Google Inc.

Moog Gmbh

Sirf Technology, Inc.

Csr Technology Inc.

Qiyue Zhang

Chao X Guo

Luca Ballan

Mahesh Ramachandran

Hongsheng Yu

Fengtao Fan

Gengsheng Zhang

Lionel Jacques Garin

Mangesh M Chansarkar

Mahesh Chowdhary

Ashutosh Pande

Ralph Michael Kling

Steve Chang

Konstantine Nicholas John Tsotsos

Darren S Liccardo

Michael A Horton

Anthony Malerich

Jie Zhang

Semen Shtigluz

A tracking system and associated algorithms are disclosed that can provide a user with a continuous, reset-free augmented reality (AR) experience. When the user wears an AR headset equipped with a camera and an inertial measurement unit (IMU), motion sensor data from the IMU can be combined with image data from the camera to create a device pose, representing a position and an orientation of the headset relative to its environment. In some implementations, when a reset occurs, a six-degrees-of-freedom (6DoF) algorithm can be configured to support the pose until a re-initialization is completed. In some implementations, a neural network can be used to correct for IMU integration drifts in the 6DoF algorithm. In some implementations, the IMU-based 6DoF uses a neural network that exploits the device's past motion to infer its future motion.

Pose algorithm for continuous AR experiences

Techniques of providing continual augmented reality navigation include combining first and second 6DoF poses from, respectively, a localization from a map in a vicinity of a location to an image and from predicted 6DoF poses based on IMU data. The first 6DoF pose is based on a visual positioning system that uses map data from a vicinity of a location combined with an image from the world-facing camera of the AR smartglasses that provides 6DoF pose in world coordinates independent of the IMU. The second 6DoF pose is based on compensated rotational velocity and acceleration measurements derived from IMU intrinsic values.

Map-aided inertial odometry with neural network for augmented reality devices

Techniques of providing continual augmented reality navigation include combining first and second 6DoF poses from, respectively, a localization from a map in a vicinity of a location to an image and from predicted 6DoF poses based on IMU data.

A true north heading is determined by using gyroscopes of differing accuracy and orienting a gyroscope of a higher accuracy to a direction that is more sensitive to azimuth change (e.g., an east/west direction). A gyroscope with a lower accuracy is placed perpendicular to the gyroscope with a higher accuracy and can be oriented towards a north or south direction. The gyroscopes may be placed on a rotatable platform to properly orient the gyroscopes. The higher-accuracy gyroscope may be implemented by using multiple gyroscopes oriented in the same direction.

North-finding using inertial navigation system

A navigation system repeatedly determines a GNSS heading for the vehicle based on GNSS data received from the GNSS receiver, and repeatedly determines an inertial heading for the vehicle based on data received from an inertial measurement unit. The navigation system repeatedly sets the inertial heading to a verified GNSS heading and then provides the set inertial heading as input to a recursive feedback algorithm. The recursive feedback algorithm receives additional inputs indicating the vehicle's angular displacement or acceleration and outputs an updated inertial heading. The navigation system compares the subsequently determined GNSS headings with the updated inertial heading. If the two headings are different, the navigation system sets the GNSS heading to the updated inertial or 180 degree reverse of the GNSS heading.

Vehicle heading validation using inertial measurement unit

A shuttle message that is passed between GPS enabled devices that is processed at either a bit level or word level with data that the GPS enable device has already gathered and augmenting the positioning data stored at GPS enabled devices by retrieving data contained in the shuttle message. The shuttle message is then passed with any updated information from a GPS enabled device to one or more other devices such as a mobile station.

Distributed data collection of satellite data

Systems and methods for detecting a vehicle static condition are provided. In this regard, a representative system includes a sensor operative to detect at least one of acceleration and angular rate of a vehicle. The sensor is further operative to generate a vehicle vibration profile based on the at least one of the detected acceleration and angular rate of the vehicle. The system further includes a computing device operative to receive the vehicle vibration profile from the sensor, the computing device being further operative to determine whether the vehicle is stationary or moving based on the vehicle vibration profile. A representative method for detecting a vehicle static condition includes detecting at least one of acceleration and angular grade of a vehicle; generating a vehicle vibration profile based on at least one of the detected acceleration and angular grade of the vehicle; receiving the vehicle vibration profile; and determining whether the vehicle is stationary or moving based on the vehicle vibration profile.

Systems and methods for detecting a vehicle static condition

Growing community of inventors

Cupertino, CA, United States of America

Qiyue Zhang