# US 12,214,799 B2 · Computing device and method for facilitating modification of the route of a vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,214,799 B2 - Document ID: US12214799B2 - Status: Granted - Kind: B2 - Application number: 17/590,889 - Filed: 2022-02-02 - Published: 2022-08-18 - Granted: 2025-02-04 - Earliest claimed: 2021-02-17 - Assignees: The Boeing Company - Applicants: The Boeing Company - Inventors: Tad W. Kellogg; Troy P. Kellogg; Michael J. Marich; William A. LaForge - Web page: https://patentgrep.com/patent/US12214799B2 ## CPC - B60W 60/001: {Planning or execution of driving tasks} - G01C 21/20: Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence) - B60W 40/068: Road friction coefficient - B60W 50/00: Details of control systems for road vehicle drive control not related to the control of a particular sub-unit {, e.g. process diagnostic or vehicle driver interfaces} - G06V 10/54: relating to texture - G06V 20/17: taken from planes or by drones - G08G 5/51: for control when on the ground, e.g. taxiing or rolling - G08G 5/55: for a single aircraft - G08G 5/723: {from the aircraft} - G08G 5/76: for monitoring atmospheric conditions - G08G 5/80: Anti-collision systems - B60W 2050/0075: {Automatic parameter input, automatic initialising or calibrating means} - G01C 21/3415: {Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents} - G08G 5/57: for unmanned aircraft - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) ## Abstract A computing device, method and computer program product are provided for facilitating modification of the route of an autonomous surface vehicle. In the context of a method, a stylized image of an input image, such as a photographic image, is constructed. The stylized image distinguishes between surfaces having different texture that are present in the input image. Based upon the stylized image, the method also includes determining a frictional coefficient associated with at least some of the surfaces having different texture. The method further includes determining whether the route of the autonomous surface vehicle is to be altered from a predefined route based upon the frictional coefficient that has been determined to be associated with a surface over which the predefined route of the autonomous surface vehicle extends. ## Claims ### Claim 1 A method for facilitating modification of a route of a vehicle, the method comprising: receiving an input image of at least one surface extending along the route of the vehicle; constructing a stylized image of the input image, wherein the stylized image is an enhanced version of the input image representing different surfaces found in the input image as geometric objects with a texture associated with each geometric object, wherein the stylized image distinguishes between surfaces having different textures that are present in the input image; based upon the stylized image, determining a frictional coefficient associated with at least some of the surfaces having different textures; and determining whether the route of the vehicle is to be altered from a predefined route based upon the frictional coefficient that has been determined to be associated with a surface over which the predefined route of the vehicle extends. ### Claim 2 (depends on 1) A method according to claim 1 wherein constructing the stylized image of the input image comprises generating the stylized image utilizing a first machine learning model that has been trained to distinguish between surfaces having different textures that appear in images. ### Claim 3 (depends on 1) A method according to claim 1 wherein constructing the stylized image of the input image comprises: defining geometric objects to represent the surfaces having different textures that are present in the input image; and associating texture information with respective geometric objects. ### Claim 4 (depends on 1) A method according to claim 1 wherein determining the frictional coefficient comprises determining the frictional coefficient utilizing a second machine learning model that has been trained to estimate frictional coefficients of surfaces having different textures that appear in stylized images. ### Claim 5 (depends on 1) A method according to claim 1 further comprising modifying the route of the vehicle in response to determining that the route of the vehicle is to be altered from the predefined route. ### Claim 6 (depends on 5) A method according to claim 5 further comprising providing the route, as modified, to a routing system of the vehicle. ### Claim 7 (depends on 1) A method according to claim 1 further comprising receiving the input image that has been captured by an image capture device of the vehicle. ### Claim 8 (depends on 1) A method according to claim 1 wherein the input image comprises a photographic image. ### Claim 9 A computing device configured to facilitate modification of a route of a vehicle, the computing device comprising processing circuitry configured to: receive an input image of at least one surface extending along the route of the vehicle construct a stylized image of the input image, wherein the stylized image is an enhanced version of the input image representing different surfaces found in the input image as geometric objects with a texture associated with each geometric object, wherein the stylized image distinguishes between surfaces having different textures that are present in the input image; based upon the stylized image, determine a frictional coefficient associated with at least some of the surfaces having different textures; and determine whether the route of the vehicle is to be altered from a predefined route based upon the frictional coefficient that has been determined to be associated with a surface over which the predefined route of the vehicle extends. ### Claim 10 (depends on 9) A computing device according to claim 9 wherein the processing circuitry comprises a first machine learning model that has been trained to distinguish between surfaces having different textures that appear in images, and wherein the processing circuitry is configured to construct the stylized image of the input image utilizing the first machine learning model. ### Claim 11 (depends on 9) A computing device according to claim 9 wherein the processing circuitry is configured to construct the stylized image of the input image by defining geometric objects to represent the surfaces having different textures that are present in the input image and by associating texture information with respective geometric objects. ### Claim 12 (depends on 9) A computing device according to claim 9 wherein the processing circuitry comprises a second machine learning model that has been trained to estimate frictional coefficients of surfaces having different textures that appear in stylized images, and wherein the processing circuitry is configured to determine the frictional coefficient utilizing the second machine learning model. ### Claim 13 (depends on 9) A computing device according to claim 9 wherein the processing circuitry is further configured to modify the route of the vehicle in response to determining that the route of the vehicle is to be altered from the predefined route. ### Claim 14 (depends on 13) A computing device according to claim 13 further comprising a communication interface, responsive to the processing circuitry, configured to provide the route, as modified, to a routing system of the vehicle. ### Claim 15 (depends on 9) A computing device according to claim 9 further comprising a communication interface configured to receive the input image that has been captured by an image capture device of the vehicle. ### Claim 16 (depends on 9) A computing device according to claim 9 wherein the input image comprises a photographic image. ### Claim 17 A method for training machine learning models to facilitate modification of a route of a vehicle, the method comprising: based upon a plurality of training images depicting surfaces having different, known textures, training a first machine learning model to distinguish between surfaces having different textures and to construct a stylized image from a respective training image that distinguishes between surfaces having different textures that are present in the respective training image; storing the first machine learning model; based upon a plurality of stylized images that distinguish between surfaces having different textures and also based upon predefined frictional coefficients associated with surfaces having different textures, training a second machine learning model to determine a frictional coefficient associated with at least some of the surfaces having different textures; and storing the second machine learning model. ### Claim 18 (depends on 17) A method according to claim 17 further comprising utilizing the first machine learning model to construct the plurality of stylized images that are utilized to train the second machine learning model from respective training images. ### Claim 19 (depends on 17) A method according to claim 17 wherein the first machine learning model is trained to construct the stylized image from the respective training image by defining geometric objects to represent the surfaces having different textures that are present in the respective training image and by associating texture information with respective geometric objects. ### Claim 20 (depends on 17) A method according to claim 17 further comprising receiving the plurality of training images depicting surfaces over which a vehicle is capable of driving.