Conference Program


The road to safe autonomous driving – a common goal

New approaches for autonomous vehicle certification: a European perspective

Maria-Cristina Galassi
Scientific project officer
European Commission
Italy
Automated driving technology is developing at an unprecedented fast pace and a quick response is needed from regulators in order not to obstacle innovation and at the same time ensure the access to the market of safe automated vehicle (AVs). The introduction of innovative certification approaches is required to assess and verify AVs safety, complementing the conventional physical testing in order to ensure the vehicle safe performance in real life. The presentation will introduce the proposed EU method for automated driving , including audit of the manufacturer design/development process, verification through track and on-road testing, and operational feedback from real-life experience after market introduction.

HEADSTART project: Harmonized European Solutions for the Testing of Automated Road Transport

Álvaro Arrúe
Project manager connected and automated driving
Applus IDIADA
Spain
HEADSTART is an H2020 EU-funded project that aims to define testing and validation procedures of connected and automated driving functions including key technologies such as communications, cybersecurity and positioning. The tests will be in the simulation and real-world fields to validate safety and security performance according to the key users’ needs. The expected impact of the HEADSTART project is based on three main action pillars: testing and validation – potentiation of development strategies bringing time and cost reduction; assessment – creation of assessment protocols increasing vehicle safety awareness; certification – support of regulations ensuring the safe introduction of CAD technologies to the market.

Coordination of R&I and pilot activities in Europe: how can we learn in order to scale up?

Dr Stephane Dreher
Senior manager - connectivity and automation, blockchain
Ertico - ITS Europe
Belgium
Many research and innovation, testing and piloting activities are being carried out independently across Europe either through EU-funded consortia projects or at the national level driven by member states, industry or public-private partnerships. The lack of alignment and common approaches often results in duplications or overlaps, prevents comparability of results and the development of interoperable solutions, and hampers the harmonized deployment of CAD in Europe. In an effort to facilitate the exchange of lessons learned and best practices, as well as the identification of synergies and gaps between projects, the EU-funded ARCADE Coordination and Support Action has set up a comprehensive knowledge base on CAD-related activities in Europe and beyond, which is currently being populated in collaboration with the EU CCAM Single Platform. The project is also organizing concertation events to support consensus-building across stakeholders on methodologies or the identification of next R&I actions on CAD. This presentation will provide an overview of the CAD knowledge base and key outcomes from other harmonization-related activities of the project on methodologies or description of use cases.

Room2 Managing the big data requirements of autonomous vehicle development

Building an ADAS test and development environment in the cloud

Gabriel Sallah
EMEA HPC and big data architect, autonomous driving platform solutions
Microsoft
United Arab Emirates
This session will focus on the key Azure Cloud services needed to meet the demanding end-to-end requirements of testing and validating autonomous driving vehicles: from large-scale data ingestion (PB), to large-scale simulations (60,000+ cores) using high-performance computing (HPC), to scalable machine learning model creation, deployment and management. The presentation will share real-world experience of successfully building this platform for major OEMs and tier suppliers.

ADAS/AD virtual end-to-end software development

Dr Clara Marina Martinez
Engineer - ADAS virtual development
Porsche Engineering Services
Germany
ADAS/AD software development needs to cope with complex sensor systems, plentiful corner cases still to be discovered and a cumbersome number of kilometers to test/certify. These tasks require high support from virtualization to be achievable under challenging deadlines and at a reasonable cost. The perfect tool that gathers all your requirements does not exist. However, many high-quality software solutions are able to simulate sensors, traffic, vehicle dynamics, driver behavior and realistic environments with the level of detail that every project needs. At Porsche Engineering, we bring together the best tools, data sources and our experience in automotive, to create a flexible simulation platform to support end-to-end ADAS development.

ADAS/AD development and data management – are you ready to leverage the cloud?

Dr Florian Baumann
CTO (Automotive&AI)
Dell Technologies
Germany
Development of AD/ADAS is a massively complex process, requiring management of vast data sets. In turn, this leads to subsequent iterative development using HiL / SiL performance testing against defined test cases, and development of real-time inference engines. A growing development ecosystem, including toolchains, algorithms, public training decks, annotation services and more, is coming but requires carefully managing security and access to highly-valuable and company confidential information. An approach that offers access to multiple public cloud services at the lowest cost, but with the greatest agility is essential to take a leading position in this highly competitive market. This webinar will discuss best-in-class methodologies for leveraging Public Cloud, shedding light on the tradeoffs and technical roadblocks introduced and how to avoid them.

