Equipment state detection method and device

Abstract

The embodiment of the invention discloses an equipment state detection method and device, which are used for improving the effectiveness of equipment state detection. According to the scheme, the method comprises the steps that a control instruction and state information of equipment are obtained, the control instruction is used for controlling the equipment to execute a target action in a target time period, and the state information is obtained by monitoring the equipment in the target time period through a state sensor; determining a first state parameter corresponding to the target action executed by the equipment and a second state parameter corresponding to the state information; determining the ground clearance probability of the equipment according to the difference degree between the first state parameter and the second state parameter; and if the ground clearance probability meets a ground clearance judgment condition, determining that the equipment is in a ground clearance state.

Description

Technical Field

[0001] The present application relates to the field of device status detection, and in particular to a device status detection method and apparatus. Background Art

[0002] In the field of equipment status monitoring, the status of the equipment can be monitored to determine whether the equipment is in a normal working state. Specifically, for robots that can move and make movements, the status of the robot can be identified to determine whether the robot has fallen, left the ground, or is in other abnormal states, which is conducive to instantly restoring the normal state in an abnormal state to restore the normal action function of the robot.

[0003] How to improve the effectiveness of device status detection is the technical problem to be solved by this application. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a device status detection method and apparatus to improve the effectiveness of device status detection.

[0005] In a first aspect, a device status detection method is provided, comprising: Acquire control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period; Determine a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information; Determining a probability of the device leaving the ground according to a degree of difference between the first state parameter and the second state parameter; If the lift-off probability satisfies a lift-off determination condition, it is determined that the device is in a lift-off state.

[0006] In a second aspect, a device state detection device is provided, comprising: An acquisition module, which acquires control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period; A first determining module determines a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information; a second determination module, determining a probability of the device leaving the ground according to a difference between the first state parameter and the second state parameter; The determination module determines that the device is in a lift-off state if the lift-off probability satisfies a lift-off determination condition.

[0007] According to a third aspect, an electronic device is provided. The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the method according to the first aspect are implemented.

[0008] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method according to the first aspect are implemented.

[0009] In a fifth aspect, a computer program product is provided, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to execute part or all of the steps of the method of the first aspect.

[0010] In the embodiment of the present application, first, the control instruction and state information of the device are obtained. The control instruction is used to control the device to perform the target action within the target time period, and the state information is obtained by the state sensor monitoring the device within the target time period; then, the first state parameter corresponding to the device performing the target action and the second state parameter corresponding to the state information are determined; then, the probability of the device leaving the ground is determined according to the degree of difference between the first state parameter and the second state parameter; if the probability of leaving the ground meets the condition for judging the device leaving the ground, it is determined that the device is in the state of leaving the ground. Among them, the first state parameter can represent the state of the device under the control instruction, the second state parameter can represent the state of the device under the monitoring of the sensor, and the degree of difference between the first state parameter and the second state parameter can represent the difference between the device's own control state based on the control instruction and the actual state, thereby reflecting the influence of external factors on the state of the device, thereby determining the probability of the device leaving the ground, so as to accurately determine whether the device is in the state of leaving the ground. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1a This is one of the flowcharts of a device status detection method according to an embodiment of the present application; Figure 1b It is a schematic diagram of the state detection logic of a robot of a device state detection method according to an embodiment of the present application; Figure 2 This is a second flow chart of a device status detection method according to an embodiment of the present application; Figure 3 This is a flowchart of a device status detection method according to an embodiment of the present application; Figure 4This is a fourth flow chart of a device status detection method according to an embodiment of the present application; Figure 5 This is a fifth flow chart of a device status detection method according to an embodiment of the present application; Figure 6 This is a sixth flow chart of a device status detection method according to an embodiment of the present application; Figure 7 This is a seventh flow chart of a device status detection method according to an embodiment of the present application; Figure 8 This is a flowchart of a device status detection method according to an embodiment of the present application; Fig. 9 It is a schematic diagram of the structure of a device status detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application. The numbering of the drawings in this application is only used to distinguish the various steps in the scheme, and is not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0013] In the field of equipment status monitoring, off-the-ground detection can also be called pick-up detection, which is a detection of when the equipment is lifted or other reasons cause it to leave the ground or other supporting surfaces. Generally speaking, when the equipment is off the ground due to external reasons, it may not be able to control its own state by controlling its own wheels or other components, and it may even cause external collisions and damage equipment components due to operation in an abnormal state. Therefore, accurately and effectively identifying the off-the-ground state of the equipment can help improve the effectiveness of equipment control and enhance equipment stability.

[0014] The off-the-ground state of the device can be realized by installing a distance detection sensor on the device. For example, a distance detection sensor is set on the surface of the device close to the ground. Once the distance from the ground is measured to be greater than a certain distance, it is determined that the device has been picked up, that is, it is in the off-the-ground state. However, in some scenarios, if the distance detection sensor is blocked when the device is picked up, the distance detection sensor will fail and cannot effectively identify the off-the-ground state.

[0015] In order to solve the problems existing in the related art, the present application embodiment provides a device status detection method, such as Figure 1a As shown, including: S11: Acquire control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period.

[0016] The control instruction may be an instruction determined by the device's processor itself through processing and calculation, or an instruction received from other devices through wired or wireless means. The control instruction is used to control the device to perform a target action within a target period of time, and the target action may include the movement of the overall position of the device, the movement of movable parts, etc.

