Robot control method and device, robot, and storage medium

Abstract

The present disclosure relates to a robot control method, device, robot and storage medium, the method comprising: in a process in which a robot follows a target object to move, in response to the robot not detecting the target object in a field of view range, controlling the robot to reduce a movement amplitude, and controlling the robot to move the field of view range through movement; in a process in which the field of view range moves, in response to the robot detecting the target object in the field of view range, according to a detection result of the target object, controlling the robot to follow the target object to move.

Description

Technical Field

[0001] This disclosure relates to the field of robotics technology, specifically to a robot control method, device, robot, and storage medium. Background Technology

[0002] In recent years, robotics technology has continuously developed, becoming increasingly intelligent and automated, with improvements in the richness, stability, and flexibility of its movements. Current robots can not only perform repetitive, periodic actions such as sweeping and walking, but also execute following actions, that is, moving alongside a target. However, in related technologies, robots are prone to losing sight of the target when performing following actions, leading to following failure. Summary of the Invention

[0003] To overcome the problems existing in the related technologies, this disclosure provides a robot control method, device, robot, and storage medium to solve the defects in the related technologies.

[0004] According to a first aspect of the present disclosure, a robot control method is provided, the method comprising:

[0005] During the process of the robot following the target object, in response to the robot not detecting the target object within the field of view, the robot is controlled to reduce the amplitude of movement and the field of view is moved by the robot.

[0006] During the movement within the field of view, in response to the robot detecting the target object within the field of view, the robot is controlled to follow the target object based on the detection result of the target object.

[0007] In one embodiment of this disclosure, the robot includes a legged robot;

[0008] Controlling the robot to reduce its range of motion includes:

[0009] Control the robot to reduce its gait frequency; and / or,

[0010] Control the robot to lower the height of its raised leg.

[0011] In one embodiment of this disclosure, it further includes:

[0012] During the process of the robot following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined.

[0013] During the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot is controlled to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance.

[0014] In one embodiment of this disclosure, controlling the robot to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance includes:

[0015] Based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot is controlled to adjust the field of view to the pitch angle corresponding to the target distance.

[0016] In one embodiment of this disclosure, it further includes:

[0017] During the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0018] Based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view.

[0019] In one embodiment of this disclosure, controlling the robot to move the field of view by means of movement includes:

[0020] The robot is controlled to move its field of view through rotational motion.

[0021] The step of controlling the robot to move the target object to a target position within the field of view based on the position of the target object within the field of view includes:

[0022] Based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to rotate so that the target object reaches the target position.

[0023] In one embodiment of this disclosure, it further includes:

[0024] During the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0025] Controlling the robot to move its field of view by means of movement includes:

[0026] Based on the most recently determined position of the target object within the field of view, determine the direction of movement of the field of view;

[0027] The robot is controlled to move its field of view in the direction of movement.

[0028] In one embodiment of this disclosure, the step of controlling the robot to reduce its movement amplitude and controlling the robot to move the field of view by moving in response to the robot not detecting the target object within its field of view includes:

[0029] In response to the robot not detecting the target object within its field of view for a duration that reaches a duration threshold, the robot is controlled to reduce its movement amplitude and to move its field of view by moving.

[0030] In one embodiment of this disclosure, the step of controlling the robot to follow the target object in response to the robot detecting the target object within the field of view, based on the detection result of the target object, includes:

[0031] In response to the robot detecting the target object within the field of view, the robot is controlled to resume its motion amplitude, and based on the detection result of the target object, the robot is controlled to follow the target object.

[0032] In one embodiment of this disclosure, it further includes:

[0033] In response to the robot detecting the target object within the field of view, the robot is controlled to adjust the field of view to a level angle.

[0034] According to a second aspect of the present disclosure, a robot control device is provided, the device comprising:

[0035] The amplitude reduction module is used to control the robot to reduce its movement amplitude when the robot does not detect the target object within its field of view during the process of the robot following the target object; and to control the robot to move the field of view by moving.

[0036] The following module is used to control the robot to follow the target object as it moves within the field of view, in response to the robot detecting the target object within the field of view.

[0037] In one embodiment of this disclosure, the robot includes a legged robot;

[0038] The amplitude reduction module is used to control the robot to reduce its movement amplitude, specifically for:

[0039] Control the robot to reduce its gait frequency; and / or,

[0040] Control the robot to lower the height of its raised leg.

[0041] In one embodiment of this disclosure, a first pitch module is further included, for:

[0042] During the process of the robot following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined.

