Boundary detection method, device, equipment and storage medium

Abstract

The present application discloses a boundary detection method, apparatus, device, and storage medium, the method comprising: detecting a boundary line signal at every preset detection period to obtain a first detection signal; when the first detection signal satisfies a preset signal condition, adding a first target peak-valley voltage in a sampled peak-valley voltage group corresponding to the first detection signal to a target feature data group; when the first detection signal does not satisfy the preset signal condition, determining a first detection time period based on the current time and a preset detection period; detecting the boundary line signal within the first detection time period to obtain a second detection signal; when the absolute value of the difference between the second target peak-valley voltage of the second detection signal and the reference voltage is greater than a first detection threshold, adding the second target peak-valley voltage to the target feature data group; and obtaining a boundary detection result based on the target feature data group. Utilizing the solution of the present application, the detection rate of the boundary range and the accuracy of the detection results can be improved, thereby increasing the working area of ​​the device.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to a boundary detection method, apparatus, device and storage medium. Background Art

[0002] With the development of the economy, fully automatic lawn mower robots, utilizing modern electronic technology and intelligent control, have emerged, and the market size of lawn mower robots is rapidly increasing. The mainstream random lawn mower robots on the market now have functions such as automatic walking, automatic mowing, and electronic boundary. The area they automatically mow is affected by the area of ​​the electronic boundary.

[0003] However, using traditional boundary detection methods, when the lawn mower robot detects a strong boundary signal near the electronic boundary line, it can more accurately identify the signal status and determine whether the lawn mower robot is within the boundary. When the lawn mower robot is far away from the electronic boundary line and the detected boundary signal is weak, it cannot well identify the signal status and determine the position of the lawn mower robot. Therefore, for the sake of accuracy of boundary detection, the area of ​​the electronic boundary is usually limited, thereby limiting the mowing area of ​​the lawn mower robot. Therefore, it is necessary to provide a more efficient boundary detection method. Summary of the Invention

[0004] This application provides a boundary detection method, apparatus, device, and storage medium that can switch between different detection modes based on the current signal strength at different locations of an electronic boundary, thereby improving the detection rate of the boundary range and the accuracy of the detection results. This allows the target walking device to effectively detect the boundary line signal even when it is far away from the boundary line, maintain normal working conditions, and thus increase the working area of ​​the autonomous walking device. The technical solution of this application is as follows:

[0005] In one aspect, a boundary detection method is provided, the method comprising:

[0006] A sensor based on a target magnification of the target autonomous vehicle detects a boundary line signal at every preset detection period to obtain a first detection signal;

[0007] When the first detection signal meets a preset signal condition, adding a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to a target characteristic data group;

[0008] When the first detection signal does not meet the preset signal condition, determining a first detection time period based on the current time and the preset detection period;

[0009] Based on the sensor of the target magnification, the boundary line signal is detected within the first detection time period to obtain a second detection signal;

[0010] When the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, adding the second target peak-to-valley voltage to the target feature data set;

[0011] Based on the comparison result of the target feature data group and the reference voltage, a boundary detection result of the target autonomous driving device is obtained.

[0012] Preferably, after adding the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to the target characteristic data group, the method further comprises:

[0013] When the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than a second detection threshold, determining a second detection time period based on the sampling time of the target characteristic data with the latest sampling time in the target characteristic data group and the preset detection period;

[0014] Based on the sensor of the target magnification, the boundary line signal is detected within the second detection time period to obtain a third detection signal;

[0015] When the third detection signal meets the preset signal condition, the third target peak-valley voltage in the sampled peak-valley voltage group corresponding to the third detection signal is added to the target characteristic data group.

[0016] Preferably, after adding the third target peak-to-valley voltage in the sampled peak-to-valley voltage group corresponding to the third detection signal to the target characteristic data group, the method further comprises:

[0017] When the absolute value of the difference between the third target peak-to-valley voltage and the reference voltage is greater than a third detection threshold, the process jumps to executing the sensor based on the target magnification of the target autonomous driving device, detecting the boundary line signal every preset detection period to obtain a first detection signal;

[0018] And / or, when the third detection signal does not meet the preset signal condition, jump to executing the step of determining the first detection time period based on the current time and the preset detection cycle.

[0019] Preferably, after adding the second target peak-to-valley voltage to the target characteristic data set, the method further comprises:

[0020] When the second detection signal satisfies the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than a third detection threshold, the process jumps to executing the sensor based on the target magnification of the target autonomous driving device, detecting the boundary line signal every preset detection period to obtain a first detection signal;

[0021] And / or, when the second detection signal satisfies the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than the second detection threshold, jump to executing the step of determining the second detection time period based on the sampling time of the target feature data with the latest sampling time in the target feature data group and the preset detection cycle.

[0022] Before adding the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to the target characteristic data group, the method further includes:

[0023] Sampling the voltage waveform of the first detection signal to obtain a plurality of sampled peak-valley voltages;

[0024] Based on the sampling time sequence of the plurality of sampled peak-valley voltages, traversing three consecutive sampled peak-valley voltages among the plurality of sampled peak-valley voltages;

[0025] Calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage;

[0026] When the sum is greater than a preset sum threshold, the three consecutive sampled peak-valley voltages currently traversed are used as the sampled peak-valley voltage group;

[0027] The second sampled peak-valley voltage in the sampled peak-valley voltage group is used as the first target peak-valley voltage.

