AdaptIVe

From FOT-Net WIKI
Jump to: navigation, search
Contact details

Aria Etemad

Volkswagen Group Research

Aria.etemad@volkswagen.de

Timing and duration of tests

Project started in January 2014 and will be finished by mid-2017. Evaluation test are conducted from September 2016 on

Location(s) of tests

Test location for technical and User-related assessment

  • Test tracks: Orbassano (I) / Hällered (S) / Aachen (D) including parking garage in Aachen
  • Open roads (not finally decided): Areas close to Aachen (D), Orbassano (I), Frankfurt (D), Gothenburg (S), Munich (D), Wolfsburg (D)

Impact Assessment as well as the in-traffic assessment is mainly simulation

Tested automation

Tested functionalities

Close distance, Urban scenarios, Highway scenarios

Overall 21 functions are developed

Level of automation tested

SAE 2 up to SAE 4 level

Tested use cases

AdaptIVE tested use cases.png

Tested transport system

Passenger cars / truck

Purposes of testing
  • Assessment of driver behaviour (human, vehicle) / road user behaviour
  • Assessment of impacts on environment (short-term, long-term)
  • Assessment of impacts on safety (short-term, long-term)
  • Assessment of impacts on traffic efficiency/mobility (short-term, long-term)
  • Assessment of user (driver, traveller, etc.) acceptance, usability, take up, etc.
  • Interaction with other traffic participants (automated vehicles, conventional vehicles, vulnerable road users)
  • Technical assessment, proof of concept (incl. vehicle, background support systems such as communication)


Methodology

Definition of baseline

Depends on type of assessment. As a general rule: ‘Normal’ driving (without automated system)

Technical Assessment

  • Objective is a collision free traffic
  • Operation in mixed traffic conditions (-> not disturbing normal traffic)

-> The functions have to be operated within range of normal driver behavior (and w.r.t. safety even beyond)

User-related assessment:

  • Driving without the system under assessment

In-traffic assessment:

  • Simulation without the system under assessment

Impact assessment:

  • Simulation without the system under assessment
Test design
  • Technical assessment Tests tracks and small field test: 34 research questions
  • User related assessment: (simulation), tracks experiments and open roads experiments: 30 research questions. Observation of driver behaviour and performance / questionnaires
  • In traffic assessment: numeric simulation
  • Impact assessment: simulation on traffic scenario level (high number of vehicles) and driving scenario (few vehicles in a certain driving simulation) level

Overview is provided below: AdaptIVE test design.png

Method of testing

Controlled field tests, Driving simulator, Naturalistic field tests, Questionnaires, Simulation, Test track


Test fleet, participants and environment

Number and make of vehicles

8 demonstrators

Description and number of participants/drivers

Will depend on test design, type of assessment and tested functions. Say, at first glance 20-30 participants for user-related assessment

Tested environment and facilities

Event based functions:

  • Test tracks / controlled environment ( parking)

Continuously operating functions:

  • Pre-tests on test track
  • Open / public roads
Legal and ethical aspects

Similar to any other types of experiments

Duration of testing

To be defined, depending on types of assessment

For the technical assessment on public roads the test length is calculated considering the measured frequency of certain driving situations and desired number of situations for the evaluation.

Input parameters and assumptions of simulation tests

Distributions from - accident data - traffic data - driver behaviour data - traffic data - infrastructure data - ...

Simulation model of the function under assessment

Simulation approach for the safety impact assessment:

AdaptIVE simulation.png

Data

Logging
  • CAN
  • GPS
  • HMI
  • In-vehicle cameras
  • Map data
  • Other cameras
  • Sensor data
  • Situational data (e.g. weather, traffic situation)
  • System internal data
Specifications for the data sources

Communication data would be logged, if relevant. Situational data will be derived by camera.

Key Performance Indicators (KPIs)

Overall more than 100 of them. However, it depends, which hypotheses are tested in the end. The test and evaluation plan provides and general overview on hypotheses. For the assessments certain hypotheses are picked.

For the impact assessment the main PI are:

  • Number of accidents / critical situations
  • Frequency of accidents / critical situations
  • Severity of accident / critical situations
  • Mean Fuel consumption
  • Mean velocity
  • Travel time / Manoeuvre time
Situational data available

Data from technical and user-related assessment

Access to different databases

Subjective data collected

Questionnaires or psychological scales to be filled for user related assessment (trust, reliance, mental representation, locus of control, stress, boredom, fatigue, situation awareness, usability, acceptance, willingness to have and pay, etc.)

Results

Issues that affected the impact assessment

On course

Results

On course

Publications

On course

Other things to report

AdaptIVe considers four different types of assessment (see overview below), which makes it hard to fill in the questionnaire in detail. Sometimes it is also not clear, to which type of assessment the questionnaire refers. Maybe it would be good to have more detailed discussion about the assessment in Adaptive (-> contact Felix Fahrenkrog, ika). AdaptIVE other.png

Facts about "AdaptIVe"
Method of testingControlled field tests +, Driving simulator +, Naturalistic field tests +, Questionnaires +, Simulation + and Test track +
Purpose of testingAssessment of driver behaviour (human, vehicle) / road user behaviour +, Assessment of impacts on environment (short-term, long-term) +, Assessment of impacts on safety (short-term, long-term) +, Assessment of impacts on traffic efficiency/mobility (short-term, long-term) +, Assessment of user (driver, traveller, etc.) acceptance, usability, take up, etc. +, Interaction with other traffic participants (automated vehicles, conventional vehicles, vulnerable road users) + and Technical assessment, proof of concept (incl. vehicle, background support systems such as communication) +