Robot control method, device, apparatus, and storage medium

Abstract

Embodiments of the present disclosure provide a robot control method, device, equipment and storage medium. The method comprises: determining a movement control parameter of the robot from a current actual position to a current expected position based on path information contained in a task to be completed; determining a parameter control strategy of the robot based on a scene category corresponding to the task to be completed; and controlling a movement state of the robot based on the parameter control strategy and the movement control parameter. The technical solution of the embodiments of the present disclosure solves the problem that the robot cannot avoid collision in the related art, guarantees the accuracy and reliability of the robot state control, thereby improving the completion rate of the corresponding task of the robot, and significantly reducing the occurrence of collision and motor overcurrent problems.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of robot control, and particularly relates to a robot control method and device, equipment and a storage medium. BACKGROUND

[0002] In the fields of warehousing, logistics, factory production, etc., scenarios are involved in which robots need to carry materials between shelves, workstations, production lines and other equipment. In particular, in factories, because there are many devices, the safety requirement is high, and the accuracy of robot movement needs to be ensured to ensure accurate handover of materials, so that production can be safely carried out. External mechanisms such as guide rails are laid out to limit the action trajectory of the robot.

[0003] In related technologies, the control optimization of robot action is mainly achieved by optimizing the motion control algorithm of the robot. However, it is difficult for the conventional control algorithm to balance the movement efficiency and control accuracy of the robot, and thus, problems such as collision and motor overcurrent cannot be avoided in the robot action. SUMMARY

[0004] Embodiments of the present disclosure provide a robot control method, device, equipment and storage medium to solve the problem that the robot cannot avoid collision in the action in related technologies.

[0005] In a first aspect, the embodiments of the present disclosure provide a robot control method, which comprises:

[0006] determining a movement control parameter of the robot from a current actual position to a current expected position based on path information contained in a task to be completed;

[0007] determining a parameter control strategy of the robot based on a scene category corresponding to the task to be completed;

[0008] controlling a movement state of the robot based on the parameter control strategy and the movement control parameter.

[0009] Optionally, determining the movement control parameter of the robot from the current actual position to the current expected position based on the path information contained in the task to be completed comprises: determining a position deviation parameter between the current actual position and the current expected position of the robot based on the path information contained in the task to be completed; and determining the movement control parameter based on the position deviation parameter.

[0010] Optionally, the position deviation parameter comprises a forward position difference, a lateral deviation and an angle deviation; and the movement control parameter comprises a forward movement speed and a rotation parameter, the rotation parameter comprising a lateral deviation control angular velocity generated based on the lateral deviation and an angle deviation control angular velocity generated based on the angle deviation.

[0011] Optionally, the mobile control parameter is determined based on the position deviation parameter, including: determining a forward mobile speed based on the forward position difference; determining a lateral deviation control angular velocity based on the lateral deviation; and determining an angle deviation control angular velocity based on the angle deviation.

[0012] Optionally, the scene category of the task to be completed includes at least three categories, and the parameter control strategy of the robot is determined based on the scene category corresponding to the task to be completed, including: if the task to be completed corresponds to a first category of scene, determining that the parameter control strategy is to abandon lateral deviation control; if the task to be completed corresponds to a second category of scene, determining that the parameter control strategy is to abandon angle deviation control; and if the task to be completed corresponds to a third category of scene, determining that the parameter control strategy is to abandon angle deviation control and lateral deviation control.

[0013] Optionally, the robot includes a picking mechanism, a backpack, and / or a charging mechanism, the first category of scene includes: a scene in which the picking mechanism of the robot is performing an action of picking out or putting back a pallet, and the picking mechanism is located below the pallet; or a scene in which the backpack of the robot is in a docking position for receiving a material box; or a scene in which the charging mechanism of the robot is docked with a charging device; or a scene in which the current actual position of the robot is located on a main road and the lateral deviation is less than a set lateral deviation value; or a scene in which the extension direction of the backpack of the robot is perpendicular to the moving direction of the material box to be received.

[0014] Optionally, the robot includes a picking mechanism, the second category of scene includes: a scene in which the picking mechanism of the robot is performing an action of picking out or putting back a pallet, and the horizontal distance between the picking mechanism and the pallet is greater than a first set distance value; or a scene in which the difference between the current actual position and the current expected position is greater than a set position difference.

[0015] Optionally, the robot includes a picking mechanism, a backpack, and / or a charging mechanism, the third category of scene includes: a scene in which the robot is located on a guide rail or a track; a scene in which the picking mechanism of the robot is performing an action of picking out or putting back a pallet, the picking mechanism is located below the pallet, and the space below the pallet includes a through hole with a size matching the picking mechanism.

[0016] Optionally, the moving state of the robot is controlled based on the parameter control strategy and the mobile control parameter, including: performing dimension reduction processing on the mobile control parameter based on the parameter control strategy to obtain a target control parameter after dimension reduction processing; determining indication information of a drive motor corresponding to the robot based on the target parameter; and sending the indication information to the drive motor, the drive motor being configured to control the moving state of the robot based on the indication information.

[0017] Optionally, based on the parameter control strategy, the mobile control parameter is reduced in dimension to obtain a target control parameter after dimension reduction, including: setting the value of the abandoned mobile control parameter in the parameter control strategy to zero, and determining the obtained mobile control parameter as the target control parameter.

[0018] In a second aspect, the embodiments of the present disclosure provide a robot control device, which comprises:

[0019] A judgment module is configured to determine a mobile control parameter of the robot from a current actual position to a current expected position based on path information contained in a task to be completed.

[0020] A determination module is configured to determine a parameter control strategy of the robot based on a scene category corresponding to the task to be completed.

[0021] A control module is configured to control a mobile state of the robot based on the parameter control strategy and the mobile control parameter.

[0022] Optionally, the judgment module is specifically configured to determine a position deviation parameter between the current actual position and the current expected position of the robot based on the path information contained in the task to be completed, and determine the mobile control parameter based on the position deviation parameter.

[0023] Optionally, the judgment module specifically includes that the position deviation parameter includes a forward position difference, a lateral deviation and an angle deviation; the mobile control parameter includes a forward moving speed and a rotation parameter, and the rotation parameter includes a lateral deviation control angular velocity generated based on the lateral deviation and an angle deviation control angular velocity generated based on the angle deviation.

