CN113561175A - Path planning method and device of mechanical arm, computer equipment and storage medium - Google Patents
Path planning method and device of mechanical arm, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113561175A CN113561175A CN202110805844.3A CN202110805844A CN113561175A CN 113561175 A CN113561175 A CN 113561175A CN 202110805844 A CN202110805844 A CN 202110805844A CN 113561175 A CN113561175 A CN 113561175A
- Authority
- CN
- China
- Prior art keywords
- candidate
- current
- posture
- mechanical arm
- evaluation value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The application relates to a path planning method and device for a mechanical arm, computer equipment and a storage medium. The method comprises the following steps: acquiring a target position, a current position and a current posture of the mechanical arm; performing attitude prediction based on the current attitude to obtain a plurality of candidate attitudes; determining a plurality of candidate positions based on the current position and the candidate poses; the candidate position corresponds to the candidate pose; screening a next position from the candidate positions according to the target position and the current position; controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position; and updating the next position to be the current position, updating the candidate posture corresponding to the next position to be the current posture, returning to the step of predicting the posture based on the current posture to obtain a plurality of candidate postures, and continuing to execute until the mechanical arm is judged to reach the target position. By adopting the method, the smoothness of the motion track of the mechanical arm can be improved.
Description
Technical Field
The present disclosure relates to the field of robot arm control technologies, and in particular, to a method and an apparatus for path planning of a robot arm, a computer device, and a storage medium.
Background
With the progress of science and technology and the continuous development of automation technology, the mechanical arm is widely applied to various industries such as industrial manufacturing, medical treatment, entertainment service, military and the like as one of the main elements in the automatic operation process. In an automated operation process, a motion path of the mechanical arm needs to be planned, so that the mechanical arm can move according to the planned motion path, and corresponding automated operation can be completed. At present, the motion path of the mechanical arm is usually determined by means of manual teaching. However, the path planning method has the problem that the motion trail is not smooth.
Disclosure of Invention
In view of the above, it is necessary to provide a method and an apparatus for planning a path of a robot arm, a computer device, and a storage medium, which can improve smoothness of a motion trajectory of the robot arm.
A method of path planning for a robotic arm, the method comprising:
acquiring a target position, a current position and a current posture of the mechanical arm;
performing attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
determining a plurality of candidate positions based on the current position and the candidate poses; the candidate position corresponds to the candidate pose;
screening a next position from the candidate positions according to the target position and the current position;
controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and updating the next position to be the current position, updating the candidate posture corresponding to the next position to be the current posture, returning to the step of predicting the posture based on the current posture to obtain a plurality of candidate postures, and continuing to execute until the mechanical arm is judged to reach the target position.
In one embodiment, the filtering the next location from the candidate locations according to the target location and the current location includes:
determining a first evaluation value based on the target position and the current position;
respectively determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position;
and screening a next position from the candidate positions based on the first evaluation value and the second evaluation value.
In one embodiment, the method further comprises:
acquiring a target posture of the mechanical arm;
the determining a first evaluation value based on the target position and the current position includes:
determining a first evaluation value based on the target position, the target attitude, the current position, and the current attitude;
the determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position includes:
and respectively determining a second evaluation value corresponding to each candidate position based on the target position, the target posture, each candidate position and the corresponding candidate posture.
In one embodiment, the screening the candidate locations for a next location based on the first evaluation value and the second evaluation value includes:
screening candidate positions corresponding to the smallest second evaluation value from the candidate positions;
and if the minimum second evaluation value is smaller than the first evaluation value, determining the screened candidate position as a next position.
In one embodiment, the method further comprises:
determining that the robot arm reaches the target position when each of the second evaluation values is greater than or equal to the first evaluation value; or the like, or, alternatively,
and when a second evaluation value which is within a preset error range and smaller than the first evaluation value exists in the second evaluation values, judging that the mechanical arm reaches the target position.
In one embodiment, the method further comprises:
acquiring the position of an obstacle;
the determining a plurality of candidate positions based on the current position and the candidate poses comprises:
determining a plurality of predicted positions based on the current position and the candidate poses;
screening candidate locations from the plurality of predicted locations based on the obstacle location.
In one embodiment, the current pose comprises: the current linear velocity, the current pitch angle and the current course angle; the obtaining a plurality of candidate postures by performing posture prediction based on the current posture comprises:
obtaining a plurality of predicted linear velocities based on the current linear velocity prediction;
obtaining a plurality of predicted pitch angles based on the current pitch angle prediction;
obtaining a plurality of predicted course angles based on the current course angle prediction;
and arranging and combining the predicted linear velocity, the predicted pitch angle and the predicted course angle to obtain a plurality of candidate postures.
A path planning apparatus for a robot arm, the apparatus comprising:
the acquisition module is used for acquiring the target position, the current position and the current posture of the mechanical arm;
the prediction module is used for carrying out attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
a determination module to determine a plurality of candidate positions based on the current position and the candidate poses;
a screening module for screening a next position from the candidate positions according to the target position and the current position;
the control module is used for controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and the updating module is used for updating the next position to be the current position and updating the candidate posture corresponding to the next position to be the current posture.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a target position, a current position and a current posture of the mechanical arm;
performing attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
determining a plurality of candidate positions based on the current position and the candidate poses; the candidate position corresponds to the candidate pose;
screening a next position from the candidate positions according to the target position and the current position;
controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and updating the next position to be the current position, updating the candidate posture corresponding to the next position to be the current posture, returning to the step of predicting the posture based on the current posture to obtain a plurality of candidate postures, and continuing to execute until the mechanical arm is judged to reach the target position.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a target position, a current position and a current posture of the mechanical arm;
performing attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
determining a plurality of candidate positions based on the current position and the candidate poses; the candidate position corresponds to the candidate pose;
screening a next position from the candidate positions according to the target position and the current position;
controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and updating the next position to be the current position, updating the candidate posture corresponding to the next position to be the current posture, returning to the step of predicting the posture based on the current posture to obtain a plurality of candidate postures, and continuing to execute until the mechanical arm is judged to reach the target position.
