Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · •...
Transcript of Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · •...
![Page 1: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/1.jpg)
1
Confidence indicators for ADAS functions
Ph. Bonnifait, V. Cherfaoui, G. Dherbomez, M. Doumiati, F. Fayad, M. Jabbour, J. Laneurit, S. Rodriguez, A. Victorino
Speaker: Ph. Bonnifait
Lab Heudiasyc CNRS, Université de Technologie de Compiègne
FRANCE
![Page 2: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/2.jpg)
2
Demos
1. Pedestrian detection – in car, real time
2. Map-matching integrity monitoring – in car, real time
3. Automatic detecting risk rollover situations– On table, real data replay
![Page 3: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/3.jpg)
3
Outline of this presentation
• Motivation and scientific Interests• The demos at a glance
– Our experimental car: Carmen– What you can see on board the vehicles
• Key technologies demonstrated – Lidar detection, pedestrian recognition and
tracking – Calibration of the extrinsic transformation
between the lidar frame and a camera frame– Map-Matching integrity monitoring– Load Transfer Ratio
![Page 4: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/4.jpg)
4
Scientific interests
• ADAS - Advanced Driver Assistance Systems– Techniques for Man-Machine cooperation
assessment• Perception
– State Observation of dynamic systems– Multi-sensor fusion in a dynamic context– Ego-localization using on-board sensors and GNSS
associated with GIS information– Dynamic behaviour (tire/road contact
characterisation)
![Page 5: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/5.jpg)
5
Intelligent Vehicles• An IV is a vehicle able to perform
– driving assistance tasks – autonomous navigation
in the presence of uncertainty and variability in its environment
• Artificial Perception and Contextual Information analysis are key issues
• Managing uncertainty in fusion processes is crucial for reliable perception
![Page 6: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/6.jpg)
6
Confidence indicators
• IV embedded systems need to– Fuse redundant information– Estimate unobserved parameters– Monitor themselves
Fault detection and isolationDiagnosisIntegrity tests
• Confidence indicators are useful for – The fusion processes (Input)– The use of the provided information (since often no
high enough reliability can be reached) (Output)
![Page 7: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/7.jpg)
7
Outline of this presentation
• Motivation and scientific Interests• The demos at a glance
– Our experimental car: Carmen– What you can see on board the vehicles
• Key technologies demonstrated – Lidar detection, pedestrian recognition and
tracking – Calibration of the extrinsic transformation
between the lidar frame and a camera frame– Map-Matching integrity monitoring– Load Transfer Ratio
![Page 8: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/8.jpg)
8
CARMEN
CAN bus
• Wheel Speed Sensors
•Yaw rate gyro 4-layer Lidar
(IBEO Alaska XT)
Front scene camera
(Sony camera)
GPS receiver
(PolarX Septentrio)
![Page 9: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/9.jpg)
9
Demo 1: Pedestrian detection/recognition using lidar-only
![Page 10: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/10.jpg)
10
Projection on the image of the 4 scanning layers of a Lidar
If the recognition confidence of the lidar-only-track > threshold
• Projection of a corresponding rectangle (2 meters high)
• Plot of “ lateral bars” to represent the confidences
What you can see during the demo
![Page 11: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/11.jpg)
11
Lidar-only pedestrian detection/recognition on-board display
(no gate on the confidence treshold)
![Page 12: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/12.jpg)
12
Lidar-only pedestrian detection/recognition on-board display (confidence treshold=95%)
![Page 13: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/13.jpg)
13
Architecture
IBEO Alasca XT (12.5 Hz)
Sony CCD Camera (15Hz)
Dat
a ac
quis
ition
Obstacle detection
Pedestrian recognition
Tracking objects
Confidence indicators computation
ROI projection into image
Win32
Calibrated parameters
Selected pedestrian list
Display
![Page 14: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/14.jpg)
14
Demo 2 : characterization of the confidence in the map matching process
of a localization system
![Page 15: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/15.jpg)
15
What you can see during the demo
Most probable hypothesis
3 other hypotheses
Map display
-The yellow square and the arrow are the position and the heading of the car
-The 4 red triangles correspond to the hypotheses
-The brackets represent the confidence interval of the track
Safety level of the output : the lower the PFA (Probability of False Alarm), the more reliable the hypothesis
Reliable
Unsafe
ConfidentAmbiguous Historic of the most probable hypothesis
![Page 16: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/16.jpg)
16
MM demo overview
![Page 17: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/17.jpg)
17
Architecture
Septentrio GPS 10Hz
CAN gateway
Odometry (25Hz) & gyrometer (100Hz)
Data acquisition
