Understanding common human driving semantics for autonomous vehicles.

Autonomous vehicles will share roads with human-driven vehicles until the transition to fully autonomous transport systems is complete. The critical challenge of improving mutual understanding between both vehicle types cannot be addressed only by feeding extensive driving data into data-driven models but by enabling autonomous vehicles to understand and apply common driving behaviors analogous to human drivers. Therefore, we designed and conducted two electroencephalography experiments for comparing the cerebral activities of human linguistics and driving understanding. The results showed that driving activates hierarchical neural functions in the auditory cortex, which is analogous to abstraction in linguistic understanding. Subsequently, we proposed a neural-informed, semantics-driven framework to understand common human driving behavior in a brain-inspired manner. This study highlights the pathway of fusing neuroscience into complex human behavior understanding tasks and provides a computational neural model to understand human driving behaviors, which will enable autonomous vehicles to perceive and think like human drivers.

A Novel GNSS Interference Detection Method Based on Smoothed Pseudo-Wigner-Hough Transform.

This paper develops novel Global Navigation Satellite System (GNSS) interference detection methods based on the Hough transform. These methods are realized by incorporating the Hough transform into three Time-Frequency distributions: Wigner-Ville distribution, pseudo -Wigner-Ville distribution and smoothed pseudo-Wigner-Ville distribution. This process results in the corresponding Wigner-Hough transform, pseudo-Wigner-Hough transform and smoothed pseudo-Wigner-Hough transform, which are used in GNSS interference detection to search for local Hough-transformed energy peak in a small limited area within the parameter space. The developed GNSS interference detection methods incorporate a novel concept of zero Hough-transformed energy distribution percentage to analyze the properties of energy concentration and cross-term suppression. The methods are tested with real GPS L1-C/A data collected in the presence of sweep interference. The test results show that the developed methods can deal with the cross-term problem with improved interference detection performance. In particular, the GNSS interference detection performance obtained with the smoothed pseudo-Wigner-Hough transform method is at least double that of the Wigner-Hough transform-based approach; the smoothed pseudo-Wigner-Hough transform-based GNSS interference detection method is improved at least 20% over the pseudo-Wigner-Hough transform-based technique in terms of the zero Hough-transformed energy percentage criteria. Therefore, the proposed smoothed pseudo-Wigner-Hough transform-based method is recommended in the interference detection for GNSS receivers, particularly in challenging electromagnetic environments.