CN114043507A - Force sensor, robot and application method of force sensor - Google Patents
Force sensor, robot and application method of force sensor Download PDFInfo
- Publication number
- CN114043507A CN114043507A CN202111405021.8A CN202111405021A CN114043507A CN 114043507 A CN114043507 A CN 114043507A CN 202111405021 A CN202111405021 A CN 202111405021A CN 114043507 A CN114043507 A CN 114043507A
- Authority
- CN
- China
- Prior art keywords
- flexible
- force sensor
- robot
- module
- interaction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000003993 interaction Effects 0.000 claims abstract description 57
- 238000013135 deep learning Methods 0.000 claims abstract description 6
- 230000007246 mechanism Effects 0.000 claims description 36
- 230000003044 adaptive effect Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 19
- 239000012530 fluid Substances 0.000 claims description 18
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 11
- 239000003550 marker Substances 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 2
- 239000011248 coating agent Substances 0.000 claims 3
- 238000000576 coating method Methods 0.000 claims 3
- 238000012512 characterization method Methods 0.000 claims 1
- 230000010399 physical interaction Effects 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 description 14
- 230000008447 perception Effects 0.000 description 12
- 210000000707 wrist Anatomy 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000013013 elastic material Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000012636 effector Substances 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 229920001971 elastomer Polymers 0.000 description 1
- 239000000806 elastomer Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 210000003857 wrist joint Anatomy 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
- B25J13/085—Force or torque sensors
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a force sensor, a robot and an application method of the force sensor. The force sensor comprises a flexible interaction module and a data acquisition module. The flexible interaction module is in contact with a target interaction object; the data acquisition module acquires a representation value of the flexible deformation generated by the flexible interaction module; and acquiring the target interaction characteristic corresponding to the flexible deformation based on computer vision and computer deep learning. The robot using the force sensor can not only remarkably reduce hardware cost and structural complexity, but also remarkably enrich the application scene of the robot. The robot can complete high-precision physical interaction tasks in unstructured environments such as land, underwater and the like.
Description
Technical Field
The invention relates to the field of sensors, in particular to a force sensor, a robot and an application method of the force sensor.
Background
The force sense means a sense of a force from the outside during a robot operation, and is different from a pressure sense, which is a sense of a force perpendicular to a force contact surface, a three-dimensional force, and a three-dimensional moment. The robot force sensor is a device for simulating the functions of joints of four limbs of a human to obtain most force information during actual operation, directly influences the force control performance of the robot, and is an essential device for the active flexible control of the robot. The main performance requirements of the robot tactile sensor are high resolution, high sensitivity, high linearity, good reliability and strong anti-interference capability. The force sensors can be divided into wrist force sensors, joint force sensors, grip force sensors, foot force sensors, finger force sensors and the like according to different installation positions of the sensors.
Force sensors are often mounted at the joints of the robot and measure the applied force indirectly by detecting the deformation of the elastomer. The force sensor arranged at the joint of the robot usually appears in a fixed three-coordinate mode, which is beneficial to meeting the requirements of a control system. The existing six-dimensional force sensor can realize the measurement of full force information, and is called a wrist force sensor because the six-dimensional force sensor is mainly arranged at a wrist joint. Most of the wrist force sensors adopt a strain electrical measurement principle and can be divided into a cylindrical wrist force sensor and a cross-shaped wrist force sensor according to the structural form of an elastic body. The cylinder type wrist force sense sensor has the characteristics of simple structure, high utilization rate of the elastic beam and high sensitivity; the cross-shaped sensor has simple structure, easy coordinate establishment and high processing precision.
The main reasons why the force control technique has not been put into practical use are: firstly, the existing robot technology has not yet completely reached the level of realizing force control; secondly, the theoretical system of force control is not yet perfect. In addition, the system configuration and corresponding universal robot language for theoretically grasping the robot actions and environment are still under further study. This series of research and development work requires implementation of sensor feedback control, and also requires a robot control system with general-purpose hardware and software. The current commercialized robot is mainly based on a position control or teaching method.
Multi-dimensional force sensors can provide multi-dimensional force information acting in three-dimensional space, and among them, six-dimensional force sensors can provide force magnitude and moment along 3 coordinate axes in three-dimensional space. In the fields of robots, medical treatment and aviation, the six-dimensional force sensor provides important sensing information for intelligent and safe operation of equipment, and has wide application prospects in the scene of intellectualization and man-machine interaction.
