Aria Etemad, Ford, euroFOT: European large-scale Field Operational Test on Active Safety Systems
description
Transcript of Aria Etemad, Ford, euroFOT: European large-scale Field Operational Test on Active Safety Systems
www.eurofot-ip.eu
euroFOT:European Large Scale Field Operational Test on In-Vehicle Systems
Bringing Intelligent Vehicles to the Road
Giancarlo Alessandretti, Angelos Amditis, Aria Etemad, Christoph Kessler
Stockholm, ITS 2009
www.eurofot-ip.eu2 ITS 2009 Stockholm
Contents
• The euroFOT projectObjectives, functions, expected results
• Highlights for on-going activitiesResearch hypothesesData acquisition Design of experimentOperation of Vehicle Management CentresData analysis plan
• Lesson learnt and conclusions
www.eurofot-ip.eu3 ITS 2009 Stockholm
Why EuroFOT?
• Intelligent Vehicles have a large potential for safer, cleaner and more efficient transport solutions
• Technologies are mature (several examples in series production)
• However, we have limited data on real-life operation and how drivers use the systems in ordinary traffic
• This restricts our capabilities to improve the systems, understand their impacts and make the right decisions for deployment
www.eurofot-ip.eu4 ITS 2009 Stockholm
euroFOT Objectives• Perform multiple coordinated tests of Intelligent
Vehicle Systems with ordinary drivers in real traffic
• Investigate performance, driver behaviour and user acceptance
• Assess the impacts on safety, efficiency and the environment, based on road data
www.eurofot-ip.eu5 ITS 2009 Stockholm
euroFOT Objectives (2)• Consolidate a common European approach for FOTs • Improve public awareness on the potentialities of
driver support functions
www.eurofot-ip.eu6 ITS 2009 Stockholm
Functions under test
www.eurofot-ip.eu7 ITS 2009 Stockholm
Exposures in different FOTs
Nr. vehicles1 10 100 1000
4
8
12
16
0
FOT
dura
tion
(mon
ths)
100 car2004
Ass.driverNL_2006
RDCW – 2005ACAS2004
Australia2005
ICC 1997
Mach2005
Freightliner 2001
Volvo trucks
Isa_UK2007
EuroFOT
euroFOT-trucks only
trucks
cars
Within euroFOT:~18,5 Mil. kmWithin euroFOT:~18,5 Mil. km
www.eurofot-ip.eu8 ITS 2009 Stockholm
The challenges....
• Wide range of driving conditions • Extraction of meaningful use cases / driving scenarios
for the equipment under test• Transferable and harmonized methods Europe-wide• Data quality assurance • Privacy and legal issues
www.eurofot-ip.eu9 ITS 2009 Stockholm
.... and the euroFOT approach
• Well developed ADAS and sensors on vehicles• Reliable Data Acquisition systems based on partners’
experience • Harmonised research questions / hypotheses for all
fleets • Common definition of scenarios
and performance indicators: specific approaches when necessary
• Framework of guidelines for the operation of the different Vehicle Management Centres
www.eurofot-ip.eu10 ITS 2009 Stockholm
Project plan
www.eurofot-ip.eu11 ITS 2009 Stockholm
Highligths for on-going activities
www.eurofot-ip.eu12 ITS 2009 Stockholm
Harmonised requirements for systems and functions
The FESTA methodology has been applied:• Approx. 250 hypotheses examined• 84 hypotheses prioritised• Main relevance: 44% safety, 46% driver, 10% environment• 5 Combinations of functions
www.eurofot-ip.eu13 ITS 2009 Stockholm
Research Questions & Hypotheses (example)• A research question is general, and has a question mark:
Does FCW decrease incidents?
• Hypotheses are either true or falseFCW reduces occurence of decelerations above 5 m/s2
• Hypotheses can only be tested by means of reasonable indicators
• Hypotheses are statistically testable
• euroFOT examined >100 hypotheses for FCW/ACC(only top-hypotheses selected)
www.eurofot-ip.eu14 ITS 2009 Stockholm
Data Acquisition SystemsThree types of Data Acquisition Systems are considered:
• CAN only basic functionality for vehicle data and GPS• CAN + video cameras will record both the road and
the driver • CAN + video + extra sensors some vehicles equipped
with radar/lidar, head/eye trackers and other sensing devices
ECUECU
Vehicle CAN bus
OBDconnector
GPS & GPRS Antennas multipurpose camera
radar
accelerometer
OR
Standard with vehicleMandatory part of the instrumentation (data)Optional part of the instrumentation
ECUECU
data logger
ECUECUECUECU
www.eurofot-ip.eu15 ITS 2009 Stockholm
Data Acquisition Systems
Some specific issues:
• Data enrichment by maps• Protection of proprietary data• Encryption of tha data• Driver annotation interface• Possibility of audio recording• Triggered logging• Synchronisation with GPS
www.eurofot-ip.eu16 ITS 2009 Stockholm
Design of experiment Drivers•Represent as much as possible the population of buyers•Professional drivers in the case of trucks•Perfomance compared with and without the system (Baseline)•Control group introduced for several functions
Vehicles•According to the present EU market, technical feasibility and interests of manufacturers•Middle+top class cars, heavy trucks
Environment• Specific events defined (e.g: overtaking manoeuvre)• Situation variables specified (e.g: weather, visibility, driver
status)• Performance indicators are the basis for the overall evaluation
(e.g: mean speed, mean time headway, frequency of braking,…)
www.eurofot-ip.eu17 ITS 2009 Stockholm
Eventsovertakingmanoeuvre
Scenarioovertaking in day light in low
traffic on rural road …
For euroFOT:• 25 events selected / 27 situation variables• 81 performance indicators• About 110 corresponding measures
Events and situation variablesweather
(e. g. rain)
traffic(e. g. low volume)
lighting(e. g. day light)
road type(e. g. rural road)
vehicle occupancy(e. g. 1 passenger)
www.eurofot-ip.eu18 ITS 2009 Stockholm
VMC Operations Center
MaintenanceMaintenance SalesSales Operation Center
+ HOT LINE
Operation Center
+ HOT LINE
Vehicles Drivers
Data pick-up method
Data storagemethod
Data ServerData Server
Data pick-up method
Data storagemethod
FOT Operations Data
FOT Operations Data
Data storagemethod
Driver liaison during FOT
Data/Operational Quality Assurance
ContractConsent formIncentivesInsurance
Questions / support
Training
Objective data Subjective dataIntervention logging / Documentation
Some of the aspects which required a special attention:
www.eurofot-ip.eu19 ITS 2009 Stockholm
Data analysis plan...
VMC-Fleet
SQL Database
CO-, CV-, CV+E-data
VMC-Specific Common
Questionnaires
Data Analysis
Data quality analysis
Data quality analysis
Data processingData processing
Data qualityanalysis
Data qualityanalysis
PI‐calculationPI‐calculation
Data miningData mining Testing of VMC
specific hyp
othe
ses
Testing of VMC
specific hyp
othe
ses
Global assessmentGlobal
assessment
Testing of commonhypotheses
Testing of commonhypotheses
QualityassessmentQuality
assessment
Cost Benefit Analysis
VMC
leve
l
www.eurofot-ip.eu20 ITS 2009 Stockholm
Data volumes: data acquisition & processing
103
106
109
1012
ON-BOARD OFF-BOARD
VEHICLE
FLEET(ONE VMC)
PROJECT
EVENTSEVENT
STATISTICS
PERFORMANCE INDICATORS
DATA BASES
Nr.
of d
ata
Mass storage
Reconstruction and analysis
www.eurofot-ip.eu21 ITS 2009 Stockholm
euroFOT network International collaboration
• An effective international cooperation is in place
• The main objective is to share methodologies for the design and operation of FOTs
• Focus on:Design of ExperimentsSynchronisation of performance indicatorsCommon tools for analysisComparison of results
• EuroFOT is also contributing to the definition of a common language
www.eurofot-ip.eu22 ITS 2009 Stockholm
Selected lesson learnt / conclusive remarks
• Use specific hypotheses; Prioritize hypotheses; Consider also combinations of functions
• Define a sound data analysis plan, focused on quality (events, metrics)
• Include baseline conditions • Define methods for safety analysis (crashes will be a rare,
hopefully absent event) • Anticipate how to deal with operational aspects (e.g: maintenance,
assistance to drivers, subjects drop-outs,…)• Plan pilot tests for a feedback on specifications and a check on
technical / organisational aspects
www.eurofot-ip.eu23 ITS 2009 Stockholm
The Consortium
www.eurofot-ip.eu24 ITS 2009 Stockholm
Project coordinator: Aria Etemad FORD Research & Advanced Engineering Europe Email: [email protected]