According to the method, the device, the computer equipment and the storage medium for planning the path of the mechanical arm, when the motion path of the mechanical arm needs to be planned, a plurality of candidate postures are obtained based on the current posture prediction of the mechanical arm, the candidate position corresponding to each candidate posture is obtained based on the candidate postures and the current position of the mechanical arm, then the next position to which the mechanical arm needs to move is screened from the predicted candidate positions based on the target position and the current position of the mechanical arm so as to achieve the local path planning of the mechanical arm, then the mechanical arm is controlled to move to the next position according to the candidate posture corresponding to the next position, the next local path planning is carried out based on the next position and the corresponding candidate posture, and the mechanical arm is controlled to move according to the planned local path until the mechanical arm is judged to reach the target position. Therefore, the automatic planning of the local path of the mechanical arm is realized based on the target position, the current position and the current posture of the mechanical arm, the mechanical arm is controlled to move according to the planned local path, the smoothness of the motion track of the mechanical arm can be improved, and the impact caused by the unsmooth motion track can be reduced.
Drawings
FIG. 1 is a schematic flow chart diagram of a method for path planning for a robotic arm in one embodiment;
FIG. 2 is a schematic diagram of a motion model of a robotic arm in one embodiment;
FIG. 3 is a schematic diagram of a simulation effect of path planning for a robotic arm in one embodiment;
FIG. 4 is a schematic diagram of a path planning method for a robotic arm in one embodiment;
FIG. 5 is a block diagram of a path planning apparatus for a robot arm according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a method for planning a path of a robot arm is provided, and this embodiment is exemplified by applying the method to a controller, and it is understood that the controller may be integrated into the robot arm as a component of the robot arm, or may be deployed independently of the robot arm, and controls a motion path of the robot arm by communicating with a control unit integrated into the robot arm. In this embodiment, the method includes the steps of:
and 102, acquiring a target position, a current position and a current posture of the mechanical arm.
The target position refers to a position to which a terminal TCP (Tool center Point) of the robot arm needs to move finally in the whole path planning process of the robot arm, and may also be understood as an end Point position. The current position refers to a current position of the mechanical arm terminal TCP in the local path planning process of the mechanical arm, and may also be understood as an initial position/starting position in the current local path planning process. The whole path planning process comprises multiple times of local path planning, wherein an initial position in the whole path planning process is used as a current position in the first local path planning process, an end position in the whole path planning process is used as a next position to be moved in the last local path planning process, and a next position to be moved in the previous local path planning process is used as a current position in the next local path planning process. The position may specifically refer to position coordinates/position information in a cartesian coordinate system in a three-dimensional space, for example, the current position is [0,0,0 ]. The current posture corresponds to the current position, and the tail end TCP of the mechanical arm corresponds to a posture at each position. The attitude can also be understood as a motion attitude, and specifically may include motion parameters such as a linear velocity V, a Pitch angle Pitch, and a heading angle Yaw.
As shown in fig. 2, in one embodiment, a schematic diagram of a motion model of a robot arm is provided. Referring to fig. 2, the motion model of the mechanical arm includes motion parameters such as a linear velocity V, a Pitch angle Pitch, a course angle Yaw, and the like, and the posture of the mechanical arm specifically includes parameter values corresponding to the motion parameters in the motion model when the mechanical arm is at a position corresponding to the posture.
Specifically, after the whole path planning process of the robot arm is triggered, that is, after the first local path planning process of the robot arm is triggered, the controller acquires a target position, an initial position, and an initial posture of the robot arm, and uses the acquired initial position and initial posture as the current position and current posture in the current local path planning process, respectively, so as to determine, based on the current position and current posture, a position to which the robot arm needs to move in the current local path planning process, and a posture corresponding to the robot arm when the robot arm moves to the position. After each subsequent local path planning process is triggered, the controller does not need to acquire the target position of the mechanical arm again, and the controller respectively takes the position to which the mechanical arm needs to move and the corresponding posture determined in the previous local path planning process as the current position and the current posture in the current local path planning process.
In one embodiment, the controller receives a manually entered target position of the robotic arm, or alternatively, a target position of the robotic arm transmitted to by other computer devices. The controller can store the received target position locally so as to obtain a pre-stored target position locally when the path of the mechanical arm is planned, and can also dynamically receive the target position of the mechanical arm when the path of the mechanical arm needs to be planned and trigger the path planning process of the mechanical arm.
In one embodiment, the initial position and the initial posture of the robot arm can be manually entered or obtained from other computer equipment or dynamically acquired by the controller during the whole path planning process of the robot arm. The controller can adopt the initial gesture of current arm gesture collection mode dynamic acquisition arm, for example, the controller accessible is integrated in the motor encoder of arm and is gathered and record the joint angle of arm, then solves through mathematical model and can obtain initial gesture, no longer gives details here. The controller may construct a cartesian coordinate system based on the position of the end TCP of the robot arm, and thus, the initial position of the robot arm may be directly determined as [0,0,0 ].
And 104, carrying out attitude prediction based on the current attitude to obtain a plurality of candidate attitudes.
