CN113103227B - Grasping posture acquisition method and grasping posture acquisition system - Google Patents
Grasping posture acquisition method and grasping posture acquisition system Download PDFInfo
- Publication number
- CN113103227B CN113103227B CN202110326746.1A CN202110326746A CN113103227B CN 113103227 B CN113103227 B CN 113103227B CN 202110326746 A CN202110326746 A CN 202110326746A CN 113103227 B CN113103227 B CN 113103227B
- Authority
- CN
- China
- Prior art keywords
- posture
- human hand
- data
- grasping
- gripping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
Abstract
The invention provides a grasping posture acquisition method and a grasping posture acquisition system. The gripping gesture acquisition method provided by the invention comprises the following steps: acquiring position data and posture data of a human hand when the human hand grasps an object when the object is at different positions; establishing a probability model of the gripping posture of the human hand according to the position data and the posture data; and planning the gripping gesture of the manipulator according to the probability model. According to the gripping posture acquisition method provided by the invention, when the object and the hands are at different relative positions, the position data and the posture data of the hands gripping the object are acquired, the probability model is established, and the gripping posture of the manipulator is planned according to the probability model, so that the gripping posture of the manipulator is prevented from being planned blindly, and the efficiency of the manipulator gripping the object is improved.
Description
Technical Field
The invention relates to the technical field of mechanical hand grasping, in particular to a grasping posture acquisition method and a grasping posture acquisition system.
Background
The manipulator plans its gripping posture before applying it to the industrial industry. Present planning scheme is mostly, in computer virtual environment, places the manipulator in object optional position all around, and the finger of manipulator is crooked, and the manipulator removes to the object direction, and when the manipulator contacted the object, the manipulator finger was opened, begins to snatch the object, if the manipulator did not snatch the object, then trades a position and continues to snatch, so repetition test, snatch the object until the manipulator. According to the planning scheme, the setting position of the manipulator is blind, and the grabbing attitude is determined by multiple attempts, so that the grabbing efficiency of the manipulator is low.
Disclosure of Invention
The invention provides a grasping posture acquisition method and a grasping posture acquisition system, which are used for solving the defect of low grasping planning efficiency of a manipulator in the prior art.
The invention provides a grasping posture acquisition method, which comprises the following steps: acquiring position data and posture data of a human hand when the human hand grasps an object when the object is at different positions; establishing a probability model of the gripping posture of the human hand according to the position data and the posture data; and planning the gripping gesture of the manipulator according to the probability model.
According to the grasping posture acquisition method provided by the invention, the step of acquiring the position data and the posture data of the human hand when the human hand grasps the object when the object is at different positions further comprises the following steps: and establishing a three-dimensional space coordinate system and acquiring a three-dimensional coordinate point of each position data.
According to the grasping posture acquisition method provided by the invention, the step of acquiring the position data and the posture data of the human hand when the human hand grasps the object when the object is at different positions further comprises the following steps: the method comprises the steps of obtaining position data and posture data of a human hand when the human hand grasps different objects when the human hand is at different positions.
According to the grasping posture acquisition method provided by the invention, the step of acquiring the position data and the posture data of the human hand when the human hand grasps the object when the object is at different positions further comprises the following steps: the method comprises the steps of obtaining position data and posture data of a human hand when the human hand grips an object when the object rotates by a preset angle.
According to the grasping posture acquisition method provided by the invention, the step of acquiring the position data and the posture data of the human hand when the human hand grasps the object when the object is at different positions further comprises the following steps: and acquiring position data and posture data of the human hand when the human hand grips the object every time the object rotates by 45 degrees.
According to the gripping posture collection method provided by the invention, the step of establishing the probability model of the gripping posture of the human hand according to the position data and the posture data further comprises the following steps: and establishing the probability model according to the three-dimensional coordinate points and the attitude data.
The gripping gesture acquisition method provided by the invention further comprises the following steps: and planning the gripping gesture of the manipulator based on the three-dimensional coordinate points and the gesture data.
