Poultry whistling low-noise routing inspection navigation method

Abstract

The invention provides a poultry chirp low-noise routing inspection navigation method. The method comprises the following steps: collecting surrounding visual identification signals and sound signals; setting a visual signal threshold value and a noise signal threshold value; when the collected visual identification signal is greater than the threshold value of the visual signal, reducing the rotating speed of the moving wheel, and entering a low-noise inspection mode; and when the collected sound signal is greater than the threshold value of the noise signal, reducing the rotating speed of the moving wheel, and entering a low-noise inspection mode. According to the poultry whistling low-noise inspection navigation method provided by the invention, surrounding visual identification signals and sound signals are collected, and the inspection robot is controlled to enter a low-noise inspection mode by comparing and analyzing the collected visual identification signals and sound signals with a visual signal threshold value and a noise signal threshold value in real time; poultry animals are prevented from being affected by noise generated by walking of the robot, and efficient and low-noise animal health state inspection can be achieved.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent inspection robots, and in particular to a low-noise inspection navigation method for bird calls. Background Art

[0002] In modern animal husbandry, real-time monitoring of animal health is an important part of improving breeding efficiency and animal welfare. However, when existing inspection robots are inspecting in pastures, the noise emitted by wheels and other equipment is loud, which may cause animals to feel uneasy and have stress reactions, affecting their health and production efficiency. In addition, inspection robots in the prior art lack intelligent adaptability when facing different terrains and animal behaviors, and cannot achieve efficient and low-noise inspections.

[0003] Inspection robots in the prior art generally include a mobile platform, a sensor module and a data processing unit; the mobile platform includes a drive motor, wheels and a speed sensor, the sensor module includes a camera, an infrared sensor and a controller, and the data processing unit includes an image processing algorithm, behavior recognition software and a communication module. This technology monitors the behavior and environmental parameters of animals through sensors, and analyzes the health status of animals in combination with a data processing unit. Although this technology can monitor the health status of animals, it does not intelligently switch between conventional inspections and noise reduction inspections. In response to the above problems, a smart animal health inspection robot that can intelligently switch between conventional inspections and noise reduction inspections is needed, which is efficient and low-noise. Summary of the invention

[0004] The present invention provides a low-noise inspection and navigation method for bird calls, which is used to solve at least one of the above technical problems.

[0005] The present invention provides a low-noise inspection and navigation method for bird calls, comprising the following steps:

[0006] Collect surrounding visual recognition signals and sound signals;

[0007] Set visual signal threshold, set noise signal threshold;

[0008] When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered;

[0009] When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

[0010] According to a low-noise inspection and navigation method for bird calls provided by the present invention, the threshold of setting the noise signal includes:

[0011] Collect the surrounding temperature signals, build a linear regression model with the collected visual recognition signals and temperature signals, and obtain the reaction degree of the poultry;

[0012] The maximum noise signal threshold that does not affect the birds is determined based on the degree of their reaction.

[0013] According to a low-noise inspection and navigation method for bird calls provided by the present invention, the linear regression model is expressed as:

[0014] According to the visual recognition signal S d , temperature signal S ir , and get the integrated signal S comb , expressed as:

[0015] S comb =w d ·S d +w ir ·S ir

[0016] Among them, w d is the weight of the visual recognition signal, w ir is the weight of the temperature signal;

[0017] For the integrated signal S comb Adjust to get the transformed integrated signal:

[0018]

[0019] The transformed integrated signal S′ comb As input features, a linear regression model is established:

[0020] N i ≈β0+β1S′ combi

[0021] Among them, N i is the response degree of poultry animals, β0 and β1 are the coefficients of the linear regression model.

[0022] According to a low-noise inspection and navigation method for bird calls provided by the present invention, a maximum noise signal threshold T of the bird is set. * Not exceeding the maximum reaction level of poultry N max :

[0023] β0+β1S′ combi ≤N max

[0024] Maximum noise signal threshold T * for:

[0025]

[0026] Among them, β1>0;

[0027] When the integrated signal S comb Greater than the maximum noise signal threshold T of poultry * , reduce the speed of the moving wheel.

[0028] According to a low-noise inspection and navigation method for bird calls provided by the present invention, the sound signal is set to S audio , then the sound signal strength I audio It is expressed as:

[0029] I audio =g(S audio )

[0030] Where g is the intensity extraction function;

[0031] When the sound signal strength I audio Greater than the maximum sound signal threshold Right now: Reduce the speed of the moving wheel and enter low-noise inspection mode.