The candidate gesture is a gesture that the mechanical arm may have when moving to the next position. Specifically, the controller exhaustively enumerates parameter values possibly corresponding to the motion parameters in the next posture based on the parameter values of the motion parameters in the current posture to obtain a motion window/dynamic window corresponding to the motion parameters, and performs permutation and combination on the parameter values possibly corresponding to the motion parameters in the next posture to obtain a plurality of candidate postures of the next posture.
Step 106, determining a plurality of candidate positions based on the current position and the candidate postures; the candidate position corresponds to the candidate pose.
The candidate position refers to a position to which the mechanical arm may move in the current local path planning process. Specifically, the controller determines a candidate position corresponding to each candidate attitude respectively based on each candidate attitude and the current position, and obtains a plurality of candidate positions.
In one embodiment, for each candidate gesture, the controller obtains a candidate position corresponding to the candidate gesture by trigonometric function conversion based on the candidate gesture and the current position.
x1＝x0+v×cos(Yaw)
y1＝y0+v×sin(Yaw)
z1＝z0+v×sin(Pitch)
Wherein x is0、y0And z0Three position parameters, x, respectively, in the current position1、y1And z1The parameters are three position parameters in the candidate position, v, Pitch and Yaw are three motion parameters in the candidate attitude, namely, the parameters respectively refer to a predicted linear velocity, a predicted Pitch angle and a predicted course angle in the candidate attitude, and cos (#) and sin (#) respectively represent a cosine value and a sine value.
And step 108, screening the next position from the candidate positions according to the target position and the current position.
Wherein, the next position is the position to which the mechanical arm needs to move in the process of the secondary local path planning. The next position corresponds to the current position, the current position refers to the current position of the mechanical arm, and the next position refers to the position to which the mechanical arm needs to be moved from the current position.
Specifically, the controller calculates an evaluation value between the current position and the target position and an evaluation value between each candidate position and the target position, respectively, according to a preset evaluation function, and screens a next position to be moved from among the plurality of candidate positions, based on each calculated evaluation value.
In one embodiment, the evaluation value between the current position and the target position is taken as a first evaluation value, and the evaluation value between each candidate position and the target position is taken as a second evaluation value. The controller selects, from the plurality of candidate positions, a candidate position to which the respective second evaluation value is the smallest and the respective second evaluation value is smaller than the first evaluation value as a next position to be moved.
And step 110, controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position.
Specifically, after the controller screens out the next position to which the mechanical arm needs to move and the candidate gesture corresponding to the next position, the controller controls the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position, so as to complete the local path planning at the current time.
In one embodiment, the robot arm corresponds to a current posture at a current position and also corresponds to a corresponding candidate posture at a next position, and therefore, in the process of controlling the robot arm to move from the current position to the next position, the posture of the robot arm is dynamically adjusted, so that when the robot arm moves from the current position to the next position, the posture of the robot arm also changes from the current posture to the candidate posture corresponding to the next position.
And step 112, updating the next position to the current position, updating the candidate posture corresponding to the next position to the current posture, and returning to the step 104 to continue the execution until the mechanical arm reaches the target position.
Specifically, in the current local path planning process, the controller controls the mechanical arm to move to the next position according to the candidate gesture corresponding to the screened next position, the next position is used as the current position in the next local path planning process, the candidate gesture corresponding to the next position is used as the current gesture in the next local path planning process, whether the mechanical arm reaches the target position or not is judged based on the current position, the current gesture and the target position, if the mechanical arm reaches the target position and is not judged to need to be moved again, the next local path planning process is ended, otherwise, in the next local path planning process, gesture prediction is carried out based on the current gesture to obtain a plurality of candidate gestures, and the candidate position corresponding to each candidate gesture is obtained based on the current position and the plurality of candidate gestures, and screening a next position to be moved from the plurality of candidate positions according to the target position and the current position, controlling the mechanical arm to move to the next position according to the candidate posture corresponding to the screened next position, and so on until the mechanical arm reaches the target position, and finishing the path planning process of the mechanical arm.
According to the path planning method of the mechanical arm, when a motion path of the mechanical arm needs to be planned, a plurality of candidate postures are obtained based on the current posture prediction of the mechanical arm, a candidate position corresponding to each candidate posture is obtained based on the candidate postures and the current position of the mechanical arm, then the next position to which the mechanical arm needs to move is screened from the predicted candidate positions based on the target position and the current position of the mechanical arm, so that the local path planning of the mechanical arm is achieved, then the mechanical arm is controlled to move to the next position according to the candidate posture corresponding to the next position, the next local path planning is carried out based on the next position and the corresponding candidate posture, and the mechanical arm is controlled to move according to the planned local path until the mechanical arm is judged to reach the target position. Therefore, the automatic planning of the local path of the mechanical arm is realized based on the target position, the current position and the current posture of the mechanical arm, the mechanical arm is controlled to move according to the planned local path, the smoothness of the motion track of the mechanical arm can be improved, and the impact caused by the unsmooth motion track can be reduced.
In one embodiment, step 108, comprises: determining a first evaluation value based on the target position and the current position; respectively determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position; and screening the next position from the candidate positions based on the first evaluation value and the second evaluation value.
In one embodiment, the controller determines a first evaluation value corresponding to the current position according to a preset evaluation function based on the target position and the current position, and determines a second evaluation value corresponding to each candidate position according to the evaluation function based on the target position and the candidate position, whereby the second evaluation value corresponding to each candidate position can be determined separately. Further, the controller selects, as a next position to be moved to, a candidate position from the plurality of candidate positions to which the respective second evaluation value is the smallest and the respective second evaluation value is smaller than the first evaluation value, based on the second evaluation value corresponding to each candidate position.
