# US 10,766,496 B2 · Method for detecting and characterizing a driving behavior of a driver or an autopilot in a transportation vehicle, control unit and transportation vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,766,496 B2 - Document ID: US10766496B2 - Status: Granted - Kind: B2 - Application number: 16/029,554 - Filed: 2018-07-07 - Published: 2019-01-24 - Granted: 2020-09-08 - Earliest claimed: 2017-07-19 - Assignees: Volkswagen Aktiengesellschaft - Applicants: Volkswagen AG - Inventors: Samuel Schacher - Web page: https://patentgrep.com/patent/US10766496B2 ## CPC - B60W 50/085: {Changing the parameters of the control units, e.g. changing limit values, working points by control input} - B60W 40/09: Driving style or behaviour - B60W 50/12: Limiting control by the driver depending on vehicle state, e.g. interlocking means for the control input for preventing unsafe operation - G06N 3/0464: Convolutional networks [CNN, ConvNet] - B60W 2520/105: Longitudinal acceleration - B60W 2520/125: Lateral acceleration - B60W 2540/30: Driving style - B60W 2556/45: External transmission of data to or from the vehicle - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for detecting and characterizing a driving behavior of a driver or an autopilot in a transportation vehicle which has at least one acceleration sensor used to record data points which indicate a lateral acceleration and a longitudinal acceleration of the transportation vehicle over a time interval, and a control unit used to generate an image space as a GG diagram from the data points of at least one sub-section of the time interval. The image space is transformed by the control unit by a transformation into a parameter space and coordinates of accumulation points in the parameter space are acquired by the control unit. From the coordinates of the accumulation points, by using a classification algorithm, the control unit determines a classification value and/or a classification profile relating to the driving behavior. ## Claims ### Claim 1 A control unit comprising: a processor; and a program having a program code for carrying out a method for detecting and characterizing a driving behavior of a driver or an autopilot in a transportation vehicle when the program code is executed on the processor, the method comprising: generating an image space as a GG diagram from data points of at least one subsection of a time interval, wherein the data points are recorded by at least one acceleration sensor and indicate a lateral acceleration and a longitudinal acceleration of the transportation vehicle over the time interval; transforming the image space by a transformation into a parameter space, wherein the transformation is a Hough transform or a Radon transform; acquiring coordinates of accumulation points in the parameter space; and determining a classification value and/or a classification profile relating to the driving behavior using a classification algorithm based on the coordinates of the accumulation points. ### Claim 2 (depends on 1) The control unit of claim 1, wherein the coordinates of the parameter space are parameters of a straight line. ### Claim 3 (depends on 1) The control unit of claim 1, wherein the coordinates of the parameter space are coordinates of a center of a circle and a radius of a circle. ### Claim 4 (depends on 1) The control unit of claim 1, further comprising smoothing and/or filtering the values of the lateral acceleration and the values of the longitudinal acceleration of at least one sub-section of the time interval by the control unit. ### Claim 5 (depends on 1) The control unit of claim 1, further comprising transmitting the classification value and/or the classification profile to a driver assistance system and/or an external central computer. ### Claim 6 (depends on 1) The control unit of claim 1, wherein the at least one sub-section of the time interval is determined by the control unit as a function of predefined geographical data and/or on values of the lateral acceleration and/or longitudinal acceleration. ### Claim 7 (depends on 1) The control unit of claim 1, wherein the classification algorithm comprises a support vector machine and/or an artificial neural network. ### Claim 8 A transportation vehicle comprising: a control unit that includes a processor and a program having a program code for carrying out a method for detecting and characterizing a driving behavior of a driver or an autopilot in a transportation vehicle when the program code is executed on the processor, the method comprising: generating an image space as a GG diagram from data points of at least one subsection of a time interval, wherein the data points are recorded by at least one acceleration sensor and indicate a lateral acceleration and a longitudinal acceleration of the transportation vehicle over the time interval; transforming the image space by a transformation into a parameter space, wherein the transformation is a Hough transform or a Radon transform; acquiring coordinates of accumulation points in the parameter space; and determining a classification value and/or a classification profile relating to the driving behavior using a classification algorithm based on the coordinates of the accumulation points. ### Claim 9 (depends on 8) The transportation vehicle of claim 8, wherein the coordinates of the parameter space are parameters of a straight line. ### Claim 10 (depends on 8) The transportation vehicle of claim 8, wherein the coordinates of the parameter space are coordinates of a center of a circle and a radius of a circle. ### Claim 11 (depends on 8) The transportation vehicle of claim 8, further comprising smoothing and/or filtering the values of the lateral acceleration and the values of the longitudinal acceleration of at least one sub-section of the time interval by the control unit. ### Claim 12 (depends on 8) The transportation vehicle of claim 8, further comprising transmitting the classification value and/or the classification profile to a driver assistance system and/or an external central computer. ### Claim 13 (depends on 8) The transportation vehicle of claim 8, wherein the at least one sub-section of the time interval is determined by the control unit as a function of predefined geographical data and/or on values of the lateral acceleration and/or longitudinal acceleration. ### Claim 14 (depends on 8) The transportation vehicle of claim 8, wherein the classification algorithm comprises a support vector machine and/or an artificial neural network. ### Claim 15 A method for detecting and characterizing a driving behavior of a driver or an autopilot in a transportation vehicle, the method comprising: recording data points by at least one acceleration sensor, wherein the data points indicate a lateral acceleration and a longitudinal acceleration of the transportation vehicle over a time interval; generating an image space, by a control unit, as a GG diagram from the data points of at least one sub-section of the time interval; transforming the image space, by the control unit, by a transformation into a parameter space, wherein the transformation is a Hough transform or a Radon transform; and acquiring coordinates of accumulation points in the parameter space by the control unit, wherein the control unit determines a classification value and/or a classification profile relating to the driving behavior by a classification algorithm from the coordinates of the accumulation points. ### Claim 16 (depends on 15) The method of claim 15, wherein the coordinates of the parameter space are parameters of a straight line. ### Claim 17 (depends on 15) The method of claim 15, wherein the coordinates of the parameter space are coordinates of a center of a circle and a radius of a circle. ### Claim 18 (depends on 15) The method of claim 15, further comprising smoothing and/or filtering the values of the lateral acceleration and the values of the longitudinal acceleration of at least one subsection of the time interval by the control unit. ### Claim 19 (depends on 15) The method of claim 15, further comprising transmitting the classification value and/or the classification profile to a driver assistance system and/or an external central computer. ### Claim 20 (depends on 15) The method of claim 15, wherein the at least one sub-section of the time interval is determined by the control unit as a function of predefined geographical data and/or on values of the lateral acceleration and/or longitudinal acceleration. ### Claim 21 (depends on 15) The method of claim 15, wherein the classification algorithm comprises a support vector machine and/or an artificial neural network.