Uber Technologies, Inc.

Carnegie Robotics, LLC

Carnegie Mellon University

Uatc, LLC

Psychogenics Inc.

The Toro Company

David LaRose

William Payne Ross

Matthew Sweeney

John Evan Bares

Vijay M Gondhalekar

Daniela Brunner

Emer Leahy

Ethan Eade

Peter Hansen

Brett Browning

Robert Zlot

David Prasser

Michael Jason Ramsay

Christopher Charles Osterwood

James Andrew Bagnell

Alexander Steven Frick

Ryan Douglas Ingvalson

Jason Thomas Kraft

Daniel Leland Strother

Christopher Chandler Fromme

Claus Thybo

John Paul Thomas Atkinson

Troy Edward Tancraitor

Michael Knoll Sergi-Curfman

Adam Richard Williams

L Douglas Baker

Matthew John Alvarado

Elliot Allen Cuzzillo

Zachary Irvin Parker

Stephen Paul Elizondo Landers

David Jonathan Stager

Anurag Jakhotia

Andrew James Somerville

David Ian Robinson

Coleman Scott Knabe

Daniel King Beaven

David R Wozny

John Bares

Daniel David Williams

Brian Daniel Beyer

Anil Harish

An assembly of a self-propelled floor cleaning unit and a floor disinfecting unit. The floor disinfecting unit may be detachably attached to the floor cleaning unit. The areas covered by the floor cleaning unit and floor disinfecting unit may be logged and reported.

Floor cleaning and disinfecting robot

A method and a system for retrieving disparity information from a stereo image pair including a first and second images obtained by first and second cameras, respectively. The first and second images are provided to a conventional disparity algorithm to an artificial intelligence (AI) driven disparity algorithm. Using the conventional disparity algorithm, the first disparity information is derived from the stereo image pair, and a confidence score function is associated with the derived first disparity information. Using the AI-driven disparity algorithm, second disparity information is derived from at least part of the stereo image pair. The first and second disparity information are fused by giving priority to the first disparity information in regions of the stereo image pair with a high confidence score and giving priority to the second disparity information in regions of the stereo image pair with a low confidence score, thereby obtaining resultant disparity information.

Method for retrieving disparity information from a stereo image pair

An indoor mobile industrial robot system is configured to provide a weight to a detected object within an operating environment, where the weight relates to how static the feature is. The indoor mobile industrial robot system includes a mechanism configured to translate reflected light energy and positional information into a set of data points representing the detected object having at least one of Cartesian and/or polar coordinates, and an intensity. If any discrete data point within the set of data points representing the detected object has an intensity at or above a defined threshold the entire set of data points is converted into a weight and potentially classified representing a static feature, otherwise such set of data points is classified as representing a dynamic feature having a lower weight.

Systems and methods for enabling navigation in environments with dynamic objects

A method of operating a robot performing a task when receiving instructions to discontinue the task and perform an additional task. Having performed the additional task, the robot will revert to the position of performing the first task and continue the first task.

Method of operating one or more robots

A system can receive a transport request from a computing device of a requesting user, where the transport request indicates a service location. The system can determines a preliminary route for the transport request, and select an autonomous vehicle from a fleet of autonomous vehicles operating in the given area to service the transport request based on determining that the selected autonomous vehicle is capable of traversing the preliminary route without intervention.

Systems and methods for managing an autonomous vehicle transport service

In a method or system in which an imaging element views navigation elements for e.g. navigation, the navigating elements may not be positioned optimally. Positions may exist in which the same angles exist from the imaging element to the same or similar navigating elements, whereby the positions are not unique. Navigation elements may then be repositioned, added or removed to make the positions unique.

Method and a system for analyzing a scene, room or venue

A method for obtaining a three-dimensional model of an inspection site, using a perception module, is disclosed. The perception module comprises a detection unit, e.g. comprising one or more cameras and/or a three-dimensional laser scanner, configured to obtain a three-dimensional image. At least one three-dimensional image is obtained by means of the detection unit. A three-dimensional model of surroundings of the perception module is created, based on the obtained three-dimensional image. The created three-dimensional model and a plan of the inspection site are compared and features of the created three-dimensional model and features of the plan of the inspection site are matched. A site-specific three-dimensional model of the inspection site is formed, based on the created three-dimensional model and the plan of the inspection site, and based on the comparison.

Method for obtaining a three-dimensional model of an inspection site

A transport arrangement system operates to receive a transport request from a user, and to make a selection of a vehicle type for the user based at least in part on a set of criteria associated with the transport request or user information. For example, the determination of whether an autonomous vehicle is to be provided can be based at least in part on the destination specified with the transport request.

Selecting vehicle type for providing transport

Autonomous machine navigation techniques may generate a three-dimensional point cloud that represents at least a work region based on feature data and matching data. Pose data associated with points of the three-dimensional point cloud may be generated that represents poses of an autonomous machine. A boundary may be determined using the pose data for subsequent navigation of the autonomous machine in the work region. Non-vision-based sensor data may be used to determine a pose. The pose may be updated based on the vision-based pose data. The autonomous machine may be navigated within the boundary of the work region based on the updated pose. The three-dimensional point cloud may be generated based on data captured during a touring phase. Boundaries may be generated based on data captured during a mapping phase.

Autonomous machine navigation and training using vision system

Sensor information is collected from human driven vehicles which are driven in a given region. From the sensor information, a road condition is detected on a road segment, where the road condition has a sufficiently high likelihood of impairing autonomous vehicles in safely navigating through the one or more road segments. Information about the one or more road segments is communicated to the one or more autonomous vehicles.

Autonomous vehicle operated with guide assistance of human driven vehicles

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

Embodiments of the present invention include multi-sensory stereo vision sensors suitable for use in robotics, navigation, machine vision, manufacturing, and other applications. In some cases, a sensor includes a stereo camera that produces image data for use in generating disparity maps to determine the positions of objects in the scene and/or the position of the sensor itself. The stereo sensor may include image sensors that are fastened to a unitary frame to prevent undesired drift and a thermal pad that wicks heat away from a processor. The processor may provide an efficient means to directly compute stereo disparity maps onboard the sensor. A sensor can also include a laser rangefinder that provides range data suitable for calibrating the stereo camera and for improving its accuracy in certain environments. In some cases, the laser is coupled to a spindle, which in turn is driven by a geartrain through a slipping clutch.

Methods, systems, and apparatus for multi-sensory stereo vision for robotics

An event is detected that impairs a confidence level of the autonomous vehicle in progressing through a current route. In response to detecting the event, the autonomous vehicle communicates information about the event to a remote source of guidance. The autonomous vehicle can receive instructions from the remote source of guidance on how to handle the event. The autonomous vehicle can then implement the instructions to handle the event while it operates.

Providing remote assistance to an autonomous vehicle

Growing community of inventors

Pittsburgh, PA, United States of America

David LaRose