[0043] During the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot is controlled to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance.

[0044] In one embodiment of this disclosure, when the first pitch module is used to control the robot to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance, it is specifically used for:

[0045] Based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot is controlled to adjust the field of view to the pitch angle corresponding to the target distance.

[0046] In one embodiment of this disclosure, a target module is further included, for:

[0047] During the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0048] Based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view.

[0049] In one embodiment of this disclosure, the amplitude reduction module is used to control the robot to move the field of view through motion, specifically for:

[0050] The robot is controlled to move its field of view through rotational motion.

[0051] The target module is used to control the robot to move the target object to the target position within the field of view based on the position of the target object within the field of view. Specifically, it is used for:

[0052] Based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to rotate so that the target object reaches the target position.

[0053] In one embodiment of this disclosure, a positioning module is further included, for:

[0054] During the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0055] The amplitude reduction module is used to control the robot to move its field of view through motion, specifically for:

[0056] Based on the most recently determined position of the target object within the field of view, determine the direction of movement of the field of view;

[0057] The robot is controlled to move its field of view in the direction of movement.

[0058] In one embodiment of this disclosure, the reduction module is specifically used for:

[0059] In response to the robot not detecting the target object within its field of view for a duration that reaches a duration threshold, the robot is controlled to reduce its movement amplitude and to move its field of view by moving.

[0060] In one embodiment of this disclosure, the follow module is specifically used for:

[0061] In response to the robot detecting the target object within the field of view, the robot is controlled to resume its motion amplitude, and based on the detection result of the target object, the robot is controlled to follow the target object.

[0062] In one embodiment of this disclosure, a second pitch module is further included, for:

[0063] In response to the robot detecting the target object within the field of view, the robot is controlled to adjust the field of view to a level angle.

[0064] According to a third aspect of the present disclosure, a robot is provided, the robot including a memory and a processor, the memory being used to store computer instructions executable on the processor, and the processor being used to implement the robot control method of the first aspect when executing the computer instructions.

[0065] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0066] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0067] The robot control method provided in this disclosure, during the process of a robot following a target object, responds to the robot not detecting the target object within its field of view by reducing the robot's movement amplitude and moving the field of view. During this movement, if the robot detects the target object within the field of view, it controls the robot to follow the target object based on the detection result. In other words, this method operates during the robot's following action; if the target is lost, this method is used to retrieve the target, allowing the robot to continue following it. Because the robot's movement amplitude is reduced before moving the field of view, the clarity and stability of the acquired images are improved, enabling timely detection of the target object after it enters the field of view, thus accurately and promptly retrieving the target object and resuming the following action. Attached Figure Description

[0068] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0069] Figure 1 This is a flowchart illustrating a robot control method according to an exemplary embodiment of this disclosure;

[0070] Figure 2 This is a schematic diagram of the pitch angle illustrating the field of view of an exemplary embodiment of the present disclosure;

[0071] Figure 3 This is a schematic diagram illustrating the disappearance of the target object from the field of view in an exemplary embodiment of this disclosure;

[0072] Figure 4 This is a schematic diagram illustrating the angle between the position of the target object within the field of view and the target position, as shown in an exemplary embodiment of this disclosure;

[0073] Figure 5 This is a schematic diagram of the structure of a robot control device shown in an exemplary embodiment of the present disclosure;

[0074] Figure 6 This is a structural block diagram of a robot illustrated in an exemplary embodiment of this disclosure. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0076] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0077] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0078] In recent years, robotics technology has continuously developed, becoming increasingly intelligent and automated, with improvements in the richness, stability, and flexibility of its movements. Current robots can not only perform repetitive, periodic actions such as sweeping and walking, but also execute following actions, that is, moving alongside a target. However, in related technologies, robots are prone to losing sight of the target when performing following actions, leading to following failure.

[0079] Based on this, in a first aspect, at least one embodiment of this disclosure provides a robot control method, please refer to the appendix. Figure 1 It illustrates the process of the method, including steps S101 to S102.

[0080] This method can be applied to robots, such as legged robots. Legged robots have multiple legs and can walk by alternating steps. The robot is equipped with image acquisition elements such as depth cameras. These elements acquire images within their field of view, and the robot can process these images to detect objects within that field of view. For example, the Reid algorithm can be used to process the image content and depth data of the depth images acquired by the depth camera to obtain the object detection results within the field of view. It can be understood that the field of view of the image acquisition elements is the same as the robot's field of view.