In an embodiment, the preset evaluation function may be customized according to requirements, and the evaluation parameters defined in the evaluation function include position parameters in positions, and the evaluation function, for example, subtracts the position parameters in two positions (e.g., a target position and a current position) involved in the calculation respectively and finds absolute values, and sums the absolute values to obtain corresponding evaluation values, or, for example, subtracts the position parameters in two positions involved in the calculation respectively and finds a square, and sums the square values to obtain corresponding evaluation values, which are not listed one by one.
In one embodiment, an evaluation value calculated based on the current position/candidate position and the target position is used for representing the distance between the current position/candidate position and the target position, so that a candidate position closest to the target position can be screened from a plurality of candidate positions based on the evaluation value to be used as a next position to be moved, and the mechanical arm can be enabled to move to the target position quickly under the condition that smoothness of the motion trajectory is guaranteed.
In the above embodiment, the next position to be moved is selected from the plurality of candidate positions based on the evaluation value between the current position/each candidate position and the target position, so that when the robot arm is controlled to move according to the selected next position and the corresponding candidate posture, the robot arm can be rapidly moved to the target position while smoothness of the motion trajectory is ensured.
In one embodiment, the method for planning the path of the robot arm further includes: acquiring a target posture of the mechanical arm; determining a first evaluation value based on the target position and the current position, including: determining a first evaluation value based on the target position, the target posture, the current position and the current posture; determining a second evaluation value corresponding to each candidate position respectively based on the target position and each candidate position, comprising: and respectively determining a second evaluation value corresponding to each candidate position based on the target position, the target posture, each candidate position and the corresponding candidate posture.
The target posture is a posture required when the mechanical arm moves to the target position. Specifically, when the controller acquires the target position of the mechanical arm, the controller also correspondingly acquires the target posture of the mechanical arm. Further, the controller determines a first evaluation value corresponding to the current position based on the target position, the target posture, the current position, and the current posture of the robot arm according to a preset evaluation function, and determines a second evaluation value corresponding to each candidate position based on the target position, the target posture, each candidate position, and the candidate posture corresponding to the candidate position, respectively, whereby the second evaluation value corresponding to each candidate position can be obtained so as to screen a next position to be moved from the plurality of candidate positions according to the first evaluation value corresponding to the current position and the second evaluation value corresponding to each candidate position.
In one embodiment, the preset evaluation function is defined in a manner similar to that of the evaluation function provided in one or more embodiments of the present application, and in this embodiment, the evaluation parameters defined in the evaluation function further include a motion parameter in a posture.
In the above embodiment, the evaluation value is determined based on the position parameter in the position and the motion parameter in the posture, so that the smaller the evaluation value is, the closer the distance between the corresponding candidate position and the target position is represented, and the more similar the corresponding candidate posture and the target posture is, so as to screen the next position from the plurality of candidate positions according to the evaluation value, and when moving the robot arm with reference to the next position and the corresponding candidate posture, it can be ensured that the robot arm moves to the target position quickly and accurately, and the posture of the robot arm when moving to the target position is close enough to the target posture, so that the accuracy of the movement of the robot arm can be ensured.
In one embodiment, screening the candidate locations for a next location based on the first and second rating values comprises: screening candidate positions corresponding to the minimum second evaluation value from the candidate positions; if the smallest second evaluation value is smaller than the first evaluation value, the screened candidate position is determined as the next position.
Specifically, the controller, after determining a first evaluation value corresponding to the current position and a second evaluation value corresponding to each candidate position, compares the second evaluation values corresponding to the candidate positions to screen a candidate position corresponding to the smallest second evaluation value from among the plurality of candidate positions according to the comparison result, and compares the second evaluation value corresponding to the screened candidate position with the first evaluation value corresponding to the current position. If the second evaluation value corresponding to the screened candidate position is smaller than the first evaluation value, the controller determines the screened candidate position as the next position to which the mechanical arm needs to move.
In the above embodiment, the candidate position corresponding to the smallest second evaluation value smaller than the first evaluation value is selected from the plurality of candidate positions, and is used as the position to which the robot arm needs to move in the secondary local path planning process, so that when the robot arm is moved to the position according to the candidate posture corresponding to the position, the smoothness of the motion trajectory of the robot arm can be ensured, and the moving speed and accuracy of the robot arm can be improved.
In one embodiment, the method for planning the path of the robot arm further includes: when each second evaluation value is greater than or equal to the first evaluation value, judging that the mechanical arm reaches the target position; or when a second evaluation value which is within a preset error range and smaller than the first evaluation value exists in the second evaluation values, judging that the mechanical arm reaches the target position.
The preset error range can be determined dynamically according to the motion precision of the mechanical arm. The preset error range is used as one of the bases for judging whether the mechanical arm reaches the target position, so that when the mechanical arm cannot accurately move to the target position due to the movement precision of the mechanical arm, the mechanical arm can be guaranteed to move to the position closest to the target position relatively, and the mechanical arm is prevented from entering a dead cycle.
Specifically, in the current local path planning process, after determining a first evaluation value corresponding to the current position and a second evaluation value corresponding to each candidate position, the controller compares the second evaluation value corresponding to each candidate position with the first evaluation value, respectively. When all the second evaluation values are greater than or equal to the first evaluation value, the current position is represented as a position relatively closest to the target position, and the controller determines that the mechanical arm reaches the target position. When at least one second evaluation value smaller than the first evaluation value exists in the plurality of second evaluation values, the second evaluation value smaller than the first evaluation value is selected from the plurality of second evaluation values, and each selected second evaluation value is compared with a preset error range. If a second evaluation value within a preset error range exists in the screened second evaluation values, the candidate position corresponding to the second evaluation value within the preset error range is represented to be close to the target position, and the controller judges that the mechanical arm reaches the target position.
