Uatc, LLC

Aurora Operations, Inc.

David Prasser

Ethan Eade

James Andrew Bagnell

Robert Zlot

Peter Hansen

Rachel Ahn

Brett Browning

Bryan John Nagy

Xxx Xinjilefu

David LaRose

Brett Bavar

Adam Henry Polk Milstein

Xiaodong Zhang

Narek Melik-Barkhudarov

Adam Cole Panzica

Adam Milstein

Gordon Peter Bailey

Jennifer Joyce Padgett

Adrian Rechy Romero

Evan Herbst

Michael Napoli

David Larose

Various examples are directed to systems and methods for locating a vehicle. A pose state estimator may access a previous position for the vehicle at a first time, wherein the previous position is on a first sub-map of a plurality of sub-maps. The pose state estimator may receive from a first localizer a first position estimate for the vehicle at a second time after the first time. The first position estimate may be on a second sub-map of the plurality of sub-maps. The pose state estimator may send to a second localizer a sub-map change message indicating the second sub-map.

Map selection for vehicle pose system

A method for receiving autonomous vehicle (AV) map data associated with an AV map of a geographic location and coverage map data associated with a coverage map of the geographic location. The AV map data is associated with an AV lane of a roadway in the geographic location, and the coverage map data is associated with a coverage lane of the roadway in the geographic location. The method includes generating a hybrid map of the geographic location based on the AV map data and the coverage map data and providing hybrid map data associated with the hybrid map for routing of an AV. The hybrid map includes the AV lane linked with the coverage lane of the roadway.

Map creation from hybrid data

A georeferenced trajectory system for vehicles receives trajectory data generated by a plurality of vehicle sensors and scaffolds of previously generated maps and aligns geometry data for a geographic region and trajectory data from the received data from different map builds. A scaffold of a geographic region to be mapped during an initial map build is generated, and the trajectory data from respective map builds is aligned with the scaffold of previously generated maps to generate a map of the geographic region. The resulting map expands the coverage of the existing map such that old and new map data is in a common consistent reference frame whereby the map may be built incrementally by merging or expanding local scaffolds and filling in the merged or expanded scaffold while ensuring global consistency.

Scaffolds for globally consistent maps

A georeferenced trajectory estimation system receives data generated by vehicle sensors from a fleet of vehicles and identifies sets of sensor measurements for a geographic region taken at different times. The sets of sensor measurements include environment geometry data and unaligned trajectory data in local coordinate frames. The georeferenced trajectory estimation system aligns the environment geometry data between sets of sensor measures, and, based on the alignment of the environment geometry data, transforms the identified corresponding trajectory data into a common coordinate frame.

Georeferenced trajectory estimation system

A georeferenced trajectory estimation system for vehicles receives trajectory data generated by a plurality of vehicle sensors and fixed reference points of previously generated maps and aligns geometry data for a geographic region and trajectory data from the received data from different map builds. The trajectory data from respective map builds is aligned with fixed reference points of previously generated maps to generate a map of the geographic region. The received map data may include submap or spatially indexed data that is used to provide estimates of where a vehicle in an unmapped area is located by generating a series of pose estimates relating back to a fixed reference point in a previously mapped area. The resulting map expands the coverage of the existing map such that old and new map data is in a common consistent reference frame whereby the map may be built incrementally while ensuring global consistency.

Log trajectory estimation for globally consistent maps

Various examples are directed to systems and methods for determining a pose of a vehicle. A first localizer may generate a first pose estimate for the vehicle based at least in part on a comparison of first remote sensor data to a first reference data. A second localizer may generate a second pose estimate for the vehicle based at least in part on a comparison of second remote sensor data to a second reference data. A pose state estimator may generate a vehicle pose for the vehicle based at least in part on a first previous pose of the vehicle, the first pose estimate, and the second pose estimate.

Vehicle pose system

A system to use submaps to control operation of a vehicle is disclosed. A storage system may be provided with a vehicle to store a collection of submaps that represent a geographic area where the vehicle may be driven. A programmatic interface may be provided to receive submaps and submap updates independently of other submaps.

Autonomous vehicle localization using image analysis and manipulation

Autonomous vehicle localization using passive image data

Growing community of inventors

Pittsburgh, PA, United States of America

David Prasser