[0081] For example, this method can be applied to the process of a robot performing a following action. If the target is lost, this method can be used to retrieve the target, thereby resuming the execution of the following action.

[0082] In step S101, during the process of the robot following the target object, in response to the robot not detecting the target object within the field of view, the robot is controlled to reduce the amplitude of its movement and to move the field of view by moving.

[0083] In this context, the robot following the target object is called the robot performing the following action.

[0084] Before the robot performs a following action, it can first acquire images within its field of view and process the acquired images to detect at least one object in the images. Then, the detection results can be presented to the user through a human-computer interaction program (such as a program installed on the robot or a program installed on a terminal device bound to the robot), prompting the user to select a target object (i.e., the object the user wants the robot to follow) from the above at least one object. After receiving the user's instruction to select the target object, the robot can extract the features of the target object from the above images and start following the target object based on the features, that is, it moves while keeping its relative position to the target object unchanged.

[0085] Once the robot begins to perform the following action, it can acquire images within the field of view at a preset frequency, process the acquired images to detect the target object within the field of view, and then control the robot to follow the target object based on the detection results, so as to keep the relative position between the robot and the target object unchanged.

[0086] For example, the detection result may include the target distance between the target object and the robot. That is, when the robot is following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined.

[0087] For another example, the detection result may include the position of the target object within the field of view. That is, during the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined.

[0088] To continue with the example, the detection results can also include the relative pose of the robot and the target object.

[0089] It is understandable that robots, especially legged robots, experience body shaking during movement, particularly when multiple legs are on the ground. For example, the landing of a legged robot's foot causes body shaking. This shaking reduces the clarity and stability of images captured by the robot, thus decreasing the accuracy of target object detection, such as a target object entering the field of view but not being detected. The amplitude of the robot's movement affects the amount of body shaking during movement; the greater the amplitude, the more severe the shaking. Therefore, reducing the amplitude of movement can improve the accuracy of target object detection within the field of view. Taking a legged robot as an example, controlling the robot to reduce its amplitude of movement can include: controlling the robot to reduce its gait frequency; and / or controlling the robot to reduce its leg lift height. Here, gait frequency represents the speed of a single step, and leg lift height represents the force of the robot's foot landing. Reducing the robot's amplitude of movement through at least one of these aspects can alleviate body shaking when the robot's foot lands, thereby improving the clarity and stability of images captured by the robot, as well as the accuracy of target object detection results.

[0090] Understandably, the pitch angle of a robot's field of view affects the real-world scene it covers. Most notably, different pitch angles result in different distance ranges within the real-world scene that can completely encompass the target object; these distance ranges can be greater than a certain value. For example, please refer to the attached diagram. Figure 2When the pitch angle of the field of view is a level angle (i.e., the center direction of the field of view is horizontal, and the angle between pitch and horizontal is 0), the distance range in a real-world scenario that can completely cover the target object is greater than n meters (i.e., if the distance between the target object and the robot is greater than or equal to n meters, the robot can be completely covered by the field of view, meaning the target object can completely enter the field of view; if the distance between the target object and the robot is less than n meters, the robot cannot be completely covered by the field of view, meaning the target object cannot completely enter the field of view). When the pitch angle of the field of view is the maximum tilt angle (i.e., the maximum tilt angle that the robot can achieve in the field of view, and the angle between pitch and horizontal is pitch_max), the distance range in a real-world scenario that can completely cover the target object is greater than m (m is less than n) meters (i.e., if the distance between the target object and the robot is greater than or equal to m meters, the robot can be completely covered by the field of view, meaning the target object can completely enter the field of view; if the distance between the target object and the robot is less than m meters, the robot cannot be completely covered by the field of view, meaning the target object cannot completely enter the field of view). Based on this, during the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot can adjust its field of view to the corresponding pitch angle based on the most recently determined target distance. For example, based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot can adjust its field of view to the pitch angle corresponding to the target distance. For instance, the pitch angle corresponding to the target distance can be calculated using the following formula:

[0091]

[0092] Where β is the pitch angle corresponding to the target distance, x is the target distance, n is the distance corresponding to the horizontal angle, m is the distance corresponding to the extreme pitch angle, and point_max is the extreme pitch angle. Both β and point_max can be represented by the angle between them and the horizontal angle.

[0093] By adjusting the pitch angle of the field of view, the target object can be covered as completely as possible when it enters the field of view, thereby increasing the probability of the target object being detected when it enters the field of view, and thus further improving the detection accuracy of the target object.

