Abstract: Provided are methods, systems, and devices for updating a sensor based on sensor data and the semantic state associated with an area. Sensor data can be received by a computing system. The sensor data can be based on sensor outputs from sensors. The sensor data can include information associated with states of areas detected by the sensors. An estimated semantic state of one of the areas from a target sensor that can detect the states of the areas can be generated. Based on a comparison of the estimated semantic state to semantic states of the area from the sensors, an uncertainty level associated with an accuracy of the estimated semantic state can be determined. In response to the uncertainty level satisfying one or more update criteria, an updated version of the sensor data from the target sensor can be obtained.

Abstract: An interactive landmark localization system includes a database of visual landmarks corresponding to prominent physical objects within a geographic area. The visual landmark database includes geographic information for each landmark including the location and height of the landmark, the orientation that the landmark faces, the size of the landmark, the appearance of the landmark, the name of the landmark, a viewshed for the landmark indicating a set of locations from which the landmark is visible, etc. When a user requests map data or navigation directions to a destination, the interactive landmark localization system verifies the location and orientation of the user using the visual landmarks and their corresponding geographic information. For example, when the user is at a particular location and orientation, the interactive landmark localization system provides indications of landmarks within the vicinity of the particular location to verify the user's location and orientation.

Abstract: Provided are methods, systems, and devices for updating a sensor based on sensor data and the semantic state associated with an area. Sensor data can be received by a computing system. The sensor data can be based on sensor outputs from sensors. The sensor data can include information associated with states of areas detected by the sensors. An estimated semantic state of one of the areas from a target sensor that can detect the states of the areas can be generated. Based on a comparison of the estimated semantic state to semantic states of the area from the sensors, an uncertainty level associated with an accuracy of the estimated semantic state can be determined. In response to the uncertainty level satisfying one or more update criteria, an updated version of the sensor data from the target sensor can be obtained.