CN109017602B - Self-adaptive center console based on human body gesture recognition and control method thereof - Google Patents
Self-adaptive center console based on human body gesture recognition and control method thereof Download PDFInfo
- Publication number
- CN109017602B CN109017602B CN201810769785.7A CN201810769785A CN109017602B CN 109017602 B CN109017602 B CN 109017602B CN 201810769785 A CN201810769785 A CN 201810769785A CN 109017602 B CN109017602 B CN 109017602B
- Authority
- CN
- China
- Prior art keywords
- display screen
- center console
- distance
- motor
- max
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005070 sampling Methods 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 230000005484 gravity Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R11/02—Arrangements for holding or mounting articles, not otherwise provided for for radio sets, television sets, telephones, or the like; Arrangement of controls thereof
- B60R11/0229—Arrangements for holding or mounting articles, not otherwise provided for for radio sets, television sets, telephones, or the like; Arrangement of controls thereof for displays, e.g. cathodic tubes
- B60R11/0235—Arrangements for holding or mounting articles, not otherwise provided for for radio sets, television sets, telephones, or the like; Arrangement of controls thereof for displays, e.g. cathodic tubes of flat type, e.g. LCD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R2011/0001—Arrangements for holding or mounting articles, not otherwise provided for characterised by position
- B60R2011/0003—Arrangements for holding or mounting articles, not otherwise provided for characterised by position inside the vehicle
- B60R2011/0007—Mid-console
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R2011/0042—Arrangements for holding or mounting articles, not otherwise provided for characterised by mounting means
- B60R2011/008—Adjustable or movable supports
- B60R2011/0092—Adjustable or movable supports with motorization
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a self-adaptive center console based on human body gesture recognition, which comprises: the support is provided with a movable slide rail; the movable sliding plate is matched with the movable sliding rail and horizontally moves on the movable sliding rail; a base fixed on the moving slide plate; the first motor is fixed on the base, and the power output end is connected with the first joint and used for driving the first joint to rotate in a horizontal plane; the power output end of the second motor is connected with one end of the first rotating arm; the second joint is rotatably connected with the other end of the first rotating arm and one end of the second rotating arm at the same time; the third joint is fixedly connected to the other end of the second rotating arm; the power output end of the third motor is connected with the driving gear; the display screen, its back is connected with driven gear through connecting branch, the driving gear mutually supports and rotates in the horizontal plane. The position of the center console can be adjusted. The invention also provides a control method of the self-adaptive center console based on human body gesture recognition.
Description
Technical Field
The invention relates to a center console, in particular to a self-adaptive center console based on human body gesture recognition and a control method thereof.
Background
The center console is usually a workbench between a driver and a passenger, on which most of control buttons of the automobile except driving are concentrated, and at the same time, function keys of comfort and entertainment devices such as an air conditioner, a sound device and the like are also arranged on the center console, so that the center console has a vital effect on the automobile. During running, a driver needs to make a road with the center console at any time, and the design and arrangement of the center console influence the comfort of each vehicle and influence the feeling of the driver during use.
As automotive technology evolves, member comfort has increasingly profound effects on automotive design. After unmanned realization, the driver's four limbs will be liberated from current constraint, and passenger's gesture will be more diversified on the vehicle. It is currently desirable to make riders more comfortable by performing adaptive adjustments of the center console based on the rider's pose and body pressure distribution data.
Disclosure of Invention
The invention designs and develops a self-adaptive center console based on human body gesture recognition, which can adjust the position of the center console, change the angle of a display screen and improve the driving comfort.
The invention also designs and develops a control method of the self-adaptive center console based on human body gesture recognition, and the actual position and the display screen angle of the center console can be adjusted according to the gesture scale of the rider.
The invention further aims to control the actual position of the center console through the BP neural network, improve the accuracy of the position adjustment of the center console and enable a rider to drive more comfortably.
The technical scheme provided by the invention is as follows:
an adaptive center console based on human body gesture recognition, comprising:
the support is provided with a movable slide rail;
the movable sliding plate is matched with the movable sliding rail and horizontally moves on the movable sliding rail;
a base fixed on the moving slide plate;
the first motor is fixed on the base, and the power output end is connected with the first joint and used for driving the first joint to rotate in a horizontal plane;
the power output end of the second motor passes through the first joint, is connected with one end of the first rotating arm and is used for driving the first rotating arm to rotate in a vertical plane;
the second joint is rotatably connected with the other end of the first rotating arm and one end of the second rotating arm at the same time;
the third joint is fixedly connected to the other end of the second rotating arm;
the power output end of the third motor passes through the third joint, and is connected with the driving gear;
the back of the display screen is connected with a driven gear through a connecting support rod, and the display screen can be mutually matched with the driving gear to rotate in a horizontal plane.
Preferably, the second joint further comprises:
the power output end of the first connecting motor is connected with the other end of the first rotating arm and is used for driving the first rotating arm to rotate;
the second connecting motor is used for driving the second rotating arm to rotate.
Preferably, a plurality of control buttons are provided on the second rotating arm.
Preferably, a jack is arranged at one end of the base.
Preferably, one side of the chassis is provided with an arc-shaped connecting plate.
Preferably, the method further comprises:
the camera is fixed on the cab top cover A column;
a pressure sensor disposed at the bottom of the rider seat;
and the controller is electrically connected with the camera, the pressure sensor, the first motor, the second motor, the third motor and the movable slide rail and controls the first motor, the second motor, the third motor and the movable slide rail.
Preferably, the controller is connected to and controls the first connection motor and the second connection motor.
The control method of the self-adaptive center console based on human body gesture recognition is characterized by comprising the following steps of:
step one, acquiring a distance Y between eyes and a display screen of a center console, a distance J between shoulders and the display screen of the center console, a distance K between hips and the display screen of the center console, a pressure G above a seat and a camera rotating speed V by adopting a sensor according to a sampling period;
step two, normalizing parameters and establishing an input layer vector x= { x of the three-layer BP neural network 1 ,x 2 ,x 3 ,x 4 ,x 5}, wherein ,x1 As the eye distance coefficient, x 2 As the shoulder distance coefficient, x 3 As a hip distance coefficient, x 4 Is the pressure coefficient, x 5 Is a velocity coefficient;
step three, the input layer is mapped to an intermediate layer, and the intermediate layer vector y= { y 1 ,y 2 ,...,y l And the number of intermediate layer nodes is equal to the number of intermediate layer nodes, and the number of intermediate layer nodes is equal to the following:wherein m is the number of nodes of the input layer, l is the number of nodes of the middle layer, and n is the number of nodes of the output layer;
step four, obtaining an output layer vector o= { o 1 ,o 2 ,o 3 ,o 4}, wherein ,o1 For adjusting coefficient of horizontal rotation angle of display screen o 2 For adjusting coefficient of vertical rotation angle of display screen, o 3 O is a distance coefficient for the display screen to move in the horizontal plane 4 A distance coefficient is moved for the display screen in the vertical display screen;
step five, controlling the horizontal corner, the vertical corner, the horizontal movement distance and the vertical movement distance of the display screen, so that:
θ (i+1) ＝o 1 i θ max ；
γ (i+1) ＝o 2 i γ max ；
L (i+1) ＝o 3 i L max ；
S (i+1) ＝o 4 i S max ；
wherein ,for the output layer parameter, θ, of the ith sampling period max For the maximum horizontal angle of the display screen, gamma max For the maximum vertical rotation angle of the display screen, L max S is the maximum horizontal movement distance of the display screen max The maximum vertical movement distance of the display screen.
Preferably, the horizontal rotation angle theta of the display screen 1 Vertical rotation angle gamma 1 Distance of horizontal movement L 1 5 and vertical movement distance S 1 The method meets the following conditions:
θ 1 ＝0.3θ max ；
γ 1 ＝0.6γ max ；
L 1 ＝0.4L max ；
S 1 ＝0.5S max ；
preferably, the rotation speed V of the camera satisfies:
wherein P is the gravity center position of the rider, P 0 For the standard value of the gravity center position, G is the pressure above the seat, e is the natural logarithmic base number, h 1 H is the distance between the camera and the saddle 2 V is the distance between the saddle and the chassis i And setting a standard rotation speed for the camera.
The beneficial effects of the invention are as follows: the position data of the rider is collected through the camera, so that the position of the center console is dynamically adjusted according to the real-time image and the action gesture of the rider, the adjustment of the center console is not limited by the small-amplitude adjustment of the original position, and the adjustment is changed into the wide-range all-field multi-angle all-dimensional adjustment. The BP neural network controls the actual position of the center console, improves the accuracy of the position adjustment of the center console, and enables a driver to drive more comfortably and with higher safety.