[0094] Since the robot detects the target object within its field of view and determines its position within that field of view during the robot's movement to follow the target object, the direction of movement for the field of view can be determined first based on the most recently determined position of the target object within the field of view. Then, the robot can be controlled to move the field of view in that direction. Generally, the target object disappears from the edge of the field of view and then reaches a certain direction within the field of view. That is, the most recently determined position of the target object within the field of view is likely at the edge of the field of view. Therefore, the direction of movement for the field of view can be determined by the position of the most recently determined target object within the field of view relative to the center of the field of view. (For example, see attached image.) Figure 3 As shown, if the most recently determined target object is located at the right edge of the field of view (i.e., the target object disappears from the right edge), then the direction of movement of the field of view is to the right.

[0095] Target objects often disappear from the field of view due to lateral movement in the real-world scene (i.e., their position on the plane changes while their height remains relatively constant). Therefore, optionally, when controlling the robot to move the field of view, the robot can be controlled to move the field of view through rotation. For example, the robot can be controlled to rotate in the direction of movement of the field of view, thereby moving the field of view in that direction.

[0096] In some cases, the robot may fail to detect the target object within its field of view due to poor image clarity and / or stability of the images acquired by its image acquisition components. This failure is caused by noise in the acquired data. The robot will recover once the noise disappears, and the target object will be successfully detected. Therefore, to avoid the target retrieval step being falsely triggered due to data noise, this step can be implemented in response to the robot's failure to detect the target object within its field of view for a duration reaching a threshold. The robot's movement amplitude can be reduced, and the field of view can be shifted through movement. In other words, the target retrieval step is only triggered after the target object has been lost for a certain duration, thereby improving the triggering accuracy of this method.

[0097] In step S102, during the movement of the field of view, in response to the robot detecting the target object within the field of view, the robot is controlled to follow the target object based on the detection result of the target object.

[0098] The explanation of step S101 mentions that the target object will disappear from the edge of the field of view. Correspondingly, during the movement of the field of view, the target object will most likely also enter the field of view from the edge of the field of view. However, the target object at the edge of the field of view is often unstable, that is, it is easy to disappear from the field of view again. Therefore, when the target object is detected in the field of view, the field of view can be moved further so that the target object reaches a more stable position in the field of view (that is, a position that is not easy to disappear, hereinafter referred to as the target position, for example, the target position can be a certain angle range on both sides of the center of the field of view).

[0099] In one possible embodiment, firstly, during the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined; nextly, based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view. For example, based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to perform a rotational movement to bring the target object to the target position.

[0100] Please refer to the appendix. Figure 4 The example illustrates the process of calculating the angle α between the position of the target object within the field of view and the target position, wherein the robot determines the position coordinates of the target object in the robot coordinate system as (x, y), and the pose of the robot in the robot coordinate system as (x, y). r y r yaw r Then α can be calculated using the following formula:

[0101]

[0102] When a robot follows a target object, its speed and sensitivity will affect the success rate of the following motion. Therefore, before continuing the following action in this step, the range of motion can be restored. That is, this step can respond to the robot detecting the target object within the field of view, control the robot to restore the range of motion, and control the robot to follow the target object based on the detection result of the target object.

[0103] In addition, robots often achieve a downward view of their field of vision by tilting their bodies, but this tilting can cause poor robot motion stability. Therefore, before continuing the following action in this step, the field of vision can be restored to a level view. That is, this step can also respond to the robot detecting the target object within the field of vision, control the robot to adjust the field of vision to a level view, and control the robot to follow the target object based on the detection result of the target object.

[0104] The robot control method provided in this disclosure, during the process of a robot following a target object, responds to the robot not detecting the target object within its field of view by reducing the robot's movement amplitude and moving the field of view. During this movement, if the robot detects the target object within the field of view, it controls the robot to follow the target object based on the detection result. In other words, this method operates during the robot's following action; if the target is lost, this method is used to retrieve the target, allowing the robot to continue following it. Because the robot's movement amplitude is reduced before moving the field of view, the clarity and stability of the acquired images are improved, enabling timely detection of the target object after it enters the field of view, thus accurately and promptly retrieving the target object and resuming the following action.

[0105] Overall, this method decouples the motion tracking and target retrieval processes. During the motion tracking phase, it accurately tracks the target object with a large motion amplitude and a field of view with a normal angle. During the target retrieval phase, it searches for the target object with a smaller motion amplitude and a field of view with a pitch angle adapted to the target distance. This improves the detection accuracy of the target object in both phases and achieves its respective objectives: accurate tracking during motion tracking and rapid retrieval during target retrieval.

[0106] According to a second aspect of the embodiments of this disclosure, a robot control device is provided; please refer to the appendix. Figure 5 The device includes:

[0107] The amplitude reduction module 501 is used to control the robot to reduce the amplitude of movement and control the robot to move the field of view by moving when the robot is following the target object and the target object is not detected within the field of view.

[0108] The following module 502 is used to control the robot to follow the target object in motion during the movement of the field of view, in response to the robot detecting the target object in the field of view, based on the detection result of the target object.

[0109] In one embodiment of this disclosure, the robot includes a legged robot;

[0110] The amplitude reduction module is used to control the robot to reduce its movement amplitude, specifically for:

[0111] Control the robot to reduce its gait frequency; and / or,

[0112] Control the robot to lower the height of its raised leg.

[0113] In one embodiment of this disclosure, a first pitch module is further included, for:

[0114] During the process of the robot following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined.

[0115] During the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot is controlled to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance.

[0116] In one embodiment of this disclosure, when the first pitch module is used to control the robot to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance, it is specifically used for:

[0117] Based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot is controlled to adjust the field of view to the pitch angle corresponding to the target distance.

[0118] In one embodiment of this disclosure, a target module is further included, for:

[0119] During the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0120] Based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view.

[0121] In one embodiment of this disclosure, the amplitude reduction module is used to control the robot to move the field of view through motion, specifically for:

[0122] The robot is controlled to move its field of view through rotational motion.

[0123] The target module is used to control the robot to move the target object to the target position within the field of view based on the position of the target object within the field of view. Specifically, it is used for:

[0124] Based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to rotate so that the target object reaches the target position.

[0125] In one embodiment of this disclosure, a positioning module is further included, for:

[0126] During the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined;

[0127] The amplitude reduction module is used to control the robot to move its field of view through motion, specifically for:

[0128] Based on the most recently determined position of the target object within the field of view, determine the direction of movement of the field of view;

[0129] The robot is controlled to move its field of view in the direction of movement.

[0130] In one embodiment of this disclosure, the reduction module is specifically used for:

[0131] In response to the robot not detecting the target object within its field of view for a duration that reaches a duration threshold, the robot is controlled to reduce its movement amplitude and to move its field of view by moving.

[0132] In one embodiment of this disclosure, the follow module is specifically used for:

[0133] In response to the robot detecting the target object within the field of view, the robot is controlled to resume its motion amplitude, and based on the detection result of the target object, the robot is controlled to follow the target object.

[0134] In one embodiment of this disclosure, a second pitch module is further included, for:

[0135] In response to the robot detecting the target object within the field of view, the robot is controlled to adjust the field of view to a level angle.

[0136] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the method in the first aspect, and will not be elaborated upon here.

[0137] Thirdly, at least one embodiment of this disclosure provides a robot, please refer to the appendix. Figure 6 The diagram illustrates the structure of the robot, which includes a memory and a processor. The memory stores computer instructions that can run on the processor, and the processor controls the robot based on the method described in any of the first aspects when executing the computer instructions.

[0138] Fourthly, at least one embodiment of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the first aspects.

[0139] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0140] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A robot control method, characterized in that, The method includes: During the process of the robot following the target object, in response to the robot not detecting the target object within the field of view, the robot is controlled to reduce the amplitude of movement and the field of view is moved by the robot. During the movement within the field of view, in response to the robot detecting the target object within the field of view, the robot is controlled to follow the target object based on the detection result of the target object; The robot includes a legged robot; Controlling the robot to reduce its range of motion includes: Control the robot to reduce its gait frequency; and / or, Control the robot to lower the height of its raised leg.

2. The robot control method according to claim 1, characterized in that, Also includes: During the process of the robot following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined. During the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot is controlled to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance.

3. The robot control method according to claim 2, characterized in that, The step of controlling the robot to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance includes: Based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot is controlled to adjust the field of view to the pitch angle corresponding to the target distance.

4. The robot control method according to claim 1, characterized in that, Also includes: During the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined; Based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view.

5. The robot control method according to claim 4, characterized in that, Controlling the robot to move its field of view by means of movement includes: The robot is controlled to move its field of view through rotational motion. The step of controlling the robot to move the target object to a target position within the field of view based on the position of the target object within the field of view includes: Based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to rotate so that the target object reaches the target position.

6. The robot control method according to claim 1, characterized in that, Also includes: During the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined; Controlling the robot to move its field of view by means of movement includes: Based on the most recently determined position of the target object within the field of view, determine the direction of movement of the field of view; The robot is controlled to move its field of view in the direction of movement.

7. The robot control method according to claim 1, characterized in that, The step of controlling the robot to reduce its movement amplitude and moving the field of view by controlling the robot to move in response to the robot not detecting the target object within its field of view includes: In response to the robot not detecting the target object within its field of view for a duration that reaches a duration threshold, the robot is controlled to reduce its movement amplitude and to move its field of view by moving.

8. The robot control method according to claim 1, characterized in that, The step of responding to the robot detecting the target object within the field of view, and controlling the robot to follow the target object based on the detection result of the target object, includes: In response to the robot detecting the target object within the field of view, the robot is controlled to resume its motion amplitude, and based on the detection result of the target object, the robot is controlled to follow the target object.

9. The robot control method according to claim 1, characterized in that, Also includes: In response to the robot detecting the target object within the field of view, the robot is controlled to adjust the field of view to a level angle.

10. A robot control device, characterized in that, The device includes: The amplitude reduction module is used to control the robot to reduce its movement amplitude when the robot does not detect the target object within its field of view during the process of the robot following the target object; and to control the robot to move the field of view by moving. The following module is used to control the robot to follow the target object in motion as the robot moves within the field of view, in response to the robot detecting the target object within the field of view. The robot includes a legged robot; The amplitude reduction module is used to control the robot to reduce its movement amplitude, specifically for: Control the robot to reduce its gait frequency; and / or, Control the robot to lower the height of its raised leg.

11. The robot control device according to claim 10, characterized in that, It also includes a first pitch module, used for: During the process of the robot following the target object, in response to the robot detecting the target object within its field of view, the target distance between the target object and the robot is determined. During the process of the robot following the target object, in response to the robot not detecting the target object within its field of view, the robot is controlled to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance.

12. The robot control device according to claim 11, characterized in that, The first pitch module is used to control the robot to adjust the field of view to the corresponding pitch angle based on the most recently determined target distance, specifically for: Based on the relative relationship between the target distance and the distance corresponding to the horizontal viewing angle, and the relative relationship between the target distance and the distance corresponding to the extreme downward viewing angle, the robot is controlled to adjust the field of view to the pitch angle corresponding to the target distance.

13. The robot control device according to claim 10, characterized in that, It also includes a target module for: During the movement within the field of view, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined; Based on the position of the target object within the field of view, the robot is controlled to move so that the target object reaches the target position within the field of view.

14. The robot control device according to claim 13, characterized in that, The amplitude reduction module is used to control the robot to move its field of view through motion, specifically for: The robot is controlled to move its field of view through rotational motion. The target module is used to control the robot to move the target object to the target position within the field of view based on the position of the target object within the field of view. Specifically, it is used for: Based on the angle and relative direction between the position of the target object within the field of view and the target position, the robot is controlled to rotate so that the target object reaches the target position.

15. The robot control device according to claim 10, characterized in that, It also includes a positioning module, used for: During the process of the robot following the target object, in response to the robot detecting the target object within the field of view, the position of the target object within the field of view is determined; The amplitude reduction module is used to control the robot to move its field of view through motion, specifically for: Based on the most recently determined position of the target object within the field of view, determine the direction of movement of the field of view; The robot is controlled to move its field of view in the direction of movement.

16. The robot control device according to claim 10, characterized in that, The amplitude reduction module is specifically used for: In response to the robot not detecting the target object within its field of view for a duration that reaches a duration threshold, the robot is controlled to reduce its movement amplitude and to move its field of view by moving.

17. The robot control device according to claim 10, characterized in that, The follow module is specifically used for: In response to the robot detecting the target object within the field of view, the robot is controlled to resume its motion amplitude, and based on the detection result of the target object, the robot is controlled to follow the target object.

18. The robot control device according to claim 10, characterized in that, It also includes a second pitch module, used for: In response to the robot detecting the target object within the field of view, the robot is controlled to adjust the field of view to a level angle.

19. A robot, characterized in that, The robot includes a memory and a processor. The memory is used to store computer instructions that can be executed on the processor. The processor is used to implement the robot control method of any one of claims 1 to 9 when executing the computer instructions.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method of any one of claims 1 to 9.

Images