Method, apparatus, storage medium, and device for positioning a dummy based on the operating state of a seat.

Abstract

The present invention provides a dummy positioning method, apparatus, computer-readable storage medium, and electronic device that enable high-precision dummy positioning according to the seat's operating state. [Solution] The target seat is divided into multiple seat reclining angles, and the applicability of the human point machine and collision dummy is evaluated using the key point coordinates of the human point machine, collision dummy, and target driver at each seat reclining angle. Then, by calculating the key point coordinates of the target collision dummy based on the evaluation results, positioning information of the target collision dummy in the operating state of the large-angle seat is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle collision, and specifically relates to a positioning method, apparatus, medium and device for a dummy (collision test dummy) based on the operating state of a seat. BACKGROUND ART

[0002] Seats that can be reclined to a large angle (large-angle seats) are more comfortable than conventional upright seats, but their impact on occupant safety has not been sufficiently verified. In automotive collision tests, usually, a Human-Point Machine (hereinafter also referred to as "HPM"), a collision test dummy, or the like is used to simulate the actual behavior of a driver, so as to evaluate the collision safety of vehicles. The reliability of the data obtained in the collision test by the collision test dummy is directly related to whether its placement posture can accurately simulate the standard posture of the driver in the actual driving environment. However, the conventional HPM, collision test dummies and the like have all been verified targeting conventional upright seats, and their performance in the operating state of large-angle seats has not yet been clarified. Therefore, there is a demand for a method capable of positioning a human body model in the operating state of a large-angle seat. SUMMARY OF THE INVENTION PROBLEMS TO BE SOLVED BY THE INVENTION

[0003] The present application is proposed to solve the above technical problems. Embodiments of the present application provide a dummy positioning method, apparatus, storage medium and device based on a seat operating state. MEANS FOR SOLVING THE PROBLEMS

[0004] According to one aspect of this application, a method for positioning a dummy based on the seat operating state is provided, which includes the steps of: establishing a coordinate system fixed to the seat (seat coordinate system); dividing the target seat into a plurality of seat reclining angles based on the seat coordinate system; measuring the first keypoint coordinates of the HPM, the second keypoint coordinates of the collision dummy, and the third keypoint coordinates of the target driver at each of the plurality of seat reclining angles; evaluating the applicability of the HPM and the collision dummy to the target driver based on the first and second keypoint coordinates, with respect to the third keypoint coordinates of the target driver; selecting the HPM and collision dummy whose applicability satisfies predetermined (preset) conditions as the target HPM and target collision dummy, respectively; and calculating the target keypoint coordinates of the target driver corresponding to the keypoint coordinates of the target HPM as the keypoint coordinates of the target collision dummy, based on the positioning conversion relationship between the target HPM and the target driver.

[0005] According to another aspect of this application, a seat tilt angle division module for establishing a seat coordinate system and dividing a target seat into a plurality of seat tilt angles based on the seat coordinate system; a first keypoint measurement module for measuring the first keypoint coordinates of the HPM in the plurality of seat tilt angles; a second keypoint measurement module for measuring the second keypoint coordinates of the collision dummy in the plurality of seat tilt angles; a third keypoint measurement module for measuring the third keypoint coordinates of the target driver in the plurality of seat tilt angles; and the first keypoint coordinates of the HPM in the plurality of seat tilt angles, based on the third keypoint coordinates of the target driver in the plurality of seat tilt angles. The present invention provides a dummy positioning device based on seat operating state, comprising: an applicability evaluation module for evaluating the applicability of the HPM and the collision dummy based on the second keypoint coordinates of the plurality of seat rearward tilt angles of the collision dummy; a target model selection module for selecting the HPM and the collision dummy that satisfy predetermined (preset) conditions for applicability as the target HPM and the target collision dummy, respectively; and a collision dummy positioning module for calculating the target keypoint coordinates of the target driver corresponding to the keypoint coordinates of the target HPM as the keypoint coordinates of the target collision dummy, based on the positioning conversion relationship between the target HPM and the target driver.

[0006] According to another aspect of this application, a computer-readable storage medium is provided which stores a computer program containing instructions for causing a computer to perform each step of any of the above methods.

[0007] According to another aspect of this application, an electronic device is provided comprising a memory for storing instructions for performing each step of any of the above methods, and a processor for performing the instructions stored in the memory. [Effects of the Invention]

[0008] The seat operating state-based dummy positioning method, apparatus, medium, and apparatus provided in this application establish a seat coordinate system, divide the target seat into multiple seat reclining angles based on the seat coordinate system, measure the first keypoint coordinates at the multiple seat reclining angles of the HPM, measure the second keypoint coordinates at the multiple seat reclining angles of the collision dummy, measure the third keypoint coordinates at the multiple seat reclining angles of the target driver, evaluate the applicability of the HPM and collision dummy based on the first keypoint coordinates at the multiple seat reclining angles of the HPM and the second keypoint coordinates at the multiple seat reclining angles of the collision dummy, and select the HPM and collision dummy whose applicability satisfies predetermined (preset) conditions. A target HPM and a target collision dummy are selected, and based on the positioning conversion relationship between the target HPM and the target driver, the target keypoint coordinates of the target driver corresponding to the keypoint coordinates of the target HPM are calculated as the keypoint coordinates of the target collision dummy. The keypoint coordinates of the HPM, collision dummy, and target driver are measured at multiple seat reclining angles, and the applicability of the HPM and collision dummy is evaluated based on these measurements. A target HPM and target collision dummy with superior applicability are selected, and during the experimental process, the keypoint coordinates of the target HPM are converted to the target keypoint coordinates of the target driver, and these target keypoint coordinates are used as the keypoint coordinates of the target collision dummy, thereby obtaining positioning information for the target collision dummy in the operating state of a large-angle seat. [Brief explanation of the drawing]

[0009] To clarify the purpose, structure, and advantages of this application, embodiments of this application will be described in more detail with reference to the drawings. The drawings are intended to aid in a further understanding of the embodiments of this application and constitute part of the specification, and are used together with the embodiments of this application for interpretation purposes, and are not intended to limit this application. In the drawings, the same reference numerals indicate the same component or process unless otherwise specified.

