Carnegie Mellon University

Uatc, LLC

Uber Technologies, Inc.

Eyesee360, Inc.

Other

Aurora Operations, Inc.

360Fly, Inc.

Eyesee380, Inc.

Anthony Joseph Stentz

Herman Herman

Sanjiv Singh

Bryan John Nagy

Michael Rondinelli

Mark Ollis

Patrick S Rowe

David McAllister Bradley

Michael Lee Phillips

Eric Michael Perko

Colin Jeffrey Green

Peter W Rander

Carl Knox Wellington

Wei Liu

Eric Lloyd Wilkinson

John E Bares

Kalin Vasilev Gochev

Samuel Philip Marden

Don Burnette

Somchaya Liemhetcharat

Harishma Dayanidhi

William L Whittaker

Brett Browning

Brett Bavar

Xiaodong Zhang

Moslem Kazemi

Adam Cole Panzica

Christopher Chandler Fromme

Alonzo James Kelly

Kerien W Fitzpatrick

Frank Higgins

Bryan G Campbell

Aaron C Courville

Robert Dean

David K Herdle

Jean-Sebastien Valois

Galen Clark Haynes

Nemanja Djuric

Jeff Schneider

Michael Happold

Micol Marchetti-Bowick

Eric Meyhofer

Tian Lan

Vladan Radosavljevic

Alexander David Styler

Tsung-Han Lin

Tzu-Kuo Huang

Thomas E Pilarski

Neil Traft

Christopher L Baker

Timothy Ennis Hegadorn

Henning M Pangels

Patrick C Leger

Regis Hoffman

Ian Dewancker

Huahua Wang

Stuart Edwin Lawrence, Iii

Christopher Randolph Baker

David G Galati

Justin C Haines

Andrew Strat

Brad Simon

Norman Keith Lay

Keith Lay

Richard McCargo Moore, Jr

Jorgen Pedersen

Steven John Scheding

Jorgen Pederson

Alonzo J Kelley

Stuart Edwin Lawrence

Peter Rander

The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can generate constraints based on where objects of interest are predicted to be relative to an autonomous vehicle. A constraint solver can identify navigation decisions for each of the constraints that provide a consistent solution across all constraints. The solution provided by the constraint solver can be in the form of a trajectory path determined relative to constraint areas for all objects of interest. The trajectory path represents a set of navigation decisions such that a navigation decision relative to one constraint doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints.

Discrete decision architecture for motion planning system of an autonomous vehicle

The present disclosure is directed to validating motion plans for autonomous vehicles. In particular, the methods, devices, and systems of the present disclosure can: receive data indicating a motion plan of an autonomous vehicle through an environment of the autonomous vehicle; receive data indicating one or more inputs utilized in generating the motion plan; and determine, based at least in part on the data indicating the motion plan and the data indicating the input(s), whether execution of the motion plan by the autonomous vehicle would violate one or more predetermined constraints applicable to motion plans for the autonomous vehicle.

Motion-plan validator for autonomous vehicle

A system can analyze a sensor view of a surrounding area of a self-driving vehicle (SDV). Based on analyzing the sensor view, the system can determine that a decision point along a current route of the SDV exceeds a predetermined risk threshold, and diverge the SDV from the current route based at least in part on the decision point exceeding the predetermined risk threshold.

Dynamic routing for self-driving vehicles

A control system for an autonomous vehicle can determine a risk value for each respective path segment of a plurality of path segments in a given area that includes a destination of the autonomous vehicle. The risk value can correspond to a cost layer in a map that includes the respective path segment. Based on the risk value for each respective path segment, the control system can determine a travel route for the autonomous vehicle to the destination, and autonomously control the autonomous vehicle to navigate along the travel route to the destination.

Autonomous vehicle routing using annotated maps

A control system of a self-driving vehicle (SDV) can process sensor data from the sensor system to autonomously operate acceleration, braking, and steering systems of the SDV throughout a given region. The control system can receive a transport directive from a transport facilitation system to service a pick-up request from a requesting user, the transport directive indicating an inputted pick-up location by the requesting user. The control system can then autonomously operate the acceleration, braking, and steering systems along a current route to a pick-up area encompassing the inputted pick-up location. The control system can further determine a corresponding set of pick-up location options for the pick-up area, and as the SDV approaches the pick-up area, perform a hierarchical operation to identify, via the sensor data, an optimal pick-up location to rendezvous with the requesting user.

Facilitating rider pick-up for a self-driving vehicle

A transport system can receive vehicle data from each self-driving vehicle (SDV) in a fleet of SDVs operating throughout a given region. The transport system may further detect, in the vehicle data, a set of properties of one or more other vehicles external to the SDV. Based on the set of properties of the one or more vehicles, the transport system can construct traffic model(s) for the given region. Utilizing the traffic model(s), the transport system can provide estimated time of arrival (ETA) data, corresponding to SDVs in the fleet, to users of a transportation arrangement service in the given region.

Travel time estimation

The present disclosure provides systems and methods for predicting the future locations of objects that are perceived by autonomous vehicles. An autonomous vehicle can include a prediction system that, for each object perceived by the autonomous vehicle, generates one or more potential goals, selects one or more of the potential goals, and develops one or more trajectories by which the object can achieve the one or more selected goals. The prediction systems and methods described herein can include or leverage one or more machine-learned models that assist in predicting the future locations of the objects. As an example, in some implementations, the prediction system can include a machine-learned static object classifier, a machine-learned goal scoring model, a machine-learned trajectory development model, a machine-learned ballistic quality classifier, and/or other machine-learned models. The use of machine-learned models can improve the speed, quality, and/or accuracy of the generated predictions.

Machine learning for predicting locations of objects perceived by autonomous vehicles

A system and method for autonomous vehicle routing using annotated maps. For at least some path segments within a geographic region in which the vehicle is operating, values are determined for the path segments based at least on risk factors associated with autonomous operation of the vehicle along each path segment. Path segments are combined to generate a travel route, from a first location to a second location, based on the determined values, and the vehicle is controlled to navigate along the travel route.

A self-driving vehicle (SDV) can dynamically analyze a sensor view of a surrounding area of the SDV, and a current localization map in order to autonomously operate acceleration, braking, and steering systems of the SDV along a current route to a destination. Upon approaching a decision point along the current route, the SDV can perform a cost optimization to determine whether to diverge from the current route.

An imaging system comprising a panoramic visual image display, an associated directional sound playback device, and an associated motion reproduction device is disclosed. The imaging system conveys visual, sound and motion information related to a particular viewing direction to provide a realistic experience for the viewer. The imaging system can also comprise a panoramic visual image recording device capable of recording panoramic images, an associated directional sound capturing device capable of recording sound, and an associated directional motion capturing device capable of recording motion. Recorded panoramic images, sound and motion can be synchronously recorded to a common time code for simultaneous playback.

Apparatus and method for playback of audio-visual recordings

The invention disclosed herein describes a supervised autonomy system designed to precisely model, inspect and process the surfaces of complex three-dimensional objects. The current application context for this system is laser coating removal of aircraft, but this invention is suitable for use in a wide variety of applications that require close, precise positioning and maneuvering of an inspection or processing tool over the entire surface of a physical object. For example, this system, in addition to laser coating removal, could also apply new coatings, perform fine-grained or gross inspection tasks, deliver and/or use manufacturing process tools or instruments, and/or verify the results of other manufacturing processes such as but not limited to welding, riveting, or the placement of various surface markings or fixtures.

Supervised autonomous robotic system for complex surface inspection and processing

Growing community of inventors

Pittsburgh, PA, United States of America

Anthony Joseph Stentz