The invention also provides a grasping posture collecting system, which comprises: an optical element disposed on a human hand; the optical sensor is used for acquiring the position data and the posture data when the human hand grasps the object; and the processor is used for analyzing the position data and the posture data, establishing the probability model and planning the gripping posture of the manipulator.
The gripping posture acquisition system further comprises a rotating piece for placing an object to be gripped.
According to the gripping posture acquisition method provided by the invention, when the object and the hands are at different relative positions, the position data and the posture data of the hands gripping the object are acquired, the probability model is established, and the gripping posture of the manipulator is planned according to the probability model, so that the gripping posture of the manipulator is prevented from being planned blindly, and the efficiency of the manipulator gripping the object is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a gripping gesture collection method provided by the present invention;
FIG. 2 is a schematic structural diagram of a gripping gesture collection system provided by the present invention;
reference numerals:
10: an optical element; 20: an optical sensor; 30: a processor;
40: a rotating member.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The gripping posture acquisition method and the gripping posture acquisition system of the present invention are described below with reference to fig. 1 and 2.
Although the existing bionic manipulator can better restore the joint freedom degree of the human hand, the existing attempt of simulating the gripping of the human hand still cannot well restore the motion of the human hand. The main reason behind this is the control of the biomimetic manipulator. When the bionic manipulator is complete in structure, the control technology corresponding to the bionic manipulator does not keep pace with the complete structure, and when different objects to be grasped are faced, the grasping posture of the bionic manipulator still has a great improvement space.
The bionic manipulator gripping parameters can be roughly divided into two types, namely related parameters of palms and fingers. The relative parameters of the palm determine the position and the orientation of the palm relative to the object, the relative parameters of the fingers determine the opening and closing degree of each finger joint, and the two parameters have important significance for the grasping posture planning of the bionic manipulator.
The invention provides a grasping posture acquisition method, as shown in fig. 1, the grasping posture acquisition method provided by the embodiment of the invention specifically comprises the following steps:
step 01: the method comprises the steps of obtaining position data and posture data of a human hand when the human hand grasps an object when the object is at different positions.
Specifically, when the object is in the first position, the human hand grasps the object, recording the position and orientation of the human hand when grasping the object. In the present embodiment, the position data refers to a position where the human hand grips the object, and the posture data refers to a relative orientation between the palm of the human hand and the object. After the position data and the posture data of the object at the first position are recorded, the object is rotated to the second position, or the human hand is moved to the second position opposite to the object. To simplify the operation, the object can be rotated each time while the human hand is still. When the human hand grasps the object, the position of the human hand at that time and the relative orientation between the human hand and the object are recorded. And continuing to rotate the object or move the hand, and recording the position data and the posture data of the hand at the position until the object returns to the initial position so as to obtain a plurality of position data and posture data when the object is gripped by the hand in the rotating process.
For example, if the test object is a banana, since the banana is a special-shaped piece, when the banana is in the first position and is held by a human hand, the first position data and the posture data are obtained. After the banana rotates by 45 degrees, the banana is located at the second position, at the moment, the shape of the position of the banana, which is opposite to the hand, is different from the shape of the banana, and when the banana is gripped by the hand, the gripping position and the gripping posture of the banana are also different, so that second position data and posture data are obtained. Accordingly, for every 45 ° rotation of the banana, one position data and attitude data is recorded, and the banana returns to the initial position after rotating 360 °. In the process, the position data and the posture data of a plurality of bananas at different positions can be acquired.
Further, in order to more finely analyze the position data and the posture data when the human hand grasps the object, the rotation angle of the object per time may be turned down to obtain more position data and posture data.
Step 02: establishing a probability model of the gripping posture of the human hand according to the position data and the posture data; step 03: and planning the gripping posture of the manipulator according to the probability model.
