Lyft, Inc.

Woven Planet North America, Inc.

Google Inc.

Wolfgang Hess

Holger H Rapp

Clemens Marschner

Emil Constantin Praun

Vinay Shet

Thomas Schiwietz

Patrick Dubroy

Damon Kohler

Luca Del Pero

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

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.

Growing community of inventors

Munich, Germany

Wolfgang Hess