Rail transit intelligent inspection robot, control method and device, and storage medium

Abstract

The application relates to a rail transit intelligent inspection robot, a control method and device and a storage medium, the method comprising the following steps: obtaining a preset inspection task; controlling an environment sensing system to collect ground environment parameters; determining a target mobile platform according to the ground environment parameters; in the case that the detachable mobile platform connected to the chassis driving system is the target mobile platform, controlling the chassis driving system to drive the target mobile platform to move according to an inspection route according to a mobile control algorithm, controlling the environment sensing system to collect target detection parameters of a target to be detected and to perform fault detection according to an inspection control algorithm, and controlling an inspection execution system to perform an auxiliary task according to the mobile control algorithm or the inspection control algorithm; through modular design and intelligent sensing and interaction, the application realizes dynamic replacement of the mobile platform in combination with the ground environment, so that a single robot can perform adaptive inspection under different ground environments, and the detection efficiency, reliability and multifunctionality of the inspection robot are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rail transit detection equipment, and in particular to a rail transit intelligent inspection robot, a control method and device, and a storage medium. BACKGROUND

[0002] With the rapid development of the motor train industry, the safety operation requirements of the motor train track are becoming higher and higher. The motor train track is exposed to the natural environment for a long time and is affected by various complex environmental factors such as high and low temperature, rain and snow, wind and sand. The track surface may have problems such as wear, cracks, depressions, and gravel, which need to be regularly inspected to ensure the safe driving of the motor train.

[0003] At present, most of the existing motor train track inspection equipment adopts a single walking mode, such as a wheel type or a track type. However, in different ground environments, the adaptability of the single walking mode is poor. SUMMARY

[0004] Therefore, it is necessary to provide a rail transit intelligent inspection robot, a control method and device, and a storage medium that can switch the moving platform based on the ground environment, share the chassis and three kinds of moving platforms (wheel type, track type, and bionic type) that can be quickly replaced, combine the mechanical arm actuator, the environment perception system, and the operation control unit, and realize efficient adaptive inspection, target grabbing, autonomous navigation and obstacle avoidance of different terrains, and real-time interaction with the diagnostic center.

[0005] In a first aspect, the present application provides a control method of a rail transit intelligent inspection robot. The rail transit intelligent inspection robot includes an operation control system, an environment perception system, a chassis driving system, an inspection execution system, a shared chassis, and a plurality of detachable moving platforms. The chassis driving system is in transmission connection with the detachable moving platforms. The method includes:

[0006] acquiring a preset inspection task; wherein the preset inspection task includes an inspection route, a target to be detected, and a target detection parameter;

[0007] controlling the environment perception system to collect ground environment parameters;

[0008] determining a target moving platform according to the ground environment parameters; the target moving platform includes any one of a wheel type moving platform, a track type moving platform, and a bionic type moving platform;

[0009] In the case that the detachable mobile platform connected to the chassis driving system is the target mobile platform, load the mobile control algorithm and the inspection control algorithm corresponding to the target mobile platform, and control the chassis driving system to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, control the environment perception system to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and control the inspection execution system to perform auxiliary tasks according to the mobile control algorithm or the inspection control algorithm.

[0010] In the case that the detachable mobile platform connected to the chassis driving system is not the target mobile platform, control the chassis driving system to stop, generate platform replacement prompt information and upload it to the diagnosis center, until the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform.

[0011] In one of the embodiments, the environment perception system includes at least one of a visual perception component, an infrared perception component, an ultrasonic perception component, a laser perception component, and an inertial measurement component; the ground environment parameter includes ground texture, ground material, ground fluctuation standard deviation, and spatial size data; and the target mobile platform is determined according to the ground environment parameter, including:

[0012] If the ground environment belongs to a first road surface condition according to the ground environment parameter, the target mobile platform is determined to be a wheeled mobile platform; and the first road surface condition is a flat road surface.

[0013] If the ground environment belongs to a second road surface condition according to the ground environment parameter, the target mobile platform is determined to be a tracked mobile platform; and the second road surface condition is a train track or a gravel road surface.

[0014] If the ground environment belongs to a third road surface condition according to the ground environment parameter, the target mobile platform is determined to be a bionic mobile platform; and the third road surface condition is a narrow pipeline.

[0015] In one of the embodiments, the chassis driving system is controlled to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, including:

[0016] In the case that the target mobile platform is a wheeled mobile platform, the chassis driving system is controlled to drive the wheeled mobile platform to move according to the inspection route according to a first mobile control algorithm; and the first mobile control algorithm includes a first obstacle avoidance strategy.

[0017] In the case where the target mobile platform is a tracked mobile platform, the chassis driving system is controlled to drive the tracked mobile platform to move along the inspection route according to a second mobile control algorithm; the second mobile control algorithm comprises a second obstacle avoidance strategy.

[0018] In the case where the target mobile platform is a tracked mobile platform, the chassis driving system is controlled to drive the tracked mobile platform to move along the inspection route according to a second mobile control algorithm; the second mobile control algorithm comprises a second obstacle avoidance strategy.

[0019] In one of the embodiments, the method further comprises:

[0020] In the case where the environment perception system detects a ground environment change, a preset inspection task change, or a robot self-checking state change, a platform replacement instruction is generated;

[0021] The target mobile platform is re-determined according to the platform replacement instruction.

[0022] In one of the embodiments, the inspection execution system comprises a three-axis mechanical arm, a base of the three-axis mechanical arm is fixedly installed at a front end of the common chassis, a grabbing mechanism is arranged at an end of the three-axis mechanical arm, and the grabbing mechanism is used to assist in removing track obstacles or grabbing a target to be detected.

[0023] The control of the inspection execution system to perform the auxiliary task according to the mobile control algorithm or the inspection control algorithm comprises:

[0024] The three-axis mechanical arm is controlled to assist in removing track obstacles according to the mobile control algorithm.

[0025] The three-axis mechanical arm is controlled to grab a target to be detected according to the inspection control algorithm.

[0026] In one of the embodiments, the working mode of the inspection execution system comprises a remote instruction control mode, a local autonomous control mode, and a preset trajectory control mode.

[0027] The method further comprises:

[0028] In the case where the grabbing control instruction is received from the diagnosis center, the working mode of the inspection execution system is determined to be the remote instruction control mode, and the auxiliary task is performed according to the grabbing control instruction; the grabbing control instruction comprises grabbing coordinates, a clamping jaw force, and a movement speed.

[0029] In the event of a communication interruption with the diagnostic center or the triggering of a local control command, the working mode of the inspection execution system is determined to be the local autonomous control mode. Based on the real-time environmental data collected by the environmental perception system, the system autonomously plans a real-time capture trajectory to execute the auxiliary task according to the real-time capture trajectory.

[0030] When a standard task is triggered on the inspection route, the working mode of the inspection execution system is determined to be the preset trajectory control mode, and the preset grasping trajectory corresponding to the standard task is loaded to execute the auxiliary task according to the preset grasping trajectory.

[0031] In one embodiment, the fault type of the target to be detected includes a first type of fault and a second type of fault;

[0032] The method further includes:

[0033] If a first type of fault is detected and it is determined from the ground environment parameters that the ground environment does not belong to the third road surface condition, the target detection parameters will be uploaded to the diagnostic center in real time.

[0034] If a second type of fault is detected and the ground environment is determined to be a third road surface condition based on the ground environment parameters, the target detection parameters are stored in the local memory. After the ground environment changes to a first road surface condition or a second road surface condition, the target detection parameters in the local memory are uploaded to the diagnostic center.

[0035] If a second type of fault is detected, a fault location movement trajectory, an alarm command, and a location upload command are generated in real time. Based on the fault location movement trajectory, the chassis drive system is controlled to drive the target mobile platform to the fault location. An audible and visual alarm is triggered based on the alarm command, and the fault location, fault type, and image data are uploaded to the diagnostic center based on the location upload command.

[0036] Secondly, this application also provides a control device for an intelligent rail transit inspection robot. The intelligent rail transit inspection robot includes an operation control system, an environmental perception system, a chassis drive system, an inspection execution system, a shared chassis, and multiple detachable mobile platforms, wherein the chassis drive system is transmissionally connected to the detachable mobile platforms; the device includes:

[0037] The task acquisition module is used to acquire preset inspection tasks; wherein, the preset inspection tasks include inspection routes, targets to be inspected, and target detection parameters;

[0038] The environmental sensing module is used to control the environmental sensing system to collect ground environmental parameters;

[0039] a platform determining module configured to determine a target mobile platform according to the ground environment parameters, wherein the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform, and a bionic mobile platform;

[0040] a patrol execution module configured to, in a case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, load a mobile control algorithm and a patrol control algorithm corresponding to the target mobile platform, control the chassis driving system to drive the target mobile platform to move according to the patrol route according to the mobile control algorithm, control the environment sensing system to collect target detection parameters of the target to be detected and perform fault detection according to the patrol control algorithm, and control the patrol execution system to perform an auxiliary task according to the mobile control algorithm or the patrol control algorithm; in a case where the detachable mobile platform connected to the chassis driving system is not the target mobile platform, control the chassis driving system to stop, generate platform replacement prompt information and upload the platform replacement prompt information to a diagnosis center, until the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform.

