Robot control method and device, robot and storage medium

Abstract

The invention discloses a robot control method and device, a robot and a storage medium. The method comprises the steps that it is determined that a robot obtains a task instruction, and an initial moving path of the robot is planned according to global map information obtained in advance; obtaining target path points in the initial moving path, and determining direction angle information of each target path point; determining a moving area of at least one area type contained in the initial moving path according to the direction angle information; wherein the region type comprises an omnidirectional region and a differential region; and controlling the robot to operate in the moving area according to a control mode associated with the area type. By running the technical scheme provided by the embodiment of the invention, the running modes of the robot can be enriched, the running of the robot conforms to the road condition in the moving path, and the running efficiency and applicability of the robot are improved.

Description

Technical Field

[0001] The present invention relates to robot technology, and in particular to a robot control method, device, robot and storage medium. Background Art

[0002] With the popularization of intelligent robots, they are being used more and more widely in service and other industries, which not only reduces labor costs but also improves work efficiency.

[0003] In the prior art, when a robot operates in a task movement path, it usually adopts a single operation mode, such as only using omnidirectional control or only using differential control; however, the robot's movement path may include a variety of road conditions, and a single operation mode may result in reduced robot operation efficiency and applicability. Summary of the invention

[0004] The present invention provides a robot control method, a device, a robot and a storage medium, so as to improve the efficiency and applicability of the robot operation.

[0005] According to one aspect of the present invention, there is provided a robot control method, the method comprising:

[0006] Determine that the robot obtains the task instruction, and plan the initial movement path of the robot according to the pre-acquired global map information;

[0007] Acquire target path points in the initial moving path, and determine direction angle information of each target path point;

[0008] Determine, according to the direction angle information, a moving area of ​​at least one area type included in the initial moving path; wherein the area type includes an omnidirectional area and a differential area;

[0009] The robot is controlled to operate in the moving area according to a control method associated with the area type.

[0010] According to another aspect of the present invention, there is provided a robot control device, the device comprising:

[0011] A path planning module, used to determine that the robot obtains the task instruction and plans the initial movement path of the robot according to the pre-acquired global map information;

[0012] A direction angle information determination module, used to obtain target path points in the initial moving path and determine the direction angle information of each target path point;

[0013] A moving area determination module, used to determine a moving area of ​​at least one area type included in the initial moving path according to the direction angle information; wherein the area type includes an omnidirectional area and a differential area;

[0014] The robot operation control module is used to control the robot to operate in the moving area according to a control method associated with the area type.

[0015] According to another aspect of the present invention, there is provided a robot, the robot comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the robot control method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot control method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention plans the initial moving path according to the pre-acquired global map information before the robot runs, so that the planning of the initial moving path and the subsequent determination of the moving area type contained in the initial moving path do not need to consider the dynamic obstacles that may be encountered during actual operation, eliminate the interference of dynamic obstacles and local planning and re-planning on the determination of the moving area type during actual operation, and improve the accuracy and stability of the determination of the moving area type. The moving area of ​​at least one area type contained in the initial moving path is determined according to the directional angle information of the target path point, that is, the determined area type is related to the road condition in the moving path, which is convenient for the subsequent control of the robot to run in the moving area according to the control mode associated with the area type, enriching the robot's operation mode, and making the robot run in accordance with the road condition in the moving path, improving the efficiency and applicability of the robot's operation. And because the area types of the moving area include omnidirectional area and differential area, avoid using only omnidirectional control mode. Since the chassis wheels are omnidirectional, the robot cannot distinguish the current path direction. If the current path direction is distinguished, fixed sampling is required for the current running path. If the current running path is long or there are many obstacles around the current running path, the robot cannot correctly identify the current path direction when the current running path is distorted, which may cause the robot to face the wrong direction. Avoid using only differential control mode, which will cause frequent changes in direction when driving straight, causing the robot to face confusion. This will reduce the impact on the execution of robot tasks such as customer guidance, improve user experience and improve the safety of task execution. The robot can adjust the body direction according to the associated control method in different moving areas, improving the coordination of the robot operation.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of a robot control method provided in Embodiment 1 of the present invention;

[0023] Figure 2 A flowchart of a robot control method provided in Embodiment 2 of the present invention;

[0024] Figure 3 A schematic diagram of an initial moving path provided in Embodiment 2 of the present invention;

[0025] Figure 4 A schematic diagram of the structure of a robot control device provided in Embodiment 3 of the present invention;

[0026] Figure 5Schematic diagram of the structure of a robot used to implement an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flowchart of a robot control method provided in Embodiment 1 of the present invention. This embodiment can be applied to the case where the moving area included in the initial moving path is determined and the robot is controlled to operate according to the type of the moving area. This method can be executed by the robot control device provided in the embodiment of the present invention, and the device can be implemented in software and / or hardware. Figure 1 , the robot control method provided in this embodiment includes:

[0031] Step 110: Determine whether the robot has obtained the task instruction, and plan the initial movement path of the robot according to the pre-acquired global map information.

[0032] The robot may be a delivery robot, a guide robot or other intelligent robot, which is not limited in this embodiment. The robot may adopt positioning methods such as laser positioning and visual positioning, and is particularly suitable for robots that adopt laser mapping and laser positioning.

[0033] Task instructions are instructions that require the robot to move to perform tasks. For example, in a restaurant scenario, they may be food delivery instructions or call instructions. In a hotel scenario, they may be customer guidance instructions, etc. This embodiment does not limit this.

[0034] If it is determined that the robot has obtained the task instruction, the task location corresponding to the task instruction can be used as the target point, the current location of the robot can be used as the starting point, and the initial movement path of the robot can be planned in combination with the pre-acquired global map information and the preset path planning algorithm. Among them, the global map information is the map information containing the initial movement path, which can be obtained by pre-collection, for example, it can include the map information of the scene where the robot is located and the static obstacle information in the scene, etc., which is not limited in this embodiment. Based on the pre-acquired global map information, the real omnidirectional road section area can be filtered out, which is not affected by local planning and re-planning, and the distinction of road section areas is not affected by dynamic obstacles, and the route stability is high.

[0035] Step 120: Acquire target path points in the initial moving path, and determine the direction angle information of each target path point.

[0036] Among them, the waypoints can be points determined during the map building process, such as grid points, which are used for the robot to pass and stay during actual operation, so that the robot can plan the path according to the waypoints. The waypoints are determined during the map building process to improve the efficiency of the robot's path planning. The waypoints can also be obtained by sampling according to the distance based on the initial moving path.

[0037] The target path point is a path point included in the initial moving path that participates in subsequent calculations. It can be all path points, or it can be a path point obtained after filtering all path points according to preset filtering conditions. This embodiment does not limit this.

[0038] Among them, the direction angle of the current target path point is the angle between the line formed by the current target path point and the adjacent target path point and the preset direction of the preset coordinate axis. Correspondingly, the direction angle information is information related to the direction angle, such as including the direction angle value.

[0039] The preset coordinate axis may be any fixed coordinate axis, and the preset direction of the preset coordinate axis may be any fixed direction in the preset coordinate axis, which is not limited in this embodiment. The adjacent target path point may be the previous target path point or the next adjacent path point, which is not limited in this embodiment. Exemplarily, the preset coordinate axis may be a two-dimensional map coordinate axis established when the robot builds a map, and the coordinates of each point on the map are determined based on the two-dimensional map coordinate axis.

[0040] In this embodiment, optionally, obtaining a target path point in the initial moving path includes:

[0041] The candidate path points in the initial moving path are obtained, and the target path points are determined from the candidate path points according to a preset sampling interval.

[0042] The candidate path points may be all the path points included in the initial moving path, and this embodiment does not limit this.

