Honeywell International Inc.

The Toro Company

Ryan Douglas Ingvalson

Alexander Steven Frick

Jason Thomas Kraft

Michael Ray Elgersma

Vibhor L Bageshwar

Wesley J Hawkinson

Robert C McCroskey

David LaRose

Wayne A Soehren

Michael Jason Ramsay

Paul Samanant

Adam Richard Williams

Christopher Charles Osterwood

Zachary Irvin Parker

Stephen Paul Elizondo Landers

Timothy Bertram Cleveland

David Arthur Larose

Brian Daniel Beyer

Apparatus, systems, and methods for directing an autonomous robotic vehicle such as a lawn mower relative to a work region. In some embodiments, the vehicle travels in a random pattern within a travelling containment zone of a lesser size than the work region. The travelling containment zone may move or travel across the work region such that, over time, the travelling containment zone travels over most all of a working surface of the work region.

System and method for operating an autonomous robotic working machine within a travelling containment zone

This disclosure provides an autonomous machine system having a scheduling controller configured to determine one or more windows of availability over a time period when the autonomous machine is allowed to operate to perform one or more operational tasks; determine a total operation time over the time period; and determine an operating schedule for a work region that assigns one or more operational tasks to the one or more windows of availability based on the total operation time. The autonomous machine may be commanded to operate in the work region according to the operating schedule.

Smart scheduling for autonomous machine operation

Autonomous machine navigation techniques may generate a three-dimensional point cloud that represents at least a work region based on feature data and matching data. Pose data associated with points of the three-dimensional point cloud may be generated that represents poses of an autonomous machine. A boundary may be determined using the pose data for subsequent navigation of the autonomous machine in the work region. Non-vision-based sensor data may be used to determine a pose. The pose may be updated based on the vision-based pose data. The autonomous machine may be navigated within the boundary of the work region based on the updated pose. The three-dimensional point cloud may be generated based on data captured during a touring phase. Boundaries may be generated based on data captured during a mapping phase.

Autonomous machine navigation and training using vision system

A method of mitigating filter inconsistency of a heading estimate in an inertial navigation system is provided. The method includes inputting inertial measurements from at least one low-performance inertial measurement unit (IMU) in the inertial navigation system; inputting an initial-heading from at least one heading-information source; inputting an initial-heading uncertainty level associated with an error in the inputted initial-heading; initializing an initial-heading estimate with the inputted initial-heading; initializing an initial-heading uncertainty estimate with the inputted initial-heading uncertainty level; initializing an accumulated heading-change estimate to zero at a startup of the at least one low-performance IMU; and initializing an accumulated heading-change uncertainty estimate with an initial accumulated heading-change uncertainty level that is a value less than the inputted initial-heading uncertainty level; and periodically updating the accumulated heading-change estimate with the inertial measurements input from the at least one low-performance IMU.

Heading inconsistency mitigation for inertial navigation using low-performance inertial measurement units with relative aiding

A method for data sharing between conditionally independent filters is provided. The method comprises initializing a plurality of conditionally independent filters operating in parallel, processing data measurements in each of the conditionally independent filters, sharing conditioning node estimates among the conditionally independent filters, merging the shared conditioning node estimates in each of the conditionally independent filters, and performing a conditional update in each of the conditionally independent filters.

Data sharing among conditionally independent parallel filters

A system and method for motion-based adaptive frequency estimation of a Doppler sensor is provided. The system comprises a Doppler sensor configured to output a digitized Doppler data signal, and a Doppler velocity estimation module operatively coupled to the Doppler sensor to receive the Doppler data signal. An inertial navigation system is operatively coupled to the Doppler velocity estimation module, and one or more inertial sensors is operatively coupled to the inertial navigation system. The inertial sensors are configured to transmit inertial navigation data to the inertial navigation system. The Doppler velocity estimation module calculates a speed or velocity estimate based on the Doppler data signal and the inertial navigation data. The speed or velocity estimate is then transmitted to the inertial navigation system.

Motion-based adaptive frequency estimation of a doppler velocity sensor

Embodiments of the present invention provide improved systems and methods for estimating N-dimensional parameters while sensing fewer than N dimensions. In one embodiment a navigational system comprises a processor and an inertial measurement unit (IMU) that provides an output to the processor, the processor providing a navigation solution based on the output of the IMU, wherein the navigation solution includes a calculation of an n-dimensional parameter. Further, the navigational system includes at most two sensors that provide an output to the processor, wherein the processor computes an estimate of an n-dimensional parameter from the output of the at most two sensors for bounding errors in the n-dimensional parameter as calculated by the processor when the trajectory measured by the IMU satisfies movement requirements, wherein 'n' is greater than the number of the at most two sensors.

Estimation of N-dimensional parameters while sensing fewer than N dimensions

A method for collaborative navigation comprises initializing a conditionally independent filter on a local platform, propagating the conditionally independent filter forward in time, and when a local measurement has been made, updating the conditionally independent filter with the local measurement. When a common measurement has been made, the conditionally independent filter is updated with the common measurement, and a determination is made whether a remote conditioning node has arrived from a remote platform. If a remote conditioning node has arrived, a determination is made whether the remote conditioning node needs to be fused with a local conditioning node of the conditionally independent filter. If the remote conditioning node needs to be fused, a node-to-node fusion is performed in the conditionally independent filter to merge the remote conditioning node with the local conditioning node to produce a merged conditioning node. A conditional update of the conditionally independent filter is then performed.

Shared state selection and data exchange for collaborative navigation using conditionally independent parallel filters

Systems and methods for differential altitude estimation utilizing spatial interpolation of pressure sensor data are provided. In one embodiment, a method for mobile navigation comprises: measuring a horizontal location of a mobile navigation unit to generate two-dimensional horizontal coordinate data; measuring a barometric pressure at the mobile navigation unit with a sensor to obtain local pressure data; processing information representative of pressure data derived from a network of a plurality reference stations to obtain a correction factor; performing a calculation using the two-dimensional horizontal coordinate data, the local pressure data, and the correction factor to calculate an altitude coordinate; and determining an altitude of the mobile navigation unit from the altitude coordinate.

Growing community of inventors

Loretto, MN, United States of America

Ryan Douglas Ingvalson