[0028] Preferably, after calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage, the method further includes:

[0029] If the sums of any three consecutive sampled peak-valley voltages among the multiple sampled peak-valley voltages during the traversal process are all less than the preset sum threshold, the three consecutive sampled peak-valley voltages with the largest corresponding sums are taken as the sampled peak-valley voltage group.

[0030] Preferably, before adding the second target peak-to-valley voltage to the target characteristic data set, the method further comprises:

[0031] Sampling the voltage waveform of the second detection signal to obtain a plurality of sampled peak-valley voltages of the second detection signal;

[0032] Among the plurality of sampled peak-valley voltages of the second detection signal, a sampled peak-valley voltage having a maximum absolute value of difference from the reference voltage is used as the second target peak-valley voltage.

[0033] Preferably, the preset signal condition includes:

[0034] The absolute value of the difference between each of the three consecutive sampled peak-valley voltages corresponding to the current detection signal and the reference voltage is greater than the first detection threshold and the sampling time interval between the target peak-valley voltage corresponding to the current detection signal and the target feature data with the latest sampling time in the target feature data group is within a preset error range.

[0035] Preferably, obtaining the boundary detection result of the target autonomous driving device based on the comparison result of the target feature data group and the reference voltage includes:

[0036] When the sampling time intervals between adjacent target number of target characteristic data in the target characteristic data group are within a preset error range, determining a target number of signal directions corresponding to the adjacent target number of target characteristic data based on a comparison result of the adjacent target number of target characteristic data with the reference voltage;

[0037] When the target number of signal directions are all within the preset boundary, the boundary detection result is that the target autonomous driving device is within the boundary range.

[0038] In another aspect, a boundary detection device is provided, comprising:

[0039] A first detection module is configured to detect a boundary line signal at predetermined detection intervals based on a sensor of a target magnification of the target autonomous vehicle to obtain a first detection signal;

[0040] a first target characteristic data group module, configured to add a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to a target characteristic data group when the first detection signal satisfies a preset signal condition;

[0041] a first detection time period determination module, configured to determine a first detection time period based on the current time and the preset detection period when the first detection signal does not meet the preset signal condition;

[0042] a second detection module, configured to detect the boundary line signal within the first detection time period based on the sensor of the target magnification to obtain a second detection signal;

[0043] a second target characteristic data group module, configured to add the second target peak-to-valley voltage of the second detection signal to the target characteristic data group when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than a first detection threshold;

[0044] The boundary detection result module is used to obtain the boundary detection result of the target autonomous driving device based on the comparison result of the target feature data group and the reference voltage.

[0045] On the other hand, an automatic walking device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the boundary detection method as described above.

[0046] On the other hand, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the boundary detection method as described above.

[0047] The boundary detection method, apparatus, device, and storage medium provided in this application have the following technical effects:

[0048] By utilizing the technical solution provided by the present application, on the one hand, utilizing the first detection mode, that is, a sensor based on the target magnification, the boundary line signal is detected every preset detection period to obtain a first detection signal. When the first detection signal meets the preset signal condition, the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal is added to the target characteristic data group, and based on the comparison result of the target characteristic data group and the reference voltage, the boundary detection result of the target automatic walking device is obtained, which can improve the accuracy of the boundary detection result when the signal strength is strong; on the other hand, when the first detection signal does not meet the preset signal condition, that is, the signal strength is weak, the first working mode is switched to the second detection mode, that is, the first detection signal is determined based on the current time and the preset detection period. Detection time period, then detect the boundary line signal within the first detection time period to obtain a second detection signal, when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, the second target peak-to-valley voltage is added to the target feature data group, and based on the comparison result of the target feature data group and the reference voltage, the boundary detection result of the target automatic walking device is obtained, which can improve the detection rate of the second target peak-to-valley voltage, thereby improving the detection rate of the boundary range, so that the target walking device can still effectively detect the boundary line signal when it is far away from the boundary line, maintain normal working state and thereby increase the working area of ​​the automatic walking device; on the other hand, different detection modes are switched based on the current signal strength to improve the flexibility of the boundary detection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 This is a flow chart of a boundary detection method provided in an embodiment of the present application;

[0051] Figure 2 1 is a flow chart of a method for determining a first target peak-to-valley voltage provided in an embodiment of the present application;

[0052] Figure 3 is a flow chart of a method for determining a second target peak-to-valley voltage provided in an embodiment of the present application;

[0053] Figure 4 This is a flow chart of obtaining a boundary detection result of a target autonomous vehicle based on a comparison result of a target feature data set and a reference voltage, provided by an embodiment of the present application;

[0054] Figure 5 This is a flow chart of the second and third detection modes provided in an embodiment of the present application;

[0055] Figure 6 This is a schematic diagram of a boundary detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0058] The following describes a boundary detection method provided by an embodiment of the present application. Figure 1A flow chart of a boundary detection method provided in an embodiment of the present application. It should be noted that this specification provides method operation steps as described in the embodiment or flow chart, but more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiment is only one way of executing the steps among many steps, and does not represent the only execution order. When the actual system or product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 1 As shown, the above method may include:

[0059] S101 , based on a sensor with a target magnification of a target autonomous vehicle, detects a boundary line signal at every preset detection period to obtain a first detection signal.

[0060] In the embodiment of this specification, the target autonomous walking device may be an intelligent robot device that can automatically walk and work within a preset working area. The target autonomous walking device may include but is not limited to a lawn mowing robot and a snow shoveling robot.

[0061] Specifically, the preset working area can be set based on the electronic boundary. In actual application, the target autonomous vehicle can travel within the boundary line of the electronic boundary, and a boundary line signal can be generated on the boundary line that can be detected by the target autonomous vehicle to identify the boundary line.

[0062] In an embodiment of the present specification, the above-mentioned boundary line signal can be a sine-like signal or a cosine-like signal, and the above-mentioned preset detection period can be a sending period of the boundary line signal. Specifically, the preset detection period can be set based on the sending period of the boundary line signal in actual applications. Taking the sending period of 17.2ms as an example, the preset detection period can be 17.2ms.

[0063] Specifically, the boundary line signal can be amplified by using a sensor with a target magnification, so as to obtain a corresponding detection signal. In practical applications, the target magnification can be a higher magnification. Optionally, the target magnification can include: 4700 times.

[0064] S103 : When the first detection signal meets a preset signal condition, a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal is added to the target characteristic data group.

[0065] In an embodiment of the present specification, the target feature data group can be used to determine whether the current target automatic walking device is within the boundary range, and each target feature data in the target feature data group can be used to determine the signal direction of the corresponding detection signal, and the signal direction can include a preset in-boundary direction and a preset out-of-boundary direction.

[0066] In an embodiment of the present specification, the preset signal condition may be a judgment condition for determining whether the current detection signal is a valid signal, wherein the valid signal may be a signal with high signal quality and capable of determining the boundary position, that is, when the first detection signal meets the preset signal condition, the first detection signal may be used to determine whether the current target automatic walking device is within the boundary range, wherein the first target peak-to-valley voltage may be used to determine whether the direction of the first detection signal is within or outside the boundary.

[0067] In the embodiment of this specification, after the target autonomous driving device starts working, the first detection mode is used by default to perform signal detection. Specifically, the first detection mode may include steps S101 to S103.

[0068] In a specific embodiment, when the intensity of the first detection signal obtained in the first detection mode is relatively strong, its waveform is a complete sine-cosine-like signal waveform. Therefore, a plurality of continuous sampled peak-valley voltages of the first detection signal are obtained through sampling processing, and the first target peak-valley voltage is determined based on a sampled peak-valley voltage group in the plurality of continuous sampled peak-valley voltages. Specifically, Figure 2 As shown, before adding the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to the target characteristic data group, the method may further include:

[0069] S201 , sampling the voltage waveform of the first detection signal to obtain a plurality of sampled peak-valley voltages.

[0070] Specifically, the voltage waveform of the first detection signal is sampled every preset sampling period within the current preset detection period to obtain multiple sampling peak-valley voltages. The multiple sampling peak-valley voltages can be multiple continuous sampling peak voltages and sampling valley voltages, wherein the sampling peak voltages and the sampling valley voltages appear alternately.

[0071] In practical applications, the preset sampling period may be set in combination with the sampling accuracy. Optionally, the preset sampling period may be any value between 12 us and 18 us.

[0072] In some embodiments, when the absolute value of the difference between the sampled peak-to-valley voltage and the reference voltage is less than the first detection threshold for a duration greater than a preset time, the sampling process in the current preset detection cycle is terminated.

[0073] Specifically, the reference voltage can be a reference for comparing signal voltages. In the embodiments of this specification, the reference voltage can include the midpoint between the peak and valley voltage values ​​of a complete sine-cosine-like signal, where the peak and valley voltage values ​​can include the maximum peak voltage and the minimum valley voltage. The first detection threshold can be the minimum absolute difference between the sampled peak and valley voltages of a valid signal and the reference voltage. In an optional embodiment, when the maximum peak voltage is set to 3.3V and the minimum valley voltage is set to 0V, the reference voltage can be set to 1.65V, and the first detection threshold can be 200mV.

[0074] Specifically, the preset time can be set based on the duration of a signal peak or a signal trough in actual applications. In an optional embodiment, when the duration of a signal peak or a signal trough is 00us~300us, the preset time can be any value from 450us to 600us.

[0075] S203 , traversing three consecutive sampled peak-valley voltages among the multiple sampled peak-valley voltages based on the sampling time sequence of the multiple sampled peak-valley voltages.

[0076] S205 , calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage.

[0077] S207 : When the sum is greater than the preset sum threshold, the three consecutive sampled peak-valley voltages currently traversed are taken as a sampled peak-valley voltage group.

[0078] In actual applications, when the target automatic walking device approaches the boundary line, there may be more than three sampled peak-valley voltages among the multiple sampled peak-valley voltages of the detected first detection signal, all of which reach the peak-valley voltage peak value. Therefore, the three consecutive sampled peak-valley voltages whose sum is greater than the preset sum threshold that are traversed earliest are taken as the sampled peak-valley voltage group; because under normal circumstances, the absolute value of the difference between the second sampled peak-valley voltage and the reference voltage in the sampled peak-valley voltage group is greater than the absolute value of the difference between the first sampled peak-valley voltage and the reference voltage and the absolute value of the difference between the third sampled peak-valley voltage and the reference voltage. Therefore, the second sampled peak-valley voltage is taken as the first target peak-valley voltage.

[0079] In some embodiments, after calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage, the method may further include:

[0080] If the sums of any three consecutive sampled peak-valley voltages among the multiple sampled peak-valley voltages during the traversal process are all less than the preset sum threshold, the three consecutive sampled peak-valley voltages with the largest corresponding sums are taken as the sampled peak-valley voltage group.

[0081] In practical applications, when the target autonomous driving device is far away from the boundary line, the multiple sampled peak-valley voltages of the detected first detection signal may not reach the peak-valley voltage top value. Therefore, three consecutive sampled peak-valley voltages with the largest total are selected as the sampled peak-valley voltage group.

[0082] S209 : Using the second sampled peak-valley voltage in the sampled peak-valley voltage group as the first target peak-valley voltage.

[0083] It can be seen from the above embodiments that when the target automatic walking device approaches the boundary line and the first detection signal is obtained using the first detection mode, the first target peak-valley voltage is determined based on the sampled peak-valley voltage group among the multiple sampled peak-valley voltages of the first detection signal. When the signal strength is large, the first target peak-valley voltage used to confirm the signal direction of the current first detection signal can be accurately obtained, thereby improving the accuracy of the current detection result.

[0084] In an embodiment of the present specification, when the target autonomous driving device is far away from the boundary line and the signal strength is very weak, that is, the first detection signal does not meet the preset signal condition, the first detection mode can be switched to the second detection mode. Specifically, the second detection mode can include steps S105 to S109.

[0085] S105 : When the first detection signal does not meet the preset signal condition, determine a first detection time period based on the current time and a preset detection cycle.

[0086] In a specific embodiment, the length of the first detection time period may be no less than the length of the preset detection period. For example, if the current time is X and the preset detection period is 17.2 ms, and the duration of a signal peak or a signal trough is 200 to 300 us, the first detection time period is set to X to X + 17.2 ms + 500 us.

[0087] S107 , based on the sensor of the target magnification, detects the boundary line signal within the first detection time period to obtain a second detection signal.

[0088] S109 , when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, adding the second target peak-to-valley voltage to the target feature data set.

[0089] Specifically, when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, the second detection signal can be used to determine whether the current target automatic walking device is within the boundary range, wherein the second target peak-to-valley voltage can be used to determine whether the direction of the second detection signal is within or outside the boundary.

[0090] It can be seen from the above embodiments that when the signal strength is very weak, that is, the first detection signal does not meet the preset signal condition, the first detection mode is switched to the second detection mode, and the detection threshold of the second target peak-valley voltage is lowered on the basis of improving the pertinence of the first detection time period, which can improve the detection rate of the second target peak-valley voltage, thereby improving the detection rate of the boundary range, so that the target walking device can still effectively detect the boundary line signal when it is far away from the boundary line, maintain normal working state, and thereby increase the working area of ​​the automatic walking device.

[0091] In a specific embodiment, when the intensity of the second detection signal obtained in the second detection mode is relatively weak, its waveform may be an incomplete sine-cosine-like signal waveform. Therefore, multiple sampled peak-valley voltages of the second detection signal are obtained through sampling processing to determine the second target peak-valley voltage. Specifically, Figure 3 As shown, before adding the second target peak-to-valley voltage to the target characteristic data set, the method may further include:

[0092] S301 , sampling the voltage waveform of the second detection signal to obtain a plurality of sampled peak-valley voltages of the second detection signal.

[0093] Specifically, during the current first detection time period, the voltage waveform of the second detection signal is sampled every preset sampling period to obtain multiple sampling peak-valley voltages. The multiple sampling peak-valley voltages can be multiple continuous sampling peak voltages and sampling valley voltages, wherein the sampling peak voltages and the sampling valley voltages appear alternately.

[0094] S303 , taking a sampled peak-valley voltage having the largest absolute value of difference from a reference voltage among the plurality of sampled peak-valley voltages of the second detection signal as a second target peak-valley voltage.

[0095] Specifically, when the signal strength of the second detection signal is weak, its waveform is an incomplete sine-cosine-like signal waveform. Therefore, the sampled peak-valley voltage with the largest absolute value among the sampled peak-valley voltages of the current second detection signal is used as the second target peak-valley voltage.

[0096] It can be seen from the above embodiments that when the target automatic walking device is far away from the boundary line and the second detection signal is obtained by using the second detection mode, the second target peak-valley voltage is determined by multiple sampled peak-valley voltages of the second detection signal, and the second target peak-valley voltage for confirming the signal direction of the current second detection signal can be accurately obtained, thereby improving the accuracy of the current detection result.

[0097] S111 , obtaining a boundary detection result of the target autonomous driving device based on a comparison result of the target feature data group and a reference voltage.

[0098] In an embodiment of the present specification, in the process of detecting the boundary line signal, the signal direction of the target feature data is determined based on the comparison result between the target feature data and the reference voltage in the current target feature data group, and according to the signal direction of the target feature data, it is judged whether the boundary detection result of the target automatic walking device is within the boundary range or outside the boundary range.

[0099] Specifically, such as Figure 4 As shown, the boundary detection result of the target autonomous driving device obtained based on the comparison result of the target feature data group and the reference voltage may include:

[0100] S401, when the sampling time intervals between adjacent target number of target feature data in the target feature data group are within a preset error range, determining a target number of signal directions corresponding to the adjacent target number of target feature data based on a comparison result between the adjacent target number of target feature data and a reference voltage.

[0101] In practical applications, the length of the sampling time interval between target feature data is usually approximately equal to the preset detection period. Therefore, the above-mentioned preset error range can be set according to the preset detection period. Taking the preset detection period of 17.2ms as an example, the preset error range can be 17.2ms±500us.

[0102] Specifically, the number of targets may be set in combination with the accuracy and efficiency of boundary detection in actual applications. In an optional embodiment, the number of targets may be greater than or equal to 3.

[0103] Specifically, signal waveforms of different signal directions can be preset. In an optional embodiment, the signal waveform in the in-boundary direction can be set so that the corresponding target characteristic data is greater than the reference voltage, that is, the corresponding target characteristic data is the peak voltage. Correspondingly, the signal waveform in the out-of-boundary direction can be set so that the corresponding target characteristic data is less than the reference voltage, that is, the corresponding target characteristic data is the valley voltage. Then, when a certain target characteristic data is greater than the reference voltage, the detection signal corresponding to the target characteristic data is the preset in-boundary direction. When a certain target characteristic data is less than the reference voltage, the detection signal corresponding to the target characteristic data is the preset in-boundary direction.

[0104] S403: When the target number of signal directions are all within the preset boundary, the boundary detection result is that the target autonomous driving device is within the boundary range.

[0105] It can be seen from the above embodiments that determining the boundary detection result according to the signal directions of the target number and target feature data can improve the accuracy of the boundary detection result.

[0106] In the embodiments of this specification, the second detection threshold and the third detection threshold can be two thresholds for determining the strength of a valid signal. Generally, the second detection threshold is lower than the third detection threshold. Optionally, when the reference voltage is 1.65V and the first detection threshold is 200mV, the second detection threshold can be 350mV and the third detection threshold can be 500mV.

[0107] In a specific embodiment, when the current first detection signal meets the preset signal condition and the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than the second detection threshold, although the current first detection signal is still a valid signal, the detected signal strength is weak, and the first detection mode can be switched to the third detection mode, and the third detection mode can be used for signal detection, such as Figure 5 As shown, Figure 5 This is a flow chart of a third detection mode provided in an embodiment of the present application, which may specifically include:

[0108] S501 , when the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than a second detection threshold, determining a second detection time period based on a sampling time of the target feature data with the latest sampling time in the target feature data group and a preset detection period.

[0109] In a specific embodiment, the length of the second detection time period is no less than the duration of a signal peak or a signal trough of the boundary line signal. Taking the sampling time of the target characteristic data with the latest current sampling time as t and the preset detection period as 17.2ms as an example, when the duration of a signal peak or a signal trough is 200us to 300us, the second detection time period is set to T-500us to T+500us, where T = 17.2ms + t.

[0110] S503 : Based on the sensor of the target magnification, the boundary line signal is detected within a second detection time period to obtain a third detection signal.

[0111] S505 : When the third detection signal meets a preset signal condition, add the third target peak-valley voltage in the sampled peak-valley voltage group corresponding to the third detection signal to the target characteristic data group.

[0112] In a specific embodiment, since the third detection signal satisfies the preset signal condition, that is, the third detection signal is still a valid signal and its waveform is a relatively complete sine-cosine-like signal waveform, a plurality of continuous sampled peak-valley voltages of the third detection signal are obtained through sampling processing, and a third target peak-valley voltage is determined based on a sampled peak-valley voltage group in the plurality of continuous sampled peak-valley voltages. Specifically, the specific steps for determining the third target peak-valley voltage here are similar to the detailed steps for determining the first target peak-valley voltage in S201 to S209 from "sampling the voltage waveform of the first detection signal to obtain a plurality of sampled peak-valley voltages" to "using the second sampled peak-valley voltage in the sampled peak-valley voltage group as the first target peak-valley voltage". For the specific steps, please refer to the detailed steps of S201 to S209 and will not be repeated here.

[0113] It can be seen from the above embodiments that when the signal strength is weak but the current signal is still a valid signal, the first detection mode is switched to the third detection mode, and the second detection time period is determined based on the sampling time of the previous target feature data and the preset detection period and signal detection is performed. This can filter out interference in time periods outside the second detection time period, improve the efficiency and accuracy of signal detection, and thus improve the detection rate of the boundary and the accuracy of the detection results.

[0114] In a specific embodiment, the preset signal condition may include: the absolute value of the difference between each of the three consecutive sampled peak-valley voltages corresponding to the current detection signal and the reference voltage is greater than the first detection threshold and the sampling time interval between the target peak-valley voltage corresponding to the current detection signal and the target feature data with the latest sampling time in the target feature data group is within a preset error range.

[0115] Specifically, the current detection signal may include any one of the first detection signal, the second detection signal, and the third detection signal. Accordingly, the target peak-valley voltage corresponding to the current detection signal may include: any one of the first target peak-valley voltage of the first detection signal, the second target peak-valley voltage of the second detection signal, and the third target peak-valley voltage of the third detection signal.

[0116] In an optional embodiment, when the preset detection period is 17.2ms, the maximum peak voltage is set to 3.3V, and the minimum valley voltage is set to 0V, the reference voltage can be set to 1.65V, the first detection threshold can be 200mV, and the preset error range can be 17.2ms±500us.

[0117] As can be seen from the above embodiments, judging whether the current detection signal is a valid signal according to the preset signal condition can improve the accuracy of valid signal judgment, thereby accurately using different detection modes and improving the accuracy of boundary detection.

[0118] In actual applications, as the target autonomous vehicle moves, its distance from the boundary line changes, and the detected signal strength also changes accordingly. Therefore, the accuracy of signal detection can be ensured by switching the detection mode.

[0119] As can be seen from the above embodiment, when the current detection mode is the first detection mode, the target autonomous driving device gradually moves away from the boundary line. If the current first detection signal does not meet the preset signal condition, that is, the detected signal strength is very weak, the first detection mode can be switched to the second detection mode. Specifically, after step S103, the process can jump to step S105.

[0120] If the current first detection signal meets the preset signal condition but the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than the second detection threshold, that is, the detected signal strength is weak, the first detection mode can be switched to the third detection mode. Specifically, the process can jump to step S501 after step S103.

[0121] In other embodiments, when the current detection mode is the second detection mode and the target autonomous driving device gradually approaches the boundary line, if the current second detection signal satisfies the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than the second detection threshold, that is, when the detected signal strength is strong, the second detection mode can be switched to the third detection mode. Specifically, after step S109, the process can jump to step S501 of "determining the second detection time period based on the sampling time and preset detection period of the target feature data with the latest sampling time in the target feature data group";

[0122] If the current second detection signal meets the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than the third detection threshold, that is, when the detected signal strength is very strong, the second detection mode can be switched to the first detection mode. Specifically, the process can jump to step S101 after step S109.

[0123] In other embodiments, when the current detection mode is the third detection mode, if the current third detection signal does not meet the preset signal condition, that is, the detected signal strength is very weak, the third detection mode can be switched to the second detection mode. Specifically, after step S505, the process can jump to step S105 of "determining the first detection time period based on the current time and the preset detection period";

[0124] If the current third detection signal meets the preset signal condition and the absolute value of the difference between the third target peak-to-valley voltage and the reference voltage is greater than the third detection threshold, that is, when the detected signal strength is very strong, the third detection mode can be switched to the first detection mode. Specifically, the process can jump to step S101 after step S505.

[0125] In practical applications, the second detection threshold and the third detection threshold can be set in combination with the detection signal voltage and the reference voltage. Optionally, when the reference voltage is 1.65V, the second detection threshold can be 350mV and the third detection threshold can be 500mV.

[0126] It can be seen from the above embodiments that switching the detection mode based on the current signal strength can improve the flexibility and accuracy of signal detection, thereby improving the flexibility and accuracy of the boundary detection method.

[0127] It can be seen from the technical solutions provided in the above embodiments of this specification that, on the one hand, by using the first detection mode and the third detection mode, when the target automatic walking device is close to the boundary line and the signal strength is strong, the sensor based on the target amplification factor performs boundary line signal detection, and determines the target peak-valley voltage based on the sampled peak-valley voltage group among the multiple sampled peak-valley voltages of the current detection signal, which can improve the accuracy of the boundary detection result when the signal strength is strong; on the other hand, when the current detection signal does not meet the preset signal condition, that is, the signal strength is weak, the current working mode is switched to the second detection mode, that is, the first detection time period is determined based on the current time and the preset detection period, and then the boundary line signal is detected within the first detection time period to obtain the second detection signal. When the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, the second target peak-to-valley voltage is added to the target feature data group, and based on the comparison result of the target feature data group and the reference voltage, the boundary detection result of the target automatic walking device is obtained, which can improve the detection rate of the second target peak-to-valley voltage, thereby improving the detection rate of the boundary range, so that the target walking device can still effectively detect the boundary line signal when it is far away from the boundary line, maintain normal working state and thereby increase the working area of ​​the automatic walking device; on the other hand, different detection modes can be switched based on the current signal strength during the movement of the automatic walking device, thereby improving the flexibility of signal detection, thereby improving the accuracy and flexibility of boundary detection.

[0128] The embodiment of the present application provides a boundary detection device, such as Figure 6 As shown, the above-mentioned device may include:

[0129] A first detection module 610 is configured to detect a boundary line signal at a preset detection period based on a sensor of a target magnification of the target autonomous vehicle to obtain a first detection signal;

[0130] A first target characteristic data group module 620 is configured to add a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to a target characteristic data group when the first detection signal satisfies a preset signal condition;

[0131] A first detection time period determination module 630 is configured to determine a first detection time period based on the current time and the preset detection period when the first detection signal does not meet the preset signal condition;

[0132] A second detection module 640 is configured to detect the boundary line signal within the first detection time period based on the sensor of the target magnification to obtain a second detection signal;

[0133] a second target characteristic data set module 650, configured to add the second target peak-to-valley voltage of the second detection signal to the target characteristic data set when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than a first detection threshold;

[0134] The boundary detection result module 660 is used to obtain a boundary detection result of the target autonomous driving device based on a comparison result of the target feature data group and the reference voltage.

[0135] In a specific embodiment, the above device may further include:

[0136] A first sampling module is used to sample and process the voltage waveform of the first detection signal to obtain a plurality of sampled peak and valley voltages;

[0137] A traversal module is used to traverse three consecutive sampled peak-valley voltages among the multiple sampled peak-valley voltages based on the sampling time sequence of the multiple sampled peak-valley voltages;

[0138] A sum calculation module is used to calculate the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage;

[0139] A first sampled peak-valley voltage group module is configured to use the three consecutive sampled peak-valley voltages currently traversed as a sampled peak-valley voltage group when the sum is greater than a preset sum threshold;

[0140] The first target peak-valley voltage module is configured to use the second sampled peak-valley voltage in the sampled peak-valley voltage group as the first target peak-valley voltage.

[0141] In some embodiments, the above apparatus may further include:

[0142] The second sampling peak-valley voltage group module is used to take the three consecutive sampling peak-valley voltages with the largest corresponding sum as the sampling peak-valley voltage group if the sum corresponding to any three consecutive sampling peak-valley voltages among the multiple sampling peak-valley voltages in the traversal process is less than the preset sum threshold.

[0143] In a specific embodiment, the above device may further include:

[0144] A second sampling module is used to sample and process the voltage waveform of the second detection signal to obtain a plurality of sampled peak and valley voltages of the second detection signal;

[0145] The second target peak-valley voltage module is configured to use a sampled peak-valley voltage having the largest absolute value of difference with a reference voltage among a plurality of sampled peak-valley voltages of the second detection signal as a second target peak-valley voltage.

[0146] In the embodiment of this specification, the boundary detection result module 660 may include:

[0147] a signal direction determining unit, configured to determine, when a sampling time interval between adjacent target number of target feature data in the target feature data group is within a preset error range, a target number of signal directions corresponding to the adjacent target number of target feature data based on a comparison result of the adjacent target number of target feature data with a reference voltage;

[0148] The boundary range identification unit is used to detect that the target autonomous driving device is within the boundary range when the target number of signal directions are all within the preset boundary.

[0149] In a specific embodiment, the above device may further include:

[0150] a second detection time period determination module, configured to determine a second detection time period based on a sampling time of the target characteristic data with the latest sampling time in the target characteristic data group and a preset detection period when the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than a second detection threshold;

[0151] a third detection module, configured to detect the boundary line signal within a second detection time period based on the sensor of the target magnification to obtain a third detection signal;

[0152] The third target characteristic data group module is used to add the third target peak-valley voltage in the sampled peak-valley voltage group corresponding to the third detection signal to the target characteristic data group when the third detection signal meets the preset signal condition.

[0153] An embodiment of the present application provides an automatic walking device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the boundary detection method provided in the above method embodiment.

[0154] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for the functions, etc.; the data storage area can store data created based on the use of the above devices, etc. In addition, the memory can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0155] The method embodiments provided in the embodiments of the present application can be executed in a computing device of an autonomous walking device.

[0156] The autonomous walking devices in the embodiments of the present application may include lawn mowing robots, snow shoveling robots, industrial robots, and other forms.

[0157] An embodiment of the present application also provides a storage medium, which can be set in a server to store at least one instruction or at least one program related to implementing a boundary detection method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the boundary detection method provided by the above method embodiment.

[0158] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0159] It can be seen from the above-mentioned embodiments of the boundary detection method, device, equipment or storage medium provided by the present application that, using the technical solution provided by the embodiments of this specification, on the one hand, using the first detection mode and the third detection mode, when the target automatic walking device is close to the boundary line and the signal strength is strong, the sensor based on the target magnification performs boundary line signal detection, and determines the target peak-valley voltage based on the sampled peak-valley voltage group among the multiple sampled peak-valley voltages of the current detection signal, which can improve the accuracy of the boundary detection result when the signal strength is strong; on the other hand, when the current detection signal does not meet the preset signal condition, that is, the signal strength is weak, the current working mode is switched to the second detection mode, that is, the first detection time period is determined based on the current time and the preset detection period, and then the boundary line is detected within the first detection time period. The signal is detected to obtain a second detection signal. When the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, the second target peak-to-valley voltage is added to the target feature data group, and based on the comparison result of the target feature data group and the reference voltage, the boundary detection result of the target automatic walking device is obtained, which can improve the detection rate of the second target peak-to-valley voltage, thereby improving the detection rate of the boundary range, so that the target walking device can still effectively detect the boundary line signal when it is far away from the boundary line, maintain a normal working state, and thus increase the working area of ​​the automatic walking device; on the other hand, different detection modes can be switched based on the current signal strength during the movement of the automatic walking device, thereby improving the flexibility of signal detection, thereby improving the accuracy and flexibility of boundary detection.

[0160] It should be noted that the order of the embodiments of the present application described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0161] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant portions, refer to the descriptions of the method embodiments.

[0162] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program. The above program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

[0163] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A boundary detection method, characterized in that: The method comprises: A sensor based on a target magnification of the target autonomous vehicle detects a boundary line signal at every preset detection period to obtain a first detection signal; When the first detection signal satisfies a preset signal condition, adding a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to a target feature data group; the preset signal condition is used to determine the signal strength of the current detection signal; When the first detection signal does not meet the preset signal condition, determining a first detection time period based on the current time and the preset detection period; Based on the sensor of the target magnification, the boundary line signal is detected within the first detection time period to obtain a second detection signal; When the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than the first detection threshold, adding the second target peak-to-valley voltage to the target feature data set; Based on the comparison result of the target feature data group and the reference voltage, a boundary detection result of the target autonomous driving device is obtained.

2. The method according to claim 1, characterized in that After adding the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to the target characteristic data group, the method further includes: When the absolute value of the difference between the first target peak-to-valley voltage and the reference voltage is less than a second detection threshold, determining a second detection time period based on the sampling time of the target characteristic data with the latest sampling time in the target characteristic data group and the preset detection period; Based on the sensor of the target magnification, the boundary line signal is detected within the second detection time period to obtain a third detection signal; When the third detection signal meets the preset signal condition, the third target peak-valley voltage in the sampled peak-valley voltage group corresponding to the third detection signal is added to the target characteristic data group.

3. The method according to claim 2, characterized in that After adding the third target peak-to-valley voltage in the sampled peak-to-valley voltage group corresponding to the third detection signal to the target characteristic data group, the method further includes: When the absolute value of the difference between the third target peak-to-valley voltage and the reference voltage is greater than a third detection threshold, the process jumps to executing the sensor based on the target magnification of the target autonomous driving device, detecting the boundary line signal every preset detection period to obtain a first detection signal; And / or, when the third detection signal does not meet the preset signal condition, jump to executing the step of determining the first detection time period based on the current time and the preset detection cycle.

4. The method according to claim 2, characterized in that After adding the second target peak-to-valley voltage to the target characteristic data set, the method further includes: When the second detection signal satisfies the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than a third detection threshold, the process jumps to executing the sensor based on the target magnification of the target autonomous driving device, detecting the boundary line signal every preset detection period to obtain a first detection signal; And / or, when the second detection signal satisfies the preset signal condition and the absolute value of the difference between the second target peak-to-valley voltage and the reference voltage is greater than the second detection threshold, jump to executing the step of determining the second detection time period based on the sampling time of the target feature data with the latest sampling time in the target feature data group and the preset detection cycle.

5. The method according to any one of claims 1 to 4, characterized in that: Before adding the first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to the target characteristic data group, the method further includes: Sampling the voltage waveform of the first detection signal to obtain a plurality of sampled peak-valley voltages; Based on the sampling time sequence of the plurality of sampled peak-valley voltages, traversing three consecutive sampled peak-valley voltages among the plurality of sampled peak-valley voltages; Calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage; When the sum is greater than a preset sum threshold, the three consecutive sampled peak-valley voltages currently traversed are used as the sampled peak-valley voltage group; The second sampled peak-valley voltage in the sampled peak-valley voltage group is used as the first target peak-valley voltage.

6. The method according to claim 5, characterized in that After calculating the sum of the absolute values ​​of the differences between the three consecutive sampled peak-to-valley voltages currently traversed and the reference voltage, the method further includes: If the sums of any three consecutive sampled peak-valley voltages among the multiple sampled peak-valley voltages during the traversal process are all less than the preset sum threshold, the three consecutive sampled peak-valley voltages with the largest corresponding sums are taken as the sampled peak-valley voltage group.

7. The method according to any one of claims 1 to 4, characterized in that: Before adding the second target peak-to-valley voltage to the target characteristic data set, the method further includes: Sampling the voltage waveform of the second detection signal to obtain a plurality of sampled peak-valley voltages of the second detection signal; Among the plurality of sampled peak-valley voltages of the second detection signal, a sampled peak-valley voltage having a maximum absolute value of difference from the reference voltage is used as the second target peak-valley voltage.

8. The method according to any one of claims 1 to 4, characterized in that: The preset signal conditions include: The absolute value of the difference between each of the three consecutive sampled peak-valley voltages corresponding to the current detection signal and the reference voltage is greater than the first detection threshold and the sampling time interval between the target peak-valley voltage corresponding to the current detection signal and the target feature data with the latest sampling time in the target feature data group is within a preset error range.

9. The method according to any one of claims 1 to 4, characterized in that: Obtaining a boundary detection result of the target autonomous driving device based on a comparison result of the target feature data group and the reference voltage includes: When the sampling time intervals between adjacent target number of target characteristic data in the target characteristic data group are within a preset error range, determining a target number of signal directions corresponding to the adjacent target number of target characteristic data based on a comparison result of the adjacent target number of target characteristic data with the reference voltage; When the target number of signal directions are all within the preset boundary, the boundary detection result is that the target autonomous driving device is within the boundary range.

10. A boundary detection device, characterized in that: The device comprises: A first detection module is configured to detect a boundary line signal at predetermined detection intervals based on a sensor of a target magnification of the target autonomous vehicle to obtain a first detection signal; a first target characteristic data group module, configured to add a first target peak-valley voltage in the sampled peak-valley voltage group corresponding to the first detection signal to a target characteristic data group when the first detection signal satisfies a preset signal condition; the preset signal condition is used to determine the signal strength of the current detection signal; a first detection time period determination module, configured to determine a first detection time period based on the current time and the preset detection period when the first detection signal does not meet the preset signal condition; a second detection module, configured to detect the boundary line signal within the first detection time period based on the sensor of the target magnification to obtain a second detection signal; a second target characteristic data group module, configured to add the second target peak-to-valley voltage of the second detection signal to the target characteristic data group when the absolute value of the difference between the second target peak-to-valley voltage of the second detection signal and the reference voltage is greater than a first detection threshold; The boundary detection result module is used to obtain the boundary detection result of the target autonomous driving device based on the comparison result of the target feature data group and the reference voltage.

11. An automatic walking device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the boundary detection method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the boundary detection method according to any one of claims 1 to 9.

Images