The existing multi-dimensional force and moment sensing scheme usually depends on an internal mechanism designed by rigid materials to realize space motion. The pressure sensing structure is common in an elastic structural formula, a Stewart parallel structural formula, a flexible structural formula and the like. The structures of the existing sensors are mainly rigid cylinders, the structures are heavy, the functions are single, and the existing sensors cannot be directly applied to interaction with articles or people.
The existing multi-dimensional force and moment sensing scheme usually depends on an internal mechanism designed by rigid materials, realizes kinematic expression of multi-dimensional motion in the physical interaction process, generally adopts an integrated design, lacks interchangeability among different sensing schemes, and has single application scene and poor flexibility.
The existing multidimensional flexible force sense sensor can deal with complex environments such as: in an underwater environment, due to the large number of internal devices and parts, more complex additional devices and designs are often required to achieve better sealing, resulting in higher cost.
Disclosure of Invention
In view of the above-mentioned problems, the present invention provides a force sensor, comprising: the flexible interaction module and the data acquisition module; the flexible interaction module is connected with the data acquisition module through a mechanical structure; the flexible interaction module is in contact with a target interaction object; the data acquisition module acquires the characteristic value of the flexible deformation generated by the flexible interaction module, and force sense data are obtained according to the characteristic value of the flexible deformation. The target interactive object includes, but is not limited to, a human body, a manipulator-manipulated object, a ground surface, and the like.
As a further development of the invention, the force sensor is designed based on machine vision.
As a further improvement of the invention, the flexible interaction module comprises: a flexible mechanism and a visual marker; the flexible mechanism includes: one of a flexible mechanism designed based on a differential stiffness principle and a variant mechanism designed based on the differential stiffness principle; the visual marker includes: the flexible mechanism is coated with one of different colors, geometric patterns, additionally attached balls or two-dimensional codes. Visual markers can increase the accuracy and robustness of data processing.
As a further improvement of the invention, the data acquisition module is provided with: one or more of an optical sensor, an image sensor, and an infrared sensor.
As a further improvement of the present invention, the flexible mechanism comprises: a passive adaptive tip configuration, e.g., a three-dimensional mesh structure finger made of an elastic material; passive composite six-dimensional configurations, e.g., three-dimensional networks made of elastic materials; the fluid drives the telescoping configuration, for example, an accordion tube configuration. The main function of the flexible mechanism is to convert the mechanical movement generated by the physical interaction process into the three-dimensional space movement of the flexible mechanism, wherein the physical interaction comprises the physical interaction caused by external force and the physical interaction from the interior of the flexible mechanism.
As a further improvement of the invention, the data acquisition module is selected to be integrally installed: one or more of a light source, a data processing module and a data display module. The data acquisition module may be combined with an LED lamp to increase light source stability in certain applications. The data acquisition module can be additionally integrated with a data processing module, and the target interaction characteristics corresponding to the flexible deformation can be obtained through a computer vision or machine learning or deep learning method. The data processing module can be integrated into the force sensor in the form of an embedded computing chip, and can also be operated on a user host computer in the form of software. On the basis of the data processing module, a data display module can be additionally added, so that the sensing data of the sensor can be presented to a user in real time.
As a further improvement of the invention, the data acquisition module is subjected to waterproof packaging, and the force sensor can be applied to an underwater environment in consideration that the flexible interaction module is not connected with the data acquisition module by any circuit and does not have any electronic component.
The present invention also provides a robot, comprising: flexible interactive sensing parts, mechanical arms or mechanical legs. The flexible interaction sensing part comprises the force sensor, and the force sensor is connected with the mechanical arm or the mechanical leg. The robot can contact with the target control object through the flexible interactive sensing part. The force sensor can be directly used as a flexible interaction sensing part of the robot, and not only can realize the function of the sensor, but also can realize the functions of contacting and interacting with people, objects, the ground and the like.
As a further improvement of the invention, the force sensor is connected with a mechanical arm or a mechanical leg.
As a further improvement of the invention, the force sensor is connected with the wrist of the mechanical arm or the mechanical leg.
As a further improvement of the present invention, the fixing means is preferably an adapter flange.
As a further improvement of the present invention, the robot arm includes: an industrial robot arm, a cooperative robot arm, an underwater robot arm, or a finger portion of a robot arm.
As a further improvement of the invention, the mechanical leg comprises: the foot part of the underwater mechanical leg and the foot type robot.