Drawings
Fig. 1 is a schematic structural diagram of a self-adaptive center console based on human body gesture recognition according to the present invention.
Fig. 2 is a front view of the adaptive center console based on human gesture recognition according to the present invention.
Fig. 3 is a flowchart of a control method of the self-adaptive center console based on human body gesture recognition.
Detailed Description
The present invention is described in further detail below with reference to the drawings to enable those skilled in the art to practice the invention by referring to the description.
As shown in fig. 1-3, the present invention provides an adaptive center console based on human body gesture recognition, comprising: the display 100, the first motor 210, the first rotating arm 230, the second rotating arm 310, the third motor 410, and the moving slide rail 430.
The support is fixed on the bottom surface of the vehicle body and positioned at the front part of the cab. The support is provided with a movable slide rail 430 which can be matched with a movable slide plate arranged on the support, and a driving motor is arranged in the movable slide rail 430 and can drive the movable slide rail 430 to drive the movable slide plate to horizontally move. The base 420 is fixed to the moving slide plate and can move together with the moving slide plate. An arc-shaped connecting plate is arranged on one side of the base 420, and a jack is arranged at one end of the base.
The first motor 410 is fixed on the base, and a power output end of the first motor 410 is connected with the first joint 330, so that the first joint 330 can be driven to rotate in a horizontal plane. The power output end of the second motor 320 passes through the first joint from left to right and is connected to one end of the first rotating arm 310, so as to drive the first rotating arm 310 to rotate in a vertical plane. A plurality of control buttons are provided on the first rotary arm 310.
The second joint 240 has a cavity therein, and a first connection motor is disposed in the second joint 240, and a power output end of the first connection motor is connected to the other end of the first rotating arm 310, for driving the first rotating arm 310 to rotate; a second connection motor is further disposed in the second joint 240, and a power output end thereof is connected to one end of the second rotating arm 230, so as to drive the second rotating arm 230 to rotate, thereby the second joint can be simultaneously and rotatably connected to the other end of the first rotating arm 310 and one end of the second rotating arm 230.
The other end of the second rotating arm 230 is fixedly connected with a third joint 220, the power output end of the third motor 210 passes through the third shutdown 220 from left to right, and a driving gear is also connected to the power output end of the third motor 210. The display screen 100 is arranged at the top of the central console, a connecting support rod is fixed at the back of the display screen 100, one end of the connecting support rod is connected with a driven gear, and the connecting support rod can be matched with a driving gear to rotate in a horizontal plane.
Still be provided with the camera in the driver's cabin, its A post of installing at the driver's cabin top cap, the camera can rotate in horizontal direction and vertical direction, shoots the rider, measures the distance in each position of rider. The pressure sensor is arranged at the bottom of the seat, can measure the pressure above the seat and senses whether a driver is on the seat. The controller is connected with the camera, the pressure camera sensor, the first motor 410, the second motor 320, the third motor 210, the first connecting motor, the second connecting motor and the movable sliding rail 430, so that the position adjustment of the center console is realized.
The invention also provides a control method of the self-adaptive center console based on human body gesture recognition, which controls the actual position of the center console through the BP neural network and improves the control precision of the position of the center console.
Meanwhile, in the control process, based on parameters such as the pressure above the seat in the control process, the empirical formula of the rotation speed of the camera is obtained to satisfy the following conditions:
wherein P is the gravity center position of the rider, the unit is mm, and P 0 The standard value of the gravity center is in mm, G is the pressure above the seat, E is the natural logarithmic base number, lambda is the correction coefficient, and the range is 0-10, h 1 The distance between the camera and the saddle is in mm and h 2 The distance between the saddle and the chassis is in mm and V i The standard rotational speed set for the camera is given in units of deg./s.
Step S210, establishing a BP neural network model,
the BP network system structure adopted by the invention is composed of three layers, wherein the first layer is an input layer, m nodes are used as the input layer, m detection signals representing the working state of equipment are corresponding to the first layer, and the signal parameters are given by a data preprocessing module. The second layer is a hidden layer, and the total number of the nodes is determined in an adaptive manner by the training process of the network. The third layer is an output layer, and n nodes are all determined by the response that the system actually needs to output.
