Hydrological cableway obstacle avoidance management and control method, system, equipment and medium

Abstract

The invention discloses a hydrological cableway obstacle avoidance management and control method, system and device and a medium, and relates to the technical field of hydrological flow measurement, and the method comprises the following steps: obtaining a monitoring video of the surrounding environment of a target fish lead; acquiring surrounding environment information of the target fish lead according to the monitoring video so as to obtain an early warning evaluation value; judging whether the early warning evaluation value is greater than a preset safety threshold value or not; if not, returning to obtain the monitoring video of the surrounding environment of the target lead fish; if yes, predicting a collision risk area in a future preset time according to the current position of the target fish lead and the surrounding environment information, and generating a local risk heat map; taking the current position of the target lead fish as a starting point, and generating a plurality of candidate obstacle avoidance paths according to the local risk heat map; the comprehensive cost function of each candidate obstacle avoidance path is obtained, the candidate obstacle avoidance path with the minimum value corresponding to the comprehensive cost function is output as the optimal obstacle avoidance path, and the method has the advantages that the optimal obstacle avoidance path can be automatically planned, and the planning precision is improved.

Description

Technical Field

[0001] This application relates to the technical field of hydrological flow measurement, and particularly to a method, system, device and medium for obstacle avoidance control of a hydrological cableway. Background Art

[0002] The hydrological cableway flow measurement system is an advanced flow measurement technology that accurately transports a measuring instrument (i.e., a lead fish) to a designated position through a cross-river cableway. The lead fish is equipped with a variety of key components, such as a radar speed measurement sensor for measuring flow velocity, a water level sensor for measuring water level, a data acquisition device responsible for collecting and processing data, and a wired or wireless transmission system for data transmission. In the field of water conservancy, its importance is self-evident, and it can accurately measure water flow information, providing key data support for water conservancy project planning, water resource management, flood control and disaster reduction, etc.

[0003] Currently, when the hydrological cableway flow measurement system conducts flow measurement operations, the lead fish moves in the water body through the cableway system, and often encounters collision risks due to rapid water flow, sudden wind speed changes or floating obstacles (such as branches, garbage, etc.). After the existing hydrological cableway obstacle avoidance control method detects an obstacle, it is difficult to automatically plan an optimal obstacle avoidance path according to the complex environment, mainly relying on manual experience to plan the obstacle avoidance path, and there are easily situations where the planned path is unreasonable or there is still a collision risk. Summary of the Invention

[0004] The main purpose of this application is to provide a method, system, device and medium for obstacle avoidance control of a hydrological cableway, aiming to solve the technical problem that it is difficult to automatically plan an optimal obstacle avoidance path according to the complex environment after the existing hydrological cableway obstacle avoidance control method detects an obstacle.

[0005] To achieve the above object, this application provides a method for obstacle avoidance control of a hydrological cableway, including the following steps:

[0006] Obtain a monitoring video of the surrounding environment of the target lead fish;

[0007] According to the monitoring video, obtain the surrounding environment information of the target lead fish to obtain a warning evaluation value;

[0008] Judge whether the warning evaluation value is greater than a preset safety threshold;

[0009] If not, return to obtaining the monitoring video of the surrounding environment of the target lead fish;

[0010] If so, predict the collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information, and generate a local risk heat map;

[0011] Take the current position of the target lead fish as the starting point, and generate multiple candidate obstacle avoidance paths according to the local risk heat map;

[0012] Obtain the comprehensive cost function of each candidate obstacle avoidance path, and output the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

[0013] Optionally, the expression of the comprehensive cost function is:

[0014] C = W1·λ1·L + W2·λ2·ΔV + W3·λ3·R max + W4·λ4·E;

[0015] In the formula, C is the comprehensive cost value of the path, L is the total length of the candidate obstacle avoidance path, ΔV is the speed change amount required for obstacle avoidance, R max is the maximum risk assessment value corresponding in the local risk heat map, E represents the motor energy consumption required for the candidate obstacle avoidance path, W1 is the first weight coefficient, W2 is the second weight coefficient, W3 is the third weight coefficient, W4 is the fourth weight coefficient, λ1 is the first adjustment coefficient, λ2 is the second adjustment coefficient, λ3 is the third adjustment coefficient, and λ4 is the fourth adjustment coefficient.

[0016] Optionally, before predicting the collision risk area within a preset future time and generating the local risk heat map based on the current position of the target lead fish and the surrounding environment information, it further includes:

[0017] Input the current position of the target lead fish and the surrounding environment information into a preset torque dynamic adjustment function;

[0018] Obtain the emergency braking torque of the brake according to the torque dynamic adjustment function to control the target lead fish to decelerate or stop moving;

[0019] Obtain the motion attitude information of the target lead fish in real time during the emergency braking process;

[0020] Judge whether the target lead fish deviates during the emergency braking process according to the motion attitude information;

[0021] If so, start the dynamic compensation mechanism; where the dynamic compensation mechanism is to correct the motion trajectory of the target lead fish by adjusting the differential speed of the motors on both sides of the cableway;

[0022] If not, return to obtaining the motion attitude information of the target lead fish in real time during the emergency braking process. Optionally, the expression of the torque dynamic adjustment function is:

[0023] T = K·V / d·e -t / τ ;

[0024] In the formula, T is the emergency braking torque, K is the proportionality coefficient, V is the current speed of the target lead fish, d is the real-time distance between the current position of the target lead fish and the obstacle, e is the natural constant, t is the duration of the target lead fish during the emergency braking process, and τ is the braking time constant.

[0025] Optionally, according to the current position of the target lead fish and the surrounding environment information, predict the collision risk area within a preset future time, and generate a local risk heat map, including:

[0026] Input the current position of the target lead fish and the surrounding environment information into a preset trajectory prediction model to obtain the future trajectory information of the target lead fish;

[0027] According to the future trajectory information, predict and mark the collision risk area within a preset future time;

[0028] Obtain the risk assessment values of each position point of the target lead fish in the collision risk area;

[0029] Generate a local risk heat map according to the magnitude of the risk assessment values.

[0030] Optionally, the expression of the trajectory prediction model is:

[0031]

[0032] In the formula, x(t), y(t) represent the predicted coordinates of the target lead fish at time t, x0, y0 represent the current position coordinates of the target lead fish, V is the current speed of the target lead fish, V1 is the moving speed of the obstacle, V2 is the water flow speed, θ is the angle between the moving direction of the obstacle and the moving direction of the target lead fish, Φ1 is the angle between the moving direction of the obstacle and the due east direction, and Φ2 is the angle between the water flow direction and the due east direction.

[0033] Optionally, after obtaining the comprehensive cost function of each candidate obstacle avoidance path and outputting the candidate obstacle avoidance path with the smallest corresponding value of the comprehensive cost function as the optimal obstacle avoidance path, it further includes:

[0034] Obtain the position deviation amount of the target lead fish in real time during the execution of the optimal obstacle avoidance path; wherein, the position deviation amount is the deviation value between the current position of the target lead fish and the optimal obstacle avoidance path;

[0035] Judge whether the position deviation amount is greater than a preset deviation threshold;

[0036] If so, return to input the current position of the target lead fish and the surrounding environment information into a preset torque dynamic adjustment function;

[0037] If not, return to obtain the position deviation amount of the target lead fish in real time during the execution of the optimal obstacle avoidance path.

[0038] To achieve the above object, the present application further provides a hydrological cableway obstacle avoidance control system, including:

[0039] A video acquisition module for acquiring a monitoring video of the surrounding environment of the target lead fish;

[0040] An early warning and evaluation module for obtaining the surrounding environment information of the target lead fish based on the monitoring video to obtain an early warning evaluation value;

[0041] A judgment module for judging whether the early warning evaluation value is greater than a preset safety threshold;

[0042] A feedback module for, if not, returning to the monitoring video of the surrounding environment of the target lead fish;

[0043] A risk analysis module for, if so, predicting the collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information and generating a local risk heat map;

[0044] A path planning module for taking the current position of the target lead fish as the starting point and generating multiple candidate obstacle avoidance paths according to the local risk heat map;

[0045] A path selection module for obtaining the comprehensive cost function of each candidate obstacle avoidance path and outputting the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

[0046] To achieve the above object, the present application also provides a computer device, which includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the above method.

[0047] To achieve the above object, the present application also provides a computer-readable storage medium, on which a computer program is stored, and the processor executes the computer program to implement the above method.

[0048] The beneficial effects that the present application can achieve are as follows:

[0049] This application can acquire the surrounding environment information of the target lead fish based on the monitoring video of the surrounding environment during the movement of the target lead fish collected in real time. Based on the relevant data of the surrounding environment information, a warning evaluation value can be calculated, and then it is judged whether the warning evaluation value is greater than the preset safety threshold. If not, the monitoring continues. If so, it means that there is a high collision risk if the target lead fish moves forward along the current route. Then, according to the current position of the target lead fish and the surrounding environment information, the collision risk area within a preset future time is predicted, and a local risk heat map is generated. Then, starting from the current position of the target lead fish and combining with the local risk heat map, multiple candidate obstacle avoidance paths can be generated. Then, the relevant parameters of each candidate obstacle avoidance path are input into the constructed comprehensive cost function to obtain the corresponding value. The smaller the value, the better the path. Finally, the candidate obstacle avoidance path with the smallest value of the comprehensive cost function is output as the optimal obstacle avoidance path. At this time, the target lead fish can move forward along the new optimal obstacle avoidance path, so as to automatically plan a better obstacle avoidance path according to the complex environment. Compared with manual planning, the planning accuracy is improved, and the planning efficiency is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0051] Figure 1 It is a schematic flowchart of a method for obstacle avoidance control of a hydrological cableway in an embodiment of the present application;

[0052] Figure 2 It is a schematic structural diagram of a hydrological cableway in an embodiment of the present application.

[0053] The realization of the purpose of the present application, the functional characteristics and advantages will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0055] It should be noted that all the directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0056] In the present application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0057] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and / or" appearing throughout the text includes three parallel scenarios. Taking "A and / or B" as an example, it includes Scenario A, or Scenario B, or the scenario where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0058] Embodiment 1

[0059] Refer to Figure 1 , this embodiment provides a method for obstacle avoidance control of a hydrological cableway, including the following steps:

[0060] Obtain a monitoring video of the surrounding environment of the target lead fish;

[0061] According to the monitoring video, obtain the surrounding environment information of the target lead fish to obtain a warning evaluation value;

[0062] Judge whether the warning evaluation value is greater than a preset safety threshold;

[0063] If not, return to obtaining the monitoring video of the surrounding environment of the target lead fish;

[0064] If so, predict the collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information, and generate a local risk heat map;

[0065] Starting from the current position of the target lead fish, multiple candidate obstacle avoidance paths are generated according to the local risk heat map;

[0066] Obtain the comprehensive cost function of each candidate obstacle avoidance path, and output the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

[0067] In this embodiment, based on the monitoring video of the surrounding environment of the target lead fish collected in real time during movement, the surrounding environment information of the target lead fish can be obtained. Based on the relevant data of the surrounding environment information, an early warning evaluation value can be calculated, and then it is judged whether the early warning evaluation value is greater than a preset safety threshold. If not, continue to monitor. If so, it means that there is a greater collision risk if the target lead fish moves forward according to the current route. Then, according to the current position of the target lead fish and the surrounding environment information, the collision risk area within a preset future time is predicted, and a local risk heat map is generated. Then, starting from the current position of the target lead fish and combining the local risk heat map, multiple candidate obstacle avoidance paths can be generated. Then, the relevant parameters of each candidate obstacle avoidance path are input into the constructed comprehensive cost function to obtain the corresponding value. The smaller the value, the better the path. Finally, the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function is output as the optimal obstacle avoidance path. At this time, the target lead fish can move forward according to the new optimal obstacle avoidance path, so as to automatically plan a better obstacle avoidance path according to the complex environment. Compared with manual planning, the planning accuracy is improved, and the planning efficiency is also improved.

[0068] It should be noted that, as Figure 2 shown, the hydrological cableway includes steel towers on both sides. There are multiple working cables driven by motors between the tops of the two steel towers. A traveling frame is slidably arranged on the working cables. A lead fish is suspended at the bottom of the traveling frame by a suspension rope. The lead fish can move synchronously with the traveling frame. By driving different working cables to slide and controlling their sliding speeds, the moving direction and speed of the lead fish can be adjusted, so as to control the moving trajectory of the lead fish. Here, a camera can be set on the traveling frame to collect the information of the target lead fish and its surrounding environment (such as water flow speed, wind speed, obstacle type, obstacle moving speed and direction, etc.) in real time. When calculating the early warning evaluation value, an early warning evaluation model can be trained based on the neural network algorithm. Inputting the parameters of the surrounding environment information into the model can quantitatively calculate an early warning evaluation value.

[0069] As an optional implementation manner, the expression of the comprehensive cost function is:

[0070] C = W1·λ1·L + W2·λ2·ΔV + W3·λ3·R max + W4·λ4·E;

[0071] In the formula, C is the comprehensive cost value of the path, L is the total length of the candidate obstacle avoidance path, ΔV is the speed change amount required for obstacle avoidance, Rmax R is the maximum risk assessment value corresponding to the local risk heat map, E represents the motor energy consumption required for the candidate obstacle avoidance path, W1 is the first weight coefficient, W2 is the second weight coefficient, W3 is the third weight coefficient, W4 is the fourth weight coefficient, λ1 is the first adjustment coefficient, λ2 is the second adjustment coefficient, λ3 is the third adjustment coefficient, and λ4 is the fourth adjustment coefficient.

[0072] In this embodiment, the path comprehensive cost value C in the formula is used to evaluate the degree of path optimization. The smaller its value, that is, the lower the cost paid, the better the selected path can be represented. And in this embodiment, the total length L of the candidate obstacle avoidance path, the speed change amount ΔV required for obstacle avoidance, and the maximum risk assessment value R corresponding to the local risk heat map are cited. max And the four more targeted and representative influence parameter factors of the motor energy consumption E required for the candidate obstacle avoidance path are used to comprehensively consider the obstacle avoidance path, so as to effectively evaluate the path comprehensive cost value C. At the same time, considering that the attributes of the above four influence parameter factors are different, they are respectively transformed and adjusted through the corresponding adjustment coefficients, so that the four influence parameter factors can be superimposed on each other. And considering that the influence degrees of the four influence parameter factors are different, the corresponding weight coefficients are also given. The weight coefficients can be calibrated according to the task priority. For example, W1 = 0.25, W2 = 0.25, W3 = 0.35, W4 = 0.15.

[0073] It should be noted that the total length L in the above formula can be calculated by the path planning algorithm. The speed change amount ΔV is the motor acceleration and deceleration amplitude required for obstacle avoidance, and the maximum risk assessment value R max can be directly extracted from the local risk heat map, which reflects the risk level of the area passed by the path. The motor energy consumption E is the power consumed by the target lead fish for the motor torque, running time, etc. during the movement on the corresponding path.

[0074] As an optional embodiment, before predicting the collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information and generating the local risk heat map, it further includes:

[0075] Input the current position of the target lead fish and the surrounding environment information into a preset torque dynamic adjustment function;

[0076] According to the torque dynamic adjustment function, obtain the emergency braking torque of the brake to control the target lead fish to decelerate or stop moving;

[0077] Obtain the motion attitude information of the target lead fish in real time during the emergency braking process;

[0078] According to the motion attitude information, judge whether the target lead fish deviates during the emergency braking process;

[0079] If so, start the dynamic compensation mechanism; wherein, the dynamic compensation mechanism corrects the movement trajectory of the target lead fish by adjusting the differential speed of the motors on both sides of the cableway.

[0080] If not, return to the real-time acquisition of the movement attitude information of the target lead fish during the emergency braking process.

[0081] In this embodiment, when it is monitored that the target lead fish has a collision risk and needs to re-plan the path, the target lead fish needs to be emergently braked before planning the path to decelerate or stop the movement. Otherwise, continuing to maintain the original trajectory state of operation will not only increase the collision risk, but also make it difficult to accurately perform subsequent trajectory planning. At this time, the current position of the target lead fish and data such as the surrounding environment information can be input into a preset torque dynamic adjustment function, so that the emergency braking torque of the brake can be calculated, and thus the deceleration or stop movement of the target lead fish can be reasonably and effectively controlled. At the same time, the movement attitude information of the target lead fish during the emergency braking process (such as whether the lateral acceleration exceeds a preset threshold) is monitored in real time, so as to judge whether the target lead fish deviates during the emergency braking process (that is, deviates from the original trajectory). If so, the dynamic compensation mechanism can be started, that is, by adjusting the differential speed of the motors on both sides of the cableway, the movement trajectory of the target lead fish can be corrected, ensuring that while emergently braking the target lead fish, its trajectory deviation is prevented.

[0082] It should be noted that the movement attitude information of the target lead fish can be monitored in real time according to the gyroscope and the acceleration sensor.

[0083] As an optional embodiment, the expression of the torque dynamic adjustment function is:

[0084] T = K·V / d·e -t / τ ;

[0085] In the formula, T is the emergency braking torque, K is the proportionality coefficient, V is the current speed of the target lead fish, d is the real-time distance between the current position of the target lead fish and the obstacle, e is the natural constant, t is the duration of the emergency braking process of the target lead fish, and τ is the braking time constant.

[0086] In this embodiment, when calculating the emergency braking torque T, all influencing parameter factors are fully considered. As in the above formula, for the current speed V of the target lead fish, the larger V is, the larger the required emergency braking torque T is, so the two are in a direct proportional relationship. The larger the real-time distance d between the current position of the target lead fish and the obstacle is, it indicates that the braking distance is larger, and the required emergency braking torque T is smaller, so the two are in an inverse proportional relationship. At the same time, the influence of parameters such as the duration t of the braking process is also comprehensively considered, and based on the proportionality coefficient K, the calculated values of the above influencing parameter factors are relatedly converted into the emergency braking torque T, which is targeted and referential. Through quantitative calculation, it can effectively and accurately guide the braking control of the target lead fish.

[0087] It should be noted that the emergency braking torque T in the formula is a dynamic value, which is dynamically adjusted according to the parameter changes at different times. By dynamically adjusting the braking force, it is executed by the electromagnetic brake. The proportionality coefficient K in the formula can be calibrated according to the lead fish mass and the cableway friction coefficient, and can be obtained by fitting based on experimental data. The speed V can be measured by an encoder or a radar speedometer. The real-time distance d can be measured based on a binocular camera or a millimeter-wave radar. The duration t is timed from the trigger of the braking instruction. The braking time constant τ reflects the inertia of the braking system and is calibrated through the brake response experiment.

[0088] As an alternative implementation, according to the current position of the target lead fish and the surrounding environment information, predict the collision risk area within a preset future time, and generate a local risk heat map, including:

[0089] Input the current position of the target lead fish and the surrounding environment information into a preset trajectory prediction model to obtain the future trajectory information of the target lead fish;

[0090] According to the future trajectory information, predict and mark the collision risk area within a preset future time;

[0091] Obtain the risk assessment values of each position point of the target lead fish in the collision risk area;

[0092] Generate a local risk heat map according to the magnitude of the risk assessment value.

[0093] In this implementation, the current position of the target lead fish and the surrounding environment information can be input into a preset trajectory prediction model here, so as to obtain the future trajectory information of the target lead fish, that is, the predicted position of the target lead fish at a certain future moment. Based on this predicted position, the collision risk area within a preset future time can be predicted and marked. Based on the relative variables (such as the relative displacement speed and relative displacement direction between the two) between the target lead fish and each position point in the collision risk area, the risk assessment values of each position point of the target lead fish in the collision risk area can be estimated. According to the corresponding value magnitudes, a local risk heat map can be formulated and generated, providing data support for subsequent evaluation of the comprehensive path cost value.

[0094] As an alternative implementation, the expression of the trajectory prediction model is:

[0095]

[0096] In the formula, x(t), y(t) represent the predicted coordinates of the target lead fish at time t, x0, y0 represent the current position coordinates of the target lead fish, V is the current speed of the target lead fish, V1 is the moving speed of the obstacle, V2 is the water flow speed, θ is the angle between the moving direction of the obstacle and the moving direction of the target lead fish, Φ1 is the angle between the moving direction of the obstacle and the due east direction, and Φ2 is the angle between the water flow direction and the due east direction.

[0097] In this embodiment, based on the above formula, the predicted coordinates of the target lead fish at time t can be predicted in real time and accurately, thus providing accurate data support for generating the local risk heat map.

[0098] As an alternative embodiment, after obtaining the comprehensive cost function of each candidate obstacle avoidance path and outputting the candidate obstacle avoidance path with the minimum value of the comprehensive cost function as the optimal obstacle avoidance path, it further includes:

[0099] Obtaining in real time the position deviation amount of the target lead fish during the execution of the optimal obstacle avoidance path; wherein, the position deviation amount is the deviation value between the current position of the target lead fish and the optimal obstacle avoidance path;

[0100] Judging whether the position deviation amount is greater than a preset deviation threshold;

[0101] If so, return to input the current position of the target lead fish and the surrounding environment information into the preset moment dynamic adjustment function;

[0102] If not, return to obtaining in real time the position deviation amount of the target lead fish during the execution of the optimal obstacle avoidance path.

[0103] In this embodiment, to further reduce the collision risk and avoid increasing the collision risk due to uncontrollable factors such as complex environmental changes (such as weather changes) causing the target lead fish to deviate from the optimal obstacle avoidance path, when the target lead fish moves along the optimal obstacle avoidance path, the position deviation amount of the target lead fish during the execution of the optimal obstacle avoidance path is also obtained in real time. When the position deviation amount is greater than the preset deviation threshold, at this time, it is difficult for the target lead fish to correct and reset again, so it is necessary to enter the emergency braking procedure again and re-plan the optimal obstacle avoidance path, thereby maximizing the reduction of the collision risk of the target lead fish.

[0104] Embodiment 2

[0105] Based on the same inventive concept as the foregoing embodiment, this embodiment further provides a hydrological cableway obstacle avoidance control system, including:

[0106] A video acquisition module, configured to acquire a monitoring video of the surrounding environment of the target lead fish;

[0107] An early warning evaluation module, configured to obtain the surrounding environment information of the target lead fish according to the monitoring video to obtain an early warning evaluation value;

[0108] A judgment module, configured to judge whether the early warning evaluation value is greater than a preset safety threshold;

[0109] A feedback module, configured to, if not, return to acquiring the monitoring video of the surrounding environment of the target lead fish;

[0110] A risk analysis module, which is configured to, if so, predict a collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information, and generate a local risk heat map;

[0111] A path planning module, which is configured to use the current position of the target lead fish as a starting point and generate multiple candidate obstacle avoidance paths according to the local risk heat map;

[0112] A path selection module, which is configured to obtain the comprehensive cost function of each candidate obstacle avoidance path and output the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

[0113] For the relevant explanations and examples of each module in the system of this embodiment, reference may be made to the methods in the foregoing embodiments, which will not be elaborated here.

[0114] Embodiment 3

[0115] Based on the same inventive concept as the foregoing embodiments, this embodiment provides a computer device, which includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the above method.

[0116] Embodiment 4

[0117] Based on the same inventive concept as the foregoing embodiments, this embodiment provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and the processor executes the computer program to implement the above method.

[0118] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for obstacle avoidance control of a hydrological cableway, characterized in that, It includes the following steps: Obtain the monitoring video of the surrounding environment of the target lead fish; According to the monitoring video, obtain the surrounding environment information of the target lead fish to obtain a warning evaluation value; Judge whether the warning evaluation value is greater than the preset safety threshold; If not, return to obtaining the monitoring video of the surrounding environment of the target lead fish; If so, according to the current position of the target lead fish and the surrounding environment information, predict the collision risk area within a preset future time and generate a local risk heat map; Taking the current position of the target lead fish as the starting point, generate multiple candidate obstacle avoidance paths according to the local risk heat map; Obtain the comprehensive cost function of each candidate obstacle avoidance path, and output the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

2. The hydrographic cableway obstacle avoidance control method according to claim 1, wherein The expression of the comprehensive cost function is: C = W1·λ1·L + W2·λ2·ΔV + W3·λ3·R max + W4·λ4·E; Wherein, C is the comprehensive cost value of the path, L is the total length of the candidate obstacle avoidance path, ΔV is the speed change amount required for obstacle avoidance, R max is the maximum risk assessment value corresponding in the local risk heat map, E represents the motor energy consumption required for the candidate obstacle avoidance path, W1 is the first weight coefficient, W2 is the second weight coefficient, W3 is the third weight coefficient, W4 is the fourth weight coefficient, λ1 is the first adjustment coefficient, λ2 is the second adjustment coefficient, λ3 is the third adjustment coefficient, and λ4 is the fourth adjustment coefficient.

3. A hydrological cableway obstacle avoidance control method according to claim 1, characterized in that, Before predicting the collision risk area within a preset future time and generating a local risk heat map according to the current position of the target lead fish and the surrounding environment information, it also includes: Input the current position of the target lead fish and the surrounding environment information into a preset torque dynamic adjustment function; According to the torque dynamic adjustment function, obtain the emergency braking torque of the brake to control the target lead fish to decelerate or stop moving; Obtain the motion attitude information of the target lead fish in real time during the emergency braking process; According to the motion attitude information, judge whether the target lead fish deviates during the emergency braking process; If so, start the dynamic compensation mechanism; wherein, the dynamic compensation mechanism is to correct the motion trajectory of the target lead fish by adjusting the differential speed of the motors on both sides of the cableway; If not, return to obtaining the motion attitude information of the target lead fish in real time during the emergency braking process.

4. The method for obstacle avoidance control of a hydrological cableway according to claim 3, wherein, The expression of the torque dynamic adjustment function is: T = K·V / d·e -t / τ ; In the formula, T is the emergency braking torque, K is the proportional coefficient, V is the current speed of the target lead fish, d is the real-time distance between the current position of the target lead fish and the obstacle, e is the natural constant, t is the duration of the target lead fish during the emergency braking process, and τ is the braking time constant.

5. The hydrographic cableway obstacle avoidance control method according to claim 1, characterized in that, Predicting the collision risk area within a preset future time and generating a local risk heat map according to the current position of the target lead fish and the surrounding environment information includes: Input the current position of the target lead fish and the surrounding environment information into a preset trajectory prediction model to obtain the future trajectory information of the target lead fish; According to the future trajectory information, predict and mark the collision risk area within a preset future time; Obtain the risk evaluation value of each position point of the target lead fish in the collision risk area; Generate a local risk heat map according to the magnitude of the risk evaluation value.

6. The hydrographic cableway obstacle avoidance control method according to claim 5, characterized in that, The expression of the trajectory prediction model is: In the formula, x(t), y(t) represent the predicted coordinates of the target lead fish at time t, x0, y0 represent the current position coordinates of the target lead fish, V is the current speed of the target lead fish, V1 is the moving speed of the obstacle, V2 is the water flow speed, θ is the angle between the moving direction of the obstacle and the moving direction of the target lead fish, Φ1 is the angle between the moving direction of the obstacle and the due east direction, and Φ2 is the angle between the water flow direction and the due east direction.

7. The method for obstacle avoidance control of a hydrological cableway according to claim 3, characterized in that, After obtaining the comprehensive cost function of each candidate obstacle avoidance path and outputting the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path, it also includes: Obtain the position deviation of the target lead fish in real time during the execution of the optimal obstacle avoidance path; wherein, the position deviation is the deviation value between the current position of the target lead fish and the optimal obstacle avoidance path. Judge whether the position deviation is greater than a preset deviation threshold. If so, return to input the current position of the target lead fish and the surrounding environment information into a preset torque dynamic adjustment function. If not, return to obtain the position deviation of the target lead fish in real time during the execution of the optimal obstacle avoidance path.

8. A hydrological cableway obstacle avoidance control system, characterized in that, It includes: A video acquisition module for acquiring a monitoring video of the surrounding environment of the target lead fish. A warning evaluation module for obtaining the surrounding environment information of the target lead fish according to the monitoring video to obtain a warning evaluation value. A judgment module for judging whether the warning evaluation value is greater than a preset safety threshold. A feedback module for, if not, returning to acquire the monitoring video of the surrounding environment of the target lead fish. A risk analysis module for, if so, predicting the collision risk area within a preset future time according to the current position of the target lead fish and the surrounding environment information, and generating a local risk heat map. A path planning module for taking the current position of the target lead fish as the starting point and generating multiple candidate obstacle avoidance paths according to the local risk heat map. A path selection module for obtaining the comprehensive cost function of each candidate obstacle avoidance path and outputting the candidate obstacle avoidance path with the smallest value corresponding to the comprehensive cost function as the optimal obstacle avoidance path.

9. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement a hydrological cableway obstacle avoidance control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and the processor executes the computer program to implement a hydrological cableway obstacle avoidance control method according to any one of claims 1-7.

Images