The disclosure relates to using ambient lighting conditions with passenger and goods pickups and drop offs with autonomous vehicles. For instance, a map of ambient lighting conditions for stopping locations may be generated by receiving ambient lighting condition data for predetermined stopping locations and arranging this data into a plurality of buckets based on time and one of the stopping locations. A vehicle may then be controlled in an autonomous driving mode in order to stop for a passenger by both observing ambient lighting conditions for different stopping locations and, in some instances, also using the map.

In some implementations, a route between a starting point and a destination point may be encoded in a map-independent way. A route is an ordered list of segments that connect the starting point to the destination point. By being map-independent, the route can be encoded on one map version, such as at a server device, and later decoded on a different map version, such as on a user device. In an embodiment, the user device may decode the route using the same codec library that was used by the server to encode the route. Moreover, in an approach, the user device may select a subset of support points along the route to provide to the server which are sufficient to describe the route in order to conserve resources. Using these techniques, a route can be encoded in a very space efficient way with a decoding error rate close to 0%.

A computer-implemented method is disclosed for validating a road object. The computer-implemented method may include: receiving a road object observation comprising road object location data of the road object; and identifying driving direction data associated with the received road object observation. The computer-implemented method may further include obtaining at least one geographic administrative boundary that is in vicinity of the road object; and determining a distance between the road object and the at least one geographic administrative boundary. Furthermore, the computer-implemented method may include determining a relative position of the road object from the at least one geographic administrative boundary; and validating the road object based on at least two of the driving direction data, the distance between the road object and the at least one geographic administrative boundary and the relative position of the road object from the at least one geographic administrative boundary.

A method and an apparatus of processing traffic data, a device, a medium and a product are provided. The method of processing traffic data includes: acquiring initial traffic data for a vehicle, wherein the initial traffic data includes current position information of the vehicle, position information of a plurality of traffic objects and feature information; determining a relative positional relationship between the current position information of the vehicle and the position information of the plurality of traffic objects; and processing the initial traffic data based on at least one of the feature information and the relative positional relationship to acquire at least one traffic data set, so as to navigate the vehicle based on the at least one traffic data set.

The present disclosure provides methods, apparatuses, and storage media for storing and loading visual localization maps. The methods for storing the visual localization maps may include acquiring a visual localization map; extracting key frame abstract information of each key frame from the visual localization map; grouping the key frame abstract information of all key frames of the visual localization map; for each group, generating and storing a sub-map-file of the group using the key frame abstract information of the group; generating key frame space index information based on the key frame abstract information of all groups; and generating and storing a master map file according to the key frame space index information for indexing the sub-map-file.

In a map data generation apparatus, probe map data is generated for each of data management units corresponding to (i) road sections, (ii) road links, or (iii) meshes into which a map is divided, based on a plurality of probe data collected from a plurality of vehicles. Difference data are obtained by comparing basic map data with the probe map data; the basic map data is updated based on a plurality of difference data, for each of the data management units. A transient data is discriminated from data corresponding to the probe data or the difference data; the transient data is excluded from the data.

The disclosure relates to using ambient lighting conditions with passenger and goods pickups and drop offs with autonomous vehicles. For instance, a map of ambient lighting conditions for stopping locations may be generated by receiving ambient lighting condition data for predetermined stopping locations and arranging this data into a plurality of buckets based on time and one of the stopping locations. A vehicle may then be controlled in an autonomous driving mode in order to stop for a passenger by both observing ambient lighting conditions for different stopping locations and, in some instances, also using the map.

Embodiments are directed to a system and methods for processing geolocation event data points and mapping the event data to road segments. An ingestion server ingests location event data. The system then processes the location event data to identify Journeys. Journey points are clustered to identify a geoshape for a parking area.

The technology disclosed relates to systems and methods for generating a multi-part place identifier with at least one part. The system includes logic to receive a location address and a place name wherein the location address is a validated address. The system includes logic to calculate a geocode for the location address and use the geocode to identify a geometrical boundary encompassing the location address. The system includes logic to convert the identified geometrical boundary to an alpha-numeric identifier forming a Where part of the multi-part place identifier. The system can use an input location address or a place name to match a previously generated and stored multi-part place identifier. The system can provide the generated or matched multi-part place identifier to a user for use in further analysis.

Methods, systems, and media for simulating movement data of pedestrians in a district are provided. The method comprises: receiving a district plan for a proposed district; determining a number of users that would populate a building in the proposed district; generating a population of simulated users based on the determined number of users that would populate the building in the proposed district; assigning, for the population of simulated users in the building, groups of simulated users in the population of simulated users to a movement category from a plurality of movement categories; distributing, for the groups of simulated users assigned to each of the plurality of movement categories, a group of simulated users to a first destination within the proposed district that satisfies the movement category by determining a probable walking path from the building to the first destination; in response to determining that the first destination within the proposed district has reached a first capacity threshold, distributing remaining users from the group of simulated users to a second destination within the proposed district that satisfies the movement category until at least one of the remaining users in the movement category has been distributed and the second destination within the proposed district has reached a second capacity threshold; distributing, for the groups of simulated users assigned to each of the plurality of movement categories, trips having the probable walking path of the group of simulated users over time by applying a distribution function to each of the plurality of movement categories; and causing a map representation of the proposed district to be presented, wherein the map representation highlights each of the trips having the probable walking path distributed over time to indicate predicted levels of congestion at a particular time in the proposed district.