[0032] According to a low-noise inspection and navigation method for bird calls provided by the present invention, reducing the rotation speed of the moving wheel includes:

[0033] Proportional adjustment of the motor's rotation speed:

[0034] u p (t) = k p e(t)

[0035] Among them, u p (t) is the output of the proportional link, reflecting the amount of adjustment required for the system at time t, e(t) is the deviation between the actual speed and the expected speed, k p is the proportionality coefficient;

[0036] In the presence of a steady-state error, the rotation speed of the motor is adjusted by an integral link (I);

[0037] When an error occurs in the integral link, the following formula is satisfied:

[0038]

[0039] Among them, k i is the integration coefficient;

[0040] When the motor speed changes beyond the threshold, the motor speed is adjusted by differential link to meet the following formula:

[0041]

[0042] Among them, k d is the differential coefficient;

[0043] The output parts of the proportional link, integral link and differential link are added together to obtain a control signal to control the speed of the motor, that is, u(t) = u p (t)+u i (t)+u d (t).

[0044] According to a low-noise inspection and navigation method for bird calls provided by the present invention, in a low-noise inspection mode, the visual recognition signal change ΔS is continuously inspected. v And the sound signal change ΔS a ;

[0045]

[0046] T a To avoid affecting the maximum noise signal threshold of birds, T v is the visual signal threshold.

[0047] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned low-noise inspection and navigation methods for avian calls are implemented.

[0048] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the low-noise inspection and navigation method for avian calls as described in any one of the above are implemented.

[0049] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned low-noise inspection and navigation methods for avian calls.

[0050] The low-noise inspection and navigation method for poultry calls provided by the present invention collects surrounding visual recognition signals and sound signals. When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered; when the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered, so as to avoid the noise generated by the walking of the robot affecting the poultry animals, and realize efficient and low-noise inspection of the health status of animals. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a flow chart of the low-noise inspection and navigation method for bird calls provided by the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figure 1 The low-noise inspection and navigation method for bird calls of the present invention comprises the following steps:

[0055] Collect surrounding visual recognition signals and sound signals;

[0056] Set visual signal threshold, set noise signal threshold;

[0057] When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered;

[0058] When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

[0059] Collect the surrounding visual recognition signals and sound signals. When the collected visual recognition signal is greater than the threshold of the visual signal, reduce the speed of the moving wheel and enter the low-noise inspection mode. When the collected sound signal is greater than the threshold of the noise signal, reduce the speed of the moving wheel and enter the low-noise inspection mode. By comparing and analyzing the collected visual recognition signals and sound signals with the visual signal threshold and the noise signal threshold in real time, the inspection robot is controlled to enter the low-noise inspection mode to avoid the noise generated by the robot's walking affecting the poultry animals, thereby realizing efficient and low-noise inspection of the health status of animals.

[0060] In the premise environment of poultry farming, the activities of inspection robots may cause noise interference to poultry animals, affecting their physiological behavior and health status.

[0061] Preferably, setting the threshold of the noise signal includes:

[0062] Collect the surrounding temperature signals, build a linear regression model with the collected visual recognition signals and temperature signals, and obtain the reaction degree of the poultry;

[0063] The maximum noise signal threshold that does not affect the birds is determined based on the degree of their reaction.

[0064] Specifically, the depth camera and infrared equipment are used for joint identification to collect comprehensive information about birds and their environment. The linear regression model is expressed as:

[0065] According to the visual recognition signal S collected by the depth camera d , the temperature signal S detected by the infrared device ir , and get the integrated signal S comb , expressed as:

[0066] S comb =w d ·S d +w ir ·S ir

[0067] Among them, w d is the weight of the visual recognition signal, w ir is the weight of the temperature signal, and the weight-price ratio is 1:1 under ideal conditions;

[0068] In complex cases, weighting cannot capture the relationship between depth information and temperature information. Therefore, a nonlinear transformation function Sigmoid is applied as g(x) after weighting. Further adjust the integrated signal S comb , S′ comb =g(S comb )

[0069]

[0070] For the integrated signal S comb Adjust to get the transformed integrated signal:

[0071]

[0072] S′ comb is the transformed integrated signal, the transformed integrated signal S′ comb It is mapped to the interval (0,1), and the transformed integrated signal S′ combi As input features, the response level of the avian animals N i As the output target, a linear regression model is established:

[0073] Ni ≈h(S′ combi )β0+β1S′ combi

[0074] Among them, N i is the degree of response of poultry, such as stress response, behavioral change, etc. β0 and β1 are the coefficients of the linear regression model. The model is trained using the data set through the least squares method, that is, the optimal model parameters β0 and β1 are found.

[0075] Furthermore, the threshold T * It can be defined so that the predicted reaction level does not exceed N max The maximum integrated signal value S′ combi,max Since the linear regression model is continuous, we are actually looking for the maximum S′ that satisfies the following conditions: combi :

[0076] β0+β1S′ combi ≤N max

[0077] Right now,

[0078] Maximum noise signal threshold T * for:

[0079]

[0080] Among them, β1>0;

[0081] When the integrated signal S comb Greater than the maximum noise signal threshold T of poultry * , triggering the low-noise inspection mode and reducing the speed of the moving wheel.

[0082] In another embodiment, the sound signal is set to S audio , then the sound signal strength I audio It is expressed as:

[0083] I audio =g(S audio )

[0084] Among them, g is the intensity extraction function, which is calculated based on the frequency, duration and other characteristics of the sound signal;

[0085] The threshold value of the sound signal is relatively simple, and does not require regression analysis. The intensity of the sound signal collected in a noisy environment at noon in a poultry farm can be directly obtained;

[0086] When the sound signal strength I audio Greater than the maximum sound signal threshold That is: I audio> Reduce the speed of the moving wheel and enter the low-noise inspection mode;

[0087] To better improve the threshold Experimental testing is also required. Let the test data be Among them A i It is the degree of response of birds to corresponding sound signals, such as changes in call frequency, behavior changes, etc.

[0088] Finally, the triggering conditions for the low-noise inspection mode of the inspection robot are:

[0089] S comb >T * or

[0090] When any of the above two conditions is met, the inspection robot will automatically enter the low-noise inspection mode, minimizing the noise and visual interference that the inspection robot's activities may cause to poultry.

[0091] Preferably, when the robot enters the low-noise inspection mode, it will execute the logic of reducing the speed. In this process, the robot controls the motor through the PID algorithm to achieve precise control of the wheel speed. Reducing the speed of the moving wheel includes:

[0092] When the robot enters the low-noise inspection mode, it compares its actual speed with the expected speed. If there is a difference between the two, the proportional link (P) of the PID algorithm will play a role first, and the motor's rotation speed will be adjusted proportionally:

[0093] u p (t) = k p e(t)

[0094] Among them, u p (t) is the output of the proportional link, reflecting the amount of adjustment required for the system at time t, e(t) is the deviation between the actual speed and the expected speed, k p It is the proportional coefficient. The larger the deviation, the stronger the control signal generated by the proportional link, and the greater the adjustment range of the motor speed.

[0095] The speed deviation cannot be completely eliminated by relying solely on the proportional link. In the presence of a steady-state error, the rotation speed of the motor is adjusted by the integral link (I);

[0096] When an error occurs in the integral link, the following formula is satisfied:

[0097]

[0098] Among them, k iis the integral coefficient; the integral link will continuously accumulate speed deviations. Even if the deviation is small, the integral term will gradually increase over time, prompting the motor to further adjust the speed until the deviation is zero, thereby achieving the purpose of precise speed control.

[0099] When the motor speed changes beyond the threshold, the motor speed is adjusted by differential link to meet the following formula:

[0100]

[0101] Among them, k d is the differential coefficient; the differential link can generate a corresponding control signal according to the rate of change of the speed deviation, reduce the amplitude of motor acceleration, and timely suppress excessive changes in motor speed.

[0102] The output parts of the proportional link, integral link and differential link are added together to obtain a control signal to control the speed of the motor, that is, u(t) = u p (t)+u i (t)+u d (t), and the obtained control signal u(t) is used to drive the motor of the robot wheel, thereby achieving precise control of the wheel speed.

[0103] Preferably, in the low-noise inspection mode, the robot continuously detects the change in the visual recognition signal ΔS v And the sound signal change ΔS a ;

[0104]

[0105] T a In order to test the impact of noise on poultry at different moving speeds of the inspection robot in the farm, the maximum noise signal threshold without affecting the poultry was obtained, T v is the visual signal threshold of birds and poultry houses detected by the depth camera.

[0106] The inspection robot uses laser SLAM technology to build path maps in the farm, and combines the A* algorithm and dynamic window method (DWA) for global and local path planning.

[0107] The inspection robot is equipped with a laser radar, which detects the contours and distance of the surrounding environment by emitting a laser beam and measuring the time it takes for it to reflect back. The high-speed rotation of the laser radar provides a 360-degree view, allowing the robot to accurately map the surrounding environment.

[0108] As the lidar continues to scan, the robot compares the collected data with the known map to identify new features or update the existing map. The process is real-time, allowing the robot to build and update a map of its environment while it moves.

[0109] Find the shortest path from an initial node to a target node in a graph. In the context of an inspection robot, the A* algorithm is used for global path planning, calculating the optimal path from the current location to the target location. The algorithm takes into account the robot's current location, the target location, and obstacles in the environment to determine the most efficient inspection route.

[0110] The hardware integration of the inspection robot's noise-reducing inspection method includes: a depth camera for capturing three-dimensional environmental information in real time, a microphone array sound sensor for capturing the sounds of poultry and animals, an inertial measurement unit for detecting the robot's posture and motion state, an embedded system for storing and analyzing the collected poultry and animal sound data sets, and processing sensor data and running ROS.

[0111] A physical structure of an electronic device, the electronic device may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may call logic instructions in the memory to execute a low-noise inspection and navigation method for bird calls, the method comprising: collecting surrounding visual recognition signals and sound signals;

[0112] Set visual signal threshold, set noise signal threshold;

[0113] When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered;

[0114] When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

[0115] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0116] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the low-noise inspection and navigation method of bird calls provided by the above methods, the method includes: collecting surrounding visual recognition signals and sound signals;

[0117] Set visual signal threshold, set noise signal threshold;

[0118] When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered;

[0119] When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

[0120] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the low-noise inspection and navigation method for bird calls provided by the above methods, the method comprising: collecting surrounding visual recognition signals and sound signals;

[0121] Set visual signal threshold, set noise signal threshold;

[0122] When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered;

[0123] When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

[0124] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0125] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A low-noise inspection and navigation method for bird calls, characterized in that: The steps include: Collect surrounding visual recognition signals and sound signals; Set visual signal threshold, set noise signal threshold; When the collected visual recognition signal is greater than the threshold of the visual signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered; When the collected sound signal is greater than the threshold of the noise signal, the rotation speed of the moving wheel is reduced and the low-noise inspection mode is entered.

2. The low-noise inspection and navigation method for bird calls according to claim 1 is characterized in that: The setting of the threshold of the noise signal comprises: Collect the surrounding temperature signals, build a linear regression model with the collected visual recognition signals and temperature signals, and obtain the reaction degree of the poultry; The maximum noise signal threshold that does not affect the birds is determined based on the degree of their reaction.

3. The low-noise inspection and navigation method for bird calls according to claim 2 is characterized in that: The linear regression model is expressed as: According to the visual recognition signal S d , temperature signal S ir , and get the integrated signal S comb , expressed as: S comb =w d ·S d +w ir ·S ir Among them, w d is the weight of the visual recognition signal, w ir is the weight of the temperature signal; For the integrated signal S comb Adjust to get the transformed integrated signal: The transformed integrated signal S' combi As input features, a linear regression model is established: N i ≈β0+β1S combi Among them, N i is the response degree of poultry animals, β0 and β1 are the coefficients of the linear regression model.

4. The low-noise inspection and navigation method for bird calls according to claim 3 is characterized in that: Set the maximum noise signal threshold T for poultry * Not exceeding the maximum reaction level of poultry N max : β0+β1S′ combi ≤N max Maximum noise signal threshold T * for: Among them, β1>0; When the integrated signal S comb Greater than the maximum noise signal threshold T of poultry * , reduce the speed of the moving wheel.

5. The low-noise inspection and navigation method for bird calls according to any one of claims 2, 3, and 4, characterized in that: Set the sound signal to S audio , then the sound signal strength I audio It is expressed as: I audio =g(S audio ) Where g is the intensity extraction function; When the sound signal strength I audio Greater than the maximum sound signal threshold Right now: Reduce the speed of the moving wheel and enter low-noise inspection mode.

6. The low-noise inspection and navigation method for bird calls according to claim 1, characterized in that: The step of reducing the rotation speed of the moving wheel comprises: Proportional adjustment of the motor's rotation speed: u p (t)=k p e(t) Among them, u p (t) is the output of the proportional link, reflecting the amount of adjustment required for the system at time t, e(t) is the deviation between the actual speed and the expected speed, k p is the proportionality coefficient; In the presence of a steady-state error, the rotation speed of the motor is adjusted by an integral link (I); When an error occurs in the integral link, the following formula is satisfied: Among them, k i is the integration coefficient; When the motor speed changes beyond the threshold, the motor speed is adjusted by differential link to meet the following formula: Among them, k d is the differential coefficient; The output parts of the proportional link, integral link and differential link are added together to obtain a control signal to control the speed of the motor, that is, u(t) = u p (t)+u i (t)+u d (t).

7. The low-noise inspection and navigation method for bird calls according to claim 1, characterized in that: In low-noise inspection mode, continuously check the visual recognition signal change ΔS v And the sound signal change ΔS a ; T a To avoid affecting the maximum noise signal threshold of birds, T v is the visual signal threshold.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the low-noise inspection and navigation method for avian calls as described in any one of claims 1 to 7 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the low-noise inspection and navigation method for avian calls as described in any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the low-noise inspection and navigation method for avian calls as described in any one of claims 1 to 7 are implemented.

Images