[0010] [Figure 1] This is a flowchart of a dummy positioning method based on the seat operating state provided in one embodiment of this application. [Figure 2] This is a schematic diagram of the seat coordinate system structure provided by one embodiment of this application. [Figure 3] This figure schematically shows the change vector of the measurement target provided by one embodiment of this application. [Figure 4] This is a schematic diagram showing a conversion model of the H-point coordinate value of a target driver provided by one embodiment of this application. [Figure 5] This is a schematic diagram showing the structure of the backplate of an HPM provided in one embodiment of this application. [Figure 6] This is a schematic diagram showing a conversion model for converting a posture portion to a positioning portion, provided by one embodiment of this application. [Figure 7] This is a schematic diagram showing a conversion model for converting a positioning portion to a posture portion, provided by one embodiment of this application. [Figure 8] This is a schematic diagram showing the structure of a dummy positioning device based on seat operating state provided by one embodiment of this application. [Figure 9] This figure shows the structure of an electronic device provided by one embodiment of this application. [Modes for carrying out the invention]

[0011] The embodiments of this application will be described in detail below with reference to the drawings. Naturally, the embodiments described are only a part of the embodiments of this application, and not all of them. It should be understood that the technical scope of this application is not limited to the embodiments described herein.

[0012] Figure 1 is a flowchart of a dummy positioning method based on seat movement state provided by one embodiment of this application. As shown in Figure 1, this dummy positioning method based on seat movement state includes the following steps 110 to 170.

[0013] Step 110: Establish a coordinate system fixed to the seat (seat coordinate system), and divide the target seat into multiple seat reclining angles based on the seat coordinate system.

[0014] Specifically, the target seat is fixed on a flat surface, and a flexible three-dimensional measuring machine is used to measure a pair of coordinate values ​​at symmetrical positions on the cushion surface and backrest surface of the target seat. Next, the height component in the direction of the plumb bob (vertical direction) of the pair of symmetrical points is compared to see if it is within a predetermined error range. If the height component falls outside the error range, the fixed plane of the target seat or the target seat base is adjusted to match the height in the direction of the plumb bob of the symmetrical points on the cushion surface and backrest surface of the target seat. The covering material that covers the rotation axis of the backrest of the target seat is removed to expose the rotation axis of the backrest of the target seat. Next, multiple marker points are stamped onto the left and right metal structures of the bottom of the target seat, respectively, for use in establishing the seat coordinate system and restoring the coordinate system after the target seat is moved. With the driver or passenger (seated person) facing forward and seated in the target seat, that is, looking from the backrest side of the target seat towards the cushion side, the left side of the seated person is defined as the left side of the target seat, and the right side of the seated person is defined as the right side of the target seat. Using a flexible 3D measuring machine, the rotation centers of the rotation axes provided on the left and right sides of the backrest are identified, and the midpoint of the line connecting the left and right rotation centers is defined as the origin of the seat coordinate system. Starting from the origin, the horizontal direction from the backrest side of the target seat towards the cushion side is defined as the positive direction of the X-axis, and the direction from the right side to the left side of the target seat on the line connecting the left and right rotation centers of the backrest is defined as the positive direction of the Y-axis. The direction perpendicular to the X and Y axes, and moving from the cushion side towards the headrest side, is defined as the positive direction of the Z-axis. The current seat coordinate system is constructed using a flexible 3D measuring machine, and this seat coordinate system is recorded. Furthermore, after the target seat is moved, the coordinates of the restoration marker points are recorded in order to restore the seat coordinate system. As shown in Figure 2(a), one fixed point on the seat backrest can be selected as the marker point, and the position of the headrest rod or any point on the seat backrest can also be selected. Furthermore, one flat area on the seat backrest of the target seat is selected as the measurement area for the backrest angle.

[0015] Mount the HPM on the target seat according to the HPM mounting requirements. During the mounting process, adjust the seat backrest so that the torso angle of the HPM reaches a design angle that matches the upright state of the seat. Next, use a flexible coordinate measuring machine to measure the restoration marker points of the seat coordinate system, and confirm that the mounting of the HPM does not affect the accuracy of the seat coordinate system.

[0016] After that, use the flexible coordinate measuring machine to measure the left and right H points (key points) of the HPM. If the error between the left and right H points is within the allowable range, measure and record the coordinates of the backrest marker points, and define this state as the "0-degree position". In addition, calculate the average value of the left and right H points as the H point coordinate value of the HPM at the "0-degree position", and define it as the "I-0-H point" (see Fig. 2(b)).

[0017] Next, remove the HPM, use a goniometer to measure and record the angle value in the backrest angle measurement area, and reset the goniometer to zero at this position.

[0018] After that, adjust the backrest to tilt backward until the reading of the goniometer reaches β degrees (shown in (d) of Fig. 2), use the flexible coordinate measuring machine to measure and record the coordinates of the backrest marker points, and define this position as the "β-degree position".

[0019] Further, adjust the backrest to tilt backward until the reading of the goniometer reaches 2β degrees, use the flexible coordinate measuring machine to measure and record the coordinates of the backrest marker points, and define this position as the "2β-degree position". Thereafter, follow the same procedure to adjust the backrest until the final position becomes the "α-degree position" (shown in (c) of Fig. 2), to obtain a total of (α-0) / β angular positions.

[0020] Step 120: Place (mount) the HPM on the target seat, and measure the coordinates of the first key point at a plurality of seat rearward tilt angles.

[0021] In the present application, with the HPM mounted on the target seat, measurements are performed at a plurality of set seat rearward tilt angles to obtain the coordinates of the first key point of the HPM.

[0022] Step 130: Attach the collision dummy to the target seat and measure the coordinates of the second keypoint at multiple seat recline angles.

[0023] In this application, with a collision dummy attached to the target seat, measurements are taken by setting multiple seat reclining angles, and the coordinates of the second key point of the collision dummy are obtained.

[0024] Step 140: With the target driver seated in the target seat, measure the coordinates of the third key point at multiple seat tilt angles.

