CN117961879A - Mechanical arm motion control method, device, equipment and readable storage medium - Google Patents
Mechanical arm motion control method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN117961879A CN117961879A CN202311377138.9A CN202311377138A CN117961879A CN 117961879 A CN117961879 A CN 117961879A CN 202311377138 A CN202311377138 A CN 202311377138A CN 117961879 A CN117961879 A CN 117961879A
- Authority
- CN
- China
- Prior art keywords
- pose
- mechanical arm
- task
- target
- target pose
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims description 42
- 238000003062 neural network model Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000002787 reinforcement Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Landscapes
- Manipulator (AREA)
Abstract
The application discloses a mechanical arm motion control method, a device, equipment and a readable storage medium, wherein when a mechanical arm cannot finish a task to be executed based on a first target pose under a scene with low precision requirements on the mechanical arm pose, a second target pose can be obtained by adjusting the first target pose, so that the mechanical arm can finish the task to be executed based on the second target pose, and therefore, the task execution success rate of the mechanical arm under the scene with low precision requirements on the mechanical arm pose can be effectively improved.
Description
Technical Field
The present application relates to the field of mechanical arm technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for controlling movement of a mechanical arm.
Background
A robotic arm is a robotic system capable of simulating the motion of a human arm. The existing mechanical arm motion control scheme is that a user gives a target pose, a motion control system of the mechanical arm calculates joint positions according to the target pose, the mechanical arm is controlled to move to the target pose based on the joint positions, but the joint positions calculated by the motion control system of the mechanical arm according to the target pose often exceed the working space of the mechanical arm or are in a singular section of the mechanical arm, and in this case, the mechanical arm cannot be successfully controlled to move to the target pose based on the joint positions, so that task failure is caused.
Under some structured application scenes (such as scenes in the fields of industrial production lines, medical operations, space exploration and the like), the precision requirement on the pose of the mechanical arm is extremely high, and task failure can be caused by the deviation of the pose of the mechanical arm, so that under the scenes, the task execution success rate of the mechanical arm can be ensured by adopting the existing mechanical arm motion control scheme. However, as the mechanical arm technologies in different fields are gradually mature, application scenes of the mechanical arm are gradually expanded, a plurality of unstructured application scenes (such as scenes in the fields of families, services, agriculture and the like) are generated, under the application scenes, the precision requirement on the pose of the mechanical arm is low, and the task can still be completed due to a certain deviation of the pose of the mechanical arm, so that under the scenes, if the conventional mechanical arm motion control scheme is adopted, the task execution success rate of the mechanical arm cannot meet the requirement of the scene.
Therefore, how to provide a method for controlling the motion of the mechanical arm so as to improve the success rate of task execution of the mechanical arm in a scene with low requirements on the precision of the pose of the mechanical arm becomes a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above problems, the present application provides a method, an apparatus, a device, and a readable storage medium for controlling movement of a mechanical arm, so as to improve the success rate of task execution of the mechanical arm in unstructured application scenarios.
The specific scheme is as follows:
a method of robotic arm motion control, the method comprising:
Acquiring a task to be executed, wherein the task to be executed is used for indicating the mechanical arm to move to a first target pose;
judging whether the task to be executed can be completed based on the first target pose;
If the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose in pose, and the task to be executed can be completed based on the second target pose;
And controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
Optionally, the determining whether the task to be performed can be completed based on the first target pose includes:
calculating joint positions of the mechanical arm based on the first target pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the first target pose.
Optionally, the adjusting the first target pose, determining a second target pose, includes:
Adjusting the first target pose to obtain an adjusted pose;
Judging whether the task to be executed can be completed based on the adjusted pose;
If the task to be executed can be completed based on the adjusted pose, determining that the adjusted pose is the second target pose;
and if the task to be executed cannot be completed based on the adjusted pose, determining that a second target pose does not exist.
