Waymo LLC

Google Inc.

Craig Lewin Robinson

Colin Andrew Braley

Seth Michael LaForge

John Tisdale

Russell Leigh Smith

Volker Grabe

Andrew Crawford

James Roseborough

Zachary Morriss

Alec Berg

Stephanie McArthur

Daniel Joseph Filip

Paul Karplus

Mingcheng Chen

Christian Lauterbach

Alexander Zbrozek

Marco Zennaro

Arunachalam Narayanaswamy

Damien Dusha

Dennis William Strelow

Jonathan Oliver Nichols

Sheng Zhao

Ionut Iordache

Hamid Mokhtarzadeh

Samuel Felix De Sousa, Jr

Shawn Nematbakhsh

Jose Melendez

A method of updating a clock associated with an autonomous vehicle includes determining, at a processor, a sensor-based position of the autonomous vehicle, which is determined based on data from one or more sensors and based on a digital map. The method also includes determining, at the processor, a global positioning system (GPS) computed position of the autonomous vehicle and a GPS time. The GPS computed position and the GPS time are determined based on a plurality of GPS signals received from GPS satellites. The method further includes comparing the sensor-based position to the GPS computed position to determine whether the sensor-based position is within a threshold distance from the GPS computed position. The method also includes updating the clock associated with the autonomous vehicle based on the GPS time in response to a determination that the sensor-based position is within the threshold distance from the GPS computed position.

Global positioning system time verification for autonomous vehicles

One example system for determining the orientation of a rotating platform comprises a rotating platform, a first magnetic field sensor configured to sense a magnetic field pointing in a first direction, a second magnetic field sensor configured to sense a magnetic field pointing in a second direction, wherein the second direction is different than the first direction (e.g., opposite the first direction), and at least one magnet producing a local magnetic field. The first magnetic field sensor, the second magnetic field sensor, and the at least one magnet are positioned relative to the rotating platform such that rotation of the rotating platform causes a change in the orientation of the local magnetic field relative to the first magnetic field sensor and the second magnetic field sensor.

Mitigating external magnetic fields on magnetic angle sensors

A method of updating a clock associated with an autonomous vehicle includes determining, at a processor, a sensor-based position of the autonomous vehicle. The sensor-based position is determined based on data from one or more sensors and based on a digital map accessible to the processor. The method also includes determining, at the processor, a global positioning system (GPS) computed position of the autonomous vehicle and a GPS time. The GPS computed position and the GPS time are determined based on a plurality of GPS signals received from GPS satellites. The method further includes comparing the sensor-based position to the GPS computed position to determine whether the sensor-based position is within a threshold distance from the GPS computed position. The method also includes updating the clock associated with the autonomous vehicle based on the GPS time in response to a determination that the sensor-based position is within the threshold distance from the GPS computed position.

The technology relates to localizing a vehicle. As one approach, a first LIDAR sensor scan data of an environment of the vehicle and localization data for the vehicle at a location where the first LIDAR sensor scan was captured are stored. Thereafter, the computing device is suspended and subsequently unsuspended. After the computing device is unsuspended, second LIDAR sensor scan data of the vehicle's environment is received. The first LIDAR sensor scan data is compared to the second LIDAR sensor scan data to determine whether the vehicle has moved. Based on the determination of whether the vehicle has moved from the location, the stored localization data is used to localize the vehicle. Other approaches are also described.

Localization initialization for autonomous vehicles

One example method involves generating a calibration control signal that causes an actuator to rotate a first platform at least one complete rotation about an axis. The method also involves receiving encoder output signals. The encoder output signals are indicative of angular positions of the first platform about the axis. The method also involves receiving sensor output signals from an orientation sensor mounted on the first platform. The sensor output signals are indicative of a rate of change to an orientation of the orientation sensor. The method also involves determining calibration data based on given sensor output signals received from the orientation sensor during the at least one complete rotation. The calibration data is for mapping the encoder output signals to calibrated measurements of the angular positions of the first platform about the axis.

Devices and methods for rotary encoder calibration

Systems and methods for extrinsic calibration of vehicle-mounted sensors are provided. One example method involves obtaining first sensor data collected by a first sensor and a second sensor while a vehicle is aligned in a first yaw direction. The method also involves obtaining second sensor data collected by the first sensor and the second sensor while the vehicle is aligned in a second yaw direction. The method also involves determining, based on the first sensor data and the second sensor data, (i) first pitch and roll misalignments of the first sensor relative to the vehicle and (ii) second pitch and roll misalignments of the second sensor relative to the first sensor. The method also involves determining third pitch and roll misalignments of the second sensor relative to the vehicle based on (i) the first pitch and roll misalignments and (ii) the second pitch and roll misalignments.

