Object picking system and method based on ultrasonic recognition

Abstract

The present application provides an object picking system based on ultrasonic recognition and a method thereof. The object picking system acquires pressure on the object through a pressure sensing module. The object contact side of the picking device is close to the object. The ultrasonic sensing module senses ultrasonic data of the object. The ultrasonic data is used to determine the recognition result and to adjust the picking force of the picked object.

Description

TECHNICAL FIELD

[0001] The present application provides an object picking system and method thereof, which is related to object picking, and in particular, to an object picking system based on ultrasonic recognition. BACKGROUND

[0002] In an automated production line, an object picking system such as a robot arm is often used to pick up objects and move them to a designated location. However, during the object picking process, if the picking force is too small, the object may fall during the moving process; if the picking force is too large, it may cause the object to deform or be damaged. Therefore, the object picking system must use the most suitable picking force for the current object to perform the picking action.

[0003] However, different materials of different objects usually require different levels of picking force, which means that no picking force can be suitable for all objects. The aforementioned material refers to the ability of the material or structure of the object to resist deformation. In existing object picking systems, the operator must manually determine the material of the object and manually set the appropriate picking force based on experience.

[0004] However, the above method not only cannot achieve unmanned picking, but also can only pick objects of the same material, and cannot achieve automatic picking of mixed objects. In addition, the ultrasonic device can detect the characteristics of the object through the reflected wave of the object. However, when there is a gap between the ultrasonic device and the object, the aforementioned reflected wave passing through different media (air and object) will have a large error, resulting in detection failure or incorrect detection results. SUMMARY

[0005] The main purpose of the present application is to provide an object picking system and method thereof, which can closely adhere to the object and dynamically adjust the picking force.

[0006] In one embodiment, an object picking system based on ultrasonic recognition includes a picking device, a pressure sensing module, an ultrasonic sensing module, and a control device electrically connected to the picking device, the pressure sensing module, and the ultrasonic sensing module. The picking device is controlled to contact an object with a contact force and to pick up the object with a picking force. The pressure sensing module is arranged on an object contact side of the picking device and is used to sense a pressure sensing value. The ultrasonic sensing module is arranged on the object contact side and is used to sense an ultrasonic data of the object. The control device is configured to adjust the contact force so that the pressure sensing value is higher than a lower limit of a contact pressure or lower than an upper limit of the contact pressure, so that the object contact side closely adheres to the object, to determine an identification result of the object based on the ultrasonic data, and to adjust the picking force based on the identification result.

[0007] In one embodiment, an object picking method based on ultrasonic recognition is applied to a picking device. The object contact side of the picking device is provided with a pressure sensing module and an ultrasonic sensing module. The method comprises: a) adjusting the contact force of the picking device on an object so that the pressure sensing value of the pressure sensing module is higher than a lower limit of contact pressure or lower than an upper limit of contact pressure, so that the object contact side is tightly attached to the object; b) obtaining an ultrasonic data of the object through the ultrasonic sensing module; c) determining a recognition result of the object based on the ultrasonic data; and d) adjusting the picking force of the picking device based on the recognition result to pick the object.

[0008] The present application can perform ultrasonic sensing closely to the object, thereby improving the reliability of the ultrasonic data. The present application can also dynamically adjust the picking force based on the recognition result, thereby avoiding the object from falling due to too small force or the object from being damaged due to too large force. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 The architecture diagram of the object picking system of one embodiment of the present application;

[0010] Figure 2 The architecture diagram of the object picking system of one embodiment of the present application;

[0011] Figure 3 The architecture diagram of the control device of one embodiment of the present application;

[0012] Figure 4 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0013] Figure 5 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0014] Figure 6 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0015] Figure 7 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0016] Figure 8 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0017] Figure 9 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0018] Figure 10 The schematic diagram of the integrated sensor of one embodiment of the present application;

[0019] Figure 11 The schematic diagram of the attenuation structure of one embodiment of the present application;

[0020] Figure 12Fig. 1 is a schematic diagram of picking up an object according to an embodiment of the present application;

[0021] Figure 13 Fig. 2 is a schematic diagram of picking up an object according to an embodiment of the present application;

[0022] Figure 14 Fig. 3 is a schematic diagram of picking up an object according to an embodiment of the present application;

[0023] Figure 15 Fig. 4 is a schematic diagram of ultrasonic data according to an embodiment of the present application;

[0024] Figure 16 Fig. 5 is a schematic diagram of waveform of ultrasonic data according to an embodiment of the present application;

[0025] Figure 17 Fig. 6 is a schematic diagram of waveform of ultrasonic data according to an embodiment of the present application;

[0026] Figure 18 Fig. 7 is a schematic diagram of waveform of ultrasonic data according to an embodiment of the present application;

[0027] Figure 19 Fig. 8 is a schematic diagram of rigidity detection according to an embodiment of the present application;

[0028] Figure 20 Fig. 9 is a schematic diagram of picking up pressure range according to an embodiment of the present application;

[0029] Figure 21 Fig. 10 is a flowchart of object picking up method according to an embodiment of the present application;

[0030] Figure 22 Fig. 11 is a flowchart of object picking up method according to an embodiment of the present application;

[0031] Figure 23 Fig. 12 is a flowchart of ultrasonic recognition according to an embodiment of the present application;

[0032] Figure 24 Fig. 13 is a flowchart of rigidity detection according to an embodiment of the present application.

[0033] BRIEF DESCRIPTION OF DRAWINGS

[0034] 10: control device

[0035] 100: object recognition module

[0036] 101: force calculation module

[0037] 11: picking up device

[0038] 12: pressure sensing module

[0039] 13: ultrasonic sensing module

[0040] 130: ultrasonic transmitter

[0041] 131: ultrasonic receiver

[0042] 14: storage device

[0043] 140: lookup table

[0044] 141: machine learning model

[0045] 142: computer program

[0046] 15: tool device

[0047] 20: network

[0048] 21: remote host

[0049] 300: object

[0050] 310, 320, 330: ultrasonic transmitter

[0051] 311, 321, 331: ultrasonic receiver

[0052] 312, 322, 332: pressure sensing module

[0053] 313, 323, 333: housing

[0054] 401: first electrically non-conductive layer

[0055] 402: ultrasonic transmitter

[0056] 403: first pressure sensing layer

[0057] 404: first sound absorbing layer

[0058] 405: second electrically non-conductive layer

[0059] 406: ultrasonic receiver

[0060] 407: second pressure sensing layer

[0061] 408: second sound absorbing layer

[0062] 409, 410, 411: housing

[0063] 4090, 4100, 4110, 412: attenuation structure

[0064] 500, 504, 508: picking device

[0065] 501: jaw

[0066] 509, 510: finger

[0067] 502, 506, 511, 512: integrated sensor

[0068] 503, 507, 513: object

[0069] 505: suction cup

[0070] 600: pickup device

[0071] 601, 602: finger

[0072] 603: integrated sensor

[0073] 604: object

[0074] 70, 72: lower limit

[0075] 71, 73: upper limit

[0076] TX signal: transmission wave

[0077] RX signal: reception wave

[0078] t1: wave propagation time

[0079] R1, R2: pressure range

[0080] W1-W12: ultrasonic wave

[0081] d1-d2: distance

[0082] d3-d4: stroke

[0083] S10-S14: first pickup step

[0084] S20-S26: second pickup step

[0085] S30-S38: ultrasonic wave recognition step

[0086] S40-S43: rigidity detection step DETAILED DESCRIPTION

[0087] A preferred embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0088] The present application proposes an object pickup system based on ultrasonic wave recognition and an object pickup method based on ultrasonic wave recognition. The present application is provided with a pressure sensing module and an ultrasonic wave sensing module on the object contact side of a pickup device.

[0089] The sensing result (pressure sensing value) of the pressure sensing module is a pressure value applied to the object by the pickup device, and can be used as a contact force or a pickup force.

[0090] The sensing result (ultrasonic data) of the ultrasonic sensing module corresponds to the physical characteristics (e.g. material, thickness, density, structure, etc.) of the object.

[0091] The present application can determine whether the object contact side is in close contact with the object (i.e. determine whether there is a gap between the picking device and the object) by the pressure sensing value, and further obtain accurate ultrasonic data.

[0092] The present application can also determine the appropriate picking force for the object based on the ultrasonic recognition result of the ultrasonic data, and output the appropriate picking force for the object through the feedback of the pressure sensing value.

[0093] Please refer to Figure 1 , the architecture diagram of the object picking system of an embodiment of the present application.

[0094] The object picking system of the present embodiment mainly includes a picking device 11, a pressure sensing module 12, an ultrasonic sensing module 13, and a control device 10 electrically connected to the above-mentioned devices.

[0095] The picking device 11 is used to pick the target object. In an embodiment, the picking device 11 can include a mobile machine and an end effector disposed at the end of the mobile machine.

[0096] The aforementioned mobile machine is used to move the end effector to a specified position (e.g. the position of the target object) in space. The aforementioned end effector is used to pick the object from the specified position.

[0097] In an embodiment, the aforementioned mobile machine can be a robotic arm with one or more degrees of freedom, or a moving stage that can move the end effector in one or more dimensions.

[0098] In an embodiment, the aforementioned end effector can be a gripper with multiple fingers, a suction nozzle, a suction disc, etc.

[0099] The pressure sensing module 12 is used to sense pressure and obtain a pressure sensing value. The pressure sensing module 12 can be disposed at the object contact side of the picking device 11. In this way, when the picking device 11 contacts or picks the object, the reaction force of the object will trigger the corresponding pressure sensing value of the pressure sensing module 12.

[0100] In an embodiment, the pressure sensing module 12 can be a piezoresistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, or a thin film pressure sensor, but is not limited thereto.

[0101] The ultrasonic sensing module 13 is configured to sense ultrasonic data of the object. The ultrasonic sensing module 13 can be disposed on the object-contacting side of the pickup device 11. In this way, when the pickup device 11 contacts or picks up the object, the ultrasonic sensing module 13 can emit ultrasonic waves toward the object and can receive ultrasonic waves (reflected waves) passing through the object to generate ultrasonic data.

[0102] It is worth mentioning that when ultrasonic waves propagate in objects with different physical characteristics, different sound speeds and attenuation amplitudes are generated. The present application can identify the material of the object by analyzing the above changes.

[0103] The control device 10 is configured to control the object pickup system.

[0104] Specifically, in the ultrasonic identification phase, the control device 10 can be configured to control the pickup device 11 to contact the object with a small force to make the object-contacting side where the ultrasonic sensing module 13 is located tightly contact the object (for example, there is no gap between the object-contacting side and the object), obtain the ultrasonic data of the object through the ultrasonic sensing module 13, obtain the identification result of the object based on the ultrasonic data, and set the pickup force based on the identification result.

[0105] In the pickup phase, the control device 10 can be configured to control the pickup device 11 to continuously adjust the pressure for picking up the object so that the pressure sensing value meets the pickup force, and control the pickup device to pick up the object with the pickup force.

[0106] In an embodiment, the control device 10 can be a computer system such as an industrial computer, a personal computer, a notebook computer, a tablet computer, or a processor such as a CPU, an FPGA, a microcontroller, a SoC, a DSP, a TPU, an NPU, etc.

[0107] The object pickup system of the present application can dynamically adjust the pickup force according to the material of the object, and will not cause the object to fall off or be damaged (for example, cause indentation) due to the pickup force being too large or too small.

[0108] Please refer to Figure 2 The figure is a block diagram of an object pickup system according to an embodiment of the present application. In an embodiment, the ultrasonic sensing module 13 can include an ultrasonic transmitter 130 configured to emit ultrasonic waves and an ultrasonic receiver 131 configured to receive ultrasonic waves. The ultrasonic transmitter 130 and the ultrasonic receiver 131 are electrically connected to the control device 10.

[0109] In an embodiment, the object pickup system can include a storage device 14 electrically connected to the control device 10. The storage device 14 is configured to store data, and the aforementioned data can include a plurality of preset speeds, a plurality of preset waveforms, a plurality of predicted spectra, a lookup table 140, a machine model 141, and a computer program 142, etc.

[0110] In one embodiment, the object picking system can include a tool device 15 electrically connected to the control device 10. The tool device 15 is used to work with the picking device 11.

[0111] For example, the tool device 15 can include a transportation device, such as a transportation table, a transportation cart, a conveyor belt, or the like, for transporting objects. The picking device 11 can pick up objects carried by the transportation device, or place picked-up objects on the transportation device.

[0112] In another example, the tool device 15 can include a processing device, such as a glue dispenser, a laser welder, a paint baking machine, or the like. The picking device 11 can pick up objects to a designated processing position, and the processing device can process the objects, such as gluing, welding, or paint baking.

[0113] In one embodiment, the control device 10 can include a network interface (not shown, such as a network interface card, a wireless network card, an Ethernet card, or the like). The control device 10 can connect to a network 20 (such as a local area network or an Internet network) through the network interface, and communicate with a remote host 21 remotely through the network 20.

[0114] For example, the remote host 21 can include a network database. The control device 10 can download the latest version of the lookup table 140 from the network database.

[0115] In another example, the remote host 21 can include a cloud AI platform, and the control device 10 can download the latest version of the machine learning model 141 from the cloud AI platform.

[0116] In another example, the remote host 21 can include an update server, and the control device 10 can download the latest version of the computer program 142 from the update server.

[0117] In another example, the remote host 21 can include a management host of an automated production line, and the control device 10 can receive control commands for the object picking system from the management host and execute, and also transmit the status of the object picking system to the management host.

[0118] Please refer to Figure 3 , a block diagram of a control device according to an embodiment of the present application. The control device 10 can include an object recognition module 100 and a force calculation module 101.

[0119] The object recognition module 100 is used to recognize objects based on ultrasonic data of the objects to obtain a recognition result. The aforementioned recognition result includes physical characteristics of the objects, such as material, thickness, density, structure, or the like.

[0120] The force calculation module 101 is used to adjust the picking force based on the recognition result.

[0121] In one embodiment, the force calculation module 101 can also perform rigidity detection on the object to obtain the rigidity of the object, and adjust the picking force based on the rigidity.

[0122] It is worth mentioning that the object recognition module 100 and the force calculation module 101 can be connected to each other (which can be electrical connection or information connection), and can be hardware modules (such as electronic circuit modules, integrated circuit modules, SoC, etc.), software modules or software and hardware module mix, without limitation.

[0123] When the object recognition module 100 or the force calculation module 101 is a software module (such as a solid, an operating system or an application), the storage device 14 can include a non-transitory computer readable recording medium, and the non-transitory computer readable recording medium stores a computer program 142, and the computer program 142 records computer executable program codes, and when the control device 10 executes the program codes, the functions of the object recognition module 100 and the force calculation module 101 can be realized.

[0124] Please refer to Figures 4 to 10 , Figure 4 The integrated sensor of one embodiment of the present application, Figure 5 The integrated sensor of one embodiment of the present application, Figure 6 The integrated sensor of one embodiment of the present application, Figure 7 The integrated sensor of one embodiment of the present application, Figure 8 The integrated sensor of one embodiment of the present application, Figure 9 The integrated sensor of one embodiment of the present application, Figure 10 The integrated sensor of one embodiment of the present application.

[0125] Figures 4 to 10 In the embodiment, the pressure sensing module and the ultrasonic sensing module are integrated into a single integrated sensor, that is, arranged in the same housing. Moreover, in the integrated sensor, the distance between the ultrasonic transmitter and the ultrasonic receiver is fixed, and the same ultrasonic parameters can be used.

[0126] In other words, when the integrated sensor is arranged on the object contact side of the picking device 11, the ultrasonic transmitter and the ultrasonic receiver in the integrated sensor can maintain a fixed distance regardless of the change of the posture of the picking device 11.

[0127] In addition, the user only needs to arrange the integrated sensor on the picking device, and all sensor installations can be completed in one action.

[0128] In the embodiment of Figures 4 to 10 In the embodiment, the integrated sensor includes a pressure sensing module, an ultrasonic transmitter, an ultrasonic receiver, and a housing covering the above elements.

[0129] At Figure 4 In one embodiment, the ultrasonic transmitter 310, the pressure sensing module 312, and the ultrasonic receiver 311 are arranged horizontally and sequentially on the object contact side.

[0130] When the integrated sensor comes into contact with object 300, the pressure sensing module 312 senses the pressure value caused by the object 300 squeezing.

[0131] Furthermore, the ultrasonic transmitter 310 emits ultrasonic waves W1 toward the object, and the ultrasonic receiver 311 receives the ultrasonic waves W1 that pass through the object 300.

[0132] At Figure 5 In one embodiment, the ultrasonic transmitter 320 and the ultrasonic receiver 321 are disposed on the object contact side.

[0133] The pressure sensing module 322 is stacked on top of the ultrasonic transmitter 320 and the ultrasonic receiver 321. The pressure caused by the object 300 pressing against the sensor is transmitted to the pressure sensing module 322 through the ultrasonic transmitter 320 and the ultrasonic receiver 321. This arrangement reduces the size of the integrated sensor.

[0134] However, Figure 4 and Figure 5 In the housing design, the spillover waves (ultrasounds W2 and W4) from the ultrasonic transmitters 310 and 320 may propagate to the ultrasonic receivers 311 and 321 through the housings 313 and 323.

[0135] Since these spillover waves do not pass through object 300, they cannot reflect the physical characteristics of object 300 and will become noise in the ultrasound data, causing errors in the recognition results.

[0136] To solve the above problems, Figures 6 to 10 An attenuation structure is formed on the casing. The attenuation structure is used to attenuate the ultrasound waves propagating from the ultrasound transmitter along the inside of the casing toward the ultrasound receiver, in order to reduce or eliminate the aforementioned noise.

[0137] Please see Figure 6 The housing 333 integrating the sensor is M-shaped (attenuation structure), and the ultrasonic transmitter 330, pressure sensing module 332 and ultrasonic receiver 331 are sequentially arranged at the three ends (object contact side) of the housing 333.

[0138] The ultrasonic waves W5 emitted by the ultrasonic transmitter 330 can pass through objects and reach the ultrasonic receiver 331.

[0139] And, since the attenuation structure greatly reduces the volume of the channel, most of the ultrasonic waves W6 (overflow) emitted by the ultrasonic transmitter 330 will be blocked or attenuated, only a small amount of ultrasonic waves W6 will propagate to the ultrasonic receiver 331, so that the noise caused by the overflow is greatly reduced.

[0140] Please refer to Figure 7 , the shell 343 of the integrated sensor is inverted U-shaped (attenuation structure), and the ultrasonic transmitter 340 and the ultrasonic receiver 341 are arranged at the two ends (object contact side) of the shell 343 in sequence. The pressure sensing module 342 is stacked on the ultrasonic transmitter 340 and the ultrasonic receiver 341.

[0141] The ultrasonic waves W7 emitted by the ultrasonic transmitter 340 can pass through the object to reach the ultrasonic receiver 341.

[0142] And, since the attenuation structure greatly reduces the volume of the channel, most of the ultrasonic waves W6 (overflow) emitted by the ultrasonic transmitter 330 will be blocked or attenuated, only a small amount of ultrasonic waves W6 will propagate to the ultrasonic receiver 331, so that the noise caused by the overflow is greatly reduced.

[0143] In an embodiment, the aforementioned shell of the integrated sensor or the attenuation structure can contain sound-absorbing materials, such as sound-absorbing cotton or sound-absorbing boards, etc. The aforementioned sound-absorbing materials can absorb ultrasonic waves propagating inside the shell.

[0144] In Figures 8 to 10 embodiment, the pressure sensing module, the ultrasonic transmitter and the ultrasonic receiver are multi-layer thin film sensors and are stacked with each other. The pressure sensing module contains two groups of pressure sensing layers.

[0145] And, the integrated sensor also contains two groups of non-conductive layers and two groups of sound-absorbing layers. The non-conductive layers are used to isolate the integrated sensor from the object, avoiding the electronic interference of the surface of the object to the pressure sensing or ultrasonic sensing. The sound-absorbing layers are used to absorb the overflow of the ultrasonic transmitter, so as to reduce the overflow energy received by the ultrasonic receiver.

[0146] In Figures 8 to 10 embodiment, the left end of the integrated sensor is arranged in the following order from the object contact side contacting the object 400 to the inside (from the outside to the inside): the first non-conductive layer 401, the ultrasonic transmitter 402, the first pressure sensing layer 403 and the first sound-absorbing layer 404.

[0147] And, the right end of the integrated sensor is arranged in the following order from the object contact side contacting the object 400 to the inside (from the outside to the inside): the second non-conductive layer 405, the ultrasonic receiver 406, the second pressure sensing layer 407 and the second sound-absorbing layer 408.

[0148] In one embodiment, the housing or the attenuation structure of the integrated sensor can comprise a range-expanding structure having a length greater than the straight-line distance between the ultrasonic transmitter and the ultrasonic receiver. The range-expanding structure can increase the propagation length of the spurious waves, and effectively attenuate the spurious waves.

[0149] Referring to Figure 8 The attenuation structure 4090 of the housing 409 of the integrated sensor is a square-shaped range-expanding structure, which can greatly increase the propagation length of the spurious waves, and thus greatly reduce the spurious wave energy received by the ultrasonic receiver.

[0150] Referring to Figure 9 The attenuation structure 4100 of the housing 410 of the integrated sensor is a continuous triangular-shaped range-expanding structure, which can greatly increase the propagation length of the spurious waves, and thus greatly reduce the spurious wave energy received by the ultrasonic receiver.

[0151] In one embodiment, the housing or the attenuation structure of the integrated sensor can comprise a partially-excavated reduction structure. The reduction structure can greatly reduce the spurious wave energy reaching the ultrasonic receiver by reducing the volume of the housing through which the spurious waves can propagate.

[0152] Referring to Figure 10 The attenuation structure 4110 of the housing 411 of the integrated sensor comprises a reduction structure. The reduction structure can greatly reduce the spurious wave energy reaching the ultrasonic receiver by excavating most of the middle region of the housing, leaving only a narrow bridge connecting the left and right ends of the housing 411.

[0153] Referring to Figure 11 A schematic diagram of an attenuation structure according to an embodiment of the present application. Figure 11 A reduction structure is shown, in which a plurality of holes are formed in the housing to further reduce the volume of the housing through which the spurious waves can propagate. Figure 11 The reduction structure shown can be used in Figures 8 to 10 Any of the integrated sensors shown.

[0154] Referring to Figures 12 to 14 , Figure 12 A schematic diagram of a picked-up object according to an embodiment of the present application, Figure 13 A schematic diagram of a picked-up object according to an embodiment of the present application, Figure 14 A schematic diagram of a picked-up object according to an embodiment of the present application.

[0155] Figure 12 In the embodiment of FIG. 5, the picking device 500 comprises two-fingered grippers 501.

[0156] The integrated sensor 502 is disposed on the object-contacting side of one finger of the gripper 501. Thus, when the gripper 501 grips the object 503, the integrated sensor 502 can sense the gripping force (pressure sensing value), and then obtains the ultrasonic data of the object 503 by transmitting and receiving the ultrasonic wave W9.

[0157] Figure 13 In an embodiment of the present application, the pickup device 504 comprises a suction nozzle 505, which can suck the object 507 by creating a vacuum between the suction nozzle 505 and the object 507.

[0158] The integrated sensor 505 is disposed on the object-contacting side of the suction nozzle 505. Thus, when the suction nozzle 505 sucks the object 507, the integrated sensor 505 can sense the sucking force (pressure sensing value), and then obtains the ultrasonic data of the object 507 by transmitting and receiving the ultrasonic wave W10.

[0159] Figure 14 In an embodiment of the present application, the pickup device 508 comprises a multi-finger gripper, which has at least a first finger portion 509 and a second finger portion 510.

[0160] The integrated sensor 511 is disposed on the object-contacting side of the first finger portion 509, and the integrated sensor 512 is disposed on the object-contacting side of the second finger portion 510.

[0161] Thus, when the multi-finger gripper grips the object 513, the integrated sensors 511, 512 can sense the gripping force (pressure sensing value).

[0162] After the first finger portion 509 and the second finger portion 510 both contact the object 513, the integrated sensor 511 can transmit the ultrasonic wave W12, so that the integrated sensor 512 receives the ultrasonic wave W12 passing through the object 513 to obtain the ultrasonic data of the object 503.

[0163] In addition, the integrated sensor 512 can transmit another ultrasonic wave W11, so that the integrated sensor 511 receives the ultrasonic wave W11 passing through the object 513 to obtain another ultrasonic data of the object 503.

[0164] The present embodiment can perform more accurate ultrasonic recognition by analyzing multiple ultrasonic data passing through the object 513.

[0165] Next, the object pickup method of the present application is described. The object pickup method of each embodiment of the present application can be applied to the object pickup system of any of the above embodiments. In the following, the object pickup method of each embodiment is exemplarily described with reference to the object pickup system of the present application. Figure 2

[0166] ​And, the pressure sensing module and the ultrasonic sensing module of the object picking method of each embodiment of the present application can be separately arranged or integrated into the aforementioned integrated sensor.

[0167] Please refer to Figure 21 is a flowchart of the object picking method of an embodiment of the present application. The object picking method of the present embodiment comprises the following steps.

[0168] Step S10: The control device 10 controls the picking device 11 to tightly contact the object.

[0169] In an embodiment, the control device 10 can first read a set of preset contact pressures from the storage device 14, and adjust the contact force of the picking device 11 to contact the object, so that the measured pressure sensing value meets the preset contact pressure.

[0170] In an embodiment, the aforementioned preset contact pressure can be a value obtained by experiment. When the picking device 11 contacts the object with a contact force meeting the preset contact pressure, the object contact side of the picking device 11 can tightly contact the surface of the object, and the object will not be damaged due to excessive pressure.

[0171] In an embodiment, the aforementioned preset contact pressure is less than the minimum picking force required to pick up the object, i.e. picking up the object with the aforementioned preset contact pressure can cause the object to fall off.

[0172] In an embodiment, the control device 10 can adjust the contact force by adjusting the stroke of the gripper or the suction force of the suction nozzle of the picking device 11, so that the pressure sensing value is maintained in the preset contact pressure range.

[0173] The aforementioned contact pressure range can include a lower limit of contact pressure and an upper limit of contact pressure. The control device 10 adjusts the contact force so that the pressure sensing value is higher than the lower limit of contact pressure and / or lower than the upper limit of contact pressure.

[0174] Step S11: After the object contact side tightly contacts the object, the control device 10 performs ultrasonic sensing on the object through the ultrasonic sensing module 11 to obtain ultrasonic data of the contacted object.

[0175] In an embodiment, the aforementioned ultrasonic data can be a voltage-time graph of the received ultrasonic wave.

[0176] Step S12: The control device 10 determines the identification result of the object based on the ultrasonic data through the object identification module 100.

[0177] In an embodiment, the identification result can include the material, thickness, density, structure and / or other physical characteristics of the object. The control device 10 can analyze the characteristics (such as speed, waveform, frequency spectrum, etc.) of the ultrasonic data to determine the physical characteristics.

[0178] Step S13: The control device 10 adjusts the picking force of the picking device 11 based on the recognition result via the force calculation module 101.

[0179] In an embodiment, the storage device 14 stores different preset picking pressures corresponding to different preset recognition results respectively.

[0180] The control device 10 can read the preset picking pressure corresponding to the current recognition result, and adjust the picking force (e.g. the stroke distance of the gripper or the suction strength of the suction nozzle) of the picking device 11 to make the pressure sensing value of the pressure sensing module 12 conform to the preset picking pressure.

[0181] In an embodiment, the aforementioned preset picking pressure is a picking pressure range composed of a picking pressure lower limit and a picking pressure upper limit.

[0182] The control device 10 can adjust the picking force of the picking device 11 to maintain the pressure sensing value of the pressure sensing module 12 between the aforementioned picking pressure lower limit and the aforementioned picking pressure upper limit.

[0183] In an embodiment, the aforementioned contact pressure lower limit is less than the aforementioned picking pressure lower limit. The aforementioned contact pressure upper limit is less than the aforementioned picking pressure upper limit.

[0184] The present application can closely adhere to the object to perform ultrasonic sensing, thereby improving the reliability of the ultrasonic data. The present application can also dynamically adjust the picking force based on the recognition result, thereby avoiding the object from falling due to too small force or the object from being damaged due to too large force.

[0185] Please refer to Figure 22 for the flowchart of the object picking method of an embodiment of the present application.

[0186] Step S20: The control device 10 controls the picking device 11 to closely adhere to the object.

[0187] Step S21: The control device 10 controls the ultrasonic transmitter 130 to emit ultrasonic waves.

[0188] Step S22: The control device 10 controls the ultrasonic receiver 131 to sense the reflected ultrasonic waves (e.g. ultrasonic waves propagating through the object) to generate ultrasonic data.

[0189] Step S23: The control device 10 determines the recognition result of the object based on the ultrasonic data via the object recognition module 100.

[0190] In an embodiment, the recognition result includes the material of the object. The control device 10 can analyze the ultrasonic features (e.g. sensing speed, sensing waveform, ultrasonic spectrum, etc.) of the ultrasonic data, and determine the material of the object based on the ultrasonic features.

[0191] Step S24: The control device 10 sets the material of the object based on the recognition result.

[0192] For example, when the material of the object is identified as metal, the material of the object can be recorded in the digital data corresponding to the object, so that the object can be subjected to a process related to metal in subsequent processing, such as moving the object to a sorting vehicle for metal, heating at a higher metal melting point, etc.

[0193] In another example, when the material of the object is identified as glass, the material of the object can be recorded in the digital data corresponding to the object, so that the object can be subjected to a process related to glass in subsequent processing, such as moving the object to a sorting vehicle for glass, adding protection during transportation, etc.

[0194] Step S25: The control device 10 adjusts the picking force of the picking device 11 based on the recognition result through the force calculation module 101 to pick up the object.

[0195] Step S26: The control device 10 controls the picking device 11 to move the object to a designated position with the adjusted picking force.

[0196] In an embodiment, different materials correspond to different designated positions (such as the positions of different sorting vehicles for different materials). The control device 10 can obtain the designated position of the corresponding sorting vehicle based on the recognition result of the object, and move the object to the designated position.

[0197] The present application can effectively identify the material of the object and pick up the object with the most suitable force.

[0198] Please refer to Figure 23 The flowchart of ultrasonic recognition of an embodiment of the present application. Four ultrasonic recognition methods are provided in this embodiment, which are ultrasonic recognition based on sound velocity (steps S30-S31), ultrasonic recognition based on waveform (steps S33-S34), ultrasonic recognition based on frequency spectrum (steps S35-S37), and ultrasonic recognition based on machine learning (step S38).

[0199] The ultrasonic recognition based on sound velocity includes the following steps:

[0200] Step S30: The control device 10 obtains a plurality of preset velocities of a plurality of preset materials.

[0201] In an embodiment, the storage device 14 can store the aforementioned plurality of preset velocities. The aforementioned plurality of preset velocities can be obtained through experiments in advance and correspond to different materials respectively.

[0202] Step S31: The control device 10 compares the sensed velocity with the plurality of preset velocities to determine the material.

[0203] Specifically, the control device 10 can analyze the ultrasonic data to determine a corresponding sensing speed, which is a speed slower than the plurality of preset speeds, and select a preset material corresponding to the preset speed matching the sensing speed as the material of the recognition result.

[0204] In an embodiment, the storage device 14 can store a lookup table 140. The lookup table 140 records a speed-material correspondence between a plurality of preset speeds and a plurality of preset materials. The control device 10 can read the lookup table 140 from the storage device 14 to obtain the plurality of preset speeds, and obtain the preset material matching the speed as the material of the object.

[0205] Referring to Figure 15 is a schematic diagram of ultrasonic data of an embodiment of the present application. Figure 15 The voltage-time diagram shown illustrates two signals, a transmission wave TX signal transmitted by the ultrasonic transmitter 130 and a reception wave RX signal received by the ultrasonic receiver 131.

[0206] Figure 15 In this embodiment, the setting distance between the ultrasonic transmitter 130 and the ultrasonic receiver 131 is fixed. The wave propagation time tl of the ultrasonic wave in the object is measured, for example, as a time difference between the transmission time of the transmission wave TX signal and the reception time of the reception wave RX signal.

[0207] Therefore, the speed of the ultrasonic wave in the object (i.e., the aforementioned sensing speed) can be calculated based on the setting distance and the wave propagation time tl.

[0208] Since the ultrasonic wave has different propagation speeds in different materials, the material of the object can be determined by comparing the sensing speed with the propagation speeds of different materials.

[0209] For example, the propagation speed of metal is 3500-7000 m / s, the propagation speed of glass is 1050-1300 m / s, the propagation speed of plastic is 600-950 m / s, and the propagation speed of rubber is 0-100 m / s.

[0210] When the sensing speed is 4000 m / s, it can be determined that the object is a metal with strong material. When the sensing speed is 650 m / s, it can be determined that the object is a plastic with poor material, and so on.

[0211] The present application can effectively identify the material of the object by analyzing the received ultrasonic speed (sensing speed).

[0212] Referring again to Figure 23 , the ultrasonic recognition based on waveforms includes the following steps.

[0213] Step S33: The control device 10 acquires multiple preset waveforms of multiple preset materials.

[0214] In one embodiment, the storage device 14 can store the aforementioned multiple preset waveforms. The aforementioned multiple preset waveforms can be obtained in advance through experiments and correspond to different materials respectively.

[0215] Step S34: The control device 10 compares the sensed waveform with multiple preset waveforms to determine the material.

[0216] Specifically, the control device 10 can analyze ultrasound data to determine the corresponding sensing waveform, compare the sensing waveform with the aforementioned multiple preset waveforms, and select the preset material corresponding to the preset waveform that matches the sensing waveform as the material of the identification result.

[0217] In one embodiment, the storage device 14 may store a lookup table 140. The lookup table 140 records waveform-material correspondences between various preset waveforms and various preset materials. The control device 10 may read the lookup table 140 from the storage device 14 to obtain various preset waveforms and select the preset material whose waveform matches as the material of the object.

[0218] Please see Figures 16 to 18 , Figure 16 This is a waveform diagram of ultrasound data according to an embodiment of the present invention. Figure 17 This is a waveform diagram of ultrasound data according to an embodiment of the present invention. Figure 18 This is a waveform diagram of ultrasound data according to an embodiment of the present invention.

[0219] Figure 16 This is a waveform diagram of ultrasound waves passing through plastic. Figure 17 This is a waveform diagram of ultrasound waves passing through metal. Figure 18 This is a waveform diagram of ultrasound waves passing through glass.

[0220] Depend on Figures 16 to 18 It is known that ultrasound waves passing through different preset materials will have different waveforms (such as periodic changes, frequency changes, and amplitude changes). By comparing the sensed waveform with the preset waveforms of different preset materials, it is possible to determine which preset material the current object's material is closest to.

[0221] In one embodiment, the present invention can perform feature extraction on each preset waveform in advance to obtain waveform feature data of the preset waveform, and use the waveform feature data to compare and sense the waveform. In this way, the amount of computation during comparison can be reduced and the comparison speed can be improved.

[0222] This invention can effectively identify the material of an object by analyzing the received ultrasonic waveform.

[0223] Please see Figure 23The spectrum-based ultrasonic recognition comprises the following steps.

[0224] Step S35: The control device 10 acquires a plurality of preset spectra of a plurality of preset materials.

[0225] In an embodiment, the storage device 14 can store the aforementioned plurality of preset spectra. The aforementioned plurality of preset spectra can be obtained through experiments in advance and correspond to different materials respectively.

[0226] Step S36: The control device 10 performs frequency domain conversion on the ultrasonic data of the object to convert the ultrasonic data of the object from the spatial / time domain to the frequency domain to obtain the ultrasonic spectrum of the object.

[0227] In an embodiment, the aforementioned frequency domain conversion can include frequency domain conversion methods such as Fast Fourier Transform (FFT), Laplace transform, wavelet transform, Z-transform, etc., without limitation.

[0228] Step S37: The control device 10 compares the ultrasonic spectrum with the plurality of preset spectra to determine the material.

[0229] Specifically, the control device 10 can analyze the ultrasonic data to determine the corresponding ultrasonic spectrum, compare the ultrasonic spectrum with the aforementioned plurality of preset spectra, and select the preset material corresponding to the preset spectrum that matches the ultrasonic spectrum as the material of the recognition result.

[0230] In an embodiment, the storage device 14 can store a lookup table 140. The lookup table 140 records the spectrum-material correspondence relationship between the plurality of preset spectra and the plurality of preset materials. The control device 10 can read the lookup table 140 from the storage device 14 to obtain the plurality of preset spectrum waveforms and acquire the preset material that matches the spectrum as the material of the object.

[0231] In an embodiment, the control device 10 can compare the energy values of the ultrasonic spectrum and each preset spectrum at each frequency to determine whether the ultrasonic spectrum and each preset spectrum are close or consistent.

[0232] In an embodiment, the present application can perform feature extraction on each preset spectrum in advance to obtain spectrum feature data of the preset spectrum, and compare the ultrasonic spectrum of the object with the spectrum feature data. In this way, the amount of calculation during comparison can be reduced, and the comparison speed can be improved.

[0233] The present application can effectively recognize the material of the object by analyzing the received ultrasonic spectrum.

[0234] The machine learning-based ultrasonic recognition comprises the following steps.

[0235] Step S38: The control device 10 reads the machine learning model 141 from the storage device 14, and inputs the ultrasonic data of the object to the machine learning model 141 to determine the material of the object as the material of the recognition result.

[0236] In an embodiment, the machine learning model 141 is obtained by training the training ultrasonic data of the training objects of different preset materials in advance.

[0237] In an embodiment, the machine learning model 141 comprises a plurality of classification rules for the ultrasonic data. These classification rules can classify the ultrasonic data according to the characteristics of the ultrasonic data (such as speed characteristics, waveform characteristics, spectral characteristics, etc.), and the ultrasonic data can be classified into one of the plurality of preset materials.

[0238] In an embodiment, the present application can add the parameters of the pressure sensing module 12 and the parameters of the ultrasonic sensing module 13 to train the machine learning model 141, such as pressure sensing sensitivity, pressure sensing value, ultrasonic emission frequency, ultrasonic emission power, ultrasonic receiving sensitivity, etc.

[0239] And the control device 10 inputs the ultrasonic data and the current parameters to the machine learning model 141 to identify the material corresponding to the ultrasonic data.

[0240] The present application can accurately identify the material of the object through machine learning.

[0241] In an embodiment, the present application can determine the material of the object by arbitrarily mixing and matching the above-mentioned plurality of ultrasonic recognition methods.

[0242] Specifically, the control device 10 can perform step S32: determining the final material based on the recognition results of the plurality of ultrasonic recognition methods.

[0243] For example, if the recognition results of the above-mentioned four ultrasonic recognition methods are all metal, or more than half of the recognition results are metal, the final material can be determined as a metal material.

[0244] The present application can improve the recognition accuracy by mixing and matching different ultrasonic recognition methods.

[0245] Please refer to Figure 24 , a flowchart of the rigidity detection of an embodiment of the present application. The present application further proposes a rigidity detection function, which can detect the rigidity (such as hardness) of the object during the picking process, and dynamically adjust the picking force to avoid the object falling due to too small force or the object being damaged due to too large force.

[0246] Compared with Figure 21 orFigure 22 The object picking method of the present embodiment, the picking action (e.g. step S13 or step S25) of the object picking method includes steps S40-S43.

[0247] Step S40: The control device 10 acquires a first picking force.

[0248] In an embodiment, the storage device 14 can store a plurality of preset picking forces, each of which corresponds to a different preset identification result, such as a different predicted material, a different preset thickness, a different preset density, a different preset structure, etc.

[0249] The control device 10 can select the preset picking force that is most consistent with the current identification result as the first picking force.

[0250] In an embodiment, the storage device 14 can store one preset picking force, and the control device 10 selects the same preset picking force as the first picking force regardless of the current identification result.

[0251] Step S41: The control device 10 performs rigidity detection based on the first picking force to obtain the rigidity of the object.

[0252] In an embodiment, the end effector of the picking device 11 can include a gripper.

[0253] The aforementioned rigidity detection can include the following steps: the control device 10 controls the gripper to clamp the same object using a plurality of detection forces to obtain a plurality of pressure sensing values of the object, the plurality of detection forces corresponding to a plurality of strokes of the gripper; and the control device 10 determines the rigidity of the object based on the changes in the plurality of strokes and the changes in the plurality of pressure sensing values.

[0254] Step S42: The control device 10 sets a second picking force based on the rigidity.

[0255] In an embodiment, the aforementioned second picking force can be a picking pressure range including a picking pressure upper limit and a picking pressure lower limit.

[0256] The control device 10 can set a picking pressure lower limit and a picking pressure upper limit with a smaller difference for a softer rigidity, and set a picking pressure lower limit and a picking pressure upper limit with a larger difference for a harder rigidity.

[0257] In an embodiment, the contact pressure lower limit can be smaller than the picking pressure lower limit, and the contact pressure upper limit can be smaller than the picking pressure upper limit.

[0258] Step S43: The control device 10 controls the picking device 11 to pick the object with the second picking force, so that the pressure sensing value of the pressure sensing module 12 is maintained within the aforementioned picking pressure range.

[0259] The present application can identify the rigidity of an object and dynamically adjust the picking force based on the rigidity, thereby avoiding dropping the object due to insufficient picking force or damaging the object due to excessive picking force.

[0260] Referring to Figure 19 and Figure 20 , Figure 19 FIG. 1 is a schematic diagram of rigidity detection according to an embodiment of the present application, Figure 20 FIG. 2 is a schematic diagram of picking pressure range according to an embodiment of the present application.

[0261] In Figure 19 (i) and Figure 19 (ii), the picking device 60 has a finger 601 and a finger 602. The finger 602 is provided with an integrated sensor 603.

[0262] As Figure 19 (i) shows, when the picking device 60 picks up an object 604 with a small force (i.e. assumes a first posture), the distance between the finger 601 and the finger 602 is d1. Moreover, a first pressure sensing value can be obtained by the integrated sensor 603.

[0263] As Figure 19 (ii) shows, when the picking device 60 picks up the object 604 with a large force (i.e. assumes a second posture), the distance between the finger 601 and the finger 602 is shortened to d2 due to deformation of the object 604.

[0264] Moreover, a second pressure sensing value can be obtained by the integrated sensor 603.

[0265] In other words, when the first posture is changed to the second posture, the stroke of the finger 601 changes by d4, and the stroke of the finger 602 changes by d3. The aforementioned stroke changes correspond to the deformation of the object 604. The pressure change is the difference between the first pressure sensing value and the second pressure sensing value.

[0266] Furthermore, the weaker (softer) the rigidity of the object 604, the easier the object 604 deforms, and the stronger (harder) the rigidity of the object 604, the more difficult the object 604 deforms. In other words, under the same stroke change, the greater the pressure change of the object 604 corresponds to the stronger rigidity, and the smaller the pressure change of the object 604 corresponds to the weaker rigidity.

[0267] Therefore, the present application can determine the rigidity of an object through the linkage between the stroke change and the pressure change.

[0268] It is worth mentioning that although only two posture changes are used to detect the rigidity in the present embodiment, the number of posture changes can be arbitrarily changed according to requirements.

[0269] Referring to Figure 20In this embodiment, the control device 10 can determine whether the object is a soft object (weak rigidity) or a hard object (strong rigidity) based on the rigidity.

[0270] When the object is determined to be a hard object (e.g. a harder material such as metal), the control device 10 can set a wider pickup pressure range R1, i.e. the difference between the lower pickup pressure limit 70 and the upper pickup pressure limit 71 is larger.

[0271] When the object is determined to be a soft object (e.g. a softer material such as an apple), the control device 10 can set a narrower pickup pressure range R2, i.e. the difference between the lower pickup pressure limit 72 and the upper pickup pressure limit 73 is smaller.

[0272] It is worth mentioning that a hard object can withstand a higher external pressure (upper pickup pressure limit) than a soft object. In this regard, the present embodiment sets a higher upper pickup pressure limit for a hard object, which allows the pickup device 10 to pick up the hard object with a stronger pickup force, and thus reduces the probability of the hard object falling off.

[0273] In one embodiment, the lower pickup pressure limit 70 for a hard object and the lower pickup pressure limit 72 for a soft object can be the same or different, but the upper pickup pressure limit 71 for a hard object is higher than the lower pickup pressure limit 73 for a soft object.

[0274] The above description is only the preferred embodiments of the present application, and is not intended to limit the scope of the claims of the present application. Therefore, any equivalent changes made in accordance with the content of the present application are also included in the scope of the present application, and are hereby disclosed.

Claims

1. A picking system based on ultrasonic recognition, comprising: a picking device controlled to contact an object with a contact force and to pick up the object with a picking force; a pressure sensing module disposed on an object contact side of the picking device to sense a pressure sensing value; an ultrasonic sensing module disposed on the object contact side to sense ultrasonic data of the object; and a control device electrically connected to the picking device, the pressure sensing module and the ultrasonic sensing module, the control device configured to adjust the contact force to make the pressure sensing value higher than a lower limit of contact pressure or lower than an upper limit of contact pressure, so that the object contact side closely contacts the object, to determine a recognition result of the object based on the ultrasonic data, and to adjust the picking force based on the recognition result; the ultrasonic sensing module comprises an ultrasonic transmitter and an ultrasonic receiver; wherein the picking system further comprises an attenuation structure disposed between the ultrasonic transmitter and the ultrasonic receiver to attenuate the ultrasonic wave propagating from the ultrasonic transmitter to the ultrasonic receiver. 2.The picking system based on ultrasonic recognition according to claim 1, wherein the attenuation structure comprises an acoustic absorption material, a range increasing structure with a range length greater than a straight line distance between the ultrasonic transmitter and the ultrasonic receiver, or a cut-down structure partially excavated. 3.The picking system based on ultrasonic recognition according to claim 1, further comprising an integrated sensor, the integrated sensor comprising the pressure sensing module, the ultrasonic transmitter, the ultrasonic receiver and a housing; wherein the housing forms the attenuation structure thereon and is used to mount the pressure sensing module, the ultrasonic transmitter and the ultrasonic receiver. 4.The picking system based on ultrasonic recognition according to claim 3, wherein the picking device comprises a gripper, a suction nozzle or a suction disc; wherein the integrated sensor is disposed on the object contact side of the gripper, the suction nozzle or the suction disc picking the object. 5.The picking system based on ultrasonic recognition according to claim 4, wherein the integrated sensor further comprises a first non-conductive layer, a second non-conductive layer, a first acoustic absorption layer and a second acoustic absorption layer; wherein the pressure sensing module comprises a first pressure sensing layer and a second pressure sensing layer wherein one end of the integrated sensor is sequentially provided with the first non-conductive layer, the ultrasonic transmitter, the first pressure sensing layer and the first acoustic absorption layer from the object contact side to an internal direction; wherein the other end of the integrated sensor is sequentially provided with the second non-conductive layer, the ultrasonic receiver, the second pressure sensing layer and the second acoustic absorption layer from the object contact side to the internal direction. 6.The picking system based on ultrasonic recognition according to claim 1, further comprising a storage device to store a machine learning model or a plurality of preset speeds, a plurality of preset waveforms or a plurality of preset frequency spectrums of a plurality of preset materials; wherein the control device is configured to perform at least one of the following: ​ inputting the ultrasonic data into a machine learning model to select one of the plurality of preset materials as the material of the identification result, wherein the machine learning model is obtained by training a plurality of training ultrasonic data of a plurality of training objects of the plurality of preset materials, and includes a plurality of classification rules for classifying the ultrasonic data into one of the plurality of preset materials; selecting the preset material corresponding to the preset speed matching the sensing speed of the ultrasonic data as the material of the identification result; selecting the preset material corresponding to the preset waveform matching the sensing waveform of the ultrasonic data as the material of the identification result; and converting the ultrasonic data into a frequency domain to obtain an ultrasonic spectrum, and selecting the preset material corresponding to the preset frequency spectrum matching the ultrasonic spectrum as the material of the identification result.

7. The ultrasonic identification based object picking system of claim 1, wherein the control device is configured to obtain a first picking force, perform rigidity detection based on the first picking force to obtain rigidity of the object, configure a second picking force based on the rigidity, and control the picking device to pick the object using the second picking force.

8. The ultrasonic identification based object picking system of claim 7, wherein the picking device comprises a gripper. wherein the control device is configured to control the gripper to clamp the object using a plurality of detection forces to obtain a plurality of pressure sensing values, wherein the plurality of detection forces correspond to a plurality of strokes, and determine the rigidity of the object based on a change in the plurality of strokes and a change in the plurality of pressure sensing values; wherein the control device is configured to configure a picking pressure lower limit and a picking pressure upper limit with a smaller difference for a softer rigidity, and configure the picking pressure lower limit and the picking pressure upper limit with a larger difference for a harder rigidity.

9. An object picking method based on ultrasonic recognition, applied to a picking device, a pressure sensing module and an ultrasonic sensing module being arranged on an object contact side of the picking device, wherein, The ultrasonic sensing module comprises an ultrasonic transmitter and an ultrasonic receiver, and an attenuation structure is arranged between the ultrasonic transmitter and the ultrasonic receiver, the attenuation structure being used to attenuate the ultrasonic waves propagating from the ultrasonic transmitter to the ultrasonic receiver. The method comprises: Step a) adjusting the contact force of the picking device on the object to make the pressure sensing value of the pressure sensing module higher than a contact pressure lower limit or lower than a contact pressure upper limit, so that the object contact side is tightly attached to the object; Step b) obtaining ultrasonic data of the object by the ultrasonic sensing module; Step c) determining an identification result of the object based on the ultrasonic data; and Step d) adjusting the picking force of the picking device based on the identification result to pick the object.

10. The ultrasonic identification based object picking method of claim 9, wherein the step c) comprises: Step c11) obtaining a plurality of preset speeds corresponding to a plurality of preset materials; Step c12) obtaining a sensing speed of the ultrasonic data; and ​ Step c13) selecting the preset material corresponding to the preset speed matching the sensed speed as the material of the recognition result.

11. The object picking method based on ultrasonic recognition of claim 9, wherein the step c) comprises: Step c21) obtaining a plurality of preset waveforms corresponding to a plurality of preset materials; Step c22) obtaining a sensed waveform of the ultrasonic data; and Step c23) selecting the preset material corresponding to the preset waveform matching the sensed waveform as the material of the recognition result.

12. The object picking method based on ultrasonic recognition of claim 9, wherein the step c) comprises: Step c31) obtaining a plurality of preset frequency spectrums corresponding to a plurality of preset materials; Step c32) converting the ultrasonic data to frequency domain to obtain an ultrasonic frequency spectrum; and Step c33) selecting the preset material corresponding to the preset frequency spectrum matching the ultrasonic frequency spectrum as the material of the recognition result.

13. The object picking method based on ultrasonic recognition of claim 9, wherein the step c) comprises: Step c41) inputting the ultrasonic data to a machine learning model to select one of a plurality of preset materials as the material of the recognition result, wherein the machine learning model is obtained by training a plurality of training ultrasonic data of a plurality of training objects of the plurality of preset materials, and comprises a plurality of classification rules for classifying the ultrasonic data to one of the plurality of preset materials.

14. The object picking method based on ultrasonic recognition of claim 9, wherein the recognition result comprises a material, a thickness, a density or a structure of the object; and the step d) is adjusting the picking device to pick the object with a larger picking force when the material of the recognition result is harder, the thickness of the recognition result is thicker or the density of the recognition result is higher, and adjusting the picking device to pick the object with a smaller picking force when the material of the recognition result is softer, the thickness of the recognition result is thicker or the density of the recognition result is higher.

15. The object picking method based on ultrasonic recognition of claim 9, wherein the step d) comprises: Step d1) obtaining a first picking force; Step d2) performing a rigidity detection based on the first picking force to obtain a rigidity of the object; Step d3) setting a second picking force based on the rigidity; and Step d4) controlling the picking device to pick the object with the second picking force.

16. The object picking method based on ultrasonic recognition of claim 15, wherein the picking device comprises a gripper; and the rigidity detection comprises: Step d21) controlling the gripper to grip the object with a plurality of detection forces to obtain a plurality of pressure sensing values, wherein the plurality of detection forces correspond to a plurality of strokes; and Step d22) determining the rigidity of the object based on a change of the plurality of strokes and a change of the plurality of pressure sensing values.

17. The object picking method based on ultrasonic recognition according to claim 15, wherein the second picking force includes a picking pressure upper limit and a picking pressure lower limit; the step d4) is setting the picking pressure lower limit and the picking pressure upper limit to a smaller gap for a softer rigidity and to a larger gap for a harder rigidity.

18. The object picking method based on ultrasonic recognition according to claim 17, wherein the contact pressure lower limit is smaller than the picking pressure lower limit, and the contact pressure upper limit is smaller than the picking pressure upper limit.

19. The object picking method based on ultrasonic recognition according to claim 9, further comprising: Step e) setting a material of the object based on the recognition result; and Step f) moving the object to a designated position of the material. ​

Images