Waymo LLC

Kevin Joseph Malta

Lauren Schwendimann

Maria Moon

Bruce Mai

Jonathan Willing

Reed Morse

Jonathan Lee Pedersen

Victor Chan

Philip Moltmann

Peter Crandall

Clement Wright

Ganesh Balachandran

Donghyun Kim

Kyle Bechtel

Daniella Gutlansky

Yu Zheng

Steven Kleiser

Eamonn Michael Doherty

Chung Eun Kim

Jason Persampieri

Brian Clair Williammee

Shiqian Zhang

Celia Zhang

Aspects of the disclosure provide for generating and using a model for identifying a plurality of pick up or drop off locations for a large venue point of interest. For instance, a large venue point of interest may be identified. The plurality may be identified for the large venue point of interest based on a combination of historical trip data and map information. The plurality may be associated with the large venue point of interest. The association may be stored in memory for later use. Thereafter, a request for a trip identifying the large venue point of interest may be received from a client computing device, and the plurality may be provided to the client computing device in response to the request. A pickup and drop off location of the plurality may be provided to an autonomous vehicle in order to cause the autonomous vehicle to transport a passenger to the pickup or drop off location.

Determining pickup and drop off locations for large venue points of interests

The technology uses augmented reality (AR) elements for enhanced wayfinding with autonomous vehicle pickups and drop-offs. The approach includes generating, for presentation in a first region of a client device UI, trip information regarding a trip. Map information associated with the trip is generated for presentation in a second UI region, including at least one of a pickup location for a rider, a walking path from a current location of the rider to the pickup location, a planned route of the vehicle to the pickup location, or a current location of the vehicle. An AR indicator is generated for presentation in the second UI region. Upon selection of the indicator, the system modifies the second region into a first section to display at least a portion of the map information and a second section to display an augmented reality view, or replace the map information with the AR view.

Augmented reality wayfinding

The technology employs a holistic approach to passenger pickups and other wayfinding situations. This includes identifying where passengers are relative to the vehicle and/or the pickup location. One aspect leverages camera imagery from a rider's client device when providing rider support. This enables an agent to receive the imagery to help guide the rider to the vehicle. Another aspect provides audio information to the rider to help them get to the vehicle. This can include selecting or curating various tones or melodies, giving the rider advanced notice of sounds to listen for, and modifying sounds as the rider approaches the vehicle or to address ambient noise in the environment. Different wayfinding tools may be selected for presentation to the rider based on their proximity state to a pickup location or to the vehicle. Gracefully transitioning between different tools can enhance their usefulness and elevate the rider's experience for a trip.

Holistic and inclusive wayfinding

Aspects of the disclosure provide for arranging tour trips. For instance, a request identifying a pickup location for a tour trip may be received from a client computing device. A set of tours may be selected from a plurality of pre-stored tours based on the pickup location. Each of the plurality of pre-stored tours may include tour locations. The set of tours may be provided to the client computing device for display. Information identifying one of the set of tours may be received from the client computing device. Instructions may be provided to an autonomous vehicle to cause the autonomous vehicle to complete the tour trip by maneuvering to the pickup location and thereafter visit one or more tour locations included in the identified one of the set of tours.

Arranging tour trips using autonomous vehicles

Aspects of the disclosure provide for arranging a trip in an autonomous vehicle without a driver. For instance, a request may be received from a client computing device associated with a first person to arrange the trip for a second person. The request may include a pickup location for the second person and a destination location for the second person. An authentication method may be identified for the trip. A signal may be sent to the autonomous vehicle in order to cause the autonomous vehicle to maneuver to the pickup location, authenticate the second person using the authentication method, and transport the second person to the destination location.

Arranging passenger trips for autonomous vehicles

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a pull-over location using machine learning. One of the methods includes obtaining data specifying a target pull-over location for an autonomous vehicle travelling on a roadway. A plurality of candidate pull-over locations in a vicinity of the target pull-over location are identified. For each candidate pull-over location, an input that includes features of the candidate pull-over location is processed using a machine learning model to generate a respective likelihood score representing a predicted likelihood that the candidate pull-over location is an optimal location. The features of the candidate pull-over location include one or more features that compare the candidate pull-over location to the target pull-over location. Using the respective likelihood scores, one of the candidate pull-over locations is selected as an actual pull-over location for the autonomous vehicle.

Pull-over location selection using machine learning

The technology employs a holistic approach to passenger pickups and other wayfinding situations. This includes identifying where passengers are relative to the vehicle and/or the pickup location. Information synthesis from different sensors, agent behavior prediction models, and real-time situational awareness are employed to identify the likelihood that the passenger to be picked up is at a given location at a particular point in time, with sufficient confidence. The system can provide adaptive navigation by helping passengers understand their distance and direction to the vehicle, for instance using various cues via an app on the person's device. Rider support tools may be provided, which enable a remote agent to interact with a customer via that person's device, such as using the camera on the device to provide wayfinding support to enable the person to find their vehicle. Ride support may also use sensor information from the vehicle when providing wayfinding support.

Identifying a customer of an autonomous vehicle

Growing community of inventors

San Francisco, CA, United States of America

Kevin Joseph Malta