Robot control method and apparatus, and robot, readable storage medium and computer program product

Abstract

A robot control method and apparatus, and a robot, a readable storage medium and a computer program product. The method comprises: collecting point cloud and image data of a target object to be grasped, and on the basis of the point cloud and image data, establishing a three-dimensional model of the target object; on the basis of the three-dimensional model, determining an easy-to-grasp part of the target object; when the current position and orientation of a chassis of a robot remain unchanged, determining a set of positions and orientations reachable by a robotic arm at the current position and orientation; controlling the robotic arm to move the target object until the position and orientation of the easy-to-grasp part fall within the set of positions and orientations; and controlling the robotic arm to grasp the easy-to-grasp part.

Description

Robot control method and device, robot, readable storage medium and computer program product

[0001] Cross-reference to Related Applications

[0002] This application claims priority to Chinese Patent Application No. 2024113207371, filed on September 20, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of robots, and in particular to a robot control method and device, a robot, a readable storage medium and a computer program product. BACKGROUND

[0004] With the development of automation technology, robots are increasingly entering people's lives, such as floor cleaning robots and express sorting robots. There are various types and functions of robots, among which robots with mechanical arms are widely used due to their ability to grasp objects.

[0005] Currently, for robots with mechanical arms, due to the limitations of the structure and degrees of freedom of the mechanical arm itself, the robot often fails to grasp objects, i.e., there is a low success rate of grasping. SUMMARY

[0006] The present disclosure provides a robot control method and device, a robot, a readable storage medium and a computer program product, which improve the success rate of grasping objects by robots with mechanical arms.

[0007] In one aspect, a robot control method is provided according to some embodiments of the present disclosure, applied to a robot with a mechanical arm, the method comprising: collecting point cloud and image data of a target object to be grasped, and establishing a three-dimensional model of the target object according to the point cloud and image data; determining an easy-to-grasp part on the target object based on the three-dimensional model;

[0008] In the case where the chassis of the robot remains unchanged in the current position and posture, determining a set of position and postures that the mechanical arm can reach in the current position and posture; and controlling the mechanical arm to move the target object until the position and posture of the easy-to-grasp part is in the set of position and postures; and controlling the mechanical arm to grasp the easy-to-grasp part.

[0009] In some embodiments, the determining of the easy-to-grasp part on the target object based on the three-dimensional model comprises:

[0010] Obtaining an easy-to-grasp score of each part on the three-dimensional model, the easy-to-grasp score representing the success rate of grasping each part of the target object;

[0011] determining the easy-to-grab part according to the easy-to-grab score.

[0012] In some embodiments, the determining the easy-to-grab part according to the easy-to-grab score comprises:

[0013] determining the easy-to-grab part as any part on the target object with the easy-to-grab score higher than a preset score threshold.

[0014] In some embodiments, the determining the easy-to-grab part according to the easy-to-grab score comprises:

[0015] determining the easy-to-grab part as the part on the target object with the largest easy-to-grab score.

[0016] In some embodiments, the determining the set of position and posture that the robot arm can reach in the current position and posture comprises:

[0017] solving the set of position and posture that the robot arm can reach in the current position and posture by an inverse kinematics model.

[0018] In some embodiments, the controlling the robot arm to move the target object comprises:

[0019] controlling the robot arm to move the target object based on a principle of moving the position and posture of the easy-to-grab part to a center point of the set of position and posture.

[0020] In some embodiments, the controlling the robot arm to grab the easy-to-grab part comprises:

[0021] calculating a motion trajectory of the robot arm according to the position and posture of the easy-to-grab part;

[0022] controlling the robot arm to move to the easy-to-grab part along the motion trajectory;

[0023] controlling the robot arm to grab the easy-to-grab part.

[0024] In some embodiments, the controlling the robot arm to move to the easy-to-grab part along the motion trajectory comprises:

[0025] controlling the robot arm to move along the motion trajectory by controlling the chassis to rotate and the joint angle of the robot arm.

[0026] In some embodiments, the determining the set of position and posture that the robot arm can reach in the current position and posture comprises:

[0027] controlling the chassis to move and rotate to a different position and posture.