Positioning EKF
Map matching +Integrity Indicators Particle filter
Map server (TCP/IP)
Display
Win32
Linux
Two Map servers
-NavTeQ
-TeleAtlas
![Page 18: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/18.jpg)
18
Outline of this presentation
• Motivation and scientific Interests• The demos at a glance
– Our experimental car: Carmen– What you can see on board the vehicles
• Key technologies demonstrated – Lidar detection, pedestrian recognition and
tracking – Calibration of the extrinsic transformation
between the lidar frame and a camera frame– Map-Matching integrity monitoring– Load Transfer Ratio
![Page 19: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/19.jpg)
19
Perception objectives
• Obstacles detection and tracking in driving situation• Pedestrians recognition• Confidence indicators management
– Detection– Recognition– Tracking
![Page 20: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/20.jpg)
20
Object level fusion moduleSensor used in the demo
![Page 21: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/21.jpg)
21
Object detection
• Four plane laser sensor• Detecting ground• Clustering
![Page 22: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/22.jpg)
22
z
xy
zmin
Layer 1
Layer 2
Layer 3
Layer 4
zmax
ω1234
ω123
ω234
ω23
ω2
ω3
0
1
0
1
0
1
0
1
0
1
0
1
(a)
(b)
(c)
Object Detection Confidence
More details in paper WeBT.27
25 50 75 100
L(cm)
0
Pr
0.5
1
125
Pedestrian Recognition Confidence
Width based Recognition function
NNNNNNNPd
/)(
33222323
23423412312312341234
ωωωωωω
+++++=
For each detected object
⎟⎟⎠
⎞⎜⎜⎝
⎛⎟⎠⎞
⎜⎝⎛×
=DLRoundN
2arctan2180
πα
![Page 23: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/23.jpg)
23
Track’s updating
![Page 24: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/24.jpg)
24
Confidences management
Method: belief functions • To combine tracks • To manage objects detection and
recognition confidences
Algorithm• transform the detection and recognition
probabilities into believe functions : basic believe assignment (bbas)
• Combine these dependent bbas with a cautious rule.
• Combine conjunctively with the associated track’s confidence
• Calculate track’s detection and recognition confidencesMore details in paper WeBT.27
0
10
20
30
40
50
60
70
80
90
100
1 4 7 10 13 16 19 22 25 28 31
time
Object Detection
Object Recognition
Track Detection
Track Recognition
![Page 25: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/25.jpg)
25
cX
cY
cZ
lX
lY
lZ
tX
tY
tZ
CCcl ,
ijlP
Extrinsic Calibration between a Multi-layer Lidar and a Camera
• 3D pose estimation of the calibration target from each sensor data.– 3D scan data (4 layers)– Images
• Estimation of the relative sensor position – 3D Robust Registration of
different poses of the target • Calibration accuracy estimation
based on registration residuals
![Page 26: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/26.jpg)
26
Demo 2 : characterization of the confidence in the map matching process
of a localization system
![Page 27: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/27.jpg)
27
Map Matching - Definition
map
« map-matching » : determining the vehicle’s position % a digital road database
![Page 28: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/28.jpg)
28
GNSS-basedPositioning
MapDatabase
EGNOSReceiver
GNSSReceiver
InfrastructurePositioning
Module
HybridPositioning
MapMatching
DRSensors
HybridSolution
MapMatchedSolution
UpdateService
Main functions of the position calculation process in POMA
![Page 29: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/29.jpg)
29
Modern Map-Matching Outputs
• MM outputs : up to 10 matched candidates• Each candidate (Map-Matched hypothesis)
– Probability with respect to the others– NIS – Normalized Innovation Squared
• Very often it is the hypothesis with the maximum probability that is used: for navigation tasks or fleet management applications it is acceptable. But for many other applications, like eCall or “Pay as you drive”, it is important to manage all the hypotheses.
![Page 30: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/30.jpg)
30
Integrity and Localization Systems
• Integrity of a localization system: the measure of confidence that can be accorded to the exactitude of the positioning delivered by this system.
• Usual scheme– apply successive checks to ensure that the input
information is valid detect and eliminate aberrant measurements
“internal reliability”– estimate a positioning with a quantified
inaccuracy. “external reliability”
![Page 31: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/31.jpg)
31
xPL – Protection LevelsMaximum error due to an undetected fault
Approximate Radius of Protection (ARP)
![Page 32: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/32.jpg)
32
Integrity of a map-matching system• Map-Matching Integrity definition (proposal)
– A multi-hypothesis map-matching process is reliable (or safe) if the ground truth matched location is within the hypotheses zones provided by the system.
Real unknown matched position Candidate matched zones
Real unknown matched position Candidate matched zones
Safe Unsafe
![Page 33: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/33.jpg)
33
How to characterize the localization system integrity in real-time?
• The Real Map-Matched position is Unknown!• Our proposal
– Multi-Hypothesis Map-Matching (MHMM)– Estimate the probability of each hypothesis with
respect to the others– Compute Normalized Residuals for each
hypothesis – Apply a decision rule (depending on the
application)
![Page 34: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/34.jpg)
34
Monitoring integrity using MHMM outputs Estimated position
Candidate matched position Most likely candidate
Estimated position Candidate matched position Most likely candidate
Case 1 : confident MM Case 2 : ambiguous MM
Estimated position Candidate matched position Most likely candidate
Case 3: inconsistent candidates
![Page 35: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/35.jpg)
35
Bayesian MHMM using Road Tracking
![Page 36: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/36.jpg)
36
MOMKFMultiple Observation Models Kalman Filter
⎩⎨⎧
+=+= −
ttt
ttt
)x(oz)x(fx
βα1
Multi-hypothesisMap-matching
GPS
Proprioceptivesensors
Roads
HypothesesEstimation/Selection
Selected
Hypotheses
Map observations are fused with the states
![Page 37: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/37.jpg)
37
MOMKF Illustration
Δ
Δ : threshold for safe duplication
More details in paper WeBT.24
![Page 38: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/38.jpg)
38
False Alarms and Missed detectionsEstimated position Real unknown position Candidate matched position Most likely candidate
Estimated position Real unknown position Candidate matched position Most likely candidate
Example of false alarm. The matched point is good but it is declared unsafe by the system
Example of missed detection. The most likely matched point is bad and the system is
confident in its map-matching
![Page 39: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/39.jpg)
39
Managing the NIS of MHMM• Criterion: heading + distance (for each hypothesis)
2 degrees of freedom• Gaussian hypothesis
NIS should follow a Chi Squared distribution • Decision rule: compare each NIS with a Threshold• Decision threshold depends on the probability of False
Alarm • Decision rule: accept hypothesis “i” if NIS(i)<Th(PFA)
– PFA = 10% Th = 4.6– PFA = 1% Th = 9.2– PFA = 0.1% Th = 13.8– PFA = 0.01% Th = 18.4
![Page 40: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/40.jpg)
40
Managing the probabilities of MHMM
• It depends on the application!• Navigation typical rule
– Take the most likely hypothesis if Pi>0.5• Intelligent Speed Adaptation
– If Pi<0.8 then confirm the extracted speed limit with the one detect by the on board camera
• Road charging – Charge the use of the road if the less likely
hypothesis j is such that Pj<0.1
![Page 41: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/41.jpg)
41
Demo 3 : An estimation methodology for vehicle wheel-ground contact normal forces: Automatic
detecting risk rollover situations
![Page 42: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/42.jpg)
42
Problem
• Usual measurements: accelerations, roll rates, suspensions deflection,…
• Missing important information– Dynamic variables: roll angle, tire-road forces
high costs sensors-> estimation
![Page 43: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/43.jpg)
43
Objective
• Replace wheels transducers by virtual sensors (observers)
+
accelerometer, gyrometer, …+ModellingObserver
kkkpk XdtUXfX∧∧
+∧
+⎟⎠⎞⎜
⎝⎛= ,,1
( )kcpkk YYKXX −−= +∧
+∧
,11
+Tire-road forces
![Page 44: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/44.jpg)
44
Why we need to estimate normal tire forces?• As a result of longitudinal and lateral accelerations,
the load distribution in a vehicle changes during a journey.
• Normal tire-road forces:– Improvement of safety systems (ABS, ESP)– Influence steering behavior, vehicle stability and cornering
stiffness– Better calculation of the LTR (Load Transfer Ratio) rollover
index parameter
Force Fz
roll pitch
![Page 45: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/45.jpg)
45
LTR parameter definition
• LTR:– LTR=(Fzr-Fzl)/(ΣFz)– Convenient method for supervising the vehicle’s
dynamic roll behavior- LTR
Lift-off of the right wheels
No load transfer
Lift-off of the left wheels
1 0 -1
![Page 46: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/46.jpg)
46
Estimation process
Observer 1 (LKF)Roll plane vehicle model
Measurements
Lateral load transfer
Observer 2 (EKF)Nonlinear wheel ground
vertical contact force model
Vertical forces, LTR
![Page 47: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/47.jpg)
47
Some experimental results
0 5 10 15 20 25
2000
3000
4000
5000
6000
Front left vertical tire force Fz fl (N )
6000
7000
Front right vertical tire force Fz fr (N )
measuredestimated
![Page 48: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/48.jpg)
48
This is the end
Have a look at our demos!
![Page 49: Confidence indicators for ADAS functionsbonnif/talks/demos_IV_UTC.pdf · 2008. 10. 30. · • Intelligent Speed Adaptation – If P i](https://reader034.fdocuments.us/reader034/viewer/2022051908/5ffad3e6fc58be5e9e6076f5/html5/thumbnails/49.jpg)
49
Demos
1. Pedestrian detection – in car, real time
2. Map-matching integrity monitoring – in car, real time
3. Automatic detecting risk rollover situations– On table, real data replay