Fecha de publicación: 28/12/2018 Fuente: WIPO "swarm" Systems and methods provide vehicle cognition through localization and semantic mapping. Localization involves in vehicle calculation of voxel signatures by hashing weighted voxel data obtained from a machine vision system, and comparison of calculated signatures to cached data within a signature localization table containing previously known voxel signatures and associated geospatial positions. Signature localization tables are developed by swarms of agents calculating signatures while traversing an environment and reporting calculated signatures and associated geospatial positions to a central server. Once vehicles are localized, they engage in semantic mapping. A swarm of vehicles characterizes assets encountered while traversing a local environment. Asset characterizations may be compared to known assets within the locally cached semantic map. Differences of omission and commission between observed assets and asset characterizations with the local map cache are reported to a central server.