In the above embodiment, when all the second evaluation values are greater than or equal to the first evaluation value, the representation of the current position is a relatively optimal position, and the robot arm is not moved any more and is determined to reach the target position, that is, the current position is used as the end position to which the robot arm actually moves, so that the moving speed and accuracy of the robot arm can be ensured, and the smoothness of the motion trajectory can be improved. And when a candidate position which is more optimal than the current position and is close enough to the target position exists in the plurality of candidate positions, controlling the mechanical arm to move to the candidate position according to a candidate posture corresponding to the candidate position which is more optimal than the current position and is close enough to the target position, and judging that the mechanical arm reaches the target position, so that the candidate position which is more optimal than the current position and is close enough to the target position is taken as an end point position to which the mechanical arm actually moves.
In one embodiment, the method for planning the path of the robot arm further includes: acquiring the position of an obstacle; step 106, comprising: determining a plurality of predicted positions based on the current position and the candidate poses; candidate locations are filtered from a plurality of predicted locations based on the location of the obstacle.
The obstacle position is position coordinates/position information used for representing the position of the obstacle in the three-dimensional space, and specifically may include feature point positions corresponding to a plurality of feature points of the obstacle, where the plurality of feature points can uniquely determine the obstacle in the three-dimensional space. Taking the obstacle as a hexahedron as an example, eight vertexes of the hexahedron can be taken as feature points, and thus, positions of the obstacle corresponding to the hexahedron include positions of vertexes corresponding to the eight vertexes, respectively.
Specifically, the controller acquires the position of the obstacle when acquiring the target position of the robot arm. Further, after determining the predicted position corresponding to each candidate attitude according to the predicted position determination method provided in one or more embodiments of the present application and each candidate attitude, the controller determines a three-dimensional region corresponding to the obstacle in the three-dimensional space based on the obstacle position, compares each predicted position with the three-dimensional region corresponding to the obstacle, determines whether each predicted position is in the three-dimensional region corresponding to the obstacle, and selects, as a candidate position, a predicted position that is not in the three-dimensional region corresponding to the obstacle from among the plurality of predicted positions, so as to further select a next position to which movement is required to be performed from among the candidate positions, and when moving the robot arm according to the selected next position, it is possible to ensure that the motion of the robot arm is not affected by the obstacle.
In one embodiment, the controller modifies the obstacle contour based on the obstacle position after acquiring the obstacle position to avoid that the robot arm is stopped at the obstacle in advance when the target position is not reached due to the existence of the obstacle plane completely perpendicular to the movement path in the path planning process. It is understood that, after the obstacle position is acquired, the controller may further determine an obstacle contour based on the obstacle position, determine whether the obstacle contour needs to be modified based on the obstacle contour, modify the obstacle contour based on the obstacle position if the obstacle contour needs to be modified, and filter candidate positions from the plurality of predicted positions based on the obstacle position if the obstacle contour does not need to be modified. It can be understood that the controller determines whether the obstacle has an obstacle plane that may be completely perpendicular to the movement path based on the obstacle contour, and if so, determines that the obstacle contour needs to be modified.
Taking an obstacle as an example of a hexahedron, the controller judges that the outline of the corresponding obstacle needs to be modified based on the position of the obstacle, takes the maximum length of the obstacle as the diameter of a sphere, takes the center of mass of the obstacle as the center of the sphere, can determine the positions of all points on the spherical surface based on the center of the sphere and the diameter, and then transforms the spherical coordinate system to a Cartesian coordinate system through homogeneous transformation, namely determines obstacle information of the modified obstacle in the Cartesian coordinate system, so that candidate positions can be screened from a plurality of predicted positions based on the modified obstacle information.
As shown in fig. 3, in one embodimentIn an embodiment, a schematic diagram of a simulation effect of path planning of a robot arm is provided. Referring to fig. 3, the initial position of the end of the robot arm TCP in the cartesian coordinate system is [0, 0]]The target position is [60,60 ]]The position of the obstacle is
The obstacle is a hexahedron represented by the reference numeral 31, the target position and the obstacle position are used as constraint conditions, the local path planning mode provided by the application is adopted, a mechanical arm motion path which is relatively smooth and successfully bypasses the obstacle can be dynamically planned and obtained based on the current position, and the planned mechanical arm motion path is represented by the reference numeral 32.
In the above embodiment, under the condition that constraint conditions such as a target position and an obstacle position of the mechanical arm are given, the locally optimal motion path of the mechanical arm is dynamically planned based on the current position, the current posture and each constraint condition of the mechanical arm, so that when the mechanical arm is moved according to the locally optimal path, the smoothness of the motion path of the mechanical arm can be improved.
In one embodiment, the current pose includes: the current linear velocity, the current pitch angle and the current course angle; step 104, comprising: obtaining a plurality of predicted linear velocities based on the current linear velocity prediction; obtaining a plurality of predicted pitch angles based on the current pitch angle prediction; obtaining a plurality of predicted course angles based on the current course angle prediction; and arranging and combining the predicted linear velocity, the predicted pitch angle and the predicted course angle to obtain a plurality of candidate postures.
Specifically, the motion parameters in the current attitude include a current linear velocity, a current pitch angle, and a current heading angle. The controller predicts the speed based on the current linear speed to obtain a plurality of predicted linear speeds, predicts the angle based on the current pitch angle to obtain a plurality of predicted pitch angles, predicts the angle based on the current course angle to obtain a plurality of predicted course angles, and arranges and combines the predicted linear speeds, the predicted pitch angles and the predicted course angles to obtain a plurality of candidate postures.
