Environmental limitation and sensor anomaly system and method

Method of determining sensor condition and environmental condition based on sensor measurement, and generating a perception visibility model (PVM) indicating sensor detection capabilities (e.g. occlusion map indicating where an object is located that is occluding the sensors, or a probability of det...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu Pan, Scott D Pendleton, You Hong Eng, James Guo Ming Fu
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Method of determining sensor condition and environmental condition based on sensor measurement, and generating a perception visibility model (PVM) indicating sensor detection capabilities (e.g. occlusion map indicating where an object is located that is occluding the sensors, or a probability of detection map 905 indicating the likelihood of an objection being detected in a given location), and planning a trajectory based on PVM. Perception pipeline may generate intermediate perception data e.g. LIDAR semantic point cloud including ground plane and detected objects. System may determine if the PVM is to be updated based on sensor and environmental conditions; if not, reusing the prior PVM as the current PVM. Prior PVM may be obtained offline 910 from a database or online 915 based on past PVMs. PVM may indicate an average perception visibility of a non-occluded object with a direct line-of-sight within a range. Sensor condition may be malfunction or occluded sensors. Environmental condition may include weather or sun/light glare.