Intelligent bridge inspection vehicle obstacle avoidance sensing method and device based on laser radar

Abstract

The invention relates to the technical field of intelligent control, in particular to an intelligent bridge inspection vehicle obstacle avoidance sensing method and device based on a laser radar, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining structure information of a target bridge, and determining a detection area based on the structure information; acquiring environment information of the target bridge, wherein the environment information comprises obstacle information in the detection area; determining an obstacle avoidance path based on the environment information, wherein the obstacle avoidance path is a moving path for maintaining a detection range of a target device in advancing to cover the detection area and enabling a facility structure of the target device to avoid the obstacle; and controlling the target equipment to complete sensing detection of the target bridge based on the obstacle avoidance path. By adopting the method, the safety and efficiency of bridge detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, device, computer equipment, storage medium and computer program product. Background Art

[0002] A bridge inspection vehicle is a special vehicle used to inspect and maintain engineering structures such as bridges and tunnels. Bridge inspection vehicles are usually equipped with various testing equipment to evaluate and test the structure, materials and status of bridges.

[0003] In the related technologies, traditional bridge inspection often requires inspectors to directly approach the bridge structure for observation and measurement. However, the current bridge inspection method not only has the risk of high-altitude operations, but may also cause accidents due to aging and damage of the bridge structure. Summary of the invention

[0004] Based on this, it is necessary to provide a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, device, computer equipment, computer-readable storage medium and computer program product to improve the safety and efficiency of bridge inspection in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method. The method comprises:

[0006] Acquiring structural information of a target bridge, and determining a detection area based on the structural information;

[0007] Acquiring environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area;

[0008] Determine an obstacle avoidance path based on the environmental information, the obstacle avoidance path being a moving path that maintains the detection range of the target device while moving to cover the detection area and the facility structure of the target device avoids the obstacle;

[0009] The target device is controlled based on the obstacle avoidance path to complete perception detection of the target bridge.

[0010] In one embodiment, the acquiring of environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area, comprises:

[0011] Acquire point cloud data of the target bridge, wherein the point cloud data includes three-dimensional geometric information of the surface of the target bridge;

[0012] The point cloud data obtained from different coordinate systems are registered to obtain registered multi-radar point cloud data.

[0013] In one embodiment, the acquiring of environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area, comprises:

[0014] Acquire the multi-radar point cloud data, and pre-process the multi-radar point cloud data;

[0015] Performing cluster analysis on the preprocessed multi-radar point cloud data to obtain a plurality of point cloud clusters, wherein the point cloud clusters are associated with the obstacles;

[0016] A bounding volume model of an associated target obstacle is determined based on the point cloud cluster.

[0017] In one embodiment, the method further comprises:

[0018] Acquire structural information of the target device, wherein the structural information includes geometric properties of a main body and components of the target device;

[0019] constructing a geometric model corresponding to the target device based on the geometric attributes;

[0020] Based on the preset distance value and the geometric model, the detection area corresponding to the target device is calculated.

[0021] In one of the embodiments, controlling the target device to complete the sensing detection of the target bridge based on the obstacle avoidance path includes:

[0022] Obtaining dynamic information of the target obstacle, wherein the dynamic information includes position, speed and direction;

[0023] Predicting the motion state of the target obstacle based on a preset filtering algorithm, the motion state including position, speed, acceleration and angular velocity;

[0024] Obtaining a motion trajectory prediction result of the target obstacle based on the motion state and the historical trajectory;

[0025] The obstacle avoidance path is adjusted based on the motion trajectory prediction result.

[0026] In one embodiment, the calculating the detection area corresponding to the target device based on the preset distance value and the geometric model includes:

[0027] Based on a plurality of preset sets of distance values, the detection area is divided into a plurality of different partitions, and a plurality of the partitions correspond to a plurality of warning levels;

[0028] The motion state of the target device is adjusted based on the partition corresponding to the position state quantity of the target obstacle.

[0029] In a second aspect, the present application also provides an obstacle avoidance sensing device for an intelligent bridge inspection vehicle based on a laser radar. The device comprises:

[0030] A structural information module, used to obtain structural information of a target bridge and determine a detection area based on the structural information;

[0031] An environmental information module, used to obtain environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area;

[0032] An obstacle avoidance path module, configured to determine an obstacle avoidance path based on the environmental information, wherein the obstacle avoidance path is a moving path that maintains the detection range of the target device while it is moving to cover the detection area and the facility structure of the target device avoids the obstacle;

[0033] A perception detection module is used to control the target device to complete perception detection of the target bridge based on the obstacle avoidance path.

[0034] In one embodiment, the environment information module includes:

[0035] A point cloud data module, used to obtain point cloud data of the target bridge, wherein the point cloud data includes three-dimensional geometric information of the surface of the target bridge;

[0036] The multi-radar registration module is used to register the point cloud data obtained from different coordinate systems to obtain the registered multi-radar point cloud data.

[0037] In one embodiment, the environment information module includes:

[0038] A preprocessing module, used for acquiring the multi-radar point cloud data and preprocessing the multi-radar point cloud data;

[0039] A cluster analysis module, used for performing cluster analysis on the preprocessed multi-radar point cloud data to obtain a plurality of point cloud clusters, wherein the point cloud clusters are associated with the obstacles;

[0040] The bounding volume model module is used to determine the bounding volume model of the associated target obstacle based on the point cloud cluster.

[0041] In one embodiment, the device further comprises:

[0042] A structure information module, used to obtain the structure information of the target device, wherein the structure information includes geometric properties of the main body and components of the target device;

[0043] A geometric model module, used for constructing a geometric model corresponding to the target device based on the geometric attributes;

[0044] The detection area module is used to calculate the detection area corresponding to the target device based on a preset distance value and the geometric model.

[0045] In one embodiment, the perception detection module includes:

[0046] A dynamic information module is used to obtain dynamic information of the target obstacle, wherein the dynamic information includes position, speed and direction;

[0047] A motion prediction module, used to predict the motion state of the target obstacle based on a preset filtering algorithm, wherein the motion state includes position, speed, acceleration and angular velocity;

[0048] A trajectory prediction module, used to obtain a motion trajectory prediction result of the target obstacle based on the motion state and the historical trajectory;

[0049] A path adjustment module is used to adjust the obstacle avoidance path based on the motion trajectory prediction result.

[0050] In one embodiment, the geometric model module includes:

[0051] A detection partition module, used for dividing the detection area into a plurality of different partitions based on a plurality of preset distance value groups, wherein the plurality of partitions correspond to a plurality of warning levels;

[0052] The state adjustment module is used to adjust the motion state of the target device based on the partition corresponding to the position state quantity of the target obstacle.

[0053] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps in the obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar as described in any one of the embodiments in the first aspect when executing the computer program.

[0054] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar as described in any one of the embodiments in the first aspect.

[0055] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the steps in the obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar as described in any one of the embodiments in the first aspect.

[0056] The above-mentioned laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, device, computer equipment, storage medium and computer program product can achieve the beneficial effects of the technical problems in the corresponding background technology by deducing the technical features in the claims:

[0057] The present application provides an obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar, including obtaining structural information of a target bridge, determining a detection area based on the structural information; obtaining environmental information of the target bridge, the environmental information including obstacle information in the detection area; determining an obstacle avoidance path based on the environmental information, the obstacle avoidance path is a moving path that maintains the detection range of the target device during movement to cover the detection area, and the facility structure of the target device avoids the obstacle; and controlling the target device based on the obstacle avoidance path to complete the perception detection of the target bridge. In implementation, by obtaining the structural information of the target bridge, the detection area for inspection and detection of the target bridge can be determined according to the structural information, and the intelligent bridge inspection vehicle can be intelligently guided to perform comprehensive detection according to the detection area. Subsequently, the environmental information of the target bridge is obtained, and the obstacle information existing in the detection area can be parsed through the environmental information. In this way, the obstacle avoidance path can be determined according to the obstacle information, and the obstacle avoidance path can maintain the detection range of the target device during movement to cover the detection area, and the facility structure of the target device avoids obstacles. Ultimately, controlling the intelligent bridge inspection vehicle based on the obstacle avoidance path helps overcome the high risk and low efficiency of manual inspection, improves the inspection efficiency and personnel safety of bridge inspection work, and shortens the inspection cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a diagram of an application environment of an obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar in one embodiment;

[0059] Figure 2 It is a schematic diagram of a first process of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in one embodiment;

[0060] Figure 3 A second flow chart of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in another embodiment;

[0061] Figure 4 A third flow chart of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in another embodiment;

[0062] Figure 5 A fourth flow chart of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in another embodiment;

[0063] Figure 6A fifth flow chart of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in another embodiment;

[0064] Figure 7 A sixth flow chart of a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method in another embodiment;

[0065] Figure 8 It is a structural block diagram of an obstacle avoidance sensing device of an intelligent bridge inspection vehicle based on a laser radar in one embodiment;

[0066] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] A bridge inspection vehicle is a special vehicle used to inspect and maintain engineering structures such as bridges and tunnels. Bridge inspection vehicles are usually equipped with various testing equipment to evaluate and test the structure, materials and status of bridges.

[0069] In the related technologies, traditional bridge inspection often requires inspectors to directly approach the bridge structure for observation and measurement. However, the current bridge inspection method not only has the risk of high-altitude operations, but may also cause accidents due to aging and damage of the bridge structure.

[0070] Based on the above problems, the embodiments of the present application provide a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, device, computer equipment, storage medium and computer program product.

[0071] The embodiment of the present application provides a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, which can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The terminal can be set on an intelligent bridge inspection vehicle for implementing bridge inspection tasks, and the intelligent bridge inspection vehicle can also be provided with. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0072] In one embodiment, Figure 2 As shown in the figure, a laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0073] Step 202: Acquire structural information of the target bridge, and determine a detection area based on the structural information.

[0074] Step 204: Acquire environmental information of the target bridge, where the environmental information includes obstacle information in the detection area.

[0075] Step 206: Determine an obstacle avoidance path based on the environmental information, where the obstacle avoidance path is a moving path that maintains the detection range of the target device while it is moving and covers the detection area, and the facility structure of the target device avoids the obstacle.

[0076] Step 208: Control the target device to complete perception detection of the target bridge based on the obstacle avoidance path.

[0077] In the above-mentioned intelligent bridge inspection vehicle obstacle avoidance perception method based on laser radar, reasonable deduction is performed in combination with the technical features in the embodiment, which can achieve the following beneficial effects of solving the technical problems raised in the background technology:

[0078] The present application provides an obstacle avoidance perception method for an intelligent bridge inspection vehicle based on a laser radar, including obtaining structural information of a target bridge, determining a detection area based on the structural information; obtaining environmental information of the target bridge, the environmental information including obstacle information in the detection area; determining an obstacle avoidance path based on the environmental information, the obstacle avoidance path is a moving path that maintains the detection range of the target device during movement to cover the detection area, and the facility structure of the target device avoids the obstacle; and controlling the target device based on the obstacle avoidance path to complete the perception detection of the target bridge. In implementation, by obtaining the structural information of the target bridge, the detection area for inspection and detection of the target bridge can be determined according to the structural information, and the intelligent bridge inspection vehicle can be intelligently guided to perform comprehensive detection according to the detection area. Subsequently, the environmental information of the target bridge is obtained, and the obstacle information existing in the detection area can be parsed through the environmental information. In this way, the obstacle avoidance path can be determined according to the obstacle information, and the obstacle avoidance path can maintain the detection range of the target device during movement to cover the detection area, and the facility structure of the target device avoids obstacles. Ultimately, controlling the intelligent bridge inspection vehicle based on the obstacle avoidance path helps overcome the high risk and low efficiency of manual inspection, improves the inspection efficiency and personnel safety of bridge inspection work, and shortens the inspection cycle.

[0079] In one embodiment, the Figure 3 As shown, step 204 includes:

[0080] Step 302: Acquire point cloud data of the target bridge, wherein the point cloud data includes three-dimensional geometric information of the surface of the target bridge.

[0081] Step 304: registering the point cloud data obtained from different coordinate systems to obtain registered multi-radar point cloud data.

[0082] For example, the intelligent bridge inspection vehicle uses sensors such as laser radar to scan the bridge structure from different angles and positions to obtain a large amount of point cloud data, which contains the three-dimensional geometric information of the bridge surface.

[0083] Since the sensor acquires point cloud data from different positions or perspectives, these data may be initially located in different coordinate systems and have different postures. The point cloud registration module transforms the point cloud data into a unified coordinate system by solving the transformation matrix (including the rotation matrix R and the translation matrix T), thus realizing the integration and alignment of the point cloud data.

[0084] The specific process is as follows:

[0085] Obtain bridge point cloud data and extract the point cloud set used to calculate the yaw angle.

[0086] Calculate the coordinates of the center point of the set in step 1, and recalculate the coordinate values ​​of the point cloud set with this coordinate as the origin.

[0087] Calculate the heading angle of each point in the point cloud collection to Divide the angle interval into sectors.

[0088] Calculate the point cloud distance value in each sector area and select the point with the largest distance value as the edge point.

[0089] According to step 4, a set of edge contour points is obtained, the slope of two adjacent edge points is calculated, and the inverse tangent value is calculated as the yaw angle.

[0090] Collect the yaw angles calculated in step 5 to The interval is calculated by histogram, and the bin with the largest proportion is taken as the maximum probability yaw angle.

[0091] Considering the stability of the estimated angle, according to the formula Calculate the final yaw angle, where The number of point clouds in the bin representing the maximum probability yaw angle; Indicates the number of point clouds in the angle bin before the maximum probability yaw angle; Indicates the number of point clouds in an angle bin after the maximum probability yaw angle; Represents the total number of three bin point clouds; represents the maximum probability yaw angle; The previous angle representing the maximum probability yaw angle; The latter angle representing the maximum probability yaw angle.

[0092] According to step 7, the initial rough external parameters of the target radar and the registration radar are calculated, and the precise external parameters between the two frames of point clouds are calculated using the NDT or ICP variant algorithm, ultimately achieving multi-radar point cloud registration.

[0093] In this embodiment, during the perception and detection of obstacle information, the point cloud data is registered and aligned, which helps to convert the point cloud data of different angles and postures obtained from multiple different radars into a unified coordinate system, thereby realizing the integration and alignment of the point cloud data.

[0094] In one embodiment, the Figure 4 As shown, step 204 includes:

[0095] Step 402: Acquire the multi-radar point cloud data, and pre-process the multi-radar point cloud data.

[0096] Step 404: performing cluster analysis on the preprocessed multi-radar point cloud data to obtain a plurality of point cloud clusters, wherein the point cloud clusters are associated with the obstacles.

[0097] Step 406: Determine a bounding volume model of the associated target obstacle based on the point cloud cluster.

[0098] For example, by carrying a laser radar, obstacles around the bridge can be monitored in real time, including information such as the type, location, and size of the obstacles. These obstacles may include fallen objects on the bridge, construction equipment, illegally parked vehicles, etc., which pose a threat to the driving safety of the bridge inspection vehicle.

[0099] The specific process is as follows:

[0100] The point cloud data collected by the LiDAR contains noise and needs to be filtered, such as pass-through filtering, voxel grid filtering, statistical filtering, etc., to reduce the amount of data, remove noise points, and smooth the point cloud data.

[0101] Detect the position of bridge piers, use the distance between bridge piers as the interface, and exclude non-interest point cloud data.

[0102] Perform cluster analysis on the preprocessed point cloud data to cluster the point cloud data belonging to the same obstacle into a cluster. Common clustering algorithms include Euclidean clustering, density clustering, superbody clustering, etc. The specific clustering analysis algorithm can be selected according to the clustering requirements, and other algorithms including but not limited to clustering algorithms can also be used to achieve obstacle detection.

[0103] For each clustered cluster, determine a three-dimensional Bounding Box that can enclose it, so as to more intuitively represent the location and shape of the obstacle.

[0104] In this embodiment, in the analysis of obstacle information, preprocessing of multi-radar point cloud data helps to reduce possible interference and noise in the point cloud data, thereby improving the data validity of the point cloud data. Subsequently, cluster analysis of the point cloud data helps to classify the point cloud data corresponding to the same obstacle into groups through cluster analysis. Ultimately, the bounding volume model of the obstacle is determined by the obtained point cloud clusters, which helps to achieve accurate perception of obstacles and improve the safety of bridge inspection vehicle motion control.

[0105] In one embodiment, the Figure 5 As shown, the method also includes:

[0106] Step 502: Acquire structural information of the target device, where the structural information includes geometric properties of the main body and components of the target device.

[0107] Step 504: construct a geometric model corresponding to the target device based on the geometric attributes.

[0108] Step 506: Based on the preset distance value and the geometric model, the detection area corresponding to the target device is obtained by calculation.

[0109] For example, according to the actual situation of the bridge and the inspection requirements, the emergency stop area, deceleration area, driving area and other areas are accurately divided. In this way, the bridge inspection vehicle can carry out detailed scanning and inspection of these areas in a targeted manner, thereby saving inspection time and resources.

[0110] The specific process is as follows:

[0111] 1. According to the plan of the bridge inspection vehicle, divide it into two parts: the main body and the components. Each part is written into the configuration file in a cube structure according to the center point, length, width and height.

[0112] 2. According to the actual on-site environment of the bridge inspection vehicle, optimize the geometric properties of the main body and components in step 1 to ensure the coverage of the sensing area without being interfered by the structure of the facilities at the bottom of the bridge.

[0113] 3. Read the configuration parameters and execute the virtual stitching algorithm. First, load the main body and component structure into the program, divide the geometric contour into upper and lower edge points according to the front view, sort the upper and lower edge points along the y-axis, sort the upper contour points clockwise, and sort the lower contour points counterclockwise, and connect them end to end to form an edge point set.

[0114] 4. Based on the virtual 2D outline of the bridge inspection vehicle in step 4, solve it into a polygonal cube according to its width.

[0115] 5. Set up three zones: emergency stop zone, deceleration zone and driving zone. The distance value of each zone can be solved into the sensing area on both sides of the driving direction of the bridge inspection vehicle.

[0116] 6. Read the direction of motor rotation, determine the direction of travel of the bridge inspection vehicle, traverse each point cloud, and determine whether it is inside the sensing area polygon. Only the point cloud within the virtual contour polygon is used to sense obstacles.

[0117] In this embodiment, the structural information of the target device is obtained to construct a geometric model corresponding to the target device, so that the detection area corresponding to the target device is determined according to the actual shape of the geometric model, which helps to improve the accuracy of detection area identification and thus improve the efficiency of bridge detection.

[0118] In one embodiment, the Figure 6 As shown, step 208 includes:

[0119] Step 602: Acquire dynamic information of the target obstacle, where the dynamic information includes position, speed, and direction.

[0120] Step 604: Predicting the motion state of the target obstacle based on a preset filtering algorithm, where the motion state includes position, speed, acceleration, and angular velocity.

[0121] Among them, the filtering algorithm not only smoothes the noise but also realizes state prediction. Specifically, Kalman filtering or other derivative algorithms based on Kalman filtering can be selected for implementation.

[0122] Step 606: Obtain a motion trajectory prediction result of the target obstacle based on the motion state and the historical trajectory.

[0123] Step 608: Adjust the obstacle avoidance path based on the motion trajectory prediction result.

[0124] For example, during the operation of the bridge inspection vehicle, the tracking and matching module can track the dynamic information of the obstacle, such as the position, speed, and direction, in real time, to ensure a comprehensive understanding of the movement of the obstacle. In addition, the tracking and matching module can be connected to the visualization system to display the operation status of the bridge inspection vehicle in real time, such as position, speed, direction, etc., so that the operator can intuitively understand the current situation of the bridge inspection vehicle.

[0125] The specific process is as follows:

[0126] Based on the contour features of the obstacle's bounding box, data association is performed on obstacle information of multiple consecutive frames to determine whether they belong to the same obstacle.

[0127] Use Kalman filter or other filtering algorithms to estimate the motion state of obstacles, including position, speed, acceleration, angular velocity, etc.

[0128] Based on the current state and historical trajectory of the obstacle, its future motion trajectory is predicted to provide a basis for the vehicle's obstacle avoidance decision.

[0129] In this embodiment, the dynamic information of the target obstacle is obtained and processed through a filtering algorithm to obtain the motion state of the target obstacle. Finally, the motion trajectory of the target obstacle is predicted through the motion state and historical trajectory, so that avoidance design can be carried out in advance, which helps to further improve the safety of intelligent bridge inspection vehicle control.

[0130] In one embodiment, the Figure 7 As shown, step 506 includes:

[0131] Step 702: Based on a plurality of preset groups of distance values, the detection area is divided into a plurality of different partitions, and a plurality of the partitions correspond to a plurality of warning levels.

[0132] Step 704: Adjust the motion state of the target device based on the partition corresponding to the position state quantity of the target obstacle.

[0133] For example, when the intelligent bridge inspection vehicle is performing bridge inspection tasks, it will continuously detect obstacles in the surrounding environment. The obstacle avoidance alarm system can immediately issue an alarm when a potential collision risk is detected, reminding the operator or automatically adjusting the driving path of the bridge inspection vehicle, thereby effectively avoiding the occurrence of collision accidents.

[0134] The specific process is as follows:

[0135] Get the obstacle collection of the tracking and matching module.

[0136] Traverse the bounding box of each obstacle, select its 2D corner points, and determine whether the four corner points are included in the perception area.

[0137] Each obstacle has three status values, which are used to indicate which zone the obstacle is in. The priority of the three zones is as follows: emergency stop zone > deceleration zone > driving zone. If two or more status values ​​of an obstacle are activated, the highest priority alarm will be used.

[0138] In this embodiment, the detection area is divided into multiple partitions with different warning levels, and corresponding motion control is performed according to the different partitions where the obstacles are located, which helps to improve the accuracy of obstacle avoidance control of the intelligent bridge inspection vehicle and improve the safety of bridge inspection work.

[0139] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiment of the present application also provides a laser radar-based intelligent bridge inspection vehicle obstacle avoidance sensing device for realizing the laser radar-based intelligent bridge inspection vehicle obstacle avoidance sensing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the laser radar-based intelligent bridge inspection vehicle obstacle avoidance sensing device provided below can refer to the above limitations on the laser radar-based intelligent bridge inspection vehicle obstacle avoidance sensing method, and will not be repeated here.

[0141] In one embodiment, Figure 8 As shown, an obstacle avoidance sensing device for an intelligent bridge inspection vehicle based on a laser radar is provided, comprising: a structure information module, an environment information module, an obstacle avoidance path module and a sensing detection module, wherein:

[0142] A structural information module, used to obtain structural information of a target bridge and determine a detection area based on the structural information;

[0143] An environmental information module, used to obtain environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area;

[0144] An obstacle avoidance path module, configured to determine an obstacle avoidance path based on the environmental information, wherein the obstacle avoidance path is a moving path that maintains the detection range of the target device while it is moving to cover the detection area and the facility structure of the target device avoids the obstacle;

[0145] A perception detection module is used to control the target device to complete perception detection of the target bridge based on the obstacle avoidance path.

[0146] In one embodiment, the environment information module includes:

[0147] A point cloud data module, used to obtain point cloud data of the target bridge, wherein the point cloud data includes three-dimensional geometric information of the surface of the target bridge;

[0148] The multi-radar registration module is used to register the point cloud data obtained from different coordinate systems to obtain the registered multi-radar point cloud data.

[0149] In one embodiment, the environment information module includes:

[0150] A preprocessing module, used for acquiring the multi-radar point cloud data and preprocessing the multi-radar point cloud data;

[0151] A cluster analysis module, used for performing cluster analysis on the preprocessed multi-radar point cloud data to obtain a plurality of point cloud clusters, wherein the point cloud clusters are associated with the obstacles;

[0152] The bounding volume model module is used to determine the bounding volume model of the associated target obstacle based on the point cloud cluster.

[0153] In one embodiment, the device further comprises:

[0154] A structure information module, used to obtain the structure information of the target device, wherein the structure information includes geometric properties of the main body and components of the target device;

[0155] A geometric model module, used for constructing a geometric model corresponding to the target device based on the geometric attributes;

[0156] The detection area module is used to calculate the detection area corresponding to the target device based on a preset distance value and the geometric model.

[0157] In one embodiment, the perception detection module includes:

[0158] A dynamic information module is used to obtain dynamic information of the target obstacle, wherein the dynamic information includes position, speed and direction;

[0159] A motion prediction module, used to predict the motion state of the target obstacle based on a preset filtering algorithm, wherein the motion state includes position, speed, acceleration and angular velocity;

[0160] A trajectory prediction module, used to obtain a motion trajectory prediction result of the target obstacle based on the motion state and the historical trajectory;

[0161] A path adjustment module is used to adjust the obstacle avoidance path based on the motion trajectory prediction result.

[0162] In one embodiment, the geometric model module includes:

[0163] A detection partition module, used for dividing the detection area into a plurality of different partitions based on a plurality of preset distance value groups, wherein the plurality of partitions correspond to a plurality of warning levels;

[0164] The state adjustment module is used to adjust the motion state of the target device based on the partition corresponding to the position state quantity of the target obstacle.

[0165] Each module in the above-mentioned intelligent bridge inspection vehicle obstacle avoidance sensing device based on laser radar can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

[0166] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for avoiding obstacles for intelligent bridge inspection vehicles based on laser radar is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0167] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0168] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0169] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0170] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0171] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0173] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0174] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A laser radar-based intelligent bridge inspection vehicle obstacle avoidance perception method, characterized in that: The method comprises: Acquiring structural information of a target bridge, and determining a detection area based on the structural information; Acquiring environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area; Determine an obstacle avoidance path based on the environmental information, the obstacle avoidance path being a moving path that maintains the detection range of the target device while moving to cover the detection area and the facility structure of the target device avoids the obstacle; The target device is controlled based on the obstacle avoidance path to complete perception detection of the target bridge.

2. The method according to claim 1, characterized in that The acquiring of the environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area, comprises: Acquire point cloud data of the target bridge, wherein the point cloud data includes three-dimensional geometric information of the surface of the target bridge; The point cloud data obtained from different coordinate systems are registered to obtain registered multi-radar point cloud data.

3. The method according to claim 2, characterized in that The acquiring of the environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area, comprises: Acquire the multi-radar point cloud data, and pre-process the multi-radar point cloud data; Performing cluster analysis on the preprocessed multi-radar point cloud data to obtain a plurality of point cloud clusters, wherein the point cloud clusters are associated with the obstacles; A bounding volume model of an associated target obstacle is determined based on the point cloud cluster.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire structural information of the target device, wherein the structural information includes geometric properties of a main body and components of the target device; constructing a geometric model corresponding to the target device based on the geometric attributes; Based on the preset distance value and the geometric model, the detection area corresponding to the target device is calculated.

5. The method according to any one of claims 1 to 4, characterized in that: The controlling the target device to complete the sensing detection of the target bridge based on the obstacle avoidance path includes: Obtaining dynamic information of the target obstacle, wherein the dynamic information includes position, speed and direction; Predicting the motion state of the target obstacle based on a preset filtering algorithm, the motion state including position, speed, acceleration and angular velocity; Obtaining a motion trajectory prediction result of the target obstacle based on the motion state and the historical trajectory; The obstacle avoidance path is adjusted based on the motion trajectory prediction result.

6. The method according to claim 4, characterized in that The step of calculating the detection area corresponding to the target device based on the preset distance value and the geometric model includes: Based on a plurality of preset sets of distance values, the detection area is divided into a plurality of different partitions, and a plurality of the partitions correspond to a plurality of warning levels; The motion state of the target device is adjusted based on the partition corresponding to the position state quantity of the target obstacle.

7. An intelligent bridge inspection vehicle obstacle avoidance sensing device based on laser radar, characterized in that: The device comprises: A structural information module, used to obtain structural information of a target bridge and determine a detection area based on the structural information; An environmental information module, used to obtain environmental information of the target bridge, wherein the environmental information includes obstacle information in the detection area; An obstacle avoidance path module, configured to determine an obstacle avoidance path based on the environmental information, wherein the obstacle avoidance path is a moving path that maintains the detection range of the target device while it is moving and covers the detection area, and the facility structure of the target device avoids the obstacle; A perception detection module is used to control the target device to complete perception detection of the target bridge based on the obstacle avoidance path.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images