[0028] determine a set of position postures that the mechanical arm can reach in the current position posture of the chassis;

[0029] if the position posture of the easy-to-grab part is outside all the sets of position postures, determine a set of position postures that the mechanical arm can reach in the current position posture of the chassis.

[0030] In a second aspect, some embodiments of the present disclosure provide a robot control device applied to a robot with a mechanical arm, the device comprising: a modeling module configured to collect point cloud and image data of a target object to be grabbed, and establish a three-dimensional model of the target object based on the point cloud and image data; a determination module configured to determine an easy-to-grab part on the target object based on the three-dimensional model, and determine a set of position postures that the mechanical arm can reach in a current position posture of a chassis of the robot; and a control module configured to control the mechanical arm to move the target object until a position posture of the easy-to-grab part is in the set of position postures, and control the mechanical arm to grab the easy-to-grab part.

[0031] In a third aspect, some embodiments of the present disclosure provide a robot, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the robot control methods.

[0032] In some embodiments, the robot is a sweeping robot.

[0033] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of any one of the robot control methods.

[0034] In a fifth aspect, some embodiments of the present disclosure provide a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the steps of any one of the robot control methods.

[0035] The one or more technical solutions provided by the present disclosure have at least the following technical effects or advantages:

[0036] The present disclosure first establishes a three-dimensional model of a target object, determines an easy-to-grab part on the target object based on the three-dimensional model, that is, determines a part on the target object with a high success rate of grabbing, then determines a set of position postures that a mechanical arm can reach in a current position posture of a chassis, controls the mechanical arm to move the target object until a position posture of the easy-to-grab part is in the set of position postures, and controls the mechanical arm to grab the easy-to-grab part, thereby improving the success rate of the robot in grabbing the object. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 is a schematic diagram of a robot according to some embodiments of the present disclosure;

[0039] Figure 2 is a schematic diagram of a robot grasping a cup according to some embodiments of the present disclosure;

[0040] Figure 3 is a flowchart of a robot control method according to some embodiments of the present disclosure;

[0041] Figure 4 is a schematic diagram of a robot control method according to some embodiments of the present disclosure;

[0042] Figure 5 is a schematic diagram of a robot control device according to some embodiments of the present disclosure.

[0043] The correspondence between the reference numerals and component names in the attached drawings is as follows:

[0044] 11. Robotic arm; 12. Chassis; 21. Cup body; 22. Handle. Embodiments of the present invention

[0045] According to some embodiments of this disclosure, a robot control method, apparatus, robot, readable storage medium, and computer program product are provided to solve the technical problem of how to improve the success rate of a robot with a robotic arm grasping objects.

[0046] To better understand the technical solution of this disclosure, the technical solution of this disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0047] As shown in Figure 1, a robot with a robotic arm consists of a chassis and a robotic arm. The robotic arm is mounted on the chassis. The chassis can move and rotate. The robotic arm can extend and retract. The robot's position can be changed by controlling the movement of the chassis, the orientation of the robotic arm can be changed by controlling the rotation of the chassis, and the extension and retraction of the robotic arm can be controlled by controlling the joint angles of the robotic arm. A camera is generally mounted on the chassis. A camera can also be mounted on the end effector of the robotic arm. When the robot grasps an object, it first moves the chassis to the vicinity of the object, then rotates the chassis so that the robotic arm faces the object, and finally extends the robotic arm to grasp the object.

[0048] In some embodiments, the scenario in which the robot has a low success rate of grasping an object includes: the robot can only reach a non-graspable part of the object but cannot reach a graspable part of the object; the non-graspable part is a part of the object with a low success rate of grasping, and the graspable part is a part of the object with a high success rate of grasping. In this scenario, the robot can only grasp the non-graspable part of the object, resulting in a low success rate of grasping. Taking a cup with a handle as an example, assuming that the non-graspable part of the cup is the cup body and the graspable part is the handle, as shown in FIG. 2, the scenario can be: the robot cannot grasp the cup body due to the limited opening angle of the robot arm but can grasp the handle, the cup is located at the foot of the wall and the handle is facing the foot of the wall, and since the wall and the cup body block the robot arm from reaching the handle, the robot arm cannot grasp the handle and can only grasp the cup body, resulting in a low success rate of grasping.