The mathematical model of the network is:
input vector: x= (x 1 ,x 2 ,...,x m ) T ；
Intermediate layer vector: y= (y) 1 ,y 2 ,...,y l ) T ；
Output vector: o= (O) 1 ,o 2 ,...,o n ) T ；
In the invention, the number of input layer nodes m=5, the number of output layer nodes n=4, and the number of hidden layer nodes l is estimated by the following formula:
according to the sampling period, a sensor is adopted to acquire the distance Y between eyes and a display screen of the center console, the distance J between shoulders and the display screen of the center console, the distance K between hips and the display screen of the center console, the pressure G above a seat and the rotation speed V of a camera;
the 5 parameters of the input signal are expressed as: x is x 1 As the eye distance coefficient, x 2 As the shoulder distance coefficient, x 3 As a hip distance coefficient, x 4 Is the pressure coefficient, x 5 Is a velocity coefficient;
since the data acquired by the sensor belong to different physical quantities, the dimensions are different. Therefore, the data needs to be normalized to a number between 0 and 1 before the data is input into the artificial neural network.
Specifically, the distance Y between the eyes of the rider and the display screen of the center console is measured through a camera, normalized, and then an eye distance coefficient x is obtained 1 ：
wherein ,Ymax For maximum eye distance, Y min Is the minimum eye distance;
similarly, the distance J between the shoulder of the rider and the display screen of the center console is measured through a camera, and after normalization, a shoulder distance coefficient x is obtained 2 ：
wherein ,Jmax For maximum shoulder distance, J min Is the minimum shoulder distance;
similarly, the distance K between the hip of the rider and the display screen of the center console is measured through a camera, and after normalization, the hip distance coefficient x is obtained 3 ：
wherein ,Kmax For maximum hip distance, K min Is the minimum hip distance;
similarly, the pressure G of the rider above the seat is measured by a pressure sensor, normalized, and then the pressure coefficient x is obtained 4 ：
wherein ,Gmax Maximum pressure G min Is the minimum pressure;
similarly, the rotation speed V of the camera is measured by a speed sensor, normalized, and then the speed coefficient x is obtained 5 ：
wherein ,Vmax For the maximum rotation speed of the camera, V min The minimum rotation speed of the camera is set.
The 4 parameters of the output layer are expressed as: o (o) 1 For adjusting coefficient of horizontal rotation angle of display screen o 2 For adjusting coefficient of vertical rotation angle of display screen, o 3 For the horizontal movement distance coefficient of the display screen, o 4 The display screen vertical movement distance coefficient.
Display screen horizontal rotation angle adjusting coefficient o 1 Expressed as the ratio of the horizontal rotation angle of the display screen in the next sampling period to the maximum horizontal rotation angle of the display screen set in the current sampling period, namely, the horizontal rotation angle of the display screen acquired in the ith sampling period is theta i Outputting the display screen horizontal rotation angle adjustment coefficient of the ith sampling period through BP neural networkThen, the horizontal rotation angle theta of the display screen in the (i+1) th sampling period is controlled i+1 So that it satisfies the following conditions:
wherein ,θmax Is the maximum horizontal rotation angle of the display screen.
Vertical rotation angle adjusting coefficient o of display screen 2 The display is expressed as the vertical rotation angle of the display screen in the next sampling period and the display set in the current sampling periodThe ratio of the maximum vertical rotation angle of the screen, namely the vertical rotation angle of the display screen acquired in the ith sampling period is gamma i Outputting a display screen vertical rotation angle adjustment coefficient of the ith sampling period through BP neural networkThen, controlling the vertical rotation angle gamma of the display screen in the (i+1) th sampling period i+1 So that it satisfies the following conditions:
γ i+1 ＝o 2 i γ max ，
wherein ,γmax The maximum vertical rotation angle of the display screen.
Horizontal movement distance coefficient o of display screen 3 Expressed as the ratio of the horizontal movement distance of the display screen in the next sampling period to the maximum horizontal movement distance set in the current sampling period, namely, the horizontal movement distance of the display screen acquired in the ith sampling period is L i Outputting a display screen horizontal movement distance adjustment coefficient of the ith sampling period through the BP neural networkThen, the horizontal movement distance L of the display screen in the (i+1) th sampling period is controlled i+1 So that it satisfies the following conditions:
wherein ,Lmax The maximum horizontal movement distance of the display screen is set.