[0025] In this application, measurements are taken with the target driver seated in the target seat, setting multiple seat tilt angles, and the coordinates of the target driver's third key point are obtained.

[0026] Step 150: The applicability of the HPM and the collision dummy is evaluated based on the coordinates of the first key point at multiple seat reclining angles of the HPM and the coordinates of the second key point at multiple seat reclining angles of the collision dummy, using the coordinates of the third key point at multiple seat reclining angles of the target driver as a reference.

[0027] In this application, the applicability of HPM and collision dummy is evaluated based on the coordinates of a third key point at multiple seat reclining angles of the target driver. Specifically, the variability between HPM, collision dummy, and target driver is calculated based on the coordinates of the first key point at multiple seat reclining angles of HPM, the coordinates of the second key point at multiple seat reclining angles of the collision dummy, and the coordinates of the third key point at multiple seat reclining angles of the target driver, and the applicability of HPM and collision dummy is evaluated.

[0028] Step 160: Select the HPM and collision dummy whose applicability meets the preset conditions as the target HPM and target collision dummy, respectively.

[0029] In this application, HPMs and collision dummies whose applicability, as evaluated in step 150, meet predetermined (preset) conditions are selected as the target HPM and target collision dummy, respectively. Specifically, the HPMs and collision dummies with optimal applicability are selected as the target HPM and target collision dummy, respectively.

[0030] Step 170: Based on the positioning conversion relationship between the target HPM and the target driver, the coordinates of the target driver's target keypoints corresponding to the coordinates of the target HPM's keypoints are calculated, and these target keypoint coordinates are used as the coordinates of the target collision dummy's keypoints.

[0031] In this application, based on the positioning conversion relationship between the target HPM and the target driver, the coordinates of the target driver's target keypoints corresponding to the coordinates of the target HPM's keypoints are calculated, and the coordinates of the target collision dummy's keypoints are obtained based on the coordinates of those target keypoints.

[0032] In the dummy positioning method based on seat operating state provided in this application, first, a seat coordinate system is established, and based on that seat coordinate system, the target seat is divided into multiple seat reclining angles.

[0033] Next, for the HPM, the coordinates of the first key point at multiple seat tilt angles are measured, for the collision dummy, the coordinates of the second key point at multiple seat tilt angles are measured, and for the target driver, the coordinates of the third key point at multiple seat tilt angles are measured.

[0034] Furthermore, the applicability of the HPM and the collision dummy is evaluated based on the coordinates of the third key point at multiple seat reclining angles of the target driver, the coordinates of the first key point at multiple seat reclining angles of the HPM, and the coordinates of the second key point at multiple seat reclining angles of the collision dummy.

[0035] Then, HPMs and collision dummies that meet the preset applicability conditions are selected as the target HPM and target collision dummies, respectively.

[0036] Subsequently, based on the positioning conversion relationship between the target HPM and the target driver, the coordinates of the target driver's target keypoint corresponding to the coordinates of the target HPM's keypoint are calculated, and these target keypoint coordinates are set as the keypoint coordinates of the target collision dummy.

[0037] This makes it possible to obtain positioning information for a target collision dummy that accurately reflects the actual driver's posture when the large-angle seat is in operation.

[0038] In one embodiment, the following method can also be adopted as a specific implementation of step 150. Specifically, for HPM, an approximation (fitting) process is performed based on the coordinates of the first keypoint at multiple seat reclining angles to obtain a first vector representing the change in the coordinates of the first keypoint as the seat reclining angle changes.

[0039] Similarly, for the collision dummy, a fitting process is performed based on the coordinates of the second keypoint at multiple seat tilt angles to obtain a second vector representing the change in the coordinates of the second keypoint as the seat tilt angle changes.

[0040] Furthermore, for the target driver, a fitting process is performed based on the coordinates of the third keypoint at multiple seat tilt angles to obtain a third vector representing the change in the coordinates of the third keypoint as the seat tilt angle changes.

[0041] Then, the angle between the first vector and the third vector (hereinafter referred to as the "first angle") and the angle between the second vector and the third vector (hereinafter referred to as the "second angle") are calculated, and the applicability of HPM and collision dummies is evaluated based on these angles.

[0042] Specifically, when evaluating the applicability of large-angle seats to lateral positioning, the contribution of values ​​in the Y direction is relatively low for some of the data collected from HPM, collision dummies, and target drivers. For example, for tragus markers, acromion markers, greater trochanter markers, left and right knee markers, and left and right ankle markers used to evaluate the lateral position of the driver in question, it is sufficient to store values ​​in the X and Z directions.

[0043] Furthermore, for the H-points collected by HPM, and the head's center of gravity, shoulder markers, knee markers, ankle markers, etc., collected by the collision dummy, it is sufficient to retain only the values ​​in the X and Z directions.

[0044] As described above, for the screened data, the X and Z values ​​of the target driver, HPM, and collision dummy collected when the seat backrest is in the "0-degree position" are used as reference values, and the difference between the X and Z values ​​and the reference values ​​when the measured subject is in the "β-degree position", "2β-degree position", ..., "α-degree position" is calculated.

[0045] When evaluating the applicability of large-angle seats in relation to the frontal position, the contribution of X-direction values ​​is relatively low for some data collected from HPMs, crash dummies, and target drivers.

[0046] For example, for tragus markers, acromion markers, greater trochanter markers, left and right knee markers, and left and right ankle markers used to evaluate the frontal position of the target driver, it is sufficient to store values ​​in the Y and Z directions.

[0047] Similarly, for the head's center of gravity, shoulder markers, knee markers, and ankle markers collected by the collision dummy, it is sufficient to retain only the values ​​in the Y and Z directions.

[0048] The data screened in this manner is also processed in the same manner as in paragraph

[0029] , and the difference between the values ​​in the Y and Z directions and the reference value is calculated when the measurement target is at the "β-degree position", "2β-degree position", ..., "α-degree position".

[0049] The left-hand side of Figure 3 plots the changes in the target driver, HPM, and collision dummy as vectors. Each vector shown here represents the change vector of each measurement target, measured for each β-degree change in the backrest angle.

