Etikettarkiv: Volvo Group

Guldkorn från svensk forskning 2021

Det här är svenska guldkorn ifrån er läsare. Stort tack för alla bidrag, och tack för ert fantastiska jobb.

PhD thesis: Decision-Making in Autonomous Driving using Reinforcement Learning.
This thesis explores different techniques based on reinforcement learning (RL) for creating a generally applicable decision-making agent for autonomous driving. One highlight is the introduction of methods that can estimate how confident the trained agent is in its decisions, which for example is important if the agent is exposed to situations outside of the training distribution. Another contribution is a method for combining planning and RL, which both improves the quality of the decisions and reduces the required amount of training samples. The full text is available here. This project was supported by Volvo Group, Chalmers, Wallenberg AI, Autonomous Systems and Software Program (WASP), Vinnova FFI, and AI Sweden. For more information, contact Carl-Johan Hoel (carl-johan.hoel@chalmers.se).

L3Pilot – Piloting Automated Driving on European Roads
The L3Pilot project (https://l3pilot.eu/) is the largest EU project on automation so far and ended in October 2021. In this project, Chalmers and Volvo Cars investigated human collaboration with automated vehicles. The Wizard of Oz approach was used both on test track and on public roads to simulate an automated driving feature that did not require drivers to supervise the system. However, the drivers occasionally had to resume manual driving in response to take-over requests. More information about the participants and the publications from this project can be found here. For more information, contact Linda Pipkorn (linda.pipkorn@chalmers.se)

Long-term demonstration of autonomous shuttle fleets in Gothenburg will run between spring 2022 and 2023 as part of the H2020 project SHOW – SHared automation Operating models for Worldwide adoption (https://show-project.eu/). Main contribution of the real-life urban demonstration is the integration of fleets of automated vehicles into public transport, to advance sustainable urban mobility, combined with evaluations of technical solutions, business models, user acceptance and scenarios for impact assessment. The project aims to be the biggest and most holistic initiative ever piloting automated vehicles in urban environments. Real-life urban demonstrations will take place in 20 cities across Europe, such as in Madrid, Turin, Salzburg, Rouen, and Linköping. SHOW gathers a strong partnership including 69 partners from 13 EU-countries and fosters international cooperation. The demonstration in Gothenburg will take place at Campus Johanneberg/Chalmers University of Technology with partners Keolis, Ericsson and RISE. The project has received funding from the European Union’s Horizon 2020 research and innovation programme. For more information contact Cilli Sobiech (cilli.sobiech@ri.se).

Demonstrating remote controlled trucks at Lindholmen/Gothenburg. Within the project SCAT – Safety Case for Autonomous Trucks we will demonstrate goods transport without a safety host onboard and with higher velocity in a mixed traffic environment at Lindholmen (https://www.ri.se/en/what-we-do/projects/safety-case-for-autonomous-trucks). The demonstration will take place in spring 2022. The project started in autumn 2020 with partners RISE, Ericsson, AstaZero, Telia and Einride. The consortium explores together how to safely handle remote access and control from a technical safety perspective and from a policy perspective to support future commercialisation of automated vehicles. We consider the gaps and challenges related to the safety of automated trucks, the digital infrastructure, the policy framework in different markets and their behavioural implications. The approach includes the legal/policy framework in Sweden, as well as France and the US exemplarily. The project is funded through the strategic innovation program Drive Sweden by Vinnova, Formas and the Swedish Energy Agency. For more information contact Cilli Sobiech (cilli.sobiech@ri.se).

Digital traffic rules for a connected and automated road transport system. In the framework of Drive Sweden Policy Lab 2021/22, one case study is identifying ways towards a future system for digital traffic rules (https://www.drivesweden.net/projekt-3/drive-sweden-policy-lab). We raise issues concerning the development of traffic regulations in Sweden through dialogue with a wide range of actors. The purpose is to investigate what is needed to create conditions for a future system with traffic rules that are geographically unambiguous and can be read by machines. Reliable information is needed already today for various applications and supporting IT systems and will become increasingly important with a connected and automated road transport system. We use policy labs as a method to find a possible solution, for example through the development of the regulations that govern how traffic regulations are decided and announced. A development of processes and routines for production, management and exchange of traffic rule data would reduce the risk of deviations that we see today. The project can contribute by looking at challenges, opportunities and alternative solutions linked to the regulations. Drive Sweden Policy Lab is a platform for collaborative policy development enabling smart mobility solutions. The platform gathers governmental agencies, municipalities, multinational corporations, start-ups and research to solve bottlenecks for innovative projects. The project Drive Sweden Policy Lab 2021/22 is funded through the strategic innovation program Drive Sweden by Vinnova, Formas and the Swedish Energy Agency. For more information contact Cilli Sobiech (cilli.sobiech@ri.se).

External interaction principles for creating trust in heavy automated vehicles. To become widely used on public roads, future automated vehicles (AVs) will need to be trusted and gain societal acceptance – something that will be greatly affected by their ability to safely, efficiently and seamlessly interact with other road users in the traffic system. This project investigates if there will be new communication needs when heavy AVs are introduced in traffic. More specifically, the project is investigating how trust and acceptance of heavy AVs can be created and maintained via External Human-Machine-Interfaces (eHMI). Currently, the project has conducted a series of studies including a virtual reality simulator study, and two Wizard of Oz studies on a test track. These studies have been focused on interaction between heavy AV’s and pedestrians. Our next goal is to investigate interaction between heavy AV’s and passenger car drivers using a driving simulator. The project is supporting an institute PhD candidate, and has also hosted two master thesis projects together with Umeå University: Designing eHMI for trucks: How to convey the truck’s automated driving mode to pedestrians and Communicating the stopping intent of an autonomous truck: The interplay between content size, timing and truck speed. This project is financed by Fordonsstrategisk Forskning och Innovation (FFI), associated to SAFER and led by Scania with RISE and Halmstad University as partners. For more information contact Yanqing Zhang (yanqing.zhang@scania.com)

Policy Lab Smarta Fartyg. Projektet undersöker hur den pågående digitaliseringen inom svensk sjöfart rimmar med dagens regelverk. Analysen görs utifrån tre konkreta fall. Två av fallen berör hur autonoma funktioner på ett godtagbart säkert sätt kan ta över människans ansvar ombord utifrån konstruktion och användningsområde. Till skillnad från fordon finns det ingen försöksförordning för autonoma fartyg så arbetet utgår från de regler och undantag som etablerats under en epok när befälhavaren alltid var ombord. I det tredje fallet samverkar två myndigheter kring hur en förändring av dagens lotsplikt kan påverkas av nationella behov och förutsättningar samtidigt som det kommer nya internationella regler. Parter i projektet är Transportstyrelsen, Sjöfartsverket, Saab Kockums, ABB, Färjerederiet och RISE. Projektet finansieras av Trafikverket. För mer information, kontakta projektledare Susanne Stenberg (susanne.stenberg@ri.se) eller Håkan Burden (hakan.burden@ri.se)