Vertical movement distance coefficient o of display screen 4 Expressed as the ratio of the vertical movement distance of the display screen in the next sampling period to the maximum vertical movement distance set in the current sampling period, namely, the vertical movement distance of the display screen acquired in the ith sampling period is S i Outputting a display screen vertical movement distance adjustment coefficient of the ith sampling period through BP neural networkAfter that, controlDisplay screen horizontal movement distance S in (i+1) th sampling period i+1 So that it satisfies the following conditions:
wherein ,Smax The maximum vertical movement distance of the display screen.
Step S220, performing BP neural network training
Obtaining training samples according to historical experience data, and giving connection weight W between input node i and hidden layer node j ij Connection weight W between hidden layer node j and output layer node k jk Threshold θ of hidden node j j The threshold value theta of the output layer node k k 、W ij 、W jk 、θ j 、θ k Are random numbers between-1 and 1.
Continuously correcting W in the training process ij 、W jk And (3) completing the training process of the neural network until the systematic error is less than or equal to the expected error.
As shown in table 1, a set of training samples and the values of the nodes during training are given.
Table 1 training process node values
Step S230, collecting a central console operation signal, inputting the central console operation signal into a neural network to obtain an output signal, and controlling the central console;
the trained artificial neural network is solidified in the controller chip, so that the hardware circuit has the functions of prediction and intelligent decision making, and intelligent hardware is formed. After the intelligent hardware is powered on and started, detecting the distance Y between eyes and a center console display screen, the distance J between shoulders and the center console display screen, the distance K between hips and the center console display screen, the pressure G above a seat and the rotating speed V of a camera, and carrying out normalization processing on the parameters to obtain an initial input vector of the BP neural networkObtaining an initial output vector by the operation of the BP neural network>
Step S240, obtaining an initial output vectorThen, the speed regulation and control can be carried out, the distance Y between the eyes and the center console display screen, the distance J between the shoulders and the center console display screen, the distance K between the hips and the center console display screen, the pressure G above the seat and the rotating speed V of the camera can be obtained through the sensor, and the input vector ∈of the ith sampling period can be obtained through formatting>Obtaining an output vector of the ith sampling period through the operation of the BP neural network>Then, controlling and adjusting the horizontal corner, the vertical corner, the horizontal movement distance and the vertical movement distance of the display screen, so that the horizontal corner, the vertical corner, the horizontal movement distance and the vertical movement distance of the display screen in the (i+1) th sampling period are respectively as follows:
γ i+1 ＝o 2 i γ max
L (i+1) ＝o 3 i L max ；
S (i+1) ＝o 4 i S max
in the initial stage of the process,
θ 1 ＝0.3θ max ；
γ 1 ＝0.6γ max ；
L 1 ＝0.4L max ；
S 1 ＝0.5S max ；
wherein ,respectively, the output parameters theta in the ith sampling period max For the maximum horizontal rotation angle gamma of the display screen max For the maximum vertical rotation angle L of the display screen max For the maximum horizontal movement distance S of the display screen max The maximum vertical movement distance of the display screen.
Through the arrangement, the control method of the self-adaptive center console based on human body gesture recognition controls the actual position of the center console through the BP neural network algorithm, improves the accuracy of center console position adjustment, and enables riders to drive more comfortably and with higher safety.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (9)
1. The control method of the self-adaptive center console based on the human body gesture recognition is characterized by controlling the self-adaptive center console based on the human body gesture recognition, and the self-adaptive center console based on the human body gesture recognition comprises the following steps:
the support is provided with a movable slide rail;
the movable sliding plate is matched with the movable sliding rail and horizontally moves on the movable sliding rail;
a base fixed on the moving slide plate;
the first motor is fixed on the base, and the power output end is connected with the first joint and used for driving the first joint to rotate in a horizontal plane;
the power output end of the second motor passes through the first joint, is connected with one end of the first rotating arm and is used for driving the first rotating arm to rotate in a vertical plane;
the second joint is rotatably connected with the other end of the first rotating arm and one end of the second rotating arm at the same time;
the third joint is fixedly connected to the other end of the second rotating arm;
the power output end of the third motor passes through the third joint, and is connected with the driving gear;
the back of the display screen is connected with a driven gear through a connecting support rod and can be mutually matched with the driving gear to rotate in a horizontal plane;
the control method of the self-adaptive center console based on human body gesture recognition comprises the following steps:
step one, acquiring a distance Y between eyes and a display screen of a center console, a distance J between shoulders and the display screen of the center console, a distance K between hips and the display screen of the center console, a pressure G above a seat and a camera rotating speed V by adopting a sensor according to a sampling period;
step two, normalizing parameters and establishing an input layer vector x= { x of the three-layer BP neural network 1 ,x 2 ,x 3 ,x 4 ,x 5}, wherein ,x1 As the eye distance coefficient, x 2 As the shoulder distance coefficient, x 3 As a hip distance coefficient, x 4 Is the pressure coefficient, x 5 Is a velocity coefficient;
step three, the input layer is mapped to an intermediate layer, and the intermediate layer vector y= { y 1 ,y 2 ,...,y l And the number of the intermediate layer nodes is equal to the number of the intermediate layer nodes, and the number of the intermediate layer nodes is equal to the following:wherein m is the number of nodes of the input layer, l is the number of nodes of the middle layer, and n is the number of nodes of the output layer;
step four, obtaining an output layer vector o= { o 1 ,o 2 ,o 3 ,o 4}, wherein ,o1 For adjusting coefficient of horizontal rotation angle of display screen o 2 For adjusting coefficient of vertical rotation angle of display screen, o 3 O is a distance coefficient for the display screen to move in the horizontal plane 4 A distance coefficient is moved for the display screen in the vertical display screen;
step five, controlling the horizontal corner, the vertical corner, the horizontal movement distance and the vertical movement distance of the display screen, so that:
θ (i+1) ＝o 1 i θ max ；
γ (i+1) ＝o 2 i γ max ；
L (i+1) ＝o 3 i L max ；
S (i+1) ＝o 4 i S max ；
wherein ,for the output layer parameter, θ, of the ith sampling period max For the maximum horizontal angle of the display screen, gamma max For the maximum vertical rotation angle of the display screen, L max S is the maximum horizontal movement distance of the display screen max The maximum vertical movement distance of the display screen.
2. The method for controlling an adaptive center console based on human body posture recognition according to claim 1, wherein the second joint further comprises:
the power output end of the first connecting motor is connected with the other end of the first rotating arm and is used for driving the first rotating arm to rotate;
the second connecting motor is used for driving the second rotating arm to rotate.
3. The control method of the adaptive center console based on human body gesture recognition according to claim 2, wherein a plurality of control buttons are provided on the second rotating arm.
4. The control method of the self-adaptive center console based on human body gesture recognition according to claim 3, wherein a jack is arranged at one end of the base.
5. The control method of the self-adaptive center console based on human body gesture recognition according to claim 4, wherein an arc-shaped connecting plate is arranged on one side of the base.
6. The method for controlling an adaptive center console based on human body posture recognition according to claim 5, further comprising:
the camera is fixed on the cab top cover A column;
a pressure sensor disposed at the bottom of the rider seat;
and the controller is electrically connected with the camera, the pressure sensor, the first motor, the second motor, the third motor and the movable slide rail and controls the first motor, the second motor, the third motor and the movable slide rail.
7. The method for controlling an adaptive center console based on human body posture recognition according to claim 6, wherein the controller is connected to and controls the first connection motor and the second connection motor.
8. The method for controlling an adaptive center console based on human body posture recognition according to claim 7, wherein in an initial state, a horizontal rotation angle θ of the display screen 1 Vertical rotation angle gamma 1 Distance of horizontal movement L 1 5 and vertical movement distance S 1 The method meets the following conditions:
θ 1 ＝0.3θ max ；
γ 1 ＝0.6γ max ；
L 1 ＝0.4L max ；
S 1 ＝0.5S max 。
9. the control method of the adaptive center console based on human body gesture recognition according to claim 8, wherein the camera rotation speed V satisfies:
wherein P is the gravity center position of the rider, P 0 Is the standard value of the gravity center position, G is the pressure above the seat, e is the natural logarithmic base number, lambda is the correction coefficient, h 1 H is the distance between the camera and the saddle 2 V is the distance between the saddle and the chassis i And setting a standard rotation speed for the camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810769785.7A CN109017602B (en) | 2018-07-13 | 2018-07-13 | Self-adaptive center console based on human body gesture recognition and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810769785.7A CN109017602B (en) | 2018-07-13 | 2018-07-13 | Self-adaptive center console based on human body gesture recognition and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109017602A CN109017602A (en) | 2018-12-18 |
| CN109017602B true CN109017602B (en) | 2023-08-18 |
Family
ID=64642116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810769785.7A Active CN109017602B (en) | 2018-07-13 | 2018-07-13 | Self-adaptive center console based on human body gesture recognition and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109017602B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109795341A (en) * | 2019-01-22 | 2019-05-24 | 南京越博动力系统股份有限公司 | A kind of energy-efficient control method of pure electric automobile equipped with CVT stepless transmission |
| CN110254362B (en) * | 2019-06-18 | 2021-01-19 | 浙江吉利控股集团有限公司 | Adjustable automobile central control large screen assembly |
| CN111717124B (en) * | 2020-06-05 | 2021-11-23 | 北京超星未来科技有限公司 | Angle adjusting device of adjustable laser radar angle |
| CN112298059A (en) * | 2020-10-26 | 2021-02-02 | 武汉华星光电技术有限公司 | Vehicle-mounted display screen adjusting device and vehicle |
| CN116061821A (en) * | 2021-11-01 | 2023-05-05 | 华人运通(江苏)技术有限公司 | Control method, device and system of vehicle, mechanical arm and vehicle |
| CN114679529A (en) * | 2022-04-07 | 2022-06-28 | 深圳市华屹医疗科技有限公司 | Optical processing device for non-contact human body posture acquisition |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5434783A (en) * | 1993-01-06 | 1995-07-18 | Nissan Motor Co., Ltd. | Active control system |
| CN105538325A (en) * | 2015-12-30 | 2016-05-04 | 哈尔滨理工大学 | Decoupling control method of single leg joint of hydraulic four-leg robot |
| EP3015313A1 (en) * | 2014-11-03 | 2016-05-04 | Volvo Car Corporation | A display assembly for an interior panel in a vehicle |
| CN105783896A (en) * | 2016-05-17 | 2016-07-20 | 吉林大学 | Interactive type unmanned aerial vehicle magnetic compass calibration device and method |
| CN106314303A (en) * | 2016-08-31 | 2017-01-11 | 法乐第(北京)网络科技有限公司 | Center control screen assembly and vehicle |
| CN106938764A (en) * | 2017-04-28 | 2017-07-11 | 浙江硕和机器人科技有限公司 | A kind of guide plate reciprocating conveying mechanism |
| CN106990410A (en) * | 2017-03-08 | 2017-07-28 | 中国汽车技术研究中心 | A kind of vehicle external dimensions device for fast detecting and method |
| CN107176098A (en) * | 2017-07-10 | 2017-09-19 | 辽宁工业大学 | A kind of poor automatic monitoring warning device in blind area of lubrication groove and control method |
| CN107344528A (en) * | 2016-05-06 | 2017-11-14 | 杨新宇 | Car-mounted device, motor vehicles and the method for installing car-mounted device |
| CN107579699A (en) * | 2017-09-12 | 2018-01-12 | 安徽亦知企业管理有限公司 | A kind of solar energy photovoltaic generator and its adjusting method based on BP neural network regulation angle |
| CN207056860U (en) * | 2017-04-17 | 2018-03-02 | 姚汉奇 | A kind of path optimization atomizing spraying system of view-based access control model identification technology |
| CN208376662U (en) * | 2018-07-13 | 2019-01-15 | 吉林大学 | A kind of adaptive console based on body state detection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7206697B2 (en) * | 2003-10-14 | 2007-04-17 | Delphi Technologies, Inc. | Driver adaptive collision warning system |