[0050] As shown in the right-hand diagram of Figure 3, in this application, the change vectors at the positions of the HPM and the collision dummy, and the vector at the same position of the target driver are plotted from the same starting point. JPEG2026170841000002.jpg29170

[0051] Next, the angles between vector A and vector B, and between vector A and vector C are calculated, and these angles indicate the difference in each vector direction and the degree of change. Based on this, the degree of deviation in change shown by HPM and the dummy for the target driver is evaluated, and its applicability is further assessed. The formula for calculating the above angle is as follows:

[0052] The angle between two vectors can be calculated using the following formula. JPEG2026170841000003.jpg35170

[0053] A larger value of θ indicates a greater directional difference (relative deviation in a given direction within the coordinate system) between the two vectors being compared, meaning that the consistency and applicability of that coordinate system are low. On the other hand, a smaller value of θ indicates a smaller directional difference between the two vectors and a smaller displacement relative to the coordinate system, which means higher applicability.

[0054] In one embodiment, the specific implementation of step 170 may be as follows: During the experimental process, the coordinates of multiple keypoints of the target HPM are measured, and these keypoint coordinates are input into a trained neural network model. This allows the coordinates of the target keypoints corresponding to the target driver to be obtained as the coordinates of the keypoints of the target collision dummy.

[0055] Specifically, this application calculates the positioning position of the target driver based on a predetermined conversion relationship by measuring the H point of a highly applicable HPM, and provides the calculation result as the basis for positioning a dummy.

[0056] In this application, a neural network is constructed as shown in Figure 4, and in this neural network, the H-point coordinates of the HPM are taken as input, and the H-point coordinates of the target driver are taken as output. The output of the i-th neuron in the l-th layer of the neural network is represented, for example, by the following expression format.

[0057] JPEG2026170841000004.jpg98170

[0058] In one embodiment, the specific implementation of step 110 may be as follows: The maximum tilt angle at which the backrest of the target seat tilts backward from an upright position to a maximum reclined position is measured, and the number of seat reclining angles and the magnitude of each seat reclining angle of the target seat are calculated based on the preset adjustment angle and the maximum tilt angle.

[0059] In this application, the number of seat reclining angles of a target seat is calculated by measuring the maximum tilt angle at which the seat backrest tilts backward from an upright position to a maximum reclined position, and the adjustment angle in a single adjustment. It is important to understand that the greater the number of seat reclining angles of the target seat, the higher the resolution of the measurement results obtained by HPM (as described later), and the greater the measurement accuracy.

[0060] In one embodiment, the specific implementation of step 120 may be as follows: The target seat is adjusted to the current seat reclining angle, and the HPM is attached to the target seat. Next, the left keypoint coordinates and right keypoint coordinates of the HPM at the seat reclining angle are measured.

[0061] If the difference between the left and right keypoint coordinates of the HPM (first error) is less than the first preset value, the first keypoint coordinate of the HPM at the seat recline angle is calculated based on the left and right keypoint coordinates.

[0062] Specifically, the seat backrest is adjusted to the β-degree position, and a predetermined HPM is selected. Next, in response to the request to install the HPM, the HPM is installed on the target seat, and the HPM is adjusted.

[0063] Subsequently, a flexible 3D measuring machine is used to measure the restored reference points of the seat coordinate system to ensure that the installation of the HPM does not affect the accuracy of the seat coordinate system. Furthermore, the left and right H points of the HPM are measured using the flexible 3D measuring machine.

[0064] If the error between the left and right H points is within the acceptable range, the average value of the left and right H points is calculated as the H point coordinate value at the β-degree position of the HPM.

[0065] Next, the seat backrest is adjusted to the 2β-degree position, and the above measurement process is repeated to obtain the H-point coordinate value of the HPM at the 2β-degree position. The same process is repeated until the seat backrest is at the α-degree position to obtain the H-point coordinate value of the HPM at each backrest angle position.

[0066] Furthermore, switch to another HPM and repeat the above operation to measure the coordinate values ​​of the key point H, which corresponds to each backrest angle position, for each of the multiple HPMs.

[0067] In this process, at each angle measurement position, in addition to measuring the H point coordinate values, the midpoints of the upper edge of the HPM's upper body (denoted as "II-0-L1", "II-β-L1", "II-2β-L1", ..., "II-α-L1") and the midpoints of the lower edge of the upper body (denoted as "II-0-L2", "II-β-L2", "II-2β-L2", ..., "II-α-L2") may also be measured, as shown in Figure 5.

[0068] In one embodiment, the specific implementation of step 130 may be as follows: The target seat is adjusted to the current seat reclining angle, and the collision dummy is attached to the target seat. Next, the left keypoint coordinates and right keypoint coordinates of the collision dummy at the current seat reclining angle are measured. If the difference (second error) between the left keypoint coordinates and the right keypoint coordinates of the collision dummy is less than the second preset value, the second keypoint coordinates at the seat reclining angle are calculated based on the left keypoint coordinates and right keypoint coordinates.

[0069] Specifically, the seat backrest is adjusted to the 0-degree position, and a crash dummy is attached to the target seat according to the requirements of the test standard, and its position is adjusted. Next, a flexible 3D measuring machine is used to measure the restoration point of the seat coordinate system to ensure that the attachment of the crash dummy does not affect the accuracy of the seat coordinate system.

[0070] Next, the left and right H points of the collision dummy are measured using a flexible three-dimensional measuring machine. If the error between the left and right H points is within the acceptable range, the average value of the left and right H points is calculated.

[0071] If the average value of point H satisfies the requirements for the position of point H of the collision dummy as stipulated in the test standard, the calculated average value shall be adopted as the coordinate value of point H at the 0-degree position of the collision dummy.

[0072] Furthermore, for subsequent comparison with the target driver measurement test, the following key points of the collision dummy will be measured: the left and right center of gravity of the head, left and right marker points on the shoulders, left and right marker points on the knees, left and right marker points on the ankles, and the pelvic angle.

[0073] If the left-right error values ​​for each of the above key points are within the acceptable range, the average values ​​for the left and right sides are calculated for the head's center of gravity point, shoulder marking point, knee marking point, and ankle marking point, respectively.

[0074] Next, adjust the backrest to the next measurement angle position, and lightly press the chest of the collision dummy against the backrest and headrest, respectively, so that the chest and head of the collision dummy are in contact with the backrest and headrest, respectively. Then, repeat the above measurement method and measure and record the angles of point H, the left and right center of gravity points of the head, the left and right marker points of the shoulders, the left and right marker points of the knees, the left and right marker points of the ankles, and the pelvis of the collision dummy at the said angle position.

[0075] If the left-right error values ​​for the above key points are within the acceptable range, the average values ​​for the left and right sides are calculated for the head's center of gravity point, shoulder marking point, knee marking point, and ankle marking point.

[0076] Similarly, the above process is repeated until the backrest reaches the α-degree position, and the measured values ​​of the key points corresponding to each backrest angle position in the measurement process are recorded.

[0077] If the chest or head of the collision dummy cannot make contact with the backrest or headrest, and if an adjustable device exists on the chest or neck of the collision dummy, the structure of the chest and head of the collision dummy can be adjusted based on the structural characteristics of the collision dummy to allow contact with the backrest and headrest. On the other hand, if the above adjustable device does not exist, the angle value of the backrest and the non-contact state of the collision dummy at that time will be recorded.

[0078] Switch to other types of collision dummies and repeat the above process until the measurement of keypoint coordinates and angle values ​​of critical parts is completed for each of the multiple types of collision dummies.

[0079] In one embodiment, the specific implementation of step 140 may be as follows, for example. The target seat is adjusted to its current seat tilt angle, and the target driver's seating posture in the target seat is adjusted. Next, the left keypoint coordinates and right keypoint coordinates of the target driver at the current seat tilt angle are measured.

[0080] If the difference between the left keypoint coordinates and the right keypoint coordinates (third error) is less than the third preset value, the third keypoint coordinates of the target driver at the above seat tilt angle are calculated based on the left keypoint coordinates and the right keypoint coordinates.

[0081] Specifically, markers are attached to the target driver's body parts, including the tragus, shoulder (acromion), knee, ankle, and greater trochanter of the pelvis. In addition, markers are attached to the T5 and L12 positions of the target driver's spine, and angle sensors are attached to the left and right anterior superior iliac spines of the pelvis.

[0082] Next, the seat backrest is adjusted to the 0-degree position, guiding the target driver to sit properly in the target seat and maintaining as much left-right symmetry as possible in their body position. Then, the restored reference point of the seat coordinate system is measured using a flexible 3D measuring machine to confirm that the target driver's seating does not affect the accuracy of the seat coordinate system.

[0083] Next, a flexible three-dimensional measuring machine is used to measure the left and right reference points of the target driver. If the error between the left and right reference points is within the acceptable range, the average value of the left and right reference points is calculated. This allows us to obtain the key points of the target driver, including the left and right reference points of the tragus, left and right reference points of the acromion, left and right reference points of the knees, left and right reference points of the ankles, and the T12 and L5 position reference points of the spine.

[0084] If the left-right error values ​​for the above key points are within the acceptable range, the average values ​​for the left and right sides are calculated for the tragus marker, acromion marker, knee marker, and ankle marker. The angle sensor is then reset to zero at this position.

[0085] Next, the seat backrest is adjusted to the next measurement angle position, and the seating posture of the subject driver is adjusted so that the chest and head are in contact with the backrest and headrest, respectively. Then, the above process is repeated, and the H point, left and right tragus marker points, left and right acromion marker points, left and right knee marker points, left and right ankle marker points, T12 position marker point and L5 position marker point of the spine are measured and recorded, and the values ​​of the angle sensor are also recorded.

[0086] Similarly, the above process is repeated until the seat backrest reaches the α-degree position, and measurements are taken to record the keypoint measurements and angle sensor values ​​corresponding to each seat backrest angle position during the process.

[0087] Switch to another target driver and repeat the above process until the coordinate values ​​of key points and the angle values ​​of important parts have been measured for each of the multiple target drivers.

[0088] In this application, after obtaining the target keypoint coordinates of the target driver corresponding to the keypoint coordinates of the target HPM through conversion, the target keypoint coordinates are set as the H-point coordinates of the collision dummy, and the coordinate values ​​of the attitude parts of the collision dummy are calculated based on the H-point coordinates.

[0089] Specifically, as shown in Figure 6, in this application, a forward-direction neural network is first trained. This neural network takes the coordinate values ​​of the center point of the eyeballs, upper neck, lower neck, upper abdomen, lower abdomen, elbows, arms, knees, ankles, heels, toes, and head center of gravity (hereinafter collectively referred to as posture parts) of the collision dummy as input, and outputs the coordinate value of point H (collectively referred to as the positioning part). The neural network constructed in this way provides a correspondence between the coordinate values ​​of the posture parts and the positioning part. The relationship is shown below.

[0090] JPEG2026170841000005.jpg97170

[0091] The above relationship can be expressed in terms of matrices and vectors as follows: JPEG2026170841000006.jpg39170

[0092] By performing an inverse operation on equation 1 of motion, the following relationship is obtained. JPEG2026170841000007.jpg19156In formula, R l This is a diagonal matrix of activation functions, where each diagonal element represents the activation function applied to each neuron. The diagonal matrix R corresponding to the activation function l This can be expressed as follows:

[0093] JPEG2026170841000008.jpg92162

[0094] Weight matrix W in a neural network l Since this is generally irreversible, it is necessary to perform a generalized inverse operation on the above relation. This yields the following relation. JPEG2026170841000009.jpg17167

[0095] In the generalized inverse process described above, the standard regularized least squares method can be adopted, α 2 represents the Tikhonov regularization parameter, and I α This represents the identity matrix corresponding to the regularization parameter. The regularization parameter can be determined based on the measured noise level obtainable by measurement or the noise level added to the response calculation. Using the regularized generalized inverse obtained in this way, the weights and biases of the neural network after inverse calculation using the equation of motion 1 can be expressed by the following equations. JPEG2026170841000010.jpg28170

[0096] By combining the above formula with the calculation, the following formula is obtained. JPEG2026170841000011.jpg29170 In other words, as shown in Figure 7, the neural network based on this inverse calculation process is a neural network that takes the coordinate values ​​of the positioning part as input and outputs the coordinate values ​​of the posture part.

[0097] The above relationship can be transformed into the following approximate formula. JPEG2026170841000012.jpg23159

[0098] By inputting the coordinate values ​​of point H, where the collision dummy is positioned, into the inverse neural network described above, it is possible to output the coordinate values ​​of the collision dummy's posture parts (hereinafter collectively referred to as posture parts), including the center of the eyeball, upper neck, lower neck, upper abdomen, lower abdomen, elbows, arms, knees, ankles, heels, toes, and head center of gravity.

[0099] Figure 8 is a schematic diagram showing the structure of a dummy positioning device based on seat operating state provided in one embodiment of this application. As shown in Figure 8, the dummy positioning device 80 based on the seat operating state is A seat tilt angle division module 81 for establishing a seat coordinate system and dividing the target seat into multiple seat tilt angles based on the seat coordinate system, A first keypoint measurement module 82 for measuring the coordinates of the first keypoint at multiple seat reclining angles of the HPM, A second keypoint measurement module 83 for measuring the coordinates of a second keypoint at multiple seat reclining angles of a crash dummy, A third keypoint measurement module 84 for measuring the coordinates of third keypoints at multiple seat reclining angles of the target driver, An applicability evaluation module 85 for evaluating the applicability of the HPM and the collision dummy based on the third keypoint coordinates of the target driver, the first keypoint coordinates of the HPM and the second keypoint coordinates of the collision dummy, A target model selection module 86 for selecting HPMs and collision dummies that meet the applicable preset conditions as target HPMs and target collision dummies, respectively, The system includes a collision dummy positioning module 87 for calculating the target keypoint coordinates of the target driver, which correspond to the keypoint coordinates of the target HPM, as the keypoint coordinates of the target collision dummy, based on the positioning conversion relationship between the target HPM and the target driver.

[0100] The dummy positioning device based on the seat operating state provided in this application establishes a seat coordinate system using a reclining angle division module 81 and divides the target seat into multiple seat reclining angles based on the seat coordinate system.

[0101] Next, the first keypoint measurement module 82 measures the first keypoint coordinates at multiple seat tilt angles of the HPM, the second keypoint measurement module 83 measures the second keypoint coordinates at multiple seat tilt angles of the collision dummy, and the third keypoint measurement module 84 measures the third keypoint coordinates at multiple seat tilt angles of the target driver.

[0102] Furthermore, the applicability evaluation module 85 evaluates the applicability of the HPM and the collision dummy based on the HPM's first key point coordinates and the collision dummy's second key point coordinates, with the target driver's third key point coordinates as the reference.

[0103] Next, the target model selection module 86 selects HPMs and collision dummies that meet the preset applicability conditions as target HPMs and target collision dummies, respectively.

[0104] Subsequently, the collision dummy positioning module 87 calculates the target keypoint coordinates of the target driver, which correspond to the keypoint coordinates of the target HPM, based on the positioning conversion relationship between the target HPM and the target driver, and uses these as the keypoint coordinates of the target collision dummy.

[0105] In this way, by measuring the keypoint coordinates at multiple seat reclining angles for the HPM, collision dummy, and target driver, and evaluating the applicability of the HPM and collision dummy based on these measurements, it is possible to select a target HPM and target collision dummy with superior applicability.

[0106] This allows for the conversion of the keypoint coordinates of the target HPM to the target driver's target keypoint coordinates during the experimental process, and by using these target keypoint coordinates as the keypoint coordinates of the target collision dummy, positioning information of the target collision dummy in the operating state of the large-angle seat can be obtained.

[0107] In one embodiment, the applicability evaluation module 85 can also be configured as follows.

[0108] The applicability evaluation module 85 performs a fitting process based on the coordinates of a first keypoint at multiple seat reclining angles of the HPM, and obtains a first vector that shows the tendency for the coordinates of the first keypoint to change with the seat reclining angle.

[0109] Furthermore, a fitting process is performed based on the second keypoint coordinates at multiple seat tilt angles of the collision dummy to obtain a second vector that shows the tendency for the second keypoint coordinates to change with the seat tilt angle.

[0110] Furthermore, a fitting process is performed based on the coordinates of the third keypoint at multiple seat tilt angles for the target driver, and a third vector is obtained that shows the tendency for the third keypoint coordinates to change in accordance with the seat tilt angle.

[0111] Subsequently, the first angle θ1 formed by the first and third vectors, and the second angle θ2 formed by the second and third vectors are calculated, and the applicability of HPM and collision dummies is evaluated based on angles θ1 and θ2.

[0112] In one embodiment, the collision dummy positioning module 87 may be further configured to measure the keypoint coordinates of the target HPM during the experimental process, input these keypoint coordinates into a trained neural network model to calculate the target keypoint coordinates of the target driver, and obtain these target keypoint coordinates as the keypoint coordinates of the target collision dummy.

[0113] In one embodiment, the seat reclining angle division module 81 may further measure the maximum tilt angle at which the backrest of the target seat tilts backward from an upright position to a maximum reclined position, and calculate the number of seat reclining angles of the target seat and the magnitude of each seat reclining angle based on the set adjustment angle and the maximum tilt angle.

[0114] In one embodiment, the first keypoint measurement module 82 may be further configured to adjust the target seat to the current seat reclining angle, attach the HPM to the target seat, and measure the left keypoint coordinates and the right keypoint coordinates at the seat reclining angle.

[0115] Furthermore, if the first error between the left keypoint coordinates and the right keypoint coordinates is less than a first preset value, the system may be configured to calculate the first keypoint coordinates of the HPM at the seat reclining angle based on the left keypoint coordinates and the right keypoint coordinates.

[0116] In one embodiment, the second keypoint measurement module 83 may be configured to further adjust the target seat to the current seat tilt angle, attach a collision dummy to the target seat, and measure the left keypoint coordinates and right keypoint coordinates of the collision dummy at the seat tilt angle.

