The road to cloud-based validation for autonomous vehicles
Janek Jochheim Product manager cloud and SaaS dSPACE GmbH Germany
It is common knowledge in the automotive industry that simulation and software-in-the-loop are key elements for the validation of autonomous vehicles. These simulations will usually be executed in the cloud. But how can a user get to a scalable cloud simulation and – even more importantly – how can they choose and execute the right test cases? And is this 'just' a technical challenge? This presentation discusses the different topics that have to be addressed in order to get to simulation and validation in the cloud, and points out the major challenges on the way.
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.
Introducing data center technologies to simplify data harvesting in test drives
Johannes Zangerle Technical business developer b-plus GmbH Germany
Sensor bandwidths and the complexity of automated vehicle setups are the main challenges for harvesting data during test drives. Measurement tasks are moving toward multi-gigabit data rates with many raw data and metadata streams. Intelligent data distribution and time correlation are crucial for exact data acquisition. In the end, data integrity and time correlation are key for further analysis and AI lessons. This presentation shows how data center technologies such as RDMA over Converged Ethernet and Ethernet switching fulfill the requirements of Level 4 or Level 5 systems, and how an intelligent data recording infrastructure reduces data management complexity.
Validation in the virtual domain
From ideal to full physics: why XIL simulation for developing and validating AD/ADAS requires multi-level sensor models
Thomas Nguyen That Head of automotive domain AV Simulation France
Vehicle-in-the-loop – bridging the gap between simulation and real world
Dr Tobias Düser Department manager AVL Germany
The integration and validation of ADAS and AD functions require new approaches in the vehicle development process. AVL’s vehicle-in-the-loop approach combines a vehicle testbed for the complete and integrated vehicle with a detailed simulation environment. Different components such as a dynamic steering force emulator, sensor over-the-air simulators, etc empower the vehicle testbed to be suitable for ADAS and AD validation. As part of an overall virtual testing toolchain, this approach helps to deal with the test coverage while reducing test effort. All scenarios can be performed at vehicle level under highly reproducible and safe conditions. Different application examples will be introduced.
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.
AD-EYE: a simulation platform for automated driving systems
José Manuel Gaspar Sánchez 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.
Validation and performance evaluation tools for higher-level autonomous perception
Michel Berendes Project manager ibeo.Reference Ibeo Automotive Systems GmbH Germany
Development and validation of ADAS/AD sensor perception require solid ground truth to be successful. With projects aiming for autonomous functions Level 3 or higher, manual ground truth labeling has reached its limitations in acceptable cost and time consumption. ibeo.Reference offers a chain of highly automated tools to enable ADAS and AD function development companies to provide their teams with the fast and reliable ground truth their projects require. This presentation will offer an overview from recording a parallel perception of the vehicle’s environment, through automatic and smart-manual ground truth generation, to automated comparison and perception performance calculation.
Real-world and open-road test and development
Practical implications of steward-less autonomous vehicle testing and operation
Tom Jansen Global domain leader connected and automated vehicles Ricardo plc Netherlands
We are seeing the deployment of many 'novel' pilots with self-driving vehicles around the world. Looking more closely, we see that often these vehicles feature a steward or safety driver on board, who is legally in control of the vehicle at all times. With new legislation slowly allowing testing without stewards on board, it is essential that we understand the practical implications for autonomous vehicles operating without safety drivers. In this session we will explain the implications for CAV design and testing from our practical experience working with industry leaders in recent (truly driverless) CAV projects.
Level 4 AV testing for urban environments: challenges and opportunities
Mohamed Azhar Halikul Zaman Research engineer CETRAN 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.
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.
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.
Deploying autonomous buses in mixed traffic
Jorgen Kjaer Business development manager - autonomous buses Vy Group Norway
Vy Group is a leading bus operator in the Nordics, operating over 3,000 buses. We are taking a leading role in the deployment of autonomous buses in public traffic. In a successful project in Kongsberg (Norway), two autonomous buses have replaced a regular diesel bus in operation (mixed traffic). This winter, we will test driving without a safety host on some parts of the route in Kongsberg. We will also test operation without a safety driver in an industry park, with traffic lights. We also have a project for bigger AV buses.
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!
Automated driving grows out of the niche
Dr Eric Sax Head of Institute of Information Processing Technology Karlsruher Institute of Technology (KIT) Germany
The motivation for the introduction of autonomous driving differs between road users. For passenger cars, safety and comfort are driving forces. For commercial vehicles, economic reasons are most promising. Increasing the service times of trucks and buses by supporting drivers or even substituting them with advanced driver assistance systems is a huge business case. The idea is to start in areas that are closed to ordinary traffic: on depots. This application domain is followed by bus rapid transport in special lanes, highways and situations that promise a controllable environment. A stepwise approach is most promising and the innovation will be derived from the niche. The idea is to learn and experiment there and, step by step, enhance the field of use.
Transitions for Level 3 automation
Anne Klamroth Research fellow Bundesanstalt für Strassenwesen (BASt) Germany
Level 3 automated vehicles require that the driver takes over control if system limits are reached. But can traffic conditions have an influence on the takeover? To investigate this question, the Federal Highway Research Institute conducted a Wizard-of-Oz study on federal motorways in the Cologne-Bonn area. Thirty-nine test participants were involved in the study; this talk will present the findings and potential consequences.
Autonomous Vehicle AI, Software and Sensor Fusion Conference
AI-in-the-loop optimization of Ford’s Predictive Dynamic Bending Light
Aleksander Spychala Software engineer Ford Germany
Automotive lighting technologies have a challenging task to offer functionalities that provide a recognizable benefit to drivers. Engineering such technologies is even more difficult.
Having successfully implemented artificial intelligence to quantify drivers’ subjective impressions of the performance of Predictive Dynamic Bending Light in real time, as well as in simulations, Ford has employed it for AI-assisted automated feature tuning by conducting AI-in-the-loop tests in addition to driver-in-the-loop tests. Using experimental design and multi-dimensional optimization techniques, various parameter sets are tested and gradually optimized with the aid of genetic algorithms to present a feature calibration offering the best performance determined by the AI.
UAVs for safety validation and development of highly automated driving
Automated driving relies heavily on data-driven methods. Large datasets of real-world measurement data in the form of road user trajectories are crucial for several tasks. Using a drone has the major advantage of recording naturalistic behavior. Due to the ideal viewing angle, an entire scenario can be measured with significantly less occlusion than with sensors at ground level. Both the class and the trajectory of each road user can be extracted from the video recordings with high precision using state-of-the-art deep neural networks. Using this method, we are creating large-scale datasets with naturalistic road user behavior using camera-equipped drones.
Linux safety plan: how far are we now?
Dr Oscar Slotosch Vorstand Validas AG Germany
After an introduction to basic safety concepts for tools, libraries and new software, we present an ISO 26262-compliant safety plan that can be applied to make Linux (and any other quality software) safe by completing its development. Completion is achieved by creating an 'interface' model for the software starting from requirements, architecture and test cases and verifying it using safety analysis and checklists. The process and the model can be applied up to ASIL D. Examples are taken from the Linux kernel source code and document the status of compliance of Linux.
Autonomous vehicles – upcoming UN ECE cybersecurity autonomous vehicle regulation
Dragos Dabija Security manager Accenture Romania
UNECE is at the center of the legal and regulatory work needed to realize the vision of new sustainable mobility and support the mass introduction of autonomous vehicles on the roads. It started dedicated work on this issue back in 2014. UNECE strongly contributes to enabling autonomous driving functionalities. The relevant forums (e.g. GRVA, WP.1 and WP.29) are following the technical progress with the aim of ensuring that the benefits of these new technologies can be captured without compromising safety and other progress achieved during the last decades (e.g. border crossing, interoperability, etc).
Establishing trust with in-vehicle software management
Roger Ordman Executive vice president Aurora Labs Israel
Mass-market adoption of new technologies requires trust. Trust that the software underpinning the technology will be safe, secure and will constantly work as advertised. This presentation will look into the challenges faced by the vehicle manufacturers and their Tier 1 suppliers in ensuring that software faults and hacks can be detected before they cause a system failure. The regulatory landscape for cybersecurity and OTA will also be addressed (UNECE WP29 GRVA).
Traditional over-the-air updates are known for delivering updates to the system software alone. This presentation will introduce a secure methodology to now also update the functionality of the system hardware controllers. The demo will show how hardware updates can instantaneously be processed in all nodes in today's connected vehicle. The demo will show integrated technologies from the RTI Connext Drive framework, Xilinx adaptable technology and a secure cloud-based system from Bosch Software Innovations.
Lessons learned and mistakes that can be prevented in cybersecurity
Miguel Bañón Vice president business line cybersecurity Dekra Spain
The autonomous vehicle is an exciting technological beast that will disrupt transportation. Other technological advances have had much longer development cycles, from the proper IT building blocks, like operating systems, to space and aviation systems. From the perspective of an IT security evaluation facility, we observe a number of repeating flaws and mistakes that can be prevented, providing a sound basis for lessons that need to be learned and applied for secure take-off and success of the autonomous vehicle.
Protecting mobility: Tesla’s vulnerability can exist in all vehicles
Yonatan Zur CEO and co-founder Regulus Cyber Israel
Researchers from Regulus Cyber recently initiated remote spoofing attacks on the Tesla GNSS (GPS) receiver, exploiting security vulnerabilities in mission-critical telematics, sensor fusion and navigation capabilities. With Tesla as a backdrop, the presentation will explore the security requirements for safe satellite-based navigation for driverless technology – cyber defense for sensors, anti-interference, anti-jamming, anti-spoofing systems that exist, and best practices for implementation. It will also discuss recent technological developments creating new threats, and will highlight the rapid growth of real-world attacks happening across these multiple sectors and how they are expected to grow as GNSS-dependent systems become more connected and autonomous.
Please note: this conference programme may be subject to change