Material identification system and method

Abstract

The invention provides a material identification system and method. The material recognition system may include a fetching device, at least one sensing device, and a processing device. The object taking device can be used for taking a target object. The sensing device can be arranged on the object taking part of the object taking device. The sensing device may include an ultrasound transmitter and an ultrasound receiver. The ultrasonic transmitter may transmit an ultrasonic transmit signal from a surface of a target. The ultrasound receiver may measure an ultrasound receive signal from a surface of a target. And a fixed distance is formed between the ultrasonic transmitter and the ultrasonic receiver. The processing device can identify the material of the target object according to the ultrasonic transmitting signal, the ultrasonic receiving signal and the fixed distance. In addition, when the object taking device takes the target object, the ultrasonic wave emitter and the ultrasonic wave receiver make contact with the surface of the target object.

Description

Technical Field

[0001] Embodiments of the present invention mainly relate to material identification technology, and more particularly to a material identification system and method for identifying the material of a target object based on an ultrasonic signal on the surface of the target object. Background Art

[0002] With the advancement of technology, the application of service robots or collaborative robots (cobots) is becoming more and more widespread.

[0003] For example, a collaborative robot (such as a robotic arm) can be used to pick up objects to provide different services. When the collaborative robot picks up an object, the collaborative robot can use an image recognition algorithm to obtain the shape and color of the object, or can use a mechanical sensor to obtain the hardness of the object to identify the object.

[0004] However, when the shape and color of the target object are difficult to identify (for example, the target object is a transparent object), it will be more difficult for the collaborative robot to identify the target object. In addition, since the material of the target object itself is unknown, when the collaborative robot applies pressure to the target object to obtain the hardness of the target object, it may cause damage to the target object.

[0005] Therefore, how to identify the target object more accurately and quickly will be a topic worth discussing. Summary of the invention

[0006] In view of the above problems in the prior art, embodiments of the present invention provide a material identification system and method.

[0007] According to one embodiment of the present invention, a material identification system is provided. The material identification system may include a picking device, at least one sensing device and a processing device. The picking device may be used to pick up a target object. The sensing device may be configured in a picking portion of the picking device. Each sensing device may include an ultrasonic transmitter and an ultrasonic receiver. The ultrasonic transmitter may be used to send an ultrasonic transmission signal from a surface of the target object. The ultrasonic receiver may be used to receive an ultrasonic reception signal from the surface of the target object. There is a fixed distance between the ultrasonic transmitter and the ultrasonic receiver. The processing device couples the picking device and the at least one sensing device. The processing device may identify the material of the target object based on the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance. In addition, when the picking device picks up the target object, the ultrasonic transmitter and the ultrasonic receiver contact the surface of the target object.

[0008] In some embodiments, the processing device obtains a sound wave propagation speed signal corresponding to the target object according to the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance.

[0009] In some embodiments, the processing device identifies the material of the target object according to the sound wave propagation speed signal and a lookup table.

[0010] In some embodiments, the processing device further obtains the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal, and inputs the ultrasonic features corresponding to the sound wave propagation velocity signal, the time domain signal and the frequency domain signal into a machine learning model to identify the material of the target object.

[0011] In some embodiments, the processing device represents the ultrasonic characteristics according to the time domain signals and frequency domain signals of the ultrasonic transmission signal and the ultrasonic reception signal, wherein the ultrasonic characteristics may include the signal impedance value, signal attenuation value, signal distortion value and signal complexity corresponding to the ultrasonic transmission signal and the ultrasonic reception signal.

[0012] In some embodiments, the ultrasonic transmitter and the ultrasonic receiver are arranged in parallel in the sensing device.

[0013] In some embodiments, the ultrasonic transmitter and the ultrasonic receiver are flat against the surface of the target object.

[0014] In some embodiments, a first sensing device is disposed on a first side of the object-taking portion, and a second sensing device is disposed on a second side of the object-taking portion.

[0015] In some embodiments, the sensing device further includes a pressure sensor to determine whether the ultrasonic transmitter and the ultrasonic receiver are in contact with the surface of the target object.

[0016] In some embodiments, the object-picking device is a robotic arm device, a suction cup device, a probe device or a clamping claw device.

[0017] According to one embodiment of the present invention, a material identification method is provided. The material identification method is applicable to a material identification system. The steps of the material identification method include: picking up a target object through a picking device of the material identification system; sending an ultrasonic transmission signal from a surface of the target object through an ultrasonic transmitter of at least one sensing device of the material identification system; receiving an ultrasonic reception signal from the surface of the target object through an ultrasonic receiver of the at least one sensing device, wherein when the picking device picks up the target object, the ultrasonic transmitter and the ultrasonic receiver contact the surface of the target object, and wherein there is a fixed distance between the ultrasonic transmitter and the ultrasonic receiver; and identifying the material of the target object according to the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance through a processing device of the material identification system.

[0018] As for other additional features and advantages of the present invention, those skilled in the art may make slight changes and modifications based on the material identification system and method disclosed in the implementation method of this case without departing from the spirit and scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A block diagram showing a material identification system 100 according to an embodiment of the present invention;

[0020] Figure 2A A schematic diagram showing the configuration of a sensing device 120 according to an embodiment of the present invention;

[0021] Figure 2B A schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention;

[0022] Figure 2C A schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention;

[0023] Figure 2D A schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention;

[0024] Figure 3A A schematic diagram showing a sensing device 120 according to an embodiment of the present invention;

[0025] Figure 3B A schematic diagram showing a sensing device 120 according to another embodiment of the present invention;

[0026] Figure 4 A flow chart of a material identification method according to an embodiment of the present invention is shown.

[0027] Description of Figure Numbers:

[0028] 100: Material identification system

[0029] 110: Pick-up device

[0030] 120: Sensing device

[0031] 121: Ultrasonic transmitter

[0032] 122: Ultrasonic Receiver

[0033] 123: Pressure sensor

[0034] 130: Processing device

[0035] 140: Storage device

[0036] 200: Target

[0037] d: distance

[0038] S410~S440: Steps DETAILED DESCRIPTION

[0039] This section describes the preferred method of implementing the present invention, which is intended to illustrate the spirit of the present invention rather than to limit the scope of protection of the present invention. The scope of protection of the present invention shall be determined by the appended claims.

[0040] Figure 1 A block diagram of a material identification system 100 according to an embodiment of the present invention is shown. Figure 1 As shown, the material identification system 100 may include a picking device 110, at least one sensing device 120, a processing device 130 and a storage device 140. Figure 1 The material identification system 100 shown in FIG. 1 is only for the convenience of illustrating an embodiment of the present invention, but the present invention is not limited to Figure 1 The material identification system 100 may also include other devices.

[0041] According to one embodiment of the present invention, the sensing device 120, the processing device 130 and the storage device 140 may be integrated into the object-retrieving device 110. According to another embodiment of the present invention, the sensing device 120 may be integrated into the object-retrieving device 110, and the processing device 130 and the storage device 140 may be integrated into another device (e.g., a tablet computer, a desktop computer, a laptop computer, etc.).

[0042] According to an embodiment of the present invention, the object-picking device 110 may be a service robot or a collaborative robot, such as a mechanical arm device, a suction cup device, a probe device or a gripper device, but the present invention is not limited thereto. The object-picking device 110 may be used to pick up a target object 200. The object-picking device 110 may include a main body portion and an object-picking portion (i.e., an end-effector of the object-picking device 110).

[0043] According to one embodiment of the present invention, the sensing device 120 is disposed on the object-retrieving portion of the object-retrieving device 110. For example, if the object-retrieving device 110 is a robot arm device, the sensing device 120 can be disposed on the gripper of the object-retrieving device 110, and if the object-retrieving device 110 is a suction cup device, the sensing device 120 can be disposed on the suction cup of the object-retrieving device 110.

[0044] According to one embodiment of the present invention, the object-retrieving portion of the object-retrieving device 110 may be configured with one or more sensor devices 120. For example, if the object-retrieving device 110 is a robotic arm device, one sensor device 120 may be configured on one side of the gripper of the object-retrieving device 110, and another sensor device 120 may be configured on the other side of the gripper of the object-retrieving device 110.

[0045] Figure 2A A schematic diagram showing the configuration of the sensing device 120 according to an embodiment of the present invention is shown. Figure 2A As shown, if the object-picking device 110 is a robotic arm device, the sensing device 120 can be disposed on one side of the gripper of the object-picking device 110 .

[0046] Figure 2B A schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention is shown. Figure 2B As shown, if the picking device 110 is a robotic arm device, a sensing device 120 can be configured on one side of the gripper of the picking device 110 , and another sensing device 120 can be configured on the other side of the gripper of the picking device 110 .

[0047] Figure 2C A schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention is shown. Figure 2C As shown, if the object-retrieving device 11 is a probe device, the sensing device 120 can be disposed on the probe of the object-retrieving device 110 .

[0048] Figure 2D FIG. 2 is a schematic diagram showing the configuration of a sensing device 120 according to another embodiment of the present invention. Figure 2D As shown, if the object picking device 11 is a suction cup device, the sensing device 120 can be disposed on the suction cup of the object picking device 110 .

[0049] Note that, Figure 2A-2D This is only used to illustrate the embodiment of the present invention, but the present invention is not limited thereto. The configuration of the sensing device 120 can also be appropriately adjusted according to the type of the object-retrieving device 110 .

[0050] Figure 3A The sensing device 120 according to one embodiment of the present invention is shown. Figure 3A As shown, according to one embodiment of the present invention, the sensing device 120 may include an ultrasonic transmitter 121 and an ultrasonic receiver 122. There is a fixed distance d between the ultrasonic transmitter and the ultrasonic receiver of the sensing device 120. When the object-picking device 110 picks up the target object 200, the ultrasonic transmitter 121 and the ultrasonic receiver 122 contact the surface of the target object 200. The ultrasonic transmitter 121 may be used to send an ultrasonic transmission signal from the surface of the target object 200. The ultrasonic receiver 122 may be used to receive an ultrasonic reception signal from the surface of the target object 200 corresponding to the ultrasonic transmission signal transmitted by the ultrasonic transmitter 121.

[0051] Figure 3B A sensing device 120 according to another embodiment of the present invention is shown. Figure 3B As shown, the sensing device 120 may include an ultrasonic transmitter 121 , an ultrasonic receiver 122 and a pressure sensor 123 . Figure 3B and Figure 3A The difference is that the sensing device 120 is additionally equipped with a pressure sensor 123. When the object picking device 110 picks up the target object 200, the pressure sensor 123 can be used to determine whether the ultrasonic transmitter 121 and the ultrasonic receiver 122 have contacted the surface of the target object 200.

[0052] According to one embodiment of the present invention, Figure 3A-3B As shown, the ultrasonic transmitter 121 and the ultrasonic receiver 122 can be arranged in parallel in the sensing device 120, but the present invention is not limited thereto. In addition, according to an embodiment of the present invention, the ultrasonic transmitter 121 and the ultrasonic receiver 122 can be flatly attached to the target object 200 to contact the surface of the target object 200, but the present invention is not limited thereto.

[0053] According to an embodiment of the present invention, the ultrasonic transmitter 121 and the ultrasonic receiver 122 may also be independent devices, and there is still a fixed distance d between the ultrasonic transmitter 121 and the ultrasonic receiver 122 .

[0054] According to one embodiment of the present invention, the processing device 130 may be a controller or a processor. The processing device 130 may be used to control the operation of the object-retrieving device 110, the sensing device 120, and the storage device 140. According to one embodiment of the present invention, the processor 210 may execute software and solid program codes to perform operations related to material identification of the target object 200.

[0055] According to one embodiment of the present invention, the storage device 140 can be used to store software and solid-state program codes, system data, etc. of the processing device 130. The storage device 140 can be a volatile memory (e.g., random access memory (RAM)), or a non-volatile memory (e.g., flash memory, read-only memory (ROM)), a hard disk, or a combination of the above storage devices. According to one embodiment of the present invention, the storage device 140 can be used to store a lookup table of material signals (e.g., sound wave propagation speed signals) corresponding to different materials (e.g., glass, plastic, metal, etc.). According to one embodiment of the present invention, the storage device 140 can also be used to store relevant data of a machine learning model or a deep learning model required for performing a machine learning operation or a deep learning operation.

[0056] According to an embodiment of the present invention, when the object-taking device 110 takes the target object 200, the processing device 130 may obtain a sound wave propagation speed signal corresponding to the target object 200 according to the ultrasonic transmission signal sent by the ultrasonic transmitter 121, the ultrasonic reception signal received by the ultrasonic receiver 122, and the distance d between the ultrasonic transmitter 121 and the ultrasonic receiver 122. Specifically, the processing device 130 may calculate the propagation time of the ultrasonic signal on the material of the target object 200 according to the ultrasonic transmission signal sent by the ultrasonic transmitter 121 and the ultrasonic reception signal received by the ultrasonic receiver 122. Then, the processing device 130 may divide the distance d by the propagation time of the ultrasonic signal on the material of the target object 200 to obtain the propagation speed of the ultrasonic signal on the material of the target object 200 (i.e., the sound wave propagation speed signal corresponding to the target object 200).

[0057] According to an embodiment of the present invention, the processing device 130 can identify the material of the target object 200 according to the sound wave propagation speed signal corresponding to the target object 200 and a lookup table. For example, the propagation speed of the ultrasonic signal on different materials can be pre-recorded in the lookup table. The processing device 130 can know the material of the target object 200 by looking up the table.

[0058] According to another embodiment of the present invention, the processing device 130 can further obtain the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal, and input the sound wave propagation speed signal corresponding to the target object 200, and the time domain signal and the frequency domain signal corresponding to the ultrasonic transmission signal and the ultrasonic reception signal into a pre-trained machine learning model or a deep learning model to identify the material of the target object 200.

[0059] More specifically, the processing device 130 can represent the ultrasonic characteristics transmitted to the surface of the target object 200 according to the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal. The ultrasonic characteristics may include signal impedance value, signal attenuation value, signal distortion value and signal complexity, etc., but the present invention is not limited thereto. Then, the processing device 130 can input the sound wave propagation speed signal corresponding to the target object 200, as well as the time domain signal characteristics of the ultrasonic transmission signal and the ultrasonic reception signal and the ultrasonic characteristics corresponding to the frequency domain signal into a pre-trained machine learning model or a deep learning model to identify the material of the target object 200.

[0060] According to an embodiment of the present invention, the time domain signal may include a root mean square (RMS) level, a waveform envelope, a zero-crossing rate, and a sample entropy, but the present invention is not limited thereto. According to an embodiment of the present invention, the frequency domain signal may include a Hilbert-Huang transform (HHT) marginal spectrum, but the present invention is not limited thereto. In one embodiment, the processing device 130 may represent the signal impedance value of the ultrasonic signal according to the root mean square level corresponding to the ultrasonic transmission signal and the ultrasonic reception signal. In another embodiment, the processing device 130 may represent the signal attenuation value of the ultrasonic signal according to the waveform envelope and the zero-crossing rate corresponding to the ultrasonic transmission signal and the ultrasonic reception signal. In another embodiment, the processing device 130 may represent the signal distortion value and signal complexity of the ultrasonic signal according to the sample entropy and the Hilbert-Huang transform marginal spectrum corresponding to the ultrasonic transmission signal and the ultrasonic reception signal.

[0061] According to one embodiment of the present invention, the machine learning model or deep learning model may include a decision tree, a support vector machine (SVM), a deep belief network (DBN), a K-nearest neighbor algorithm or a convolutional neural network (CNN), but the present invention is not limited thereto.

[0062] After the processing device 130 knows the material of the target object 200, the accuracy of identifying the target object can be increased and improved.

[0063] Figure 4 A flow chart of a material identification method according to an embodiment of the present invention is shown. Figure 4 The flowchart of FIG. 1 is applicable to the material identification system 100 . In step S410 , a target object is picked up by a picking device of the material identification system 100 .

[0064] In step S420 , an ultrasonic transmitter of at least one sensing device of the material identification system 100 sends an ultrasonic transmission signal from a surface of the target object.

[0065] In step S430, an ultrasonic receiving signal is received from the surface of the target object by an ultrasonic receiver of the at least one sensing device of the material identification system 100. In the material identification method, when the object picking device picks up the target object, the ultrasonic transmitter and the ultrasonic receiver will contact the surface of the target object, and there is a fixed distance between the ultrasonic transmitter and the ultrasonic receiver.

[0066] In step S440 , a processing device of the material identification system 100 identifies the material of the target object according to the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance.

[0067] According to an embodiment of the present invention, in the material identification method, the processing device of the material identification system 100 can further obtain the sound wave propagation speed signal corresponding to the target object according to the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance.

[0068] According to an embodiment of the present invention, in the material identification method, the processing device of the material identification system 100 can further identify the material of the target object according to the sound wave propagation speed signal and a lookup table.

[0069] According to an embodiment of the present invention, in the material identification method, the processing device of the material identification system 100 can further obtain the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal. Then, the processing device of the material identification system 100 can input the ultrasonic features corresponding to the obtained sound wave propagation velocity signal, time domain signal and frequency domain signal into a machine learning model to identify the material of the target object.

[0070] According to an embodiment of the present invention, in the material identification method, the processing device of the material identification system 100 can further represent the ultrasonic characteristics according to the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal. The ultrasonic characteristics may include a signal impedance value, a signal attenuation value, a signal distortion value and a signal complexity corresponding to the ultrasonic transmission signal and the ultrasonic reception signal.

[0071] According to an embodiment of the present invention, in the material identification method, the ultrasonic transmitter and the ultrasonic receiver may be configured in parallel in the above-mentioned sensing device.

[0072] According to an embodiment of the present invention, in the material identification method, the ultrasonic transmitter and the ultrasonic receiver may be placed flat on the surface of the target object.

[0073] According to one embodiment of the present invention, in a material identification method, a first sensing device is configured on a first side of a picking part of a picking device of a material identification system 100, and a second sensing device is configured on a second side of a picking part of a picking device of the material identification system 100.

[0074] According to an embodiment of the present invention, in the material identification method, the sensing device further includes a pressure sensor to determine whether the ultrasonic transmitter and the ultrasonic receiver are in contact with the surface of the target object.

[0075] According to an embodiment of the present invention, in the material identification method, the object-picking device may be a robotic arm, a suction cup device, a probe device or a gripper device.

[0076] According to the material identification method proposed by the present invention, the material of the target object can be identified by the signal characteristics generated by the ultrasonic signal transmitted on the surface of the target object, thereby increasing and improving the accuracy of identifying the target object.

[0077] Serial numbers in this specification and application claims, such as "first", "second", etc., are only for convenience of explanation and have no sequential relationship with each other.

[0078] The steps of the method and algorithm disclosed in the specification of the present invention can be directly applied to hardware and software modules or a combination of the two by executing a processor. A software module (including execution instructions and related data) and other data can be stored in a data storage device, such as a random access memory (RAM), a flash memory, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electronically erasable programmable read-only memory (EEPROM), a temporary register, a hard disk, a portable hard disk, a compact disk read-only memory (CD-ROM), a DVD or any other computer-readable storage medium format in the prior art in this field. A storage medium can be coupled to a machine device, for example, such as a computer / processor (for convenience of explanation, the processor is represented in this specification), and the above-mentioned processor can read signals (such as program codes) and write signals to the storage medium. A storage medium can integrate a processor. An application-specific integrated circuit (ASIC) includes a processor and a storage medium. A user device includes an application-specific integrated circuit. In other words, the processor and the storage medium are included in the user device in a way that is not directly connected to the user device. In addition, in some embodiments, any suitable computer program product includes a readable storage medium, wherein the readable storage medium includes program code related to one or more disclosed embodiments. In some embodiments, the computer program product may include packaging materials.

[0079] The above paragraphs are described using multiple levels. Obviously, the teachings of this article can be implemented in multiple ways, and any specific architecture or function disclosed in the examples is only a representative situation. Based on the teachings of this article, any person skilled in the art should understand that each level disclosed in this article can be implemented independently or two or more levels can be combined for implementation.

[0080] Although the present disclosure has been disclosed as above by way of embodiments, it is not intended to limit the present disclosure. Any person skilled in the art may make some changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the protection scope of the present invention shall be determined by the appended claims.

Claims

1. A material identification system, comprising: A picking device for picking up a target object; At least one sensing device is disposed in the object-retrieving portion of the object-retrieving device, wherein the sensing device comprises: an ultrasonic transmitter for transmitting an ultrasonic transmission signal from the surface of the target object; and An ultrasonic receiver for receiving an ultrasonic receiving signal from the surface of the target object, wherein the ultrasonic transmitter is at a fixed distance from the ultrasonic receiver; and a processing device coupled to the object-retrieving device and the at least one sensing device, and identifying the material of the target object according to the ultrasonic emission signal, the ultrasonic reception signal and the fixed distance, When the object-picking device picks up the target object, the ultrasonic transmitter and the ultrasonic receiver contact the surface of the target object.

2. The material identification system according to claim 1, wherein the processing device obtains the sound wave propagation speed signal corresponding to the target object according to the ultrasonic transmission signal, the ultrasonic reception signal and the fixed distance.

3. The material identification system according to claim 2, wherein the processing device identifies the material of the target object based on the sound wave propagation velocity signal and a lookup table.

4. The material identification system according to claim 2, wherein the processing device further obtains the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal, and inputs the ultrasonic features corresponding to the sound wave propagation velocity signal, the time domain signal and the frequency domain signal into a machine learning model to identify the material of the target object.

5. The material identification system according to claim 4, wherein the processing device represents the ultrasonic characteristics according to the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal, wherein the ultrasonic characteristics include signal impedance values, signal attenuation values, signal distortion values ​​and signal complexity corresponding to the ultrasonic transmission signal and the ultrasonic reception signal.

6. The material identification system according to claim 1, wherein the ultrasonic transmitter and the ultrasonic receiver are arranged in parallel in the sensing device.

7. The material identification system according to claim 1, wherein the ultrasonic transmitter and the ultrasonic receiver are flat against the surface of the target object.

8. A material identification system according to claim 1, wherein a first sensing device is configured on a first side of the picking portion, and a second sensing device is configured on a second side of the picking portion.

9. The material identification system according to claim 1, wherein the sensing device further comprises a pressure sensor to determine whether the ultrasonic transmitter and the ultrasonic receiver are in contact with the surface of the target object.

10. The material identification system according to claim 1, wherein the object picking device is a robotic arm device, a suction cup device, a probe device or a gripper device.

11. A material identification method, applicable to a material identification system, comprising: Taking the target object by means of the taking device of the material identification system; Sending an ultrasonic emission signal from the surface of the target object through an ultrasonic transmitter of at least one sensing device of the material identification system; Receiving an ultrasonic reception signal from the surface of the target object by means of an ultrasonic receiver of the at least one sensing device, wherein when the object-picking device picks up the target object, the ultrasonic transmitter and the ultrasonic receiver contact the surface of the target object, and wherein a fixed distance exists between the ultrasonic transmitter and the ultrasonic receiver; as well as The material of the target object is identified by the processing device of the material identification system according to the ultrasonic emission signal, the ultrasonic reception signal and the fixed distance.

12. The material identification method according to claim 11, further comprising: The processing device obtains a sound wave propagation speed signal corresponding to the target object according to the ultrasonic emission signal, the ultrasonic reception signal and the fixed distance.

13. The material identification method according to claim 12, further comprising: The material of the target object is identified by the processing device according to the sound wave propagation speed signal and a lookup table.

14. The material identification method according to claim 12, further comprising: Obtaining the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal through the processing device; as well as The processing device inputs the ultrasonic wave propagation velocity signal, the time domain signal and the ultrasonic wave features corresponding to the frequency domain signal into a machine learning model to identify the material of the target object.

15. The material identification method according to claim 14, further comprising: The processing device represents the ultrasonic characteristics according to the time domain signal and the frequency domain signal of the ultrasonic transmission signal and the ultrasonic reception signal, wherein the ultrasonic characteristics include signal impedance value, signal attenuation value, signal distortion value and signal complexity corresponding to the ultrasonic transmission signal and the ultrasonic reception signal.

16. The material identification method according to claim 11, wherein the ultrasonic transmitter and the ultrasonic receiver are arranged in parallel in the sensing device.

17. The material identification method according to claim 11, wherein the ultrasonic transmitter and the ultrasonic receiver are flat against the surface of the target object.

18. The material identification method according to claim 11, wherein the first sensing device is configured on a first side of the picking portion, and the second sensing device is configured on a second side of the picking portion.

19. The material identification method according to claim 11, wherein the sensing device further comprises a pressure sensor to determine whether the ultrasonic transmitter and the ultrasonic receiver are in contact with the surface of the target object.

20. The material identification method according to claim 11, wherein the object picking device is a mechanical arm device, a suction cup device, a probe device or a clamping claw device.

Images