Specifically, the acquired position data and posture data record the gripping position and posture of the human hand when one object faces different directions, and the position data and posture data are counted to obtain the frequency of the position data and posture data when the human hand grips the same object, so that a probability model is established. When the gripping of the manipulator is planned, the manipulator can be preferentially arranged at a position with a high probability for gripping according to the probability model.
For example, if a probability model is established by grasping a banana with a human hand, and the human hand is in a position parallel to the horizontal plane and opposite to and perpendicular to the arc-shaped part of the banana, and the frequency of the posture for grasping the banana is high, the manipulator can be set to the grasping posture, and if the manipulator cannot grasp an object in the grasping posture, the manipulator is set to the grasping posture with the second highest frequency for testing.
According to the test results, the probability that the robot grips the object in the gripping posture with high frequency is correspondingly high.
According to the grasping posture collecting method provided by the embodiment of the invention, when the object and the hand are at different relative positions, the position data and the posture data of the hand grasping the object are collected, the probability model is established, and the grasping posture of the manipulator is planned according to the probability model, so that the grasping posture of the manipulator is prevented from being planned blindly, and the efficiency of the manipulator grasping the object is improved.
In one embodiment of the present invention, the step of acquiring position data and posture data of the human hand when the human hand grasps the object while the object is at different positions further comprises: and establishing a three-dimensional space coordinate system and acquiring a three-dimensional coordinate point of the position data.
Specifically, the three-dimensional coordinate points of the position can be acquired in the three-dimensional coordinate system according to the position of the human hand when the human hand grasps the object, the three-dimensional coordinate points of the position of the human hand grasping the object are counted, and a probability model is established to obtain the frequency of each three-dimensional coordinate point in the human hand grasping process when different directions of the object face the human hand.
In one embodiment of the present invention, the step of acquiring position data and posture data of the human hand when the human hand grasps the object while the object is at different positions further comprises: the method comprises the steps of obtaining position data and posture data of a human hand when the human hand grasps an object when different objects are located at different positions.
Specifically, position data and posture data of the human hand when the human hand grasps the object can be acquired for different objects to establish a probability model of the grasping posture of the human hand. The object with different shapes is different from the object when the human hand grasps the object, and the position data and the posture data are different. For example, when a user grasps a banana or an apple, the position data and the posture data of the hand of the user are obviously different, at this time, a probability model for grasping the object can be obtained according to the shape of each object, and then when the manipulator grasps the object, the position and the posture of the manipulator can be obtained, and the probability for grasping the object is higher.
In one embodiment of the present invention, the step of acquiring position data and posture data of the human hand when the human hand grasps the object while the object is at different positions further comprises: and acquiring position data and posture data of the hand grasping the object when the hand rotates by a preset angle.
Specifically, in order to obtain position data and posture data of the grip of the human hand in a plurality of relative positional relationships between the object and the human hand, the object may be rotated by a preset angle each time. Further, the preset angle may be a fixed angle for each rotation, or may be an unfixed angle. If the object to be gripped is an axisymmetric object, the object can be rotated by a fixed angle each time, and the value of the angle of rotation can be larger. For the axisymmetric structure, the difference between the grip position data and the posture data is small at different positions, and the preset angle may be set to a fixed value. Such as 45 at a time.
If the object of grasping is a special-shaped piece, such as a banana, the preset angle can be a variable angle, such as a second position obtained by rotating 15 degrees, a third position obtained by rotating 30 degrees, and the like, so as to obtain position data and posture data of a person's hand grasping the banana in a plurality of positions.
It can be understood that: the preset angle can be set according to the specific shape and the statistical accuracy of the object.
In one embodiment of the present invention, the step of establishing a probabilistic model of the gripping posture of the human hand based on the position data and the posture data further comprises: and establishing a probability model according to the three-dimensional coordinate points and the posture data, and planning the gripping posture of the manipulator based on the three-dimensional coordinate points and the posture data.
