Neural Signatures Enhance Emergency Braking Intention Detection during Simulated Driving
-
1
Berlin Institute of Technology, Machine Learning Group, Germany
-
2
Bernstein Focus Neurotechnology, BFNT- B, Germany
-
3
Fraunhofer FIRST, IDA, Germany
-
4
Humboldt University and the Free University, Charité University Medicine, Germany
In many safety-critical areas such as individual car traffic, human performance has become the limiting factor. Modern driving assistance systems can detect potential upcoming crashes and take preparatory measures or even initiate automatic emergency braking.We conducted a driving simulator study (N=20) using a customized version of the open-source racing software TORCS. The experiment comprised 3 blocks (45 minutes each) of driving, in which the subjects had to tightly follow a computer-controlled car at a speed of 100 km/h. While subjects were within the desired maximal distance of 20 m, the preceding car occasionally (20-40 seconds ISI, randomized) performed sudden brakings, forcing the subject to immediately brake as well in order to avoid a crash.Various ERP components predictive of emergency braking occasions could be observed between the initial flashing of the preceding car's brake light and the onset of braking: a VEP related to low-level visual processing of the brake light stimulus and a P3 reflecting the rareness and importance of this event. Further, a readiness potential (LRP) was present, building up before the actual movement. While radar-derived features (distance and acceleration) were the first to indicate a critical situation at all, neural parameters were the earliest to reflect driver's intent to brake, followed by electromyographic, gas pedal and braking pedal derived features.All the observed ERPs occur frequently during normal driving. However, our analysis shows that their co-occurrence robustly characterizes certain critical situations. Furthermore, inclusion of (neuro-) physiological features lead to an increase of detection performance even in early stages of critical situations, showing that such features carry information about the driver's intent that is strictly additive to behavioural and technical parameters.
Figure 1:Grand-average ERPs relative to braking onset
Keywords:
computational neuroscience
Conference:
Bernstein Conference on Computational Neuroscience, Berlin, Germany, 27 Sep - 1 Oct, 2010.
Presentation Type:
Presentation
Topic:
Bernstein Conference on Computational Neuroscience
Citation:
Haufe
S,
Treder
M,
Gugler
M,
Sagebaum
M,
Ewald
A,
Curio
G and
Blankertz
B
(2010). Neural Signatures Enhance Emergency Braking Intention Detection during Simulated Driving.
Front. Comput. Neurosci.
Conference Abstract:
Bernstein Conference on Computational Neuroscience.
doi: 10.3389/conf.fncom.2010.51.00026
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
20 Sep 2010;
Published Online:
23 Sep 2010.
*
Correspondence:
Dr. Stefan Haufe, Berlin Institute of Technology, Machine Learning Group, Berlin, Germany, haufe_work@mailbox.org