[0017] The above-mentioned state information is obtained by monitoring the device by a state sensor during the target period. The state sensor can be set inside the device or in the environment. The state information can include instantaneous state parameter values, such as angles. The state information can also include speed values, such as angular velocity, linear velocity, etc.

[0018] Optionally, the state sensor provided inside the device may be, for example, an inertial measurement unit (IMU), which may calculate the measured data parameters through a state fusion algorithm to obtain a state quaternion. In addition, the state sensor provided inside the device may also include a speed sensor encoder, which may be specifically used to measure the wheel speed of the device to calculate the linear velocity and angular velocity of the device to obtain the state parameters of the device.

[0019] Optionally, the status sensor disposed outside the device may be an image acquisition device such as a camera, which can analyze the status of the device by acquiring and analyzing images.

[0020] S12: Determine a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information.

[0021] In this step, the control instruction and the state information are parsed respectively to determine the first state parameter corresponding to the target action indicated by the control instruction and the second state parameter corresponding to the state information. The state parameter may be a parameter used to characterize the state of the device. For example, the state parameter may include a linear velocity parameter, an angular velocity parameter, etc., wherein the angular velocity parameter may include a pitch angle parameter, a yaw angle parameter, a roll angle parameter, etc.

[0022] Any state parameter may include multiple type parameters, and the first state parameter and the second state parameter include at least one common type parameter.

[0023] S13: Determine the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter.

[0024] In this step, a difference comparison is performed on the first state parameter and the second state parameter to determine the degree of difference. The degree of difference may refer to the difference in the type parameter shared by the first state parameter and the second state parameter.

[0025] For example, the first state parameter includes a linear speed parameter of 1m / s, and the second state parameter includes a linear speed parameter of 0.1m / s. Since the difference between the two linear speed parameters is large, it can be determined that the device is likely to be lifted off the ground due to external factors, resulting in the actual linear speed of the device not achieving the linear speed of the target state indicated by the control instruction, and the probability of the device lifting off the ground can be determined based on the difference.

[0026] For another example, the first state parameter includes a linear velocity parameter of 1m / s and an angular velocity parameter of 30° / s; the second state parameter includes a linear velocity parameter of 0.8m / s and an angular velocity parameter of 20° / s. Although the difference between the above two linear velocity parameters is small, and the difference between the above two angular velocity parameters is small, there are differences between the linear velocity parameter and the angular velocity parameter. It can be determined that the device is likely to be lifted off the ground due to external factors, resulting in the actual state of the device not achieving the target state indicated by the control instruction, and then the probability of the device lifting off the ground can be determined based on the above degree of difference.

[0027] In this step, the degree of difference between the first state parameter and the second state parameter can be determined based on a variety of factors such as the difference between the first state parameter and the second state parameter, the type of parameter difference, and the like, and then the probability of the device leaving the ground can be determined based on the degree of difference.

[0028] S14: If the lift-off probability satisfies a lift-off determination condition, determining that the device is in a lift-off state.

[0029] The above-mentioned lift-off determination condition can be preset according to actual needs. For example, the lift-off determination condition can include a first preset lift-off probability, and if the lift-off probability is greater than or equal to the first preset lift-off probability, it is determined that the device is in a lift-off state.

[0030] The lift-off determination condition may also be set based on time. For example, if the lift-off probability is continuously greater than a second preset lift-off probability within a preset time period, it is determined that the device is in a lift-off state.

[0031] Through the scheme provided by the embodiment of the present application, first, the control instruction and state information of the device are obtained, the control instruction is used to control the device to perform the target action within the target period, and the state information is obtained by the state sensor monitoring the device within the target period; then, the first state parameter corresponding to the device performing the target action and the second state parameter corresponding to the state information are determined; then, the probability of the device leaving the ground is determined according to the degree of difference between the first state parameter and the second state parameter; if the probability of leaving the ground meets the condition of leaving the ground, it is determined that the device is in the state of leaving the ground. Among them, the first state parameter can represent the state of the device under the control instruction, the second state parameter can represent the state of the device under the monitoring of the sensor, and the degree of difference between the first state parameter and the second state parameter can represent the difference between the device's own control state based on the control instruction and the actual state, thereby reflecting the influence of external factors on the state of the device, thereby determining the probability of the device leaving the ground, so as to accurately determine whether the device is in the state of leaving the ground. In addition, the scheme provided by the embodiment of the present application detects the state of the device through the state sensor. For devices with built-in state sensors, this scheme does not require additional detection modules, which can help reduce detection costs.

[0032] The solution provided in the embodiments of the present application can be applied to a variety of devices, such as a robot with two wheels, three wheels, etc. that moves based on wheels, or a robot with multiple legs, etc.

[0033] Next, the present solution is further described with reference to an example. In the present embodiment, a two-wheeled robot is taken as an example, and the central axes of the two wheels of the robot are on the same straight line. Figure 1b A schematic diagram of the robot's state detection logic is shown.

[0034] Among them, the robot's state sensor includes an IMU, which is used to detect the actual state of the robot and output IMU data. The IMU data is calculated through a state fusion algorithm to obtain a state quaternion, and then the pitch angle parameter pitch, yaw angle parameter yaw, and roll angle parameter roll that characterize the device state are calculated.

