto, Link Motion

Now Technologist in Link
Motion. Looking on future

technologies.

Mission: making connected

cars safe & secure

SLIDE 3

Link Motion

2002 2004 2006 2008 2015 2013 2011 2009

Our HQ is in Finland We m a k e C O N N E C T E D C A R C O M P U T E R S w i t h H A R D WA R E - O S - A P P L I C AT I O N S

10 years & 200+

Automotive software projects delivered

Focus on SECURITY with cost efficient performance

SLIDE 4

What’s ADAS ?

Level 0 No Automation Level 1 Driver Assistance Level 2 Partial Automation Level 3 Conditional Automation Level 4 High Automation

Classification: SAE Applications:

Taxi service
Moving office space
“Ultimate IoT machine”

Applications:

Commuter
Efficient transport
Local concierge

Applications:

Automated parking
Highway cruiser
Platooning

Applications:

Lane assist
Adaptive Cruise control
Collision avoidance

Applications:

Reverse camera
Cruise control
Visualization

Applications:

Manually driven car

Level 5 Full Automation

SLIDE 5

Trends & Role of OSS

Level 0 No Automation Level 1 Driver Assistance Level 2 Partial Automation Level 3 Conditional Automation Level 4 High Automation Level 5 Full Automation

Platformisation of ADAS systems & cost-efficiency Enablement of functionality with OSS ADAS becoming mainstream Need for openness

SLIDE 6

Linux for ADAS – why ?

Few years ago instrument cluster running Linux was

thought not to be possible, now reality

ADAS becoming more complex – deeply embedded

designs do not offer structure & re-use that well structured platforms, like Linux, can offer.

Developers prefer desktop platforms.
Linux is evolving into direction that it can be used for safety

critical applications. Examples: NXP Linux, OSADL

Linux is POSIX compliant, possible to transfer results to
ther POSIX platforms. Also hybrid designs possible.

SLIDE 7

Autonomous Driving Biggest challenge: how to ensure car behaves correctly in ALL situations ?

Answer is Open Source: by making algorithms open those can be tested by large community

SLIDE 8

OSS Toolbox for ADAS

Algorithms New components Products Tools, testbench, drivers, platform, architecture, process, community OSS ADAS Platform OSS SW / communities Automotive Platforms Lower cost & faster time-to- market

SLIDE 9

ISO 26262

ASIL Levels

A B C D ASIL = Severity x (Exposure x Controllability)

Safety based view of the system

ASIL = Automotive Safety Integrity Level (ISO 26262)

SLIDE 10

Open Source vs ISO 26262 process

Process Compliancy

Rigorous reviews
Adherence to

good coding conventions

Well structured

software

External reviews
Known-to-work

designs

No controlled

process

No responsible

persons

Lack of testing

coverage

Lack of design

documentation

Need to also take account cyber security (eg SAE J3061)

SLIDE 11

OSS ASIL Maturization

Developers Community Maturization Product development Product Stable release by the development community ASIL pre-qualified release by maturization community Examples: RHEL, OSADL ASIL qualified product by company

SLIDE 12

Technologies BlueZ

Need more:

Sensing
Connectivity
Fusion
ADAS

components

Testbenches
Simulation
Auditing
Security

SLIDE 13

Evolutionary: OSS Rear Vision Camera

Drive train control Visualization Collision detection Braking

Visual guidance Sensory guidance Moving object recognition Collision detection Emergency brake

ASIL A B C SAE L0 L2 L1

https://github.com/openautocam

SLIDE 14

Revolutionary: ADAS Processor

ADAS processor

as brains of a car

Connected to

vision, sensors, connectivity, actuators

Linux as a base

instead of embedded system

LIDAR Radar Camera Cluster & Infotainment Connectivity Drivetrain ADAS processor

SLIDE 15

ASIL B+ ASIL A ASIL C / D ASIL A / B

Hybrid Designs

Cluster & Infotainment Drive Control

Microkernel Safety Critical SW Cluster / Infotainment

SLIDE 16

Less, but more Powerful computers

SLIDE 17

What’s needed ? Co Components

V2X, Sensing, Controller

Co Community

Co-development, information

Pr Process

ISO 26262 compliant

Ex Examples

Reverse camera, cruise control

SLIDE 18

Accelerating ADAS with Open Source

Introduction

フルスカイネン

in Nokia, Notava, Nomovok, Suunto, Link Motion

technologies.

cars safe & secure

Link Motion

10 years & 200+

What’s ADAS ?

Trends & Role of OSS

Linux for ADAS – why ?

thought not to be possible, now reality

designs do not offer structure & re-use that well structured platforms, like Linux, can offer.

critical applications. Examples: NXP Linux, OSADL

Autonomous Driving Biggest challenge: how to ensure car behaves correctly in ALL situations ?

Answer is Open Source: by making algorithms open those can be tested by large community

OSS Toolbox for ADAS

ISO 26262

ASIL Levels

Safety based view of the system

Open Source vs ISO 26262 process

Process Compliancy

OSS ASIL Maturization

Technologies BlueZ

Evolutionary: OSS Rear Vision Camera

Revolutionary: ADAS Processor

as brains of a car

vision, sensors, connectivity, actuators

instead of embedded system

Hybrid Designs

Microkernel Safety Critical SW Cluster / Infotainment

Less, but more Powerful computers

What’s needed ? Co Components

V2X, Sensing, Controller

Co Community

Co-development, information

Pr Process

ISO 26262 compliant

Ex Examples

Reverse camera, cruise control

Thank you ! ありがとうございます