Abstract: Techniques for autonomous vehicle boundary intersection detection and avoidance are described. In an example, a geofence boundary is received at a display coupled to a control module of a vehicle. A 2D footprint is generated using a definition of the vehicle and an implement coupled to the vehicle. Using geographic coordinates for the vehicle, a current position and orientation for the footprint are determined. A 2D projection footprint is generated for the vehicle using the current position and orientation, a current steering state, and a direction of travel. A first distance from the current position and orientation at which the projection footprint intersects with the boundary is determined. Based on the first distance, the speed of the vehicle is maintained at or below a maximum speed.

Abstract: Construction vehicles using a teach and repeat system can ascertain boundaries of a task area while working, without knowing a perimeter of the task area before starting the task. The system maps a first path of the vehicle by recording a position of a vehicle moving from a first start position to a first end position. A second path is predicted, based on a shape of the first path, the second path having a second start position and a second end position. A third path is mapped from a third start position to a third end position. Boundaries of the task area are ascertained based on the first path, the first start position, the second start position, the third start position, the third path, the first end position, the second end position, and the third end position.

Abstract: Techniques for orchestrating activities at an earthmoving site are described. In an example, a stream of images are captured by an image capturing device removably fixed to a mobile earthmoving machine with a field of view overlapping with a working range of an attachment coupled to the mobile earthmoving machine. Using a selected subset of images from the stream captured during a time period, a first trained algorithm generates a probability that the subset of images depicts an action performable by the machine. Based on the probability, it is determined that the machine was performing the action during the time period, and in response, an image from the subset of images is selected. The image and an indication that the machine was performing the action during the time period are transmitted to a remote server system through a network.

Abstract: Described herein are systems, methods, and other techniques for computing a position of a rover using satellite signals from a plurality of satellites. Safe ephemeris data may be received at a base station. The safe ephemeris data may indicate positions of the plurality of satellites. The safe ephemeris data may be wirelessly transmitted from the base station to the rover. Rover carrier-phase measurements may be obtained based on the satellite signals received at the rover. The position of the rover may be computed using at least the rover carrier phase measurements and the safe ephemeris data.

Abstract: Disclosed are a method and apparatus for determining the heading of a 4WS vehicle. The 4WS vehicle's dynamic pivot point is calculated from the steering angles. A distance between the dynamic pivot point and a Global Navigation Satellite System (GNSS) antenna is determined. A time delay is determined in the form of the distance between the GNSS antenna and the pivot point divided by the current vehicle horizontal velocity. The time delay is multiplied by a vehicle yaw rate to obtain a result which is added to a GNSS antenna heading to give a true heading. A control point for the 4WS vehicle is selected to allow that control point to follow a desired trajectory.

Abstract: Sets of digital samples associated with received wireless signals are received, each of the sets of digital samples corresponding to a particular RF path. The sets of digital samples are provided to a plurality of pipelines, each of the plurality of pipelines including a plurality of stages, each of the plurality of stages including one or more digital logic circuits. Sets of interconnect data are generated by the plurality of pipelines based on the sets of digital samples, the sets of interconnect data including at least one accumulating value. The sets of interconnect data are passed between adjacent pipelines of the plurality of pipelines along a direction. A result is generated by a last pipeline of the plurality of pipelines based on the at least one accumulating value.

Abstract: One or more three-dimensional models that corresponds to at least one two-dimensional image are determined by receiving image data that corresponds to the at least one two-dimensional image, generating features based on the image data corresponding to the at least one two-dimensional image, generating a representation vector for the at least one two-dimensional image by transforming the features into a predetermined amount of numerical representations corresponding to the features, and outputting the representation vector for the at least one two-dimensional image to facilitate a search query for the one or more three-dimensional models associated with the at least one two-dimensional image.

Abstract: Disclosed are a method and apparatus for avoiding collisions with obstacles by a first vehicle using sensors on an accompanying second vehicle. The second vehicle navigates proximate the first vehicle while aiming an obstacle detection sensor at a path of the first vehicle to detect objects in the path of the first vehicle. The locations of the objects are determined and transmitted to the first vehicle.

Abstract: Systems and methods are disclosed for placing a set of building elements within a building model. A set of space bodies are defined within a building, where each of the set of space bodies represents a non-overlapping volume within the building. A set of gaps are formed between the set of space bodies. A set of placement rules for the set of building elements are obtained based on physical characteristics of the set of gaps. A set of placements for the set of building elements within the building model are generated in accordance with the set of placement rules.

Abstract: Disclosed are a method and apparatus for calibrating a sensor. An object is placed in a field of view of the sensor at a known location. The object is moved (e.g., rotated) in a known manner. Data from the sensor is processed to detect an object image moving in the known manner. An apparent location of the object is determined from the object image. The apparent location is compared to the known location of the object to determine an offset. The offset is stored and used to adjust future detected locations of objects.

Abstract: Described herein are systems, methods, and other techniques for determining vehicle turn difficulty using overhead satellite imagery. In some implementations, an overhead image of a road intersection is obtained. A footprint of the road intersection is predicted using the overhead image. The footprint of the road intersection is analyzed to calculate one or more distances associated with a turn at the road intersection. A turn difficulty value associated with the turn is calculated based on the one or more distances for the turn.

Abstract: An augmented-reality device is used with a surveying system to guide a base station, such as a total station, during relock after loss of line of sight with a surveying instrument, such as a surveying pole with a reflective prism. A position of the surveying instrument in relation to the augmented-reality device is calculated while an object in the environment blocks line of sight from the base station to the surveying instrument. A position of the surveying instrument in relation to the environment is calculated based on the position of the surveying instrument in relation to the augmented-reality device. The position of the surveying instrument in relation to the environment is used by the base station to point toward to the surveying instrument.

Abstract: A sampling device receives, from each a plurality of transducer computing devices, respective vibration input samples. The sampling device generates a loop buffer corresponding to a most recent threshold number of samples received from each of the plurality of transducer computing devices including first and second transducer devices each located within a predefined proximity to first and second flow tubes of an equipment. The sampling device accesses, from the loop buffer, a most recent first sample logged by the first transducer computing device. The sampling device assigns, using a trained model, the first input sample to a first category of a set of categories. The sampling device accesses, from the loop buffer subsequent to accessing the first sample, a most recent second sample logged by a second transducer computing device and, using the model, assigns the second input sample to a second category of the set of categories.

Abstract: Disclosed are techniques for avoiding collisions with obstacles by a vehicle, in particular an off-road vehicle. Objects are detected with sensors in a calculated projected path zone of the vehicle footprint based on a vehicle trajectory. Possible path zones on either side of the projected path zone where the vehicle could potentially go with a change in trajectory are determined. The vehicle is slowed down or stopped for objects in the projected path and is slowed less for objects within the possible path zones.

Abstract: Methods for determining corrected positions of a global navigation satellite system (GNSS) rover using a GNSS base station and one or more GNSS reference stations include determining a statistical representation of position measurements from the GNSS reference stations and an instantaneous position measurement from the GNSS reference stations. A position correction is determined based on the statistical representation and the instantaneous position measurement. A corrected position of the GNSS rover is determined based on a position of the GNSS rover and the position correction.

Abstract: Embodiments describe a method for positioning a hinged vehicle including a primary part and a secondary part coupled to the primary part at a project site. The method includes receiving, from an image capturing device, digital image data representing one or more features of the secondary part; performing image analysis on the digital image data to identify positions of the one or more features of the secondary part; identifying an angle of at least a portion of the secondary part; calculating a current position of the secondary part based on the angle; calculating a positional difference between a correct position at the project site for the secondary part and a current position of the secondary part at the project site; and initiating a change in a position of the primary part to compensate for the positional difference and to position the secondary part on the correct position.

Abstract: A navigation system includes an IMU, a navigation estimator configured to estimate a current navigation solution based on (i) a previous navigation solution, and (ii) a specific force vector and an angular rate vector measured by the IMU, an RI sensor, an RI data preprocessor configured to perform an a priori transformation of RI data acquired by the RI sensor using the current navigation solution to obtain transformed RI data, an RI map database configured to retrieve a valid keyframe map based on the transformed RI data, and an RI filter manager (RFM) configured to construct a map registration cost gradient (MRCG) measurement based on (i) the transformed RI data, and (ii) the known position and the known orientation of the valid keyframe map. The navigation estimator is further configured to determine an absolute navigation solution based on at least (i) the current navigation solution, and (ii) the MRCG measurement.

Abstract: A method of area coverage planning with replenishment planning includes receiving information of a boundary of the work area, location information of one or more refill stations, and information of a current amount of the material left in the autonomous vehicle, laying a plurality of tracks within the boundary of the work area so as to minimize a total distance of the plurality of tracks, generating a coverage trajectory, and based on (i) the coverage trajectory, (ii) the location information of the one or more refill stations, (iii) the current amount of the material left in the autonomous vehicle, and (iv) a nominal full amount and a nominal consumption rate of the material by the autonomous vehicle, determining one or more logistic points along the coverage trajectory at which a remaining amount of the material reaches a threshold, for each logistic point, generating a replenishment trajectory.

Abstract: Disclosed are techniques for navigating a mobile machine, such as an autonomous robot, in an environment that includes objects that may block, reflect, or distort satellite signals to be used for positioning. Satellite data may be captured from one or more satellites. An image may be captured using an imaging device that is at least partially oriented toward the one or more satellites. A set of sky scores may be calculated for a set of ground positions surrounding the mobile machine based on the satellite data and the image. Each of the set of sky scores may be indicative of an accuracy of a satellite-based position at one of the set of ground positions. The mobile machine's navigation may be modified using the set of sky scores.

Abstract: A system for providing manual guidance of a vehicle includes a first inertial measurement unit (IMU) attached to a steering wheel, a second IMU attached to a fixed part of the vehicle, a global navigation satellite systems (GNSS) receiver, a data storage device for storing a pre-planned path, and a feedback module. The feedback module is configured to determine a current angle of the steering wheel, determine a deviation of the current position of the vehicle from the pre-planned path, determine a current heading of the vehicle, determine a current velocity of the vehicle, and determine a desired angle of the steering wheel relative to the vehicle. The system further includes a user interface configured to provide a visual indication of the desired angle of the steering wheel or a deviation of the current angle of the steering wheel from the desired angle of the steering wheel.