[0041] In a third aspect, the present application further provides an intelligent rail transit patrol robot, comprising: an operation control system, an environment sensing system, a chassis driving system, a patrol execution system, a common chassis, and a plurality of detachable mobile platforms, wherein the operation control system, the environment sensing system, the chassis driving system, and the patrol execution system are arranged on the common chassis; the operation control system is connected with the environment sensing system, the chassis driving system, and the patrol execution system respectively; and the chassis driving system is in transmission connection with the detachable mobile platforms.

[0042] The operation control system is configured to perform the steps of the control method of the intelligent rail transit patrol robot according to the first aspect.

[0043] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the control method of the intelligent rail transit patrol robot according to the first aspect.

[0044] In summary, this application proposes an intelligent inspection robot for rail transit, a control method, a device, and a storage medium. The method includes: acquiring a preset inspection task; controlling an environmental perception system to collect ground environmental parameters; determining a target mobile platform based on the ground environmental parameters; when the detachable mobile platform connected to the chassis drive system is the target mobile platform, controlling the chassis drive system to drive the target mobile platform to move along the inspection route according to a motion control algorithm; controlling the environmental perception system to collect target detection parameters of the target to be inspected and perform fault detection according to an inspection control algorithm; and controlling the inspection execution system to perform auxiliary tasks according to a motion control algorithm or an inspection control algorithm. This application, through modular design and intelligent perception and interaction, combined with the ground environment, enables the mobile platform to be dynamically replaced, allowing a single robot to perform adaptive inspections in different ground environments, significantly improving the inspection efficiency, reliability, and multifunctionality of the inspection robot. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the structure of an intelligent inspection robot for rail transit in one embodiment;

[0046] Figure 2 This is a schematic diagram of the structure of a rail transit intelligent inspection robot equipped with a wheeled mobile platform in one embodiment;

[0047] Figure 3 This is a schematic diagram of the universal coupling of a wheeled mobile platform in one embodiment;

[0048] Figure 4 This is a schematic diagram of the structure of an intelligent inspection robot for rail transit equipped with a tracked mobile platform in one embodiment.

[0049] Figure 5 This is a schematic diagram of the structure of an intelligent rail transit inspection robot equipped with a biomimetic mobile platform in one embodiment.

[0050] Figure 6 This is a schematic diagram of the bionic foot of a bionic mobile platform in one embodiment.

[0051] Figure 7 This is a flowchart illustrating the control method of an intelligent inspection robot for rail transit in one embodiment;

[0052] Figure 8 This is a flowchart illustrating the control method for an intelligent inspection robot for rail transit in another embodiment;

[0053] Figure 9 This is a flowchart illustrating the process of a smart rail transit inspection robot performing a complete inspection task in one embodiment.

[0054] Figure 10A structural block diagram of a control device of an intelligent track inspection robot in an embodiment;

[0055] Figure 11 An internal structural diagram of a computer device in an embodiment.

[0056] Summary of reference signs:

[0057] 1-common chassis, 2-three-axis mechanical arm, 3-high-definition camera, 4-infrared thermal imager, 5-ultrasonic detector, 6-laser radar, 7-IMU, 8-flange, 9-transmission motor shaft, 201-bionic foot, 301-wheel, 302-universal coupling, 401-track wheel, 402-track body, 403-assistant wheel, 404-connecting rod. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with 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.

[0059] In the related art, most of the inspection equipment for high-speed rail tracks adopts a single walking mode, such as a wheel type or a track type. However, in different ground environments, the adaptability of the single walking mode is poor. For example, the wheel type inspection equipment is efficient in driving on flat surfaces, but is easy to slip when encountering train tracks and gravel roads. The track type inspection equipment has good passability on gravel roads, but has high energy consumption on flat surfaces. The bionic type equipment is suitable for obstacle crossing in narrow channels, but has poor versatility. If different ground environments (flat surface, train track / gravel road, narrow channel) are equipped with different equipment respectively, the inspection cost and maintenance burden will be increased. At the same time, most of the track inspection robots at the present stage only have a single inspection function, and do not have environment perception, actuator and efficient interaction function.

[0060] Therefore, it is urgent to develop an inspection robot which can flexibly switch the moving platform, integrate the actuator, intelligently perceive and efficiently interact.

[0061] In an embodiment, as shown in Figure 1 a track inspection intelligent robot based on a switchable moving platform of ground environment is provided, comprising: an operation control system (OCU), an environment perception system, a chassis driving system, an inspection execution system, a common chassis 1 and a plurality of detachable moving platforms. The operation control system, the environment perception system, the chassis driving system and the inspection execution system are all arranged on the common chassis 1. The operation control system is connected with the environment perception system, the chassis driving system and the inspection execution system respectively, and the chassis driving system is in transmission connection with the detachable moving platforms.

[0062] In the embodiment, the detachable mobile platform includes at least three types of mobile platforms, such as a wheeled mobile platform, a tracked mobile platform, and a bionic mobile platform. The detachable platform is detachably connected with the shared chassis 1. The shared chassis 1 provided in the embodiment is provided with standard connection structures matched with the three types of mobile platforms, including positioning holes and locking devices, for realizing accurate positioning and stable connection.

[0063] In the embodiment, the chassis driving system includes a transmission motor fixedly arranged on the shared chassis 1, and the motor shaft of the transmission motor is fixedly arranged. The mobile platform can be quickly connected and replaced with the chassis and the transmission motor shaft 9 through manual operation. The transmission motor shaft 9 is provided with a standardized connection interface, and the three types of mobile platforms are each provided with a matched transmission connecting piece. For example, the output end of the transmission motor shaft 9 is provided with a flange type standard drive interface, and the standard drive interface includes uniformly distributed positioning pin holes and bolt holes along the circumference. The wheeled mobile platform, the tracked mobile platform, and the bionic mobile platform are each provided with a driven flange plate 8 (driven interface) matched with the flange type standard drive interface. The driven flange plate 8 (driven interface) is provided with a positioning pin groove and a connecting bolt hole. The positioning pin groove of the driven interface is gap-fitted with the positioning pin hole of the standard drive interface, and the connecting bolt hole of the driven interface is coaxially arranged with the bolt hole of the standard drive interface, so as to realize detachable connection with the transmission motor shaft 9 through bolt fastening.

[0064] In the embodiment, as shown in Figure 2 and Figure 3 , the wheeled mobile platform further includes a universal coupling 302 and a wheel set 301. The universal coupling 302 is connected with the transmission motor shaft 9 through the driven interface, the universal coupling 302 rotates synchronously with the transmission motor shaft 9, and the universal coupling 302 synchronously transmits the rotation to the wheel set 301. All the wheels 301 of the wheel set 301 are driving wheels and rotate synchronously with the universal coupling 302, and can be made of high wear-resistant rubber material, which is suitable for high-speed cruising on flat road surfaces. In specific embodiments, the wheel 301 is made of high wear-resistant rubber material, which has good elasticity and wear resistance. The universal coupling 302 can improve the shared chassis 1 of the robot while transmitting power without changing the position of the transmission shaft.

[0065] As shown in Figure 4 , the tracked mobile platform further includes a track wheel 401, an auxiliary wheel 403, a track body 402 with anti-skid convex patterns on the surface, and a connecting rod 404. The track wheel 401 is connected with the transmission motor shaft 9 through the driven interface, and the connecting rod 404 connects the intermediate position transmission motor shaft 9 with the auxiliary wheel 403 of the shared chassis 1. The connecting rod 404 can be lifted by the intermediate position transmission motor to raise / lower the auxiliary wheel 403, so as to realize obstacle crossing. In specific embodiments, the track is made of high-strength wear-resistant material, which has strong grip and passability, and the front wheel can be raised by rotating the connecting rod 404 to pass through the obstacle.

[0066] As shown in Figure 5 and Figure 6 The bionic mobile platform includes a "C" shaped bionic foot, the bionic foot 201 is provided with a convex on the contact surface, is connected with the transmission motor shaft 9 through the driven interface, and is adapted to the narrow pipeline environment through the rolling movement. In specific embodiments, the bionic mobile platform is suitable for narrow pipelines (such as inside the pipeline or narrow space), the bionic foot 201 adopts a C-shaped structure, the bionic foot 201 is provided with a convex on the contact surface with the ground, which can increase the grip, and the robot advances by rolling the C-shaped claws, which can flexibly cross obstacles.

[0067] It should be noted that the bionic foot 201 of the bionic mobile platform can also be replaced by other shapes of bionic foot 201 according to the needs of the actual application scene to adapt to different types of narrow space scenes. And the material of the above mobile platform can be adaptively replaced according to the needs of the actual application scene.

[0068] In this embodiment, the environment perception system integrates various inspection sensor components, including visual perception components, infrared perception components, ultrasonic perception components, laser perception components, and inertial measurement components. And the environment perception system integrates the synchronous positioning and mapping technology (Simultaneous Localization And Mapping, SLAM), which can realize autonomous planning of mobile path and execution of obstacle avoidance strategy.

[0069] In this embodiment, the visual perception component can adopt a high-definition camera 3, the infrared perception component can adopt an infrared thermal imager 4, the ultrasonic perception component can adopt an ultrasonic detector 5, the laser perception component can adopt a laser radar 6, and the inertial measurement component can adopt an inertial measurement unit (Inertial Measurement Unit, abbreviated as IMU). Specifically, the high-definition camera 3, the infrared thermal imager 4, the ultrasonic detector 5, the laser radar 6 and the IMU 7 can be installed on the common chassis 1 in the manner shown in Figure 1 The various inspection sensor components send data to the operation control system in real time through the CAN bus, or directly upload data to the cloud diagnosis system, realize multi-sensor (visual, infrared, ultrasonic, laser) information fusion, to build an environment map and accurately locate.

[0070] In this embodiment, the sensor assembly built-in the common chassis 1 can also be extended as a smart navigation controller, which automatically loads control algorithms according to the current mobile platform type and environmental perception data, such as loading a first mobile control algorithm from the wheel algorithm library to adapt to flat road cruising and plan obstacle avoidance paths. Load a second mobile control algorithm from the track algorithm library to adapt to train track / gravel road anti-skid cruising and dynamically execute obstacle avoidance strategies. Load a third mobile control algorithm from the bionic algorithm library to adapt to narrow pipeline obstacle crossing and run narrow space navigation algorithm. The operation control system provided in this embodiment can optimize the path in real time based on sensor fusion data, automatically adjust the motion of the mobile platform when encountering obstacles, or control the inspection execution system to move.

[0071] In this embodiment, the inspection execution system includes a three-axis mechanical arm 2. The three-axis mechanical arm 2 is installed on the common chassis 1, the mechanical arm base is fixed to the front end position of the chassis, and the mechanical arm end is provided with a grabbing mechanism (claw). The claw adopts an adjustable design, which supports grabbing track debris, samples or small obstacles.

[0072] The operation control unit (OCU) is integrated into the control module of the robot common chassis 1, which is the relay processing unit of the local control and remote instruction of the diagnosis center, and is the core hub of the interaction between the robot and the diagnosis center. In this embodiment, the OCU can adopt an industrial-grade embedded processor, support multi-thread processing, and ensure the real-time performance of data transmission and instruction response. The core functions include receiving instructions issued by the diagnosis center and performing protocol analysis (compatible with CAN bus communication protocol). Upload the preprocessed sensor data and robot state information (such as mobile platform type, mechanical arm posture, energy consumption data, etc.) to the diagnosis center. Implement the switching logic of local control and remote control (default remote control, which can be switched to local manual control in emergency).

[0073] In summary, the embodiment provides a rail transit intelligent inspection robot, which adopts a modular mobile platform design. Three platforms share the same robot chassis and fixed-position transmission motor shaft. The robot can be quickly replaced by manual operation, so that the robot can flexibly select the appropriate movement mode according to the ground environment. The three-axis mechanical arm actuator supports multifunctional operation, such as grabbing obstacles or samples, thereby improving the practicability of the robot. The environment perception system realizes intelligent navigation and high-precision detection. The integration of the operation control unit strengthens the "perception-analysis-decision-execution" closed loop of the robot and the diagnosis center. Through real-time interaction and encrypted transmission of 5G, the efficiency and security of remote operation and maintenance are ensured. The wheeled mobile platform runs quickly and saves energy on flat roads. The tracked mobile platform stably passes through the train track and gravel road. The bionic mobile platform flexibly overcomes obstacles in narrow pipes. Combined with the remote interaction capability of the intelligent control and operation control unit, the inspection efficiency, reliability and self-adaptive capability are greatly improved. There is no need to equip different environments with separate equipment, which reduces the investment and maintenance cost. Meanwhile, the sensor fusion technology and data processing capability of the operation control unit ensure the comprehensiveness and accuracy of the inspection data.

[0074] In one embodiment, as shown in Figure 7 , a control method of a rail transit intelligent inspection robot is provided. The method is applied to the operation control system of the rail transit intelligent inspection robot in Figure 1 for illustration, which includes the following steps:

[0075] S701, a preset inspection task is acquired.

[0076] In the embodiment, the preset inspection task includes an inspection route, a target to be detected and a target detection parameter. In specific embodiments, the target to be detected includes ground cracks, equipment appearance damage, foreign matter, outdoor high-speed rail tracks, gravel ballast beds and reinforced concrete drainage pipes under the tracks, etc. The target detection parameter includes, for example, a gauge deviation threshold value, a crack width threshold value, etc.

[0077] In the embodiment, the preset inspection task can be issued by a cloud diagnosis center or allocated by an inspection robot control center. The embodiment does not limit the issuing process of the preset inspection task. The corresponding inspection task can be loaded for the inspection robot according to the needs of the actual application scene, so as to plan the inspection route, inspection target and inspection parameter.

[0078] S702, the environment perception system is controlled to collect ground environment parameters.

[0079] In the embodiment, after the inspection task starts, the operation control unit cooperatively collects parameters such as ground texture, ground material, ground fluctuation standard deviation and spatial size data through multiple sensor components of the environment perception system as ground environment parameters.

[0080] For example, by starting the laser radar and the IMU, the ground three-dimensional point cloud data and the attitude data can be collected, and the ground relief standard deviation can be calculated. The high-definition camera can be started to collect the ground texture image, and the image recognition algorithm can be used to distinguish the flat road texture (such as cement / asphalt texture), gravel texture, track texture and pipeline inner wall texture. The ultrasonic detector is started to collect spatial distance data to determine whether it is a narrow pipeline environment. In the case of a spatial diameter ≤50 cm, it is determined that the ground environment belongs to a narrow pipeline environment. It should be noted that the judgment threshold of different ground environments can be determined according to the needs of the actual application scene.

[0081] S703, determining the target mobile platform according to the ground environment parameters. The target mobile platform includes any one of a wheeled mobile platform, a tracked mobile platform and a bionic mobile platform.

[0082] In the embodiment, the ground environment type in which the inspection robot is located can be determined according to the ground environment parameters collected in the foregoing steps and the parameter threshold values corresponding to different types of ground environments. The ground environment type in which the inspection robot is located can also be directly determined according to the image data collected by the environment perception system and in combination with the image analysis algorithm.

[0083] In one embodiment, the environment perception system includes at least one of a visual perception component, an infrared perception component, an ultrasonic perception component, a laser perception component and an inertial measurement component. The ground environment parameters include ground texture, ground material, ground relief standard deviation and spatial size data. The target mobile platform is determined according to the ground environment parameters, including:

[0084] If it is determined according to the ground environment parameters that the ground environment belongs to the first road surface condition, the target mobile platform is determined to be a wheeled mobile platform. The first road surface condition is a flat road surface.

[0085] If it is determined according to the ground environment parameters that the ground environment belongs to the second road surface condition, the target mobile platform is determined to be a tracked mobile platform. The second road surface condition is a train track or a gravel road surface.

[0086] If it is determined according to the ground environment parameters that the ground environment belongs to the third road surface condition, the target mobile platform is determined to be a bionic mobile platform. The third road surface condition is a narrow pipeline.

[0087] For example, when the fluctuation standard deviation is less than or equal to a preset threshold value, and the road surface is free of ballast or pipeline structure, the ground environment is determined to be flat road surface, and it can be determined that the target mobile platform is a wheeled mobile platform. When the fluctuation standard deviation is greater than the preset threshold value, and the road surface has a sleeper / ballast texture, the ground environment is determined to be a train track or a ballast road surface, and it can be determined that the target mobile platform is a tracked mobile platform. When the spatial diameter is less than or equal to a preset size, and the road surface texture has an inner wall texture, the ground environment is determined to be a narrow pipeline, and it can be determined that the target mobile platform is a bionic mobile platform.

[0088] S704, in the case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, loading the movement control algorithm and the inspection control algorithm corresponding to the target mobile platform, and controlling the chassis driving system to drive the target mobile platform to move along the inspection route according to the movement control algorithm, controlling the environment perception system to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and controlling the inspection execution system to perform an auxiliary task according to the movement control algorithm or the inspection control algorithm.

[0089] In this embodiment, the movement control algorithm can be called from the autonomous planning and obstacle avoidance strategy library built in the operation control system, and the autonomous planning and obstacle avoidance strategy library includes a wheeled algorithm library, a tracked algorithm library and a bionic algorithm library. The inspection control algorithm corresponds to a specific preset inspection task in an actual application scenario, including a sensor sampling frequency, a detection parameter threshold value, an inspection route, an inspection target, etc. The auxiliary task includes grabbing obstacles or samples to be detected.

[0090] In this embodiment, after the preset inspection task starts to be executed, it is first judged whether the detachable mobile platform connected to the chassis driving system is the target mobile platform, and in the case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, the movement control algorithm and the inspection control algorithm corresponding to the target mobile platform are loaded. The movement control algorithm includes a first movement control algorithm, a second movement control algorithm and a third movement control algorithm. The inspection control algorithm includes a first inspection control algorithm, a second inspection control algorithm and a third inspection control algorithm.

[0091] In the case where the target mobile platform is a wheeled mobile platform, the chassis driving system is controlled to drive the wheeled mobile platform to move along the inspection route according to the first movement control algorithm. The environment perception system is controlled to collect the target detection parameter of the target to be detected and perform fault detection according to the first inspection control algorithm. The first movement control algorithm includes a first obstacle avoidance strategy.

[0092] In the case that the target mobile platform is a tracked mobile platform, the chassis driving system is controlled to drive the tracked mobile platform to move along the inspection route according to a second mobile control algorithm. The environmental perception system is controlled to collect target detection parameters of the target to be detected and perform fault detection according to a second inspection control algorithm. The second mobile control algorithm includes a second obstacle avoidance strategy.

