Lyft, Inc.

Woven Planet North America, Inc.

Google Inc.

Holger H Rapp

Wolfgang Hess

Clemens Marschner

Thomas Schiwietz

Emil Constantin Praun

Damon Kohler

Vinay Shet

Wilhelm Richert

Patrick Dubroy

Nikolai Morin

Ying Di Zhang

Luca Del Pero

Christopher Edward Hoover

Daniel Sievers

Examples disclosed herein may involve a computing system that is operable to (i) receive first data of one or more geographical environments from a first type of localization sensor, (ii) receive second data of the one or more geographical environments from a second type of localization sensor, (iii) determine constraints from the first data and the second data, (iv) determine shared pose data associated with both of the first data and the second data using the constraints determined from both the first data and the second data by determining one or more sequences of common poses between respective poses generated from each of the first and second data, wherein the shared pose data provides a common coordinate frame for the first data and the second data, and (v) generate a map of the one or more geographical environments using the determined shared pose data.

Map generation using two sources of sensor data

The present invention relates to a method of generating an overhead view image of an area. More particularly, the present invention relates to a method of generating a contextual multi-image based overhead view image of an area using ground map data and field of view image data. Various embodiments of the present technology can include methods, systems and non-transitory computer readable media and computer programs configured to receive a plurality of images of the geographical area, determine a ground map of the geographical area, divide the ground map into a plurality of sampling points of the geographical area; and determine a color for each of the plurality of sampling points, wherein the color of each of the sampling points is determined by determining a correlation between the sampling points of the geographical area and color of the sampling points captured in at least one of the plurality of images.

Overhead view image generation

Systems, methods, and non-transitory computer-readable media can receive a geometric map and a semantic map associated with a geographic area, the semantic map comprising semantic data associated with vehicle navigation. A first semantic position estimate associated with a first piece of semantic data contained in the semantic map is generated based on semantic data location information associated with the first piece of semantic data. A final position for the first semantic position estimate is received. One or more three-dimensional semantic labels are applied to the geometric map based on the final position of the first semantic position estimate. A warped semantic map is generated. Generating the warped semantic map comprises warping the semantic map based on the one or more three-dimensional semantic labels.

Systems and methods for aligning map data

Systems, methods, and non-transitory computer-readable media can determine a first label at a first position in a first image captured from a vehicle, the first label indicating that a first object is depicted in the first image at the first position, wherein the first image is a two-dimensional image. The first object is identified in a three-dimensional coordinate space representative of an environment of the vehicle based on the first position of the first label within the first image. A second label is automatically generated at a second position in a second image captured from the vehicle based on simultaneous localization and mapping (SLAM) information associated with the vehicle. The second label indicates that the first object is depicted in the second image at the second position.

Systems and methods for automated image labeling for images captured from vehicles

In one embodiment, a computing system accesses a number of features extracted from one or more first images. The extracted features are associated with at least one object captured in the first images. The first images are captured by a camera associated with a vehicle. The computing system identifies, in a reference map, reference features matching one or more of the features extracted from the first images. The reference features are associated with the at least one object captured in the first images. The computing system generates, for the camera, a calibration model by comparing the identified reference features in the reference map and the features that match the one or more reference features. The calibration model is used to calibrate second images captured by the camera associated with the vehicle.

Camera calibration using reference map

Computer-implemented methods and systems for detecting loop closure in SLAM applications can include accessing one or more range measurement data scans that each provide a collection of consecutively observed spatial data obtained at a given location. A relative scan pose for each range measurement data scan can be determined. Frames from each of the one or more range measurement data scans then can be aligned to frames within one or more submaps based at least in part by the determined relative scan pose. An enhanced scan pose for each range measurement data scan and an enhanced submap pose for each submap can be periodically determined and used to identify one or more closed loops within the one or more submaps. An output indicative of the identified one or more closed loops can be provided, along with optionally generated floorplan maps and/or given location determinations.

Systems and methods of detecting loop closure in simultaneous localization and mapping (SLAM) applications

Systems and methods for extracting regions from occupancy grids are provided. One example method includes performing a plurality of assignment iterations. Each assignment iteration includes assigning each of a first plurality of cells to one of a plurality of centroids based on a cost formula such that a plurality of regions respectively associated with the plurality of centroids are formed. The region for each centroid comprises all of the cells assigned to such centroid. Each assignment iteration includes reassigning one or more of the first plurality of cells to one or more respective alternate regions. The one or more reassigned cells were included in one or more problem areas of one or more of the plurality of regions. Each assignment iteration includes relocating the plurality of centroids to be the respective means of the plurality of regions. One example system includes computing devices implementing instructions stored on non-transitory computer-readable media.

Growing community of inventors

Bavaria, Germany

Holger H Rapp