Validation of safety through scenarios. Simulation with common standards.

Validating ADS toward an industrial scenarios database

Marc Pajon
Expert leader - testing and measurement technologies
Renault Group
France
Validating AV safety is a crucial part of ongoing research. The approach of separately track-testing sensors and driving algorithms is hardly sufficient to demonstrate AV safety. Scenario-based simulation approaches are necessary complements to the traditional approach, allowing computation of a controlled diversity of key variables in many iterations in a safe, fast and documented way. French car manufacturers Renault and PSA, together with academic researchers (VEDECOM, SystemX, Lab and Ceesar) and other partners (Valeo, AVS and Expleo), propose to address the challenge of demonstrating AV safety by taking into account an array of 'in-the-field' situations.

Enabling virtual test and validation: creating a virtual proof of validation in the ENVITED ecosystem

Carlo van Driesten
Systems architect for virtual test and validation
BMW Group
Germany
New forms of cooperation are necessary to turn the vision of autonomous driving and fully connected mobility systems into reality. Virtual validation is an essential part of the development process. Standards for model and system interchange are vital for cross-company and cross-domain virtual integration and simulation of HAD functions. Standards like FMI, SSP and the OpenX at ASAM eV showcase current possibilities, challenges and future directions, as well as a vision of future collaborations. The foundations for the future ecosystem have been laid by the ENVITED ecosystem: standardized data for virtual test and validation; open and modular simulation architecture; traceability of standardized data and test results for a virtual proof of validation.

ASAM simulation standards – past, present and future

Benjamin Engel
Global technology manager
ASAM eV
Germany
In 2018 ASAM acquired its first simulation standards in the form of the OpenX portfolio (openDRIVE, openCRG and openSCENARIO), with the addition of the Open Simulation Interface in 2019. Since then, simulation experts worldwide have been working hard on the first official ASAM revisions, the first of which are to be released in Q1 of 2020. This presentation will give an overview of the ASAM activities to date, and provide some insight into where we see the road leading in 2020 and beyond. Our goal is standardization to facilitate the development of safe, regulated autonomous driving.

Room2 Developing AI, ADAS and AV technologies through data application & management, high-performance computing and advanced simulation.

Embedding smartness into validation and verification of automated driving functions

Matthieu Worm
Director autonomous vehicles
Siemens Digital Industries Software
Belgium
Execution of 100.000s of test runs with a trustworthy virtual vehicle in a cluster or cloud environment is a challenge in itself. With Simcenter Prescan360, we introduced an off-the-shelf solution to generate scenario variants, to orchestrate the massive numbers of test runs and to post-process these results for easy interpretation. However, by adding additional smartness, the process can be optimized and automated much further. In this presentation we will highlight how design exploration and AI techniques are applied to create critical but unseen scenarios that might make the system fail. Secondly we’ll introduce smart metrics to automate accurate safety assessments of the automated driving functional performance.

Capturing and managing big data for Autonomous Driving (AD)

Frank Kraemer
Systems architect
IBM
Germany
Alexander Noack
Head of automotive electronics
b-plus GmbH
Germany
ADAS/AD providers use Artificial Intelligence as one key component. Researchers and developers who can deliver insights faster while managing rapid infrastructure growth will be poised to be industry leaders. Following the process of data-acquisition from test drives via ingest to the data center and processing of big data many challenges occur. To handle these unstructured data, seamlessly scaling systems and toolsets are necessary from the sensor to data center with storage and computing systems. This combined presentation provides a case-study how synchronized data capturing in test drives, big data computing, storage and archiving are integrated in today’s ADAS/AD development workflow.

Room 1 Safe, safer, safest – developments in and discussions of AV/ADAS safety technology

SOTIF in a Volvo Cars context

Carina Björnsson
Technical expert, driver assistance and active safety test methods
Volvo Car Corporation
Sweden
Volvo Cars has developed cars with ADAS since the beginning of 2000. The company's ambition is and always has been to make safe cars. How does the SOTIF ISO/PAS 21448 affect active safety development? Are we perhaps fulfilling the SOTIF PAS already? How did we handle non-ISO hazards before SOTIF PAS existed? The presentation will explore some use cases/examples where SOTIF affects the product.

From absolute safety to informed safety: the role of the operational design domain

Siddartha Khastgir
Head of Verification & Validation, Intelligent Vehicles
WMG, University of Warwick
UK
To prove that automated driving systems (ADS) are safer than human drivers, it is suggested that they need to be driven for over 11 billion miles. A number of miles is not an appropriate metric and doesn’t guarantee absolute safety. This highlights the question: “How safe is safe enough?” To answer, we suggest a departure from the world of absolute safety to informed safety. A key aspect of informed safety includes an accurate and standardized definition of the operational design domain for an ADS, including conveying it to users, regulators and other stakeholders. The first step in all safety standards: ODD definition.

Pedestrian protection through automated driving

Robert Klarner
Head of Branch Office - Technology Marketing
DLR
Germany
A new concept for an autonomous driving system is presented, which in particular protects other road users such as pedestrians and cyclists. Furthermore, the system automatically ensures compliance with traffic regulations in a smart city equipped with it. It goes far beyond what we have seen so far with lane-keeping or automatic braking systems. The concept of geofencing will be further developed with unprecedented granularity. Detailed maps of the traffic areas of a city with 4in resolution will be used.

Room2 Vision, sensor and lidar test, development and validation

Employing simulation environments for sensing performance evaluation – challenges and opportunities

Farid Kondori
Verification tools lead
Aptiv
Sweden
To tackle the problem of verification and validation of autonomous vehicles, synthetic data generated in simulation environments can be employed to complement field testing, due to the fact that these environments are highly flexible and inexpensive. Although in recent years virtual environments have been employed by the community to develop and test ADAS/AD functionalities, such as AEB or ACC, there has been limited possibility to utilize synthetic data for sensing functions performance evaluation. This presentation will address the challenges and opportunities of simulation environments for verification and validation of camera-based sensing algorithms.

Successful test and development for integration and acceptance of autonomous vehicles

Autonomous vehicle engineering simulation tools for appropriate driver acceptance and comfort

Dr Andras Kemeny
Expert leader immersive simulation
Renault
France
The challenge of autonomous vehicle validation relies on massive simulation, due to the vast number of kilometers to run in various road, traffic and weather conditions. Nevertheless, acceptance of the proposed automation system will have a heavy impact on the use of the system and the efficiency of handling it when sharing or taking back vehicle control. Driver-in-the-loop simulation will play an essential role, using high-performance driving simulators or dedicated configurations, including virtual reality and web-based online solutions. These simulation tools will be essential to complete efficient autonomous vehicle engineering design for driver acceptance and comfort.

Ensuring successful implementation and uptake of new mobility services

Kevin Vincent
Director - Centre for Connected and Autonomous Automotive Research
Coventry University
UK
The technological challenges/opportunities of CAV/CAM and the roadmap to autonomy are maturing. However, the requirements to generate market pull and the skills required for the successful implementation and uptake of services are less well understood. For example, safe ongoing operation of vehicles needs new MOT tests addressing security, software and data privacy; new and disruptive ownership models present issues and opportunities regarding individual design and brand identity; trust and perception require more human-centered design for viable solutions. These and more questions need answering if economic, environmental and productivity projections are to be realized.

Room2 Collaborative and open-source approaches to autonomous vehicle development

Why the safety of autonomous vehicles must be a collaborative affair

Jack Weast
Senior principal engineer, Intel & VP autonomous vehicle standards, Mobileye
Intel Corporation
USA
The AV industry now has a key opportunity to formalize safety standards, give guidance to regulators, and get AVs off the test track and into the real world. For years, Intel and Mobileye have advocated for industry and regulatory consensus on AV safety, culminating in a forthcoming standard – IEEE 2846 – that will establish a model for AV decision making that will be formally and mathematically verifiable, technology-neutral and regionally customizable. This session will provide an overview of the safety standards landscape, how this IEEE standard initiative plays a unique role, and why it is imperative for the industry to adopt a more open, transparent and collaborative approach to deliver on the AV promise.