The invention also provides an application method of the force sensor, which comprises the following steps: contacting the flexible interaction module with a target interaction object; the data acquisition module acquires a representation value of the flexible deformation generated by the flexible interaction module; and acquiring the target interaction characteristic corresponding to the flexible deformation based on computer vision and computer deep learning.
As a further improvement of the invention, the characteristic value of the flexible deformation can be deformation image change, optical signal change or marker characteristic value extracted by computer vision, and the characteristic value can be obtained by single data acquisition or a sequence of multiple data acquisition.
As a further improvement of the invention, the target interaction characteristics comprise the deformation amount of the flexible mechanism, the magnitude of the contact acting force, the contact position, the shape of the interaction object or the hardness and softness of the interaction object.
As a further improvement of the invention, a mapping model is obtained through the representation value of the flexible deformation and the target interaction characteristic, and the mapping model can be a neural network model which is obtained through collecting training data with labels and through back propagation learning.
Compared with the prior art, the application has the advantages that:
1. according to the flexible mechanism, through the nonlinear elastic deformation and the three-dimensional metamaterial configuration of the flexible mechanism, the three-dimensional response to the actual physical interactive deformation of the contact interface is realized; when the flexible mechanism is subjected to lateral acting force from an external environment, the flexible mechanism can realize the concave deformation of the flexible connecting rod through the uniquely designed network structure, so that the adaptive configuration with the external environment is realized; so that the force sensor can be directly used as a robot end effector, such as a robot finger and the like. The force sense sensor senses multidimensional force sense signals in real time while realizing self-adaptive grabbing.
2. According to the method, different flexible mechanisms can be replaced only through a mechanical flange interface under the condition that the electrical interface of the whole machine is not changed according to different actual interaction scenes, rich multi-dimensional flexible force sense perception is achieved, and the method is directly adaptive to an application scene; thereby promote the commonality of this application by a wide margin.
3. The multi-dimensional force perception sensor adopts a machine vision-based device as a main sensor for multi-dimensional force perception, the number of required sensors is greatly reduced, and the available sensing signal dimension is more abundant in data dimension compared with a single time sequence signal in the prior art.
4. The multi-dimensional force perception device based on the machine learning can realize multi-dimensional force perception of the same original data under different flexible mechanisms and complex scenes by adopting a data processing mode based on the machine learning, and can realize multi-dimensional force perception performance under different scenes without replacing hardware.
5. The method and the device can be simultaneously suitable for rich scenes including land and underwater.
Drawings
FIG. 1 is a schematic diagram of a force sensor according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of four configurations of a compliant mechanism according to one embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a robot with force sensor according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method for applying a force sensor according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a deformation of a force sensor in interaction with a human hand according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a deformation of a force sensor interacting with a linearly moving object according to an embodiment of the present invention;
FIG. 7 is a schematic view of a robot foot with force sensor according to an embodiment of the present invention;
in the figure:
1, a flexible interaction module; 2, a data acquisition module; 2' a data acquisition module support; 3 an image sensor; 4, a data display module; 5, a data processing module; 6 a first passive adaptive tip configuration; 7 a second passive adaptive tip configuration; 7-1 deformation one of the second passive adaptive tip configuration; 7-2 deformation of a second passive adaptive tip configuration; 7-3 deformation of a second passive adaptive tip configuration; 7-4 deformation of the second passive adaptive tip configuration; 8 a fluid driven telescopic configuration; 8-1, fluid-driven telescopic configuration deformation I; 8-2, driving the deformation II of the telescopic configuration by fluid; 8-3, deformation of a fluid-driven telescopic configuration is III; 9 passive compound six-dimensional configuration; 10, a mechanical arm; 10' mechanical legs; 11 target interactive objects.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
embodiment one, multidimensional flexible force sense transducer
As shown in fig. 1, the present invention provides a force sensor featuring multi-dimensional flexibility, comprising: the device comprises a flexible interaction module 1, a data acquisition module 2, a data acquisition module support 2', a data display module 4 and a data processing module 5. The flexible interaction module 1 is positioned on the uppermost layer and is in contact with a target interaction object; the data acquisition module 2 is connected with the lower part of the flexible interaction module 1 through a mechanical structure, the image sensor 3 is arranged in the data acquisition module support 2', the image sensor 3 is arranged in the data acquisition module, and the image sensor 3 is used for acquiring flexible deformation of the flexible interaction module 1 caused by contact force. The data acquisition module 2 is also integrated with a data processing module 5 and a data display module 4. The data processing module 5 communicates with the data acquisition module through a picture transmission protocol, and common transmission interfaces comprise wired transmission forms such as USB and CSI and wireless transmission forms such as WIFI. The data display module 4 is located on the side face of the data acquisition module support 2', the data display module 4 is connected with the data processing module 5, and the data display module 4 receives the target interaction characteristics obtained by the data processing module 5 so as to display the target interaction characteristic values in real time.