-
2018
- 2018-07-13 CN CN201810769785.7A patent/CN109017602B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5434783A (en) * | 1993-01-06 | 1995-07-18 | Nissan Motor Co., Ltd. | Active control system |
| EP3015313A1 (en) * | 2014-11-03 | 2016-05-04 | Volvo Car Corporation | A display assembly for an interior panel in a vehicle |
| CN105538325A (en) * | 2015-12-30 | 2016-05-04 | 哈尔滨理工大学 | Decoupling control method of single leg joint of hydraulic four-leg robot |
| CN107344528A (en) * | 2016-05-06 | 2017-11-14 | 杨新宇 | Car-mounted device, motor vehicles and the method for installing car-mounted device |
| CN105783896A (en) * | 2016-05-17 | 2016-07-20 | 吉林大学 | Interactive type unmanned aerial vehicle magnetic compass calibration device and method |
| CN106314303A (en) * | 2016-08-31 | 2017-01-11 | 法乐第(北京)网络科技有限公司 | Center control screen assembly and vehicle |
| CN106990410A (en) * | 2017-03-08 | 2017-07-28 | 中国汽车技术研究中心 | A kind of vehicle external dimensions device for fast detecting and method |
| CN207056860U (en) * | 2017-04-17 | 2018-03-02 | 姚汉奇 | A kind of path optimization atomizing spraying system of view-based access control model identification technology |
| CN106938764A (en) * | 2017-04-28 | 2017-07-11 | 浙江硕和机器人科技有限公司 | A kind of guide plate reciprocating conveying mechanism |
| CN107176098A (en) * | 2017-07-10 | 2017-09-19 | 辽宁工业大学 | A kind of poor automatic monitoring warning device in blind area of lubrication groove and control method |
| CN107579699A (en) * | 2017-09-12 | 2018-01-12 | 安徽亦知企业管理有限公司 | A kind of solar energy photovoltaic generator and its adjusting method based on BP neural network regulation angle |
| CN208376662U (en) * | 2018-07-13 | 2019-01-15 | 吉林大学 | A kind of adaptive console based on body state detection |
Non-Patent Citations (1)
| Title |
|---|
| 陈俊豪，任金东，刘涛，华猛，刘洪浩.《汽车工程》，基于H 点装置仿真的压力分布与座椅 参数测量和舒适性评价的研究.2017,第39卷(第5期),593-605. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109017602A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109017602B (en) | Self-adaptive center console based on human body gesture recognition and control method thereof | |
| CN108657029B (en) | Intelligent automobile driver seat adjusting system and method based on limb length prediction | |
| CN106994915B (en) | Driving seat self-adaptive adjusting device based on body characteristics of driver | |
| US20210154430A1 (en) | Systems and methods for predicting and preventing motion sickness | |
| CN109263654B (en) | Self-adaptive speed regulation system and speed regulation method for automobile speed passing belt | |
| CN107599783A (en) | A kind of environment inside car management system and its control method | |
| JP2020513372A (en) | Device and method for automatically adjusting driver seating posture | |
| CN108357595B (en) | Model-based self-balancing unmanned bicycle and model driving control method thereof | |
| CN110155168B (en) | Vehicle intelligent steering adjusting method and system based on driver motion sensing | |
| CN110843613B (en) | Seat automatic adjusting method based on human factors engineering | |
| EP4112372A1 (en) | Method and system for driver posture monitoring | |
| US20220242417A1 (en) | Operational Assistance Method for a Vehicle, Control Unit, and Vehicle | |
| CN101511637A (en) | Head rest adjusting device and method | |
| CN111267681A (en) | Shared automobile intelligent seat adjusting method based on ergonomics | |
| CN111530021B (en) | Virtual holder equipment and intelligent behavior sensing method | |
| CN111717147A (en) | Automatic adjusting system and method for vehicle seat | |
| CN206534797U (en) | A kind of multi-functional regulation wheelchair | |
| JP2020029210A (en) | Driving control adjustment device and driving control adjustment method | |
| CN108515936B (en) | Self-adaptive safety airbag based on posture of rider and control method thereof | |
| WO2023020139A1 (en) | Method and apparatus for controlling brake manipulator, device, medium and program product | |
| CN110466470B (en) | Safety airbag control device and control method | |
| JP2020075570A (en) | Vehicle control device | |
| CN108298011A (en) | A kind of unmanned bicycle of self-balancing based on model and its control method of data acquisition driving | |
| CN113044045A (en) | Self-adaptive adjustment method for seats in intelligent cockpit | |
| CN113244062A (en) | Attitude control method and device based on dual-gyroscope intelligent wheelchair |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |