Intelligent regulation and control system of vehicle bottom detection robot

Abstract

The invention discloses an intelligent regulation and control system of a vehicle bottom detection robot, and relates to the technical field of vehicle bottom detection, a data acquisition module is configured to acquire omnibearing data information of a target vehicle bottom, and the data information at least comprises position information of a vehicle bottom target, distance information between different vehicle bottom targets and contour information of the vehicle bottom target; the data analysis module is connected with the data acquisition module, and is configured to execute the following steps: performing deep analysis on the acquired data, and identifying the type, position, shape and size characteristics of each target at the bottom of the vehicle; the optimized moving path is generated through the path planning module in combination with the distribution condition and the parameter condition of the vehicle bottom target to be detected, compared with traditional path planning, unnecessary acceleration, deceleration and steering operation of the robot can be reduced, energy consumption is reduced, and meanwhile detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of under-vehicle detection, and more specifically, to an intelligent control system of an under-vehicle detection robot. Background Art

[0002] The underbody inspection robot is an intelligent device used to inspect the underbody condition of vehicles. It is widely used in subways, high-speed railways, public security, customs and other fields. In the under-vehicle object detection technology, under-vehicle detection robots usually use preset fixed routes for detection. This detection method requires the robot to frequently adjust its parameters during the detection process to adapt to different detection tasks and environments. However, this frequent parameter adjustment not only increases the complexity of the operation, but also significantly reduces the robot's grasping efficiency. Summary of the invention

[0003] In order to solve the above problems, the present invention provides an intelligent control system for an underbody inspection robot.

[0004] The present invention provides an intelligent control system for an underbody detection robot, comprising: A data acquisition module is configured to collect all-round data information of the target vehicle bottom, wherein the data information at least includes position information of the target under the vehicle bottom, spacing information between different targets under the vehicle bottom, and contour information of the target under the vehicle bottom; A data analysis module, connected to the data acquisition module, configured to perform: in-depth analysis of the acquired data to identify the type, location, shape and size characteristics of each target under the vehicle; Use data analysis algorithms to statistically analyze target distribution patterns and determine the detection parameters corresponding to each target; The path planning module is connected to the data analysis module and is configured to generate a moving path based on target characteristics and distribution law information and in combination with the kinematic parameters of the robot.

[0005] Preferably, the specific steps of generating the moving path based on the under-vehicle target features and target distribution information provided by the data analysis module and combining the motion parameters of the under-vehicle detection robot are: A1: Divide the space under the vehicle into multiple detection areas, each area corresponding to the first type of target to be detected or the second type of target to be detected; A2: Execute the following operations on the area where the first type of target to be detected is located: Obtain the detection parameters corresponding to each target in the area; Generate a moving path in the order of monotonically increasing or monotonically decreasing adjustment amplitudes of the detection parameters; A3: Execute the following operations on the area where the second type of target to be detected is located: Calculate the distance between each target in the area; The moving path is generated based on the principle of minimizing the difference in moving distances between adjacent targets.

[0006] Preferably, the detection area division method specifically includes: Determine the detection parameter accuracy requirements for each target to be detected; Classifying multiple targets whose detection parameter accuracy requirements are within a preset fixed range as a first type of target area to be detected; A plurality of targets whose detection parameter accuracy allows for dynamic adjustment are classified as the second type of target area to be detected.

[0007] Preferably, the specific manner in which the path planning module selects the moving path is: When the detection path needs to be extended to adjacent areas: If the next area contains the first type of target to be detected: Get the detection parameters of the target at the end of the current path; Calculate the adjustment range of the target detection parameters in adjacent areas; Select the target with the smallest adjustment amplitude of detection parameters as the next path node; If the next area contains the second type of target to be detected: Calculate the distance between the end position of the current path and each target in the adjacent area; Select the target with the smallest distance as the next path node.

[0008] Preferably, the path planning module is further used to re-evaluate the path according to the precise parameters required for the current target, specifically: Get the initial path, which is the current position of the detection robot , and use this as the starting point and the target location As the end point, plan a straight line shortest path , its length ; According to the precise parameters required for the current goal provided by the data analysis module, the formula , get the time required for parameter adjustment ,in, Indicates the current detection angle of the robot. Represents the optimal detection angle required to complete high-precision detection of the current target. Refers to the adjustment speed of the robot's detection angle, that is, the degree to which the robot can change the detection angle per unit time; Calculate the initial path moving time; Compare the times to determine whether rerouting is necessary or not; Introducing new heuristic functions for re-planning routes , in the original heuristic function that only considers distance On the basis of ,in, It is used to measure the degree of circuitousness of the path, and to measure the To Node The circuitousness of this path, is the weight coefficient, which is used to control the degree of penalty for detour. Represents a node in the path search process, where i is the index of the node, A newly designed heuristic function for evaluating slave nodes To the target location The estimated path cost of is the original heuristic function that only considers distance, Is a node To the target location distance; The robot's current position As a starting point, using the improved A* algorithm, according to the new heuristic function Finding the middle point , , , , ; Calculate the time to move to the target along the adjusted path to see if it can meet the time required for parameter adjustment; If satisfied, this path is the path that meets the parameter adjustment requirements; if not satisfied, adjust the weight coefficient in the heuristic function and search the path again; The circuitousness of the path was assessed by comparing the length of the adjusted path with the length of the initial path.

[0009] Preferably, the specific steps of calculating the initial path moving time are: Get the robot's provided speed v; By formula , calculate along the initial path Time to move to the target.

[0010] Preferably, the comparison of time to obtain the result of whether the route needs to be re-planned or not is specifically: contrast and ,judge whether it is established; If true, it means that the initial path cannot meet the time required for parameter adjustment and the path needs to be replanned. Otherwise, the initial path meets the requirements and no replanning is required.

[0011] Preferably, the specific method of evaluating the circuitousness of the path is: Calculate the detour factor by the formula It is obtained that, among which, the circuitous factor It is an indicator used to quantify the degree of path tortuosity. By comparing the proportional relationship between the adjusted path length and the initial straight shortest path length, it reflects the tortuosity of the path relative to the shortest path. Refers to the adjusted path length, which is the total length of the path obtained after replanning, taking into account the robot's need to meet parameter adjustment requirements. As a benchmark length, it is used to compare with the adjusted path length to evaluate whether the path is detour due to meeting parameter adjustment requirements.

[0012] Preferably, the path planning module further includes: Execute serialized inspection operations along the planned moving path, and trigger the correlation analysis instruction when an abnormality is detected in the current target component to be inspected; According to the preset fault propagation model and component dependency graph, it is determined that all components that are functionally associated with the target component to be detected that currently has problems need to be repaired simultaneously. At the same time, based on the fault history data, real-time operating parameters and system operating status of all components that are functionally associated with the target component to be detected that currently has problems, a decision on exemption from inspection of all components that are functionally associated with the target component to be detected that currently has problems is generated; In response to the detection exemption decision, an updated path is generated by an online replanning algorithm.

[0013] Preferably, the updating path is generated by an online replanning algorithm, specifically: Remove all component positions that are functionally associated with the target component to be inspected that has a problem, from the initial path node sequence; Recalculate the optimal traversal order of the remaining nodes.

[0014] Beneficial effects: Through the path generated by the path planning module, the under-vehicle robot can move under the vehicle in an orderly manner, avoid missing the detection area, improve the detection efficiency, save detection time, and the optimized moving path generated by combining the distribution of the under-vehicle targets to be detected and the parameters can reduce the robot's unnecessary acceleration, deceleration and steering operations, reduce energy consumption, and improve detection efficiency compared to traditional path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the control system of the present invention. DETAILED DESCRIPTION

[0016] like Figure 1As shown: An intelligent control system for an underbody detection robot, comprising: The data acquisition module is configured to collect all-round data information of the target vehicle bottom, and the data information includes at least the position information of the target under the vehicle, the spacing information between different targets under the vehicle, and the contour information of the target under the vehicle; specifically, this module uses a variety of sensors in combination. For example, the laser radar can accurately measure the distance between the target under the vehicle and the robot by emitting a laser beam and receiving the reflected light, and then obtain the position information of the target under the vehicle. When measuring the position, its accuracy can reach the millimeter level. The industrial camera is equipped with a special wide-angle lens to shoot the bottom of the vehicle from different angles. Through the image processing algorithm, the contour information of the target under the vehicle can be extracted, such as the exhaust pipe and suspension parts under the vehicle, which can clearly present their contours. The ultrasonic sensor array is used to measure the spacing information between different targets under the vehicle. It uses the reflection characteristics of ultrasonic waves to quickly and accurately obtain the target spacing data. Actual effect: Taking the detection of the bottom of a car as an example, through the data acquisition module, we can clearly obtain the precise position of each component under the car, such as the engine oil pan, gearbox, etc., as well as the distance between them. At the same time, we can also get the outline of these components, providing a rich and accurate data basis for subsequent analysis.

[0017] The data analysis module is connected to the data acquisition module and is configured to perform: performing in-depth analysis on the acquired data to identify the type, location, shape and size characteristics of each target under the vehicle; Use data analysis algorithms to statistically analyze target distribution patterns and determine the detection parameters corresponding to each target; Specifically, first, use advanced image recognition algorithms and point cloud analysis technology to conduct in-depth analysis of the collected data. For example, by using a deep learning model to identify images taken by an industrial camera, it is possible to accurately determine the type of each target under the vehicle, whether it is a tire, shock absorber or other component. At the same time, combined with the data from the lidar and ultrasonic sensors, the position, shape and size characteristics of the target can be accurately determined. Then, use data analysis algorithms to statistically analyze a large amount of detection data to find out the distribution pattern of targets under the vehicle. For example, count the common distribution locations and occurrence frequencies of underbody components of different vehicle models. Finally, determine the detection parameters corresponding to each target based on the type, location and other characteristics of the target, such as deciding what resolution camera to use and what detection frequency to use for different types of underbody components; Actual effect: Through the operation of this module, we can clearly understand the specific conditions of each component under the vehicle, and formulate targeted testing plans based on the characteristics of the components, greatly improving the accuracy and efficiency of testing.

[0018] The path planning module is connected to the data analysis module and is configured to generate a moving path based on target characteristics and distribution law information and in combination with the kinematic parameters of the robot.

[0019] Specifically, based on the target features and distribution information obtained by the data analysis module, the robot's own kinematic parameters, such as the robot's turning radius and moving speed, are taken into account. Path planning algorithms, such as the A* algorithm, are used to calculate the optimal movement path of the robot under the vehicle. For example, if the targets in certain areas under the vehicle are densely distributed, the path planning module will plan a path that can efficiently cover these areas; if the space under the vehicle is narrow and the robot's turning is restricted, a suitable turning path will also be planned based on its kinematic parameters; Actual effect: Through the path generated by the path planning module, the under-vehicle robot can move under the vehicle in an orderly manner to avoid missing the inspection area. At the same time, it can also reduce unnecessary movement, improve inspection efficiency, and save inspection time. As a further embodiment, the specific steps of generating a moving path based on the under-vehicle target features and target distribution information provided by the data analysis module and in combination with the motion parameters of the under-vehicle detection robot are as follows: A1: Divide the space under the vehicle into multiple detection areas, each area corresponding to the first type of target to be detected or the second type of target to be detected; A2: Execute the following operations on the area where the first type of target to be detected is located: Obtain the detection parameters corresponding to each target in the area; Generate a moving path in the order of monotonically increasing or monotonically decreasing adjustment amplitudes of the detection parameters; Specifically, the structure of the space under the vehicle is complex and contains many different types of components. In order to perform inspections more efficiently, the space under the vehicle needs to be divided into multiple inspection areas. The basis for division is the type of target under the vehicle, that is, each area corresponds to the first type of target to be inspected or the second type of target to be inspected. For example, the area under the vehicle that contains suspension system components (such as shock absorbers, springs, etc.) can be divided into the first type of target area to be inspected, because the inspection focus of such components is on structural integrity, degree of wear, etc., and the inspection parameters are relatively uniform. The area under the vehicle that contains electrical circuits, fuel lines, etc. is divided into the second type of target area to be inspected. The inspection parameters of such components vary greatly. For example, electrical circuits focus on insulation performance testing, and fuel lines focus on sealing testing. Through this division method, the underbody inspection robot can adopt more targeted inspection strategies and mobile path planning in different areas; In the area where the first type of targets to be detected are located, the data analysis module has determined the corresponding detection parameters for each target based on the type, location, shape and size characteristics of the target. For example, for shock absorbers in the suspension system, the detection parameters may include that the camera resolution must reach 1080P to clearly capture fine cracks on the surface, and the detection frequency is once every 5 seconds; for springs, it may be required to use light of a specific wavelength to detect stress concentration areas on the surface, etc. Generate a moving path in the order of monotonically increasing or monotonically decreasing adjustment amplitudes of the detection parameters. Assuming that the detection parameter is the camera resolution, shock absorbers at different positions in the area may require cameras with different resolutions for detection due to different importance or potential failure risks. Starting from the shock absorber with the lowest resolution requirement, the robot moves along a path to the shock absorber positions with gradually increasing resolution requirements. This can avoid the robot from frequently and significantly adjusting the detection parameters and improve the detection efficiency. For example, from the relatively uncritical shock absorber at the edge of the bottom of the vehicle with a resolution requirement of 720P, to the shock absorber close to the axle with a resolution requirement of 1080P, and then to the shock absorber close to the engine with a resolution requirement of 4K, a monotonically increasing detection path is formed.

[0020] A3: Execute the following operations on the area where the second type of target to be detected is located: Calculate the distance between each target in the area; The moving path is generated based on the principle of minimizing the difference in moving distances between adjacent targets.

[0021] Specifically, in the area where the second type of targets to be detected are located, due to the variety of target types and large differences in detection parameters, the distance between the targets in the area must be calculated first. For example, in areas where electrical lines and fuel lines coexist, the distance between each electrical line and the adjacent fuel line must be accurately measured. The data obtained by the lidar and ultrasonic sensors, combined with the spatial coordinate calculation, can obtain accurate spacing information. Assume that the closest point distance between a section of electrical line and the adjacent fuel line is 20 centimeters; The moving path is generated based on the principle of minimizing the difference in moving distances between adjacent targets. This means that when the underbody inspection robot moves from one target to the next, it tries to keep the change in moving distance as small as possible. For example, in the above area, the robot moves from one electrical connection point to the nearest fuel pipe interface, and then to another electrical connection point adjacent to it with the smallest distance change. This can reduce unnecessary acceleration, deceleration and steering operations of the robot, reduce energy consumption, and improve inspection efficiency. If this principle is not followed, the robot may make large jumps in the area, which not only wastes time and energy, but may also miss some potential inspection areas.

[0022] As a further embodiment, the detection area division method specifically includes: Determine the accuracy requirements of the detection parameters for each target to be detected; it should be understood that in the process of underbody detection, different targets to be detected have different requirements for the accuracy of detection parameters due to their different functions, structures and importance in vehicle operation. For example, for the brake line under the vehicle, since it is related to the safety of the vehicle's braking system, any slight leakage or damage may lead to serious consequences, so the accuracy requirements for its detection parameters are extremely high. When detecting the wall thickness of the brake line, it may be necessary to be accurate to 0.01 mm, and the pressure detection accuracy is required to reach ±0.05 MPa. For some decorative parts under the vehicle, such as plastic guard plates, their main function is to protect the underbody parts from mud and water splashing, and the accuracy requirements for detection parameters are relatively low. When detecting their surface flatness, an accuracy of 1 mm can meet the requirements. Through comprehensive consideration of factors such as the function, quality standards and potential risks of each target to be detected under the vehicle, its specific detection parameter accuracy requirements are determined.

[0023] Multiple targets whose detection parameter accuracy requirements are within a preset fixed range are classified as the first type of target area to be detected; it should be understood that the preset fixed range is formulated based on long-term underbody detection experience and industry standards. For some underbody targets with similar functions and quality requirements, their detection parameter accuracy requirements are often concentrated in a relatively stable range. For example, the suspension system components under the vehicle, including shock absorbers, springs, lower swing arms, etc., are mainly responsible for the driving stability and comfort of the vehicle. When detecting the size, shape and mechanical properties of these components, the detection parameter accuracy requirements are relatively fixed. For example, the diameter detection accuracy of the shock absorber piston rod is required to be ±0.05 mm, and the elastic coefficient detection accuracy of the spring is required to be ±5%. Multiple targets such as suspension system components whose detection parameter accuracy requirements are within a preset fixed range are classified as the first type of target area to be detected. The advantage of this division is that when the underbody detection robot performs detection in this area, it can use relatively unified detection equipment parameters and detection processes. For example, industrial cameras with the same resolution and measurement sensors with the same accuracy level can be used to detect targets in the area at a fixed detection frequency to improve detection efficiency and accuracy, and also facilitate the management and analysis of detection data.

[0024] A plurality of targets whose detection parameter accuracy allows for dynamic adjustment are classified as the second type of target area to be detected.

[0025] It should be understood that there are some targets under the vehicle, and the accuracy requirements of their detection parameters will vary depending on the use of the vehicle, the operating environment, and the state changes of the target itself, that is, the accuracy of the detection parameters allows dynamic adjustment. For example, the electrical circuit under the vehicle may have a relatively low detection accuracy requirement for its insulation resistance in the new car state, but as the vehicle is used for a longer time, the electrical circuit may be affected by factors such as aging and wear, and at this time, it is necessary to improve the accuracy of the insulation resistance detection. For another example, the fuel line under the vehicle has a pressure accuracy requirement of ±0.1 MPa for its sealing detection during normal operation, but when the vehicle is driving in special environments such as high temperature and high altitude, the detection pressure accuracy may need to be increased to ±0.05 MPa. Multiple targets such as electrical circuits and fuel lines, whose detection parameter accuracy allows dynamic adjustment, are classified as the second type of target area to be detected. In this area, the undercarriage detection robot needs to have the ability to dynamically adjust the detection parameters according to the real-time situation. For example, when the temperature of the electrical circuit is detected to rise, the accuracy of the insulation resistance detection is automatically improved; when the vehicle is in a special operating environment, the pressure accuracy of the fuel line sealing detection is adjusted in time according to the information fed back by the sensor. Through this dynamic adjustment mechanism, potential problems of these targets in different states can be detected more accurately to ensure the safe operation of the vehicle.

[0026] As a further embodiment, the specific manner in which the path planning module selects the moving path is: When the detection path needs to be extended to adjacent areas: If the next area contains the first type of target to be detected: Get the detection parameters of the target at the end of the current path; Calculate the adjustment range of the target detection parameters in adjacent areas; Select the target with the smallest adjustment amplitude of detection parameters as the next path node; It should be understood that during the underbody inspection process, the decision of the path planning module is crucial for the robot to complete the inspection task efficiently and accurately. When the inspection path needs to be extended to an adjacent area, different path selection strategies will be adopted based on the different target types in the adjacent area. When the underbody inspection robot moves along the planned path, when it reaches the end of the current path, it needs to record the inspection parameters of the target being inspected (assuming it is target A). For example, if target A is a shock absorber in the underbody suspension system, its inspection parameters may include a camera resolution of 1080P for detecting surface cracks, an inspection frequency of once every 3 seconds, and an inspection light intensity of 500Lux. These parameters reflect the current inspection status and the inspection requirements for the target; There are multiple first-class targets to be detected in the adjacent area. For each target, the amplitude of the adjustment from the detection parameters of the target at the end of the current path to the detection parameters required for the target must be calculated. Assume that there are targets B and C in the adjacent area. Target B is also a shock absorber, but due to the importance and potential risks of its location, it may require a higher-resolution camera for detection. For example, the resolution needs to be increased to 4K, the detection frequency is changed to once every 2 seconds, and the light intensity is adjusted to 600Lux. Then the adjustment amplitude of the detection parameters from target A to target B is calculated as follows: camera resolution adjustment amplitude = |(4K-1080P) / 1080P|×100% (here the resolution needs to be unified for calculation), detection frequency adjustment amplitude = |(3-2) / 3|×100%, light intensity adjustment amplitude = |(600-500) / 500|×100%, and the adjustment amplitudes of these parameters are combined to obtain an overall adjustment amplitude value. Similarly, calculate the adjustment amplitude of the detection parameters from target A to target C; By comparing the adjustment range of the detection parameters of each target in the adjacent area, the target with the smallest adjustment range is selected as the next path node. The reason for this is that a small adjustment range of the detection parameters means that when the robot switches the detection target, it does not need to make large parameter changes to the detection equipment, which reduces the equipment adjustment time and the probability of error, and can complete the detection task more efficiently. For example, after calculation, it is found that the adjustment range of the detection parameters of target C is the smallest, then the robot will move to the location of target C, use target C as the next path node, and continue the detection operation; If the next area contains the second type of target to be detected: Calculate the distance between the end position of the current path and each target in the adjacent area; Select the target with the smallest distance as the next path node.

[0027] It should be understood that in the space under the vehicle, when the robot reaches the end of the current path, it uses devices such as laser radar and ultrasonic sensors to measure the distance between the current position and each second type of target to be detected in the adjacent area. For example, the end of the current path is located near the electrical circuit under the vehicle, and the adjacent area contains multiple targets such as fuel line joints. The sensor measures that the distance between the current position and fuel line joint 1 is 30 cm, the distance to fuel line joint 2 is 45 cm, the distance to electrical connection point 3 is 20 cm, etc.; From the calculated distances, select the target with the shortest distance from the end of the current path as the next path node. This is because selecting the target with the shortest distance can reduce unnecessary movement distance and energy consumption during the movement of the robot, and at the same time, it can reach the next detection target faster and improve detection efficiency. For example, in the above example, the distance between the current position and electrical connection point 3 is the shortest, so the robot will move to electrical connection point 3 and use it as the next path node to carry out detection of the target.

[0028] As a further embodiment, the path planning module is further used to re-evaluate the path according to the precise parameters required by the current target, specifically: Get the initial path, which is the current position of the detection robot , and use this as the starting point and the target location As the end point, plan a straight line shortest path , its length ; According to the precise parameters required for the current goal provided by the data analysis module, the formula , get the time required for parameter adjustment ,in, Indicates the current detection angle of the robot. Represents the optimal detection angle required to complete high-precision detection of the current target. Refers to the adjustment speed of the robot's detection angle, that is, the degree to which the robot can change the detection angle per unit time; Calculate the initial path moving time; Compare the times to determine whether rerouting is necessary or not; Introducing new heuristic functions for re-planning routes , in the original heuristic function that only considers distance On the basis of ,in, It is used to measure the degree of circuitousness of the path, and to measure the To Node The circuitousness of this path, is the weight coefficient, which is used to control the degree of penalty for detour. Represents a node in the path search process, where i is the index of the node, A newly designed heuristic function for evaluating slave nodes To the target location The estimated path cost of is the original heuristic function that only considers distance, Is a node To the target location The distance between By formula ,in, Indicates starting point go through , , , , To the current node The sum of the actual path lengths, that is, the sum of the distances between adjacent nodes on each segment of the path, This ratio reflects the length multiple of the current path relative to the initial straight shortest path. When this ratio is 1, it means that the current path has no detours and is the straight shortest path; when the ratio is greater than 1, the larger the part greater than 1, the more tortuous the path is. The degree of circuitousness of the path can be quantified and added to the heuristic function as a circuitous penalty term to penalize the circuitous path. By jointly acting on the heuristic function through these parameters, the improved A* algorithm can minimize the circuitousness of the path while meeting the parameter adjustment requirements when searching for the path, and find a path with better overall performance.

[0029] It should be further explained that in the current formula, i represents the index of the node currently being evaluated in the path node sequence. The path planning process starts from the starting point Start searching for expansion nodes step by step, and when you find a specific node When , the expression is used to calculate the value from the starting point To the current node The degree of circuity of this path. As the search algorithm traverses different nodes, the value of i will change accordingly, so that the circuity of the path at different nodes can be dynamically evaluated; Example: When i = 3, it means that the go through , arrive The circuitousness of this section of the path.

[0030] In the current formula, j represents the loop variable used for sum calculation. To the current node When the sum of the path lengths is calculated, each node index from 0 to i−1 is traversed through j to accumulate the distance between each adjacent node .

[0031] It needs to be further explained that The value of is determined as follows: 1. Set the weight coefficient based on your in-depth understanding of the robot's operating environment and task requirements and past experience. If you have extensive practical experience in this type of robot task and path planning, and understand the relative importance of path detours and parameter adjustments in specific scenarios, you can set the weight coefficient based on this. The value of 2. Try different value, observe the path planning results, and determine the optimal value based on the preset evaluation indicators, etc.

[0032] When replanning the path, a new heuristic function H is designed, which adds a detour penalty term based on the distance factor. This makes the path planning not only focus on the direct distance from the current point to the target point, but also take into account the degree of detour of the path. The penalty for detours can be flexibly controlled to guide the search algorithm to find a path that can meet the parameter adjustment time requirements without being too detour, thus balancing the path efficiency and parameter adjustment requirements. By rationally planning the path and reducing unnecessary detours, the total path length of the robot to reach the target is shortened, thus saving running time and energy consumption. At the same time, frequent parameter adjustments or inadequate parameter adjustments caused by unreasonable paths are avoided, further improving the overall efficiency of the robot in completing tasks.

[0033] The robot's current position As a starting point, using the improved A* algorithm, according to the new heuristic function Finding the middle point , , , , ; It should be noted that when searching, the cost of expanding from the current point to the adjacent point is considered. This cost includes the actual moving distance and the cost to the target point estimated by the heuristic function (including the detour penalty term). After continuously expanding and evaluating nodes, an adjusted path is formed . Calculate the time to move to the target along the adjusted path to see if it can meet the time required for parameter adjustment; If it is satisfied, this path is the path that meets the parameter adjustment requirements; if it is not satisfied, adjust the weight coefficient in the heuristic function and search the path again; it should be noted that the adjusted path length , Re-planning the route A series of nodes on the network, i is the index of these nodes, i=0 corresponds to is the starting position of the robot. As i increases from 0 to n-1, Represent different intermediate points on the path, express The next adjacent node of . By calculating each pair of adjacent nodes and The distance between , we can get the length of each small segment on the path; Representation Node and the next adjacent node Usually, this distance can be calculated based on the coordinate system of the robot's space using the corresponding distance formula.

[0034] Furthermore, the time to move to the target along the adjusted path is calculated to see whether the time required for parameter adjustment can be met. Specifically, the time required to move to the target along the adjusted path is calculated. Time to move to target , judge again Is it true?

[0035] By comparing the length of the adjusted path with the initial path, the degree of tortuosity of the path is evaluated. It should be noted that if R is too large, it indicates excessive tortuosity. The heuristic function should be adjusted or the parameter adjustment method should be reconsidered to reduce the path tortuosity and improve the detection efficiency while meeting the parameter adjustment requirements.

[0036] It should be understood that traditional path planning usually focuses on basic goals such as shortest distance and obstacle avoidance. The present invention introduces the factor of time and space required for parameter adjustment to construct a new path planning logic. For example, by analyzing the time required for adjusting parameters such as the detection angle and comparing it with the time of moving along the path, it is decided whether to re-plan the path. This method of associating parameter adjustment with path movement time helps to plan the path more reasonably; The path planning module can reasonably re-evaluate the path based on the precise parameters required for the target, ensuring that the robot has enough time and space to adjust the parameters to the optimal state when approaching the target to meet high-precision detection requirements.

[0037] As a further embodiment, the specific steps of calculating the initial path moving time are: Get the robot's provided speed v; By formula , calculate along the initial path Time to move to the target.

[0038] It should be understood that the above formula is used to obtain the The time to move to the target is used to facilitate subsequent comparative calculations and to plan the path.

[0039] As a further embodiment, the time is compared to obtain the result of whether the route needs to be re-planned or not: contrast and ,judge whether it is established; If true, it means that the initial path cannot meet the time required for parameter adjustment and the path needs to be replanned. Otherwise, the initial path meets the requirements and no replanning is required.

[0040] It should be understood that the judgment formula can be used to determine whether further route planning is required and to plan the optimal route.

[0041] As a further embodiment, the specific method of evaluating the circuitousness of the path is: Calculate the detour factor by the formula It is obtained that, among which, the circuitous factor It is an indicator used to quantify the degree of path tortuosity. By comparing the proportional relationship between the adjusted path length and the initial straight shortest path length, it reflects the tortuosity of the path relative to the shortest path. Refers to the adjusted path length, which is the total length of the path obtained after replanning, taking into account the robot's need to meet parameter adjustment requirements. As a benchmark length, it is used to compare with the adjusted path length to evaluate whether the path is detour due to meeting parameter adjustment requirements.

[0042] It should be noted that The closer the value is to 1, the closer the path is to the shortest straight path and the less circuitous it is; The larger the value, the longer the path is relative to the initial shortest path and the more circuitous it is.

[0043] It should be understood that in the above description, the time required for parameter adjustment is accurately calculated by analyzing the parameter adjustment requirements, such as the adjustment of the detection angle. . Compare it with the time it takes to move along the initial path Compare and judge whether the initial path meets the parameter adjustment requirements. If not, re-plan the path, which ensures that the robot has enough time to adjust the parameters to the optimal state before reaching the target, thereby meeting the strict requirements of high-precision detection on parameters and improving the accuracy and reliability of the detection results; In actual detection tasks, different targets may require different detection parameters, and the accuracy of the parameters is required to be high. This method can dynamically plan the path according to the specific parameter requirements of each target, so that the robot can flexibly respond to various complex detection task scenarios and improve the robot's adaptability in diverse working environments.

[0044] As a further embodiment, the path planning module further includes: Execute serialized inspection operations along the planned moving path, and trigger the correlation analysis instruction when an abnormality is detected in the current target component to be inspected; According to the preset fault propagation model and component dependency graph, it is determined that all components that are functionally associated with the target component to be detected that currently has problems need to be repaired simultaneously. At the same time, based on the fault history data, real-time operating parameters and system operating status of all components that are functionally associated with the target component to be detected that currently has problems, a decision on exemption from inspection of all components that are functionally associated with the target component to be detected that currently has problems is generated; In response to the detection exemption decision, an updated path is generated through an online replanning algorithm.

[0045] Specifically, the underbody inspection robot performs serial inspections on the target components under the vehicle according to a pre-planned moving path. During the inspection process, the robot uses various sensors and inspection equipment to collect data on the target components in real time. For example, when inspecting the shock absorber of the underbody suspension system, its working status is determined by measuring parameters such as the stroke and damping force of the shock absorber. Once an abnormality is detected in the current target component to be inspected, such as the damping force of the shock absorber exceeds the normal range, the robot will immediately trigger the associated analysis instruction. This trigger mechanism is like an "alarm switch". When the detection data deviates from the preset normal range, the switch is turned on, triggering a series of subsequent operations; When the correlation analysis instruction is triggered, the system will analyze according to the preset fault propagation model and component dependency map. The fault propagation model is constructed based on a large amount of vehicle fault data and principles such as mechanics and electricity. It describes the propagation rules between faults of different components. The component dependency map intuitively shows the functional correlation between the various components under the vehicle. For example, the shock absorber, spring, lower arm and other components together constitute the suspension system, and they are functionally interdependent. Taking the shock absorber abnormality as an example, the fault propagation model can determine that the shock absorber failure may cause uneven force on the spring, thereby affecting the working state of the lower arm. According to the component dependency map, all components that are functionally associated with the shock absorber, such as springs, lower arms, steering knuckles, etc., can be clearly identified. The system determines that these components need to be repaired simultaneously, because the failure of one component often affects other components associated with it. Timely maintenance of related components can avoid the occurrence of potential faults and ensure the overall performance of the vehicle; After determining the associated components that need to be repaired simultaneously, the system will generate a detection exemption decision based on the fault history data, real-time operating parameters and system operating status of these components. The fault history data records the type, time, frequency and other information of each associated component's past faults. By analyzing these data, the failure tendency of the component can be understood. The real-time operating parameters reflect the current operating status of the vehicle, such as vehicle speed, engine speed, vehicle load, etc. These parameters will affect the working conditions of the components. The system operating status includes the working status of the detection system itself, such as the accuracy of the sensor, the stability of data transmission, etc. For example, for a spring associated with a shock absorber, if its fault history data shows that there are few faults, and the current real-time operating parameters indicate that the vehicle is running smoothly, the spring is under normal force, and the detection system is in good operating condition, after comprehensive evaluation, the system may generate a detection exemption decision for the spring, that is, it is considered that detailed inspection can be temporarily omitted under the current circumstances to improve detection efficiency. However, if the fault history data of an associated component shows frequent faults, and the current real-time operating parameters indicate that its working conditions are relatively poor, then the system will not grant a detection exemption; After the inspection exemption decision is made, the path planning module will respond to this decision and generate an updated path through the online replanning algorithm. The online replanning algorithm takes into account factors such as the location of the exempted components, the distribution of the remaining components to be inspected, and the kinematic parameters of the robot. Assuming that an associated component (such as a spring) is exempted from inspection, and the originally planned path includes an inspection point for the spring, the online replanning algorithm will automatically avoid this inspection point and recalculate a more efficient path so that the robot can continue to inspect other components that are not exempted from inspection. For example, the algorithm may plan a path from the current position directly to the next non-exempt and closest component to be inspected, while ensuring that the path meets the robot's motion restrictions, such as turning radius, moving speed, and other requirements. By generating an updated path, the underbody inspection robot can quickly adjust the inspection strategy after discovering component anomalies and making inspection exemption decisions, and continue to efficiently complete the underbody inspection task, thereby improving the flexibility and adaptability of the entire inspection process.

[0046] As a further embodiment, an update path is generated by an online replanning algorithm, specifically: Remove all component positions that are functionally associated with the target component to be inspected that has a problem, from the initial path node sequence; Recalculate the optimal traversal order of the remaining nodes.

[0047] It should be understood that during the inspection process, once the underbody inspection robot has determined all the components that are functionally associated with the target component to be inspected that currently has a problem, the first step in path replanning is to remove the positions of these associated components from the initial path node sequence. For example, the initial path node sequence is planned in sequence according to the layout of the components under the vehicle. Assuming that an abnormality is detected in the shock absorber in the underbody suspension system, according to the fault propagation model and the component dependency graph, the components that are functionally associated with it are determined to be springs, lower control arms, steering knuckles, etc. These components correspond to their own detection nodes in the initial path. When performing path replanning, the system will delete the position information of associated components such as springs, lower control arms, and steering knuckles in the initial path node sequence. This operation is like erasing the mark of a specific location on a map, so that subsequent path planning no longer involves the positions of these components that have been determined to require synchronous maintenance and may be exempted from inspection, thereby avoiding useless work by the robot and improving inspection efficiency; After removing the associated component positions, the remaining nodes constitute a new set of components to be inspected. At this point, the online replanning algorithm needs to recalculate the optimal traversal order of these remaining nodes, replan the route based on the above planning method, and finally determine the optimal traversal order of the remaining nodes, and plan a new and efficient inspection path for the underbody inspection robot, so that it can continue to complete the underbody inspection task while ensuring the comprehensiveness and accuracy of the inspection.

[0048] The above are only preferred implementations of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical staff in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

Claims

1. An intelligent control system for an underbody inspection robot, characterized in that: include: A data acquisition module is configured to collect all-round data information of the target vehicle bottom, wherein the data information at least includes position information of the target under the vehicle bottom, spacing information between different targets under the vehicle bottom, and contour information of the target under the vehicle bottom; A data analysis module, connected to the data acquisition module, configured to perform: performing in-depth analysis on the acquired data to identify the type, location, shape and size characteristics of each target under the vehicle; Use data analysis algorithms to statistically analyze target distribution patterns and determine the detection parameters corresponding to each target; The path planning module is connected to the data analysis module and is configured to generate a moving path based on target characteristics and distribution law information and in combination with the kinematic parameters of the robot.

2. The intelligent control system of the vehicle underbody inspection robot according to claim 1, characterized in that: The specific steps of generating a moving path based on the vehicle bottom target features and target distribution information provided by the data analysis module and combining the motion parameters of the vehicle bottom detection robot are as follows: A1: Divide the space under the vehicle into multiple detection areas, each area corresponding to the first type of target to be detected or the second type of target to be detected; A2: Execute the following operations on the area where the first type of target to be detected is located: Obtain the detection parameters corresponding to each target in the area; Generate a moving path in the order of monotonically increasing or monotonically decreasing adjustment amplitudes of the detection parameters; A3: Execute the following operations on the area where the second type of target to be detected is located: Calculate the distance between each target in the area; The moving path is generated based on the principle of minimizing the difference in moving distances between adjacent targets.

3. The intelligent control system of the vehicle underbody inspection robot according to claim 2, characterized in that: The detection area division method specifically includes: Determine the detection parameter accuracy requirements for each target to be detected; Classifying multiple targets whose detection parameter accuracy requirements are within a preset fixed range as a first type of target area to be detected; A plurality of targets whose detection parameter accuracy allows for dynamic adjustment are classified as the second type of target area to be detected.

4. The intelligent control system of the vehicle underbody inspection robot according to claim 3, characterized in that: The specific method of selecting the moving path by the path planning module is: When the detection path needs to be extended to adjacent areas: If the next area contains the first type of target to be detected: Get the detection parameters of the target at the end of the current path; Calculate the adjustment range of the target detection parameters in adjacent areas; Select the target with the smallest adjustment amplitude of detection parameters as the next path node; If the next area contains the second type of target to be detected: Calculate the distance between the end position of the current path and each target in the adjacent area; Select the target with the smallest distance as the next path node.

5. The intelligent control system of the vehicle underbody inspection robot according to claim 1, characterized in that: The path planning module is also used to re-evaluate the path according to the precise parameters required by the current goal, specifically: Get the initial path, which is the current position of the detection robot , and use this as the starting point and the target location As the end point, plan a straight line shortest path , its length ; According to the precise parameters required for the current goal provided by the data analysis module, the formula , get the time required for parameter adjustment ,in, Indicates the current detection angle of the robot. Represents the optimal detection angle required to complete high-precision detection of the current target. Refers to the adjustment speed of the robot's detection angle, that is, the degree to which the robot can change the detection angle per unit time; Calculate the initial path moving time; Compare the times to determine whether rerouting is necessary or not; Introducing new heuristic functions for re-planning routes , in the original heuristic function that only considers distance On the basis of, add the detour penalty term, get ,in, It is used to measure the degree of circuitousness of the path, and to measure the To Node The circuitousness of this path, is the weight coefficient, which is used to control the degree of penalty for detour. Represents a node in the path search process, where i is the index of the node, A newly designed heuristic function for evaluating slave nodes To the target location The estimated path cost is is the original heuristic function that only considers distance, Is a node To the target location distance; The robot's current position As a starting point, using the improved A* algorithm, according to the new heuristic function Finding the middle point , , , , ; Calculate the time to move to the target along the adjusted path to see if it can meet the time required for parameter adjustment; If satisfied, this path is the path that meets the parameter adjustment requirements; if not satisfied, adjust the weight coefficient in the heuristic function and search the path again; The circuitousness of the path was assessed by comparing the length of the adjusted path with the length of the initial path.

6. The intelligent control system of the vehicle underbody inspection robot according to claim 5, characterized in that: The specific steps of calculating the initial path moving time are: Get the robot's provided speed v; By formula , calculate along the initial path Time to move to the target.

7. The intelligent control system of the vehicle underbody inspection robot according to claim 5, characterized in that: The comparison of the time to obtain the result of whether the route needs to be re-planned or not is specifically: contrast and ,judge whether it is established; If true, it means that the initial path cannot meet the time required for parameter adjustment and the path needs to be replanned. Otherwise, the initial path meets the requirements and no replanning is required.

8. The intelligent control system of the vehicle underbody inspection robot according to claim 7, characterized in that: The specific method of evaluating the circuitousness of the path is: Calculate the detour factor by the formula It is obtained that, among which, the circuitous factor It is an indicator used to quantify the degree of path tortuosity. By comparing the proportional relationship between the adjusted path length and the initial straight shortest path length, it reflects the tortuosity of the path relative to the shortest path. Refers to the adjusted path length, which is the total length of the path obtained after replanning, taking into account the robot's need to meet parameter adjustment requirements. As a benchmark length, it is used to compare with the adjusted path length to evaluate whether the path is detour due to meeting parameter adjustment requirements.

9. The intelligent control system of the vehicle underbody inspection robot according to claim 8, characterized in that: The path planning module also includes: Execute serialized inspection operations along the planned moving path, and trigger the correlation analysis instruction when an abnormality is detected in the current target component to be inspected; According to the preset fault propagation model and component dependency graph, it is determined that all components that are functionally associated with the target component to be detected that currently has problems need to be repaired simultaneously. At the same time, based on the fault history data, real-time operating parameters and system operating status of all components that are functionally associated with the target component to be detected that currently has problems, a decision on exemption from inspection of all components that are functionally associated with the target component to be detected that currently has problems is generated; In response to the detection exemption decision, an updated path is generated by an online replanning algorithm.

10. The intelligent control system of the vehicle underbody inspection robot according to claim 9, characterized in that: The update path is generated by the online replanning algorithm, specifically: Remove all component positions that are functionally associated with the target component to be inspected that has a problem, from the initial path node sequence; Recalculate the optimal traversal order of the remaining nodes.

Images