Waymo LLC

Google Inc.

Yu-Hsin Chen

Michael Epstein

John Wesley Dyer

Luis Torres

Ignacio Lopez Moreno

Vadim Furman

Matthieu Devin

Aleksandra Faust

Franklin Morley

Carlos Alberto Fuertes Pascual

Aspects of the disclosure provide systems and methods for confirming the identity of a passenger and changing destination of a vehicle. This may include receiving dispatching instructions to pick up a first passenger at a pickup location and to drop off the first passenger at a first destination as well as authentication information for authenticating a first client computing device of the first passenger. Once the client device is authenticated and a second passenger enters the vehicle, the vehicle is maneuvered towards the first destination. While doing so, a location of the vehicle is compared to location information received from the client computing devices. A notification is sent to a dispatching server based on the comparison and a second destination location is received in response. The vehicle is then maneuvered towards the second destination instead of the first destination.

Identifying unassigned passengers for autonomous vehicles

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes generating, by a speech recognition system, a matrix from a predetermined quantity of vectors that each represent input for a layer of a neural network, generating a plurality of sub-matrices from the matrix, using, for each of the sub-matrices, the respective sub-matrix as input to a node in the layer of the neural network to determine whether an utterance encoded in an audio signal comprises a keyword for which the neural network is trained.

Sub-matrix input for neural network layers

Aspects of the disclosure provide systems and methods for recognizing an assigned passenger. For instance, dispatching instructions to pick up a passenger at a pickup location are received. The instructions include authentication information for authenticating a client computing device associated with the passenger. A vehicle is maneuvered in an autonomous driving mode towards the pickup location. The client device is then authenticated. After authentication, a set of pedestrians within a predetermined distance of the vehicle are identified from sensor information generated by a sensor of the vehicle and location information is received over a period of time from the client device. The received location information is used to estimate a velocity of the passenger. This estimated velocity is used to identify a subset of set of pedestrians that is likely to be the passenger. The vehicle is stopped to allow the passenger to enter the vehicle based on the subset.

Recognizing assigned passengers for autonomous vehicles

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing an interactive autonomous vehicle agent. One of the methods includes receiving a request to generate an experience tuple for a vehicle in a particular driving context. A predicted environment observation representing a predicted environment of the autonomous vehicle after the candidate action is taken by the autonomous vehicle in an initial environment is generated, including providing an initial environment observation and the candidate action as input to a vehicle behavior model neural network trained to generate predicted environment observations. An immediate quality value is generated from a context-specific quality model that generates immediate quality values that are specific to the particular driving context. An experience tuple comprising the initial environment observation, the candidate action, and the immediate quality value is generated and used as input to a reinforcement learning system for the autonomous vehicle.

Interactive autonomous vehicle agent

Growing community of inventors

Sunnyvale, CA, United States of America

Yu-Hsin Chen