PUBLICApril 17, 2018 1

This project has received funding from the ECSEL Joint Undertaking under grant agreement No 692455. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation programmeand Austria, Denmark, Germany, Finland, Czech Republic, Italy, Spain, Portugal, Poland, Ireland, Belgium, France, Netherlands, United Kingdom, Slovakia, Norway.

ENABLE-S3ECSEL EU PROJECT

Comprehensive modular verification and validation framework for automated systems -ENABLE-S3

Jürgen Holzinger, Andrea Leitner, AVL, April 17, 2018

http://www.enable-s3.eu/

PUBLICApril 17, 2018 2

How can we make sure that the system behaves correctly in every

situation?

PUBLICApril 17, 2018 33

PUBLICApril 17, 2018 6

Expected ADAS/AD Validation Efforts

~106

Level 4 Level 5Level 3Level 2Level 1

~108

Single

ADASPartial

Automation

Limited Self-

Driving

High /Full

Automation

Required Equivalent

Road-Kilometers for

Validation *

* Prof. Winner FZD,

Absicherung

automatisches Fahren,

6.FAS Tagung München

2013

On-road validation ~ x 106 km

HIL/VIL-Test bed validation ~ y 107 Eq.R.km

SIL/MIL - Virtual Validation

~ 108 Equivalent Road km

Virtual Validation will

be the dominant

validation method

PUBLICApril 17, 2018 7

Development & validation challenges

• Complex control systems with intensive interaction on-board and with the environment

• Uncountable potential scenarios which might occur in reality

• Test definitions (e.g. scenarios), test plans and conditioning, test reports differ from test environments and test tools

• No or not enough unit under tests available for real life testing

• Real life test can be too dangerous for humans

• Many of the necessary test situations do occur just by accident in real world - reproducibility?

• Realistic tests in pure simulation environments are often not possible

• Safety and security are tied together

• Certification of automated vehicles is unclear

PUBLICApril 17, 2018 8

Modular validation framework in ENABLE-S3

Validation scenarios

Full scenario coverage with all

variationsx*10^12 tests

Virtual world models

Reusable validation procedures

Intelligent accelerated validation

y*10^3 tests

Scenario variations

System variants

Environment

Routes

Personality types

Scenario parameters

Runtime validation

Input from other related projects

Real world data analysis

Results of safety &

security analysis

Scenario extraction

Hardware in the loop

System variants in the loop

Validation Methodology Validation Platform

Proving groundModel/Software in

the loop

… other parameters

PUBLICApril 17, 2018 14

Seamless development and test environments

11

MIL Cloud simulation

MIL / SIL Office Simulation

VIL - Vehicle in the loop

HIL - Hardware in the loop

Knowledge about country / region specifics for automated driving (traffic signs, traffic lights, traffic rules,

traffic density, driver behavior, …)

Seamless use of models

Seamless data management

Seamless data processing and reports

Seamless use of tools

Seamless use of test scenarios

MIL / SIL Cloud Simulation

THANK YOU

The research leading to these results has received funding from the H2020-ECSEL-2015-2-IA-two-stage for ENABLE-S3 – European Initiative to Enable Validation for Highly Automated Safe and Secure Systems Joint Undertaking under grant agreement

n° 692455 and from specific national programs and / or funding authorities.

Contact: andrea.leitner@avl.com, juergen.holzinger@avl.com