In one embodiment, the controller obtains a plurality of linear accelerations and angular accelerations corresponding to the pitch angles and the heading angles respectively, obtains a plurality of predicted linear velocities according to the current linear velocity and the plurality of linear accelerations, obtains a plurality of predicted pitch angles according to the current pitch angle and the plurality of corresponding angular accelerations, and obtains a plurality of predicted heading angles according to the current heading angle and the plurality of corresponding angular accelerations. The controller may specifically predict the speed and angle, respectively, with reference to the following equations.
V[k]＝V[k-1]+∫f(Velocity_Accelerate)dt
Pitch[k]＝Pitch[k-1]+∫∫f(Pitch_Accelerate)dt
Yaw[k]＝Yaw[k-1]+∫∫f(Yaw_Accelerate)dt
Wherein k-1 represents the current time point, specifically the time point corresponding to the current position/current attitude, k represents the next time point, specifically the time point corresponding to the next position/next attitude, Vk-1, Pitch [ k-1] and Yaw [ k-1] respectively represent the linear Velocity, Pitch angle and heading angle corresponding to the current position/current attitude, that is, respectively represent the current linear Velocity, current Pitch angle and current heading angle, Vk, Pitch [ k ] and Yaw [ k ] respectively represent the linear Velocity, Pitch angle and heading angle possibly corresponding to the next position/next attitude, that is, respectively represent the predicted linear Velocity, predicted Pitch angle and predicted heading angle, Velocity _ pitchangle, Pi _ Accelerate and Yaw _ Accelerate respectively represent the linear acceleration, the angular acceleration corresponding to the Pitch angle and the heading angle, integral is denoted by ^ dt, and double integral is denoted by ^ jdct.
It can be understood that, according to the above formula, the linear accelerations are respectively integrated to obtain a plurality of corresponding linear velocities, and each linear velocity obtained by integration is respectively summed with the current linear velocity to obtain a corresponding predicted linear velocity, so that a plurality of predicted linear velocities can be obtained, and similarly, a plurality of predicted pitch angles and predicted heading angles can be obtained. Wherein the integral range of linear acceleration/angular acceleration is [ k-1, k ].
In one embodiment, the plurality of linear accelerations and angular accelerations are determined by the maximum linear acceleration and the maximum angular acceleration corresponding to the mechanical arm, respectively, and the maximum linear acceleration and the maximum angular acceleration are determined by the performance and/or parameters of the mechanical arm itself. The controller can receive a plurality of linear accelerations manually recorded or transmitted by other computer equipment, can dynamically determine the plurality of linear accelerations according to the maximum linear acceleration and the preset acceleration number, and can dynamically determine the plurality of linear accelerations according to the maximum linear acceleration and the preset acceleration value step length. The controller can acquire a plurality of angular accelerations corresponding to the pitch angle and the heading angle in a similar manner, and details are not repeated herein.
In the above embodiment, a plurality of candidate poses possible for the next pose are dynamically predicted based on each motion parameter in the current pose, so that all positions that the mechanical arm may reach are further determined based on the plurality of candidate poses that are dynamically predicted, and a next position to be moved is screened from all the positions that the mechanical arm may reach, so that when the mechanical arm is moved according to the local path planning method, smoothness of a motion trajectory of the mechanical arm can be ensured.
As shown in fig. 4, in one embodiment, a schematic diagram of a path planning method for a robot arm is provided. Referring to fig. 4, at the beginning of the whole path planning process of the robot arm, the controller acquires a target position and a target attitude of the robot arm, predicts a motion window of each motion parameter based on a current attitude, respectively obtains a plurality of predicted linear velocities, predicted pitch angles, and predicted course angles, performs permutation and combination on the prediction results to obtain a plurality of candidate attitudes, obtains a plurality of candidate positions based on the current position and each candidate attitude, determines a first evaluation value based on the target position, the target attitude, the current position, and the current attitude, determines a second evaluation value based on the target position, the target attitude, each candidate position, and the candidate attitude, and determines whether all the second evaluation values are greater than or equal to the first evaluation value, if yes, determines that the robot arm reaches the target position, and ends the path planning process, if no, determines whether a second evaluation value within a preset error range exists in each second evaluation value, and if so, judging that the mechanical arm reaches the target position, ending the path planning process, otherwise, screening a next position from the candidate positions based on the first evaluation value and the second evaluation value, controlling the mechanical arm to move to the next position according to the corresponding candidate posture, updating the next position to the current position, updating the candidate posture corresponding to the next position to the current posture, and returning to the step of predicting the motion window of each motion parameter based on the current posture to continue execution.
In the above embodiment, under the condition that constraint conditions such as a target position and a target attitude are given, the local optimal path is screened by exhaustively exhausting all motion parameters (linear velocity, pitch angle, course angle and the like) of the mechanical arm, and the mechanical arm is controlled to move according to the local optimal path, so that the smoothness of the motion track of the mechanical arm can be improved.
It should be understood that although the steps in the flowcharts of fig. 1 and 4 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 and 4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternatively with other steps or at least a portion of the other steps or stages.
In one embodiment, as shown in fig. 5, there is provided a path planning apparatus 500 for a robot arm, including: an obtaining module 501, a predicting module 502, a determining module 503, a screening module 504, a controlling module 505, and an updating module 506, wherein:
an obtaining module 501, configured to obtain a target position, a current position, and a current posture of a mechanical arm;
a prediction module 502, configured to perform pose prediction based on a current pose to obtain multiple candidate poses;
a determining module 503 for determining a plurality of candidate positions based on the current position and the candidate poses;
a screening module 504, configured to screen a next location from the candidate locations according to the target location and the current location;
the control module 505 is configured to control the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
an updating module 506, configured to update the next position to the current position, and update the candidate pose corresponding to the next position to the current pose.