[0035] The linear speed closed-loop controller determines the first linear speed instruction according to the target linear speed and the encoder linear speed of the robot and transmits it to the pitch angle closed-loop controller. The yaw angle can be input into the yaw angle closed-loop controller, and the yaw angle closed-loop controller outputs the control instruction corresponding to the yaw angle according to the target angular speed to control the angular speed of the robot. The pitch angle can be input into the pitch angle closed-loop controller, and the instructions output by the pitch angle closed-loop controller and the linear speed closed-loop controller jointly control the linear speed of the robot.

[0036] In the embodiment of the present application, the robot can detect the linear speed by detecting the rotation speed of the left and right wheels. Specifically, the encoder speed v_encoder_left of the robot's left wheel and the encoder speed v_encoder_right of the right wheel are detected respectively, and then the encoder linear speed v_robot=(v_encoder_left+v_encoder_right) / 2 of the robot can be determined by combining the speeds of the two wheels. And the encoder angular speed w_robot=(v_encoder_left-v_encoder_right) / L of the robot can be determined by combining the speeds of the two wheels, where L is the distance between the left and right wheels.

[0037] For a two-wheeled robot, the closed-loop control in the embodiment of the present application is mainly divided into two parts. The first part is the closed-loop control of the pitch angle, which is mainly used to control the linear speed of the robot's forward and backward movement. The second part is the closed-loop control of the rotation angle yaw (also called the yaw angle), which controls the robot's orientation.

[0038] In the closed-loop control of linear speed, the control input can specifically be the target linear speed and the current linear speed v_robot. After being controlled by the linear speed closed-loop controller, the target value of the pitch angle is obtained, and then, it is input into the pitch angle closed-loop controller together with the detected current pitch angle pitch, thereby realizing the closed-loop control of the pitch angle of the mobile robot.

[0039] In the closed-loop control of angular velocity, the control input can specifically be the target angle and the current yaw angle yaw. After passing through the yaw angle closed-loop controller, the motor torque signal is output, thereby realizing the yaw angle closed-loop control of the mobile robot.

[0040] Among them, any closed-loop controller can specifically perform calculations through control algorithms such as PID (Proportion Integral Differential), and can be used to achieve control of multiple loops including position, speed, force, etc.

[0041] Based on the solution provided in the above embodiment, optionally, the state parameter includes at least one of the following types of parameters: Linear velocity parameters, pitch angle parameters, yaw angle parameters, and roll angle parameters.

[0042] In the embodiment of the present application, the yaw angle yaw is used to control the angular orientation of the robot on the plane. Since the pitch angle of a two-wheeled robot changes when it moves forward and backward, the pitch angle pitch is used to control the linear speed of the robot on the plane. In practical applications, appropriate parameters can be selected for state detection based on the actual structure and motion characteristics of the robot. For example, for a three-wheeled robot, the pitch angle often does not change during its forward and backward movement, so other parameters other than the pitch angle can be used for state detection for the linear speed. This solution starts from the control of the pitch angle and azimuth angle of the robot, and on this basis fully explores the control change rules caused by various picking up actions, which is conducive to the effective realization of picking up detection through multiple state combination judgments.

[0043] Based on the solution provided in the above embodiment, optionally, Figure 2 As shown, in the above step S13, determining the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter includes: S21: Determine the degree of difference between the first state parameter and the second state parameter.

[0044] In this step, the first state parameter and the second state parameter are compared, and the degree of difference can be reflected in various forms such as difference value, percentage, difference level, etc.

[0045] In the example of the present application, it is assumed that the state parameters include a pitch angle parameter, a yaw angle parameter and a roll angle parameter. In this step, the difference between these three angle parameters is compared respectively, and the difference between these three angles is used to determine the difference between the first state parameter and the second state parameter.

[0046] S22: If the difference between the first state parameter and the second state parameter satisfies a preset timing condition, start timing, and if the difference between the first state parameter and the second state parameter does not satisfy the preset timing condition during the timing process, reset the timing time.

[0047] The preset timing conditions may be preset according to actual needs. For example, the preset timing conditions may include that the difference degree is greater than the preset difference degree, or the difference degree of at least one angle parameter is greater than the preset angle parameter difference degree, or the number of angle parameters with differences is greater than the preset number, etc.

[0048] For ease of explanation, it is assumed in the examples of the present application that the preset instant condition is that the degree of difference of at least one angle parameter is greater than the preset degree of difference of the angle parameter.

[0049] When the difference degree meets the preset timing condition, the timing is started, which can be realized by the built-in timer. During the timing process, the timing continues as long as the timing reset is not triggered. If the difference degree no longer meets the preset timing condition during the timing process, the timing time is reset. The timing is paused until the difference degree meets the preset timing condition again and then the timing is started.

[0050] In practical applications, it is possible to periodically determine whether the degree of difference meets the preset timing conditions. For example, in the first time period, the difference degree of the pitch angle parameter is greater than the preset pitch angle parameter difference degree, and the timing is started. In the second time period, the difference degree of the pitch angle parameter is less than the preset pitch angle parameter difference degree, but the difference degree of the yaw angle parameter is greater than the preset yaw angle parameter difference degree, then the timing continues. In the third time period, if the difference degree of any angle parameter is less than the corresponding angle parameter difference degree, the timing time length is reset, and the timing is paused until the difference degree meets the preset timing conditions again and then the timing is started again.

[0051] S23: Determine the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter and the length of the timing.

