A method for generation of a vehicle path for a vehicle. The method includes, using an excursion planning processor to perform generating a grid of attitude constraint masks, wherein each attitude constraint mask corresponds to a respective possible attitude of the vehicle. The method also includes defining a distance function between two points on a vehicle path, such that the vehicle path defines a change in orientation of the vehicle, determining a vehicle path component, of the vehicle path, between the two points having a selected cost, selecting a vehicle path in the grid of attitude constraint masks from the vehicle path component, and generating an excursion plan so that the vehicle travels along the vehicle path.

A method for generation of a vehicle path for a vehicle. The method includes, using an excursion planning processor to perform generating a grid of attitude constraint masks, wherein each attitude constraint mask corresponds to a respective possible attitude of the vehicle. The method also includes defining a distance function between two points on a vehicle path, such that the vehicle path defines a change in orientation of the vehicle, determining a vehicle path component, of the vehicle path, between the two points having a selected cost, selecting a vehicle path in the grid of attitude constraint masks from the vehicle path component, and generating an excursion plan so that the vehicle travels along the vehicle path.

Image data is used to determine wind speed and wind direction during takeoff and landing by an unmanned aerial vehicle (UAV). The flight data, including image data, may be received using sensors onboard the UAV and/or the flight data may be received from other sources, such as nearby anemometer, cameras, other UAVs, other vehicles, and/or local weather stations. Machine learning models may train using the flight data gathered by the UAVs to determine the wind velocity based on image data. The UAV may adjust flight control settings to generate side forces to overcome the predicted wind velocity.

A controller for a trailer is disclosed. An example trailer controller assembly includes a force transducer that measures a force between a trailer and a towing vehicle connected to the trailer indicative of a difference in speeds between the trailer and the towing vehicle, and a controller communicatively coupled to the force transducer. The controller includes a brake controller that controls brakes of the trailer based on an input signal from the force sensor.

A vehicle comprising a steering wheel; a steering switch disposed on the steering wheel; an other-vehicle-detector for detecting another vehicle; a tactile sensation presentation unit for presenting a tactile sensation to an operator by vibrating the steering switch; and a controller configured to, according to detection by the other-vehicle-detector, cause the tactile sensation presentation unit to vibrate the steering switch to present a tactile sensation to the operator.

Drones are engineered with sensors for use in insurance applications. After locating an object of interest, a drone performs an investigation by probing the object of interest. Sensors receive feedback from the object of interest. An electronic fingerprint of the drone is produced. Afterward, perils are computed based on the feedback and the fingerprint of the drone is used in insuring the object of interest. The act of probing includes thumping, drumming, or radiating ultrasound waves against the object of interest. The sensors can be turned off when they are within a geographic zone of prohibited operations.

Drones are engineered with sensors for use in insurance applications. After locating an object of interest, a drone performs an investigation by probing the object of interest. Sensors receive feedback from the object of interest. An electronic fingerprint of the drone is produced. Afterward, perils are computed based on the feedback and the fingerprint of the drone is used in insuring the object of interest. The act of probing includes thumping, drumming, or radiating ultrasound waves against the object of interest. The sensors can be turned off when they are within a geographic zone of prohibited operations.

Apparatuses and methods for movement control of a device are disclosed. The apparatus comprises memory for storing information of patterns covering sectors of the area indicating whether the patterns have at least one item relevant to movement in the area. The information has been configured based on determination of at least one pattern that has at least one item relevant to movement in the area, division of the determined at least one pattern into smaller patterns, determination of at least one of the smaller patterns with at least one item relevant to movement in the area, and repeat of the division until predefined smallest pattern size is reached. A processor is configured to determine whether a search path between first and second locations extends through at least one pattern having at least one item relevant to movement in the area, and to selectively use a path finding algorithm to determine a path of movement within at least one pattern with relevant items through which the search path is determined to extend.

A steering for a marine propulsion unit adjusts at least one of a required steering speed and a required steering torque such that the required steering speed and the required steering torque fall within an output region when the required steering speed and the required steering torque are outside the output region, sets a target steering angle according to the adjusted required steering speed and required steering torque, and sets the target steering angle according to a rotation angle of a steering wheel when the required steering speed and the required steering torque are within the output region.

An approach is provided for providing predictive classification of sensor error. The approach involves, for example, receiving sensor data from at least one sensor, the sensor data collected at a geographic location. The approach also involves extracting a set of input features from the sensor data, map data representing the geographic location, or combination thereof. The approach further involves processing the set of input features using a machine learning model to calculate a predicted sensor error of a target sensor operating at the geographic location. The machine learning model, for instance, has been trained on ground truth sensor error data to use the set of input features to calculate the predicted sensor error.