Zoox, Inc.

Taylor Andrew Arnicar

Christopher James Gibson

Derek Adams

Michael Carsten Bosse

Johannes Edren

Till Kroeger

Peter Scott Schleede

Byungil Jeong

Aaron Guerrero

Era Yuan Yuan Ming

Systems and methods are provided where requests to modify or validate a road network map are received, and a determination is made as to whether a requested modification, or the road network map, is invalid based on a location at which the modification is desired to be made, and rules associated with a corresponding bounded area of the road network map to which the location belongs. Where a requested modification, or the road network map, is determined to be invalid, the modification is inhibited, or a notification is displayed to a user that the road network map violates the set of rules.

Validation of a road network map based on location bounded rules

Techniques are disclosed for utilizing synchronized robot observations. The techniques may include receiving first log data associated with a first vehicle, receiving second log data associated with a second vehicle, determining that a first portion of the first log data is time related to a second portion of the second log data, and using the first portion and the second portion for mapping and/or training models.

Using robot observations

Techniques for validating operation of vehicle systems using map data are described herein. The techniques may include receiving sensor data associated with an environment in which a vehicle is operating and generating estimated map data based at least in part on the sensor data. Additionally, stored map data may be received and compared with the estimated map data. If it is determined that an inconsistency exists between the estimated map data and the stored map data, the techniques may include determining whether the inconsistency is attributable to an error associated with the stored map data, the sensor data, or a localization system of the vehicle. As such, one or more specific remedial actions may then be performed based at least in part on determining that the error is associated with at least one of the stored map data, the sensor data, or the localization system.

Monitoring map data for validation of vehicle systems

Techniques for determining behavior profiles and unique identities for objects observed in an environment surrounding an autonomous vehicle are described. The behavior profiles may be generated and associated with unique identifiers that are stored and used by a fleet of vehicles for planning and navigating in traffic environments. The behavior profiles may be used to control operation of the vehicle and increase safety of the vehicle by identifying potentially risky or erratic objects and navigating through the environment accordingly. The behavior profiles may be stored at a central database and propagated across a fleet to increase observations used to build profiles and thereby increase profile confidence.

Autonomous vehicle interaction and profile sharing

Techniques for determining behavior profiles and unique identities for objects observed in an environment of an autonomous vehicle are described. The behavior profiles may be used to control operation of the vehicle and increase safety of the vehicle by identifying potentially risky or erratic behaviors and navigating through the environment accordingly. The behavior profiles may be stored locally for a short-term period of time to ensure rapid access to profiles when the object is observed and readily identified.

Autonomous vehicle interaction memory

Motion can be induced at a vehicle, e.g., by actuating components of an active suspension system, and first sensor data and second sensor data representing an environment of the vehicle can be captured at a first position and a second position, respectively, resulting from the induced motion. A second sensor can determine motion information associated with the first position and the second position. Calibration information about the sensor, the first sensor data, and the motion information can be used to determine an expectation of sensor data at the second position. A calibration error can be the difference between the second sensor data and the expected sensor data.

Sensor calibration and verification using induced motion

Techniques for determining a location and type of traffic-related features and using such features in route planning are discussed herein. The techniques may include determining that sensor data represents a feature such as a traffic light, road segment, building type, and the like. The techniques further include determining a cost of a feature, whereby the cost is associated with the effect of a feature on a vehicle traversing an environment. A feature database can be updated based on features in the environment. A cost of the feature can be used to update costs of routes associated with the location of the feature.

Capturing features for determining routes

An augmentation system may supplement a person's view from at least one of an actual vehicle or a virtual vehicle of an environment through which the vehicle travels. The system may include a receiver configured to receive data signals representative of operation of the vehicle and representative of objects in the environment through which the vehicle travels. The system may also include a converter in communication with the receiver. The converter may be configured to convert the data signals into display data representative of the operation of the vehicle and representative of the objects in the environment through which the vehicle travels. The converter may also be configured to communicate the display data to a display in communication with the converter and configured to display, within the person's view from the vehicle, images representative of the display data to supplement the person's view.

Growing community of inventors

Sunnyvale, CA, United States of America

Taylor Andrew Arnicar