Optionally, the adjusting the first target pose to obtain an adjusted pose includes:
acquiring parameters of the mechanical arm;
and adjusting the first target pose based on the parameters of the mechanical arm to obtain the adjusted pose.
Optionally, the adjusting the first target pose based on the parameters of the mechanical arm to obtain an adjusted pose includes:
Inputting parameters of the mechanical arm and the first target pose into a pose adjustment model, and outputting the adjusted pose by the pose adjustment model;
The pose adjustment model is obtained by training a preset neural network model by taking training poses and parameters of the training mechanical arm as inputs and adopting a reinforcement learning mode, and a reward function in the training process is obtained by calculating the difference between the adjusted poses and corresponding training poses when the training mechanical arm is successfully moved based on the probability that the adjusted poses output by the preset neural network model enable the training mechanical arm to successfully move and the adjusted poses output by the preset neural network model.
Optionally, the determining whether the task to be performed can be completed based on the adjusted pose includes:
Calculating the joint position of the mechanical arm based on the adjusted pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
and if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the adjusted pose.
Optionally, after the determining that the second target pose does not exist, the method further comprises:
and generating prompt information, wherein the prompt information is used for prompting that the task to be executed cannot be executed.
A robotic arm motion control device, the device comprising:
The system comprises a task to be executed acquisition unit, a first target pose detection unit and a second target pose detection unit, wherein the task to be executed acquisition unit is used for acquiring a task to be executed, and the task to be executed is used for indicating the mechanical arm to move to the first target pose;
The first judging unit is used for judging whether the task to be executed can be completed based on the first target pose;
A second target pose determining unit, configured to adjust the first target pose if the task to be performed cannot be completed based on the first target pose, determine a second target pose, where the second target pose is the same as the first target pose in position and different in pose, and the task to be performed can be completed based on the second target pose;
And the motion control unit is used for controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
Optionally, the first judging unit is specifically configured to:
calculating joint positions of the mechanical arm based on the first target pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the first target pose.
Optionally, the second target pose determining unit includes:
the adjusting unit is used for adjusting the first target pose to obtain an adjusted pose;
The second judging unit is used for judging whether the task to be executed can be completed based on the adjusted pose;
The processing unit is used for determining that the adjusted pose is the second target pose if the task to be executed can be completed based on the adjusted pose; and if the task to be executed cannot be completed based on the adjusted pose, determining that a second target pose does not exist.
Optionally, the adjusting unit includes:
the parameter acquisition unit of the mechanical arm is used for acquiring parameters of the mechanical arm;
and the adjustment subunit is used for adjusting the first target pose based on the parameters of the mechanical arm to obtain the adjusted pose.
Optionally, the adjusting subunit is specifically configured to:
Inputting parameters of the mechanical arm and the first target pose into a pose adjustment model, and outputting the adjusted pose by the pose adjustment model;
The pose adjustment model is obtained by training a preset neural network model by taking training poses and parameters of the training mechanical arm as inputs and adopting a reinforcement learning mode, and a reward function in the training process is obtained by calculating the difference between the adjusted poses and corresponding training poses when the training mechanical arm is successfully moved based on the probability that the adjusted poses output by the preset neural network model enable the training mechanical arm to successfully move and the adjusted poses output by the preset neural network model.
Optionally, the second judging unit is specifically configured to:
Calculating the joint position of the mechanical arm based on the adjusted pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
and if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the adjusted pose.
Optionally, the apparatus further comprises:
and the prompting unit is used for generating prompting information after the second target pose does not exist, wherein the prompting information is used for prompting that the task to be executed cannot be executed.
A mechanical arm movement control device comprises a memory and a processor;
The memory is used for storing programs;
The processor is configured to execute the program to implement the steps of the mechanical arm motion control method described above.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a robotic arm motion control method as described above.