[0043] The preset sampling interval may be a distance interval, for example, 0.1 meters. This embodiment does not impose any restrictions on this. The target path point is determined from the candidate path points according to the preset sampling interval. The path points with an interval of the preset sampling interval may be retained in sequence from the first path point among the candidate path points, and the retained path points are determined as the target path points.

[0044] By determining the target path point from the candidate path points according to the preset sampling interval, the problem of sudden changes in the direction angle information of the determined path points due to sudden changes in the positions of adjacent path points can be avoided if all path points are retained, and the stability of the direction angle information determination can be improved, thereby improving the accuracy of the area type determination of the moving area. Interval sampling can improve the robustness of the solution. When building a map, the grid points determined are relatively dense, and the direction angles of adjacent points are unstable.

[0045] Step 130: Determine a moving area of ​​at least one area type included in the initial moving path according to the direction angle information; wherein the area types include an omnidirectional area and a differential area.

[0046] The moving area and area type of each target path point are determined according to the azimuth information of each target path point. The area type of the moving area to which the target path point belongs can be determined by judging the type condition corresponding to the area type satisfied by the azimuth information of the target path point. For example, the azimuth information is the azimuth change value between the current target path point and the previous target path point, and the type condition is the azimuth change threshold. If the azimuth change value is greater than the azimuth change threshold, the area type of the moving area to which the target path point belongs is determined to be a differential area, otherwise, the area type of the moving area to which the target path point belongs is determined to be an omnidirectional area.

[0047] The differential speed area may be an area where the robot operates in a differential speed control mode, and the omnidirectional area may be an area where the robot operates in an omnidirectional control mode.

[0048] After determining the area type of the moving area to which each target path point belongs, each moving area is constituted by adjacent target path points of the same area type. For example, if there are target path points 1-100, and target path points 1-60 are determined to belong to a moving area with an omnidirectional area type according to the direction angle information, then target path points 1-60 constitute target area one, and target path points 61-100 are determined to belong to a moving area with a differential area type according to the direction angle information, then target path points 61-100 constitute target area two, that is, the initial moving path includes moving area one and moving area two, and the area type of moving area one is an omnidirectional area, and the area type of moving area two is a differential area.

[0049] If the area types of the moving areas to which the target path points belong are the same, the initial moving path may include a single moving area. For example, if the area types of the moving areas to which the target path points belong are all omnidirectional areas, the initial moving path includes and only includes a single omnidirectional area.

[0050] Step 140: Control the robot to operate in the moving area according to a control method associated with the area type.

[0051] After determining the moving areas included in the initial moving path, if there are multiple types of moving areas, the coordinates of the starting position and the end position of each moving area can be recorded so that the robot can adjust the control mode in time when actually moving to each moving area to operate according to the control mode associated with the area type.

[0052] Among them, the control method may include a chassis control method of the robot, a direction control method of the robot, etc., which is not limited in this embodiment.

[0053] The control mode associated with the area type, for example, if the area type is an omnidirectional area, the control mode may include a direction control mode in which the robot keeps the same direction as the road section in the omnidirectional area, and the direction remains unchanged during the movement process, and a chassis control mode in which the chassis wheels can move in all directions to drive the robot to move, such as forward, backward, sideways, diagonal, etc. If the area type is a differential area, the control mode may include a direction control mode in which the robot direction follows the wheel rotation direction in real time, and a chassis control mode in which the chassis wheels move differentially to drive the robot to move. For example, the robot direction refers to the direction in which the main body of the robot is facing except for the chassis. For example, when an interactive display screen is provided on the front of the robot body, it may refer to the direction of the interactive display screen.