[0024] Optionally, the judgment module is specifically configured to determine the forward moving speed based on the forward position difference, determine the lateral deviation control angular velocity based on the lateral deviation, and determine the angle deviation control angular velocity based on the angle deviation.

[0025] Optionally, the determination module is specifically configured to, if the scene category of the task to be completed includes at least three types, if the task to be completed corresponds to a first type of scene, determine that the parameter control strategy is to abandon lateral deviation control; if the task to be completed corresponds to a second type of scene, determine that the parameter control strategy is to abandon angle deviation control; and if the task to be completed corresponds to a third type of scene, determine that the parameter control strategy is to abandon angle deviation control and lateral deviation control.

[0026] Optionally, the determining module specifically comprises: if the robot comprises a taking mechanism, a backpack and / or a charging mechanism, the first type of scenario comprises: a scenario in which the taking mechanism of the robot is performing an action of taking out a pallet or putting back a pallet, and the taking mechanism is located below the pallet; or a scenario in which the backpack of the robot is in a docking position for receiving a bin; or a scenario in which the charging mechanism of the robot is docked with a charging device; or a scenario in which the current actual position of the robot is located on a main road and the lateral deviation is less than a set lateral deviation value; or a scenario in which the extension direction of the backpack of the robot is perpendicular to the moving direction of the bin to be received.

[0027] Optionally, the determining module specifically comprises: if the robot comprises a taking mechanism, the second type of scenario comprises: a scenario in which the taking mechanism of the robot is performing an action of taking out a pallet or putting back a pallet, and the horizontal distance between the taking mechanism and the pallet is greater than a first set distance value; or a scenario in which the difference between the current actual position and the current expected position is greater than a set position difference.

[0028] Optionally, the determining module specifically comprises: if the robot comprises a taking mechanism, a backpack and / or a charging mechanism, the third type of scenario comprises: a scenario in which the robot is located on a guide rail or a track; a scenario in which the taking mechanism of the robot is performing an action of taking out a pallet or putting back a pallet, the taking mechanism is located below the pallet, and the space below the pallet comprises a through hole with a size matching the taking mechanism.

[0029] Optionally, the control module is specifically configured to: perform dimension reduction processing on the movement control parameters based on the parameter control strategy to obtain target control parameters after the dimension reduction processing; determine indication information of the driving motor of the robot based on the target parameters; and send the indication information to the driving motor, so that the driving motor controls the movement state of the robot based on the indication information.

[0030] Optionally, the control module is specifically configured to: set the value of the abandoned movement control parameter in the parameter control strategy to zero, and determine the obtained movement control parameter as the target control parameter.

[0031] In a third aspect, the embodiments of the present disclosure further provide a control device, which comprises:

[0032] at least one processor;

[0033] and a memory in communication connection with the at least one processor;

[0034] wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the control device to perform the robot control method of the first aspect of the present disclosure.

[0035] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement the robot control method according to the first aspect of the present disclosure.

[0036] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, which contains computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement the robot control method according to the first aspect of the present disclosure.

[0037] The robot control method, device, equipment and storage medium provided by the embodiments of the present disclosure can determine the movement control parameter of the robot from the current actual position to the current expected position based on the path information contained in the task to be completed, determine the parameter control strategy of the robot based on the scene category corresponding to the task to be completed, and finally control the movement state of the robot based on the parameter control strategy and the movement control parameter. Therefore, the robot can adjust the control strategy of the movement related parameter in different business scenarios of path tracking control, ensure the accuracy and reliability of the state control of the robot, and thus improve the completion rate of the corresponding task of the robot, and significantly reduce the occurrence of collision and motor overcurrent problems. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure, together with the description.

[0039] Figure 1 An application scenario diagram of the robot control method provided by the embodiments of the present disclosure;

[0040] Figure 2 A flowchart of the robot control method provided by an embodiment of the present disclosure;

[0041] Figure 3a A flowchart of the robot control method provided by another embodiment of the present disclosure;

[0042] Figure 3b A related parameter relationship diagram of the robot position deviation provided in the embodiment shown in FIG. 8; Figure 3a

[0043] A deviation control diagram in the first case provided in the embodiment shown in FIG. 9; Figure 3c Figure 3a A deviation control diagram in the second case provided in the embodiment shown in FIG. 10;

[0044] Figure 3d Figure 3a A deviation control diagram in the third case provided in the embodiment shown in FIG. 11;

[0045] Figure 3e A​​Figure 3a a third case bias control schematic diagram provided in the embodiment shown;

[0046] Figure 3f for Figure 3a a fourth case bias control schematic diagram provided in the embodiment shown;

[0047] Figure 3g for Figure 3a a forklift takes away the pallet process schematic diagram provided in the embodiment shown;

[0048] Figure 3h for Figure 3a a forklift puts down the pallet process schematic diagram provided in the embodiment shown;

[0049] Figure 3j for Figure 3a a robot and guide rail docking process schematic diagram provided in the embodiment shown;

[0050] Figure 4 a schematic diagram of the robot control device provided in another embodiment of the present disclosure;

[0051] Figure 5 a schematic diagram of the control device provided in an embodiment of the present disclosure.

[0052] The above figures have shown the specific embodiments of the present disclosure, which will be described in more detail hereinafter. These figures and textual descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concept of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] The exemplary embodiments will be described in detail herein with reference to the attached drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure. Instead, they are merely examples in accordance with some aspects of the present disclosure as detailed in the appended claims.

[0054] The technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present disclosure will be described below with reference to the drawings.

[0055] In the fields of warehousing, logistics, factory production, etc., there are scenarios that require robots to transport materials between shelves, workstations, production lines, etc. In factories, due to the large number of devices, higher safety requirements are needed to ensure the accuracy of robot movement, so that the production can be carried out safely, and the movement trajectory of the robot is limited by setting guide rails and other external mechanisms. In addition, the movement requirements of the robot are different in different stages of the task. For example, when running on a wide main road, the robot is expected to ensure efficiency and smoothness while appropriately sacrificing control accuracy. When near dense storage locations or workstations, the robot is expected to prioritize control accuracy, especially angular accuracy, to prevent collisions. For example, when a forklift unloads a stack of goods, the forklift is expected to prioritize angular accuracy to prevent collisions with the inner wall of the stack caused by rotation.

[0056] In related technologies, the control optimization of robot movement is mainly achieved by optimizing the motion control algorithm of the robot. However, it is difficult for conventional control algorithms to balance the movement efficiency and control accuracy of the robot, especially for nonholonomic robots (i.e., robots whose movement is composed of forward movement and turning, such as forklift robots used for transporting containers). To eliminate lateral position deviation, the robot needs to rotate, which may increase angular deviation. Therefore, simply adjusting control parameters cannot guarantee high accuracy of both lateral position deviation and angular deviation. At the same time, due to position deviation, objects may block the movement trajectory of the robot, resulting in a movement speed of the robot that does not meet the expected speed, causing the drive motor of the robot to continuously increase the current (in an attempt to increase speed), leading to excessive current and causing the motor or driver to burn out, i.e., motor overcurrent problem. In summary, conventional control algorithms cannot avoid problems such as collisions and motor overcurrent in robot movement.

[0057] To solve this problem, the present disclosure provides a robot control method that determines a parameter control strategy for robot deviation according to the type of scenario in which the robot is located, and generates corresponding instructions accordingly to control the movement of the robot, so as to ensure the accuracy of the robot during movement and minimize the occurrence of problems such as collisions and motor overcurrent.

[0058] The application scenarios of the embodiments of the present disclosure are explained as follows:

[0059] Figure 1 An application scenario diagram of the robot control method provided by the embodiments of the present disclosure is shown in FIG. 1. Figure 1 As shown in FIG. 1, in an intelligent warehousing system, a robot 100 will transport goods 121 between a conveyor line 110 and a shelf 120 according to the received task, and will ensure the accuracy and safety of movement through a control algorithm according to the path information in the received task to be completed, so as to effectively complete the goods transportation task.

[0060] It should be noted that, Figure 1 The robot, the conveying line, the shelf and the goods in the illustrated scenario are only used as examples for illustration, but the present disclosure is not limited thereto, that is, the number of the robot, the conveying line, the shelf and the goods can be any.

[0061] The robot control method provided by the present disclosure will be described in detail below through specific embodiments.

[0062] Figure 2 The flowchart of the robot control method provided by an embodiment of the present disclosure. As Figure 2 illustrated, the robot control method provided by the present embodiment includes the following steps:

[0063] Step S201, determining the movement control parameter of the robot from the current actual position to the current expected position based on the path information contained in the task to be completed.

[0064] Specifically, the robot is a mobile robot that needs to move in a factory, warehouse or the like to complete various tasks, including a forklift robot comprising a forklift structure, a carrying robot comprising a plurality of backpacks, etc.

[0065] The task to be completed is usually a task of moving the robot to a specified starting position to receive a box (or other goods to be carried), and then moving to a specified end position according to the determined path information and placing the box. Thus, the task to be completed will contain the path information, the starting position and the end position (the starting position and the end position can also be contained in the path information) that the robot needs to move.

[0066] After receiving the task to be completed, the robot will move based on the starting position, the path information and the end position in the task to be completed, and will determine the current actual position in real time, and compare it with the current expected position determined based on the path information (such as the position point in the path information corresponding to the current actual position, or if the path information also contains the time requirement for reaching each position point, the current expected position can also be the position point corresponding to the current time point).

[0067] The movement of the robot is usually through the movement of the robot chassis in a two-dimensional plane (i.e. the area where the robot moves is a two-dimensional plane by default), and the control dimensions include two-dimensional position (x, y) and angle θ. The deviation between the current actual position P of the robot and the current expected position in the path information is calculated as the current control deviation ΔP. On this basis, based on the control deviation ΔP, the movement mode that the robot needs to execute can be obtained, including the movement speed, the steering angle, etc., that is, the movement control parameter of the robot. Through the movement control parameter, the robot can be driven to move from the current actual position to the current expected position.

[0068] Step S202: Determine the parameter control strategy of the robot based on the scenario type corresponding to the task to be completed.

[0069] Specifically, since driving the robot to move directly according to the movement control parameters is prone to problems such as collision and motor overcurrent, it is necessary to determine the processing strategy for the movement control parameters (i.e., parameter control strategy) in combination with the scenario type of the task to be completed, such as abandoning the control of some parameters (for example, when the robot moves to the guide rail, the control of the robot's angle and lateral deviation can be abandoned, and it can move directly based on the forward deviation, because the guide rail will limit the lateral movement of the robot and will not allow the lateral deviation to increase further).

[0070] Each task can correspond to multiple scenarios, such as receiving a container at a dumper, moving along a main road, and placing a container on a shelf. Parameter control strategies typically vary across scenarios, so it's necessary to predetermine the appropriate control strategy for each scenario. Once the robot identifies the scenario it's in based on the task and the environment, it can then execute the corresponding parameter control strategy.

[0071] Step S203: Control the movement state of the robot based on the parameter control strategy and the movement control parameters.

[0072] Specifically, by executing the parameter control strategy, the movement control parameters are processed (usually dimensionality reduction processing to reduce the parameters that need to be considered for the robot to move), and then the working state of the robot's drive motor is determined based on the processed parameters. The robot is controlled by the operation of the drive motor to move from the current actual position to the current expected position according to the determined movement state.

[0073] The robot control method provided by the disclosed embodiments determines the robot's movement control parameters from its current actual position to its current desired position based on the path information contained in the task to be completed. It then determines the robot's parameter control strategy based on the scenario type corresponding to the task to be completed. Finally, the robot's movement state is controlled based on the parameter control strategy and movement control parameters. This allows the robot to adjust its control strategy for its movement-related parameters in different business scenarios of path tracking control, ensuring the accuracy and reliability of the robot's state control, thereby improving the robot's completion rate for the corresponding task and significantly reducing the occurrence of collisions and motor overcurrent issues.

[0074] Figure 3a This is a flow chart of a robot control method provided by one embodiment of the present disclosure. Figure 3a As shown, the robot control method provided in this embodiment includes the following steps:

[0075] Step S301 : determining a position deviation parameter between the current actual position and the current expected position of the robot based on the path information included in the task to be completed.

[0076] Specifically, the position deviation parameters include forward position difference, lateral deviation and angular deviation.

[0077] After receiving a task to be completed, the robot will determine its current actual position in real time, and based on the path information (the expected path included), find the point on the expected path closest to the robot's current actual position as a reference point (that is, the current expected position).

[0078] Then, take this point as the origin of the reference coordinate system, and the forward direction of the path tangent as the positive direction of the x-axis to establish a reference coordinate system. Then, define the horizontal axis coordinate value of the robot's current actual position expressed in the reference coordinate system as the lateral deviation Δy, and the angle as the angular deviation Δθ. The forward position difference Δx is the distance from the current expected position to the end point of the expected path.

[0079] Therefore, the goal of controlling the robot's movement state is to control the position deviation parameter ΔP = (Δx, Δy, Δθ) to 0, that is, to control the robot to move strictly along the desired path to the end point of the path.

[0080] like Figure 3b Figure 1 shows the relationship between the parameters of the robot's position deviation. Point O is the center of the robot, the hollow arrow is the robot's forward movement direction, O1 is the fulcrum on the nearest desired path (starting position A, ending position B), forward X, side Y, and angle θ are the three dimensions representing the robot's posture, and Δx, Δy, and Δθ are the three position deviation parameters.

[0081] Step S302: Determine movement control parameters based on the position deviation parameters.

[0082] Specifically, to control the position deviation parameter to zero, the robot's movement state must be controlled. Controlling the robot's movement involves movement control parameters, which include forward movement speed and rotation parameters. The rotation parameters include the lateral deviation control angular velocity generated based on the lateral deviation and the angular deviation control angular velocity generated based on the angular deviation. These movement control parameters are described in detail below.

[0083] During the movement of the robot, its posture includes three dimensions: forward x, side y and angle θ. That is, the robot's motion control can be decoupled into forward movement speed and rotation parameters, where the forward movement speed corresponds to the desired speed v sp , the corresponding position deviation parameter is Δx; the corresponding control quantity of the rotation parameter is the desired angular velocity ω spThe corresponding position deviation parameters are Δy and Δθ. The movement control quantity v is obtained by controlling the forward position difference Δx sp , thereby controlling the robot to move to the path end point; the rotation control quantity ω is obtained by controlling the lateral deviation Δy and the angle deviation Δθ sp , thereby controlling the robot on the desired path and the angle being consistent with the direction of the desired path.

[0084] Wherein, the forward movement speed can be determined based on the forward position difference; the lateral deviation control angular velocity is determined based on the lateral deviation; and the angle deviation control angular velocity is determined based on the angle deviation.

[0085] Specifically, it can be expressed as:

[0086] The forward movement speed: v sp = CTR(Δx);

[0087] The rotation parameter:

[0088] Wherein, CTR(·) represents a controller algorithm function built in the robot, including but not limited to a PID controller. ω sp_Δy is the rotation control quantity generated based on the lateral deviation, i.e., the lateral deviation control angular velocity; ω sp_Δθ is the rotation control quantity generated based on the angle deviation, i.e., the angle deviation control angular velocity. The definition of ω sp is that counterclockwise rotation is positive and clockwise rotation is negative.

[0089] The forward position difference can be controlled by a controller algorithm function or a speed planning method, and if the forward movement control is abandoned, the robot can only rotate in place (only the rotation control quantity ω sp is left, and the robot cannot reach the end point, so the forward movement control cannot be abandoned. Therefore, in actual application, the abandonment of the control of the lateral deviation Δy and the angle deviation Δθ (i.e., different parameter control strategies) is mainly controlled, thereby reducing the control dimension.

[0090] For example, as shown in FIG. 1, it is a deviation control schematic diagram in the first case, in which Δy>0 (Δy is the distance from O to O1 in the figure), i.e., the robot is on the left side of the path (as viewed along the path direction, i.e., the direction indicated by the vertical solid arrow in the figure), and the control quantity ω sp_Δy <0 is generated by the lateral deviation, i.e., in order to eliminate Δy, the robot is expected to rotate clockwise, and Δθ>0, i.e., in order to keep the travel direction of the robot straight, the robot needs to rotate clockwise, i.e., ω sp_Δθ <0, therefore, the robot can be directly controlled to rotate clockwise and move in the direction of eliminating Δy.

[0091] For another example, as shown in FIG. 2, it is a deviation control schematic diagram in the second case, in which Δy<0 (Δy is the distance from O to O1 in the figure), i.e., the robot is on the right side of the path (as viewed along the path direction, i.e., the direction indicated by the vertical solid arrow in the figure), and the control quantity ω sp_Δθ >0 is generated by the lateral deviation, i.e., in order to eliminate Δy, the robot is expected to rotate counterclockwise, and Δθ<0, i.e., in order to keep the travel direction of the robot straight, the robot needs to rotate counterclockwise, i.e., ω sp_Δy >0, therefore, the robot can be directly controlled to rotate counterclockwise and move in the direction of eliminating Δy.Figure 3d As shown in the figure, it is a schematic diagram of the deviation control in the second case. Figure 3d In the case of Δy>0, Δθ<0, since ω sp_Δy <0, then the robot needs to be controlled to rotate clockwise, and the control amount ω generated by the angle deviation sp_Δθ >0, that is, in order to make the robot direction consistent with the path direction, the robot is expected to rotate counterclockwise. Therefore, the actual rotation direction is based on ω sp_Δy and ω sp_Δθ The size of is relatively certain, if |ω sp_Δy |>|ω sp_Δθ |, you need to rotate clockwise, otherwise, you need to rotate counterclockwise.

[0092] For example Figure 3e As shown, it is a schematic diagram of deviation control in the third case. Figure 3e In the case of Δy<0, Δθ<0, Figure 3d The situation is similar to that in , while rotating clockwise, that is, ω sp_Δy >0, the car needs to rotate counterclockwise, and ω sp_Δθ <0, the car needs to rotate clockwise, so it is also necessary to determine the direction of rotation by comparing the two values.

[0093] For example Figure 3f As shown, it is a schematic diagram of deviation control in the fourth case. Figure 3f In the equation, Δy<0, Δθ>0, which means ω sp_Δy >0 and ω sp_Δθ >0, therefore, counterclockwise rotation is required to ensure vehicle control.

[0094] In summary, during the path tracking process, the robot may encounter various situations. Therefore, it is necessary to select the corresponding parameter control strategy according to the type of scenario.

[0095] Step S303: If the task to be completed corresponds to the first type of scenario, the parameter control strategy is determined to abandon lateral deviation control.

[0096] Specifically, the classification of scenes can be determined based on the task to be completed, the perception of the surrounding or designated equipment, the robot's own positioning, etc. Different parameter control strategies are selected according to different scenes (i.e., whether to abandon the lateral deviation or angle deviation control, i.e., to force ω sp_Δy or ω sp_Δθ Assign 0).

[0097] Among them, the first type of scenario is that it is necessary to give up the control of lateral deviation in order to ensure angle accuracy (that is, the scenario where angle accuracy is obviously more important).

[0098] For example, if the angle deviation is large, it is easy to collide (if the chassis of the robot is rectangular, the larger the angle deviation within a certain range, the more space the robot will occupy), for example, if the angle deviation is Δθ, the robot or the edge of the shelf with a distance L from the center of the robot will have a position deviation of Δθ*L due to the angle deviation, that is, the position deviation caused by the angle deviation will be amplified by the distance L, and when L is large (that is, the size of the robot or the goods is large), the position deviation is more obvious. However, the lateral deviation Δy will not be amplified, that is, the robot center lateral deviation Δy, and the deviation of all points on the entire robot or shelf due to the robot center lateral deviation is Δy.

[0099] For example, a large angle deviation (relative to the lateral deviation) affects the operation effect more, because a large angle deviation will give people a "twist" intuitive feeling, affecting customer experience.

[0100] Further, the first type of scenario can include:

[0101] Scenario one, the scenario in which the taking mechanism of the robot is executing the action of taking out or putting back the pallet, and the taking mechanism is located below the pallet.

[0102] Specifically, if the robot is a forklift robot, its taking mechanism includes tines (if it is a carrying robot, the corresponding structure is a mechanical arm or a receiving rod, etc., and this example is described taking the forklift robot as an example). Because the tines are long, a large angle deviation will cause a large tine position deviation, and compared with the lateral deviation, the angle deviation is obviously more likely to cause collision risk.

[0103] In the process of taking out the pallet, the forklift robot will insert the tines into the pallet hole below the pallet, and then lift the tines to realize the process of taking out the pallet. Conversely, in the process of putting back the pallet, the forklift lowers the tines to the bottom, and then moves out of the pallet to realize the process of putting back the pallet. Because the internal space of the pallet hole is limited, the navigation control accuracy of the forklift is relatively high, especially the angle accuracy, if the forklift has a large angle movement during the taking process, the tines will collide with the internal space of the pallet hole.

[0104] However, if the taking mechanism is already located below the pallet, that is, the tines are about to enter the pallet or have entered the pallet, at this time, the angle alignment needs to be ensured, that is, the lateral deviation control is abandoned, and the angle deviation of the forklift is controlled to 0 as soon as possible. After the tines enter the pallet hole, it is hoped that the angle of the forklift is parallel to the pallet, and the lateral deviation control is completely abandoned, that is, ω sp_Δy is forced to 0 until the forklift takes the pallet.

[0105] Therefore, the lateral deviation control needs to be abandoned in this scenario.

[0106] Scenario two, the scenario in which the backpack of the robot is in the docking position for receiving the material box.

[0107] Specifically, similar to scenario one, angle deviation will cause large position deviation at the corners of the backpack, and the space near the docking position is cramped (usually there is a discharger), which makes it easy for the backpack to collide with the discharger. Therefore, compared with lateral deviation, angle accuracy is obviously more important at this time.

[0108] Scenario three: The robot's charging mechanism is docked with the charging equipment.

[0109] Specifically, the connection between the charging mechanism and the charging device is usually the connection between the charging plug and the charging port. At this time, angular deviation will cause a large positional deviation between the charging port and the charging plug, affecting the success rate of charging docking. Therefore, it is also necessary to prioritize ensuring angular accuracy.

[0110] Scenario 4: The robot's current actual position is on the main road and the lateral deviation is less than the set lateral difference.

[0111] Specifically, when the robot is driving on a main road, if the lateral deviation is small (i.e., the lateral deviation is less than the set lateral difference), the angular deviation is significantly more important than the small lateral deviation. Because the main road is wide, small lateral deviation is not a big deal, but the robot is expected to keep its direction correct (i.e., maintain accurate direction).

[0112] Scenario 5: The extension direction of the robot's backpack is perpendicular to the movement direction of the material box to be received.

[0113] Specifically, in addition to directly docking the robot's backpack with the unloader, the robot can also be positioned sideways to the unloader, enabling sideways pickup. In this case, the backpack of such an unloader typically includes a retractable receiving mechanism with considerable margin (and the cargo to be received also has a certain size), so lateral deviation does not affect the pickup task. However, if the angle is not correct, the robot can easily collide with the cargo or the unloader (because the receiving mechanism may extend a long distance), so angular accuracy is clearly more important than lateral deviation.

[0114] The above only lists some common scenarios where lateral deviation needs to be abandoned, but the present solution is not limited by the above list. That is, technical personnel in this field can configure various scenarios as the first type of scenarios where lateral deviation needs to be abandoned according to the needs of actual applications, which are all within the scope of protection of this solution.

[0115] Step S304: If the task to be completed corresponds to the second type of scenario, the parameter control strategy is determined to abandon the angle deviation control.

[0116] Specifically, in contrast to the first type of scenario, the second type of scenario is a scenario where angle deviation control needs to be abandoned to ensure lateral position accuracy (or in other words, lateral accuracy is more important in this type of scenario).

[0117] Further, the second type of scenario includes:

[0118] Scenario six, the scenario where the picking mechanism of the robot is performing the action of picking up or putting down a pallet, and the horizontal distance between the picking mechanism and the pallet is greater than the first set distance value.

[0119] Specifically, in the same task as scenario one (but the scenario is different), if the horizontal distance between the picking mechanism and the pallet is far (i.e., the horizontal distance is greater than the first set distance value), the front end of the fork teeth will not collide with the pallet due to rotation at this time, in order to eliminate the lateral deviation as soon as possible, so that the fork teeth can be aligned with the pallet hole, the angle deviation can be abandoned first, and the lateral deviation can be converged as soon as possible. Therefore, at this time, the angle deviation control is abandoned in priority.

[0120] Scenario seven, the scenario where the difference between the current actual position and the current expected position is greater than the set position difference.

[0121] Specifically, when the robot deviates far from the expected path (i.e., the lateral deviation is large) and the lateral deviation is still expanding, if the robot does not return to the expected path as soon as possible, it is likely to cause a collision risk. Therefore, the angle deviation can be abandoned to make the robot return to the expected path as soon as possible.

[0122] The above only lists some common scenarios that need to abandon the angle deviation, but the present solution is not limited by the above list, that is, those skilled in the art can configure various scenarios to be the second type of scenario that needs to abandon the angle deviation according to the needs of actual application, which are all within the protection scope of the present solution.

[0123] Step S305, if the third type of scenario corresponding to the task to be completed is determined, the parameter control strategy is abandoned angle deviation control and lateral deviation control.

[0124] Specifically, in addition to the first two types of scenarios, there are scenarios that need to abandon both lateral deviation and angle deviation control. In this type of scenario, the expected angular velocity ω sp of the robot is definitely 0, that is, there is no expected rotation control of the robot, and the control of the rotation parameter can be abandoned, and there is only the expected v sp of the movement control parameter. Taking the case of the motion mechanism of the robot as a differential car as an example, that is, the expected left and right wheel speeds are consistent, taking the case of the forklift robot as an example, that is, the expected rudder angle and chassis angular velocity are 0. In this way, the motion of the robot is reduced from two-dimensional plane motion to one-dimensional forward and backward motion, and this type of scenario is usually when the robot is constrained by an external mechanism to only move forward and backward.

[0125] Further, the third type of scenario includes:

[0126] Scenario eight, the scenario where the robot is located on a guide rail or track.

[0127] Specifically, in some warehouses or factories, guide rails are arranged near the shelves, unloading equipment or workstations to accurately limit the pose of the robot. In such scenarios, the robot is in a free two-dimensional motion state when it is outside the guide rail, and at this time, the deviation in three dimensions (i.e., three position deviation parameters) needs to be controlled.

[0128] Once the robot enters the guide rail through the guide rail port, the guide rail completely limits the lateral movement of the robot. However, due to the fluctuation of perception positioning and other reasons, the lateral deviation and the angle deviation cannot be absolutely zero, and if the control of the rotation parameter is performed at this time, the rotation and lateral movement components are generated, which will cause the motor to be in a locked-rotor or wheel slip state due to the guide rail limitation. In the case of serious locked-rotor, there is a risk of motor overcurrent. Therefore, when the robot recognizes that it has entered the guide rail, the lateral deviation and the angle deviation control need to be abandoned at the same time, so that the chassis control quantity only exists v sp That is, the left and right wheel expected speeds are always equal, reducing the two-dimensional plane motion of the robot to one-dimensional forward and backward motion.

[0129] In addition, in order to improve efficiency and safety, there is a new business model at present: the robot runs in normal two-dimensional motion mode on the main road, but the ground track is arranged in the lane for picking and placing goods (limiting the movement of the robot and allowing the speed of the robot to be increased with confidence), and the robot enters the track when picking and placing goods, so that the two-dimensional plane motion becomes one-dimensional forward and backward motion, and at this time, the lateral deviation and the angle deviation control also need to be abandoned at the same time.

[0130] Scenario nine, the picking mechanism of the robot is executing the action of picking out or placing back the pallet, the picking mechanism is located below the pallet, and the space below the pallet contains a through hole with a size matching the picking mechanism.

[0131] Specifically, in contrast to scenarios one and six, when the picking mechanism has cooperated with the pallet hole (i.e., the through hole below the pallet), it is equivalent to limiting the lateral movement of the forklift. If the pallet hole is very small (comparable to the width of the tines), at this time, the picking mechanism and the robot only need to move forward and backward to drive the pallet to implement the picking out and placing back actions, and at this time, the lateral deviation and the angle deviation of the robot do not need to be adjusted, so the lateral deviation and the angle deviation control also need to be abandoned at the same time.

[0132] The above only lists some common scenarios that need to abandon the lateral deviation and the angle deviation, but the present solution is not limited by the above list, that is, the person skilled in the art can configure various scenarios to be the third type of scenario that needs to abandon the lateral deviation and the angle deviation according to the actual application requirements, which are all within the protection scope of the present solution.

[0133] In actual applications, in addition to the above three types of scenarios, there are also scenarios that do not need to abandon the mobile control parameters, that is, scenarios in which the robot can normally move according to the position deviation parameters, such as the scenario in which the robot normally drives on the main road. In this type of scenario, the robot is in a normal driving state relative to the path information, and since no parameter control strategy is involved, this will not be described here.

[0134] For example, as shown in Figure 3g and Figure 3h , they are respectively a schematic diagram of the process of the forklift taking away the pallet, a schematic diagram of the process of the forklift putting down the pallet, and in Figure 3g , for example, the upper left side, the white figure between points AB corresponds to the forklift robot (referred to as forklift), and the white and gray alternating image between points BC corresponds to the pallet, where white represents the pallet hole below the pallet.

[0135] The forklift moves to the vicinity of the pallet, including AB and BC paths, and in the AB segment, the distance between the forklift and the pallet needs to be reduced as soon as possible, so the angle deviation control can be abandoned (corresponding to scenario six above), and in the BC segment, the tines of the forklift need to be aligned with the hole below the pallet, so the lateral deviation control can be abandoned (corresponding to scenario one above), and then the forklift tines enter the hole below the pallet, and then the forklift only needs to move forward and backward (corresponding to scenario nine above), and when the tines are lifted and connected to the pallet at point C, the pallet can be moved.

[0136] In Figure 3h , during the process of the forklift putting down the pallet, when the tines of the forklift are disconnected from the pallet at point C, only the method in scenario nine can be used to move to point B to make the pallet and the tines disengage, and after point B, normal control can be restored to move along the BA direction and leave the vicinity of the pallet.

[0137] For example, as shown in Figure 3j , it is a schematic diagram of the process of the robot and the guide rail docking, the left robot carries a shelf (i.e. the rectangular frame in the figure containing four gray rectangles) and moves the shelf into the guide rail (i.e. the structure corresponding to the gray long strip in the figure) until it is docked with the machine table (or storage location, i.e. the gray rectangle on the right side of the figure), which corresponds to scenario eight.

[0138] In step S306, the mobile control parameters are processed by dimension reduction based on the parameter control strategy to obtain the target control parameters after dimension reduction.

[0139] Specifically, according to the selected parameter control strategy, it is determined whether to abandon the lateral deviation and angle deviation control, and since the value of the mobile control parameter abandoned in the parameter control strategy is set to zero, the obtained mobile control parameter is determined as the target control parameter, and this process is the process of dimension reduction.

[0140] Further, after the dimension reduction processing, the comprehensive mobile control parameter v sp 、ω sp_Δy 、ω sp_Δθ The control amount required for the robot to move can be obtained: the expected speed v sp 、expected angular velocity ω sp =ω sp_Δy +ω sp_Δθ .

[0141] Step S307, based on the target parameter, determining the indication information of the corresponding drive motor of the robot.

[0142] Specifically, by performing kinematic inverse solution on the control amount in the foregoing step, the expected control amount (i.e. motor expected speed) corresponding to each motor drive can be obtained. By sending the expected control amount as the indication information to each drive motor, the drive motor can be driven to work according to the set state (i.e. according to the state corresponding to the expected control amount).

[0143] Step S308, sending the indication information to the drive motor, and the drive motor is used to control the moving state of the robot based on the indication information.

[0144] Specifically, by issuing the indication information to the drive motor for execution, the control of the moving state of the robot can be realized.

[0145] Further, under the indication information, the robot will judge whether the to-be-completed task is completed, and if the to-be-completed task is still in an uncompleted state, it will return to step S301 and enter the next cycle.

[0146] The robot control method provided by the embodiments of the present disclosure determines the position deviation parameter between the current actual position and the current expected position of the robot based on the path information contained in the to-be-completed task, determines the mobile control parameter based on the position deviation parameter, then determines the corresponding parameter control strategy according to the scene category corresponding to the to-be-completed task, and then performs dimension reduction processing on the mobile control parameter based on the parameter control strategy to obtain the target control parameter after the dimension reduction processing, and determines the indication information of the corresponding drive motor of the robot based on the target parameter. Finally, the indication information is sent to the drive motor, and the drive motor is used to control the moving state of the robot based on the indication information. Thus, the robot can choose whether to give up lateral deviation or angle deviation control according to different business scenarios, always ensuring the safety and reliability of the robot moving process, thereby improving the task completion rate and reducing the occurrence of collision and motor overcurrent problems.

[0147] Figure 4 The structure schematic diagram of the robot control device provided by an embodiment of the present disclosure is shown in FIG. 1. As shown in FIG. 1, the robot control device comprises a robot control method and a robot control device. Figure 4As shown, the robot control device 400 comprises a judging module 410, a determining module 420 and a control module 430. Wherein:

[0148] The judging module 410 is configured to determine a movement control parameter of the robot from a current actual position to a current expected position based on path information contained in a task to be completed.

[0149] The determining module 420 is configured to determine a parameter control strategy of the robot based on a scene category corresponding to the task to be completed.

[0150] The control module 430 is configured to control a movement state of the robot based on the parameter control strategy and the movement control parameter.

[0151] Optionally, the judging module 410 is specifically configured to determine a position deviation parameter between the current actual position and the current expected position of the robot based on the path information contained in the task to be completed, and determine the movement control parameter based on the position deviation parameter.

[0152] Optionally, the judging module 410 specifically comprises that the position deviation parameter comprises a forward position difference, a lateral deviation and an angle deviation; and the movement control parameter comprises a forward movement speed and a rotation parameter, the rotation parameter comprises a lateral deviation control angular velocity generated based on the lateral deviation and an angle deviation control angular velocity generated based on the angle deviation.

[0153] Optionally, the judging module 410 is specifically configured to determine the forward movement speed based on the forward position difference, determine the lateral deviation control angular velocity based on the lateral deviation, and determine the angle deviation control angular velocity based on the angle deviation.

[0154] Optionally, the determining module 420 is specifically configured to, if the scene category of the task to be completed comprises at least three categories, if the task to be completed corresponds to a first category of scene, determine that the parameter control strategy is to abandon lateral deviation control; if the task to be completed corresponds to a second category of scene, determine that the parameter control strategy is to abandon angle deviation control; and if the task to be completed corresponds to a third category of scene, determine that the parameter control strategy is to abandon angle deviation control and lateral deviation control.

[0155] Optionally, the determining module 420 specifically comprises that, if the robot comprises a taking mechanism, a backpack and / or a charging mechanism, the first category of scene comprises: a scene in which the taking mechanism of the robot is performing an action of taking out or putting back a pallet, and the taking mechanism is located below the pallet; or, a scene in which the backpack of the robot is in a docking position for receiving a material box; or, a scene in which the charging mechanism of the robot is docked with a charging device; or, a scene in which the current actual position of the robot is located on a main road and the lateral deviation is less than a set lateral deviation value; or, a scene in which the stretching direction of the backpack of the robot is perpendicular to the moving direction of the material box to be received.

[0156] Optionally, the determining module 420 specifically comprises: if the robot comprises the taking mechanism, the second type of scenario comprises: a scenario in which the taking mechanism of the robot is performing an action of taking out a pallet or putting back a pallet, and the horizontal distance between the taking mechanism and the pallet is greater than a first set distance value; or a scenario in which the difference between the current actual position and the current expected position is greater than a set position difference.

[0157] Optionally, the determining module 420 specifically comprises: if the robot comprises the taking mechanism, the backpack and / or the charging mechanism, the third type of scenario comprises: a scenario in which the robot is located on a guide rail or a track; a scenario in which the taking mechanism of the robot is performing an action of taking out a pallet or putting back a pallet, the taking mechanism is located below the pallet, and the space below the pallet comprises a through hole with a size matching the taking mechanism.

[0158] Optionally, the control module 430 is specifically configured to: perform dimension reduction processing on the movement control parameter based on the parameter control strategy to obtain a target control parameter after the dimension reduction processing; determine, based on the target parameter, indication information of a drive motor corresponding to the robot; and send the indication information to the drive motor, so that the drive motor controls the movement state of the robot based on the indication information.

[0159] Optionally, the control module 430 is specifically configured to: set the value of the abandoned movement control parameter in the parameter control strategy to zero, and determine the obtained movement control parameter as the target control parameter.

[0160] In this embodiment, the robot control apparatus solves the problem that the robot cannot avoid collision in the related art, guarantees the accuracy and reliability of the robot state control, and thus improves the completion rate of the robot for the corresponding task and significantly reduces the occurrence of collision and motor overcurrent.

[0161] Figure 5 A structural schematic diagram of a control device provided for an embodiment of the present disclosure is shown in FIG. 5. Figure 5 As shown in FIG. 5, the control device 500 comprises a memory 510 and a processor 520.

[0162] The memory 510 stores a computer program executable by the at least one processor 520. The computer program is executed by the at least one processor 520, so that the control device implements the material taking method provided in any one of the above embodiments or the robot control method provided in any one of the above embodiments.

[0163] The memory 510 and the processor 520 can be connected through a bus 530.

[0164] The relevant description can be understood by referring to the relevant description and effects of the method embodiments, which will not be repeated here.

[0165] The related description can be understood by referring to the related description and effects corresponding to the method embodiments, which will not be repeated here.

[0166] One embodiment of the present disclosure provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the material taking-out method according to any one of the method embodiments or the robot control method according to any one of the embodiments.

[0167] The computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0168] One embodiment of the present disclosure provides a computer program product, which contains computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement the material taking-out method according to the method embodiments or the robot control method according to any one of the embodiments.

[0169] In several embodiments provided by the present disclosure, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the described embodiments of the apparatus are merely schematic. For example, the division of the modules is merely a logical function division. There can be another division manner for the actual implementation. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or modules, and can be electrical, mechanical or in other forms.

[0170] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the present disclosure disclosed here. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure following the general principles thereof and including the general and specific knowledge in the art not disclosed in the present disclosure. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0171] It should be understood that the present disclosure is not limited to the precise structures described and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the claims appended hereto.

Claims

1. A robot control method characterized by, The robot control method comprises: determining a movement control parameter of the robot from a current actual position to a current expected position based on path information contained in a task to be completed; determining a parameter control strategy of the robot based on a scene category corresponding to the task to be completed; controlling a movement state of the robot based on the parameter control strategy and the movement control parameter; The method comprises: determining a position deviation parameter between the current actual position and the current expected position of the robot based on the path information contained in the task to be completed; determining the movement control parameter based on the position deviation parameter; The position deviation parameter comprises a forward position difference, a lateral deviation and an angle deviation; The movement control parameter comprises a forward movement speed and a rotation parameter, and the rotation parameter comprises a lateral deviation control angular velocity generated based on the lateral deviation and an angle deviation control angular velocity generated based on the angle deviation; The scene category of the task to be completed comprises at least three categories, The method comprises: if the task to be completed corresponds to a first category of scene, determining that the parameter control strategy is to abandon lateral deviation control; if the task to be completed corresponds to a second category of scene, determining that the parameter control strategy is to abandon angle deviation control; if the task to be completed corresponds to a third category of scene, determining that the parameter control strategy is to abandon angle deviation control and lateral deviation control.

2. The method of claim 1, wherein, The method comprises: determining the forward movement speed based on the forward position difference; determining the lateral deviation control angular velocity based on the lateral deviation; determining the angle deviation control angular velocity based on the angle deviation.

3. The method of claim 1, wherein, The robot comprises a goods taking mechanism, a backpack and / or a charging mechanism, The first category of scene comprises: a scene in which the goods taking mechanism of the robot is performing an action of taking out or putting back a pallet, and the goods taking mechanism is located below the pallet; or, a scene in which the backpack of the robot is in a docking position for receiving a material box; or, a scene in which the charging mechanism of the robot is docked with a charging device; or, a scene in which the current actual position of the robot is located on a main road and the lateral deviation is less than a set lateral deviation value; or, a scene in which the extension direction of the backpack of the robot is perpendicular to the movement direction of the material box to be received.

4. The method of claim 1, wherein, The robot comprises a goods taking mechanism, and the second category of scene comprises: a scene in which the goods taking mechanism of the robot is performing an action of taking out or putting back a pallet, and the horizontal distance between the goods taking mechanism and the pallet is greater than a first set distance value; or, a scene in which the difference between the current actual position and the current expected position is greater than a set position difference.

5. The method of claim 1, wherein, The robot comprises a goods taking mechanism, a backpack and / or a charging mechanism, The third category of scene comprises: a scene in which the robot is located on a guide rail or a track; The robot's taking mechanism performs the action of taking out or putting back the pallet, the taking mechanism is located below the pallet, and the scenario below the pallet includes a through hole with a size matching the taking mechanism.

6. The method according to any one of claims 1 to 5, characterized in that, The parameter-based control strategy and the movement control parameter are used to control the movement state of the robot, including: The parameter-based control strategy is used to reduce the dimension of the movement control parameter to obtain a target control parameter after dimension reduction; Based on the target control parameter, the indication information of the corresponding drive motor of the robot is determined; The indication information is sent to the drive motor, and the drive motor is used to control the movement state of the robot based on the indication information.

7. The method of claim 6, wherein, The parameter-based control strategy is used to reduce the dimension of the movement control parameter to obtain a target control parameter after dimension reduction, including: The value of the abandoned movement control parameter in the parameter control strategy is set to zero, and the obtained movement control parameter is determined as the target control parameter.

8. A robot control device characterized by comprising: The robot control device includes: A judgment module is configured to determine the movement control parameter of the robot from the current actual position to the current expected position based on the path information included in the to-be-completed task; A determination module is configured to determine the parameter control strategy of the robot based on the scene category corresponding to the to-be-completed task; A control module is configured to control the movement state of the robot based on the parameter control strategy and the movement control parameter; The parameter control strategy of the robot is determined based on the scene category corresponding to the to-be-completed task, including: Based on the path information included in the to-be-completed task, the position deviation parameter between the current actual position and the current expected position of the robot is determined; Based on the position deviation parameter, the movement control parameter is determined; The position deviation parameter includes a forward position difference, a lateral deviation, and an angle deviation; The movement control parameter includes a forward movement speed and a rotation parameter, and the rotation parameter includes a lateral deviation control angular velocity generated based on the lateral deviation and an angle deviation control angular velocity generated based on the angle deviation; The scene category of the to-be-completed task includes at least three categories, The parameter control strategy of the robot is determined based on the scene category corresponding to the to-be-completed task, including: If the to-be-completed task corresponds to a first type of scene, the parameter control strategy is determined to abandon lateral deviation control; If the to-be-completed task corresponds to a second type of scene, the parameter control strategy is determined to abandon angle deviation control; If the to-be-completed task corresponds to a third type of scene, the parameter control strategy is determined to abandon angle deviation control and lateral deviation control.

9. A control device, characterized by It includes: At least one processor; and a memory connected in communication with the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the control device to perform the robot control method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the robot control method of any one of claims 1 to 7.

11. A computer program product, characterised in that, The computer program product comprises computer-executable instructions for implementing the robot control method according to any one of claims 1 to 7 when the computer-executable instructions are executed by a processor.

Images