[0117] Furthermore, if the second error between the left keypoint coordinates and the right keypoint coordinates is less than the second preset value, the system may be configured to calculate the second keypoint coordinates at the seat tilt angle of the collision dummy based on the left keypoint coordinates and the right keypoint coordinates.

[0118] In one embodiment, the third keypoint measurement module 84 may further be configured to adjust the target seat to the current seat tilt angle, adjust the seating posture of the target driver in the target seat, and measure the left keypoint coordinates and right keypoint coordinates of the target driver at the seat tilt angle.

[0119] Furthermore, if the third error between the left keypoint coordinates and the right keypoint coordinates is less than the third preset value, the system may be configured to calculate the third keypoint coordinates at the seat tilt angle of the target driver based on the left keypoint coordinates and the right keypoint coordinates.

[0120] Hereinafter, an electronic device according to an embodiment of this application will be described with reference to Figure 9. The electronic device may be either one or both of the first and second devices, or it may be a single device independent of them. The single device can communicate with the first and second devices and receive input signals collected from them.

[0121] Figure 9 is a block diagram of an electronic device according to one embodiment of this application.

[0122] As shown in Figure 9, the electronic device 10 includes one or more processors 11 and memory 12.

[0123] The processor 11 may include a central processing unit (CPU) or other types of processing units having data processing capability and / or instruction execution capability, and can control other components in the electronic device 10 to perform desired functions.

[0124] The memory 12 described above may include one or more computer program products, which can be implemented as various computer-readable storage media, including, for example, volatile memory and / or non-volatile memory.

[0125] The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache). The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0126] The computer-readable storage medium may store one or more computer program instructions, and the processor 11 can implement the methods of each embodiment of this application and / or other desired functions by executing these program instructions. Furthermore, the computer-readable storage medium may also store various data such as input signals and signal components.

[0127] In one embodiment, the electronic device 10 may further include an input device 13 and an output device 14, and these components are connected to each other by a bus system and / or other form of connection mechanism (not shown).

[0128] If the electronic device 10 is a single device, the input device 13 may be a communication network connector for receiving collected input signals from the first and second devices.

[0129] Furthermore, the input device 13 may also include user interface devices such as a keyboard or mouse.

[0130] The output device 14 can output various information, including calculated distance information and direction information, to an external source. The output device 14 may include, for example, a display, speaker, printer, communication network, or remote output device connected thereto.

[0131] For the sake of simplification, Figure 9 shows only some of the components of the electronic device 10 that are relevant to this application, and components such as buses and input / output interfaces are omitted. Depending on the specific usage, the electronic device 10 may include any other suitable components.

[0132] In addition to the above-described method and apparatus, embodiments of this application may further include a computer program product that includes computer program instructions. When the above-described computer program instructions are executed by a processor, the processor performs the steps of the method according to each embodiment of this specification.

[0133] The aforementioned computer program product can generate program code for performing the operations of the embodiments of this application using any combination of one or more programming languages. The programming languages ​​are not limited to object-oriented programming languages ​​such as Java and C++, but may also include general procedural programming languages ​​such as the "C" language. The program code may be executed entirely on the user's device, partially on the user's device, or partially or entirely on a remote computer or server.

[0134] Furthermore, the embodiments of this application may be computer-readable storage media in which computer program instructions are stored. When the computer program instructions are executed by the processor, the processor performs the steps of the methods of each embodiment described herein.

[0135] The computer-readable storage medium described above may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, but is not limited to, devices or apparatus using, for example, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor technology, or any combination thereof. More specific examples (non-exclusive list) of readable storage media include electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0136] The basic principles of this application have been explained above with specific examples, but the advantages, superiority, and effects mentioned in connection with this application are merely illustrative and do not limit this application. Furthermore, these advantages, superiority, and effects should not be assumed to be present in each example of this application. Moreover, the specific details disclosed above are for illustrative purposes and to facilitate understanding, and do not limit this application, nor do they mean that this application must necessarily be realized in the manner described above.

[0137] The block diagrams of devices, apparatus, equipment, and systems described in connection with this application are for illustrative purposes only and do not require or suggest that connections, arrangements, or configurations must be made only in accordance with the methods shown in the block diagrams. As will be understood by those skilled in the art, these devices, apparatus, equipment, or systems can be connected, arranged, or configured in any suitable manner. For example, phrases such as “includes,” “consist of,” and “have” are open vocabulary and mean “includes, but not limited to.” Also, unless explicitly stated in the context, the terms “or” and “and” as used herein shall be interpreted as “and / or.” Furthermore, the term “for example” shall mean “for example, but not limited to.”

[0138] Furthermore, in the apparatus or method of this application, each component or each process can be divided and / or reorganized. These divisions and / or reorganizations should be treated as equivalent embodiments based on the technical concept of this disclosure.

[0139] The above disclosure will enable any person skilled in the art to implement or utilize this application. Furthermore, various modifications or changes to these embodiments will be obvious to a person skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit of the invention. Accordingly, this application is not limited to the embodiments shown herein, but covers the broadest scope that corresponds to the disclosed principles and novel features.

[0140] The above description is provided for illustrative and explanatory purposes only and is not intended to limit this application to the specific forms disclosed herein. While several exemplary embodiments and examples have been described above, those skilled in the art will understand that various modifications, alterations, changes, additions, and secondary combinations are possible with respect to these.