By means of the technical scheme, the application discloses a mechanical arm movement control method, a device, equipment and a readable storage medium, wherein after a task to be executed for indicating the mechanical arm to move to a first target pose is acquired, whether the task to be executed can be completed based on the first target pose is judged; if the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose, and the task to be executed can be completed based on the second target pose; and finally, controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed. Based on the scheme, when the mechanical arm cannot finish the task to be executed based on the first target pose under the scene with lower precision requirement on the mechanical arm pose, the first target pose can be adjusted to obtain the second target pose, so that the mechanical arm can finish the task to be executed based on the second target pose, and the task execution success rate of the mechanical arm under the scene with lower precision requirement on the mechanical arm pose can be effectively improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 is a schematic flow chart of a method for controlling movement of a mechanical arm according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for determining whether a task to be executed can be completed based on a first target pose according to an embodiment of the present application;
FIG. 3 is a flow chart of a method for adjusting a first target pose and determining a second target pose according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a mechanical arm motion control device according to an embodiment of the present application;
Fig. 5 is a hardware structure block diagram of a mechanical arm motion control device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Next, the method for controlling the movement of the mechanical arm provided by the present application will be described by the following embodiments.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for controlling movement of a mechanical arm according to an embodiment of the present application, where the method may include:
step S101: and acquiring a task to be executed, wherein the task to be executed is used for indicating the mechanical arm to move to the first target pose.
In the application, a task to be executed refers to a task to be executed of a mechanical arm, and the task to be executed is used for indicating the mechanical arm to move to a first target pose. As an alternative, the first target pose may be a pose in cartesian space.
Step S102: judging whether the task to be executed can be completed based on the first target pose, and executing step S103 and step S104 if the task to be executed cannot be completed based on the first target pose; if the task to be performed can be completed based on the first target pose, step S105 is performed.
The mechanical arm comprises a plurality of joints, the reachable area of each joint of the mechanical arm is restrained by the working area of the mechanical arm, if one joint position exceeds the working area of the mechanical arm, the joint of the mechanical arm cannot reach the joint position, so that movement failure is caused, in addition, because the mechanical arm is controlled by a controller, but a real physical component moves, the physical component cannot realize infinite angular velocity rotation, and if the controller commands a certain joint of the mechanical arm to rotate 180 degrees at infinite angular velocity, singular points can appear on the joint of the mechanical arm, so that movement failure is caused. Therefore, in the application, whether the task to be executed can be based on the first target pose can be judged by judging whether each joint position exceeds the working space of the mechanical arm or whether a singular point appears in the process of moving the mechanical arm to the first target pose.
Step S103: and adjusting the first target pose and determining a second target pose.
In the application, the second target pose is the same as the first target pose in position and different in pose, and the task to be executed can be completed based on the second target pose.
In the present application, the pose includes a position and a posture. As an implementation manner, the position of the first target pose may be kept unchanged, and the pose of the first target pose may be adjusted to obtain the second target pose.
Step S104: and controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
Step S105: and controlling the mechanical arm to move based on the first target pose so as to complete the task to be executed.
The application discloses a mechanical arm movement control method, which comprises the steps of firstly judging whether a task to be executed can be completed based on a first target pose after acquiring the task to be executed for indicating the mechanical arm to move to the first target pose; if the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose, and the task to be executed can be completed based on the second target pose; and finally, controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed. Based on the scheme, when the mechanical arm cannot finish the task to be executed based on the first target pose under the scene with lower precision requirement on the mechanical arm pose, the first target pose can be adjusted to obtain the second target pose, so that the mechanical arm can finish the task to be executed based on the second target pose, and the task execution success rate of the mechanical arm under the scene with lower precision requirement on the mechanical arm pose can be effectively improved.
In another embodiment of the present application, describing a specific implementation manner of determining whether the task to be performed can be completed based on the first target pose in step S102, referring to fig. 2, fig. 2 is a schematic flow chart of a method for determining whether the task to be performed can be completed based on the first target pose according to an embodiment of the present application, where the method may include:
step S201: and calculating the joint position of the mechanical arm based on the first target pose.
In the present application, the joint position of the mechanical arm may be calculated based on the first target pose by using inverse kinematics of a conventional mechanical arm, for example, the joint position of the mechanical arm may be calculated based on the first target pose by using a closed resolution method or a numerical approximation method, and considering that the numerical approximation method may be general for mechanical arms with different parameters, as an implementation manner, in the present application, the joint position of the mechanical arm may be calculated based on the first target pose by using a numerical approximation method.
Step S202: judging whether a target joint position exists in the joint positions of the mechanical arm, if the target joint position exists in the joint positions of the mechanical arm, executing step S203, and if the target joint position does not exist in the joint positions of the mechanical arm, executing step S204.
In the application, the target joint position is a joint position beyond the working section of the mechanical arm, or a joint position with a singular point;
Step S203: determining that the task to be performed cannot be completed based on the first target pose.
Step S204: and determining that the task to be executed can be completed based on the first target pose.
In this embodiment, if one or more joint positions exceed the working space of the mechanical arm during the movement of the mechanical arm to the first target pose, and/or if one or more joint positions have singular points, it is determined that the task to be performed cannot be completed based on the first target pose of the mechanical arm, and if each joint position does not exceed the working space of the mechanical arm during the movement of the mechanical arm to the first target pose, and no singular point occurs at each joint position, it is determined that the task to be performed can be completed based on the first target pose of the mechanical arm.
In another embodiment of the present application, a specific implementation manner of adjusting the first target pose and determining the second target pose in step S103 is described, and referring to fig. 3, fig. 3 is a schematic flow chart of a method for adjusting the first target pose and determining the second target pose according to an embodiment of the present application, where the method may include:
Step S301: and adjusting the first target pose to obtain the adjusted pose.
As an implementation manner, the adjusting the first target pose to obtain the adjusted pose includes: acquiring parameters of the mechanical arm; and adjusting the first target pose based on the parameters of the mechanical arm to obtain the adjusted pose.
The parameters of the mechanical arm include DH (Denavit Hartenberg) parameters (also referred to as four parameters), joint limiting parameters, and the like, and the application is not limited in any way.
As an embodiment, in the present application, parameters of the training pose and the training mechanical arm may be used as input, and a preset neural network model may be trained by reinforcement learning to obtain a pose adjustment model.
The training pose is a pose that causes the training robot arm to fail to move. In the training process, the training poses are poses which are generated randomly, so that the training mechanical arm fails to move. Randomly generated poses if the training mechanical arm is successfully moved, the poses are not used for training of the pose adjustment model.
In the present application, any reinforcement learning method such as PPO (Proximal Policy Optimization, near-end policy optimization) algorithm, SAC (Soft Actor-Critic) algorithm, muZero algorithm, etc. may be used, and the present application is not limited in any way.
In addition, the training model adopting the reinforcement learning mode relates to a reward function, and in the training process of the pose adjustment model, the reward function is calculated based on the probability that the adjusted pose output by the preset neural network model enables the mechanical arm for training to successfully move and the difference between the adjusted pose and the corresponding pose for training when the adjusted pose output by the preset neural network model enables the mechanical arm for training to successfully move. The reward function can be designed in combination with task requirements, for example, under the task of determining a limiting range for the gesture quaternion, the +_ -norm of the gesture quaternion difference before and after adjustment can be calculated, and the success rate is taken as the reward only if the norm is within the limiting range and the calculated pose is reachable.
Based on the above pose adjustment model, as an implementation manner, the adjusting the first target pose based on the parameters of the mechanical arm to obtain an adjusted pose includes: and inputting the parameters of the mechanical arm and the first target pose into a pose adjustment model, and outputting the adjusted pose by the pose adjustment model.
Step S302: and judging whether the task to be executed can be completed based on the adjusted pose, if so, executing step S303, and if not, executing step S304.
It should be noted that, the specific implementation manner of determining whether the task to be executed can be completed based on the adjusted pose may be the same as the specific implementation manner of determining whether the task to be executed can be completed based on the first target pose, and the principle is the same.
Then, as an implementation manner, the determining whether the task to be performed can be completed based on the adjusted pose includes: and calculating the joint position of the mechanical arm based on the adjusted pose. Judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point; and if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the adjusted pose. And if the target joint position does not exist in the joint positions of the mechanical arm, determining that the task to be executed can be completed based on the adjusted pose.
In the present application, the joint position of the mechanical arm may be calculated based on the adjusted pose by using inverse kinematics of a conventional mechanical arm, for example, the joint position of the mechanical arm may be calculated based on the adjusted pose by using a closed analysis method or a numerical approximation method, and considering that the numerical approximation method may be general for mechanical arms with different parameters, as an implementation manner, in the present application, the joint position of the mechanical arm may be calculated based on the adjusted pose by using a numerical approximation method.
In this embodiment, if one or more joint positions exceed the working space of the mechanical arm during the movement of the mechanical arm to the adjusted pose, and/or if one or more joint positions have singular points, it is determined that the task to be performed cannot be completed based on the adjusted pose of the mechanical arm, if each joint position does not exceed the working space of the mechanical arm during the movement of the mechanical arm to the adjusted pose, and no singular point occurs at each joint position, it is determined that the task to be performed can be completed based on the adjusted pose of the mechanical arm.
Step S303: determining the adjusted pose as the second target pose;
Step S304: it is determined that the second target pose is not present.
In the present application, after the determining that the second target pose does not exist, the method further includes: and generating prompt information, wherein the prompt information is used for prompting that the task to be executed cannot be executed.
The following describes a motion control device for a mechanical arm disclosed in an embodiment of the present application, and the motion control device for a mechanical arm described below and the motion control method for a mechanical arm described above may be referred to correspondingly.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a mechanical arm motion control device according to an embodiment of the present application. As shown in fig. 4, the robot arm movement control device may include:
The task to be executed acquiring unit 11 is configured to acquire a task to be executed, where the task to be executed is used to instruct the mechanical arm to move to the first target pose;
a first judging unit 12, configured to judge whether the task to be executed can be completed based on the first target pose;
a second target pose determining unit 13, configured to adjust the first target pose if the task to be performed cannot be completed based on the first target pose, determine a second target pose, where the second target pose is the same as the first target pose in position and different in pose, and the task to be performed can be completed based on the second target pose;
and a motion control unit 14, configured to control the motion of the mechanical arm based on the second target pose so as to complete the task to be performed.
As an embodiment, the first determining unit is specifically configured to:
calculating joint positions of the mechanical arm based on the first target pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the first target pose.
As an embodiment, the second target pose determining unit includes:
the adjusting unit is used for adjusting the first target pose to obtain an adjusted pose;
The second judging unit is used for judging whether the task to be executed can be completed based on the adjusted pose;
The processing unit is used for determining that the adjusted pose is the second target pose if the task to be executed can be completed based on the adjusted pose; and if the task to be executed cannot be completed based on the adjusted pose, determining that a second target pose does not exist.
As an embodiment, the adjusting unit includes:
the parameter acquisition unit of the mechanical arm is used for acquiring parameters of the mechanical arm;
and the adjustment subunit is used for adjusting the first target pose based on the parameters of the mechanical arm to obtain the adjusted pose.
As an embodiment, the adjusting subunit is specifically configured to:
Inputting parameters of the mechanical arm and the first target pose into a pose adjustment model, and outputting the adjusted pose by the pose adjustment model;
The pose adjustment model is obtained by training a preset neural network model by taking training poses and parameters of the training mechanical arm as inputs and adopting a reinforcement learning mode, and a reward function in the training process is obtained by calculating the difference between the adjusted poses and corresponding training poses when the training mechanical arm is successfully moved based on the probability that the adjusted poses output by the preset neural network model enable the training mechanical arm to successfully move and the adjusted poses output by the preset neural network model.
As an embodiment, the second determining unit is specifically configured to:
Calculating the joint position of the mechanical arm based on the adjusted pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
and if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the adjusted pose.
As an embodiment, the apparatus further comprises:
and the prompting unit is used for generating prompting information after the second target pose does not exist, wherein the prompting information is used for prompting that the task to be executed cannot be executed.
Referring to fig. 5, fig. 5 is a block diagram of a hardware structure of a motion control device for a mechanical arm according to an embodiment of the present application, and referring to fig. 5, the hardware structure of motion control for a mechanical arm may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete the communication with each other through the communication bus 4;
The processor 1 may be a central processing unit CPU, or an Application-specific integrated Circuit ASIC (Application SPECIFIC INTEGRATED Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, etc.;
The memory 3 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory) or the like, such as at least one magnetic disk memory;
wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
Acquiring a task to be executed, wherein the task to be executed is used for indicating the mechanical arm to move to a first target pose;
judging whether the task to be executed can be completed based on the first target pose;
If the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose in pose, and the task to be executed can be completed based on the second target pose;
And controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the present application also provides a readable storage medium storing a program adapted to be executed by a processor, the program being configured to:
Acquiring a task to be executed, wherein the task to be executed is used for indicating the mechanical arm to move to a first target pose;
judging whether the task to be executed can be completed based on the first target pose;
If the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose in pose, and the task to be executed can be completed based on the second target pose;
And controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for controlling movement of a robotic arm, the method comprising:
Acquiring a task to be executed, wherein the task to be executed is used for indicating the mechanical arm to move to a first target pose;
judging whether the task to be executed can be completed based on the first target pose;
If the task to be executed cannot be completed based on the first target pose, the first target pose is adjusted, a second target pose is determined, the second target pose is the same as the first target pose in position and different from the first target pose in pose, and the task to be executed can be completed based on the second target pose;
And controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
2. The method of claim 1, wherein the determining whether the task to be performed can be completed based on the first target pose comprises:
calculating joint positions of the mechanical arm based on the first target pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the first target pose.
3. The method of claim 1, wherein said adjusting the first target pose to determine a second target pose comprises:
Adjusting the first target pose to obtain an adjusted pose;
Judging whether the task to be executed can be completed based on the adjusted pose;
If the task to be executed can be completed based on the adjusted pose, determining that the adjusted pose is the second target pose;
and if the task to be executed cannot be completed based on the adjusted pose, determining that a second target pose does not exist.
4. A method according to claim 3, wherein said adjusting the first target pose to obtain an adjusted pose comprises:
acquiring parameters of the mechanical arm;
and adjusting the first target pose based on the parameters of the mechanical arm to obtain the adjusted pose.
5. The method of claim 4, wherein adjusting the first target pose based on the parameters of the robotic arm results in an adjusted pose, comprising:
Inputting parameters of the mechanical arm and the first target pose into a pose adjustment model, and outputting the adjusted pose by the pose adjustment model;
The pose adjustment model is obtained by training a preset neural network model by taking training poses and parameters of the training mechanical arm as inputs and adopting a reinforcement learning mode, and a reward function in the training process is obtained by calculating the difference between the adjusted poses and corresponding training poses when the training mechanical arm is successfully moved based on the probability that the adjusted poses output by the preset neural network model enable the training mechanical arm to successfully move and the adjusted poses output by the preset neural network model.
6. The method of claim 1, wherein the determining whether the task to be performed can be completed based on the adjusted pose comprises:
Calculating the joint position of the mechanical arm based on the adjusted pose;
judging whether a target joint position exists in the joint positions of the mechanical arm, wherein the target joint position is a joint position exceeding a working interval of the mechanical arm or a joint position with a singular point;
and if the target joint position exists in the joint positions of the mechanical arm, determining that the task to be executed cannot be completed based on the adjusted pose.
7. A method according to claim 3, wherein after said determining that there is no second target pose, the method further comprises:
and generating prompt information, wherein the prompt information is used for prompting that the task to be executed cannot be executed.
8. A robotic arm motion control device, the device comprising:
The system comprises a task to be executed acquisition unit, a first target pose detection unit and a second target pose detection unit, wherein the task to be executed acquisition unit is used for acquiring a task to be executed, and the task to be executed is used for indicating the mechanical arm to move to the first target pose;
The first judging unit is used for judging whether the task to be executed can be completed based on the first target pose;
A second target pose determining unit, configured to adjust the first target pose if the task to be performed cannot be completed based on the first target pose, determine a second target pose, where the second target pose is the same as the first target pose in position and different in pose, and the task to be performed can be completed based on the second target pose;
And the motion control unit is used for controlling the mechanical arm to move based on the second target pose so as to complete the task to be executed.
9. A mechanical arm motion control device, comprising a memory and a processor;
The memory is used for storing programs;
the processor is configured to execute the program to implement the respective steps of the robot arm motion control method according to any one of claims 1 to 7.
10. A readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the respective steps of the robot arm motion control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311377138.9A CN117961879A (en) | 2023-10-23 | 2023-10-23 | Mechanical arm motion control method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311377138.9A CN117961879A (en) | 2023-10-23 | 2023-10-23 | Mechanical arm motion control method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117961879A true CN117961879A (en) | 2024-05-03 |
Family
ID=90860460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311377138.9A Pending CN117961879A (en) | 2023-10-23 | 2023-10-23 | Mechanical arm motion control method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117961879A (en) |
-
2023
- 2023-10-23 CN CN202311377138.9A patent/CN117961879A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5261495B2 (en) | Real-time self-collision and obstacle avoidance using weight matrix | |
| WO2022088593A1 (en) | Robotic arm control method and device, and human-machine cooperation model training method | |
| US11235461B2 (en) | Controller and machine learning device | |
| US9387589B2 (en) | Visual debugging of robotic tasks | |
| JP5750657B2 (en) | Reinforcement learning device, control device, and reinforcement learning method | |
| Saveriano et al. | Incremental kinesthetic teaching of end-effector and null-space motion primitives | |
| JP5225720B2 (en) | Apparatus and method for generating and controlling robot motion | |
| JP7324932B2 (en) | dynamic planning controller | |
| JP5156836B2 (en) | Real-time self-collision and obstacle avoidance | |
| Lee et al. | Incremental motion primitive learning by physical coaching using impedance control | |
| US11759947B2 (en) | Method for controlling a robot device and robot device controller | |
| Romano et al. | The codyco project achievements and beyond: Toward human aware whole-body controllers for physical human robot interaction | |
| Nemec et al. | Speed adaptation for self-improvement of skills learned from user demonstrations | |
| CN114529010A (en) | Robot autonomous learning method, device, equipment and storage medium | |
| CN110147891B (en) | Method and device applied to reinforcement learning training process and electronic equipment | |
| CN113290553A (en) | Trajectory generation device, multi-link system, and trajectory generation method | |
| CN117961879A (en) | Mechanical arm motion control method, device, equipment and readable storage medium | |
| CN114502338A (en) | Techniques for generating controllers for robots | |
| CN111984000A (en) | Method and device for automatically influencing an actuator | |
| CN110114195B (en) | Action transfer device, action transfer method, and non-transitory computer-readable medium storing action transfer program | |
| WO2022172812A1 (en) | Robot model learning device, robot model machine learning method, robot model machine learning program, robot control device, robot control method, and robot control program | |
| KR102281119B1 (en) | Method for controlling 7-axis robot using reinforcement learning | |
| CN114571463B (en) | Motion detection method and device, readable storage medium and electronic equipment | |
| Liu et al. | Deep deterministic policy gradient with constraints for gait optimisation of biped robots | |
| US20240054393A1 (en) | Learning Device, Learning Method, Recording Medium Storing Learning Program, Control Program, Control Device, Control Method, and Recording Medium Storing Control Program |
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 |