[0049] To solve the problem of a low success rate of grasping an object by a robot in the scenario described above, a robot control method applied to a robot with a robot arm is proposed according to some embodiments of the present disclosure, as shown in FIG. 3, which includes steps S1-S5.

[0050] In step S1, point cloud and image data of a target object to be grasped are collected, and a three-dimensional model of the target object is established based on the point cloud and image data;

[0051] In some embodiments, the robot chassis can be controlled to move and rotate around the target object, and the robot arm can be controlled to move; the camera on the chassis and the camera at the end of the robot arm can be controlled to scan the target object multiple times; the point cloud and image data of each part of the target object can be collected multiple times; and the point cloud and image data of each part can be spliced to establish a three-dimensional model of the target object;

[0052] In step S2, a graspable part on the target object is determined based on the three-dimensional model;

[0053] The graspable part on the three-dimensional model should be determined, and the part on the target object that is the same as the graspable part is the graspable part on the target object; as mentioned above, the robot arm has a high success rate of grasping the graspable part, such as a success rate of grasping higher than 80%; there can be multiple graspable parts, and the success rate of grasping each graspable part can be different. For example, the graspable part can be a part of the handle of the cup in FIG. 2, or any part of the handle, and the success rate of grasping each part of the handle is different;

[0054] In step S3, a set of position and posture that the robot arm can reach under the current position and posture of the robot is determined while the chassis of the robot remains unchanged in the current position and posture;

[0055] The set of reachable positions and postures of the mechanical arm has the following characteristics: as long as the position and posture of the easy-to-grab part of the target object is in the set of positions and postures, the mechanical arm can grab the easy-to-grab part; considering that if the position and posture of the chassis is uncertain, the set of positions and postures that the mechanical arm can reach under the position and posture of the chassis is also uncertain, therefore, the purpose of controlling the chassis to maintain the current position and posture is to ensure that a certain set of positions and postures can be obtained, thereby providing a clear moving direction for subsequent moving of the target object; the current position and posture maintained by the chassis needs to ensure that the mechanical arm can reach the target object, otherwise the mechanical arm cannot move the target object subsequently, for example, the current position and posture maintained by the chassis needs to ensure that the mechanical arm can reach the cup body;

[0056] In step S4, the mechanical arm is controlled to move the target object until the position and posture of the easy-to-grab part is in the set of positions and postures;

[0057] Since the mechanical arm cannot grab the target object at this time, the way in which the mechanical arm moves the target object can be to move other parts of the target object to change the position and posture of the target object, thereby changing the position and posture of the easy-to-grab part; for example, in FIG. 4, the cup body can be moved towards the position of the robot to move, so that the handle is closer to the robot, so that the mechanical arm can reach the handle;

[0058] In step S5, the mechanical arm is controlled to grab the easy-to-grab part;

[0059] For the mechanical arm, the easy-to-grab part should exist in the form of position and posture data, and controlling the mechanical arm to grab the easy-to-grab part is to control the mechanical arm to move to the position and posture of the easy-to-grab part and then grab.

[0060] As can be seen from the above, in the robot control method provided according to some embodiments of the present disclosure, a three-dimensional model of the target object is first established, and then the easy-to-grab part on the target object is determined based on the three-dimensional model, that is, the part on the target object with a high success rate of grabbing is determined; then the set of positions and postures that the mechanical arm can reach under the current position and posture of the chassis is determined, and the mechanical arm is controlled to move the target object until the position and posture of the easy-to-grab part is in the set of positions and postures; at this time, the success rate of the mechanical arm grabbing the easy-to-grab part is high, that is, the success rate of the robot grabbing the object is improved.

[0061] In some embodiments, step S2 can include: obtaining an easy-to-grab score of each part on the three-dimensional model, the easy-to-grab score representing the success rate of grabbing each part of the target object; and determining the easy-to-grab part according to the easy-to-grab score.

[0062] The higher the easy-grab score of a part is, the higher the success rate of grabbing the part is. The easy-grab score of each part on the three-dimensional model of the target object can be calculated by a known grab point selection evaluation algorithm, or a grab experiment can be performed on a plurality of objects in advance; for each object, the success rate of grabbing each part of the object is tested, and then the three-dimensional standard model of each object and the success rate of grabbing each part on the three-dimensional standard model of each object are stored in a database; when the target object needs to be grabbed, the three-dimensional standard model identical to the three-dimensional model of the target object is searched in the database, and the success rate of grabbing each part on the three-dimensional standard model is the easy-grab score of each part on the three-dimensional model of the target object. Of course, it is impossible to store the three-dimensional standard models of all objects in the database, and the latter way of obtaining the easy-grab score has certain limitations.

[0063] According to the easy-grab score, the easy-grab part can be determined as any part on the target object with an easy-grab score higher than a preset score threshold. The preset score threshold can be regarded as a demarcation line of the success rate of grabbing, and the preset score threshold can be 80%. The easy-grab score of a part higher than the preset score threshold represents that the success rate of grabbing the part is high. The easy-grab score of a part lower than the preset score threshold represents that the success rate of grabbing the part is low. If the easy-grab score of any part of the handle in FIG. 2 is higher than the preset score threshold, the easy-grab part is any part of the handle, and in this case, step S4 only needs to move the cup body to make the position and posture of the any part of the handle in the position and posture set.

[0064] The easy-grab part being any part on the target object with an easy-grab score higher than a preset score threshold can make the position and posture of the easy-grab part in the position and posture set faster, but the success rate of grabbing is not the highest. If it is necessary to ensure that the success rate of grabbing is the highest, in step S2, according to the easy-grab score, the easy-grab part can also be determined as a part on the target object with the maximum easy-grab score. The maximum easy-grab score represents the highest success rate of grabbing, and in this case, the easy-grab part is the part with the highest success rate of grabbing, and step S4 needs to move the target object to make the position and posture of the part with the highest success rate of grabbing in the position and posture set. If the success rate of grabbing the outermost part of the handle in FIG. 2 is the highest, step S4 needs to move the cup body to make the position and posture of the outermost part of the handle in the position and posture set, and in this case, the speed of making the position and posture of the easy-grab part in the position and posture set can be slightly slower.

[0065] In some embodiments, step S3 can include solving the position and posture set that the robot arm can reach in the current position and posture by an inverse kinematics model. The solving principle of the inverse kinematics model is relatively common, and will not be described in detail here.

[0066] In some embodiments, step S4 can control the mechanical arm to move the target object in any direction at will, but this will cause the time required for the position and posture of the easy-to-grab part to be in the position and posture set to be long and the efficiency to be low. In order to improve the efficiency of the position and posture of the easy-to-grab part in the position and posture set, in step S4, the control of the mechanical arm to move the target object can include: based on the principle of moving the position and posture of the easy-to-grab part to the center point of the position and posture set, controlling the mechanical arm to move the target object. The center point of the position and posture set can be the average of all position and posture data. Moving the easy-to-grab part towards the center point of the position and posture set can make the motion distance of the easy-to-grab part shorter, thereby improving the efficiency of the position and posture of the easy-to-grab part in the position and posture set.

[0067] In some embodiments, step S5 can include: calculating a motion trajectory of the mechanical arm according to the position and posture of the easy-to-grab part; controlling the mechanical arm to move along the motion trajectory to the easy-to-grab part; and controlling the mechanical arm to grab the easy-to-grab part. That is, after the position and posture of the easy-to-grab part is in the position and posture set that the mechanical arm can reach, it is necessary to calculate the motion trajectory of the mechanical arm according to the current position and posture of the easy-to-grab part before grabbing.

[0068] In some embodiments, if the mechanical arm is currently just towards the easy-to-grab part, the mechanical arm can move along the motion trajectory without rotating the chassis; but if the mechanical arm is not currently towards the easy-to-grab part, the mechanical arm may not be able to move along the motion trajectory only by relying on the motion of the mechanical arm, at this time the chassis needs to be rotated to cooperate, that is, in step S5, the control of the mechanical arm to move along the motion trajectory to the easy-to-grab part can include: controlling the mechanical arm to move along the motion trajectory by controlling the rotation of the chassis and the joint angle of the mechanical arm.

[0069] It can be understood that the basic principle of the robot control method in the embodiments of the present disclosure is to enable the mechanical arm to grab the easy-to-grab part in the case that the mechanical arm cannot grab the easy-to-grab part, so the robot control method only needs to be implemented in the case that the mechanical arm cannot grab the easy-to-grab part, that is, it is necessary to determine whether the mechanical arm can grab the easy-to-grab part before implementing the robot control method. Therefore, step S3 can further include: controlling the chassis to move and rotate to different position and postures; determining the position and posture set that the mechanical arm can reach at each position and posture of the chassis; and if the position and posture of the easy-to-grab part is outside all position and posture sets, determining the position and posture set that the mechanical arm can reach at the current position and posture. The position and posture of the easy-to-grab part being outside all position and posture sets means that the mechanical arm cannot grab the easy-to-grab part no matter how the chassis moves and rotates, at this time it is necessary to move the target object, which can avoid unnecessary movement of the target object.

[0070] As shown in FIG. 5, the robot control device applied to the robot with the mechanical arm according to some embodiments of the present disclosure comprises:

[0071] a modeling module configured to collect point cloud and image data of a target object to be grabbed, and establish a three-dimensional model of the target object based on the point cloud and the image data;

[0072] a determining module configured to determine a grabbable part on the target object based on the three-dimensional model;

[0073] and determine a set of position and posture that the mechanical arm can reach under the current position and posture of the robot, without changing the current position and posture of the chassis of the robot;

[0074] a control module configured to control the mechanical arm to move the target object until the position and posture of the grabbable part is in the set of position and posture; and

[0075] control the mechanical arm to grab the grabbable part.

[0076] In some embodiments, the determining module can be configured to:

[0077] obtain a grabbable score of each part on the three-dimensional model, the grabbable score representing a success rate of grabbing each part of the target object;

[0078] determine the grabbable part based on the grabbable score.

[0079] In some embodiments, the determining module can be configured to:

[0080] determine the grabbable part as any part on the target object with a grabbable score higher than a preset score threshold.

[0081] In some embodiments, the determining module can be configured to:

[0082] determine the grabbable part as a part on the target object with the highest grabbable score.

[0083] In some embodiments, the determining module can be configured to:

[0084] obtain the set of position and posture that the mechanical arm can reach under the current position and posture of the robot by solving an inverse kinematics model.

[0085] In some embodiments, the control module can be configured to:

[0086] control the mechanical arm to move the target object based on a principle of moving the position and posture of the grabbable part to a center point of the set of position and posture.

[0087] In some embodiments, the control module can be configured to:

[0088] The motion trajectory of the robotic arm is calculated based on the position and orientation of the easily graspable parts;

[0089] Control the robotic arm to move along the motion trajectory to an easily graspable part;

[0090] Control the robotic arm to grasp easily graspable parts.

[0091] In some implementations, the control module can be used for:

[0092] The movement of the robotic arm along the motion trajectory is controlled by controlling the rotation of the chassis and the joint angles of the robotic arm.

[0093] In some implementations, the determining module can be used for:

[0094] Control the chassis to move and rotate to different positions and postures;

[0095] Determine the set of positions and orientations that the robotic arm can achieve under each position and orientation of the chassis;

[0096] If the position and orientation of the easily graspable part are outside the set of all position and orientations, then the set of position and orientations that the robotic arm can reach under the current position and orientation is determined.

[0097] Based on the same inventive concept as the robot control method described above, according to some embodiments of this disclosure, a robot is also provided, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of any of the robot control methods described above. In some embodiments, the robot may be a sweeping robot.

[0098] Since the robot described in this disclosure is the robot used to implement the robot control method in this disclosure, those skilled in the art can understand the specific implementation methods and various variations of the robot in this disclosure based on the robot control method described in this disclosure. Therefore, how the robot implements the method in this disclosure will not be described in detail here. Any robot used by those skilled in the art to implement the robot control method in this disclosure falls within the scope of protection intended by this disclosure.

[0099] Based on the same inventive concept as the robot control method described above, this disclosure also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any robot control method.

[0100] Based on the same inventive concept as the robot control method described above, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any robot control method.

[0101] Those skilled in the art will appreciate that embodiments of the disclosure can be supplied as a method, a system, or a computer program product. Accordingly, the disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the disclosure can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer-readable program code.

[0102] The disclosure is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the disclosure. It should be understood that each flow and / or block in the flowchart and / or block diagrams, and a combination of flows and / or blocks in the flowchart and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate means for implementing the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means, which implement the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operational steps are performed on the computer or other programmable data processing apparatus to generate a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0105] Although preferred embodiments of the disclosure have been described, those skilled in the art will appreciate that additional modifications and variations to the preferred embodiments can be made without departing from the spirit and scope of the disclosure. Accordingly, it is intended that the appended claims be interpreted as including all such alterations and modifications as fall within the scope of the disclosure.

[0106] It is apparent that a person skilled in the art can make various changes and modifications to the disclosure without departing from the spirit and scope of the disclosure. Thus, if these modifications and variations of the disclosure fall within the scope of the claims of the disclosure and their equivalents, the disclosure is also intended to include these changes and modifications.

Claims

1. A robot control method applied to a robot with a mechanical arm, the method comprising: collecting point cloud and image data of a target object to be grasped, and establishing a three-dimensional model of the target object based on the point cloud and image data; determining a graspable part on the target object based on the three-dimensional model; determining a set of position and posture that the mechanical arm can reach in a current position and posture of a chassis of the robot without changing the current position and posture of the chassis; controlling the mechanical arm to move the target object until a position and posture of the graspable part is in the set of position and posture; and controlling the mechanical arm to grasp the graspable part. The determining of the graspable part on the target object based on the three-dimensional model comprises:

2. The robot control method of claim 1, wherein, obtaining a graspability score of each part on the three-dimensional model, the graspability score representing a grasping success rate of each part of the target object; and determining the graspable part based on the graspability score. The determining of the graspable part based on the graspability score comprises:

3. The robot control method of claim 2, wherein, determining the graspable part as any part on the target object with a graspability score higher than a preset score threshold. The determining of the graspable part based on the graspability score comprises:

4. The robot control method of claim 2, wherein, determining the graspable part as a part on the target object with a maximum graspability score. The determining of the set of position and posture that the mechanical arm can reach in the current position and posture of the chassis comprises:

5. The robot control method of claim 1, wherein, solving the set of position and posture that the mechanical arm can reach in the current position and posture of the chassis by an inverse kinematics model. The controlling of the mechanical arm to move the target object comprises:

6. The robot control method of claim 1, wherein, controlling the mechanical arm to move the target object based on a principle of moving the position and posture of the graspable part to a center point of the set of position and posture. The controlling of the mechanical arm to grasp the graspable part comprises:

7. The robot control method of claim 1, wherein, calculating a motion trajectory of the mechanical arm according to the position and posture of the graspable part; controlling the mechanical arm to move to the graspable part along the motion trajectory; and controlling the mechanical arm to grasp the graspable part. The controlling of the mechanical arm to move to the graspable part along the motion trajectory comprises:

8. The robot control method of claim 7, wherein, controlling the mechanical arm to move along the motion trajectory by controlling the chassis to rotate and the joint angle of the mechanical arm. The determining of the set of position and posture that the mechanical arm can reach in the current position and posture of the chassis comprises:

9. The robot control method of claim 1, wherein, controlling the chassis to move and rotate to different position and postures; determining a set of position and posture that the mechanical arm can reach in each position and posture of the chassis; and determining the set of position and posture that the mechanical arm can reach in the current position and posture of the chassis if the position and posture of the graspable part is outside all the sets of position and posture. 10.A robot control device applied to a robot with a mechanical arm, the device comprising: a modeling module configured to collect point cloud and image data of a target object to be grasped, and establish a three-dimensional model of the target object based on the point cloud and image data; ​ determining a graspable part on the target object based on the three-dimensional model, and determining a set of position and posture that the robot arm can reach at a current position and posture of the robot chassis without changing the current position and posture of the robot chassis; and controlling the robot arm to move the target object until the graspable part is at a position and posture in the set of position and postures, and controlling the robot arm to grasp the graspable part. 11.A robot comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the method of any one of claims 1-9.

12. The robot of claim 11, wherein, The robot is a robot vacuum cleaner.

13. A computer readable storage medium comprising a computer program stored thereon, wherein, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1-9.

14. A computer program product comprising a computer program, wherein, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1-9. The computer program, when executed by the processor, implements the steps of the method of any one of claims 1-9.

Images