Method and device for controlling inspection of train inspection robot

Abstract

The invention relates to a method and device for controlling a train inspection robot to inspect, and the method comprises the steps: obtaining various real-time inspection data of an inspection area through inspection navigation equipment on the train inspection robot, and then carrying out the calculation through combining the map data of the inspection area to obtain an optimal driving path for reaching an inspection target position, and the train inspection robot is accurately navigated to a specified inspection target position, so that effective inspection of the train is realized, and the safety of railway transportation is finally ensured.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of automatic control technology, and particularly relates to a method and device for controlling a train inspection robot to perform inspection. BACKGROUND

[0002] In the railway transportation industry, safe operation of railways is crucial to ensuring the efficiency of goods transportation and the safety of freight cars, and the inspection work of railway freight cars is a key link to ensure their normal operation. The traditional inspection method mainly relies on manual work, which is inefficient and prone to omissions and other problems. In order to solve these problems, train inspection robots have gradually been applied to the inspection work of railway freight cars in recent years. However, the navigation system of existing train inspection robots is easily affected by the environment, such as in interference conditions or insufficient light conditions, and cannot achieve precise cruising, thereby affecting effective inspection of the train. Therefore, how to ensure that the train inspection robot can be accurately navigated under different environmental conditions to complete effective inspection of the train has become a problem that needs to be solved. SUMMARY

[0003] Therefore, it is necessary to provide a method and device for controlling a train inspection robot to perform inspection, which acquires various real-time inspection data of an inspection area through an inspection navigation device on the train inspection robot, then calculates an optimal driving path to reach an inspection target position in combination with map data of the inspection area, thereby accurately navigating the train inspection robot to the specified inspection target position for inspection under different environmental conditions, and finally achieving effective inspection of the train to ensure the safety of railway transportation.

[0004] The first aspect of the present application provides a method for controlling a train inspection robot to perform inspection, which comprises: acquiring various real-time inspection data of an inspection area based on an inspection navigation device provided on the train inspection robot, performing data fusion processing in combination with preset map data of the inspection area, and calculating an optimal driving path for the train inspection robot to reach an inspection target position; controlling the train inspection robot to move to the inspection target position according to the optimal driving path and complete inspection of the train.

[0005] Optionally, before acquiring various real-time inspection data of an inspection area based on an inspection navigation device provided on the train inspection robot, it comprises: acquiring preset radar data and preset visual data of the inspection area based on the inspection navigation device; performing fusion processing of the preset visual data on the preset radar data, and generating the preset map data according to the fusion processing result.

[0006] Optionally, the preset visual data is fused with the preset radar data, and the preset map data is generated according to a fusion result.

[0007] Optionally, the inspection navigation device includes a plurality of sensor devices, and the preset map data includes environment detection data. Before the inspection navigation device arranged on the train inspection robot acquires the plurality of real-time inspection data of the inspection area, the method further includes: According to the environment detection data, an environment working condition to which the inspection area belongs is determined. According to the determined environment working condition, a corresponding sensor device is called to acquire corresponding real-time inspection data.

[0008] Optionally, the plurality of real-time inspection data includes obstacle data. After the inspection navigation device arranged on the train inspection robot acquires the plurality of real-time inspection data of the inspection area, and data fusion processing is performed in combination with the preset map data of the inspection area, and an optimal driving path of the train inspection robot to reach a target inspection position is calculated, the method further includes: Based on the obstacle data, and in combination with a preset path planning algorithm and a real-time obstacle avoidance principle, the optimal driving path is adjusted in real time.

[0009] Optionally, the sensor device includes two or more of the following: a laser radar, a visual sensor, a positioning instrument RTK, a radio frequency identification RFID, a magnetic navigation sensor, an odometer, an inertial measurement unit IMU, and an ultrasonic sensor. According to the determined environment working condition, a corresponding sensor device is called, including: When the environment working condition of the inspection area is a work area, the magnetic navigation sensor, the radio frequency identification RFID, the odometer, the inertial measurement unit IMU, the visual sensor, and the laser radar are called. When the environment working condition of the inspection area is a non-work area, the magnetic navigation sensor, the laser radar, the positioning instrument RTK, the inertial measurement unit IMU, the odometer, and the visual sensor are called. When the environment working condition of the inspection area is a cross-rail area, the magnetic navigation sensor, the positioning instrument RTK, the laser sensor, the inertial measurement unit IMU, the odometer, and the visual sensor are called. Furthermore, when there is interference in the inspection area, the visual sensor and the positioning instrument RTK are called. In a case where the illumination in the inspection area is less than a preset illumination threshold, the ultrasonic sensor and the magnetic navigation sensor are called.

[0010] The second aspect of the present application provides a device for controlling a train inspection robot to perform inspection, the device comprising: a processing module configured to acquire a plurality of real-time inspection data of an inspection area based on an inspection navigation device arranged on the train inspection robot, perform data fusion processing in combination with preset map data of the inspection area, and calculate an optimal travel path of the train inspection robot to reach an inspection target position; and a control module configured to control the train inspection robot to move to the inspection target position according to the optimal travel path and complete the inspection of the train.

[0011] The third aspect of the present application provides a system for controlling a train inspection robot to perform inspection, the system comprising: a train inspection robot and a control center. The train inspection robot is configured to acquire a plurality of real-time inspection data of an inspection area based on an inspection navigation device arranged on the train inspection robot, perform data fusion processing in combination with preset map data of the inspection area, calculate an optimal travel path to reach an inspection target position, control itself to move to the inspection target position according to the optimal travel path and complete the inspection of the train, and synchronously transmit data of itself to the control center in real time and perform corresponding operations according to a control instruction sent by the control center. The control center is configured to generate a control instruction according to data sent by the train inspection robot and a current inspection task, and send the control instruction to the train inspection robot to control the train inspection robot to complete the inspection task.

[0012] The fourth aspect of the present application provides a train inspection robot comprising a processor and a memory, wherein the memory is configured to store computer instructions, and the processor is configured to execute the computer instructions stored in the memory to implement the steps of any one of the above-mentioned methods for controlling a train inspection robot to perform inspection.

[0013] The fifth aspect of the present application provides a computer-readable storage medium storing one or more programs, wherein the one or more programs are executable by one or more processors to implement the steps of any one of the above-mentioned methods for controlling a train inspection robot to perform inspection.

[0014] The present application has the following beneficial effects: through the inspection navigation equipment on the train inspection robot, various real-time inspection data of the inspection area are obtained, then the optimal driving path to the inspection target position is calculated combined with the map data of the inspection area, and the train inspection robot is accurately navigated to the specified inspection target position, so that the train inspection robot can be accurately navigated under different environmental conditions to effectively inspect the train, and finally the safety of railway transportation is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of a method for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure. Figure 2 A structural diagram of a device for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure. Figure 3 An internal structure diagram of a train inspection robot in another embodiment of the present application is shown in the figure. Figure 4 A structural diagram of a system for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0016] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0017] Figure 1 A flowchart of a method for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure. Figure 2 A structural diagram of a device for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure. Figure 3 An internal structure diagram of a train inspection robot in another embodiment of the present application is shown in the figure. Figure 4 A structural diagram of a system for controlling train inspection robot inspection in an embodiment of the present application is shown in the figure.

[0018] Embodiment one According to Figure 1 It can be known that the present embodiment discloses a method for controlling train inspection robot inspection, which comprises: S101, based on the inspection navigation equipment arranged on the train inspection robot, acquiring various real-time inspection data of the inspection area, and combining the preset map data of the inspection area to perform data fusion processing and calculate the optimal driving path of the train inspection robot to the inspection target position; In particular, the embodiment is to set the inspection navigation device on the train inspection robot in advance, and then obtain various real-time inspection data of the inspection area through the inspection navigation device. The inspection navigation device of the embodiment includes various sensors capable of realizing navigation positioning, such as laser radar, visual sensor, RTK, RFID, magnetic navigation sensor, odometer, IMU, ultrasonic sensor, etc. The specific person skilled in the art can set them according to actual needs, and the present application does not make specific limitations thereto.

[0019] Specifically, the embodiment is directed to the existing train inspection robot based on track navigation, which usually only sets laser radar or visual sensor for navigation. However, in practice, laser radar navigation is easily disturbed in complex environment, and the navigation accuracy and reliability of visual sensor will also decrease greatly when the light is insufficient or the scene changes greatly. For example, laser radar is also prone to misjudgment when facing smooth and reflective surfaces such as glass, and the navigation effect of visual sensor will be greatly reduced when the light is dark and there are dust and other interference in the tunnel. In addition, the existing train inspection robot usually runs on a fixed track, that is, the existing train inspection robot travels along the pre-laid track or marker line. This movement mode obviously causes poor flexibility of the train inspection robot, which cannot adapt to complex inspection environment and temporary task adjustment. In order to solve these problems, the embodiment sets various different inspection navigation devices on the train inspection robot, and starts the required inspection navigation device into working state according to the current inspection area environment detection data, so as to ensure that the train inspection robot can be accurately navigated to the specified inspection target position under different environmental conditions, thereby realizing effective inspection of the train, and finally ensuring the safety of railway transportation.

[0020] It should be noted that, unlike the existing method of navigating the train inspection robot through the track, the train inspection robot of the embodiment is not limited by the track, but determines the driving path according to the inspection target position. Therefore, the method of the embodiment is simple, reliable and highly flexible, can meet the needs of various different inspection scenes, and has very good market application prospect.

[0021] In the embodiment, the distance information of the train inspection robot and the surrounding environment is acquired by the laser radar; the feature points and markers in the environment where the train inspection robot is located are recognized by the visual sensor, so as to assist navigation and positioning based on the recognized feature points and markers; at the same time, the train inspection robot is globally positioned based on satellites by the positioning instrument RTK; the radio frequency point where the train inspection robot is located is recognized by the radio frequency identification RFID, so as to determine the current position of the train inspection robot; the train inspection robot is navigated and positioned by the magnetic navigation sensor; the running increment of the train inspection robot is measured by the odometer, so as to compensate for the positioning drift; the acceleration and angular velocity of the train inspection robot are measured by the inertial measurement unit IMU, so as to obtain the motion state information of the train inspection robot; and the obstacle information around the train inspection robot is acquired by the ultrasonic sensor.

[0022] Of course, the above-mentioned inspection navigation device is only an example of the embodiment, and in actual implementation, those skilled in the art can make any settings according to actual needs, and the embodiment does not make specific limitations thereto.

[0023] S102, controlling the train inspection robot to move to the inspection target position according to the optimal driving path and completing the inspection of the train; That is, the optimal driving path to the inspection target position is calculated by combining the map data of the inspection area, so as to accurately navigate the train inspection robot to the specified inspection target position, and then the effective inspection of the train is realized, and finally the safety of railway transportation is ensured.

[0024] In another embodiment, the above-mentioned step S101 further comprises: acquiring preset radar data and preset visual data of the inspection area based on the inspection navigation device; fusing the preset visual data to the preset radar data, and generating the preset map data according to the fusion result.

[0025] Specifically, the preset visual data is used to correct the preset radar data, and the preset map data is generated according to the correction result. Specifically, the laser radar and the visual sensor are used to scan the inspection area, then the feature points recognized by the visual sensor are used to correct the data collected by the laser radar, and the map information is generated.

[0026] In a specific implementation, the preset map data can be generated in advance from the perspective of saving time, so that the optimal travel path of the train inspection robot to the inspection target position can be quickly calculated based on the preset map data during the inspection. Of course, the preset map data can also be generated in real time during the inspection, so as to effectively ensure the accuracy of the generated preset map data, and further ensure the accuracy of the finally calculated optimal travel path. In short, the preset map data can be generated before the start of the inspection task or in real time during the inspection process, and the specific setting can be made according to the actual situation, which is not limited in the present application.

[0027] In a specific implementation, the plurality of real-time inspection data in the embodiment includes obstacle data. After the step S101, the method further comprises: adjusting the optimal travel path in real time based on the obstacle data, and combining a preset path planning algorithm and a real-time obstacle avoidance principle.

[0028] In short, the train inspection robot of the embodiment detects obstacles in real time before or during the inspection, and adjusts the travel path based on the detected obstacles to achieve obstacle avoidance. Of course, the travel state of the inspection robot may also need to be adjusted during the obstacle avoidance process, for example, the travel speed and travel posture of the train inspection robot are adjusted to avoid obstacles.

[0029] In another embodiment, the inspection navigation device comprises a plurality of sensor devices, and the preset map data comprises environment detection data. Before the inspection navigation device arranged on the train inspection robot acquires the plurality of real-time inspection data of the inspection area, the method further comprises: determining the environment working condition to which the inspection area belongs according to the environment detection data; and calling the corresponding sensor device to acquire the corresponding plurality of real-time inspection data according to the determined environment working condition.

[0030] That is, the embodiment calls the corresponding sensor device according to the environment working condition of the inspection area to acquire the plurality of real-time inspection data. The sensor device of the embodiment comprises two or more of the following: laser radar, visual sensor, positioning instrument RTK, radio frequency identification RFID, magnetic navigation sensor, odometer, inertial measurement unit IMU and ultrasonic sensor.

[0031] That is, the embodiment is to start the required inspection navigation device according to the environmental working condition of the inspection area, for example, the required inspection navigation device can be started in real time according to the current inspection area and inspection scene, the corresponding inspection navigation device is triggered to collect data, and then the optimal driving path of the train inspection robot to the inspection target position is calculated through fusion processing of the collected data. Because the embodiment only starts the required inspection navigation device to collect data, the application can collect as little data as possible under the premise of ensuring that the train inspection robot is accurately navigated to the inspection target position to complete the inspection task, thereby reducing the consumption of system resources for subsequent data processing, and further greatly improving user experience.

[0032] In the embodiment, the inspection scene can include an interference existing inspection scene and an insufficient light inspection scene. The two kinds of inspection scenes are mainly set for the scene that the laser radar navigation is easily interfered in a complex environment, and the navigation accuracy and reliability of the visual sensor are greatly reduced when the light is insufficient or the scene changes greatly.

[0033] It should be noted that the insufficient light inspection scene in the embodiment refers to an inspection scene in which the light is less than a preset brightness threshold.

[0034] That is, the embodiment sets a preset brightness threshold, and when it is detected that the current brightness is less than the preset brightness threshold, it is determined that the current is in the insufficient light inspection scene, and the inspection navigation device in the insufficient light inspection scene needs to be started to collect information.

[0035] In specific implementation, a person skilled in the art can set other various inspection scenes according to actual needs, for example, different levels of inspection scenes can be set according to the degree of interference, and of course different levels of inspection scenes can be set according to the degree of insufficient light. Different thresholds can be set, that is, a first light threshold, a second light threshold, and an nth light threshold, or a first interference threshold, a second interference threshold, and an nth interference threshold. Each threshold can correspond to an inspection scene of a level, and the corresponding inspection navigation device is started according to the inspection scene of different levels, so that the number of started inspection navigation devices is as small as possible on the basis of ensuring train inspection, that is, only the required inspection navigation device is started, which can reduce the amount of collected data, and in turn reduce the amount of subsequent data, thereby saving the consumption of computing resources of the train inspection robot, and also reducing the energy consumption of the train inspection robot. In other words, the embodiment starts only the required inspection navigation device under the premise of ensuring the normal work of the train inspection robot, so as to reduce the consumption of computing resources of the train inspection robot to the greatest extent.

[0036] The inspection area in the embodiment can include a work area, a non-work area, a cross-rail area, and the like, that is, the embodiment is to divide the area reached by the train inspection robot, and then start different inspection navigation devices for different areas, so as to further save the consumption of the computing resources of the train inspection robot and reduce the energy consumption of the train inspection robot as much as possible.

[0037] In another embodiment, according to the determined environmental conditions, the corresponding sensor device is called, including: When the environmental conditions of the inspection area are the work area, the magnetic navigation sensor, the radio frequency identification (RFID), the odometer, the inertial measurement unit (IMU), the visual sensor, and the laser radar are called. When the environmental conditions of the inspection area are the non-work area, the magnetic navigation sensor, the laser radar, the real-time kinematic (RTK), the inertial measurement unit (IMU), the odometer, and the visual sensor are called. When the environmental conditions of the inspection area are the cross-rail area, the magnetic navigation sensor, the real-time kinematic (RTK), the laser sensor, the inertial measurement unit (IMU), the odometer, and the visual sensor are called. Moreover, when there is interference in the inspection area, the visual sensor and the real-time kinematic (RTK) are called. When the illumination of the inspection area is less than a preset illumination threshold, the ultrasonic sensor and the magnetic navigation sensor are called.

[0038] That is, the embodiment is to start different sensor devices for different environmental conditions, that is, inspection scenes and inspection areas, so as to save the consumption of the computing resources of the train inspection robot and reduce the energy consumption of the train inspection robot itself.

[0039] It should be noted that the embodiment of the present application is only an example of starting the required inspection navigation device based on the environmental detection data of the different inspection areas, and the specific person skilled in the art can make any setting according to the actual needs, and the present application does not make specific limitations.

[0040] In specific implementation, in the embodiment, the navigation controller is used to obtain the multiple real-time inspection data of the inspection area based on the inspection navigation devices arranged on the train inspection robot, the data fusion processing is performed in combination with the preset map data of the inspection area, and the optimal driving path of the train inspection robot to the inspection target position is calculated.

[0041] The navigation control device is installed on the train inspection robot, and the navigation controller in the embodiment can be arranged on the train inspection robot, of course, in order to reduce the cost of the train inspection robot, the navigation controller can also be arranged on the control center, that is, the fusion processing of the data collected by the navigation control device can be completed by the train inspection robot itself, of course, the train inspection robot can also send all the data to the control center, and the control center can complete the data fusion, and the optimal driving path to the inspection target position is fed back to the train inspection robot, so that the train inspection robot moves to the inspection target position according to the optimal driving path, and the train is inspected, and the specific person skilled in the art can set according to the actual need, and the application does not make specific limitation.

[0042] In the specific implementation, before the inspection, the inspection area is scanned by the laser radar and the visual sensor, then the navigation controller corrects the data collected by the laser radar by using the feature points recognized by the visual sensor, and generates preset map information. Based on the preset map information, the real-time inspection data sent by the enabled positioning instrument RTK, radio frequency identification RFID, magnetic navigation sensor, odometer, inertial measurement unit IMU and ultrasonic sensor are combined to calculate the optimal driving path from the current position to the inspection target position, and the preset path planning algorithm and the real-time obstacle avoidance principle are used to adjust the driving direction and speed of the train inspection robot, until the train inspection robot reaches the inspection target position and completes the inspection of the inspection target position. By sequentially scanning all the inspection target positions and generating the optimal driving path, the inspection of all the inspection target positions is completed.

[0043] That is, the train inspection robot is navigated to the inspection target position, and after the train inspection is completed at the inspection target position, the train inspection robot is navigated to the next inspection target position, until the train inspection robot completes the inspection of the train.

[0044] In another embodiment, the method further comprises: sending the calculated optimal driving path, the called navigation control device and the state information of the train inspection robot to the control center in real time, receiving the control instruction sent by the control center, and controlling the train inspection robot to perform corresponding operations based on the received control instruction.

[0045] In short, all the real-time data of the train inspection robot are synchronized to the control center, so that the control personnel can command and control the operation of the train inspection robot through the control center according to the received real-time data, so that the train can be better inspected.

[0046] That is, the embodiment realizes a high-efficiency and flexible navigation and inspection method by combining the control of the train inspection robot itself with the control of the control center, improves the driving speed and inspection efficiency of the train inspection robot, and can quickly respond to temporary task adjustment, thereby being more suitable for the needs of complex inspection environments.

[0047] That is, the embodiment sets the inspection navigation device on the train inspection robot, which can include various different sensor devices, then activates the required sensor devices for work according to the actual situation, and performs data fusion processing on the obtained inspection data, thereby accurately and stably navigating the train inspection robot to the specified inspection target position in a complex environment, ensuring that the train inspection robot can be accurately navigated to the position in different environmental conditions, different surface materials, and the presence of interference, and ultimately ensuring the safety of railway transportation.

[0048] Embodiment Two In view of the problems in the prior art that the train inspection robot cannot normally drive once the track or marker line is damaged, worn, etc., and the cost and time cost of re-laying the track or marker line is high when the inspection route needs to be adjusted, and the single sensor navigation scheme cannot effectively ensure accurate navigation to the position, the embodiment provides a method for controlling train inspection robot inspection, which comprises: The inspection navigation device is a combination of multiple sensor devices, which can specifically include a laser radar, a vision sensor, a positioning instrument RTK, a radio frequency identification RFID, a magnetic navigation sensor, an odometer, an inertial measurement unit IMU, and an ultrasonic sensor, etc. The inspection area of the train inspection robot is divided into an operation area, a non-operation area, and a cross-track area. Among them, In the operation area, multi-sensor navigation positioning is performed by using magnetic navigation + RFID scanning positioning + IMU + odometer + vision sensor, and obstacle avoidance is performed by relying on vision and laser sensors; in the non-operation area, navigation and obstacle avoidance are performed by using laser sensors + IMU + odometer + vision sensors; and in the cross-track area, positioning and navigation are realized by using RTK + laser sensors + IMU + odometer. Of course, the above is only an example, and in specific implementation, those skilled in the art can arbitrarily set the inspection navigation devices activated in each area according to actual needs.

[0049] Specifically, in the embodiment, the magnetic navigation\RFID is used for navigation and positioning in a non-fixed scene in a partial indoor environment, and is also the main navigation mode of the train inspection robot. The magnetic navigation is used to complete the straight driving and translation functions of the train, and the RFID is used to complete the recording function of the position of the train. Each area is marked with a specific RFID, so after identifying the RFID, it is confirmed that a certain area is entered, and the corresponding inspection navigation equipment is started to complete navigation and obstacle avoidance and other work.

[0050] In the embodiment, the laser radar\vision sensor is used for close-range obstacle detection to prevent collision. The laser radar is used to obtain accurate distance information of the environment around the train inspection robot, and the obtained information is three-dimensional, which can accurately avoid obstacles. The vision sensor is used to identify feature points and markers in the environment, assist in navigation and positioning, and is mainly used for close-range obstacle detection during vehicle driving, and serves as a supplement to the laser radar to complete the obstacle avoidance function. RTK is used for global positioning in a non-fixed scene by relying on satellites. It is mainly used in outdoor navigation sensor-free scenes to guide the train inspection robot to complete straight driving, turning, translation and other actions through satellite positioning. The odometer is used to measure the speed of the vehicle running, and the incremental positioning drift is compensated to achieve auxiliary positioning, which is mainly used for positioning in the position of the RFID-free section during driving. The IMU is used to measure the acceleration and angular velocity of the train inspection robot, and provides motion state information. The vehicle state is determined through the vehicle motion state information. If abnormal alarm information such as excessive axial acceleration or excessive angular velocity change occurs, part of the sensor or driver should be closed to confirm whether the vehicle state is stable. The navigation controller: fuses the data of multiple sensors, calculates the optimal driving path of the train inspection robot according to the preset navigation algorithm and map information, and controls the motion of the train inspection robot.

[0051] In the embodiment, the collected data is fused and processed by Kalman filtering and other algorithms, that is, the data collected by the laser radar, vision sensor, ultrasonic sensor and IMU is fused and processed by Kalman filtering and other algorithms. In the embodiment, the multi-sensor device combination navigation can integrate the advantages of multiple sensor devices, effectively overcome the limitations of single sensor devices in different environments, and thus improve the navigation accuracy and stability. For example, in an environment with insufficient light or interference, the data fusion of the vision sensor and the laser radar can ensure that the inspection robot can still navigate accurately; when facing close-range obstacles, the ultrasonic sensor and the real-time obstacle avoidance principle can respond in time, which can effectively avoid collision.

[0052] In short, the embodiment of the present application effectively fuses the data of various sensors such as laser radar, visual sensor, ultrasonic sensor and IMU through algorithms such as Kalman filtering, thereby effectively improving the accuracy and reliability of navigation data, and then effectively ensuring the accuracy of the final navigation.

[0053] In specific implementation, the embodiment first preliminarily fuses the data of laser radar and visual sensor, that is, corrects the laser radar data with the feature points recognized by the visual sensor to improve the accuracy of distance measurement. Then, the fused data is further fused with the data of ultrasonic sensor and IMU, and the motion state of the train inspection robot and the surrounding environment information are comprehensively considered, so as to obtain more accurate navigation data.

[0054] The navigation algorithm in the embodiment adopts a combination of a preset path planning algorithm and a real-time obstacle avoidance principle. Before the start of the inspection task, the inspection area is scanned by laser radar and visual sensor to generate high-precision map information. Of course, the inspection area can also be scanned by laser radar and visual sensor during the inspection process to generate high-precision map information. In the navigation process, the optimal driving path from the current position to the target position is calculated by using path planning algorithms such as A* algorithm according to the map information and the data collected by the sensor device in real time. At the same time, the surrounding environment is monitored in real time, and when an obstacle is detected, the driving direction and speed of the train inspection robot are adjusted by using the real-time obstacle avoidance principle to ensure safe obstacle avoidance.

[0055] In specific implementation, the train inspection robot in the embodiment maintains real-time communication with the control center through the wireless communication module, so that the control center can remotely adjust the train inspection robot through control instructions according to the actual inspection requirements. That is, the train inspection robot in the embodiment sends the sensor device data and its own state information to the control center in real time, so that the control center can monitor and manage the inspection process. Of course, the control center can also save all the inspection data for subsequent query.

[0056] It should be noted that the navigation scheme of the embodiment can quickly calculate the optimal driving path according to real-time environmental information and adjust the driving direction and speed in real time, thereby improving the driving speed and inspection efficiency of the inspection robot. In addition, the embodiment realizes real-time data transmission and instruction interaction between the train inspection robot and the control center through the wireless communication module, which can effectively improve the flexibility and management efficiency of the inspection work.

[0057] The working method of the train inspection robot of the embodiment of the present application will be explained and described in detail through a specific example as follows: After the train inspection robot is started, the required inspection navigation device is started to work according to the environment detection data, and the real-time inspection data around is collected; The navigation controller receives the collected real-time inspection data, performs data fusion processing, and calculates the optimal driving path according to the preset navigation algorithm; The train inspection robot drives along the calculated path according to the instructions of the navigation controller, while monitoring the surrounding environment detection data in real time, and performs obstacle avoidance operation based on the preset path planning algorithm and real-time obstacle avoidance principle; In the driving process, the wireless communication module sends the data collected by each sensor device and the state information of the train inspection robot to the control center, and the control center sends control instructions to the train inspection robot according to the received data and the current inspection task. When the train inspection robot receives the control instructions sent by the control center, the navigation parameters are adjusted according to the control instructions, and the inspection task is finally completed; When the inspection task is completed, the train inspection robot returns to the starting point or the specified position and waits for the next control instruction.

[0058] As can be seen from the above, the train inspection robot of the embodiment does not need to run according to the predetermined track, so the method according to the embodiment does not need to lay the track, and therefore the embodiment does not have the track construction cost, and it is also unnecessary to maintain the track in the later period, so the present application can effectively reduce the inspection cost. In addition, the embodiment improves the accuracy of robot positioning and navigation through multi-sensor fusion technology, can avoid repeated calibration and loss of positioning coordinates of the robot, and the embodiment selects the matched sensor device for information collection and fusion in the corresponding scene in a complex environment, thereby improving the working efficiency of the robot. As can be seen from the above, the train inspection robot of the embodiment has more market competitiveness.

[0059] Embodiment three The embodiment provides a device for controlling train inspection robot inspection, referring to Figure 2 , the device comprises: A processing module 11 is configured to acquire a plurality of real-time inspection data of an inspection area based on an inspection navigation device arranged on a train inspection robot, perform data fusion processing in combination with preset map data of the inspection area, and calculate an optimal driving path of the train inspection robot to reach an inspection target position. A control module 12 is configured to control the train inspection robot to move to the inspection target position according to the optimal driving path and complete the inspection of the train.

[0060] Therefore, the embodiment obtains multiple real-time inspection data of an inspection area based on an inspection navigation device arranged on a train inspection robot through the processing module 11, performs data fusion processing on the multiple real-time inspection data and preset map data of the inspection area to obtain an optimal driving path, and accurately guides the train inspection robot to a specified inspection target position through the control module 12, thereby realizing effective inspection of the train and finally ensuring the safety of railway transportation.

[0061] In another embodiment, the processing module 11 is further configured to obtain preset radar data and preset visual data of the inspection area based on the inspection navigation device, perform fusion processing on the preset visual data and the preset radar data, and generate the preset map data according to a fusion processing result.

[0062] Specifically, the processing module 11 of the embodiment corrects radar data by using visual data, so that more accurate preset map data can be obtained, and the driving path obtained based on the preset map data is more accurate, thereby effectively ensuring that the train inspection robot is accurately guided to the specified inspection target position.

[0063] Further, in specific implementation, the preset map data can be generated in advance from the perspective of saving time, so that the optimal driving path of the train inspection robot to the inspection target position can be quickly calculated based on the preset map data during inspection. Of course, the preset map data can also be generated in real time during inspection, so as to effectively ensure the accuracy of the generated preset map data and the accuracy of the finally calculated optimal driving path. In short, the preset map data can be generated before the start of the inspection task or in real time during the inspection process, and the specific implementation can be set according to actual conditions, which is not limited in the present application.

[0064] In addition, considering that the inspection area is complex and unexpected situations may occur at any time, the processing module 11 of the embodiment further adjusts the optimal driving path in real time based on a preset path planning algorithm and a real-time obstacle avoidance principle, thereby effectively ensuring the smooth completion of the train inspection.

[0065] In specific implementation, the inspection navigation device in the embodiment includes multiple sensor devices, and the preset map data includes environmental detection data. In specific implementation, the processing module 11 of the embodiment is further configured to determine an environmental working condition to which the inspection area belongs according to the environmental detection data, and call corresponding sensor devices to obtain corresponding multiple real-time inspection data according to the determined environmental working condition. That is, the embodiment is according to the environmental conditions of the inspection area, calling the corresponding inspection navigation device to obtain the plurality of real-time inspection data; wherein, the sensor device of the embodiment includes two or more of the following: laser radar, visual sensor, positioning instrument RTK, radio frequency identification RFID, magnetic navigation sensor, odometer, inertial measurement unit IMU and ultrasonic sensor.

[0066] Specifically, when the environmental conditions of the inspection area are the working area, the magnetic navigation sensor, the radio frequency identification RFID, the odometer, the inertial measurement unit IMU, the visual sensor and the laser radar are called; when the environmental conditions of the inspection area are the non-working area, the magnetic navigation sensor, the laser radar, the positioning instrument RTK, the inertial measurement unit IMU, the odometer and the visual sensor are called; when the environmental conditions of the inspection area are the cross-rail area, the magnetic navigation sensor, the positioning instrument RTK, the laser sensor, the inertial measurement unit IMU, the odometer and the visual sensor are called; and when there is interference in the inspection area, the visual sensor and the positioning instrument RTK are called; when the illumination of the inspection area is less than a preset illumination threshold, the ultrasonic sensor and the magnetic navigation sensor are called.

[0067] In specific implementation, the processing module 11 in the embodiment fuses the data collected by the laser radar and the visual sensor to obtain map information, and then calculates the optimal driving path from the current position to the next inspection target position based on the map information and the data sent by the enabled positioning instrument RTK, radio frequency identification RFID, magnetic navigation sensor, odometer, inertial measurement unit IMU and ultrasonic sensor, adjusts the driving direction and speed of the train inspection robot by using a preset path planning algorithm and real-time obstacle avoidance principle, until the train inspection robot reaches the inspection target position and completes the inspection of the current inspection target position; and all the inspection target positions are scanned in the above manner to generate the optimal driving path, until the inspection of all the inspection target positions is completed.

[0068] In specific implementation, the device further includes a wireless communication module, which sends the calculated optimal driving path, the enabled sensor device and the self-state information of the train inspection robot to the control center in real time, receives the control instructions sent by the control center, and then controls the train inspection robot to perform corresponding operations based on the received control instructions. It should be noted that the control instructions of the embodiment include navigation parameters, which can include driving route, driving speed, driving posture and various parameters, and the train inspection robot can be controlled to drive to the required position by the navigation parameters, so as to meet the different use conditions of the train inspection robot.

[0069] In other words, this embodiment uses the processing module 11 to obtain various real-time inspection data of the inspection area based on the inspection navigation device set on the train inspection robot, and combines it with preset map data to perform data fusion processing to obtain the optimal driving path. Then, the train inspection robot is accurately navigated to the designated inspection target location, thereby realizing effective inspection of the train and ultimately ensuring the safety of railway transportation.

[0070] Example 4 This embodiment provides a train inspection robot, which can be a wheeled train inspection robot, a walking train inspection robot (single-legged, two-legged, and multi-legged), a tracked train inspection robot, a crawling train inspection robot, a wiggling train inspection robot, or a roaming train inspection robot, etc. Its internal structure diagram can be shown as follows: Figure 3 As shown, the train inspection robot includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data. The network interface communicates with external terminals via a network. When the computer program is executed by the processor, it implements any of the above-described methods for controlling the train inspection robot's inspection process.

[0071] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the train inspection robot to which the present application is applied. A specific train inspection robot may include more or fewer components than those shown in the diagram, or combine certain components, or have different component arrangements. Furthermore, the terminology and implementation principles involved in this embodiment can be specifically referred to in the steps of any method for controlling a train inspection robot in the embodiments of the present invention, and will not be repeated here.

[0072] Example 5 This embodiment provides a system for controlling a train inspection robot to perform inspections. See [link / reference] Figure 4 The system includes: a train inspection robot and a control center; The train inspection robot is used for acquiring various real-time inspection data of an inspection area based on its own inspection navigation device, performing data fusion processing in combination with preset map data of the inspection area, calculating an optimal driving path to an inspection target position, controlling itself to move to the inspection target position according to the optimal driving path to complete the inspection of the train, and synchronizing its own data to the control center in real time and performing corresponding operations according to the control instruction sent by the control center. The control center is used for generating a control instruction according to the data sent by the train inspection robot and a current inspection task, and sending the control instruction to the train inspection robot to control the train inspection robot to complete the inspection task.

[0073] Therefore, the train inspection robot is used to acquire various real-time inspection data of an inspection area based on an inspection navigation device, and the optimal driving path is obtained by performing data fusion processing in combination with preset map data, and then the train inspection robot is automatically and accurately navigated to a specified inspection target position to complete the inspection of the train. Meanwhile, the control center can send a control instruction to the train inspection robot, so that the train inspection robot is controlled to operate according to the requirement of the control center. On the basis of automatic control and navigation inspection of the train inspection robot, the train inspection robot can also be controlled by the control center, so that the effective inspection of the train inspection robot is more effectively ensured, and the safety of railway transportation is ensured.

[0074] Briefly, in the embodiment, the train inspection robot synchronizes all generated data to the control center in real time. For example, the train inspection robot sends the optimal driving path calculated, the currently started inspection navigation device and the state information of the train inspection robot to the control center in real time, so that the control center can adjust the driving route and driving speed of the train inspection robot by sending a control instruction to the train inspection robot according to the requirement of the current inspection task, so as to better ensure the effective operation of the train inspection robot on the basis of automatic control and navigation inspection of the train inspection robot.

[0075] Embodiment six The embodiment provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the method for controlling a train inspection robot to perform inspection.

[0076] The terms and implementation principles of the computer readable storage medium in the embodiment can refer to the steps of the method for controlling a train inspection robot to perform inspection in any embodiment of the application, which will not be described herein.

[0077] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, databases, or other media in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and memory bus dynamic RAM (MDRAM), etc.

[0078] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0079] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent protection of the present application should be subject to the appended claims.

Claims

1. A method for controlling a train inspection robot to perform inspections, characterized in that, The method includes: Based on the inspection and navigation equipment installed on the train inspection robot, various real-time inspection data of the inspection area are obtained, and combined with the preset map data of the inspection area, data fusion processing is performed to calculate the optimal travel path for the train inspection robot to reach the inspection target location. The train inspection robot is controlled to move along the optimal travel path to the inspection target location and complete the inspection of the train.

2. The method according to claim 1, characterized in that, Before the inspection navigation device mounted on the train inspection robot acquires various real-time inspection data of the inspection area, the process includes: Based on the inspection navigation device, preset radar data and preset visual data of the inspection area are acquired; The preset visual data is fused with the preset radar data, and the preset map data is generated based on the fusion processing result.

3. The method according to claim 2, characterized in that, The preset visual data is fused with the preset radar data, and the preset map data is generated based on the fusion processing result, including: The preset radar data is corrected based on the preset visual data, and the preset map data is generated based on the correction result.

4. The method according to any one of claims 1-3, characterized in that, The inspection and navigation device includes a variety of sensor devices, and the preset map data includes environmental detection data; Before the inspection navigation device mounted on the train inspection robot acquires various real-time inspection data of the inspection area, the method further includes: Based on the environmental monitoring data, the environmental conditions of the inspection area are determined; Based on the determined environmental conditions, the corresponding sensor devices are invoked to obtain the various real-time inspection data.

5. The method according to claim 1, characterized in that, The various real-time inspection data include: obstacle data; The method further includes: acquiring various real-time inspection data of the inspection area based on the inspection navigation equipment installed on the train inspection robot; performing data fusion processing by combining the data with the preset map data of the inspection area; and calculating the optimal travel path for the train inspection robot to reach the inspection target location. Based on the obstacle data, and combined with the preset path planning algorithm and real-time obstacle avoidance principle, the optimal driving path is adjusted in real time.

6. The method according to claim 4, characterized in that, The sensor devices include two or more of the following: lidar, vision sensor, RTK positioning device, RFID, magnetic navigation sensor, odometer, inertial measurement unit (IMU), and ultrasonic sensor; The step of calling the corresponding sensor device based on the determined environmental conditions includes: When the environmental conditions in the inspection area are those of a work area, the magnetic navigation sensor, the radio frequency identification (RFID) system, the odometer, the inertial measurement unit (IMU), the visual sensor, and the lidar are activated. When the environmental conditions in the inspection area are non-operational, the magnetic navigation sensor, the lidar, the RTK positioning device, the inertial measurement unit (IMU), the odometer, and the vision sensor are activated. When the environmental conditions in the inspection area are a cross-track area, the magnetic navigation sensor, the RTK positioning device, the laser sensor, the inertial measurement unit (IMU), the odometer, and the vision sensor are activated. Furthermore, interference exists in the inspection area, triggering the visual sensor and the RTK positioning device; If the illumination in the inspection area is less than the preset illumination threshold, the ultrasonic sensor and the magnetic navigation sensor are activated.

7. A device for controlling a train inspection robot, characterized in that, The device includes: The processing module is used to acquire various real-time inspection data of the inspection area based on the inspection navigation device set on the train inspection robot, perform data fusion processing in combination with the preset map data of the inspection area, and calculate the optimal travel path for the train inspection robot to reach the inspection target location. The control module is used to control the train inspection robot to move along the optimal travel path to the inspection target position and complete the inspection of the train.

8. A system for controlling a train inspection robot, characterized in that, The system includes: a train inspection robot and a control center; The train inspection robot is used to acquire various real-time inspection data of the inspection area based on its own inspection navigation equipment, perform data fusion processing by combining the preset map data of the inspection area, calculate the optimal driving path to the inspection target location, control itself to move according to the optimal driving path to the inspection target location to complete the inspection of the train, and synchronize its own data to the control center in real time, and execute corresponding operations according to the control instructions sent by the control center. The control center is used to generate control commands based on the data sent by the train inspection robot and the current inspection task, and send the control commands to the train inspection robot to control the train inspection robot to complete the inspection task.

9. A train inspection robot, characterized in that, It includes a processor and a memory; the memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to implement the steps of the method for controlling a train inspection robot to perform inspections as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the method for controlling a train inspection robot to perform inspections as described in any one of claims 1 to 6.

Images