In one embodiment, the filtering module 504 is further configured to determine a first evaluation value based on the target position and the current position; respectively determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position; and screening the next position from the candidate positions based on the first evaluation value and the second evaluation value.
In one embodiment, the obtaining module 501 is further configured to obtain a target pose of the robot arm; the screening module 504 is further configured to determine a first evaluation value based on the target position, the target pose, the current position, and the current pose; and respectively determining a second evaluation value corresponding to each candidate position based on the target position, the target posture, each candidate position and the corresponding candidate posture.
In an embodiment, the screening module 504 is further configured to screen a candidate position corresponding to the smallest second evaluation value from the candidate positions; if the smallest second evaluation value is smaller than the first evaluation value, the screened candidate position is determined as the next position.
In one embodiment, the screening module 504 is further configured to determine that the robot arm reaches the target position when each of the second evaluation values is greater than or equal to the first evaluation value; or when a second evaluation value which is within a preset error range and smaller than the first evaluation value exists in the second evaluation values, judging that the mechanical arm reaches the target position.
In one embodiment, the obtaining module 501 is further configured to obtain a position of an obstacle; a determining module 503, further configured to determine a plurality of predicted positions based on the current position and the candidate poses; candidate locations are filtered from a plurality of predicted locations based on the location of the obstacle.
In one embodiment, the current pose includes: the current linear velocity, the current pitch angle and the current course angle; the prediction module 502 is further configured to obtain a plurality of predicted linear velocities based on the current linear velocity prediction; obtaining a plurality of predicted pitch angles based on the current pitch angle prediction; obtaining a plurality of predicted course angles based on the current course angle prediction; and arranging and combining the predicted linear velocity, the predicted pitch angle and the predicted course angle to obtain a plurality of candidate postures.
For specific definition of the path planning device of the robot arm, reference may be made to the above definition of the path planning method of the robot arm, and details are not described here. All or part of each module in the path planning device of the mechanical arm can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a controller, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of path planning for a robot arm. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory having a computer program stored therein and a processor that implements the steps of the method embodiments when the processor executes the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the respective method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for path planning of a robot arm, the method comprising:
acquiring a target position, a current position and a current posture of the mechanical arm;
performing attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
determining a plurality of candidate positions based on the current position and the candidate poses; the candidate position corresponds to the candidate pose;
screening a next position from the candidate positions according to the target position and the current position;
controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and updating the next position to be the current position, updating the candidate posture corresponding to the next position to be the current posture, returning to the step of predicting the posture based on the current posture to obtain a plurality of candidate postures, and continuing to execute until the mechanical arm is judged to reach the target position.
2. The method of claim 1, wherein the filtering the next location from the candidate locations according to the target location and the current location comprises:
determining a first evaluation value based on the target position and the current position;
respectively determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position;
and screening a next position from the candidate positions based on the first evaluation value and the second evaluation value.
3. The method of claim 2, further comprising:
acquiring a target posture of the mechanical arm;
the determining a first evaluation value based on the target position and the current position includes:
determining a first evaluation value based on the target position, the target attitude, the current position, and the current attitude;
the determining a second evaluation value corresponding to each candidate position based on the target position and each candidate position includes:
and respectively determining a second evaluation value corresponding to each candidate position based on the target position, the target posture, each candidate position and the corresponding candidate posture.
4. The method of claim 2, wherein the screening the candidate locations for a next location based on the first and second evaluation values comprises:
screening candidate positions corresponding to the smallest second evaluation value from the candidate positions;
and if the minimum second evaluation value is smaller than the first evaluation value, determining the screened candidate position as a next position.
5. The method of claim 2, further comprising:
determining that the robot arm reaches the target position when each of the second evaluation values is greater than or equal to the first evaluation value; or the like, or, alternatively,
and when a second evaluation value which is within a preset error range and smaller than the first evaluation value exists in the second evaluation values, judging that the mechanical arm reaches the target position.
6. The method according to any one of claims 1 to 5, further comprising:
acquiring the position of an obstacle;
the determining a plurality of candidate positions based on the current position and the candidate poses comprises:
determining a plurality of predicted positions based on the current position and the candidate poses;
screening candidate locations from the plurality of predicted locations based on the obstacle location.
7. The method of any of claims 1 to 5, wherein the current pose comprises: the current linear velocity, the current pitch angle and the current course angle; the obtaining a plurality of candidate postures by performing posture prediction based on the current posture comprises:
obtaining a plurality of predicted linear velocities based on the current linear velocity prediction;
obtaining a plurality of predicted pitch angles based on the current pitch angle prediction;
obtaining a plurality of predicted course angles based on the current course angle prediction;
and arranging and combining the predicted linear velocity, the predicted pitch angle and the predicted course angle to obtain a plurality of candidate postures.