[0093] In the case that the target mobile platform is a bionic mobile platform, the chassis driving system is controlled to drive the wheeled mobile platform to move along the inspection route according to a third mobile control algorithm. The environmental perception system is controlled to collect target detection parameters of the target to be detected and perform fault detection according to a third inspection control algorithm. The third mobile control algorithm includes a third obstacle avoidance strategy.

[0094] For example, in the case that the target mobile platform is a wheeled mobile platform, a first mobile control algorithm in the wheeled algorithm library is called to control the chassis driving system to drive the wheel group through the universal joint to travel along the inspection route at a cruising speed of 3 km / h ± 0.5 km / h, steering is achieved through differential control, and the IMU corrects the travel trajectory in real time. The first obstacle avoidance strategy can be to re-plan the mobile path or to control the three-axis mechanical arm to move away the obstacle.

[0095] In the case that the target mobile platform is a tracked mobile platform, a second mobile control algorithm in the tracked algorithm library is called to control the chassis driving system to drive the tracked mobile platform to travel along the inspection route at a cruising speed of 1.5 km / h ± 0.3 km / h, and when an obstacle is encountered, the auxiliary wheel is lifted by the control of the connecting rod (the lifting angle is fed back in real time by the angle sensor). The second obstacle avoidance strategy can be to control the connecting rod of the tracked mobile platform to lift the auxiliary wheel to move over the obstacle or to control the three-axis mechanical arm to move away the obstacle.

[0096] In the case that the target mobile platform is a bionic mobile platform, a third mobile control algorithm in the bionic algorithm library is called to control the chassis driving system to drive the "C" shaped bionic foot to move along the inspection route through rolling motion, and the IMU monitors the posture in real time to avoid overturning. The third obstacle avoidance strategy can be to control the bionic foot to roll over the obstacle or to control the three-axis mechanical arm to move away the obstacle.

[0097] S705, in the case that the detachable mobile platform connected to the chassis driving system is not the target mobile platform, the chassis driving system is controlled to stop, platform replacement prompt information is generated and uploaded to the diagnosis center, and the chassis driving system is replaced by the target mobile platform until the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform. Wherein, the platform replacement prompt information includes the positioning information of the inspection robot.

[0098] In this embodiment, in the case that it is determined that the detachable mobile platform connected with the chassis driving system is not the target mobile platform, the inspection robot is controlled to stay in place, platform replacement prompt information is generated and uploaded to the cloud diagnosis center to remind the staff to replace the detachable mobile platform in time at the specified location, so that the detachable mobile platform meets the target mobile platform and adapts to the road surface environment in front of the inspection route, so as to continue to perform the inspection task.

[0099] To sum up, the embodiment provides a control method of an inspection robot, which covers flat road surface, track, gravel and pipeline scenes through quick switching of three mobile platforms, without the need of separately arranging equipment. The functions of environmental perception, detection, mechanical arm operation and remote interaction are integrated to form a complete inspection closed loop. The high-speed cruising of the wheeled platform improves the inspection efficiency in flat areas, the high-precision detection of the tracked platform guarantees the reliability of track detection, and the flexible obstacle crossing of the bionic platform reduces the overall procurement and maintenance costs. The collaborative obstacle avoidance, fault alarm and encrypted data transmission control steps ensure the safety and controllability of the inspection process.

[0100] In one of the embodiments, as shown in Figure 8 the control method of the intelligent inspection robot for rail transit further comprises:

[0101] S801, in the case that the environmental perception system detects ground environment changes, preset inspection task changes or robot self-checking state changes, a platform replacement instruction is generated;

[0102] S802, the target mobile platform is re-determined according to the platform replacement instruction.

[0103] In this embodiment, the replacement trigger conditions of the detachable mobile platform are mainly determined by the environmental perception system in cooperation with the operation control unit (OCU) based on multi-source data, which specifically includes the following types:

[0104] First, the ground environment feature change trigger, the high-definition camera is combined with the image recognition algorithm to analyze the ground texture and material. For example, when it is detected that the road surface changes from flat cement texture to irregular gravel texture, the tracked or bionic platform replacement instruction is triggered. The three-dimensional point cloud map constructed by laser radar scanning data can also be used for auxiliary judgment. If the standard deviation of ground fluctuation exceeds the set threshold and the continuous time length exceeds 5 seconds, it is determined that the road surface is not flat, and the platform switching process is started.

[0105] Second, the inspection task demand change trigger, the diagnosis center issues specific task instructions through the OCU according to the maintenance plan or sudden failure of the track facility. For example, when switching from regular track surface inspection to track internal structure detection, the OCU triggers the bionic platform replacement process due to the need to enter narrow spaces. If it involves rapid investigation of a large area of track area, the wheeled platform is replaced to improve the moving speed.