In the specific implementation process, flexible mechanisms with different structures can be selected according to the characteristics and the use purpose of the target interaction object. As shown in fig. 2, the structure of the flexible mechanism includes: a first passive adaptive tip configuration 6, a second passive adaptive tip configuration 7, a fluid driven telescoping configuration 8, and a passive compound six-dimensional configuration 9.
Second embodiment, robot
The flexible interactive module 1 can be arranged at the tail end of the finger of any manipulator, and comprises common electric, pneumatic, two-finger, three-finger and multi-finger manipulators, and is used for prolonging or replacing the original mechanical finger to enable the mechanical finger to have sensing capability.
As shown in fig. 3, the flexible mechanism in the flexible interactive module 1 adopts a second passive adaptive end configuration 7, and the second passive adaptive end configuration 7 is a mesh structure. The second passive self-adaptive tail end configuration 7, the mechanical arm 10, the data acquisition module 2, the data processing module 5 and the two-finger mechanical structure form a mechanical arm.
When the manipulator is used for grabbing an object, the second passive self-adaptive end configuration 7 of the net structure generates self-adaptive deformation to wrap the target interactive object 11; the second passive adaptive end configuration 7 can generate deformations such as a first deformation 7-1 of the second passive adaptive end configuration, a second deformation 7-2 of the second passive adaptive end configuration, a third deformation 7-3 of the second passive adaptive end configuration, and a fourth deformation 7-4 of the second passive adaptive end configuration; the data acquisition module 2 acquires an image sequence of flexible deformation and a motion position signal of a mechanical finger; based on the collected signals and the neural network model in the deep learning algorithm, the hardness and softness of the target interactive object 11, the magnitude of the contact force and the direction of the contact force are obtained through the data processing module 5.
Embodiment three, application method of force sensor
An application method of the force sensor provided in the embodiment of the present invention is shown in fig. 4, and includes the following steps:
s1, the flexible mechanism of the flexible interaction module 1 is in contact deformation with the target interaction object;
s2, the data acquisition module 2 acquires a representation value of the flexible deformation;
and S3, acquiring the target interaction characteristics corresponding to the flexible deformation based on the computer vision and the deep learning algorithm.
Example four construction of 6-dimensional force mapping model
As shown in fig. 5, the flexible mechanism of the force sensor flexible interaction module 1 is a fluid drive telescopic structure 8, the upper surface of the fluid drive telescopic structure 8 is coated with a two-dimensional code, the fluid drive telescopic structure 8 is mounted on the data acquisition module 2 through an adapter flange, and the data acquisition module 2 acquires data through an ATI sensor.
A human hand is used for translating or rotating the top of the fluid driving telescopic structure 8, the fluid driving telescopic structure 8 can generate flexible deformation under the action of 6-dimensional force, an image of the flexible deformation is collected at the same time (for example, the first deformation 8-1, the second deformation 8-2 and the third deformation 8-3 of the fluid driving telescopic structure are obtained), the 6D pose variation of the two-dimensional code is identified through an ATI sensor, the variation is used as a characteristic value of the flexible deformation, and a deep learning model is trained through back propagation by utilizing the collected training data to serve as a flexible deformation and 6-dimensional force mapping model.
Based on the flexible deformation and the 6-dimensional force mapping model, 6-dimensional force information including forces and moments in 3 directions on the bottom of the multi-dimensional flexible force sensor is obtained.
As shown in fig. 6, on the basis of fig. 5, a fluid driven telescopic configuration 8 is further connected to the top of the fluid driven telescopic configuration 8, a two-dimensional code or other pattern features are coated on the plane of the top fluid driven telescopic configuration 8, so that the two fluid driven telescopic configurations 8 connected in series are subjected to extrusion and lifting deformation, the data acquisition module 2 acquires an image of the flexible deformation, and the displacement of the two-dimensional code or other pattern features along the central axis direction of the two fluid driven telescopic configurations 8 can be further acquired as a representative value of the flexible deformation; and obtaining the force information along the central axial direction based on the flexible deformation and the 6-dimensional force mapping model.