Specifically, a plurality of three-dimensional coordinate points and posture data acquired by the same object under different gripping postures are counted, and a probability model is established. For example, when a banana is gripped, the frequency of gripping the banana is high in the range of 0-20 x-axis coordinates, 0-20 y-axis coordinates and 30-50 z-axis coordinates of a hand, the probability that the banana is gripped by the manipulator is high in the spatial coordinate points of 0-20 x-axis coordinates, 0-20 y-axis coordinates and 30-50 z-axis coordinates, and the manipulator can be arranged at the position corresponding to the coordinate points to grip when the gripping posture of the manipulator is planned.
Correspondingly, when grabbing the object that has the arc like the staff, like the banana, can select the outside convex position of gripping banana usually, promptly the position of gripping banana arc back, the probability that the staff was towards arc back gripping this moment is great, when planning the gripping gesture to the manipulator, can set up the manipulator and grasp in the direction that is carried on the back mutually with the banana arc.
As shown in fig. 2, an embodiment of the present invention further provides a grasping posture collecting system, including: an optical element 10, an optical sensor 20 and a processor 30. The optical element 10 is arranged on a human hand, the optical sensor 20 is used for collecting position data and posture data when the human hand grasps an object, and the processor 30 is used for analyzing the position data and the posture data, establishing a probability model and planning the grasping posture of the manipulator.
Specifically, when the human hand grips the object while the object is at the first position, the optical sensor 20 collects position data and posture data when the human hand grips the object. When the object is rotated by a certain angle and located at the second position, the human hand grips the object again, and the optical sensor 20 collects position data and posture data of the human hand gripping the object again. The object continues to rotate, and is located in the third position, the fourth position … … to the nth position in sequence, and the optical sensor 20 collects position data and posture data of N people when holding the object. The processor 30 analyzes the N data, counts the frequency of occurrence of each data in each segment, and establishes a probability model.
For example, if the test object is a banana, since the banana is a special-shaped piece, when the banana is in the first position and is held by a human hand, the first position data and the posture data are obtained. After the banana rotates by 45 degrees, the banana is located at the second position, at the moment, the shape of the position of the banana, which is opposite to the hand, is different from the shape of the banana, and when the banana is gripped by the hand, the gripping position and the gripping posture of the banana are also different, so that second position data and posture data are obtained. Accordingly, for every 45 ° rotation of the banana, one position data and attitude data is recorded, and the banana returns to the initial position after rotating 360 °. In the process, position data and posture data of a plurality of bananas at different positions can be acquired.
When the banana is gripped, the frequency of gripping the banana is high in the ranges of 0-20% of x-axis coordinates, 0-20% of y-axis coordinates and 30-50% of z-axis coordinates of a hand, the probability that the banana is gripped by the manipulator in the spatial coordinate points of 0-20% of x-axis coordinates, 0-20% of y-axis coordinates and 30-50% of z-axis coordinates is high, and when the gripping posture of the manipulator is planned, the manipulator can be arranged at the position corresponding to the coordinate points for gripping.
Correspondingly, when a human hand grasps an object with an arc shape, such as a banana, the position of the banana, which protrudes outwards, of the banana arc-shaped back part can be generally selected to be grasped, the probability that the human hand grasps towards the arc-shaped back part is higher, and when the grasping posture of the manipulator is planned, the manipulator can be arranged in the direction opposite to the banana arc shape to grasp.
According to the grasping posture acquisition system provided by the embodiment of the invention, the optical element, the optical sensor and the processor are arranged, so that the position data and the posture data of the object when the object and the hand grasp the object at different relative positions are acquired, the probability model is established, the grasping posture of the manipulator is planned according to the probability model, the condition that the grasping posture of the manipulator is planned blindly is avoided, and the efficiency of the manipulator grasping the object is improved.
Further, in one embodiment of the present invention, the gripping posture acquiring system further includes a rotating member 40, and the rotating member 40 is used for placing the object to be gripped.