8. A path planning apparatus for a robot arm, the apparatus comprising:
the acquisition module is used for acquiring the target position, the current position and the current posture of the mechanical arm;
the prediction module is used for carrying out attitude prediction based on the current attitude to obtain a plurality of candidate attitudes;
a determination module to determine a plurality of candidate positions based on the current position and the candidate poses;
a screening module for screening a next position from the candidate positions according to the target position and the current position;
the control module is used for controlling the mechanical arm to move to the next position according to the candidate gesture corresponding to the next position;
and the updating module is used for updating the next position to be the current position and updating the candidate posture corresponding to the next position to be the current posture.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110805844.3A CN113561175B (en) | 2021-07-16 | 2021-07-16 | Path planning method and device of mechanical arm, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110805844.3A CN113561175B (en) | 2021-07-16 | 2021-07-16 | Path planning method and device of mechanical arm, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113561175A true CN113561175A (en) | 2021-10-29 |
| CN113561175B CN113561175B (en) | 2023-04-11 |
Family
ID=78165140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110805844.3A Active CN113561175B (en) | 2021-07-16 | 2021-07-16 | Path planning method and device of mechanical arm, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113561175B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116690585A (en) * | 2023-07-25 | 2023-09-05 | 上海汇丰医疗器械股份有限公司 | Shadowless lamp path planning method and device based on automatic mechanical arm |
| CN116901074A (en) * | 2023-08-03 | 2023-10-20 | 南京云创大数据科技股份有限公司 | Mechanical arm track planning method and device, storage medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268031A (en) * | 2016-12-30 | 2018-07-10 | 深圳光启合众科技有限公司 | Paths planning method, device and robot |
| CN110413007A (en) * | 2019-08-30 | 2019-11-05 | 中国科学技术大学 | Control method, system, electronic equipment and the medium in unmanned plane during flying path |
| CN110549339A (en) * | 2019-09-11 | 2019-12-10 | 上海软中信息系统咨询有限公司 | navigation method, navigation device, navigation robot and storage medium |
| US20190375094A1 (en) * | 2018-06-14 | 2019-12-12 | Lg Electronics Inc. | Moving robot and operating method for the same |
| CN110850807A (en) * | 2019-12-04 | 2020-02-28 | 广东博智林机器人有限公司 | Singular point avoiding method, device, equipment and medium |
| CN111290385A (en) * | 2020-02-19 | 2020-06-16 | 深圳前海达闼云端智能科技有限公司 | Robot path planning method, robot, electronic device and storage medium |
| CN111546327A (en) * | 2019-01-28 | 2020-08-18 | 罗伯特·博世有限公司 | Method, apparatus and computer program for determining a motion or trajectory of a robot |
-
2021
- 2021-07-16 CN CN202110805844.3A patent/CN113561175B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268031A (en) * | 2016-12-30 | 2018-07-10 | 深圳光启合众科技有限公司 | Paths planning method, device and robot |
| US20190375094A1 (en) * | 2018-06-14 | 2019-12-12 | Lg Electronics Inc. | Moving robot and operating method for the same |
| CN111546327A (en) * | 2019-01-28 | 2020-08-18 | 罗伯特·博世有限公司 | Method, apparatus and computer program for determining a motion or trajectory of a robot |
| CN110413007A (en) * | 2019-08-30 | 2019-11-05 | 中国科学技术大学 | Control method, system, electronic equipment and the medium in unmanned plane during flying path |
| CN110549339A (en) * | 2019-09-11 | 2019-12-10 | 上海软中信息系统咨询有限公司 | navigation method, navigation device, navigation robot and storage medium |
| CN110850807A (en) * | 2019-12-04 | 2020-02-28 | 广东博智林机器人有限公司 | Singular point avoiding method, device, equipment and medium |
| CN111290385A (en) * | 2020-02-19 | 2020-06-16 | 深圳前海达闼云端智能科技有限公司 | Robot path planning method, robot, electronic device and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116690585A (en) * | 2023-07-25 | 2023-09-05 | 上海汇丰医疗器械股份有限公司 | Shadowless lamp path planning method and device based on automatic mechanical arm |
| CN116690585B (en) * | 2023-07-25 | 2024-01-12 | 上海汇丰医疗器械股份有限公司 | Shadowless lamp path planning method and device based on automatic mechanical arm |
| CN116901074A (en) * | 2023-08-03 | 2023-10-20 | 南京云创大数据科技股份有限公司 | Mechanical arm track planning method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113561175B (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113561175B (en) | Path planning method and device of mechanical arm, computer equipment and storage medium | |
| EP3410246B1 (en) | Robot obstacle avoidance control system and method, robot, and storage medium | |
| US11235461B2 (en) | Controller and machine learning device | |
| US11537130B2 (en) | Robot plan online adjustment | |
| EP3126936B1 (en) | Portable apparatus for controlling robot and method thereof | |
| CN109683175A (en) | Laser radar configuration method, device, equipment and storage medium | |
| JP2019135076A (en) | Locus generation method and device | |
| EP1795315A1 (en) | Hand-held control device for an industrial robot | |
| US11559893B2 (en) | Robot control for avoiding singular configurations | |
| KR20240052808A (en) | Multi-robot coordination using graph neural networks | |
| CN113119104A (en) | Mechanical arm control method, mechanical arm control device, computing equipment and system | |
| CN114260899A (en) | Hand-eye calibration method and device, electronic equipment and computer readable storage medium | |
| WO2021231242A1 (en) | Accelerating robotic planning for operating on deformable objects | |
| US11691283B2 (en) | Robot control parameter interpolation | |
| CN106826814B (en) | Motion control method and motion control system of robot | |
| Rottmann et al. | Adaptive autonomous control using online value iteration with gaussian processes | |
| CN114800523B (en) | Mechanical arm track correction method, system, computer and readable storage medium | |
| CN116038686B (en) | Robot singular point avoidance method, apparatus, computer device, and storage medium | |
| CN114454180B (en) | Motion control method and device of mobile robot and mobile robot | |
| CN113658247B (en) | Instrument space prediction method, apparatus, computer device and storage medium | |
| CN114571460A (en) | Robot control method, device and storage medium | |
| CN110948489B (en) | Method and system for limiting safe working space of live working robot | |
| CN112135718B (en) | Control of robots | |
| Pajak et al. | Planning of a point to point collision-free trajectory for mobile manipulators | |
| CN114083545B (en) | Moving object robot grabbing method and device based on visual perception |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |