CN109857110A - Motion planning method, device, equipment and computer readable storage medium - Google Patents

Motion planning method, device, equipment and computer readable storage medium Download PDF

Info

Publication number
CN109857110A
CN109857110A CN201910112554.3A CN201910112554A CN109857110A CN 109857110 A CN109857110 A CN 109857110A CN 201910112554 A CN201910112554 A CN 201910112554A CN 109857110 A CN109857110 A CN 109857110A
Authority
CN
China
Prior art keywords
state
motion
determining
axis
target
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
Application number
CN201910112554.3A
Other languages
Chinese (zh)
Inventor
杨开红
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Shiyuan Electronics Thecnology Co Ltd
Original Assignee
Guangzhou Shiyuan Electronics Thecnology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Shiyuan Electronics Thecnology Co Ltd filed Critical Guangzhou Shiyuan Electronics Thecnology Co Ltd
Priority to CN201910112554.3A priority Critical patent/CN109857110A/en
Publication of CN109857110A publication Critical patent/CN109857110A/en
Pending legal-status Critical Current

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present disclosure provides a motion planning method, apparatus, device and computer-readable storage medium. The motion planning method, the motion planning device, the motion planning equipment and the computer readable storage medium provided by the disclosure initialize a current path first, and then reasonably judge the path, if the path comprises an unreasonable motion state, obstacle avoidance increment corresponding to the unreasonable motion state can be calculated, so that the unreasonable state is updated according to the obstacle avoidance increment, the planned motion path is updated, and then the new path is repeatedly and reasonably judged, a reasonable and fully continuous motion path can be obtained, and the motion path can be used for guiding a motion part to move, thereby solving the problem that the mechanical arm motion planning method in the prior art is not high in practicability.

Description

Motion planning method, device, equipment and computer readable storage medium
Technical Field
The present disclosure relates to exercise planning technologies, and in particular, to an exercise planning method, apparatus, device, and computer-readable storage medium.
Background
Motion Planning (Motion Planning) determines a path between given positions that meets a constraint. This constraint may be collision-free, shortest path, minimal mechanical work, etc.
The current commonly used motion planning methods are an artificial potential field method and an a-matrix algorithm based on heuristic search. The path planned by applying the artificial potential field method is generally smooth and safe. One problem with this approach, which requires rasterization of the space, is how to select the step size for each grid to be considered as the step size for the robotic arm to move. If the step size is too large, that is, the spatial resolution is low, many repeated meaningless calculations are generated, and the application and efficiency of path planning are increased; if the step length is too small, that is, the spatial resolution is high, the trajectory of the mechanical arm cannot be calculated easily in the path planning process.
Therefore, the mechanical arm motion planning method in the prior art is not high in practicability.
Disclosure of Invention
The present disclosure provides a motion planning method, device, apparatus, and computer-readable storage medium to solve the problem of low practicability of a mechanical arm motion planning method in the prior art.
A first aspect of the present disclosure is to provide an exercise planning method, including:
determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform;
dividing the current path according to the number of preset path points to obtain a motion state with time information;
judging whether the motion state accords with a rationality rule or not;
if not, determining the obstacle avoidance increment corresponding to the unreasonable state;
determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path;
and continuing to execute the step of judging whether the motion state is reasonable or not according to the updated motion state.
Another aspect of the present disclosure is to provide an exercise planning apparatus, including:
the first determining module is used for determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform;
the segmentation module is used for segmenting the current path according to the number of preset path points to obtain a motion state with time information;
the judging module is used for judging whether the motion state accords with a rationality rule or not;
if not, the second determination module determines the obstacle avoidance increment corresponding to the unreasonable state;
the updating module is used for determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path;
and the judging module continues to execute the step of judging whether the motion state is reasonable or not according to the updated motion state.
Yet another aspect of the present disclosure is to provide an exercise planning apparatus, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the motion planning method according to the first aspect.
Yet another aspect of the present disclosure is to provide a computer readable storage medium having stored thereon a computer program for execution by a processor to implement the motion planning method as described in the first aspect above.
The technical effects of the motion planning method, the motion planning device, the motion planning equipment and the computer readable storage medium are as follows:
the motion planning method, device, equipment and computer readable storage medium provided by the present disclosure include: determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform; segmenting the current path according to the number of preset path points to obtain a motion state with time information; judging whether the motion state accords with a rationality rule; if not, determining the obstacle avoidance increment corresponding to the unreasonable state; determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path; and continuously executing the step of judging whether the motion state is reasonable or not according to the new updated motion state. The motion planning method, the motion planning device, the motion planning equipment and the computer readable storage medium provided by the disclosure initialize a current path, and then reasonably judge the path, if the path comprises an unreasonable motion state, obstacle avoidance increment corresponding to the unreasonable motion state can be calculated, so that the unreasonable state is updated according to the obstacle avoidance increment, the planned motion path is updated, and then the new path is repeatedly and reasonably judged, a reasonable and fully continuous motion path can be obtained, and the motion path can be used for guiding a motion part to move.
Drawings
FIG. 1 is a flow chart illustrating a method of athletic planning in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method of athletic planning in accordance with another exemplary embodiment of the present invention;
FIG. 3 is a flow chart illustrating a method of athletic planning in accordance with yet another exemplary embodiment of the present invention;
FIG. 4 is a block diagram of an exercise planning apparatus according to an exemplary embodiment of the present invention;
FIG. 5 is a block diagram of an exercise planning apparatus according to another exemplary embodiment of the present invention;
fig. 6 is a block diagram illustrating an exercise planning apparatus according to an exemplary embodiment of the present invention.
Detailed Description
Fig. 1 is a flowchart illustrating an exercise planning method according to an exemplary embodiment of the present invention.
The method provided by the embodiment can plan the motion state of the motion part of the movable mechanical platform. For example, the state of each joint of the robot arm, the motion state of the leg of the robot, and the like. For a robot arm, the state refers to the state value of each joint in the robot arm, such as a four-axis robot arm, in which the first, second, and fourth joints are moved by adjusting the angle of the axis and the third joint is moved by adjusting the height, so the state of the robot arm may include (θ)1、θ2、h、θ4) Wherein, theta1、θ2、θ4The angle values of the first joint, the second joint and the fourth joint are indicated, and h is the height value of the third joint relative to the ground. Other types of robotic arms are similar.
As shown in fig. 1, the exercise planning method provided in this embodiment includes:
step 101, determining a current path according to an initial motion state and a target motion state of a motion part of the movable platform.
The method provided by the embodiment can be executed by an electronic device with computing function, for example, a computer, a tablet computer, a smart mobile device (such as a smart phone), and the like. The electronic device movable platform may or may not be directly or indirectly connected. If the two are connected, the electronic equipment can also control the motion part of the movable platform to move according to the planned motion track.
The electronic equipment can acquire an initial motion state and a target motion state of a motion part of the movable platform.
The electronic device may detect an initial motion state of the moving member through a sensor or the like, and may input the initial motion state of the moving member by a user.
Specifically, the target motion state of the moving component may also be manually input by a user, or may also be automatically detected by the electronic device. For example, if the user inputs an object to be grabbed by the moving part or a specific position to be reached, the electronic device may determine which state the moving part is in, and then the electronic device may grab the object or reach the specific position, so as to determine the target moving state.
Further, the current path may be determined according to the obtained initial motion state and the target motion state. The current path may specifically be determined by using a polynomial, for example, a cubic polynomial, a quadratic polynomial, or a quintic polynomial may be constructed, where time is used as an independent variable and a motion state is used as a dependent variable, and parameters in the polynomial may be adjusted, so that at time 0, a result of the polynomial is an initial motion state, at time t, a result of the polynomial is a target motion state, and t may be set as required, and specifically may be a predicted motion duration of the motion component.
In practical application, before the movement planning for the moving part is started, some parameters may be set, specifically, the parameters may be set by a user according to needs, or the parameters may be determined by the electronic device according to historical experience. When setting the parameters, the path duration t can be set, so that when planning the movement, the movement track with the movement time meeting the path duration t is planned.
Based on the initial current path obtained in step 101, a complete and sufficiently continuous motion trajectory can be obtained by constructing the path through a polynomial, and the motion trajectory conforms to the expected motion duration.
And 102, segmenting the current path according to the number of preset path points to obtain a motion state with time information.
When setting parameters, the number of preset path points can be set. The more the preset path point number is set, the larger the data processing amount in the post-processing, but the more the planned path is in accordance with the expectation. Therefore, the number of preset path points can be set according to requirements.
Specifically, the electronic device may obtain a preset number of path points, and may segment the current path based on the preset number of path points, so as to obtain a plurality of motion states. Although the current path can be understood as a motion track, the current path comprises a plurality of motion states, and the motion part is switched according to the motion states in the current path so as to form the motion track.
Further, the moving part may be in different moving states in the current path at different times. For example, at time 0, the moving part is in an initial moving state, and at time t0In the intermediate motion state, and in the target motion state at time t. Thus, the current path can be segmented according to time.
In practical application, the current path can be equally divided according to time, and the division point is the motion state with time. Specifically, 0 to t may be divided to obtain a plurality of time points, and then the motion states corresponding to the time points are calculated based on a polynomial, so as to obtain the correspondence between the time points and the motion states.
If the current path is determined in other manners, the current path may also be cut in other manners, for example, a plurality of motion states may be obtained in a manner of equally dividing the path, and a time point corresponding to each motion state may be determined according to the current path.
And 103, judging whether the motion state accords with the rationality rule.
Specifically, after the current path is planned, it is also necessary to verify whether the path is feasible and meets the expected constraint condition. In the method provided in this embodiment, since the current path is cut in step 102 to obtain a plurality of motion states, it can be determined whether the motion states are reasonable, and if both the motion states are reasonable, the current path can be considered to be reasonable.
In which rationality rules for judging whether the motion state is reasonable or not may be set in advance, so that each motion state is judged based on these rules. In practical application, the motion states can be judged one by one, or a plurality of motion states can be judged simultaneously in parallel.
If the motion state simultaneously satisfies the following conditions, the motion state can be considered to accord with the rationality rule:
the moving state belongs to the moving range of the moving part, and the distance between the moving part and the obstacle in the moving state is larger than or equal to the safety distance.
The reasonable motion state means that the motion part does not exceed the reasonable motion range of the motion part in the state, and the distance between the motion part and all obstacles is larger than or equal to the safe distance in the state. The reasonable movement range of the moving part can be preset, so that whether the moving part is in the reasonable movement range or not can be directly judged, and if the moving part is in the movement state, the movement state is determined to accord with the first condition. And judging whether the distances between the moving part and all the obstacles are greater than or equal to the safe distance or not when the moving part is in the moving state according to a preset obstacle model, and if so, determining that the moving state is a reasonable state. Or whether the motion state meets the second condition or not can be determined firstly, and then whether the motion state meets the first condition or not can be judged.
If the moving part exceeds the reasonable movement range, the moving part cannot move normally, and if the moving part collides with an obstacle, the moving part is damaged, so that the moving state meeting the two conditions is the state which can be experienced by the moving part.
In addition, if the preset path points are less, whether the state between two adjacent motion states meets the rationality rule can be judged. If the two adjacent motion states both accord with the rule, a plurality of motion sub-states can be obtained by dividing between the two motion states, and if the plurality of motion sub-states all accord with the rule, the two motion adjacent states are determined to be reasonable states.
An obstacle model may be preset, and the obstacle included in the model may be an obstacle that the robot arm may collide with during reasonable movement, for example, in some postures, the hand grip may collide with the base of the robot arm, and therefore, the base of the robot arm may also be added to the obstacle model.
If the motion state is not reasonable, go to step 104.
And step 104, determining obstacle avoidance increment corresponding to the unreasonable state.
When the moving part moves a small distance, if the distance between the moving part and the obstacle increases, the direction can be regarded as an obstacle avoidance increment. It can be considered as the opposite direction between the moving part and the obstacle.
Specifically, a model of the moving part can be preset, and obstacle avoidance increment between the moving part and the obstacle when the moving part is in an unreasonable state can be calculated according to the obstacle model and the moving part model. For example, if the two collide, the collision position may be calculated, and the opposite direction between the moving member and the obstacle may be determined based on the collision position.
Specifically, the direction may be converted to a specific value, for example, for a two-dimensional plane, horizontally an x-axis and vertically a y-axis. Then (1, 0) indicates that the level is to the right. In practical applications, the value corresponding to the direction may be calculated according to requirements, and for example, (1, 0) may be used to represent the right, or (2, 0) may be used to represent the right.
Furthermore, the posture of the moving part in an unreasonable state can be determined according to the positive kinematics of the moving part, the obstacle model can be converted into a plane model according to a preset obstacle model, the two models are projected to a specific straight line at the same time, the distance between the moving part and the obstacle can be obtained, meanwhile, the direction information between the moving part and the obstacle can be determined, and then the direction information can be converted into obstacle avoidance increment based on the differential inverse kinematics.
And 105, determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path.
Because the obstacle avoidance increment is the opposite direction between the moving part and the obstacle, the unreasonable state can be adjusted according to the obstacle avoidance increment, so that the moving part cannot collide with the obstacle when in the new state. For example, the motion state of the moving component and the obstacle avoidance increment can be added, so that the motion state moves towards the direction of the obstacle avoidance increment, and the purpose of avoiding the obstacle is achieved.
If the moving state is not reasonable due to the moving part not belonging to the reasonable moving range when the moving part is in the moving state, the state can be adjusted based on step 105, and after multiple adjustments, the state belongs to the reasonable moving range and does not collide with the obstacle.
Specifically, the current path may be updated according to the updated motion state, and the unreasonable motion state may be directly replaced with the updated motion state.
Further, after updating the current path, the step 103 may be continued based on the updated motion state.
In actual application, since it is not determined whether the updated motion state itself meets the rationality rule, there may be an unreasonable situation in the updated motion state, and step 103 may be continuously executed according to the updated motion state, so as to perform rationality determination on a new route. If the motion states are judged to be reasonable according to the updated motion states, the current updated path can be determined to be reasonable.
The method provided by the present embodiment is used for performing motion planning, and is performed by a device provided with the method provided by the present embodiment, which is typically implemented in hardware and/or software.
The exercise planning method provided by the embodiment comprises the following steps: determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform; segmenting the current path according to the number of preset path points to obtain a motion state with time information; judging whether the motion state accords with a rationality rule; if not, determining the obstacle avoidance increment corresponding to the unreasonable state; determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path; and continuously executing the step of judging whether the motion state is reasonable or not according to the new updated motion state. The motion planning method provided by this embodiment initializes a current path, and then performs rationalization judgment on the path, and if the path includes an unreasonable motion state, an obstacle avoidance increment corresponding to the unreasonable motion state may be calculated, so that the unreasonable state is updated according to the obstacle avoidance increment, and the planned motion path is updated, and then the new path is repeatedly subjected to rationalization judgment, so that a reasonable and sufficiently continuous motion path can be obtained, and the motion path can be used for guiding a motion component to move.
Fig. 2 is a flowchart illustrating an exercise planning method according to another exemplary embodiment of the present invention.
As shown in fig. 2, the exercise planning method provided in this embodiment includes:
step 201, constructing a fifth-order polynomial with time as an independent variable and a motion state as a dependent variable, wherein the fifth-order polynomial satisfies the following conditions:
when the time is 0, the polynomial result is the initial motion state, and when the time is the predicted motion time, the polynomial result is the target motion state.
The curve of the fifth-order polynomial is smoother, and the motion path is determined based on the fifth-order polynomial, so that a smoother motion track can be obtained. And the motion path determined according to the fifth-order polynomial can ensure that the speed and the acceleration at the starting point and the end point are continuous, so that a current path can be initialized in a fifth-order polynomial mode.
Specifically, the fifth order polynomial may be:
θ(t)＝a0+a1t+a2t2+a3t3+a4t4+a5t5
t is time, θ (t) is the state of motion at time t, a0、a1、a2、a3、a4、a5Is a polynomial coefficient. When t is equal to 0, θ (t) is equal to the initial moving state, indicating that the moving member is in the initial moving state at time 0. When T is equal to T, θ (T) is equal to the target motion state, indicating that the motion component is in the target motion state at time T, i.e., the motion component moves to the end point. T is the expected movement duration.
Further, the polynomial coefficient can be adjusted to satisfy the condition that the polynomial result is in the initial motion state when the time is 0 and in the target motion state when the time is the predicted motion time.
At step 202, a fifth order polynomial is determined as the current path.
The fifth-order polynomial constructed in step 201 may be determined as a current path, the path takes the initial motion state as a starting point, the target motion state as an end point, and a curve based on the fifth-order polynomial is smooth and sufficiently continuous, so that a path may be constructed based on the fifth-order polynomial.
The path does not consider the external environment and the motion specification of the moving part, only considers the smoothness and continuity of the path, and therefore the reasonability judgment of the path is needed. Since the motion path includes a plurality of motion states, if each motion state is reasonable, the path can be considered reasonable.
And step 203, cutting the expected movement time according to the preset path points, and determining a plurality of sub-times.
Because there are multiple motion states in the motion path, for example, the motion states corresponding to each second are different, the estimated motion duration may be cut according to the number of preset path points, multiple sub-times may be determined, and then the motion state corresponding to each sub-time may be determined.
Specifically, the preset time duration refers to a time duration from time 0 to an expected movement time when the fifth-order polynomial is constructed, for example, a time duration from 0 to T. The time period can be divided equally to obtain sub-time of the preset path point, such as 0 and T1、T2、T3...T。
Furthermore, the number of preset path points can be preset, and the preset path points are used for selecting a motion state in the current path according to the number of the preset path points. If the number of the preset path points is large, the selected motion state is also large, which results in large calculation amount in the subsequent steps. If the number of preset path points is small, the selected motion state is also small, and the accuracy of judging the rationality of the current path is influenced, so that the number of the preset path points can be set reasonably according to requirements, and balance is performed between the preset path points and the current path points.
And step 204, determining the motion state corresponding to the sub-time according to the fifth-order polynomial.
In practical application, the motion state can be calculated by utilizing a fifth-order polynomial by taking the sub-time as an independent variable. For example, when the sub-time is T1In time, the motion state is:
a0+a1T1+a2T1 2+a3T1 3+a4T1 4+a5T1 5
by means of the above formula, the motion state corresponding to each sub-time can be obtained, so that the motion states have time information.
Step 205, judging whether the motion state accords with the rationality rule.
Reasonable rules include the following conditions:
the moving state belongs to the moving range of the moving part, and the distance between the moving part and the obstacle in the moving state is larger than or equal to the safety distance.
The reasonable motion state means that the motion part does not exceed the reasonable motion range of the motion part in the state, and the distance between the motion part and all obstacles is larger than or equal to the safe distance in the state. The reasonable movement range of the moving part can be preset, so that whether the moving part is in the reasonable movement range or not can be directly judged, and if the moving part is in the movement state, the movement state is determined to accord with the first condition. And judging whether the distances between the moving part and all the obstacles are greater than or equal to the safe distance or not when the moving part is in the moving state according to a preset obstacle model, and if so, determining that the moving state is a reasonable state. Or whether the motion state meets the second condition or not can be determined firstly, and then whether the motion state meets the first condition or not can be judged.
If the moving part exceeds the reasonable movement range, the moving part cannot move normally, and if the moving part collides with an obstacle, the moving part is damaged, so that the moving state meeting the two conditions is the state which can be experienced by the moving part.
If each motion state meets the rationality rules, step 206 is executed, otherwise, step 207 is executed.
Step 206, determining the current path as the final path.
If each motion state is reasonable, the current path can be considered to be reasonable, the current path can be used as a final path, namely, when the motion part moves along the path, the end point can be reached, and the motion process is reasonable.
And step 207, determining opposite direction information between the moving part and the obstacle according to the preset obstacle model and the moving part model.
The position with the closest distance between the preset obstacle model and the moving part model can be determined according to the preset obstacle model and the moving part model, and then opposite direction information between the preset obstacle model and the moving part model is determined based on the position. The distance between the moving member and the obstacle after moving in a certain direction can be calculated, and if the distance increases, the direction can be considered to be the opposite direction between the moving member and the obstacle. When the moving member moves the same distance, the direction in which the distance between the obstacle and the moving member increases the most is determined as the final direction information.
And step 208, determining obstacle avoidance increment corresponding to the unreasonable state according to the direction information.
The directions may be converted to specific values, for example, for a two-dimensional plane, horizontally the x-axis and vertically the y-axis. Then (1, 0) indicates that the level is to the right. In practical applications, the value corresponding to the direction may be calculated according to requirements, and for example, (1, 0) may be used to represent the right, or (2, 0) may be used to represent the right.
Step 209 determines the smoothness increment corresponding to the irrational state.
Wherein, in order to make the finally planned movement path smoother, smoothness increment corresponding to the unreasonable state can be determined. The smoothness increment can be determined according to the unreasonable state and the state at the previous moment or the state at the next moment, and the unreasonable state is adjusted by combining the smoothness increment, so that the updated path is smooth.
Determining smoothness increments corresponding to unreasonable conditions, including:
acquiring time information corresponding to the unreasonable state;
determining the last motion state corresponding to the unreasonable state according to the time information;
and determining the smoothness increment according to the last motion state, the unreasonable state and the preset smoothness weighted value.
In the method provided by this embodiment, each motion state has a time attribute, so that time information corresponding to an unreasonable motion state can be obtained, the previous time information can be found according to the time information, and the previous motion state corresponding to the previous time information can be determined. For example, the unreasonable motion state corresponds to a time T3The last time information is T2Can obtain T2The corresponding motion state.
Wherein, can also set up the slipperiness weighted value in advance to according to last motion state, unreasonable state, predetermine the slipperiness weighted value, confirm the slipperiness increment. A general preset smoothness weight value can be determined, and different preset smoothness weight values can also be determined according to different time information.
Specifically, the increase in smoothness may be determined using the following equation:
wherein,is an unreasonable state thetaiCorresponding increase in smoothness, θi-1Is an unreasonable state thetaiLast motion state of wmThe smoothness weight value is preset, and may be general or corresponding to the time i.
The timing between step 207-.
And step 210, determining and updating the motion state according to the obstacle avoidance increment, the smoothness increment and the unreasonable state.
Further, in order to make the updated motion state approach to be reasonable, the unreasonable motion state can be adjusted according to the obstacle avoidance increment, and meanwhile, in order to make the updated motion path smoother, the unreasonable motion state can be updated by combining the obstacle avoidance increment and the smoothness increment.
In practical application, the total increment can be determined by combining the obstacle avoidance increment and the smoothness increment, and the unreasonable state is adjusted according to the total increment, so that the updated motion state is obtained.
Wherein the total increase may be determined using the following equation:
Δθt＝α(wmΔθm+waΔθa)
specifically, Δ θtIs the total increment, α is the learning rate, which can be set as required, wmIs the obstacle avoidance weight; w is aaIs the smoothness weight; delta thetamIs the increment of smoothness, Delta thetaaIs an obstacle avoidance increment.
And step 211, updating the current path according to the updated motion state to obtain a new current path.
The specific principle and implementation of step 211 is similar to that of updating the current path in step 105, and is not described here again.
After step 211, execution of step 205 may continue according to the updated motion state.
Fig. 3 is a flowchart illustrating an exercise planning method according to another exemplary embodiment of the present invention.
As shown in fig. 3, the exercise planning method provided in this embodiment includes:
step 301, obtaining a third axis state value in the initial state, and obtaining a target third state value in the target state.
The method provided by the embodiment is suitable for the four-axis mechanical arm, and for the four-axis mechanical arm, the state values comprise fourState value (theta) of each axis1、θ2、h、θ4). Therefore, when the mechanical arm is in the initial state, the four corresponding state values can be obtained as a first axis state value, a second axis state value, a third axis state value and a fourth axis state value.
Specifically, in the four-axis mechanical arm, the state value of the third axis is only used for adjusting the height value of the hand grab, and the position and the posture of the hand grab are not changed. And the height of the gripper tail end relative to the ground can be adjusted based on the first axis state value, the second axis state value and the fourth axis state value. Therefore, the state value h of the third axis can be stripped off in the motion planning process, and only the state values of the first axis, the second axis and the fourth axis are considered, so that the calculation amount in the planning process is reduced.
Further, in the finally planned movement path, the state of the third joint needs to be specified for the robot arm. In the method provided by the embodiment, the state corresponding to the third joint of the mechanical arm in the final motion path may be determined based on the third axis state value in the initial state and the target third state value in the target state.
In practical application, the third axis state values in the initial state and the target state can be obtained first, and the third axis state values in the two states can be directly read.
Step 302, determining the larger value of the third axis state value and the target third state value as the planning third axis state value.
And step 303, acquiring a height value of the obstacle in the obstacle model.
An obstacle model may be preset, wherein the obstacle included in the obstacle model may be an obstacle that the robot arm may collide with during reasonable movement, for example, in some postures, the hand grip may collide with the base of the robot arm, and therefore, the base of the robot arm may also be added to the obstacle model.
In practical application, the obstacle model includes information of obstacles, such as height information, from which a height value of each obstacle can be obtained.
And 304, if the height value is smaller than the planned third axis state value, deleting the obstacle in the obstacle model to obtain a final obstacle model.
And the motion state of the third shaft of the mechanical arm in the motion process can be specified according to the planned state value of the third shaft. In the movement process, if the obstacle is lower than the third axis state value, the hand of the mechanical arm cannot collide with the obstacle, so that the obstacle with the height lower than the planned third axis state value can be deleted from the obstacle model, and the data processing amount in the path planning process can be further reduced.
Specifically, all obstacles with height values smaller than the planned third axis state value in the obstacle model are deleted, so that the final obstacle model is obtained.
And 305, determining the current path of the moving part according to the movable platform according to the first axis state value, the second axis state value, the fourth axis state value, the target first axis state value, the target second axis state value and the target fourth axis state value included in the target state.
In the method provided by this embodiment, the current path may be initialized according to only the state values of the first axis, the second axis, and the fourth axis in the initial state and the target state.
Specifically, the current path may be constructed by a fifth-order polynomial. In the fifth-order polynomial, the independent variable is time, and the dependent variable is a state value of a first axis, a second axis and a fourth axis. When the time is 0, the polynomial result is equal to the first axis state value, the second axis state value, and the fourth axis state value included in the initial state, and when the time is the predicted movement duration, the polynomial result is equal to the target first axis state value, the target second axis state value, and the target fourth axis state value included in the target state.
And step 306, segmenting the current path according to the number of preset path points to obtain a motion state with time information.
Step 306 is similar to step 102 in specific principles and implementations, and will not be described here again.
In the solution provided in this embodiment, the motion state included in the current path only includes the state values of the first axis, the second axis, and the fourth axis, and therefore the motion state obtained by dividing the current path also includes these three state values.
And 307, judging whether the motion state accords with the rationality rule or not according to the final obstacle model.
The specific rationality rules are similar to the above embodiments and are not described in detail.
The difference between the solution of the present embodiment and the above solution is that the final obstacle model has fewer obstacles, and the motion states only have the state values of the first axis, the second axis, and the fourth axis, so that the data processing amount for determining whether the data processing amount is reasonable can be reduced.
If each motion state meets the rationality rules, step 308 is executed, otherwise step 309 is executed.
And 308, determining a final path according to the current path and the planned third axis state value.
The current path obtained by planning in the above steps only includes three-axis state values, specifically, a first-axis state value, a second-axis state value, and a fourth-axis state value. A planned third axis state value may be added to each state, making each state a four-axis state value, to form the final path. For example, if the planned third axis state value is 5 and one state of the current path is (1,2,3), the planned third axis state value is added to the state, and then the state (1,2,5,3) can be obtained. This is done for each state in the current path.
And acquiring a starting point state and an end point state in the four-axis motion state. And comparing the starting state with the initial state, judging whether the starting state and the initial state are completely consistent, and if not, taking the initial state as the first state of the movement route. And comparing the end point state with the target state, judging whether the end point state and the target state are completely consistent, and if not, taking the target state as the last state of the movement route. It should be noted that if the starting state is not completely consistent with the initial state, or if the key state is not completely consistent with the target state, only the third axis may be different.
In the solution of this embodiment, the movement plan based on the first axis, the second axis, and the fourth axis already bypasses the obstacle higher than the planned third axis state value. In the final movement route, the height of the third axis is the planned state value of the third axis, so that the obstacle lower than the planned state value does not affect the mechanical arm, and therefore the part of the obstacle can not be considered in the movement planning.
And 309, determining the obstacle avoidance increment corresponding to the unreasonable state.
And step 310, determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path.
After step 310, execution continues with step 307 based on the updated motion state.
Fig. 4 is a block diagram illustrating an exercise planning apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 4, the exercise planning apparatus provided in this embodiment includes:
a first determining module 41, configured to determine a current path according to an initial motion state and a target motion state of a motion component of the movable platform;
the segmentation module 42 is configured to segment the current path according to a preset number of path points to obtain a motion state with time information;
a judging module 43, configured to judge whether the motion state meets a rationality rule;
if not, the second determining module 44 determines an obstacle avoidance increment corresponding to the unreasonable state;
an updating module 45, configured to determine an updated motion state according to the obstacle avoidance increment and the unreasonable state, and update the current path according to the updated motion state to obtain a new current path;
the judging module 43 continues to execute the step of judging whether the motion state is reasonable according to the updated motion state.
The motion planning apparatus provided in this embodiment includes: the first determining module is used for determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform; the segmentation module is used for segmenting the current path according to the number of preset path points to obtain a motion state with time information; the judging module is used for judging whether the motion state accords with a rationality rule or not; if not, the second determination module determines the obstacle avoidance increment corresponding to the unreasonable state; the updating module is used for determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path; and the judging module continues to execute the step of judging whether the motion state is reasonable or not according to the updated motion state. The device provided by the embodiment initializes a current path, and then reasonably judges the path, if the path includes an unreasonable motion state, the obstacle avoidance increment corresponding to the unreasonable motion state can be calculated, so that the unreasonable state is updated according to the obstacle avoidance increment, the planned motion path is updated, and then the new path is repeatedly and reasonably judged, so that a reasonable and fully continuous motion path can be obtained, and the device can be used for guiding the motion component to move.
The specific principle and implementation of the movement planning apparatus provided in this embodiment are similar to those of the embodiment shown in fig. 1, and are not described herein again.
Fig. 5 is a block diagram illustrating an exercise planning apparatus according to another exemplary embodiment of the present invention.
As shown in fig. 5, on the basis of the above embodiment, the exercise planning apparatus provided in this embodiment further includes:
a third determining module 46, configured to determine that the current path is a final path if each of the motion states is reasonable.
The first determining module 41 is specifically configured to:
constructing a fifth-order polynomial with time as an independent variable and the motion state as a dependent variable, wherein the fifth-order polynomial satisfies the following conditions:
when the time is 0, the polynomial result is the initial motion state, and when the time is the predicted motion time, the polynomial result is the target motion state;
determining the fifth order polynomial as the current path.
The segmentation module 42 is specifically configured to:
cutting the expected movement duration according to the preset path points, and determining a plurality of sub-times;
and determining the motion state corresponding to the sub-time according to the fifth-order polynomial.
The rational rules include the following conditions:
the motion state belongs to the motion range of the motion part, and the distance between the motion part and the obstacle in the motion state is larger than or equal to the safety distance.
The second determining module 44 is specifically configured to:
determining opposite direction information between the moving part and the obstacle according to a preset obstacle model and a moving part model;
and determining obstacle avoidance increment corresponding to the unreasonable state according to the direction information.
If the motion state is judged not to accord with the reasonableness rule, the second determining module is further used for determining the smoothness increment corresponding to the unreasonable state;
the update module 45 is specifically configured to:
and determining an updated motion state according to the obstacle avoidance increment, the smoothness increment and the unreasonable state.
The second determining module 44 is specifically configured to:
acquiring time information corresponding to the unreasonable state;
determining the last motion state corresponding to the unreasonable state according to the time information;
and determining the smoothness increment according to the last motion state, the unreasonable state and a preset smoothness weighted value.
Optionally, the initial state includes a first axis state value, a second axis state value, a third axis state value, and a fourth axis state value; the target state comprises a target first axis state value, a target second axis state value, a target third axis state value and a target fourth axis state value;
the first determining module 41 is specifically configured to:
and determining the current path of the moving part according to the movable platform according to the first axis state value, the second axis state value and the fourth axis state value included in the initial state, the target first axis state value, the target second axis state value and the target fourth axis state value included in the target state.
Optionally, the apparatus provided in this embodiment further includes:
a pre-processing module 47 for:
acquiring the third axis state value in the initial state, and acquiring a target third state value of the target state;
determining the larger value of the third axis state value and the target third state value as a planning third axis state value;
a model processing module 48 for:
acquiring a height value of an obstacle in the obstacle model;
if the height value is smaller than the planned third axis state value, deleting the obstacle in the obstacle model to obtain a final obstacle model;
the determining module 43 is specifically configured to:
and judging whether the motion state accords with a rationality rule or not according to the final obstacle model.
Optionally, the apparatus provided in this embodiment further includes:
a fourth determining module 49, configured to determine a final path according to the current path and the planned third axis state value if each motion state is reasonable.
The specific principle and implementation of the apparatus provided in this embodiment are similar to those of the embodiments shown in fig. 2 to 3, and are not described herein again.
Fig. 6 is a block diagram illustrating an exercise planning apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 6, the exercise planning apparatus provided in this embodiment includes:
a memory 61;
a processor 62; and
a computer program;
wherein the computer program is stored in the memory 61 and configured to be executed by the processor 62 to implement any of the motion planning methods as described above.
The present embodiments also provide a computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement any of the motion planning methods described above.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (24)