Specifically, for the convenience of the test, an object may be placed on the rotary member 40, and a preset rotation angle may be set according to the shape of the object and the precision required for the test. For example, the position data and the posture data of the object which is held by the human hand once are collected every time the preset rotation is 30 degrees or 45 degrees. Aiming at objects with different shapes, the preset angle can be a fixed angle or a variable angle. If the object to be gripped is an axisymmetric object, the object can be rotated by a fixed angle each time, and the value of the angle of rotation can be larger. For the axisymmetric structure, the difference between the grip position data and the posture data is small at different positions, and the preset angle may be set to a fixed value. Such as 45 at a time.
If the object of grasping is a special-shaped piece, such as a banana, the preset angle can be a variable angle, such as a second position obtained by rotating 15 degrees, a third position obtained by rotating 30 degrees, and the like, so as to obtain position data and posture data of a person's hand grasping the banana in a plurality of positions.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A grasping posture acquiring method is characterized by comprising the following steps:
the method comprises the following steps of acquiring position data and posture data of a human hand when the human hand grasps an object when the object is at different positions, and specifically comprises the following steps:
establishing a three-dimensional space coordinate system, acquiring a three-dimensional coordinate point of each position data, and recording the position and the orientation of a hand when the hand grasps the object when the object is at an initial position;
rotating the object to a plurality of positions until the object is rotated to the initial position, and recording the position and the orientation of the human hand when the human hand grasps the object at each position in the rotating process;
establishing a probability model of the gripping posture of the human hand according to the position data and the posture data;
and planning the gripping gesture of the manipulator according to the probability model.
2. The grasping posture acquiring method according to claim 1, wherein the step of acquiring position data and posture data of the human hand grasping the object when the human hand is at different positions further comprises:
the method comprises the steps of obtaining position data and posture data of a human hand when the human hand grasps different objects when the human hand is at different positions.
3. The grasping posture acquiring method according to claim 2, wherein the step of acquiring position data and posture data of the human hand grasping the object when the human hand is at different positions further comprises:
and acquiring position data and posture data of the hand when the hand grips the object when the object rotates by a preset angle.
4. The grasping posture acquiring method according to claim 3, wherein the step of acquiring position data and posture data of the human hand grasping the object when the human hand is at different positions further comprises:
and acquiring position data and posture data of the human hand when the human hand grips the object every time the object rotates by 45 degrees.
5. The method according to claim 1, wherein the step of establishing a probability model of the human hand gripping posture based on the position data and the posture data further comprises:
and establishing the probability model according to the three-dimensional coordinate points and the attitude data.
6. The grip posture acquisition method according to claim 5, further comprising:
and planning the gripping gesture of the manipulator based on the three-dimensional coordinate points and the gesture data.
7. A grip posture acquisition system that executes the grip posture acquisition method according to any one of claims 1 to 6, characterized by comprising:
an optical element disposed on a human hand;
the optical sensor is used for acquiring the position data and the posture data when the human hand grasps the object;
and the processor is used for analyzing the position data and the posture data, establishing the probability model and planning the gripping posture of the manipulator.
