Track inspection device and method for autonomously planning path

Abstract

The invention discloses a track inspection device and method capable of autonomously planning a path, relates to the technical field of track inspection, and aims to solve the problems of high labor intensity and low efficiency of inspection personnel. The track inspection device capable of autonomously planning the path comprises a vehicle body, a driving module, a calculation module, an ultrasonic array and a visual sensor, the driving module, the calculation module, the ultrasonic array and the visual sensor are arranged on the vehicle body, the driving module is used for driving the vehicle body to advance, and the ultrasonic array and the visual sensor are in communication connection with the calculation module. The driving module is used for detecting and collecting environment information around the vehicle body and sending the environment information to the calculation module, the calculation module is used for planning the advancing path of the vehicle body in real time according to the received information, and the calculation module is electrically connected with the driving module to control the driving module to act. According to the track inspection device and method capable of automatically planning the path, the track inspection path can be quickly and accurately planned, and the inspection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of track inspection, and particularly to an orbit inspection device and method for autonomously planning a path. Background Art

[0002] In the existing technical scope, the traditional method of manual inspection is often used, which includes two modes: walking inspection and riding inspection. In the walking inspection mode, the inspection personnel use inspection tools such as inspection hammers to gradually check and determine the damage condition of the railway. This method has obvious deficiencies, specifically manifested as poor inspection efficiency, limited railway line sections that can be covered by a single inspection, and high operating intensity of the inspection personnel. In the riding inspection mode, the inspection personnel ride on a running train to observe the damage situation of the railway. This mode highly depends on the observation ability of the inspection personnel, and in actual applications, its detection accuracy and accuracy are both at a low level.

[0003] Current track inspection mainly relies on manual or single sensors (such as visual recognition), and there are the following problems: Visual limitation: The camera is easily affected by environmental factors such as rain, snow, haze, etc., and its recognition ability decreases at night or under low light conditions; Blind area risk: It is difficult for a single sensor to cover the complex terrain around the track (such as turnout areas, tunnel inner walls); Insufficient dynamic response: Traditional path planning algorithms lag in response to sudden obstacles (such as falling rocks, animal intrusion); Machine inspection also requires manual placement of machine equipment, and the equipment cannot go to the operation area by itself, resulting in poor efficiency. Summary of the Invention

[0004] The purpose of the present invention is to provide an orbit inspection device and method for autonomously planning a path, which is used to quickly and accurately plan the path of orbit inspection.

[0005] To achieve the above purpose, in the first aspect, an orbit inspection device for autonomously planning a path provided by the present invention adopts the following technical solution: An orbit inspection device for autonomously planning a path includes a vehicle body, a driving module, a calculation module, an ultrasonic array, and a vision sensor arranged on the vehicle body. The driving module is used to drive the vehicle body to move forward. The ultrasonic array and the vision sensor are communicatively connected to the calculation module, and are used to detect and collect the environmental information around the vehicle body and send the environmental information to the calculation module. The calculation module is used to plan the moving path of the vehicle body in real time according to the received information, and the calculation module is electrically connected to the driving module to control the driving module to act.

[0006] A further technical solution lies in that the driving module includes a crawler traveling mechanism arranged on the vehicle body and a controller for driving the crawler traveling mechanism to start and stop.

[0007] A further technical solution lies in that the crawler traveling mechanism includes two sets of triangular crawlers arranged at the front part of the side of the vehicle body and two sets of conventional crawlers arranged at the rear part of the side of the vehicle body.

[0008] A further technical solution lies in that the ultrasonic array includes: Forward ultrasonic waves, including two sets of rotatable ultrasonic radars arranged at the front part of the vehicle body, for detecting the area in front of the vehicle body; Lateral ultrasonic waves, including a set of rotatable wide-beam ultrasonic sensors arranged on each side of the vehicle body, and each set of the rotatable wide-beam ultrasonic sensors is respectively used for detecting the area on both sides of the vehicle body; Bottom ultrasonic waves, including two sets of high-frequency ultrasonic sensors arranged at the bottom of the vehicle body, for detecting the area below the vehicle body.

[0009] A further technical solution lies in that a robotic arm is arranged on the vehicle body, and the vision sensor is arranged on the robotic arm.

[0010] A further technical solution lies in that a laser rangefinder is also arranged on the robotic arm, and the laser rangefinder is used to assist in collecting the environmental information around the vehicle body.

[0011] Compared with the prior art, the present invention has the following beneficial effects: In the orbit inspection device for autonomously planning a path provided by the present invention, the combination of ultrasonic waves and vision is adopted, which avoids the problem that vision cannot play a role in a low-light environment, avoids the disadvantages of low vision accuracy and slow response in complex road conditions, and at the same time, avoids the probability of damage to the rail vehicle during operation in complex situations.

[0012] In the second aspect, a method for orbit inspection for autonomously planning a path provided by the present invention adopts the following technical solution: A method for orbit inspection for autonomously planning a path, which is applied to any one of the orbit inspection devices for autonomously planning a path in the foregoing first aspect, includes: The vision sensor is started, the image information in front of the vehicle body is collected and sent to the calculation module, and the target position of the orbit inspection is calculated through analysis by the calculation module; Ultrasonic array startup: The bottom ultrasonic wave detects the information of the ballast settlement and water accumulation depth, and sends it to the calculation module; the lateral ultrasonic wave detects the lateral obstacle information of the vehicle body such as tunnel wall cracks and cable detachment, and sends it to the calculation module; the forward ultrasonic wave identifies the information of broken rails and large obstacles, and sends it to the calculation module; the calculation module judges the feasibility of the route according to the received ultrasonic detection information, and conducts path planning within five meters in front of the vehicle body; among them, the forward ultrasonic wave scans once per second. When neither the bottom ultrasonic wave nor the lateral ultrasonic wave alarms, and after the calculation module completes the path planning, the drive module starts and drives the vehicle body to move along the planned path. After the vehicle body reaches the target position, the distance between the vehicle and the track is determined through the lateral ultrasonic wave device, the distance between the vehicle and the track is kept within the set range, the detection device is started to conduct track damage detection, and at the same time the vehicle body moves along one side of the track. If the forward ultrasonic wave device detects an obstacle, the drive module drives the vehicle body to avoid the obstacle. After completing the detection task in the specified area, the target position is determined again.

[0013] Compared with the prior art, the present invention has the following beneficial effects: In the track inspection method for autonomous path planning provided by the present invention, ultrasonic waves are used for path planning and obstacle avoidance. The road conditions can be quickly and accurately judged through the changes of ultrasonic waves, providing a data basis for subsequent traveling conditions and reducing time for the overall inspection and repair process. The present invention uses a computer to calculate the path planning situation, providing accurate data for subsequent path planning, which is beneficial to the formulation of maintenance plans. Moreover, through the long-term accumulation and analysis of data trends of these data, data support can be provided for the adjustment of the track inspection path planning plan. Description of the Drawings

[0014] The drawings described herein are used to provide a further understanding of the present invention, and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention, and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a schematic structural diagram of a device provided by an embodiment of the present application; Figure 2 It is a flowchart of a method provided by an embodiment of the present application; Figure 3 It is a logic diagram of a method flow provided by an embodiment of the present application.

[0015] Reference Signs: 1. Vehicle body; 21. Triangular crawler; 22. Conventional crawler; 3. Manipulator; 31. Lower arm; 32. Upper arm; 41. Forward ultrasonic wave; 42. Lateral ultrasonic wave; 43. Bottom ultrasonic wave; 5. Vision sensor; 51. Laser rangefinder. Detailed implementation manners

[0016] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention.

[0018] In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication between two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0019] Please refer to Figure 1 , an orbit inspection device for autonomous path planning provided by an embodiment of the present invention includes: a vehicle body 1 and a driving module, a calculation module, an ultrasonic array, and a vision sensor 5 provided on the vehicle body 1. The driving module is used to drive the vehicle body 1 to move forward. The ultrasonic array and the vision sensor 5 are communicatively connected to the calculation module, and are used to detect and collect the environmental information around the vehicle body 1 and send the environmental information to the calculation module. The calculation module is used to plan the moving path of the vehicle body 1 in real time according to the received information, and the calculation module is electrically connected to the driving module to control the driving module to act.

[0020] Specifically, the driving module includes a crawler traveling mechanism provided on the vehicle body 1 and a controller for driving the start and stop of the crawler traveling mechanism. Among them, the controller is a driving circuit for driving the start and stop of the crawler traveling mechanism, and is electrically connected to the calculation module, so that the calculation module can control the crawler traveling mechanism to travel along the planned path.

[0021] The crawler traveling mechanism includes two sets of triangular crawlers 21 arranged at the front part of the side of the vehicle body 1 and two sets of conventional crawlers 22 arranged at the rear part of the side of the vehicle body 1. Considering that the environment in the outdoor or tunnel track layout area is relatively complex, the combined setting of the triangular crawlers and the conventional crawlers 22 facilitates the vehicle body 1 to move forward in various environments and improves the passability of the vehicle body 1.

[0022] The ultrasonic array includes forward ultrasonic waves 41, lateral ultrasonic waves 42, and bottom ultrasonic waves 43.

[0023] Among them, the forward ultrasonic waves 41 include two sets of rotatable ultrasonic radars arranged at the front part of the vehicle body 1, with a scanning radius of five meters and a rotation range of 120 degrees forward. By rotating to scan the road conditions ahead, it is judged whether there are obstacles on the road ahead and whether it is passable. When an obstacle is scanned ahead, it is judged whether it can be avoided within the 120-degree range ahead. If it can be avoided, the vehicle body 1 is controlled to automatically avoid through the analysis and calculation of the calculation module. If it cannot be avoided, it is combined with the information collected by the lateral ultrasonic wave 42 device, and then the traveling direction is changed.

[0024] The lateral ultrasonic waves 42 include a set of rotatable wide-beam ultrasonic sensors arranged on each side of the vehicle body 1. Each set of the rotatable wide-beam ultrasonic sensors is respectively used to detect the side areas of the vehicle body 1. The lateral ultrasonic device is a rotatable ultrasonic radar, with a scanning range of 60 degrees laterally and a scanning radius of three meters. The passability is judged by detecting whether there are obstacles on the side, or the steering is judged in combination with the forward ultrasonic wave 41 device.

[0025] The bottom ultrasonic waves 43 include two sets of high-frequency ultrasonic sensors arranged at the bottom of the vehicle body 1, which are used to detect the area below the vehicle body 1. The bottom ultrasonic wave 43 device is non-rotatable, with a scanning radius of 20 centimeters. The passability is judged through the analysis of the road conditions below, and data is accumulated for future path planning.

[0026] In one embodiment, the calculation module is a processor, which is used to receive the information collected by the vision sensor 5 and the ultrasonic array, and perform path planning or control the vehicle body 1 to avoid obstacles according to the received information.

[0027] In another embodiment, the calculation module includes a communication unit and a computer. The communication unit is arranged on the vehicle body 1, and the communication unit communicates with the computer remotely.

[0028] Specifically, the calculation module performs path planning and obstacle avoidance through modeling, which specifically includes the following steps: First, the ultrasonic array and the vision acquisition module 5 are used to collect the obstacles and azimuth angles around the vehicle body, and these data are sent to the calculation module. These data are aligned by time stamps to ensure spatio-temporal consistency.

[0029] Secondly, after the ultrasonic pulse is emitted and reflected by an obstacle, the receiving end records the time difference, calculates the distance, combines the installation angles of the sensors in the ultrasonic array, converts the polar coordinate data into Cartesian coordinates, generates a cross-sectional point cloud, and removes the outliers in the point cloud through the threshold method.

[0030] Then, use the SLAM technology to fuse multiple frames of ultrasonic data and construct a three-dimensional grid map, specifically including: Data association: Match the current frame point cloud with the historical frame point cloud, and optimize the pose transformation matrix through the iterative closest point algorithm; Pose estimation: Predict the vehicle pose based on IMU or odometry data and correct it through ICP; Map update: Transform to the global coordinate system and fill it into the three-dimensional grid map.

[0031] Finally, based on the grid map, search for the optimal path from the starting point to the target position and generate a global path.

[0032] During the vehicle body's movement, local obstacle avoidance adjustment is carried out in real time, specifically including: Real-time monitoring: The forward ultrasonic wave scans and updates the obstacle position every second; Dynamic re-routing: If a new obstacle is detected, insert a detour node and generate a local U-shaped path; Speed control: Dynamically adjust the vehicle speed according to the distance to the obstacle.

[0033] The response levels for the ultrasonic array detecting obstacles are as follows: First-level response: When the lateral ultrasonic sensor 42 detects that the intrusion object is less than 0.5 m away from the track, trigger a lateral path offset (maximum offset of 15 cm); Second-level response: When the bottom ultrasonic sensor 43 detects a continuous 20-cm ballast cavity, automatically generate a U-shaped detour path and reduce the speed to 0.3 m / s; Emergency braking: When the forward radar identifies an obstacle within 1 m that cannot be bypassed, activate the magnetic track brake and stop the vehicle within 0.5 seconds.

[0034] Adaptive speed control of vehicle body 1: Dynamically adjust the vehicle speed according to the ultrasonic point cloud density. When moving in an obstacle-free area, vehicle body 1 advances at a speed of 1.2 m / s.

[0035] Furthermore, a robotic arm 3 is provided on the vehicle body, and the vision sensor 5 is arranged at the end of the robotic arm 3. The robotic arm 3 includes a lower arm 31 and an upper arm 32, and the lower arm 31 and the upper arm 32 are hinged to adjust the height of the vision sensor 5.

[0036] Compared with the prior art, in an orbit inspection device capable of autonomously planning a path provided by the present invention, ultrasonic waves and vision are combined, avoiding the problem that vision cannot function in a low-illumination environment, and avoiding the disadvantages of low vision accuracy and slow response in complex road conditions. At the same time, the probability of the rail vehicle being damaged during operation in complex situations is avoided.

[0037] Please refer to Figure 2 and Figure 3 , the embodiment of the present invention further provides an orbit inspection method capable of autonomously planning a path, which is applied to any one of the above orbit inspection devices capable of autonomously planning a path, and includes: Step 1: The vision sensor 5 is activated to collect the image information in front of the vehicle body 1 and send it to the calculation module, and the calculation module analyzes and calculates the target position of the orbit inspection.

[0038] Among them, there are two ways to determine the target position. One is automatic determination, and the other is manual determination. Automatic determination is to capture the nearest rail by the vision sensor 5 and set it as the end point. Manual determination is to transmit the image seen by the vision sensor 5 back to the manual terminal through video transmission, and the manual terminal determines the end point position.

[0039] Step 2: The ultrasonic array is activated: The bottom ultrasonic wave 43 detects the information of the ballast settlement and the water depth, and sends it to the calculation module; the lateral ultrasonic wave 42 detects the lateral obstacle information of the vehicle body 1 such as the tunnel wall crack and the cable detachment, and sends it to the calculation module; the forward ultrasonic wave 41 identifies the information of the broken rail and the large obstacle, and sends it to the calculation module; the calculation module judges the feasibility of the route according to the received ultrasonic detection information and conducts path planning within 5 meters in front of the vehicle body 1. Among them, the forward ultrasonic wave 41 scans once per second.

[0040] Step 31: When neither the bottom ultrasonic wave 43 nor the forward ultrasonic wave 41 alarms, and the calculation module completes the path planning, the driving module is activated to drive the vehicle body 1 to travel along the planned path.

[0041] Step 32: After the forward ultrasonic wave 41 detects an obstacle, it is judged whether the obstacle is within 120° in front. If so, obstacle avoidance is directly performed. If not, the lateral ultrasonic wave 42 is activated for steering obstacle avoidance. Among them, Step 31 and Step 32 are selected alternately.

[0042] Step 4: After the vehicle body 1 reaches the target position, the distance between the vehicle and the track is determined by the lateral ultrasonic wave 42 device, and the distance between the vehicle body 1 and the track is kept within the set range. The detection device is activated to perform track damage detection, and at the same time, the vehicle body 1 travels along one side of the track.

[0043] Step 5: If the forward ultrasonic wave 41 device detects an obstacle, the vehicle body 1 is driven by the driving module to avoid the obstacle.

[0044] Step 6: After completing the detection task in the specified area, re-determine the target position.

[0045] Compared with the prior art, in an orbit inspection method with autonomous path planning provided by the present invention, ultrasonic waves are used for path planning and obstacle avoidance. The road conditions can be quickly and accurately judged through the changes in ultrasonic waves, providing a data basis for the subsequent movement of vehicle body 1 and reducing the time for the overall inspection and maintenance process.

[0046] The present invention uses a computer to calculate the path planning situation, providing accurate data for subsequent path planning, which is beneficial to the formulation of maintenance plans. Moreover, through the long-term accumulation and analysis of data trends of these data, it provides data support for the adjustment of the orbit inspection path planning plan.

[0047] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be assigned to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0048] In the embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system.

[0049] In addition, each functional unit in the various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0050] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A track inspection device with autonomous path planning, characterized in that: The invention comprises a vehicle body (1) and a driving module, a computing module, an ultrasonic array and a visual sensor (5) arranged on the vehicle body (1); the driving module is used to drive the vehicle body (1) to move; the ultrasonic array and the visual sensor (5) are communicatively connected with the computing module and are used to detect and collect environmental information around the vehicle body (1) and send the environmental information to the computing module; the computing module is used to plan the moving path of the vehicle body (1) in real time according to the received information; and the computing module is electrically connected with the driving module to control the action of the driving module.

2. A track inspection device with autonomous path planning according to claim 1, characterized in that: The driving module comprises a crawler track mechanism arranged on the vehicle body (1) and a controller for driving the crawler track mechanism to start and stop.

3. A track inspection device with autonomous path planning according to claim 2, characterized in that: The crawler track travel mechanism comprises two sets of triangular crawlers (21) arranged at the front part of the side of the vehicle body (1) and two sets of conventional crawlers (22) arranged at the rear part of the side of the vehicle body (1).

4. A track inspection device with autonomous path planning according to claim 1, characterized in that: The ultrasonic array comprises: A forward ultrasonic wave (41) comprising two groups of rotatable ultrasonic radars arranged at the front of the vehicle body (1) and used for detecting the area in front of the vehicle body (1); The lateral ultrasonic wave (42) comprises a group of rotatable wide-beam ultrasonic sensors arranged on both sides of the vehicle body (1), each group of rotatable wide-beam ultrasonic sensors being used to detect the side areas of both sides of the vehicle body (1); The bottom ultrasonic wave (43) comprises two groups of high-frequency ultrasonic sensors arranged at the bottom of the vehicle body (1) and used for detecting the area below the vehicle body (1).

5. The track inspection device with autonomous path planning according to claim 1, characterized in that: A mechanical arm (3) is arranged on the vehicle body (1), and the visual sensor (5) is arranged on the mechanical arm (3).

6. A track inspection device with autonomous path planning according to claim 5, characterized in that: The mechanical arm (3) is also provided with a laser rangefinder (51), and the laser rangefinder (51) is used to assist in collecting environmental information around the vehicle body (1).

7. A track inspection method with autonomous path planning, applied to a track inspection device with autonomous path planning as claimed in any one of claims 1 to 6, characterized in that: include: The visual sensor (5) is activated to collect image information in front of the vehicle body (1) and send it to the calculation module, which analyzes and calculates the target position of the track inspection; The ultrasonic array is activated: the bottom ultrasonic wave (43) detects the subsidence of the roadbed and the depth of water accumulation, and sends the information to the calculation module; the lateral ultrasonic wave (42) detects the lateral obstacle information of the vehicle body (1) such as cracks in the tunnel wall and cable shedding, and sends the information to the calculation module; the forward ultrasonic wave (41) identifies the broken rail and large obstacle information, and sends the information to the calculation module; the calculation module determines the feasibility of the route based on the received ultrasonic detection information, and performs path planning within five meters in front of the vehicle body (1); wherein the forward ultrasonic wave (41) performs a scan once per second; When the bottom ultrasonic wave (43) and the lateral ultrasonic wave (42) do not sound an alarm and the calculation module completes the path planning, the driving module starts and drives the vehicle body (1) to move along the planned path; After the vehicle body (1) reaches the target position, the distance between the vehicle and the track is determined by a lateral ultrasonic wave (42) device, the distance between the vehicle and the track is kept within a set range, and the detection device is started to perform track damage detection, while the vehicle body (1) moves along one side of the track; If the forward ultrasonic wave device (41) detects an obstacle, the vehicle body (1) is driven to avoid the obstacle through the driving module; After completing the detection task in the specified area, the target location is re-determined.

Images