# US 10,768,632 B2 · Device and method for automated, semi automated, or assisted maneuvering of a motor vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,768,632 B2 - Document ID: US10768632B2 - Status: Granted - Kind: B2 - Application number: 15/880,668 - Filed: 2018-01-26 - Published: 2018-08-02 - Granted: 2020-09-08 - Earliest claimed: 2017-02-01 - Assignees: Volkswagen Aktiengesellschaft - Applicants: Volkswagen AG - Inventors: Philipp Hüger - Web page: https://patentgrep.com/patent/US10768632B2 ## CPC - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G05D 1/0212: {with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287)} - G05D 1/0246: {using a video camera in combination with image processing means} - G05D 1/0253: {extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow (determining position or orientation from images G06T7/70)} - G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) - G06T 7/579: from motion - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06T 2200/04: involving 3D image data - G06T 2207/10016: Video; Image sequence - G06T 2207/30241: Trajectory - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06V 2201/07: Target detection - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An apparatus for automated, partly automated or assisted maneuvering of a motor vehicle from a start point to a 3D target position including a mono camera and an evaluation and control unit, wherein the evaluation and control unit has at least one structure-from-motion algorithm, wherein the evaluation and control unit calculates a maneuvering trajectory composed of three partial trajectories, wherein a first partial trajectory leads from the start point to a first intermediate point, a second partial trajectory leads from the first to a second intermediate point, and the third partial trajectory leads from the second intermediate point to the target point, wherein at least the first or at least the second partial trajectory is embodied so the mono camera captures the target position from at least two different viewing directions, wherein the viewing directions are selected so the 3D determination of the structure-from-motion is optimized. ## Claims ### Claim 1 An apparatus for automated, partly automated or assisted maneuvering of a motor vehicle from a start position to a 3D target position, the apparatus comprising: a mono camera; and an evaluation and control unit, wherein the evaluation and control unit includes at least one structure-from-motion algorithm, wherein the evaluation and control unit calculates a maneuvering trajectory, wherein the maneuvering trajectory is calculated based on data captured by the mono camera including image data capturing the target position viewed from at least two different viewing directions, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm, wherein each viewing direction is based on a direction the motor vehicle is traveling along the maneuvering trajectory. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the maneuvering trajectory or a partial trajectory of the maneuvering trajectory is a curved trajectory from the start position to the 3D target position. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the maneuvering trajectory is composed of three partial trajectories, wherein a first partial trajectory leads from the start position to a first intermediate position, a second partial trajectory leads from the first intermediate position to a second intermediate position and the third partial trajectory leads from the second intermediate position to the target position, wherein at least the first partial trajectory or at least the second partial trajectory is calculated based on data captured by the mono camera including image data capturing the target position viewed from at least two different viewing directions, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm. ### Claim 4 (depends on 3) The apparatus of claim 3, wherein the first intermediate position is the target position. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the evaluation and control unit produces control signals for a steering actuator system. ### Claim 6 A method for automated, partly automated or assisted maneuvering of a motor vehicle from a start position to a target position, the method comprising: a mono camera capturing image data capturing the target position viewed from at least two different viewing directions; and an evaluation and control unit, including at least one structure-from-motion algorithm, calculating a maneuvering trajectory based on the data captured by the mono camera, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm, wherein each viewing direction is based on a direction the motor vehicle is traveling along the maneuvering trajectory. ### Claim 7 (depends on 6) The method of claim 6, wherein the maneuvering trajectory or a partial trajectory of the maneuvering trajectory is a curved trajectory from the start position to the 3D target position. ### Claim 8 (depends on 6) The method of claim 6, wherein the maneuvering trajectory is composed of three partial trajectories, wherein a first partial trajectory leads from the start position to a first intermediate position, a second partial trajectory leads from the first intermediate position to a second intermediate position and the third partial trajectory leads from the second intermediate position to the target position, wherein at least the first partial trajectory or at least the second partial trajectory is calculated based on data captured by the mono camera including image data capturing the target position viewed from at least two different viewing directions, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm. ### Claim 9 (depends on 8) The method of claim 8, wherein the target position is selected as first intermediate point. ### Claim 10 (depends on 8) The method of claim 8, wherein the first partial trajectory is calculated based on image data captured by the mono camera including image data capturing the target position viewed from at least two viewing directions, wherein the second intermediate position is ascertained so the viewing direction of the mono camera toward the target position is maintained constant along the third partial trajectory. ### Claim 11 A method for automated, partly automated or assisted maneuvering of a motor vehicle from a start position to a target position, the method comprising: a mono camera capturing image data capturing the target position viewed from at least two different viewing directions; and an evaluation and control unit, including at least one structure-from-motion algorithm, calculating a maneuvering trajectory based on the data captured by the mono camera, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm, wherein the maneuvering trajectory is composed of three partial trajectories, wherein a first partial trajectory leads from the start position to a first intermediate position, a second partial trajectory leads from the first intermediate position to a second intermediate position and the third partial trajectory leads from the second intermediate position to the target position, wherein at least the first partial trajectory or at least the second partial trajectory is calculated based on data captured by the mono camera including image data capturing the target position viewed from at least two different viewing directions, wherein the viewing directions are selected based on whether a sufficient amount of image data has been ascertained in order to determine the 3D target position performed by the structure-from-motion algorithm, and wherein the first partial trajectory is calculated based on image data captured by the mono camera including image data capturing the target position viewed from at least two viewing directions, wherein the second intermediate position is ascertained so the viewing direction of the mono camera toward the target position is maintained constant along the third partial trajectory.