Extrinsic calibration of sensors mounted on a vehicle

Example systems and methods are disclosed for determining vehicle pose data for an autonomous vehicle. The vehicle computer system may receive pose data from multiple pose measurement systems of the autonomous vehicle. Each pose measurement system may include one or more corresponding sensors of the autonomous vehicle. The vehicle computer system may determine a pose data quality for the received pose data for each pose measurement system. The vehicle computer system may set the vehicle pose data to the pose data of the pose measurement system with the highest pose data quality. The vehicle computer system may control the autonomous vehicle based on the vehicle pose data.

System and method for determining pose data for a vehicle

Systems and methods for estimating sensor timestamps by oversampling are provided. One example method involves observing, at a sampling frequency, sensor data from a register of a sensor. The sensor updates the register with sensor data at as sensor update frequency. The sampling frequency is different from the sensor update frequency. The method also involves generating, based on the sensor update frequency and the sampling frequency, an observed sequence representing the sensor data. The observed sequence indicates whether the register is observed to be updated or not updated. The method also involves estimating, from the observed sequence, the sensor update frequency and a sensor update phase. The method also involves determining, based on the sensor update frequency as estimated and the sensor update phase as estimated, a timestamp corresponding to an update of the register.

Estimating sensor timestamps by oversampling

The disclosure provides for a method of calibrating a detection system that is mounted on a vehicle. The method includes detecting characteristics of the mirror and characteristics of a vehicle portion using the detection system. The mirror reflects the vehicle portion to be detected using the detection system. The method also includes determining a first transform based on the detected one or more of mirror characteristics, determining a second transform based on the one or more vehicle portion characteristics, and determining a third transform based on a known position of the vehicle portion in relation to the vehicle. Further, the method includes determining a position of the detection system relative to the vehicle based on the first, second, and third transforms and then calibrating the detection system using the determined position of the detection system relative to the vehicle.

Calibration of detection system to vehicle using a mirror

In one example, a vehicle includes a platform and a yaw sensor mounted on the platform. The yaw sensor provides an indication of a yaw rate of rotation of the yaw sensor. The vehicle also includes an actuator that rotates the platform. The vehicle also includes a controller coupled to the yaw sensor and the actuator. The controller receives the indication of the yaw rate from the yaw sensor. The controller also causes the actuator to rotate the platform (i) along a direction of rotation opposite to a direction of the rotation of the yaw sensor and (ii) at a rate of rotation based on the yaw rate of the yaw sensor. The controller also estimates a direction of motion of the vehicle in an environment of the vehicle based on at least the rate of rotation of the platform.

Devices and methods for a sensor platform of a vehicle

Aspects of the disclosure provide for a method of calibrating a vehicle's plurality of detection systems. To calibrate a first detection system, orientation data is collected using the first detection device when the vehicle faces a first direction and a second direction opposite the first direction. To calibrate a second detection system, data is collected using the second detection device while the vehicle moves in a repeatable pattern near a first object. To calibrate a third detection system, light reflected off a second object is detected using the third detection system as the vehicle is moved towards the second object. To calibrate a fourth detection system, data collected using the second detection system and the fourth detection system is compared. To calibrate a fifth detection system, radar signals reflected off a third object is received using the fifth detection system while the vehicle moves relative to the third object.

Method and system for calibrating a plurality of detection systems in a vehicle

Camera pose optimization, which includes determining the position and orientation of a camera in three-dimensional space at different times, is improved by detecting a higher-confidence reference object in the photographs captured by the camera and using the object to increase consistency and accuracy of pose data. Higher-confidence reference objects include objects that are stationary, fixed, easily recognized, and relatively large. In one embodiment, street level photographs of a geographic area are collected by a vehicle with a camera. The captured images are geo-coded using GPS data, which may be inaccurate. The vehicle drives in a loop and captures the same reference object multiple times from the substantially same position. The trajectory of the vehicle is then closed by aligning the points of multiple images where the trajectory crosses itself. This creates an additional constraint on the pose data, which in turn improves the data's consistency and accuracy.

Growing community of inventors

Palo Alto, CA, United States of America

Craig Lewin Robinson