Automotive Grade Linux: enabling industry collaboration through open-source software

Dan Cauchy
Executive director, Automotive Grade Linux
The Linux Foundation
USA
The Automotive Grade Linux (AGL) community consists of more than 150 companies across the automotive and tech industries who are working together to develop an open-source software platform for all in-vehicle applications from infotainment to autonomous driving. Sharing a single software platform across the industry decreases development times so OEMs and suppliers can focus on rapid innovation and bringing products to market faster. This talk provides an overview of AGL, production use cases including Toyota and Subaru, the project roadmap and how to get involved.

Autonomous driving and open-source technology – does it fit?

Andreas Riexinger
Product manager
Robert Bosch GmbH
Germany
Automated driving solutions introduce new complexity into the development of embedded systems in cars. This complexity rises with each level of control and autonomy. The toolchain for such challenges is also complex and the integration of all the tools requires considerable effort without a real competitive advantage for the automated driving solution. Instead of solving these challenges alone, wasting lots of money along the way, Bosch's automated driving division has started an open-source community known as OpenADx. This talk will present the open-source approach, the current state of the community and the currently available solutions.

Verification and validation. Homologation and standards. Improving safety and reducing development time

Applying the PEGASUS approach to automation for the urban environment

Dr Hardi Hungar
Team Leader Verification and Validation Methods
German Aerospace Center
Germany
The PEGASUS project developed and demonstrated a method for the validation of automated driving functions for the highway domain. Two projects currently elaborate on this approach and apply it to the far more complex urban environment. Simulation is supposed to provide the bulk of evidence for the homologation of the vehicles. For that, the simulation must be adaptable to various tasks in the verification and validation chain. And, of course, the simulation results must be validated. One project, SET Level 4-5, is developing simulation technology based on a modular architecture with standardized interfaces. The other, VVMethoden, covers the full development lifecycle and employs simulation technology. The talk will present the intended role of the simulation and the projects' approach to providing the technology with the desired features.

Homologation of automated driving functions: worldwide overview, customer acceptance and strategic aspects

Emmeram Klotz
Head of test and validation
TÜV Süd
Germany
Homologation of automated driving functions presents a huge challenge for their market introduction. Existing regulatory safety frameworks applicable to conventional vehicles and their components are insufficient to fully assess the operational characteristics of current and future automated vehicle technologies. With increasing automation, vehicles transform into cyber-physical systems that no longer require a human driver; therefore, new safety challenges will have to be considered. This presentation discusses those challenges, provides an overview of the current regulatory and standardization work in progress and explains the possibilities for how to approve automated vehicles for public roads today.

Virtual validation of autonomous driving functions by AI-based simulation

Oliver Bleisinger
Business area manager automotive
Fraunhofer IESE
Germany
Due to the high degree of connectivity of highly automated and autonomous vehicles, they must function in a variety of scenarios during the utilization phase. Providing a realistic test environment that covers these usage scenarios is a major challenge for virtual engineering of autonomous driving functions. Especially for the virtual validation of the driving functions, this requires a large number of simulation models of external systems involved, to which not every developer has access. However, AI procedures can possibly be used in future to reduce the effort required to generate the necessary simulation models.

Room2 Real-world/physical test and development. Integration with and implications for virtual testing

CAV testing on public roads – crucial learning or unnecessary risk?

John Fox
Program director – Midlands Future Mobility
WMG - University of Warwick
UK
Testing of CAVs on public roads is a hot topic. Does it expose the public to unnecessary risk or is it essential for profound safety improvement on the world’s roads? Can we have the best of both worlds: on-road learning with enhanced safety? The presentation addresses these questions, using the £35m Midlands Future Mobility test and trialling ecosystem as a case study. There are exciting times ahead!

Level 4 AV testing for urban environments: challenges and opportunities and physical testing

Niels de Boer
Program director, CETRAN
Nanyang Technological University
Singapore
As autonomous vehicles (AVs) increase in maturity, the complexity in ensuring they are safe increases as well. The traditional automotive testing methodologies need to evolve to suit the ever-changing nature of AVs. This will bridge the gap between regulators and AV developers, and eventually lead to safe and effective implementation of AVs. In this presentation, CETRAN will present the key challenges it faces when testing Level 4 AVs, and will share its approach and the ongoing research/projects to tackle these challenges. The focus will be on the current unresolved issues in virtual and physical testing.

From real driving data to concrete test scenarios

Florian Hauer
Chair of software and systems engineering (department of informatics)
Technical University of Munich / ITK Engineering GmbH
Germany
We present a holistic approach that takes recorded traffic scenario instances and yields 'good' test scenarios for automated and autonomous driving systems. Such test scenarios are usually generated from scenario types, for which we present an approach that allows measuring both the test case quality and system behavior. Since this requires completeness of the list of scenario types, we provide both a statistical model and a methodological approach to assess completeness. To achieve the latter, we automatically derive scenario types from real data, which complements current manual scenario derivation. We show technical solutions for each of the steps presented.

Real-world/physical test and development. Integration with and implications for virtual testing (continued)

Have we collected enough traffic data?

Sytze Kalisvaart
Project manager StreetWise, integrated vehicle safety department
TNO
Netherlands
Many OEMs and other automated driving companies are collecting massive amounts of driving data to identify what scenarios the automated vehicle might have to deal with. Through scenario extraction, repeated driving patterns are categorized and turned into statistics essential for effective safety assessment. But when is the data collection enough? The TNO StreetWise scenario database includes completeness indicators at various steps in the scenario mining pipeline. We will introduce the meaning and application of these completeness indicators. In this way, OEMs can compare coverage of their data collection and quantify the completeness of the collected data.

Robopilot – Level 4 autonomous driving on mixed roads

Nicholas Clay
Head of homologation and quality
Arrival
UK
The presentation will outline the challenges, lessons and successes of Robopilot – a UK CCAV-funded project delivering a demonstration of Level 4 autonomous driving on mixed roads in the UK. It will focus on the testing and validation journey from research and simulation to on-road testing and live demos. Robopilot is a £12m consortium project based in the UK. Partners include UPS, Thales, Bristol Robotics Lab, Loughborough University, TVS and South Gloucestershire Council.

Automated public road testing based on digital twins

Patrick Luley
R&D manager - automated driving
Joanneum Research - Digital
Austria
To pave the ground for saleable and cost-efficient test and validation of AD functions by real testing on public roads, Joanneum Research is producing Ultra High Definition Maps (UHDmaps) based on mobile mapping data in a saleable automated workflow. UHDmaps contain a digital copy of reality, which sets the benchmark for the digital assessment of automated driving functions. The depicted solution is already utilized by the Austrian Light Vehicle Proving Region for Automated Driving (ALP.Lab GmbH) and its partners. The presentation will give an overview of the technical solution and certain test use cases.

Collaboration and standards in scenarios and simulation

AD-EYE: a simulation platform for automated driving systems

Maxime Sainte Catherine
Research engineer
KTH Royal Institute of Technology
Sweden
Automated driving systems (ADS) require solving a multitude of capabilities including perception, decision making and planning in real time. Each of them represents a challenge on its own, and researchers usually focus on one while abstracting away the rest of the system. In this presentation, we will introduce the AD-EYE platform, which has been developed under several EU projects and with the collaboration of multiple industrial partners. The goal of the project is to provide a simulation platform for ADS-related simulations with common base functionality that can be modified as per need. The aim is to provide better integration of the different projects by letting research groups work in a common environment. AD-EYE targets, in particular, dependability-related evaluation of architectures and algorithms for highly automated vehicles; as a prominent feature, it provides a configurable safety supervisor architecture. The talk will present the current status of the platform, illustrate its use and discuss its current roadmap.

Developing a future-proof scenario database in a world of emergent standards

Mike Freeman
Project engineer
Warwick Manufacturing Group
UK
Testing is fundamental to the safety of automated driving software, but driving billions of miles to achieve sufficient scenario coverage is unfeasible and requires a better approach. Scenario sharing across the industry is gaining support as being the solution. With this aim, the standardization of scenario description is being worked on but we are still some way from a universal standard. This puts the system architect in a difficult position: how to design a scenario database that will support today’s standards as well as those of tomorrow? As part of the UK’s Midlands Future Mobility project, we answer this question.

Please note: This conference program may be subject to change