[0054] Since the initial movement path is the path planned when the robot is not moving, when the robot is actually operating in the movement area according to the control method associated with the area type, the dynamic obstacles encountered during the operation can be considered for real-time local path planning; and the corresponding path planning algorithm or obstacle avoidance algorithm can be determined according to the area type, such as the use of a steering engine steering obstacle avoidance algorithm in the omnidirectional area, etc., which is not limited in this embodiment. It can be understood that in the omnidirectional area, such as a long straight channel, the robot adopts omnidirectional control, and through omnidirectional movement and omnidirectional obstacle avoidance, the efficiency and flexibility of the robot's task execution can be improved.

[0055] In this embodiment, optionally, it also includes:

[0056] If the number of area types of the moving areas included in the initial moving path is greater than or equal to two, and there is a single moving area of ​​the second area type between two moving areas of the first area type, determining whether the area length of the moving area of ​​the second area type is less than a preset length threshold; wherein the first area type is different from the second area type;

[0057] If so, the area type of the mobile area of ​​the second area type is updated to the first area type.

[0058] If the number of area types of the moving areas included in the initial moving path is greater than or equal to two, it indicates that the initial moving path includes at least two moving areas; there is a single moving area of ​​the second area type between two moving areas of the first area type, that is, there is a moving area of ​​a different type between two moving areas of the same type, for example, there is a differential area between two omnidirectional areas; it is determined whether the area length of the moving area of ​​the second area type is less than a preset length threshold, that is, it is determined whether the area length of the moving areas of the different types is less than the preset length threshold, for example, there is a differential area between two omnidirectional areas, then it is determined whether the area length of the differential area is less than the preset length threshold.

[0059] If the area length of the moving area of ​​the second area type is not less than the preset length threshold, the moving area of ​​the second area type may be retained.

[0060] If the area length of the moving area of ​​the second area type is less than the preset length threshold, the area type of the moving area of ​​the second area type is updated to the first area type. For example, there is a differential area between two omnidirectional areas, and the area length of the differential area is less than the preset length threshold, then the area type of the moving area corresponding to the differential area is changed from the differential area to the full-speed area.

[0061] By updating the area type of different types of moving areas with a shorter length between two moving areas of the same type, the effect of area merging is achieved. Since the lengths of different types of moving areas are shorter, the temporary use of other control methods has less impact on the robot operation. Therefore, while reducing the impact on the robot operation, it can avoid the robot from frequently switching control methods or path planning algorithms when passing through different types of moving areas, thereby reducing the robot's operating resource consumption and improving the robot's operating efficiency.

[0062] The technical solution provided in this embodiment plans the initial moving path according to the pre-acquired global map information before the robot runs, so that the planning of the initial moving path and the determination of the moving area included in the subsequent initial moving path do not need to consider the dynamic obstacles that may be encountered during actual operation, eliminates the interference of dynamic obstacles and local planning and re-planning during actual operation on the determination of the moving area, and improves the accuracy and stability of the determination of the moving area.

[0063] A moving area of ​​at least one area type contained in the initial moving path is determined based on the directional angle information of the target path point, that is, the determined area type is related to the road condition in the moving path, which is convenient for subsequent control of the robot to operate in the moving area according to the control method associated with the area type, enriching the robot's operating mode, and making the robot's operation conform to the road condition in the moving path, thereby improving the efficiency and applicability of the robot's operation.

[0064] And because the area types of the moving area include omnidirectional areas and differential areas, it is avoided that only omnidirectional control is used. Since the chassis wheels are omnidirectional, the robot cannot distinguish the current path direction. If the current driving path direction is identified by fixed sampling based on the points of local planning of the real-time route, the current running path is long or there are many obstacles around the current running path, especially the appearance of dynamic obstacles, which makes the current running path move distorted, and the robot is difficult to correctly identify the current path direction, and cannot stably distinguish long straight channels. When replanning or triggering obstacle avoidance, there will be a greater risk of misidentification, which may lead to the problem of the robot facing the wrong direction; it can also avoid using only differential control, which leads to frequent changes in orientation when going straight, resulting in confusion in the robot orientation; thereby reducing the impact on the execution of robot tasks such as customer guidance, improving user experience and improving the safety of task execution. The robot can make the body orientation consistent with the path direction according to the associated control method in different moving areas, improving the coordination of the robot operation. According to the real omnidirectional area, it can be filtered out, which is not affected by local planning and replanning.

[0065] Embodiment 2

[0066] Figure 2 This is a flow chart of a robot control method provided in the second embodiment of the present invention. This technical solution is to provide a supplementary explanation of the process of determining the angular direction information of each target path point. Compared with the above solution, this solution is specifically optimized as follows: the angular direction information includes the average angular direction information, and the angular direction information of each target path point is determined, including:

[0067] Determine the direction angle of each target path point according to the coordinate information of adjacent target path points;

[0068] The direction angles of other path points within a preset range of a single target path point are obtained, and the average direction angle associated with the single target path point is determined based on the direction angle of the single target path point and the direction angles of other path points. Specifically, the flowchart of the robot control method is as follows Figure 2 As shown:

[0069] Step 210: Determine whether the robot has obtained the task instruction, and plan the initial movement path of the robot according to the pre-acquired global map information.

[0070] Step 220: Acquire target path points in the initial moving path, and determine the direction angle of each target path point based on the coordinate information of adjacent target path points.

[0071] Among them, the adjacent target path point of the current target path point can be the next target path point closest to the current target path point, or it can be the previous target path point closest to the current target path point. A unified standard can be used when determining the direction angle. For example, except for the target path point at the end point, the adjacent path points of each target path point are the next target path point closest to the current target path point. This embodiment does not limit this.

[0072] Determining the direction angle of each target path point according to the coordinate information of the adjacent target path points can be performed by determining the angle between the straight line formed by the current target path point and the adjacent target path points and the preset direction of the preset coordinate axis according to the coordinate information of the current target path point and the adjacent target path points in the preset coordinate axis, and determining the angle as the direction angle of the current target path point. The preset coordinate axis can be any fixed coordinate axis, and the preset direction of the preset standard axis can be any fixed direction in the preset coordinate axis, which is not limited in this embodiment.

[0073] Step 230, obtaining the azimuth angles of other path points within a preset range of the single target path point, and determining the average azimuth angle associated with the single target path point based on the azimuth angle of the single target path point and the azimuth angles of other path points.

[0074] Obtain the direction angles of other path points within a preset range of a single target path point, where the preset range can be a fixed length range starting from a single target path point. Exemplarily, the preset range is within 4 meters behind the current target path point, where the rear is determined according to the direction of the initial moving path. For example, if the initial moving path is from point A to point B, the position closer to point A is the front relative to the position closer to point B.

[0075] The other path points within the preset range of a single target path point are all target path points within the preset range except the current target path point; the average direction angle is determined based on the direction angle angle of the single target path point and the direction angle angle of the other path points, for example, the direction angle angle of the single target path point and the direction angle angle of the other path points are divided by the number of target path points within the preset range to obtain the average direction angle, where if the target path point is determined by sampling, the number of target path points can be determined by dividing the length of the preset range by the preset sampling interval.

[0076] The average value of the direction angle associated with each target path point can be obtained in the above manner.

[0077] Step 240: Determine a moving area of ​​at least one area type included in the initial moving path according to the direction angle information; wherein the area type includes an omnidirectional area and a differential area; and the direction angle information includes an average direction angle.

[0078] The moving area of ​​at least one area type included in the initial moving path is determined based on the average direction angle, and the change value of the average direction angle between the current target path point and the previous target path point can be obtained. If the change value of the average direction angle is greater than the preset average direction angle change threshold, the area type of the moving area to which the target path point belongs is determined to be a differential area, otherwise, the area type of the moving area to which the target path point belongs is determined to be an omnidirectional area. After the area type of the moving area to which each target path point belongs is determined, each moving area is formed by adjacent target path points of the same area type.

[0079] In this embodiment, optionally, the directional angle information also includes directional angle variance, and determining the directional angle information of each target path point also includes:

[0080] Determine the angular variance of a single target path point based on the angular averages of other path points and the angular average of a single target path point;

[0081] Accordingly, determining the moving area of ​​at least one type of area included in the initial moving path according to the direction angle information includes:

[0082] According to the azimuth variance of each target path point and a preset variance threshold, the area type associated with each target path point is determined, and the moving area is determined by the target path points that are continuously associated with the same area type.

[0083] Since each target path point corresponds to an average direction angle, the average direction angle value is used as the direction angle value corresponding to the single target path point according to the average direction angle values ​​associated with other path points within the preset range and the average direction angle value associated with the single target path point, thereby calculating the direction angle variance of the single target path point.

[0084] The angular variance of each target path point and the preset variance threshold determine the area type associated with each target path point. For example, if the angular variance is greater than the preset variance threshold, the area type of the moving area to which the target path point belongs is determined to be a differential area. Otherwise, the area type of the moving area to which the target path point belongs is determined to be an omnidirectional area. A single moving area is formed by continuously associated target path points of the same area type. For example, if there are target path points 1-100, and continuous target path points 1-60 are determined to belong to a moving area of ​​an omnidirectional area according to the angular variance, then target path points 1-60 constitute target area one, and continuous target path points 61-100 are determined to belong to a moving area of ​​a differential area according to the angular variance, then target path points 61-100 constitute target area two, that is, the initial moving path includes moving area one and moving area two, and the area type of moving area one is an omnidirectional area, and the area type of moving area two is a differential area.

[0085] The angular variance of a single target path point is determined according to the angular mean value of the target path points within a preset range, and the moving area to which each target path point belongs is determined according to the angular variance and a preset variance threshold, thereby determining the range of each type of moving area. Since the angular variance can more intuitively reflect the discrete degree of the angular mean value, when the angular variance is large, it may indicate that the target path point is in an area of ​​the initial moving path that is suitable for controlling the robot's operation by a differential control method, such as a turning area. When the angular variance is small, it may indicate that the target path point is in an area of ​​the initial moving path that is suitable for controlling the robot's operation by an omnidirectional control method, such as a straight-ahead area, thereby improving the accuracy of determining the type of moving area.

[0086] In this embodiment, optionally, the preset range includes a front range and a rear range of the target path point.

[0087] The preset range can be based on each target path point as the starting point, and a fixed length range is taken before and after to form the overall preset range. For example, the preset range is 2 meters before and after the current target path point, for a total of 4 meters. This embodiment does not limit this.

[0088] It should be noted that when the target path point is the starting point, the preset range may only include the rear range of the target path point, and when the target path point is the ending point, the preset range may only include the front range of the target path point. This embodiment does not limit this.

[0089] The preset range includes the front range and the rear range of the target path point, avoiding the problem of only obtaining the directional angle information of the target path point in the rear range or the front range of the target path point, which causes the determined differential area position to be too early or too late, thereby improving the accuracy of determining the mobile area type.

[0090] Step 250: Control the robot to operate in the moving area according to a control method associated with the area type.

[0091] An embodiment of the present invention determines the azimuth angle of a target path point based on adjacent target path points, and calculates the average value of the azimuth angles within a preset range with each target path point itself as the starting point, as the average value of the azimuth angle associated with the target path point. By calculating the average value, the impact of a sudden change in the azimuth angle of a single target path point on the subsequent movement area determination is reduced, thereby improving the accuracy of the movement area determination.

[0092] In order to enable those skilled in the art to more clearly understand the present solution, the embodiment of the present invention also provides a specific implementation method.

[0093] Determine that the robot obtains the task instruction, and plan the initial movement path of the robot according to the pre-acquired global map information; obtain the target path points in the initial movement path, and determine the angular variance of each target path point; determine the area type associated with each target path point according to the angular variance of each target path point and a preset variance threshold, and determine the movement area by continuously associating the target path points of the same area type; wherein the area type includes an omnidirectional area and a differential area.

[0094] Figure 3 A schematic diagram of an initial moving path provided in the second embodiment of the present invention is shown as follows: Figure 3 As shown, the solid line portion is the omnidirectional area, and the dotted line portion is the differential area.

[0095] During the actual operation of the robot, the robot can be controlled to operate in an omnidirectional control mode in the solid line part and in a differential control mode in the dotted line part. For example, in the omnidirectional control mode, the robot's direction remains unchanged, and the chassis wheels can move omnidirectionally to drive the robot to move, thereby enhancing the robot's visual coordination and safety. For example, in the omnidirectional area, the robot may avoid obstacles through omnidirectional movement. If the robot's direction changes with the robot's movement direction, the robot's direction will change frequently, which will give pedestrians a sense of oppression. Especially for delivery robots in restaurant scenarios, frequent changes in the robot's direction will also cause risks such as falling and collision. Therefore, keeping the robot's direction consistent with the path direction in the omnidirectional area can enhance coordination, improve user experience and the safety of robot operation; in the differential control mode, the robot's direction follows the wheel rotation direction in real time, and the chassis wheels move differentially to drive the robot to move, thereby ensuring that the robot's direction is always facing the path direction, and the robot's body rotates synchronously when passing through a turning section, making the vision more coordinated and improving the user experience.

[0096] Embodiment 3

[0097] Figure 4This is a schematic diagram of the structure of a robot control device provided in the third embodiment of the present invention. The device can be implemented by hardware and / or software, can execute a robot control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 4 As shown, the device comprises:

[0098] A path planning module 410 is used to determine that the robot obtains a task instruction and plans an initial movement path of the robot according to pre-acquired global map information;

[0099] A direction angle information determination module 420 is used to obtain target path points in the initial moving path and determine the direction angle information of each target path point;

[0100] A moving area determination module 430, configured to determine a moving area of ​​at least one area type included in the initial moving path according to the direction angle information; wherein the area type includes an omnidirectional area and a differential area;

[0101] The robot operation control module 440 is used to control the robot to operate in the moving area according to a control method associated with the area type.

[0102] Based on the above technical solutions, optionally, the directional angle information includes a directional angle average value, and the directional angle information determination module includes:

[0103] A direction angle determination unit, used to determine the direction angle of each target path point according to the coordinate information of the adjacent target path points;

[0104] The direction angle average value determination unit is used to obtain the direction angle angles of other path points within a preset range of the single target path point, and determine the direction angle average value associated with the single target path point based on the direction angle angle of the single target path point and the direction angle angles of the other path points.

[0105] Based on the above technical solutions, optionally, the directional angle information further includes directional angle variance, and the directional angle information determination module further includes:

[0106] A direction angle variance determining unit, used to determine the direction angle variance of a single target path point according to the direction angle average value of the other path points and the direction angle average value of the single target path point;

[0107] Accordingly, the moving area determination module includes:

[0108] The moving area determination unit is used to determine the area type associated with each target path point based on the direction angle variance of each target path point and a preset variance threshold, and determine the moving area by the target path points continuously associated with the same area type.

[0109] Based on the above technical solutions, optionally, the preset range includes a front range and a rear range of the target path point.

[0110] On the basis of the above technical solutions, optionally, the direction angle information determination module includes:

[0111] The target path point determination unit is used to obtain candidate path points in the initial moving path and determine the target path point from the candidate path points according to a preset sampling interval.

[0112] On the basis of the above technical solutions, optionally, the device further includes:

[0113] an area length judgment module, configured to judge whether the area length of the moving area of ​​the second area type is less than a preset length threshold if the number of the area types of the moving area included in the initial moving path is greater than or equal to two, and there is a single moving area of ​​the second area type between two moving areas of the first area type; wherein the first area type is different from the second area type;

[0114] The area type updating module is configured to update the area type of the moving area of ​​the second area type to the first area type if the area length judging module judges that the result is yes.

[0115] Embodiment 4

[0116] Figure 5 A schematic diagram of a robot 10 that can be used to implement an embodiment of the present invention is shown. The robot is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The robot can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0117] like Figure 5As shown, the robot 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the robot 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] A number of components in the robot 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the robot 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a robot control method.

[0120] In some embodiments, the robot control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the robot 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the robot control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the robot control method in any other suitable manner (e.g., by means of firmware).

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on a robot having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the robot. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0126] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A robot control method, characterized in that: The method includes: Determine that the robot obtains the task instruction, and plan the initial movement path of the robot according to the pre-acquired global map information; Acquire target path points in the initial moving path, and determine direction angle information of each target path point; Determine, according to the direction angle information, a moving area of ​​at least one area type included in the initial moving path; wherein the area type includes an omnidirectional area and a differential area; The robot is controlled to operate in the moving area according to a control method associated with the area type.

2. The method according to claim 1, characterized in that The direction angle information includes a direction angle average value, and determining the direction angle information of each target path point includes: Determine the direction angle of each target path point according to the coordinate information of the adjacent target path points; Obtain the azimuth angles of other path points within a preset range of the single target path point, and determine the average azimuth angle associated with the single target path point based on the azimuth angle of the single target path point and the azimuth angles of the other path points.

3. The method according to claim 2, characterized in that The azimuth information also includes azimuth variance, and determining the azimuth information of each target path point also includes: Determine the directional angle variance of the single target path point according to the directional angle average value of the other path points and the directional angle average value of the single target path point; Accordingly, determining, according to the direction angle information, a moving area of ​​at least one area type included in the initial moving path includes: The area type associated with each target path point is determined according to the direction angle variance of each target path point and a preset variance threshold, and the moving area is determined by the target path points that are continuously associated with the same area type.

4. The method according to claim 2 or 3, characterized in that: The preset range includes a front range and a rear range of the target path point.

5. The method according to claim 1, characterized in that Obtaining a target path point in the initial moving path includes: The candidate path points in the initial moving path are obtained, and the target path point is determined from the candidate path points according to a preset sampling interval.

6. The method according to claim 1, characterized in that Also includes: If the number of the area types of the moving areas included in the initial moving path is greater than or equal to two, and there is a single moving area of ​​the second area type between two moving areas of the first area type, determining whether the area length of the moving area of ​​the second area type is less than a preset length threshold; wherein the first area type is different from the second area type; If so, the area type of the mobile area of ​​the second area type is updated to the first area type.

7. A robot control device, characterized in that: include: A path planning module, used to determine that the robot obtains the task instruction and plans the initial movement path of the robot according to the pre-acquired global map information; A direction angle information determination module, used to obtain target path points in the initial moving path and determine the direction angle information of each target path point; A moving area determination module, used to determine a moving area of ​​at least one area type included in the initial moving path according to the direction angle information; wherein the area type includes an omnidirectional area and a differential area; The robot operation control module is used to control the robot to operate in the moving area according to a control method associated with the area type.

8. The device according to claim 7, characterized in that The direction angle information includes a direction angle average value, and the direction angle information determination module includes: A direction angle determination unit, used to determine the direction angle of each target path point according to the coordinate information of the adjacent target path points; The direction angle average value determination unit is used to obtain the direction angle angles of other path points within a preset range of the single target path point, and determine the direction angle average value associated with the single target path point based on the direction angle angle of the single target path point and the direction angle angles of the other path points.

9. A robot, characterized in that: The robot comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the robot control method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot control method according to any one of claims 1 to 6 when executed.

Images