Precog: Kravhantering för säkra maskininlärningsbaserade perceptionssystem för autonom mobilitet. Självkörande fordon kräver tillförlitliga perceptionssystem. Framgångsrika perceptionssystem förlitar sig på maskininlärning. Maskininlärning bygger på träningsdata av hög kvalitet. Vad innebär detta för fordonens perceptionssystem? Hur kan vi specificera förväntningarna på träningsdatan? Vad innebär kvalitetssäkring på data-nivån? Hur påverkas fordonets funktionssäkerhet på systemnivån? Den nystartade förstudien Precog genomförs av RISE, Göteborgs universitet, Annotell och Zenseact med stöd från Vinnova. Projektet kommer att skapa samsyn för krav på maskininlärningsbaserade perceptionssystem för fordon. Precog ska utreda kedjan 1) annoteringsnoggrannhet för träningsdata, 2) maskinlärningsmodellernas precision, 3) perceptionssystemens korrekthet och 4) funktionssäkerhet. Förstudien kommer att organisera en serie workshops med nyckelspelare inom svensk fordonsindustri. Vidare kommer dessa workshops att kompletteras med djupintervjuer och litteraturstudier. Efter syntes av projektresultaten kommer vi att arrangera en öppen workshop för att delge våra slutsatser under våren 2022. För mer information kan ni kontakta Markus Borg (markus.borg@ri.se)

Motion-Planning approach for autonomous bus driving. A collaboration between Scania and KTH Royal Institute of Technology resulted in the development of a novel Motion-Planning approach for autonomous bus driving. The results of this collaboration have been recently presented in the IEEE Vehicular Technology Magazine (https://ieeexplore.ieee.org/document/9470918). The article presents a motion-planning framework that leverages expert bus driver behavior, increasing the safety and maneuverability of autonomous buses. To deploy autonomous driving technologies in urban public transport, many challenges related to self-driving buses still need to be addressed. Unlike passenger cars, buses have long and wide dimensions and a distinct chassis configuration, which significantly challenges their maneuverability. To deal with the bus special dimensions, the authors introduce a novel optimization objective that centers the whole bus body as its travels along a road. Furthermore, the authors present a new environment classification scheme that enables self-driving buses to take advantage of the elevated overhangs, to increase maneuverability. Finally, a novel collision checking method is presented that explicitly considers a bus’s front wheels and how they can protrude from beneath the chassis when maneuvering near stops. The benefits of the proposed solution are presented through exp8eriments using an autonomous bus in real road scenarios. The work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. For more information contact Rui Oliveira (rui.oliveira@scania.com) from the KTH Royal Institute of Technology.

Industrial PhD project: Machine Learning to Enhance AI Planning for Intelligent Autonomous Transport Systems. Scania has developed an Offboard system by which its autonomous vehicles can be controlled and managed to perform their operations. This Offboard system can allow an automated planning and scheduling system (a.k.a. AI Planner) to create missions (plan) and dispatch them to the autonomous vehicles. Scania is now researching how to improve AI planning methods for fleets of autonomous vehicles using Machine Learning (ML) techniques. Learning algorithms will support AI planners in order to save human effort leading to good quality plans in less time, thus overcoming the challenge of depending upon the fleet transport managers experience. The PhD project’s outcome is expected to help Scania’s Offboard ATS to improve the plan quality and enable the system to scale up so that it could deal with the future challenges as autonomous vehicles will be taking over in many areas that are of immediate interest to Scania. The project, partly founded by the Swedish Foundation for Strategic Research (SSF), started in April 2020 and it will last 4 years, leading to a PhD degree from Örebro University. For more information contact the Industrial PhD student Simona Gugliermo (simona.gugliermo@scania.com), the industrial supervisor Christos Koniaris (Christos.koniaris@scania.com)  or the academic supervisor Federico Pecora (federico.pecora@oru.se)

Thesis on Cyber Resilient Vehicles. Cyber security focuses on detecting and preventing attacks whereas resilience concentrates on maintaining the vehicle’s intended operation in the presence of faults and attacks, which may even require the vehicle to disable some functionality to protect the passengers in and around the car. This becomes more important when higher levels of autonomy are introduced. In this thesis, we provide methods that aid practitioners in identifying and selecting the necessary and appropriate security and resilience techniques during the design of an automotive system. Additionally, this thesis also proposes three techniques to secure them, namely a mechanism to secure the internal communication, a model to assess a vehicle’s behaviour and reliability when it is driving in traffic, and a framework to detect attacks and anomalies in a vehicle fleet. This thesis was partially supported by the VINNOVA FFI projects HoliSec, and CyReV Phase 1 & 2. For more information contact Thomas Rosenstatter (thomas.rosenstatter@ri.se).

Enhanced ADAS – nästa generations ADAS. Advanced Driver Assistance Systems (ADAS) have the potential to improve traffic safety and efficiency. However, there are challenges with these systems in terms of their limited situation awareness and insufficient driver-vehicle interaction capabilities. If not addressed, these could lead to poor driver experience and decreased use of these systems. This project is led by RISE together with Aptiv and Smart Eye as partners. The aim of this project is to explore how safety, efficiency and drivers’ experience, acceptance and trust can be enhanced by enriching the situation awareness of existing ADAS with real-time information from a) digital road maps, b) driver monitoring, and c) by incorporating dynamic driver-vehicle interaction strategies. The project aims to include two iterations of prototypes with testing of each one on public roads or test track. The first iteration of prototypes has been evaluated and was completed now in december together with expert participants that work in the field of automotive technology. We have received valueable feedback for initiating the second iteration where we aim to develop ADAS functionality together with an intelligent vehicle-driver interface that derives information from internal and external vehicle sensors, as well as digital road maps. This project is financed by Fordonsstrategisk Forskning och Innovation (FFI). For more information contact Niklas Strand (Niklas.strand@ri.se)

