According to various embodiments, systems, methods, and mediums for operating an autonomous driving vehicles (ADV) are described. The embodiments use a number of machine learning models to extract features individually from audio data and visual data captured by sensors mounted on the ADV, and then to fuse these extracted features to create a concatenated feature vectors. The concatenated feature vector is provided to a multiplayer perceptron (MLP) as input to generate a detection result related to the presence of an emergency vehicle in the surrounding environment. The detection result can be used by the ADV to take appropriate actions to comply with the local traffic rules.
MACHINE LEARNING MODEL TO DETECT EMERGENCY VEHICLES FUSING AUDIO AND VISUAL SIGNALS
MASCHINELLES LERNEN MODELL ZUR ERKENNUNG VON EINSATZFAHRZEUGEN DURCH VERBINDUNG VON AUDIO- UND VISUELLEN SIGNALEN
MODÈLE D'APPRENTISSAGE MACHINE POUR DÉTECTER LES VÉHICULES D'URGENCE EN FUSIONNANT DES SIGNAUX AUDIO ET VISUELS
2024-01-31
Patent
Electronic Resource
English
EMERGENCY VEHICLE DETECTION FUSING AUDIO AND VISUAL DATA
European Patent Office | 2022
|Machine learning model to fuse emergency vehicle audio and visual detection
European Patent Office | 2023
|MACHINE LEARNING MODEL TO FUSE EMERGENCY VEHICLE AUDIO AND VISUAL DETECTION
European Patent Office | 2022
|MACHINE LEARNING MODEL TO FUSE EMERGENCY VEHICLE AUDIO AND VISUAL DETECTION
European Patent Office | 2022
|Driver fatigue monitoring method fusing visual identification and vehicle signals
European Patent Office | 2023
|