Uber Technologies, Inc.

Carnegie Mellon University

Uatc, LLC

Caterpillar Inc.

Peter W Rander

David McAllister Bradley

Anthony Joseph Stentz

Bryan John Nagy

Matthew Shaw Wood

Brett Browning

Randon Warner

Kenneth Lee Stratton

Herman Herman

Michael Lee Phillips

Takeo Kanade

Eric Michael Perko

Colin Jeffrey Green

Alonzo James Kelly

Jessica Elizabeth Smith

Randy Warner

Louis A Bojarski

P J Narayanan

Jason Ziglar

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

Systems and methods for autonomous vehicle testing are provided. In one example embodiment, a computer implemented method includes obtaining, by a computing system including one or more computing devices, simulated perception data indicative of one or more simulated states of at least one simulated object within a surrounding environment of an autonomous vehicle. The computer-implemented method includes determining, by the computing system, a motion of the autonomous vehicle based at least in part on the simulated perception data. The computer-implemented method includes causing, by the computing system, the autonomous vehicle to travel in accordance with the determined motion of the autonomous vehicle through the surrounding environment of the autonomous vehicle.

Autonomous vehicle hybrid simulation testing

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

A vehicle determines a traction value for a surface of a road segment, and associates the traction value with a location of the surface. The vehicle stores the traction value and location as part of a traction map.

Vehicle traction map for autonomous vehicles

An autonomous vehicle (AV) can receive a pick-up location to rendezvous with a rider and a set of configuration instructions to configure one or more adjustable components of the configurable interior system for the rider. The AV can analyze sensor data to autonomously control acceleration, steering, and braking systems along a route to the pick-up location. Prior to arriving at the pick-up location, the AV can execute the set of configuration instructions to configure the one or more adjustable components of the configurable interior system for the rider.

Configuring an autonomous vehicle for an upcoming rider

A computer system maintains, for a given geographic region, a data structure that identifies a traction value for each of a plurality of locations of a road network within a geographic region. At least of a start or destination location is determined for the trip. The computer system may plan the trip, including selecting at least one of a route or a vehicle to use for the trip, based on the traction values of one or more of the plurality of locations.

Planning trips on a road network using traction information for the road network

A computer system operates to determine a traction value for each of a plurality of regions of the road network. A region of the road network for which the traction value is unknown is identified. A vehicle is directed to operate over the region of the road network to obtain additional data that is indicative of a current traction value.

System and method to determine traction of discrete locations of a road segment

An autonomous vehicle (AV) can receive a pick-up location from a backend transport facilitation system to service a pick-up request from a requesting user. The AV can further process sensor data from a sensor array of the AV to dynamically identify potential hazards while autonomously operating the AV along a current route to the pick-up location. The AV can receiving, from the backend transport facilitation system, a set of configuration instructions to configure adjustable components of an interior of the AV based on comfort preferences of the requesting user, and determine an optimal timing schedule to implement each of the set of configuration instructions. Thus, the AV can execute the set of configuration instructions based on the optimal timing schedule to configure the adjustable components of the configurable interior system prior to arriving at the pick-up location.

Optimizing timing for configuring an autonomous vehicle

A mapping system includes a pose sensor, a mapping sensor, a database defining a work surface, and a controller. The controller is configured to receive pose signals and determine the position and the orientation of the machine and receive mapping signals and determine a plurality of raw data points. The controller further determines a plurality of machine points defining a position of a portion of the machine and filters the plurality of raw data points based upon the plurality of machine points to define a plurality of filtered data points. The database may be updated with the plurality of filtered data points.

System and method for terrain mapping

A method and system for controlling an apparatus including receiving data indicative of an actual state of the apparatus, defining a first viewpoint relative to at least one of the environment and the apparatus, determining a first predicted state of the apparatus at time T, determining a first predicted state of the environment at time T, producing a first virtualized view from the first viewpoint, sending a first control signal to the apparatus after producing the first virtualized view, defining a second viewpoint relative to at least one of the apparatus and the environment, determining a second predicted state of the apparatus at time T+delta T, determining a second predicted state of the environment at time T+delta T, producing the second virtualized view from the second viewpoint, sending a second control signal to the apparatus after producing the second virtualized view, and changing the actual state of the apparatus based on the first control signal.

Apparatuses, systems, and methods for apparatus operation and remote sensing

A method of virtualizing reality, i.e., a method of creating virtual reality from images of a real event, is comprised of the steps of capturing a plurality of images of each time instant of a real event using a plurality of cameras positioned at a plurality of angles. Each image is stored as intensity and/or color information. A suitable internal representation is computed from these images and the information regarding the camera angles. An image of each time instant may be generated from any viewing angle using the internal representation of it. The virtual viewpoints could be displayed on a single TV screen or using a stereoscopic display device for a true three-dimensional effect. The event thus virtualized can be navigated through, and interacted with, any virtual reality system.

Growing community of inventors

Pittsburgh, PA, United States of America

Peter W Rander