The 6-dimensional force mapping model can be applied to a mechanical arm or a mechanical leg, and the dragging of the mechanical arm or the mechanical leg is reversely guided by the 6-dimensional force signal and the admittance control method.
Example five, foot type robot
As shown in fig. 7, the present embodiment provides a legged robot including: mechanical leg 10', flexible interaction module 1, data acquisition module 2 and data processing module 5. The flexible mechanism of the flexible interaction module 1 adopts a passive composite six-dimensional structure 9, and the target interaction object 11 is a contact object of the sole of the foot type robot.
The legged robot recognizes a target interaction object 11 through the flexible interaction module 1, the data acquisition module 2 and the data processing module 5, so as to sense an external environment, and then reversely controls the motion of the mechanical legs 10' according to a 6-dimensional force mapping model.
And (4) conclusion:
1. the force sensor realizes self-adaptive grabbing and simultaneously senses multidimensional force signals in real time.
2. According to the method, different flexible mechanisms can be replaced only through a mechanical flange interface under the condition that the electrical interface of the whole machine is not changed according to different actual interaction scenes, rich multi-dimensional flexible force sense perception is achieved, and the method is directly adaptive to an application scene; thereby promote the commonality of this application by a wide margin.
3. The multi-dimensional force perception sensor adopts a machine vision-based device as a main sensor for multi-dimensional force perception, the number of required sensors is greatly reduced, and the available sensing signal dimension is more abundant in data dimension compared with a single time sequence signal in the prior art.
4. The multi-dimensional force perception device based on the machine learning can realize multi-dimensional force perception of the same original data under different flexible mechanisms and complex scenes by adopting a data processing mode based on the machine learning, and can realize multi-dimensional force perception performance under different scenes without replacing hardware.
5. The method and the device can be simultaneously suitable for rich scenes including land and underwater.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A force sensor, characterized in that the force sensor comprises: the flexible interaction module and the data acquisition module;
the flexible interaction module is connected with the data acquisition module through a mechanical structure;
the flexible interaction module is in contact with a target interaction object;
the data acquisition module acquires a representation value of the flexible deformation generated by the flexible interaction module;
and obtaining force sense data according to the characterization value of the flexible deformation.
2. The force sensor of claim 1, wherein the flexible interaction module comprises: a flexible mechanism and a visual marker;
the flexible mechanism includes: one of a flexible mechanism designed based on a differential stiffness principle and a variant mechanism designed based on the differential stiffness principle;
the visual marker includes: one of different colors on the surface coating of the flexible mechanism, geometric shape patterns on the surface coating of the flexible mechanism, additionally attached small balls on the flexible mechanism and two-dimensional codes on the surface coating of the flexible mechanism.
3. The force sensor of claim 2, wherein the flexible mechanism comprises: passive adaptive tip configurations, passive compound six-dimensional configurations, and fluid driven telescoping configurations.
4. The force sensor of claim 1, wherein the data acquisition module has installed therein: one or more of an optical sensor, an image sensor, and an infrared sensor.
5. The force sensor of claim 4, wherein the data acquisition module is selectively and integrally mounted with: one or more of a light source, a data processing module and a data display module.
6. The force sensor of claim 4, wherein the data acquisition module is waterproof encapsulated.
7. A robot, comprising: a flexible interactive sensing site, robotic arm or robotic leg, wherein the flexible interactive sensing site comprises a force sensor according to any one of claims 1-6;
the force sensor is connected with the mechanical arm or the mechanical leg.
8. The robot of claim 7, wherein the robotic arm comprises: an industrial robot arm, a cooperative robot arm, an underwater robot arm, or a finger portion of a robot arm;
the mechanical leg comprises: the foot part of the underwater mechanical leg and the foot type robot.
9. The method of applying a force sensor according to any of claims 1-6, wherein the step of applying the method comprises: contacting the flexible interaction module with a target interaction object; the data acquisition module acquires a representation value of the flexible deformation generated by the flexible interaction module; and acquiring the target interaction characteristic corresponding to the flexible deformation based on computer vision and deep learning.
10. The application method of claim 9, wherein a mapping model is obtained by the representation value of the flexible deformation and the target interaction characteristic;
the mapping model is a neural network model;
the mapping model is obtained by collecting training data with labels and through back propagation learning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405021.8A CN114043507B (en) | 2021-11-24 | Force sensor, robot and application method of force sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405021.8A CN114043507B (en) | 2021-11-24 | Force sensor, robot and application method of force sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114043507A true CN114043507A (en) | 2022-02-15 |
| CN114043507B CN114043507B (en) | 2024-05-31 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114659678A (en) * | 2022-04-12 | 2022-06-24 | 深圳市松果体机器人科技有限公司 | Surface-shaped flexible touch sensor |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002182817A (en) * | 2000-12-12 | 2002-06-28 | National Institute Of Advanced Industrial & Technology | Inner force representing device |
| US20080147239A1 (en) * | 2006-12-14 | 2008-06-19 | Industrial Technology Research Institute | Apparatus with Surface Information Displaying and Interaction Capability |
| CN112485140A (en) * | 2020-11-06 | 2021-03-12 | 浙江大学 | Fruit hardness sensor integrated on flexible finger |
| CN112568878A (en) * | 2020-12-09 | 2021-03-30 | 魏培企 | Vision-based pressure sensor, equipment and application method |
| CN113334414A (en) * | 2021-06-21 | 2021-09-03 | 南方科技大学 | Photoelectric touch sensing flexible robot finger and using method thereof |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002182817A (en) * | 2000-12-12 | 2002-06-28 | National Institute Of Advanced Industrial & Technology | Inner force representing device |
| US20080147239A1 (en) * | 2006-12-14 | 2008-06-19 | Industrial Technology Research Institute | Apparatus with Surface Information Displaying and Interaction Capability |
| CN112485140A (en) * | 2020-11-06 | 2021-03-12 | 浙江大学 | Fruit hardness sensor integrated on flexible finger |
| CN112568878A (en) * | 2020-12-09 | 2021-03-30 | 魏培企 | Vision-based pressure sensor, equipment and application method |
| CN113334414A (en) * | 2021-06-21 | 2021-09-03 | 南方科技大学 | Photoelectric touch sensing flexible robot finger and using method thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114659678A (en) * | 2022-04-12 | 2022-06-24 | 深圳市松果体机器人科技有限公司 | Surface-shaped flexible touch sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102183497B1 (en) | Spring type worm gripper for robotic devices | |
| Asfour et al. | ARMAR-III: An integrated humanoid platform for sensory-motor control | |
| Zhou et al. | RML glove—An exoskeleton glove mechanism with haptics feedback | |
| Qu et al. | Recent progress in advanced tactile sensing technologies for soft grippers | |
| Scimeca et al. | Model-free soft-structure reconstruction for proprioception using tactile arrays | |
| US10551923B2 (en) | Haptic glove as a wearable force feedback user interface | |
| CN100372503C (en) | Force feedback data gloves based on pneumatic artificial muscle | |
| McInroe et al. | Towards a soft fingertip with integrated sensing and actuation | |
| Caldwell et al. | Multi-armed dexterous manipulator operation using glove/exoskeleton control and sensory feedback | |
| Paredes-Madrid et al. | Dataglove-based interface for impedance control of manipulators in cooperative human–robot environments | |
| CN114043507B (en) | Force sensor, robot and application method of force sensor | |
| Goryanina et al. | Review of robotic manipulators and identification of the main problems | |
| CN114043507A (en) | Force sensor, robot and application method of force sensor | |
| Heisnam et al. | 20 DOF robotic hand for tele-operation:—Design, simulation, control and accuracy test with leap motion | |
| Collins et al. | Force/torque sensing for soft grippers using an external camera | |
| Deng et al. | Learning-based Object Recognition via a Eutectogel Electronic Skin Enabled Soft Robotic Gripper | |
| CN115089429A (en) | Upper limb rehabilitation training robot, upper limb rehabilitation training system and method | |
| Foroughi et al. | Tactile sensors for robot handling | |
| Vanbrussel et al. | Design and control of a multi-fingered robot hand provided with tactile feedback | |
| KR20150117556A (en) | Apparatus for walk imitation control of biped robot | |
| CN110877335A (en) | Self-adaptive unmarked mechanical arm track tracking method based on hybrid filter | |
| US20230364806A1 (en) | Systems, devices, and methods for a robotic joint | |
| TWI831531B (en) | Method and system of simulating human posture by using robot | |
| CN204064533U (en) | A kind of new six wrist force sensor | |
| Li et al. | Design of Tai-Chi Push-Hands Robot Control System and Construction of Visual Platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |