Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Systems and State-of-the–Art Evaluation

Presentation given at the IRCOBI pre-Conference Workshop on Collision Avoidance and Driver Assistance Systems - Field data, what do we have and what do we need for future research? September 10, 2013 @ Lindholmen Conference Centre, Gothenburg
by

Michiel van Ratingen

on 21 January 2014

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Systems and State-of-the–Art Evaluation

Blind Spot Monitoring
Systems and State-of-the–Art Evaluation
Road to
Accident Free Driving

Adaptive Cruise Control
Forward Collision Warning and/or Autonomous Emergency Braking
Pedestrian Detection
Speed Assistance Systems
Lane Departure Warning and/or Keeping

Crossing Assistant
Night Vision
Driver Monitoring
Market Restraints
Consumer reaction to any system “failures”
Pushback on technology
Pricing strategies – economic crisis
Lack of market incentives
Automation will be gradual and based on progressive improvements in ADAS ...

Identify key safety technologies
Promote “best practice”
Increase consumer awareness
Influence uptake
Pave the way for mandatory fitment

NCAP Agenda
System
Safety Potential
Accident Mechanism
Target
Performance
Tests & Criteria
Expected Benefit
Real-world Experience
Approach
Identify from real world data relevant crash parameters,
the role of HMI
Establish potential impact of a technology in EU-28
Determine real world effectiveness
User feedback,
False positives,
distraction levels, etc.
Evaluate suitable test devices
Design evaluation criteria and suitable procedures
Field data drives the development of the rating
(Best practice)
Michiel van Ratingen
Technical Enablers
Push for greater road safety
Need for new features
Consumers interest is growing
Prices are coming down

Growth Drivers
Market for Collision Avoidance & ADAS
Consumer Ratings
19%
of European road fatalities*
* World Health Organization Global: Status report on road safety, 2009
Pedestrian crashes
Real-world crashes
Pedestrian walks out into the path of turning car
Pedestrian walks out from behind obstruction

Pedestrian runs out from the far side
Pedestrian walks along road in the dark
Pedestrian walks from nearside

51%
14%
9%
3%
6%
Overall: going ahead 87%,
Turning 13%

54%

37%
5%
32%
7%
28%
8%
18%
STATS 19 (n=10,574)
Frontal collisions
OTS (n=175)
Frontal collisions
GDV (n=234)
Frontal collisions
IIHS (FARS/GES)
All car-pedestrians

27%
25%
IRCOBI pre-Conference Workshop on
Collision Avoidance and Driver Assistance Systems - Field data, what do we have and what do we need for future research?
September 10, 2013, Gothenburg, Sweden
Recognizing the importance of avoidance technology
Integrated pedestrian safety systems could reduce pedestrian road fatalities up to
Mono Camera
Stereo Camera
LIDAR Camera Fusion
Mono Radar Camera Fusion
“3D” Electronic Scan Radar
Stereo Camera Radar Fusion
"Surfboard" – Flexible and Robust

(Multiple generations of some systems)
Test Scenarios
Represents most common accident types
Rewards current production systems
Discriminates between current production and future prototypes
Sensor Solutions
Test Devices – Propulsion
Test Devices – Dummy
Adult & child - Robust, reliable, stable
Points Scoring
Points approximate accident frequency – 60 km/h captures around 85% of all pedestrian crashes

30%
Dummy Speed
(Size)
Offset
Vehicle Speed
3 km/h (Adult)
8 km/h (Adult)
5 km/h (Adult)
5 km/h (Child)
50%
50%
25%
75%
20-60 km/h
10-50 km/h
20-60 km/h
10
20
30
40
3 pts
60
50
Speed reduction
Relevance / allocated points
Test speed
Avoidance Shark's Fin
TTC=0.7
2 pts
1 pt
Participants from: Australia (ANCAP), Germany, France, Netherlands, UK, Sweden, Italy + ACEA
New Euro NCAP working group to estimate “a posteriori effectiveness” of existing safety functions


Validating Vehicle Safety through Meta Analysis (VVSMA)

Mass Data
Statistical Methods
Safety Function Fitment
Data can be derived from
Police
Insurance
Others (NHTSA,
Fitment is identified by
Car Make and Model (typically)
Existent Coding in Database
Comparison between observed and expected number (Farmer et al.)
Crash relative risk - Adjusted Odds-Ratios (Evans et al.)
First application: low speed AEB systems
IRTADA, etc.)
(very rare)
Full transcript