1. A method of motion planning, comprising:
determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform;
dividing the current path according to the number of preset path points to obtain a motion state with time information;
judging whether the motion state accords with a rationality rule or not;
if not, determining the obstacle avoidance increment corresponding to the unreasonable state;
determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path;
and continuing to execute the step of judging whether the motion state is reasonable or not according to the updated motion state.
2. The method of claim 1, wherein if each of the motion states is reasonable, determining the current path as a final path.
3. The method of claim 1, wherein determining the current path based on the initial motion state and the target motion state of the moving part of the movable platform comprises:
constructing a fifth-order polynomial with time as an independent variable and the motion state as a dependent variable, wherein the fifth-order polynomial satisfies the following conditions:
when the time is 0, the polynomial result is the initial motion state, and when the time is the predicted motion time, the polynomial result is the target motion state;
determining the fifth order polynomial as the current path.
4. The method according to claim 3, wherein the segmenting the current path according to the number of preset path points to obtain the motion state with time information comprises:
cutting the expected movement duration according to the preset path points, and determining a plurality of sub-times;
and determining the motion state corresponding to the sub-time according to the fifth-order polynomial.
5. The method of claim 1, wherein the sensible rule comprises the following condition:
the motion state belongs to the motion range of the motion part, and the distance between the motion part and the obstacle in the motion state is larger than or equal to the safety distance.
6. The method of claim 1, wherein determining the obstacle avoidance increment corresponding to the unreasonable state comprises:
determining opposite direction information between the moving part and the obstacle according to a preset obstacle model and a moving part model;
and determining obstacle avoidance increment corresponding to the unreasonable state according to the direction information.
7. The method of claim 1, wherein if the motion state is determined not to comply with a rationality rule, the method further comprises:
determining smoothness increment corresponding to the unreasonable state;
the determining and updating the motion state according to the obstacle avoidance increment and the unreasonable state comprises:
and determining an updated motion state according to the obstacle avoidance increment, the smoothness increment and the unreasonable state.
8. The method of claim 7, wherein determining the smoothness increment to which the irrational state corresponds comprises:
acquiring time information corresponding to the unreasonable state;
determining the last motion state corresponding to the unreasonable state according to the time information;
and determining the smoothness increment according to the last motion state, the unreasonable state and a preset smoothness weighted value.
9. The method of claim 1,
the initial state comprises a first axis state value, a second axis state value, a third axis state value and a fourth axis state value; the target state comprises a target first axis state value, a target second axis state value, a target third axis state value and a target fourth axis state value;
the determining the current path according to the initial motion state and the target motion state of the motion part of the movable platform comprises the following steps:
and determining the current path of the moving part according to the movable platform according to the first axis state value, the second axis state value and the fourth axis state value included in the initial state, the target first axis state value, the target second axis state value and the target fourth axis state value included in the target state.
10. The method of claim 9,
acquiring the third axis state value in the initial state, and acquiring a target third state value of the target state;
determining the larger value of the third axis state value and the target third state value as a planning third axis state value;
before judging whether the motion state meets the rationality rule, the method comprises the following steps:
acquiring a height value of an obstacle in the obstacle model;
if the height value is smaller than the planned third axis state value, deleting the obstacle in the obstacle model to obtain a final obstacle model;
the judging whether the motion state accords with the rationality rule comprises the following steps:
and judging whether the motion state accords with a rationality rule or not according to the final obstacle model.
11. The method of claim 10, wherein if each of the motion states is rational, determining a final path based on the current path and the planned third axis state value.
12. An exercise planning apparatus, comprising:
the first determining module is used for determining a current path according to the initial motion state and the target motion state of the motion part of the movable platform;
the segmentation module is used for segmenting the current path according to the number of preset path points to obtain a motion state with time information;
the judging module is used for judging whether the motion state accords with a rationality rule or not;
if not, the second determination module determines the obstacle avoidance increment corresponding to the unreasonable state;
the updating module is used for determining an updated motion state according to the obstacle avoidance increment and the unreasonable state, and updating the current path according to the updated motion state to obtain a new current path;
and the judging module continues to execute the step of judging whether the motion state is reasonable or not according to the updated motion state.
13. The apparatus of claim 12, further comprising:
and the third determining module is used for determining the current path as a final path if each motion state is reasonable.
14. The apparatus of claim 12, wherein the first determining module is specifically configured to:
constructing a fifth-order polynomial with time as an independent variable and the motion state as a dependent variable, wherein the fifth-order polynomial satisfies the following conditions:
when the time is 0, the polynomial result is the initial motion state, and when the time is the predicted motion time, the polynomial result is the target motion state;
determining the fifth order polynomial as the current path.
15. The apparatus of claim 14, wherein the segmentation module is specifically configured to:
cutting the expected movement duration according to the preset path points, and determining a plurality of sub-times;
and determining the motion state corresponding to the sub-time according to the fifth-order polynomial.
16. The apparatus of claim 12, wherein the sensible rule comprises the following condition:
the motion state belongs to the motion range of the motion part, and the distance between the motion part and the obstacle in the motion state is larger than or equal to the safety distance.
17. The apparatus of claim 12, wherein the second determining module is specifically configured to:
determining opposite direction information between the moving part and the obstacle according to a preset obstacle model and a moving part model;
and determining obstacle avoidance increment corresponding to the unreasonable state according to the direction information.
18. The apparatus according to claim 12, wherein the second determining module is further configured to determine a smoothness increment corresponding to the unreasonable condition if the motion state is determined not to comply with the rationality rules;
the update module is specifically configured to:
and determining an updated motion state according to the obstacle avoidance increment, the smoothness increment and the unreasonable state.
19. The apparatus of claim 18, wherein the second determining module is specifically configured to:
acquiring time information corresponding to the unreasonable state;
determining the last motion state corresponding to the unreasonable state according to the time information;
and determining the smoothness increment according to the last motion state, the unreasonable state and a preset smoothness weighted value.
20. The apparatus of claim 12,
the initial state comprises a first axis state value, a second axis state value, a third axis state value and a fourth axis state value; the target state comprises a target first axis state value, a target second axis state value, a target third axis state value and a target fourth axis state value;
the first determining module is specifically configured to:
and determining the current path of the moving part according to the movable platform according to the first axis state value, the second axis state value and the fourth axis state value included in the initial state, the target first axis state value, the target second axis state value and the target fourth axis state value included in the target state.
21. The apparatus of claim 20, further comprising:
a pre-processing module to:
acquiring the third axis state value in the initial state, and acquiring a target third state value of the target state;
determining the larger value of the third axis state value and the target third state value as a planning third axis state value;
a model processing module to:
acquiring a height value of an obstacle in the obstacle model;
if the height value is smaller than the planned third axis state value, deleting the obstacle in the obstacle model to obtain a final obstacle model;
the judgment module is specifically configured to:
and judging whether the motion state accords with a rationality rule or not according to the final obstacle model.
22. The apparatus of claim 21, further comprising:
and the fourth determining module is used for determining a final path according to the current path and the planned third axis state value if each motion state is reasonable.
23. An exercise planning apparatus, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-11.
24. A computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement the method according to any of claims 1-11.
CN201910112554.3A 2019-02-13 2019-02-13 Motion planning method, device, equipment and computer readable storage medium Pending CN109857110A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910112554.3A CN109857110A (en) 2019-02-13 2019-02-13 Motion planning method, device, equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910112554.3A CN109857110A (en) 2019-02-13 2019-02-13 Motion planning method, device, equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN109857110A true CN109857110A (en) 2019-06-07

Family

ID=66897861

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910112554.3A Pending CN109857110A (en) 2019-02-13 2019-02-13 Motion planning method, device, equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN109857110A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110347162A (en) * 2019-07-29 2019-10-18 南京市晨枭软件技术有限公司 A kind of industrial robot path modified method and system automatically
CN111390909A (en) * 2020-03-30 2020-07-10 上海应用技术大学 Obstacle avoidance method and system for industrial robot

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104029203A (en) * 2014-06-18 2014-09-10 大连大学 Path planning method for implementation of obstacle avoidance for space manipulators
CN107030697A (en) * 2017-04-28 2017-08-11 广州大学 A kind of planing method of robot cartesian space smooth track
CN108274465A (en) * 2018-01-10 2018-07-13 上海理工大学 Based on optimization A*Artificial Potential Field machinery arm, three-D obstacle-avoiding route planning method
CN108664021A (en) * 2018-04-12 2018-10-16 江苏理工学院 Robot path planning method based on genetic algorithm and quintic algebra curve interpolation
CN108705532A (en) * 2018-04-25 2018-10-26 中国地质大学（武汉） A kind of mechanical arm obstacle-avoiding route planning method, equipment and storage device
CN108839019A (en) * 2018-06-25 2018-11-20 广州视源电子科技股份有限公司 Method and device for determining motion path of mechanical arm
CN108858198A (en) * 2018-07-26 2018-11-23 西北工业大学 A kind of robotic arm path planing method based on Genetic Simulated Annealing Algorithm
CN108958244A (en) * 2018-06-28 2018-12-07 广州视源电子科技股份有限公司 Motion planning method, device, equipment and computer readable storage medium
CN109048892A (en) * 2018-07-26 2018-12-21 西北工业大学 A kind of mechanical arm tail end barrier-avoiding method based on Q study

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104029203A (en) * 2014-06-18 2014-09-10 大连大学 Path planning method for implementation of obstacle avoidance for space manipulators
CN107030697A (en) * 2017-04-28 2017-08-11 广州大学 A kind of planing method of robot cartesian space smooth track
CN108274465A (en) * 2018-01-10 2018-07-13 上海理工大学 Based on optimization A*Artificial Potential Field machinery arm, three-D obstacle-avoiding route planning method
CN108664021A (en) * 2018-04-12 2018-10-16 江苏理工学院 Robot path planning method based on genetic algorithm and quintic algebra curve interpolation
CN108705532A (en) * 2018-04-25 2018-10-26 中国地质大学（武汉） A kind of mechanical arm obstacle-avoiding route planning method, equipment and storage device
CN108839019A (en) * 2018-06-25 2018-11-20 广州视源电子科技股份有限公司 Method and device for determining motion path of mechanical arm
CN108958244A (en) * 2018-06-28 2018-12-07 广州视源电子科技股份有限公司 Motion planning method, device, equipment and computer readable storage medium
CN108858198A (en) * 2018-07-26 2018-11-23 西北工业大学 A kind of robotic arm path planing method based on Genetic Simulated Annealing Algorithm
CN109048892A (en) * 2018-07-26 2018-12-21 西北工业大学 A kind of mechanical arm tail end barrier-avoiding method based on Q study

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
党浩明: "六自由度机械臂运动规划", 《国优秀硕士学位论文全文数据库•信息科技辑》 *
白玉昊: "面向双臂协调的运动规划方法研究", 《中国优秀硕士学位论文全文数据库•信息科技辑》 *
马超: "6R串联机械臂复杂空间环境规划路径研究", 《中国优秀硕士学位论文全文数据库•信息科技辑》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110347162A (en) * 2019-07-29 2019-10-18 南京市晨枭软件技术有限公司 A kind of industrial robot path modified method and system automatically
CN111390909A (en) * 2020-03-30 2020-07-10 上海应用技术大学 Obstacle avoidance method and system for industrial robot
CN111390909B (en) * 2020-03-30 2022-06-28 上海应用技术大学 Obstacle avoidance method and system for industrial robot

Similar Documents

Publication Publication Date Title
US8831777B2 (en) Robot program changing device
JP7324932B2 (en) dynamic planning controller
JP5025598B2 (en) Interference check control apparatus and interference check control method
US20090326713A1 (en) Autonomous mobile robot system
CN109760040B (en) Interference determination method, interference determination system, and storage medium
CN112809682B (en) Mechanical arm obstacle avoidance path planning method and system and storage medium
CN113552877A (en) Initial reference generation for robot-optimized action planning
US12099364B2 (en) Trajectory generation system, trajectory generation method, and program
JP2017102529A (en) Workpiece position posture calculator and handling system
CN113246143A (en) Mechanical arm dynamic obstacle avoidance trajectory planning method and device
CN115502961B (en) Human-machine on-line obstacle avoidance method and system based on human arm motion information prediction
US11673271B2 (en) Trajectory generation apparatus, multi-link system, and trajectory generation method
CN113043278B (en) Mechanical arm track planning method based on improved whale searching method
CN109857110A (en) Motion planning method, device, equipment and computer readable storage medium
CN115781685A (en) High-precision mechanical arm control method and system based on reinforcement learning
CN111716352B (en) Power distribution network live working mechanical arm navigation obstacle avoidance method and system
CN116117813A (en) Mechanical arm control method, mechanical arm, robot and storage medium
CN113814985B (en) Robot control method, control cabinet and system
CN114454981B (en) Jumping motion control method and device of biped robot and biped robot
CN111984000A (en) Method and device for automatically influencing an actuator
CN108958244B (en) Motion planning method, device, equipment and computer readable storage medium
CN116690557A (en) Method and device for controlling humanoid three-dimensional scanning motion based on point cloud
JP6848761B2 (en) Distance evaluation method between objects and interference evaluation method between relatively moving objects
CN110717970B (en) Method for moving corrected position by normal based on discrete collision detection
CN114820802A (en) High-freedom-degree dexterous hand grabbing planning method and device and computer equipment

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20190607

RJ01 Rejection of invention patent application after publication