Claims

1. A step of establishing a seat coordinate system and dividing the target seat into multiple seat reclining angles based on the seat coordinate system, In each of the aforementioned multiple seat reclining angles, The process of measuring the first key point coordinates of the human point machine, The process of measuring the coordinates of the second key point of the collision dummy, The process of measuring the third key point coordinates of the target driver, A step of evaluating the applicability of the Human Point Machine and the collision dummy to the target driver based on the third key point coordinates of the target driver, the first key point coordinates and the second key point coordinates, A step of selecting a human point machine and a collision dummy whose applicability satisfies predetermined conditions as the target human point machine and target collision dummy, respectively. A dummy positioning method based on seat operating state, executed by a processor, includes the step of calculating the target key point coordinates of the target driver, corresponding to the key point coordinates of the target human point machine, as the key point coordinates of the target collision dummy, based on the positioning conversion relationship between the target human point machine and the target driver, The process of evaluating the applicability of the Human Point Machine and the collision dummy to the target driver is as follows: The process involves performing an approximation process based on the first keypoint coordinates at the multiple seat reclining angles of the Human Point Machine, and calculating a first vector in which the first keypoint coordinates change with the seat reclining angle. The process involves performing an approximation process based on the second keypoint coordinates at the multiple seat tilt angles of the collision dummy, and calculating a second vector in which the second keypoint coordinates change with the seat tilt angle. A step of performing an approximation process based on the coordinates of the third keypoint at the multiple seat tilt angles of the subject driver, and calculating a third vector in which the coordinates of the third keypoint change with the seat tilt angle, A step of calculating the angle θ1 between the first vector and the third vector and the angle θ2 between the second vector and the third vector, A step of evaluating the applicability of the human point machine and the collision dummy based on the angles θ1 and θ2, A dummy positioning method based on the seat operating state, characterized by including the following:

2. The step of calculating the target keypoint coordinates of the target driver, corresponding to the keypoint coordinates of the target human point machine, as the keypoint coordinates of the target collision dummy, based on the positioning conversion relationship between the target human point machine and the target driver, is as follows: The process involves measuring the key point coordinates of the target human point machine, The process involves inputting the measured keypoint coordinates of the target human point machine into a trained neural network model, obtaining the target keypoint coordinates of the target driver as the output, and using the output as the keypoint coordinates of the target collision dummy. A dummy positioning method based on the seat operating state according to claim 1, characterized by including the following:

3. The step of dividing the target seat into a plurality of seat reclining angles based on the aforementioned seat coordinate system includes the step of measuring the maximum reclining angle at which the backrest of the target seat tilts from an upright position to the maximum reclining position, A step of calculating the number of seat reclining angles of the target seat and the angle value of each seat reclining angle based on the set adjustment angle and the maximum tilt angle, A dummy positioning method based on the seat operating state according to claim 1, characterized by including the following:

4. The step of measuring the first key point coordinates of the human point machine includes the steps of adjusting the target seat to a predetermined seat reclining angle and placing the human point machine on the target seat, A step of measuring the left keypoint coordinates and the right keypoint coordinates at the seat reclining angle of the Human Point Machine, If the difference between the left keypoint coordinate and the right keypoint coordinate is less than a first preset value, the process involves calculating the first keypoint coordinate at the seat reclining angle based on the left keypoint coordinate and the right keypoint coordinate. A dummy positioning method based on the seat operating state according to claim 1, characterized by including the following:

5. The step of measuring the coordinates of the second key point of the collision dummy includes the steps of adjusting the target seat to a predetermined seat reclining angle and placing the collision dummy on the target seat, A step of measuring the left keypoint coordinates and right keypoint coordinates of the seat rear tilt angle of the collision dummy, If the difference between the left keypoint coordinate and the right keypoint coordinate is less than a second preset value, the process involves calculating the second keypoint coordinate at the seat reclining angle based on the left keypoint coordinate and the right keypoint coordinate. A dummy positioning method based on the seat operating state according to claim 1, characterized by including the following:

6. The step of measuring the third key point coordinates of the target driver includes the steps of adjusting the target seat to a predetermined seat reclining angle and adjusting the seating posture of the target driver in the target seat, A step of measuring the left keypoint coordinates and right keypoint coordinates at the seat tilt angle of the subject driver, If the difference between the left keypoint coordinates and the right keypoint coordinates of the subject driver is less than the third preset value, the third keypoint coordinates at the seat tilt angle are calculated based on the left keypoint coordinates and the right keypoint coordinates of the subject driver. A dummy positioning method based on the seat operating state according to claim 1, characterized by including the following:

7. A seat tilt angle division module for establishing a seat coordinate system and dividing a target seat into multiple seat tilt angles based on the seat coordinate system, A first keypoint measurement module for measuring the coordinates of a first keypoint at the multiple seat reclining angles of the Human Point Machine, A second keypoint measurement module for measuring the coordinates of the second keypoint at the multiple seat reclining angles of the collision dummy, A third keypoint measurement module for measuring the coordinates of the third keypoint at the multiple seat reclining angles of the target driver, An applicability evaluation module for evaluating the applicability of the Human Point Machine and the collision dummy, based on the third keypoint coordinates of the multiple seat reclining angles of the target driver, the first keypoint coordinates of the multiple seat reclining angles of the Human Point Machine, and the second keypoint coordinates of the multiple seat reclining angles of the collision dummy, A target model selection module for selecting the human point machine and the collision dummy that satisfy the aforementioned applicability conditions as the target human point machine and target collision dummy, respectively. The system includes a collision dummy positioning module for calculating the target key point coordinates of the target driver, corresponding to the key point coordinates of the target human point machine, as the key point coordinates of the target collision dummy, based on the positioning conversion relationship between the target human point machine and the target driver. The aforementioned applicability evaluation module is Based on the coordinates of the first keypoints at the multiple seat reclining angles of the Human Point Machine, an approximation process is performed to calculate the first vector. Based on the coordinates of the second keypoints at the multiple seat tilt angles of the collision dummy, an approximation process is performed to calculate the second vector. Based on the coordinates of the third keypoints at the multiple seat tilt angles of the subject driver, an approximation process is performed to calculate the third vector. The first angle between the first vector and the third vector and the second angle between the second vector and the third vector are calculated, Based on the first and second angles, the applicability of the human point machine and the collision dummy to the target driver is evaluated. A dummy positioning device based on the seat operating state, characterized by the above.

8. A computer-readable storage medium storing a computer program which includes instructions for causing a computer to perform each step of the method according to any one of claims 1 to 6.

9. A memory for storing instructions for performing each step of the method according to any one of claims 1 to 6, A processor for executing the instructions stored in the memory, The memory for storing instructions that the processor can execute, An electronic device characterized by comprising the following features.

Images