8. The grip posture acquiring system according to claim 7, further comprising a rotating member for placing an object to be gripped.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110326746.1A CN113103227B (en) | 2021-03-26 | 2021-03-26 | Grasping posture acquisition method and grasping posture acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110326746.1A CN113103227B (en) | 2021-03-26 | 2021-03-26 | Grasping posture acquisition method and grasping posture acquisition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113103227A CN113103227A (en) | 2021-07-13 |
| CN113103227B true CN113103227B (en) | 2022-12-02 |
Family
ID=76712498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110326746.1A Active CN113103227B (en) | 2021-03-26 | 2021-03-26 | Grasping posture acquisition method and grasping posture acquisition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113103227B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9014857B2 (en) * | 2012-01-13 | 2015-04-21 | Toyota Motor Engineering & Manufacturing North America, Inc. | Methods and computer-program products for generating grasp patterns for use by a robot |
| US9095978B2 (en) * | 2012-12-07 | 2015-08-04 | GM Global Technology Operations LLC | Planning a grasp approach, position, and pre-grasp pose for a robotic grasper based on object, grasper, and environmental constraint data |
| US9321176B1 (en) * | 2014-04-01 | 2016-04-26 | University Of South Florida | Systems and methods for planning a robot grasp based upon a demonstrated grasp |
| CN106078748B (en) * | 2016-06-13 | 2018-09-14 | 北京理工大学 | A kind of control method of the robot crawl object based on hand, eye, arm coordinated manipulation |
| US11097418B2 (en) * | 2018-01-04 | 2021-08-24 | X Development Llc | Grasping of an object by a robot based on grasp strategy determined using machine learning model(s) |
| JP7044047B2 (en) * | 2018-12-14 | 2022-03-30 | トヨタ自動車株式会社 | robot |
| CN111251277B (en) * | 2020-01-31 | 2021-09-03 | 武汉大学 | Human-computer collaboration tool submission system and method based on teaching learning |
| CN112297013B (en) * | 2020-11-11 | 2022-02-18 | 浙江大学 | Robot intelligent grabbing method based on digital twin and deep neural network |
| CN112257293A (en) * | 2020-11-16 | 2021-01-22 | 江苏科技大学 | Non-standard object grabbing method and device based on ROS |
-
2021
- 2021-03-26 CN CN202110326746.1A patent/CN113103227B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113103227A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kang et al. | Toward automatic robot instruction from perception-temporal segmentation of tasks from human hand motion | |
| CN108268129B (en) | Method and apparatus for calibrating a plurality of sensors on a motion capture glove and motion capture glove | |
| Kang et al. | Toward automatic robot instruction from perception-mapping human grasps to manipulator grasps | |
| Weisz et al. | Pose error robust grasping from contact wrench space metrics | |
| US9649764B1 (en) | Systems and methods for planning a robot grasp that can withstand task disturbances | |
| Liarokapis et al. | Functional anthropomorphism for human to robot motion mapping | |
| WO2020190166A1 (en) | Method and system for grasping an object by means of a robotic device | |
| Vahrenkamp et al. | Bimanual grasp planning | |
| Kang et al. | Determination of motion breakpoints in a task sequence from human hand motion | |
| Wang et al. | Joining force of human muscular task planning with robot robust and delicate manipulation for programming by demonstration | |
| CN113103227B (en) | Grasping posture acquisition method and grasping posture acquisition system | |
| Kang et al. | Grasp recognition and manipulative motion characterization from human hand motion sequences | |
| Roa et al. | Graspability map: A tool for evaluating grasp capabilities | |
| Romero et al. | Modeling and evaluation of human-to-robot mapping of grasps | |
| Culleton et al. | Framework for assessing robotic dexterity within flexible manufacturing | |
| Vaughan et al. | Modeling reaching and manipulating in 2-and 3-D workspaces: The posture-based model | |
| CN115635482A (en) | Vision-based robot-to-human body transfer method, device, medium and terminal | |
| CN113561172B (en) | Dexterous hand control method and device based on binocular vision acquisition | |
| Frisoli et al. | Mechanical design of a haptic interface for the hand | |
| Scharfe et al. | Hybrid physics simulation of multi-fingered hands for dexterous in-hand manipulation | |
| CN113450903A (en) | Human body action mapping method and device, computer equipment and storage medium | |
| Caccavale et al. | Kinematic control with force feedback for a redundant bimanual manipulation system | |
| CN110877335A (en) | Self-adaptive unmarked mechanical arm track tracking method based on hybrid filter | |
| Xinyu et al. | Research on robot dexterous grasping for aerospace product parts | |
| CN111002295A (en) | Teaching glove and teaching system of two-finger grabbing robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |