Systems and methods for aggregating and integrating distributed grid element inputs are disclosed. A data platform is provided for a distribution power grid. The data platform provides a crowd-sourced gaming system for identifying grid elements and determining dynamic electric power topology. The data platform also provides an interactive interface for displaying a view of a certain area with identified grid elements. The data platform communicatively connects to the identified grid elements, collects data from the identified grid elements, and manages the distribution power grid.

In some implementations, a computing device can provide a map application providing a representation of a physical structure of venues (e.g., shopping centers, airports) identified by the application. The application can provide an inside view of the venue, which is accessible by other applications and programs on the user's device. Thus, whether intended or not, search results that are identified by the map application as having an inside view of the venue are also presented on a graphical user interface along with typical search results from the other applications.

A navigation system for providing driving instructions to a driver of a vehicle traveling on a route is provided. The driving instructions are generated by executing a multimodal fusion method that comprises extracting features from sensor measurements, annotating the features with directions for the vehicle to follow the route with respect to objects sensed by the sensors, and encoding the annotated features with a multimodal attention neural network to produce encodings. The encodings are transformed into a common latent space, and the transformed encodings are fused using an attention mechanism producing an encoded representation of the scene. The method further comprises decoding the encoded representation with a sentence generation neural network to generate a driving instruction and submitting the driving instruction to an output device.

This specification describes a system for generating positions of map items such as buildings, for placement on a virtual map. The system comprises: at least one processor; and a non-transitory computer-readable medium including executable instructions that when executed by the at least one processor cause the at least one processor to perform at least the following operations: receiving an input at a generator neural network trained for generating map item positions; generating, with the generator neural network, a probability of placing a map item for each subregion of a plurality of subregions of the region of the virtual map; and generating position data of map items for placement on the virtual map using the probability for each subregion. The input to the generator neural network comprises: map data comprising one or more channels of position information for at least a region of the virtual map, said one or more channels including at least one channel comprising road position information for the region; and a latent vector encoding a selection of a placement configuration.

A processing apparatus is provided, to, for each candidate point-of-interest of at least one candidate point-of-interest identified for association with a road in a network of roads for determining a name for the road, generate first data indicative of a relationship relating to a distance between the candidate point-of-interest and a road segment of the road, generate second data indicative of a relationship between the road segment and a projection of the candidate point-of-interest in a direction of the road segment, and, if the first and second relationships satisfy a first and second conditions for association respectively, generate data indicative of the candidate point-of-interest being an associated point-of-interest, process data corresponding to the associated point-of-interest to extract name data indicative of a road name associated with the associated point-of-interest, and generate, based on the name data, data indicative of the name for the road.

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S260; and/or any other suitable processes.

A route recording with real-time annotation and re-display system includes a first automobile vehicle having one or more camera systems. An imaging display device defining a head-up display (HUD) is positioned within the first automobile vehicle and receives camera imaging data from the one or more camera systems. The HUD includes a video display screen presenting the camera imaging data either in real-time or re-displayed from a pre-recorded image file. A microphone array receives vehicle operator voice data of a first operator of the first automobile vehicle. An annotated-recorded-route is created by adding a user input of the first operator of the first automobile vehicle including the voice data. The annotated-recorded-route identifies specific coordinates or locations along a travel route driven by the automobile vehicle through the voice data after activating recording of the camera imaging data.

A map having surfaces that are depicted at different levels that are not related to topography, with boundaries between the surfaces, where the boundaries are disposed at travel ways. The travel ways form cliff faces in the map between the surfaces, with information items disposed on the cliff faces at positions corresponding to items of interest at locations along the travel ways where the information items are disposed.

Some embodiments provide a mapping application that displays a rotation of a 3D map and corresponding rotation of a set of map labels overlaying the 3D map in response to receiving input to rotate the 3D map. When a particular map label in the set of map labels rotates towards an upside down orientation, the mapping application also replaces the particular map label with a version of the particular map label arranged in a right side up orientation to prevent the particular map label from being displayed in the upside down orientation in the 3D map.

Aspects of the present disclosure relate generally to identifying and displaying traffic lanes that are available for autonomous driving. Information is displayed to a driver of a vehicle having an autonomous driving mode to inform the driver of where the autonomous driving mode can be used by visually distinguishing between lanes that are available for autodrive from those that are not, and when a lane is an autodrive lane the display includes information indicating how much further the vehicle may continue in the autonomous driving mode in that particular lane before requiring a particular maneuver to depart that lane in order to stay on a route. The display may also indicate the position of a lane (autodrive or not) currently occupied by the vehicle. The display may also display information indicating the remaining autodrive distance in other lanes as well as the lane with the greatest remaining autodrive distance.