[0052] In this step, the probability of the device leaving the ground is determined based on the above-mentioned difference degree and the length of time for timing. Among them, the difference degree can indicate the difference between the state of the device based on the control instruction and the state of the device detected, and can indicate the possibility of the device being off the ground from the dimension of state difference. The length of time for timing indicates the length of time that the actual state of the device is inconsistent with the theoretical state. The longer the time, the higher the probability that the device is off the ground. Therefore, the length of time for timing can indicate the possibility of the device being off the ground from the dimension of time. In this step, the above-mentioned difference degree and time length are combined to comprehensively determine the probability of the device leaving the ground from the two dimensions of state difference and time, which can effectively improve the accuracy of the detection of the probability of leaving the ground.

[0053] Based on the solution provided in the above embodiment, optionally, Figure 3 As shown, in the above step S21, determining the difference between the first state parameter and the second state parameter includes: S31: If the second parameter value in the second state parameter is greater than the corresponding preset error value, determine the parameter difference between the first parameter value and the second parameter value in the first state parameter, the first parameter value and the second parameter value belong to the same type of parameters, and the preset error value corresponding to the parameter difference is the preset error value corresponding to the type of parameters to which the parameter difference belongs.

[0054] In actual applications, the status information obtained by the detection modules such as sensors from detecting the device may contain errors. The errors may be caused by various reasons such as uneven supporting surface and slight collision during the movement of the device.

[0055] In this step, the preset error value is compared with the second parameter value in the second state parameter actually detected. If the second parameter value is greater than the corresponding preset error value, the second parameter value and the first parameter value of the same type of parameter are further used to determine the parameter difference. If the parameter difference is less than or equal to the preset error value, it may be caused by an error, and the parameter difference is not used to further determine the parameter difference.

[0056] The preset error values ​​corresponding to different types of parameters can be preset according to actual needs. In practical applications, the preset error values ​​corresponding to various types of parameters can be set according to the structure and movement mode of the device, so that the preset error values ​​can be used to accurately determine whether the actually detected second parameter value is caused by an error.

[0057] In the example of the present application, the difference between the first state parameter and the second state parameter is expressed in the form of parameter difference. In this step, it is possible to first determine which parameters of the same type are in the first state parameter and the second state parameter, and then compare the second parameter values ​​in the second state parameter with the preset error value of the common type parameter to eliminate the second parameter value caused by the error. The second parameter value obtained after screening is further compared with the first parameter value of the type parameter to determine the parameter difference.

[0058] Through the solution provided in the embodiment of the present application, the numerical size of the second parameter value of the type is determined based on the error value corresponding to the type parameter, which can avoid the negative impact of small changes in state information caused by detection errors on the probability of lift-off, and can effectively improve the accuracy of determining the probability of lift-off.

[0059] Based on the solution provided in the above embodiment, optionally, Figure 4 As shown, in the above step S23, determining the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter and the length of the timing time includes: S41: If the parameter difference is greater than the corresponding preset judgment threshold, the corresponding parameter judgment probability is determined based on the parameter difference and the corresponding preset judgment threshold, wherein the preset judgment threshold corresponding to the parameter difference is the preset judgment threshold corresponding to the type parameter to which the parameter difference belongs, and the preset judgment threshold is greater than the preset error value corresponding to the type parameter to which it belongs.

[0060] In this step, the parameter difference is compared with its numerical value using the preset judgment threshold corresponding to the type parameter to which the parameter difference belongs. If the parameter difference is greater than the corresponding preset judgment threshold, it indicates that there is a significant difference between the control theoretical value and the actual detection value of the type parameter, and the difference is often caused by external factors. Then the corresponding parameter judgment probability is determined for the type parameter.

[0061] Among them, the parameter determination probability corresponds to the type parameter. The parameter determination probability indicates the probability of the device leaving the ground represented by the parameter difference in the evaluation dimension of the type parameter. In practical applications, the parameter determination probability can be determined by the parameter difference of the type parameter and the theoretical interval of the type parameter. For example, assuming that the theoretical interval of the robot in the evaluation dimension of roll angle is [0°, 50°], then the closer the parameter difference of the roll angle is to the upper limit of the theoretical interval, the greater the probability of the robot leaving the ground, that is, the closer the parameter difference of the roll angle is to 50°, the greater the parameter determination probability of the roll angle.

[0062] S42: Determine the probability of the device leaving the ground according to the parameter judgment probability corresponding to the parameter difference and the length of the timing.

[0063] In this step, the probability of the device leaving the ground is determined according to the parameter determination probability determined in the above step and the time length of the timing. If there are multiple parameter determination probabilities, the multiple parameter determination probabilities can be weighted and summed to determine the probability of the device leaving the ground.

[0064] Optionally, weights corresponding to the type parameters may be preset to implement weighted summation, wherein the weights corresponding to different type parameters may be the same or different, and the weights may be set according to factors such as the structure or movement mode of the device.

[0065] Below, this scheme is further explained with reference to examples.

[0066] In one example, it is assumed that the same type of parameters included in the first state parameter and the second state parameter include a linear speed parameter, and the preset judgment threshold corresponding to the linear speed parameter is represented as v_thread. When the robot is picked up, the change in the pitch angle of the robot can be reflected in the state information. For the changed pitch angle, the pitch angle closed-loop controller will control the motor speed according to the change in the currently detected pitch angle, and try its best to restore the pitch angle to the target state in an attempt to restore itself to a normal state, which will cause a large difference between the linear speed v_goal indicated by the control instruction and the actually detected linear speed v_robot. In addition, in order to avoid false triggering caused by wheel jamming, it is necessary to pre-determine that the currently detected linear speed is greater than the preset error value v_err_max corresponding to the linear speed parameter.

[0067] In addition, if the robot has three or more wheels, the robot often does not cause a pitch angle change due to forward and backward movement. The linear velocity error of the mobile robot can be replaced by the error of the state angle pitch.

[0068] In one example, assuming that the same type of parameters included in the first state parameter and the second state parameter include a rotation angle parameter (also called a yaw angle parameter), the preset determination threshold corresponding to the rotation angle parameter is represented as w_thread. The rotation angular velocity (i.e., the first parameter value) in the first state parameter is represented as w_robot, and the rotation angular velocity (i.e., the second parameter value) in the second state parameter is represented as w_sensor.

[0069] Among them, the second parameter value can be specifically determined according to the angular velocity data of the IMU sensor around the z direction. When the angle is in closed-loop control, if the robot wheels are off the ground and the yaw angle changes, an angular velocity w_robot opposite to the actual angular velocity will be generated in the control logic to try to offset the change. Specifically, the wheel speed w_robot of the robot can be measured by the speed sensor encoder, and the wheel speed, that is, the control logic tries to offset the change in the yaw angle of the robot body. If the robot is on the support surface, the yaw angle of the robot body can be effectively adjusted by controlling the wheel speed. However, if the robot is off the ground, the wheels of the robot are not in contact with the support surface, which makes the robot's own rotational angular velocity w_sensor and the robot wheel speed w_robot have a significant difference. Then, in this example, the parameter difference between the first parameter value and the second parameter value can be used to effectively determine whether the robot is picked up.

[0070] It should be noted that, in the solution provided in the embodiment of the present application, the first state parameter can be directly determined by the control instruction, for example, the control instruction is parsed to obtain the first state parameter indicated by the control instruction. Alternatively, the first state parameter can also be a parameter obtained by measuring the controlled component, for example, in this example, the rotational angular velocity of the robot's wheel is measured by a speed sensor encoder, so that the measured target action reflects the first state parameter indicated by the control logic.

[0071] In one example, it is assumed that the same type of parameters included in the first state parameter and the second state parameter include a roll angle parameter. In actual applications, the roll angle of the robot on the horizontal support surface is close to 0°. When the robot is picked up, it may tilt, and then a roll angle parameter of a certain angle can be detected. Therefore, the parameter difference of the roll angle parameter can be used to determine whether the robot is picked up.

[0072] It should be understood that the preset determination threshold corresponding to the type parameter can be flexibly set according to actual needs, and the preset determination thresholds corresponding to different type parameters can be the same or different.

[0073] Through the scheme provided by the embodiment of the present application, a numerical comparison is performed based on a preset judgment threshold and a parameter difference. When the parameter difference is greater than the corresponding preset judgment threshold, the parameter difference is used to determine the parameter judgment probability, and then the probability of the device leaving the ground is determined by combining the parameter judgment probability and the above-mentioned time length. In this scheme, the parameter difference is preliminarily judged by the preset judgment threshold, and it can be preliminarily determined whether the parameter difference indicates that the device is likely to be off the ground. Then, the probability of the device leaving the ground is comprehensively determined using at least one parameter judgment probability after screening, avoiding the negative impact of the parameter difference with too small a value on the judgment of the probability of leaving the ground, thereby improving the accuracy of the probability of leaving the ground.

[0074] Based on the solution provided in the above embodiment, optionally, the control instruction is used to periodically control the device to perform a target action within a target time period according to a preset duration.

[0075] The preset duration can be flexibly set according to actual needs. In the embodiment of the present application, the device is periodically controlled based on the preset duration, that is, a new control instruction is periodically issued at intervals of the preset duration to control the device to perform the target action.

[0076] Among them, Figure 5 As shown, in the above step S22, if the difference between the first state parameter and the second state parameter meets the preset timing condition, then starting the timing includes: S51: If there is a parameter difference value greater than the corresponding preset error value, start timing from the moment corresponding to the parameter difference value.

[0077] In the embodiment of the present application, if at least one parameter difference is greater than the corresponding preset error value, it indicates that at least one parameter difference indicates that the device may be off the ground. In this step, the timing starts from the moment when the parameter difference is greater than the corresponding preset error value, and the timing time length can represent the probability that the device is off the ground in the time dimension. That is, the longer the timing time length, the greater the probability that the device is off the ground.

[0078] Wherein, in the above step S22, if the difference between the first state parameter and the second state parameter during the timing process does not meet the preset timing condition, resetting the timing time length includes: S52: If there is no parameter difference greater than the corresponding preset error value during the timing process, the timing time length is reset.

[0079] During the timing process, if the difference of each parameter at a certain moment is not greater than the corresponding preset error value, it means that the dimensions of each type of parameter indicate that the device is most likely on a horizontal support surface, that is, it is not off the ground. At this moment, the timing time is reset. The timing is paused until there is a parameter difference greater than the corresponding preset error value, and then the timing is restarted based on the reset time length.

[0080] Among them, in the above step S42, determining the probability of the device leaving the ground according to the parameter determination probability corresponding to the parameter difference and the time length of the timing includes: S53: Determine the probability of the device leaving the ground by adding the product of the parameter determination probability and the preset time length and the time length of the timing.

[0081] In this step, the probability of the device leaving the ground is determined comprehensively based on the parameter determination probability, the preset duration, and the time length of the timing. Assuming that the preset duration is represented as cycle, the time length of the timing is represented as t, and the parameter determination probability is represented as vt, the probability of the device leaving the ground can be represented as t+vt*cycle.

[0082] Through the solution provided in the embodiment of the present application, the probability of the device leaving the ground is comprehensively determined based on the control cycle of the device, the parameter determination probability and the time length of the timing. Among them, based on the preset time length corresponding to the control cycle, the parameter determination probability can be integrated into the time dimension and added with the time length of the timing, reflecting the probability of the device as a whole being off the ground from the time dimension, which can effectively improve the accuracy of the determined probability of leaving the ground.

[0083] Based on the solution provided in the above embodiment, optionally, the preset judgment threshold is smaller than the preset parameter maximum value corresponding to the type parameter, and the preset parameter maximum value is the sum of the preset error value corresponding to the type parameter and the maximum value of the equipment performance parameter.

[0084] In the embodiment of the present application, the preset judgment threshold is expressed as v_thread, and the preset parameter maximum value is expressed as v_max+v_err_max (i.e., the sum of the maximum value v_max of the device performance parameter and the preset error value v_err_max). The relationship between the preset judgment threshold, the preset error value and the preset parameter maximum value can be expressed as: v_err_max <v_thread<v_max+v_err_max。

[0085] Among them, the maximum value of the equipment performance parameter refers to the maximum value that can be achieved based on the equipment's own performance in the dimension of the type parameter, and the preset error value refers to the error value caused by hardware or software reasons. Based on this, for the type parameter, the detected value should not be greater than the sum of the maximum value of the above-mentioned equipment performance parameter and the preset error value. In the embodiment of the present application, the preset judgment threshold is set to a value that is less than the maximum value of the preset parameter and greater than the preset error value, so that the determined preset judgment threshold can be reasonably and effectively used to judge the size of the parameter difference of the type parameter to which it belongs, thereby determining the probability that the device is in an off-the-ground state under the dimension of the parameter difference of the type parameter to which it belongs.

[0086] Among them, Figure 6 As shown, in the above step S41, if the parameter difference is greater than the corresponding preset determination threshold, the corresponding parameter determination probability is determined according to the parameter difference and the corresponding preset determination threshold, including: S61: Determine the parameter determination probability of the corresponding type of parameter by multiplying the first ratio of the parameter difference to the preset parameter maximum value by the second ratio of the preset determination threshold to the preset parameter maximum value.

[0087] In this step, the parameter determination probability of the corresponding type of parameter is determined comprehensively based on the parameter difference, the preset parameter maximum value, and the preset determination threshold value, which is explained below with reference to an example.

[0088] In one example, for the type of parameter of the line speed parameter, the maximum value of the device performance parameter is expressed as v_max, the preset error value is expressed as v_err_max, and the preset judgment threshold is expressed as v_thread. The above parameter size relationship satisfies: v_err_max <v_thread<v_max+v_err_max。

[0089] In this example, it is assumed that the detected linear velocity parameter value v_robot is greater than the preset error value, that is, v_robot>v_err_max is satisfied. Moreover, the parameter difference of the linear velocity parameter is greater than the preset judgment threshold v_thread, that is, abs(abs(v_robot)-abs(v_goal))>v_thread is satisfied, where abs is the absolute value calculation.

[0090] In this case, the parameter determination probability vt1 of the linear velocity parameter determined by this step is: vt1=(abs(abs(v_robot)-abs(v_goal))) / (v_max+v_err_max)×(v_thread) / (v_max+v_err_max) In one example, for a parameter type such as angular velocity (e.g., the yaw angle parameter yaw), the maximum value of the device performance parameter is denoted as w_max, the preset error value is denoted as w_err_max, and the preset determination threshold is denoted as w_thread. Then, the following parameter magnitude relationship holds: w_err_max < w_thread < w_max + w_err_max.

[0091] In this example, it is assumed that the detected angular velocity parameter value w_robot is greater than the preset error value, that is, w_robot > w_err_max. And, the parameter difference of the angular velocity parameter is greater than the preset determination threshold w_thread, that is, it satisfies: abs(abs(w_robot) - abs(w_sensor)) > w_thread, where abs is the absolute value calculation.

[0092] In this case, the parameter determination probability vt2 of the angular velocity parameter is determined through this step as: vt2 = (abs(abs(w_robot) - abs(w_sensor))) / (w_max + w_err_max) × (w_thread) / (w_max + w_err_max) In one example, for a parameter type of roll angle parameter, since the roll angle parameter involves rolling in different directions, the roll angle range in which the robot operates normally in various environments can be determined first, denoted as (roll_min, roll_max). Assume that 50° is the angle value of the maximum roll angle in the robot's rollover state. Further, based on this roll angle range, the value of the preset determination threshold roll_thread of the roll parameter satisfies: max(abs(roll_min), abs(roll_max)) < roll_thread < 50°, where max() is to take the maximum value, that is, to take the item with the largest value from the absolute value of roll_min and the absolute value of roll_max.

[0093] For a parameter type of roll angle, the parameter difference can be the difference between the actually detected roll angle and 0°, that is, the detected roll angle value. When the parameter difference of the roll angle (i.e., the detected roll angle value) is greater than the preset determination threshold roll_thread, that is, it satisfies abs(roll) > roll_thread, the parameter determination probability vt3 of the angular velocity parameter is determined through this step as: vt3 = (abs(roll_robot)) / 50 × (roll_thread) / 50 Through the solution provided in the embodiment of the present application, the parameter difference, the preset parameter maximum value, and the preset judgment threshold can be integrated to comprehensively determine the parameter judgment probability, thereby expressing the probability of the equipment being off the ground in the parameter dimension of the corresponding category in numerical form.

[0094] Based on the solution provided in the above embodiment, optionally, Figure 7 As shown, in the above step S53, the product of the parameter determination probability and the preset time length and the sum of the time length of the timing are determined as the probability of the device leaving the ground, including: S71: If there are multiple parameter differences to be determined, the product of the parameter determination probabilities corresponding to the multiple parameter differences to be determined and the preset time length and the sum of the timing time length are determined as the probability of the device leaving the ground, wherein any parameter difference to be determined is greater than the corresponding preset determination threshold.

[0095] In actual applications, there may be multiple types of parameters that are common to the first state parameter and the second state parameter. In this example, the probability of the device leaving the ground is comprehensively determined based on the differences between the multiple parameters.

[0096] In this step, the type parameters common to the first state parameter and the second state parameter can be determined first, and then it can be determined whether the second parameter values ​​of each common type parameter are greater than the corresponding preset error value. For the second parameter value greater than the preset error value, it is further determined whether the parameter difference is greater than the corresponding preset determination threshold, and the parameter difference greater than the preset determination threshold is recorded as the parameter difference to be determined.

[0097] In the case where there are multiple parameter differences to be determined, the parameter determination probabilities corresponding to the parameter differences to be determined are determined respectively. Then, the products of the parameter determination probabilities and the preset time lengths are calculated respectively, so as to convert the parameter determination probabilities into probabilities in the time dimension. Finally, the product of the parameter determination probabilities corresponding to the parameter differences to be determined and the preset time lengths and the sum of the time lengths are determined as the probability of the device leaving the ground.

[0098] For example, assuming that there are three parameter differences to be determined, the corresponding three parameter determination probabilities are represented as vt1, vt2 and vt3, the timing time is represented as t, and the preset time is represented as cycle. Then in this step, the probability of taking off is determined as: t+(vt1+vt2+vt3)*cycle.

[0099] In this example, the length of the timing is related to the differences of the three parameters to be determined. Assuming that condition 1 is that the parameter difference corresponding to vt1 is greater than the corresponding preset determination threshold, condition 2 is that the parameter difference corresponding to vt2 is greater than the corresponding preset determination threshold, and condition 3 is that the parameter difference corresponding to vt3 is greater than the corresponding preset determination threshold, then the flow chart of the device status detection method is as follows: Figure 8 shown.

[0100] First, the device starts the pick-up detection function, and starts timing if at least one of conditions 1, 2, and 3 is met. During the timing process, if none of the above conditions 1, 2, and 3 are met, the timing is reset.

[0101] During the timing process, the above-mentioned vt1, vt2 and vt3 are calculated in real time, and the above-mentioned vt1, vt2 and vt3 are integrated based on the timing time length t to represent the probability of the device leaving the ground from the time dimension. In this example, the probability of leaving the ground is represented by timing t, and the calculation method of timing t is timing t=t+(vt1+vt2+vt3)*cycle.

[0102] Finally, if the lift-off probability satisfies the lift-off determination condition, it is determined that the device is in the lift-off state. In this step, the lift-off determination condition is specifically that the timer t is greater than or equal to the lift-off determination threshold, that is, the lift-off detection is triggered when the value of the timer t is greater than or equal to the lift-off determination threshold, that is, it is determined that the device is in the lift-off state. If the timer t is less than the lift-off determination threshold, the lift-off detection judgment step can be repeated to continue to perform the device status detection.

[0103] Through the solution provided in the embodiment of the present application, the difference between the device's own control state based on the control instruction and the actual state can be expressed through multiple types of parameters, thereby reflecting the impact of external factors on the device state, thereby determining the device's lift-off probability, and integrating the parameter differences of multiple types of parameters into the time dimension, thereby adding them to the timing time length, thereby accurately expressing the probability of the device being off the ground in numerical form in the time dimension, thereby improving the effectiveness of the lift-off judgment.

[0104] In order to solve the problems existing in the related art, the embodiment of the present application further provides a device state detection device 90, such as Fig. 9 As shown, including: An acquisition module 91 is configured to acquire control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period; A first determining module 92 determines a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information; A second determination module 93 determines a probability of the device leaving the ground according to a difference between the first state parameter and the second state parameter; The determination module 94 determines that the device is in a lift-off state if the lift-off probability satisfies a lift-off determination condition.

[0105] Through the device provided by the embodiment of the present application, first, the control instruction and state information of the device are obtained, the control instruction is used to control the device to perform the target action within the target time period, and the state information is obtained by the state sensor monitoring the device within the target time period; then, the first state parameter corresponding to the device performing the target action and the second state parameter corresponding to the state information are determined; then, the probability of the device leaving the ground is determined according to the degree of difference between the first state parameter and the second state parameter; if the probability of leaving the ground meets the condition for judging the device leaving the ground, it is determined that the device is in the state of leaving the ground. Among them, the first state parameter can represent the state of the device under the control instruction, the second state parameter can represent the state of the device under the monitoring of the sensor, and the degree of difference between the first state parameter and the second state parameter can represent the difference between the device's own control state based on the control instruction and the actual state, thereby reflecting the influence of external factors on the state of the device, thereby determining the probability of the device leaving the ground, so as to accurately determine whether the device is in the state of leaving the ground.

[0106] Among them, the above modules in the device provided by the embodiment of the present application can also implement the method steps provided by the above method embodiment. Alternatively, the device provided by the embodiment of the present application can also include other modules in addition to the above modules to implement the method steps provided by the above method embodiment. And the device provided by the embodiment of the present application can achieve the technical effects that can be achieved by the above method embodiment.

[0107] Preferably, an embodiment of the present application also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, each process of the above-mentioned device status detection method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0108] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned device status detection method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0109] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. The computer program can be operated to enable a computer to execute part or all of the steps of the above-mentioned device status detection method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0112] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0119] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A device status detection method, characterized in that: include: Acquire control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period; Determine a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information; Determining a probability of the device leaving the ground according to a degree of difference between the first state parameter and the second state parameter; If the lift-off probability satisfies a lift-off determination condition, it is determined that the device is in a lift-off state.

2. The method according to claim 1, characterized in that Determining the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter includes: determining a degree of difference between the first state parameter and the second state parameter; If the difference between the first state parameter and the second state parameter satisfies a preset timing condition, then start timing, and if the difference between the first state parameter and the second state parameter does not satisfy the preset timing condition during the timing process, then reset the timing time length; The probability of the device leaving the ground is determined according to the difference between the first state parameter and the second state parameter and the length of the timing.

3. The method according to claim 2, characterized in that Determining a degree of difference between the first state parameter and the second state parameter includes: If the second parameter value in the second state parameter is greater than the corresponding preset error value, the parameter difference between the first parameter value and the second parameter value in the first state parameter is determined, the first parameter value and the second parameter value belong to the same type of parameters, and the preset error value corresponding to the parameter difference is the preset error value corresponding to the type of parameters to which the parameter difference belongs.

4. The method according to claim 3, characterized in that Determining the probability of the device leaving the ground according to the difference between the first state parameter and the second state parameter and the length of time of timing includes: If the parameter difference is greater than the corresponding preset judgment threshold, the corresponding parameter judgment probability is determined according to the parameter difference and the corresponding preset judgment threshold, wherein the preset judgment threshold corresponding to the parameter difference is the preset judgment threshold corresponding to the type parameter to which the parameter difference belongs, and the preset judgment threshold is greater than the preset error value corresponding to the type parameter to which it belongs; The probability of the device leaving the ground is determined according to the parameter determination probability corresponding to the parameter difference and the length of the timing.

5. The method according to claim 4, characterized in that The control instruction is used to periodically control the device to perform a target action within a target period according to a preset duration; If the difference between the first state parameter and the second state parameter satisfies a preset timing condition, starting the timing includes: If there is a parameter difference greater than the corresponding preset error value, then the timing starts from the moment corresponding to the parameter difference; If the difference between the first state parameter and the second state parameter does not satisfy a preset timing condition during the timing process, resetting the timing time length includes: If there is no parameter difference greater than the corresponding preset error value during the timing process, the timing time length is reset; Wherein, determining the probability of the device leaving the ground according to the parameter determination probability corresponding to the parameter difference and the length of the timing time includes: The probability of the device leaving the ground is determined by adding the product of the parameter determination probability and the preset time length and the time length of the timing.

6. The method according to claim 5, characterized in that The preset determination threshold is less than the preset parameter maximum value corresponding to the type parameter, and the preset parameter maximum value is the sum of the preset error value corresponding to the type parameter and the maximum value of the equipment performance parameter; Wherein, if the parameter difference is greater than the corresponding preset determination threshold, determining the corresponding parameter determination probability according to the parameter difference and the corresponding preset determination threshold, including: The product of a first ratio of the parameter difference value to the preset parameter maximum value and a second ratio of the preset determination threshold value to the preset parameter maximum value is determined as the parameter determination probability of the corresponding type of parameter.

7. The method according to claim 6, characterized in that Determining the probability of the device leaving the ground by adding the product of the parameter determination probability and the preset time length and the time length of the timing, comprises: If there are multiple parameter difference values ​​to be determined, the product of the parameter determination probabilities corresponding to the multiple parameter difference values ​​to be determined and the preset time length and the sum of the timing time length are determined as the probability of the device leaving the ground, wherein any parameter difference value to be determined is greater than the corresponding preset determination threshold.

8. The method according to any one of claims 1 to 7, characterized in that The state parameter includes at least one of the following types of parameters: Linear velocity parameters, pitch angle parameters, yaw angle parameters, and roll angle parameters.

9. A device status detection device, characterized in that: include: An acquisition module, which acquires control instructions and status information of a device, wherein the control instructions are used to control the device to perform a target action within a target period, and the status information is obtained by a status sensor monitoring the device within the target period; A first determining module determines a first state parameter corresponding to the device executing the target action and a second state parameter corresponding to the state information; a second determination module, determining a probability of the device leaving the ground according to a difference between the first state parameter and the second state parameter; The determination module determines that the device is in a lift-off state if the lift-off probability satisfies a lift-off determination condition.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 8 when executed by the processor.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, characterized in that The computer program product comprises a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to execute part or all of the steps of the method according to any one of claims 1 to 8.

Images