The focus of automation in the Project I.hamn. Sweden’s ports are facing a major challenge to function as a transport node in the transformation to a more sustainable transport system that is expressed through the UN’s goals for sustainable development and the strategy for transferring freight transport from land to sea and rail. This means a higher pressure on infrastructure and resources, which places demands on new capabilities in the execution of the port’s operations. Ports need to be more efficient, enable sustainable transport and become a natural node in the integrated transport system. The project I.Hamn (https://www.ri.se/sv/vad-vi-gor/projekt/ihamn) gathers a continuous expanding cluster of today 22 Swedish small and medium sized ports allowing them to join forces to lower thresholds in adopting solution associated to digitalisation, automation, and electrification. The project also involves system and infrastructure suppliers, and other port stakeholder, such as shipping lines, authorities and industry associations. During 2020/2021 the vision of the future port has been co-developed together with involved ports and its stakeholders, through workshops and interviews. Based on the vision, a number of demonstrators are planned for in the areas of electrification, digitalisation, and automation. The demonstrators aim to identify potential and future solutions, based on the capabilities required to realize the vision of the sustainable port. Examples within the area of automation that are exploited are auto-mooring, automatic loading operations, autonomous transports in the port area and automatic hinterland entry and exits to the port. I.hamn is a three-year demonstration project funded by the Swedish Transport Administration within the framework of the Lighthouse industry program for sustainable shipping and coordinated by RISE together with Chalmers and GU. For more information contact Sandra Haraldson (sandra.haraldson@ri.se)

MobilityXlab har valt nya startuppföretag

Den Göteborgsbaserade samarbetshuben MobilityXlab väljer två gånger om året ut några startups att stötta. I denna omgång har sex svenska och sex utländska (europeiska) hightech-startupföretag valts ut.

De svenska bolagen är Datator Lab (In-cabin tech), Dpella (Affordable AI), Emsense (Sensor software innovation), Lolo (Serverless Compute och Networkless Connectivity), Omen Technologies (Sensor software innovation) och Radchat (Sensor software innovation) [2].

Dessa kommer under minst ett halvårs tid erbjudas direkt återkoppling och stöd från MobilityXlabs internationella medlemsföretag CEVT, Ericsson, Veoneer, Volvo Cars, Volvo Group, och Zenseact [1].

Källor

[1] Djurberg, J., A., Computer Sweden. De är Göteborgs hetaste startupgäng – när industrin får välja. 2021-06-09 Länk

[2] MobilityXlab. Twelve startups selected to collaborate with six world-leading Swedish companies. 2021-06-08 Länk

På gång i Göteborgs hamn

Volvo Autonomous Solutions, DFDS, APM Terminals, Göteborgs Hamn och Platzer har påbörjat ett kommersiellt pilotprojekt kring autonoma lastbilar [1].

En lastbil som är utrustad med sensorer som känner av omgivningen körs av en mänsklig förare runt i Arendal i Göteborg, både i hamnen och på allmänna vägar. Tanken är att de data som samlas in ska användas för att lära sig mer om komplexa vardagliga trafiksituationer och hur föraren interagerar med fordonet. Detta ska i sin tur användas för utveckling av artificiell intelligens för säker autonom körning. 

Projektet ses som ett första steg mot att skapa ett automatiserat och uppkopplat system för ett kontinuerligt flöde av gods.

Projektet delfinansieras av Connecting Europe Facility of the European Union och VINNOVA.

Egen kommentar

Dessa aktörer har också samarbetat vid testning av Volvos självkörande lastbilsprototyp Vera som inleddes 2019. Här kan ni läsa mer om det. 

Källor

[1] Volvo Autonomous Solutions. Full speed ahead on autonomous transport solutions for ports. 2021-05-31 Länk

Automatiserade eldrivna bussars samhällseffekter

Det Trafikverksfinansierade projektet ABE Södertörn har publicerat sin slutrapport. Projektet syftade till att utforska och kartlägga vilka fysiska och digitala åtgärder som krävs för autonom framdrift av fullstora bussar. Utgångspunkten var det expanderande området Södertörn men tanken var att slutsatserna skulle kunna vara generella.

Arbetet och slutsatserna bygger på tre (relativt extrema) scenarion: ”Bus Driver Plus”, ”Automation with Adaption” och ”Automation Utopia”. En av slutsatserna är att introduktionen av automatiserade fullängdsbussar kan komma att dröja längre än tidigare bedömningar givit vid handen. Däremot bedömdes det finnas stora potentiella samhälleliga vinster bara av att göra bussresan mer bekväm med hjälp av högautomatiserade förarstödsystem.

Projektpartners var ITRL (KTH), Sweco, Trafikverket, Volvo, Keolis, och Scania. Rapporten finns att ladda ner gratis i sin helhet.

Källor

[1] KTH. ABE Södertörn releases report on autonomous buses. 2021-05-24 Länk

Nytt samarbete mellan Volvo och Aurora

Volvo Groups affärsenhet Autonomous Solutions har gått in i ett samarbete med det amerikanska företaget Aurora för att skapa en mobilitetslösning i Nordamerika [1].

I samarbetet som skall sträcka sig över flera år skall initialt fokus ligga på att Auroras självkörande system vid namn Aurora Driver ska integreras med Volvos lastbilar.

Avsikten är att tillsammans skapa en hub-till-hub mobilitetslösning.

Källa

[1] AB Volvo. Volvo partners with Aurora to accelerate the deployment of autonomous transport solutions. 2021-03-30 Länk

Volvo verifierar

Volvo Group har ingått partnerskap med det Israeliska verifieringsbolaget Foretellix för att skapa en lösning som kan utvärdera och validera autonoma fordon i stor skala [1].

Lösningen bygger på den plattform vi nämnde i september. Säkerhet, beteenden och effektivitet ska utvärderas för maskiner och fordon i olika slags miljöer, inklusive begränsade utrymmen som till exempel gruvor.

Källor

[1] Volvo Group. Volvo Autonomous Solutions forms Partnership with Foretellix 2021-03-02 Länk

Guldkorn från svensk forskning

Dessa guldkorn är bidrag från våra läsare – stort tack för det, och för all fantastisk forskning och utveckling som ni gör. Keep up the good work!

iQ-Pilot & iQ-Mobility. These are two recently finished projects co-funded by the Strategic vehicle research and innovation programme (FFI). The focus of the projects was development of new technology to realize flexible, energy-efficient transport solutions in cities. Several proof-of-concept prototypes have been developed and demonstrated, including autonomous buses and a smart coordination system for bus fleets. The research results were presented in a webinar earlier this week. These results are the joint efforts of Scania, Ericsson, INIT, Veoneer, Royal Institute of Technology (KTH) and Örebro University. 

Human interaction with autonomous minibuses. Tom Ziemke’s research group at Linköping University, in collaboration with researchers at VTI, will during the autumn start a new research project on people’s interaction with autonomous minibuses on campus. The research will focus on method development and empirical studies of how pedestrians, bicyclists and car drivers interact with the buses. A two-year postdoc position is available via this link (application deadline: August 5). For more information contact Tom Ziemke (tom.ziemke@liu.se).

GLAD – Goods delivery under the Last mile with Autonomous Driving vehicles. Small autonomous electric delivery vehicles (ADV) are expected to transform transportation of goods under the first and last mile. The advantages are increased transportation and energy effectiveness, but it is also important that these vehicles are safe and accepted in society. The aim of the GLAD project is to develop an initial knowledge base on efficiency, safety and human experience of ADVs for the first and last mile delivery of goods in Sweden, and on how to create a balance between these three aspects from a socio-technical perspective. To achieve this, the project will utilize Zbee vehicles that will be adapted in terms of vehicle design and autonomous vehicle behaviour, human-machine interface, teleoperation and vehicle management. The overall goal is to develop knowledge that accelerate introduction of new efficient goods delivery in our society and contributes to meeting the goals of Agenda 2030. This will be assured also by connecting a licentiate candidate to the project. The project is co-funded by Trafikverket and involves RISE, Halmstad University, Aptiv, Combitech and Clean Motion. It started in June 2020 and will run for ca 2 years. For more information contact azra.habibovic@ri.se.

Tactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation. Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving. However, previous approaches only output decisions and do not provide information about the agent’s confidence in the recommended actions. This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous driving. A method for classifying whether or not an action should be considered safe is also introduced. The performance of the ensemble RPF method is evaluated by training an agent on a highway driving scenario. It is shown that the trained agent can estimate the uncertainty of its decisions and indicate an unacceptable level when the agent faces a situation that is far from the training distribution. Furthermore, within the training distribution, the ensemble RPF agent outperforms a standard Deep Q-Network agent. In this study, the estimated uncertainty is used to choose safe actions in unknown situations. However, the uncertainty information could also be used to identify situations that should be added to the training process. The paper will be presented at the Intelligent Vehicles Symposium (IV) in October 2020, and a preprint is available on arXiv. The code that was used is also available on GitHub For more information, contact Carl-Johan Hoel (carl-johan.hoel@volvo.com) at Volvo Autonomous solutions. This work was partially supported by the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP), funded by Knut and Alice Wallenberg Foundation, and partially by Vinnova FFI.

Autonomous Mapping of Unknown Environments Using a UAV. As part of the research conducted within the project LASH-Fire (Eu-Horizon 2020, No.814975), RISE supervised the work of Chalmers students developing an automatic object search for indoor environments using a flying drone. At the core of this system a reinforcement learning (RL) algorithm was implemented for the drone to navigate, detect obstacles, recognize objects and explore the environment. This machine learning (ML) project marks a starting point for further development towards an autonomous identification and surveillance solution in a wide range of study cases where cargo ships, like the ones studied in LASH-Fire, are an ideal target application. A modularized approach was used targeting research areas such as obstacle avoidance, object detection & recognition, simultaneous localization and mapping, etc. The exploration module was specially challenging and will require further work but the project in general was successful in providing a methodology and tools when using flying drones for indoor environments. The Master’s thesis was conducted by Erik Persson and Filip Heikkilä, and is available via this link. For more information contact boris.duran@ri.se

Projektet ESPLANADE, som började 2017 och avslutades sista mars 2020, handlade om hur man visar att ett automatiserat fordon är säkert. Det finns flera problem som måste hanteras för att man ska kunna göra en komplett säkerhetsargumentation. Projektets resultat inkluderar därför nya metoder för säkerhetsargumentation för en ADS, några av dessa är: 

  • En process för säkerhetsanalys samt designprinciper för interaktionen när en människa överlämnar kontrollen över ett fordon till en ADS eller tvärtom. Processen innehåller existerande metoder som sekvensdiagram, orsak-konsekvensanalys och felträd, men applicerade på människa-maskininteraktion istället för enbart tekniska system
  •  Hur man definierar den operativa designdomänen (ODD) för en ADS utgående från önskade användningsfall, vilket innebär en definition av parametrar inom vilka en ADS-funktion är avsedd att fungera, samt strategier för att säkerställa att fordonet håller sig inom sin ODD.
  • En metod (kallad QRN) för riskanalys och framtagande av säkerhetsmål. Till skillnad från vanliga riskanalysmetoder bygger den inte på analys av specifika situationer utan på definition av acceptabel frekvens av incidenter med olika allvarlig konsekvens, och en mappning av incidenter till olika klasser av konsekvenser. Säkerhetsmålen uttrycks så att man säkert hamnar inom acceptabla frekvenser.
  • Ett ramverk för formell och systematisk hantering av säkerhetskrav med en kombination av åtgärder under utveckling och under drift, bland annat baserat på modeller av osäkerhet.
  • Användning av metoden funktionsanalys för att distribuera beslutsfattande på en ADS-arkitektur samt framtagande av säkerhetskrav.
  • Säkerhetskontrakt och komponentbaserad design för att underlätta kompletthetsbevisning i kravnedbrytning, möjliggöra kontinuerlig produktuppdatering, samt kunna uttrycka säkerhetskrav för sensorsystem som inkluderar kamera, radar mm.

En publik rapport och länkar till de flesta av projektets publikationer finns på projekthemsidan.

Prepare Ships Project. Running for 26 months, the H2020 project “Prepare Ships”, funded by the European Global Navigation Satellite System Agency (GSA), was successfully started in December 2019. The 5 consortium partners, coming from 3 European countries have developed a machine learning based future position prediction for ships in order to avoid ship collisions and close quarter situations as well as reducing environmental impact by more advanced decision making. In a RTK (Real Time Kinematic) software solution, it will both exploiting the distinguished features of Galileo signals as well as combining it with other positioning and sensor technologies. It will use the next generation maritime communication techniques VDES and the new suit of IALA Standards (S100) on sea charts. The innovation developed during the project can make more autonomy of navigation feasible by exchanging future positions and allow eased decision making on ships, suitable to become an international game changer for the future of autonomous shipping. The demonstration and testing will be done onboard three different vessels in the Gothenburg archipelago. The project is coordinated by RISE with partners from across Europe, including SAAB, Lantmäteriet, Telko and Anavs. For more information check out our homepage, join our linkedin group or contact Johannes Hüffmeier at RISE (johannes.huffmeier@ri.se).  

How do you ensure safety of autonomous shipping? Today’s risk assessment methods, application of methods and models used in shipping are usually based on humans being directly in charge of ships, VTS, port controls, etc. and may not be sufficient to reflect and evaluate the complexities and inherent risks of introducing further automation and digitalization in the shipping domain. The introduction of smart ships will create traffic situations between manned and unmanned ships where on one hand decisions and actions are based on algorithms and on the other hand by a human operator where a large part of the decision making. Increasing the level of automation implies that the goal-based standards for shipping need to be based on a risk assessment that reflects the expected roadmaps towards more smart ships and so far, research on autonomous transportation has focused on other parts than the effect of introducing and mixing different levels of automation and only very basic standards have been proposed by classification societies, where DNVs standards [DNV, 2018] have two pages in the appendix on basic set-ups for testing and validation. The main objective of the RFAF project financed by Trafikverket is to analyse how autonomous navigation can be proven to be safe. The aim of the project is to perform a simulator-based risk identification for autonomous shipping traffic. Increasing the level of automation implies that the goal-based standards for shipping need to be based on a risk assessment that reflects the expected roadmaps towards autonomy. Based on two use cases, the routes Fredrikshamn-Göteborg and crossing of the Ljusterö fairway, relevant risks are identified based on ship simulations performed by mariners describing especially nautical challenges for more autonomous shipping resulting in a common risk model. The project lasts from January 2020-December 2022. There are 3 project partners with RISE as coordinator. For more information visit the project website or contact Johannes Hüffmeier (johannes.huffmeier@ri.se).

The SWEA-financed (Energimyndigheten) Data-driven Optimised Energy Efficiency of Ships is a national project involving 7 ship owners, 3 companies from the supply chain and RISE, lasting for 16 months. The data analysis of energy consumption is often complex and there are different driving forces for decisions. However, increased data collection can be unprofitable if you do not have methods to analyze the complex systems. Developments within machine learning provides new opportunities to develop both technically and economically powerful tools energy efficiency. Even today, to some extent, economic driving is applied, for example. eco-driving, however, the effect is in many cases limited as decision-making is more complex than the operator / navigator can see. Also, not always available incentives and motivation of individuals to reduce energy use. However, data collection is increasing both quality review and analysis are not performed to the same extent. Using the results of the project’s data collection and analysis, recommendations can be given about which tools which can be developed in a next step, such as: a) nudging, decision support system or autopilot for ECO driving, b) route optimization based on the ship’s accelerations and motions, and c) decision support based on statistics or real-time analysis of data to identify optimal operation (parameters such as sea state, current, speed, load condition, etc.). The objectives of the project are to: a) Achieve reduced energy use on the project’s vessels by 10–35% both at quay and in sea operations, b) Demonstrate potential with machine learning of operational data, and c) Demonstrate the possibility that better operational data may form the basis for the development of generic energy efficiency tools for smaller vessels in commercial traffic. For any details on the project, reach out to Johannes Hüffmeier (johannes.huffmeier@ri.se).

Photonics Private Public Partnership Roadmaps for EU’s next Framework Program Horizon EuropéThe area of photonics for automotive applications is a significant area which includes not only photonics sensors for the EU defined topic Mobility and Safety for automated Road Transport. Photonics also plays a role in the path towards the targets of Zero Emission Road Transport, Clean Energy Transition, and the Industrial Battery Value Chain. The work of defining the Strategic Research Agenda (SRA) in the specific area of Photonics with EU industrial partners, universities and research centers is performed through the EU technology platform ”Photonics21”, which is funded by the EU commission. The current roadmap for Photonics was published in the document: “Europe’s age of light! How photonics will power growth and innovation, Strategic Roadmap 2021–2027” The section on Automotive and Transport can be found in section 3.9. The coordinator of the whole Photonics 21 is done by VDI Technologiezentrum GmbH in Düsseldorf, Link. We believe this is important as there are a lot of EU research money at stake. The current recommendation by the European Parliament for the whole Horizon Europe budget 2021 -2017 is €120 Billion. The research funding will be divided among many topics where Climate, Energy, and Mobility is one of the clusters. There is a large Swedish interest in the cluster and cooperation with industry is one important factor in the program. Most, if not all, of the European automotive industry are usually involved in at least selected programs.

Now, based on feedback from the new European Commission, the board of Photonic21 have decided to reshape the roadmap and as a consequence automotive & transport will henceforth be combined with the topics of climate and energy. Besides merging the different topics in one document, this gives us an opportunity to revise the previous document into something that we believe should support our industry even better, considering that the current document was prepared in 2018 and the present situation the industry is facing. We want to ensure that the guiding document capture the specific needs of the automotive industry. The aim of the work is to define the research topics of the Strategic Research Agenda (SRA) which will define the upcoming calls in the Horizon Europe program. 

We now invite comments on the current chapter and roadmap (provided in the link above). Determined by EU commission schedules this work has to be completed on 4 September, why we need your input no later than 24 August 2020. We ask for specific text suggestions and specific roadmap suggestions (compare with p. 140 in the above mentioned Strategic Roadmap). Please forward your suggestions to Jan-Erik Källhammer at jan-erik.kallhammer@veoneer.com. He acted as chair of the group Automotive and Transport in the current roadmap and now act as co-chair of the new group Climate, Energy, and Mobility together with Dr. Heinz Seyringer of V-Research GmbH in Austria. 

Säve flygplats blir testbana

Volvokoncernen har ingått ett tre år långt avtal med fastighetsbolaget Castellum om att använda den gamla landningsbanan på Säve flygplats utanför Göteborg som testbana [1]. Tanken är att testa eldrivna och automatiserade tunga fordon där med planerad start under våren. 

Källor

[1] Soxbo, S. Expressen. Flygplats blir testbana för självkörande fordon. 2020-03-16 Länk

Svensk forskning: Framtiden är ljus

MICA. CoEXist. SMART. PLATT. PRoPART. PERCEPTRON. PRELAT. DENSE. Barmark. BRAVE, HATric. Ja, så heter några av projekten som ni har äran att läsa om i årets sista sammanställning av relevant svensk forskning. För varje gång blir jag mer och mer imponerad av vår forskning och forskare. Det är fantastiskt att se hur mycket görs i vårt ”lilla” land, och det här är nog bara en bråkdel av det hela! Vi behöver bara bli bättre på att sprida våra resultat, och jag hoppas att OmAD bidrar till detta. Något annat vi behöver bli bättre på är att koppla samman våra projekt till en helhet och visa hur de leder till positiva samhällsförändringar. Kanske ett lämpligt nyårslöfte?

Stort tack till er alla som bidragit till den här sammanställningen! Det hade inte varit möjligt utan era bidrag och engagemang.

Modeling driver behavior in interactions with other road usersDriver models help improve and evaluate systems for road crash mitigation and avoidance. As systems develop and address increasingly complex scenarios. Driver models also need to be developed to be able to account for the interactions among these road users. Even as we improve driver modeling with control-theory models and actual data-driven implementations, existing driver models fail to sufficiently take interaction among road users into consideration. This paper addresses this insufficiency by proposing a new operational framework to computationally model interactions among road users. For this purpose, we introduce a definition for interaction among road users. The modeling framework is demonstrated by a specific driving scenario: the overtaking of a cyclist when an oncoming vehicle may be present. In this scenario, modeling driver interaction using Unified modeling language within our framework can lead to improved crash mitigation and avoidance through tailored system activation of automated emergency braking. This is a paper that will be presented at TRA-conference next year. The work was partly carried out at SAFER and within the FFI-project Modelling Interaction between Cyclists and Automobiles (MICA). For more information contact Prateek Thalya at Veoneer (prateek.thalya@veoneer.com).

Researchers from Veoneer have also published several other relevant papers, contact Ola Boström (ola.bostrom@veoneer.com) at Veoneer for more information: 

  • Occupant activities and sitting positions in automated vehicles in China and Sweden – The 26th International Technical Conference on the Enhanced Safety of Vehicles (ESV)
  • Passenger Car Safety Beyond ADAS: Defining Remaining Accident Configurations As Future Priorities Conference: The 26th International Technical Conference on the Enhanced Safety of Vehicles (ESV)
  • Intersection AEB Implementation Strategies for Left-Turn Across Path Crashes – Traffic Injury Prevention (ADAS)
  • A Model of Indian Drivers’ Ratings of In-Vehicle Alerts to Pedestrian Encounters on Roads in India, for presentation at the coming Human Factors and Ergonomics Society’s 2019 International Annual Meeting
  • Benefits of intuitive auditory cues for blind spot in supporting personalization; ESV2019
  • Adaptive Transitions for Automation in Cars, Trucks, Busses and Motorcycles; Intelligent Transport Systems (got invited for a journal track after the ITS World Congress)
  • How do oncoming traffic and cyclist lane position influence cyclist overtaking by drivers? – Shown at ICSC and submitted to AAP journal
  • Radar Interference Mitigation for Automated Driving – IEEE Signal processing magazine
  • How do drivers negotiate intersections with pedestrians? Fractional factorial design in an open-source driving simulator – AAP
  • Modelling discomfort: How do drivers feel when cyclists cross their path? – AAP

Driver/passenger activity mapping. FFI funded DRAMA project (2018-2020) addresses knowledge building around activity identification of drivers and passengers in vehicles to improve interaction between them and the vehicle. Mapping and detecting activities at drivers and passengers is important for both UX and traffic safety. With knowledge about activites, the HMI can be adjusted to, the currently most efficient modality. If the vehicle knows the body posture of the passengers safety functions such as airbags, brakes and steering system can be adjusted by the safety systems in the vehicle. The project develops a system that can recognizes individual and interaction activities of driver and passengers in vehicles of high level of automation (SAE3+). The project studies from literature the most relevant activities of driver and/or passenger in highly automated vehicles in terms of safety and comfort. The developed prototype acquires input data from multiple cameras mounted in the cabin of a vehicle and classify the detected activities according to the chosen in-cabin activities of interest. Machine learning algorithms are used to extract timeseries of activity features including: Body poses, head position/eye gaze/face landmark, objects, dense optical flow, and detected activity/interaction. The work is a collaboration between RISE AB and Smart Eye AB. For more information contact Thanh Hai Bui (thanh.bui@ri.se) at RISE, or Henrik Lind (henrik.lind@smarteye.se) at Smart Eye AB.

Mimicking professional bus drivers. Scania and KTH Royal Institute of Technology are currently researching motion planning algorithms for autonomous buses driving in cities. The research has so far discovered that current motion planning approaches, which are suitable for passenger vehicles, are not successful at driving buses in cities. The problem arises due to the large dimensions of buses, but mostly due to the particular chassis configuration, where the wheelbase length is much shorter than the vehicle length, resulting in large vehicle overhangs. The research then focuses on how to use these overhangs to increase the maneuverability of buses driving in cities. The result is a new motion planning approach which allows buses to briefly drive with the overhangs outside of the road and over curbs, in order to drive along narrow roads and sharp turns, while ensuring the safety of the drive. The first results of this work have been recently published in the Intelligent Transportation Systems Conference 2019. The paper can be accessed via IEEE here, or arXiv here, and a video of the results here. This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. For more information contact Rui Oliveira (rui.oliveira@scania.com) from the KTH Royal Institute of Technology.

CoEXist is a European project (May 2017 – April 2020) which aims at preparing the transition phase during which automated and conventional vehicles will co-exist on cities’ roads. CoEXist aims at enabling mobility stakeholders to get “AV-ready” (Automated Vehicles-ready). To achieve its objective, CoEXist have developed an assessment framework including both microscopic and macroscopic traffic models that take the introduction of automated vehicles into account. The tools developed in the framework of CoEXist are tested by road authorities in the four project cities: Helmond (NL), Milton Keynes (UK), Gothenburg (SE) and Stuttgart (DE) in order to assess the “AV-readiness” of their local-designed use cases. Swedish partners in the CoEXist project is VTI and the City of Gothenburg. Preliminary results from the traffic modelling show decreases in traffic performance in an introductory stage with lower penetration rates and AVs with limited capabilities and cautious driving logics while higher penetration rates of more advanced AVs leads to a modal change from public transport to private cars. Final event will be held in Milton Keynes (UK) on 25-26 March 2020, Homepage: https://www.h2020-coexist.eu/. Contact Johan Olstam (johan.olstam@vti.se) for more information.

SMART. The aim of the SMART project (Simulation and Modelling of Automated Road Transport) is to enhance and further develop todays state-of-the-art traffic models in order to enable analysis of future traffic systems. The project consists of two PhD projects, one focusing on microscopic traffic simulation and the behaviour of and interaction between conventional and automated vehicles, and one focusing on mesoscopic simulation and fleets of automated vehicles for public transport operations. The licentiate thesis Simulation based evaluation of flexible transit was presented by the PhD student David Leffler on June 13th, 2019. The project is carried out by VTI, KTH and LiU and is funded by Trafikverket via Centre for Traffic Research (CTR). Contact Johan Olstam (johan.olstam@vti.se) or Wilco Burghout (wilco@kth.se) for more information.

PLATT – Policylab för Autonoma Transporttjänster. Inom ramen för DriveSweden (Vinnova) har PLATT har Volvo GTT, Einride, Combitech och RISE bedrivit policyutveckling tillsammans med offentliga och kommersiella aktörer inom transportnäringen. Därigenom har vi identifierat en rad utmaningar som de sökande står inför. Det handlar både om att kunna budgetera för ansökan i form av kostnad och ledtid men också hur man vet vad som ska ingå i en ansökan. Men vi har också sett en rad olika strategier för att hantera den osäkerheten. Dels beprövade strategier som använts både specifikt inom fordonsutvecklingen och generellt inom svensk myndighetsutövning, dels nya strategier som sätter fingret på hur man kan hantera säkerheten vid införande av ny teknologi utan att hämma innovationstakten. Genom att bjuda in brett till projektets aktiviteter har vi också samlat på oss många praktiska tips på hur man som sökande både kan påverka hur lång tid det tar att få igenom en ansökan men också mängden arbete man behöver lägga ner på en framgångsrik ansökan. Tipsen belyser också aspekter som inverkar gynnsamt på hur försöksverksamheten uppfattas av omvärlden, t.ex. räddningstjänsten och allmänheten. Här hittar ni slutrapporten och projektets hemsida. För mer information kontakta Håkan Burden på RISE (hakan.burden@ri.se). 

Driving automation state-of-mind: Using training to instigate rapid mental model development. I takt med att automatiserade funktioner blir alltmer avancerade och vanliga, ökar också kraven på användarens (förarens) förståelse för korrekt användning. Inte förrän den mänskliga föraren helt kan ersättas kommer förarens förståelse av systemen vara en kritiskt komponent i att fordonet (människan tillsammans med de automatiserade systemen) framförs säkert på vägen. Finns det då något sätt att snabb-träna förare i hur man ska använda sådana system? Den nyligen publicerade studien ämnade undersöka just detta. Tidigare forskning inom förarträning och inlärning kombinerades till en tränings-metodik som sedan inkorporerades i ett träningsprogram ämnad att träna noviser i användningen av ett hypotetiskt förarassistanssystem motsvarande SAE Level 2. Resultaten indikerade inte bara att automations-träning av förare är möjlig, utan kanske viktigast av allt att de tränade förarna i betydligt större utsträckning var benägna att ingripa i situationer som krävde det (baserat på systemets begränsningar) jämfört med deras otränade motparter. Studien gjordes inom ramen för FFI-projekt HATrick. För mer information kontakta Martin Krampell (krampell@gmail.com).

PRoPART finalized. After 24 months of work, H2020 project „PRoPART”, funded by the European Global Navigation Satellite System Agency (GSA), was successfully closed. The 7 consortium partners, coming from 4 European countries have developed an RTK (Real Time Kinematic) software solution by both exploiting the distinguished features of Galileo signals as well as combining it with other positioning and sensor technologies. RTK gives the possibility of cm-level accuracy using correction data from reference stations. The innovation developed during the project can be a game changer for the future mass market of autonomous transport. The final demonstration was done in November at AstaZero and here you can see a movie and presentation material. The project was coordinated by RISE with partners from across Europe, including Scania, AstaZero and Waysure. For more information contact Stefan Nord at RISE (stefan.nord@ri.se).  

PERCEPTRON är ett FFI-projekt är ett samarbete mellan Volvokoncernen, Semcon och Chalmers som avslutas nu vid årsskiftet. Målsättningen med PERCEPTRON har varit att ta fram ett koncept för kontinuerlig datadriven utveckling vilket inbegriper infrastruktur för att ta hand om loggad data, design av neurala nätverk, träning och validering. Ett resultat av projektet är tre neurala nätverk att exekvera i fordonet för objektdetektering, detektering av filmarkeringar och vägdetektering. Nätverken har tränats på insamlad och annoterad data för lastbil på svenska vägar. En översiktlig utvärdering av hårdvara och programvara för användande neurala nätverk har också gjorts för att ge vägledning åt utvecklare. För ytterligare information kontakta projektledare Carlos Camacho, Volvokoncernen.

PRELAT är ett FFI-projekt som slutar vid årsskiftet efter fem års samarbete mellan Volvokoncernen och Chalmers. Projektet har arbetat med fully convolutional neural network för fusion av kamera och lidar i syfte att uppnå robust vägdetektion och klassificering av vägmarkeringar för lateral filhållning. Ett tidigt resultat pekar på nyttan av använda lidar för snabb och noggrann vägdetektion. Ett annat resultat från PRELAT är på vilken detaljnivå fusion av kamera och lidar bör utföras. Slutligen är ett tredje resultat hur semi-supervised training kan utformas i syfte att minska mängden kostsam annotering. PRELAT och PERCEPTRON har varit en del av den snabbt expanderande utvecklingen och användningen av neurala nätverk inom fordonsindustrin. Resultaten har bidragit med ökad förståelse och kommer att användas i framtida projekt i Volvokoncernen. För ytterligare information hänvisas till projektledare Martin Sanfridson, Volvokoncernen

Universally designed mobility for increased accessibility to societal functions. A consortium of organisations in West Sweden (Västra Götalandsregion, Västtrafik, RISE, Norconsult Astando AB, with user organisations SRF and DHR) have collaborated on a number of projects with the vision of working towards autonomous and universally designed mobility for increased accessibility to societal functions. A series of projects performed by the consortium have explored the following subjects:

  • Samverkande system för sjukresor och sjukhus (eng. Cooperative systems for medical journeys and hospitals). How a System-of-systems approach can be utilised to bridge accessibility gaps when making service journeys between public transport and hospital departments. (funded by Vinnova FFI)
  • Autonoma skyttelbussar för ökad tillgänglighet till viktiga samhällsfunktioner (eng. Autonomous shuttle busses for increased accessibility to important societal functions). Pre-study for a trial of autonomous shuttle-busses at Sahlgrenska Hospital in Gothenburg. (funded by Västra Götalandsregion kollektivtrafiknämnden)
  • Guidning till autonoma fordon för blinda, döva och dövblinda (eng. Guidance to autonomous vehicles for persons with blindness, deafness and deaf-blindness) Guiding for journeys with autonomous vehicles for people with blindness, deafness and deaf-blindness. (funded by Drive Sweden – Vinnova, Energimyndigheten och Formas)

A combination of methods including design-thinking workshops, user-trials, field studies, service-design methods and innovation processes have been utilised to ensure that user needs have been clearly understood and taken into consideration in design of potential solutions. The studies have resulted in increased understanding of the needs of users with visual impairments in autonomous transport systems and how public authorities can contribute to designing services that reduce barriers to independent travel. A large number of service improvements and solutions have been identified. Methods for using vibro-tactile communication to guide users with visual impairments to public transport have been evaluated. A plan for a one year test of autonomous busses in a hospital environment is undergoing an approval process within the regional authority. The insights gained from these projects have already begun to create value. Many solutions can be applied to existing public transport solutions. However to create future transport solutions which are created with accessibility for all from the outset, the results require more communication for example to vehicle manufacturers, city and public transport planners and more. For more information contact Steve Cook at Norconsult (Steve.Cook@norconsult.com). 

What happens to self-driving cars if the weather turns bad? Current systems offer comfort and safety in good weather. However, they often fail to sense its surroundings in visibility conditions with heavy rain, snow or fog causing the automated systems to stop their support. The DENSE project, under the ECSEL joint undertaking and co-financed by EU and national funding bodies, addresses this key challenge of autonomous driving by developing an environment perception technology that extends the performance of sensors in adverse visibility conditions. The project designs, tests and validates a generic sensor suite that enables driver assistance systems and autonomous driving systems to operate also in adverse weather. The DENSE 24/7 all-weather sensor suite combines Radar, Short-Wave Infrared (SWIR), gated camera sensor, and LIDAR. In addition, a mobile Road State Sensor assesses the road surface conditions. For maximizing efficiency, DENSE implements a high-level fusion platform integration between the individual sensors. DENSE use artificial neural networks to fuse all sensor information at pixel level, leading to an enriched and enhanced multi-spectral image. The system has been integrated in a test vehicle and demonstrated under controlled conditions in a weather chamber and evaluated under real-life conditions in Central and Northern Europe. Project duration is between June 2016-February 2020. There are 15 project partners with Daimler as coordinator. For more information visit the project website or contact Jan-Erik Källhammer at Veoner (jan-erik.kallhammer@veoneer.com).

Projekt Automatiserad vägdrift med kortnamn ”Barmark” har som målsättning att genom automatisering av drift- och underhållsfordon bidra till förbättrad arbetsmiljö, ökad resiliens samt minskade säsongsvariationer vid val av transportslag. Projektet tar fram ett fordon som kör och navigerar självständigt längs en definierad rutt samtidigt som det utför ett arbetsuppdrag och interagerar med omgivningen. Inom projektet sker fordonsanpassning exv. av bromssystem, midja och EHI styrning, utveckling och anpassning av sensorsystem exv. drönarburna radarsystem, ultraljud, GPS/Video samt utveckling och anpassning av webbaserad front-end med loggning av fordon med förare i trafik. Vidare utförs analys av infrastruktur och testscenarier inför projektdemonstrationer som kommer utföras kommande vinter- och sommarsäsong. Projektgruppen utgörs av RISE, Semcon, CIT, Peab, Swevia, Skanska, Svensk Markservice, Trafikverket, Alkit, Teade, AstaZero och Lundberg Hymas, där RISE är koordinator. Projektet pågår 2018-05-01 till 2020-08-30 och finansieras av det strategiska innovationsprogrammet InfraSweden2030, en gemensam satsning av Vinnova, Formas och Energimyndigheten samt av projektpartners. For mer information kontakta Viveca Wallqvist på RISE (viveca.wallqvist@ri.se). 

Användargränssnitt för att upptäcka oskyddade trafikanter I syfte att förbättra tilltro och acceptans för SAE nivå 3. I EU-projektet BRAVE, Bridging gaps for the adoption of Automated VEhicles som koordineras av VTI, Statens väg- och transportforskningsinstitut, bedrivs forskning för att bidra till förbättrad säkerhet och acceptans av automatiserade fordon. I projektet har VTI under hösten genomfört en studie i körsimulatorn Sim IV på Lindholmen i Göteborg. Bakgrunden till studien är att implementering av automatiserade körsystem på SAE nivå 3 i urbana miljöer utgör en utmaning, i det att återkommande och svårförutsägbara interaktioner mellan fordon och oskyddade trafikanter behöver hanteras. För att adressera utmaningen har projektet utvecklat ett koncept för användargränssnittet som håller föraren informerad om närvaron av oskyddade trafikanter i den närliggande omgivningen. Genom att göra denna typ av information tillgänglig för föraren ges hen möjlighet att avsluta uppgifter av sekundär karaktär, såsom att se på film och liknande, och i samarbete med systemet övervaka körningen fram till dess att det är säkert att återgå till sekundära uppgifter. I körsimulatorstudien fick deltagare med och utan erfarenhet av supportfunktioner på SAE nivå 2 köra i en urban miljö samtidigt som dom kunde titta på film. Nivån av information angående oskyddade trafikanter varierades över fyra betingelser: (1.) ingen information, (2.) en varning för att förmå föraren att återta kontroll när en kollision var nära förestående, (3.) en förvarning som meddelade om närvaron av oskyddade trafikanter, samt (4.) kombination av varnings- och förvarningskoncepten. Studiens resultat visar att en strategi för användargränssnittet som integrerar förvarnings- och varningsmeddelandet är den lösning som är att föredra för att förbättra säkerheten, samtidigt som förarens tilltro till systemet förbättras. Vidare visade studien att tidigare erfarenhet av SAE nivå 2 är avgörande för om strategin fungerar eller inte. Resultaten stödjer design av användargränssnitt för automatiserade körfunktioner baserat på behov, preferenser och förmågor hos förare för att säkerställa bättre acceptans och säkerhet. För mer information om projektet kontakta Niklas Strand, Ignacio Solis Marcos eller Ingrid Skogsmo på VTI eller se www.brave-project-eu eller följ projektet på Twitter @BRAVE_H2020 

Resultat från MAN:s platooningtester

MAN har kört platooningtester med två lastbilar i Bayern; de har sammanlagt kört 39 000 km på Autobahn mellan München och Nürnberg. Bilarna höll ett avstånd på 15-20 m mellan varandra via vad man kallar en ”elektronisk dragstång”. Den första bilen är manuellt körd medan de bakom följer automatiskt men med förare i hytten [1]. I nästa steg tänker MAN att minska avståndet till ca 10 m.

Resultaten var blandade: visserligen hade systemen en ganska bra tillförlitlighet (98%) och förarna litade på systemet, men samtidigt så blev inte bränslebesparingen den förväntade. Det sägs bero på alla störningar som sker i verklig trafik, så som regn, vägarbeten, motorvägskorsningar etc. Typiskt måste fordonståget lösas upp vid varje sådan störning, ett skäl till att konkurrenten Mercedes sagt sig ge upp tankarna på platooning. Samtidigt har Ford Otosan (en turkisk lastbilstillverkare som samägs av Ford Motor Company och Koç Holding) och AVL startat tester med platooning i Turkiet [2], liksom Hyundai i Korea.

Egen kommentar

Platooning eller inte? Tekniken är kanske inte jättesvår men samtidigt verkar det som att de ekonomiska vinsterna inte är så stora heller. Så för lastbilstillverkarna finns det kanske lägre hängande frukter, som t.ex. autonom körning i gruvor eller i hamnar (t.ex. Scania och Volvo/UD Trucks).

Källor

[1] Peter Maahn, Maximiliane Reichhardt: Platooning: MAN stellt Testergebnisse vor, Automobil-Industrie 2019-11-26 Länk

[2] Tara Craig: Ford Otosan and AVL take next AV step, Autonomous Vehicle International 2019-11-08 Länk