while driving a car, because with real road driving
we observe much different speed (and acceleration)
profiles on curves as compared to those obtained on
a simulator with only visual feedback (Partouche et
al, 2007) .
On the other hand, some practical tasks can be
solved without analysing dangerous acceleration
profiles. If one manages to predict with reasonable
precision the moment of deceleration in front of a
curve, then one can warn on the events where a
driver failed to observed the curve, e.g. due to
reduced visibility (warning in this case would be
based on absence of deceleration event where it
should appear).
One could argue that the curve shape features we
are introducing are not practical, as stable visual
analysis of a scene 6s in front of a car driving at
motorway speeds (100 km/h or more) is not realistic
to achieve. Our experience with visual analysis
prompts the same. Yet with new developments,
where interactive roads are foreseen (Jakubiak et al,
2008), or systems where map integrated into the car
provides upcoming curvatures (Mammar et al, 2006)
would solve the problem.
Turning to details of this study, good
acceleration prediction results were obtained when
curve shape parameters SP, E, CA, SD-1.5 or SD-2
were provided as input parameters and S-shape
curve was analyzed separately. For the first driver
the mean squared error of acceleration prediction
was 16% and for the second driver the mean squared
error was 13%. For the second driver adding
parameter S allowed to reduce the error further.
Although, those conclusions should only be taken as
preliminary, and experiments with more data are
required to refine parameter choice.
ACKNOWLEDGEMENTS
This work was supported in part by the European
Commission project “Learning to Emulate
Perception – Action Cycles in a Driving School
Scenario” (DRIVSCO), FP6-IST-FET, contract No.
016276-2.
REFERENCES
Chen, L., Ulsoy, A., 2006. Experimental evaluation of a
vehicle steering assist controller using a driving
simulator. Vehicle System Dynamics, 44, 223-245.
Comte, S. L., Jamson, A. H., 2000. Traditional and
innovative speed-reducing measures for curves: an
investigation of driver behaviour using a driving
simulator, Safety Science, vol. 36, issue 3, 137-150
Gipps, P., 1981. A behavioral Car Following Model for
Computer Simulation. Transportation Research B., 15,
105-111.
Gipps, P., 1986. A Model for the Structure of Lane
Changing Decisions. Transportation Research B, 20,
107-120.
Fenton, R., 1988. On the optimal design of an automative
lateral controller, IEEE Transactions on Vehicular
Technology, 37, 108-113.
He1, J., Crolla, D., Levesley, M., and Manning, W., 2007.
Coordination of active steering, driveline, and braking
for integrated vehicle dynamics control. Proc. IMechE
Vol. 220 Part D: J. Automobile Engineering, 1401-
1421.
Hong, I., Iwasaki, M, Furuichi, T, Kadoma, T. (2006) Eye
movement and driving behaviour in curved section
passages of an urban motorway. Proc. IMechE, 220
Part D: J. Automobile Engineering, 1319-1331
Hsu, J., Tomizuka, M., 1998. Analysis of vision-based
lateral control for automated highway systems.
Vehicle System Dynamics, 30, 345-373.
Jakubiak, J., Koucheryavy, Y., 2008. State of the Art and
Research Challenges for VANETs. 5th IEEE
Consumer Communications and Networking
Conference, 912-916
Jin, Z., Weng1, J., and Hu, H., 2007. Rollover stability of
a vehicle during critical driving manoeuvres. Proc.
IMechE vol. 221 Part D: J. Automobile Engineering,
1041-1049
Mammar, S., Glaser, S., and Netto, M., 2006. Time to Line
Crossing for Lane Departure Avoidance: A
Theoretical Study and an Experimental Setting. IEEE
Transactions on Intelligent Transportation Systems, 7,
226-241
Olstam, J., and Tapani, A., 2004. Comparison of Car
Following Models. Swedish National Road and
Transportation Institute.
Partouche, D., Spalanzani, D., Pasquier, M., 2007.
Intelligent Speed Adaptation Using a Self-Organizing
Neuro-Fuzzy Controller. IEEE Transactions on
Intelligent Transportation Systems, 7, 846 - 851
Salvucci, D., Mandalia, H., Kuge, N., and Yamamura, T.,
2007. Lane-Change Detection Using a Computational
Driver Model. Human Factors, 49, 532-542
Song, J., 2008. Enhanced braking and steering yaw
motion controllers with a non-linear observer for
improved vehicle stability. Proc. IMechE, 222 Part D:
J. Automobile Engineering, 293-303
Yuhara, N., Tajima, J., 2001. Advanced Steering System
Adaptable to Lateral Control Task and Driver's
Intention. Vehicle System Dynamics, 36, 119-158.
ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics
152