[0106] Third, the robot self-checking state triggers. During the driving process of the wheeled platform, if the motor current continuously exceeds the rated value by 20% and the vehicle speed is lower than the set cruising speed by more than 30% for a duration of 10 seconds, the OCU determines that the wheeled platform is blocked on the current road surface and may need to be switched to the tracked platform to enhance the passability. If the tracked platform appears to have a tracked slip frequency of more than 5 times per minute and an advancing distance that is lower than the expected value by 50%, it is considered to be replaced by a platform that is more suitable for the terrain.

[0107] It should be noted that the actual situation of the ground environment change, the preset inspection task change or the robot self-checking state change can be customized according to the needs of the actual application scene. The platform replacement instruction can include the specific type of the target mobile platform, or instruct the operation control unit to re-execute S702-S703.

[0108] In one embodiment, the inspection execution system includes a three-axis mechanical arm, the base of the three-axis mechanical arm is fixedly installed at the front end of the common chassis, and a grabbing mechanism is arranged at the end of the three-axis mechanical arm. The grabbing mechanism is used to assist in removing track obstacles or grabbing detection targets.

[0109] According to the mobile control algorithm or the inspection control algorithm, the inspection execution system performs an auxiliary task, including:

[0110] According to the mobile control algorithm, the three-axis mechanical arm assists in removing track obstacles.

[0111] According to the inspection control algorithm, the three-axis mechanical arm grabs the detection target.

[0112] In this embodiment, the auxiliary task of removing track obstacles is usually triggered when the inspection robot moves according to the mobile control algorithm along the specified path. The auxiliary task of grabbing the detection target is usually triggered when the inspection robot identifies the fault of the detection target according to the inspection control algorithm.

[0113] In this embodiment, the cooperative control of the three-axis mechanical arm and the mobile platform is realized through the closed-loop linkage of the intelligent navigation controller extended by the environment perception system built in the common chassis and the operation control unit (OCU). The core logic includes three levels of motion synchronization, action planning and obstacle avoidance cooperation.

[0114] Motion synchronization is based on the action timing alignment of the mechanical arm and the mobile platform through the same set of time reference. For example, when the mobile platform executes a turning instruction, the OCU sends a “pause operation” signal to the mechanical arm controller to avoid the mechanical arm from deviating from the target position due to inertia during the turning process. After the mobile platform completes the turning (after the IMU feedback posture is stable), the OCU issues an instruction for the mechanical arm to continue working.

[0115] The speed signal of the mobile platform is transmitted to the robot arm controller in real time as a reference for the speed of the robot arm movement. For example, when the mobile platform moves at a speed of 0.5 m / s, the extension / contraction speed of the robot arm is automatically matched to 0.3 m / s (preset proportion coefficient), ensuring that the relative position is stable when the target is grabbed.

[0116] The action planning is based on the three-dimensional environment map generated by the environment perception system and provided to the OCU to complete the path planning of the mobile platform and the trajectory planning of the robot arm. For example, when an obstacle (such as gravel) is detected beside the track, the system first plans the parking position of the mobile platform, and then calculates the grabbing trajectory of the robot arm based on the position. When the laser radar detects an obstacle in front of the mobile platform, the obstacle avoidance collaborative control logic is triggered synchronously. The collaborative control logic includes emergency braking of the mobile platform, rapid retraction of the robot arm to a safe posture, and resumption of work of the robot arm after the mobile platform plans a detour path and executes the path.

[0117] In one embodiment, the working modes of the inspection execution system include a remote instruction control mode, a local autonomous control mode, and a preset trajectory control mode. The inspection robot control method further includes:

[0118] In the case of receiving a grabbing control instruction issued by the diagnosis center, the working mode of the inspection execution system is determined to be the remote instruction control mode, and the auxiliary task is executed according to the grabbing control instruction; the grabbing control instruction includes grabbing coordinates, clamping jaw force, and movement speed;

[0119] In the case of communication interruption with the diagnosis center or local control instruction triggering, the working mode of the inspection execution system is determined to be the local autonomous control mode, and a real-time grabbing trajectory is autonomously planned based on real-time environment data collected by the environment perception system, so as to execute the auxiliary task according to the real-time grabbing trajectory;

[0120] In the case of a standard task triggering on the inspection route, the working mode of the inspection execution system is determined to be the preset trajectory control mode, and a preset grabbing trajectory corresponding to the standard task is loaded to execute the auxiliary task according to the preset grabbing trajectory.

[0121] In this embodiment, the control mode of the robot arm includes remote instruction control (default), local autonomous control (emergency), and preset trajectory control (regular task), and the three modes are seamlessly switched through the OCU. The remote instruction control receives sensor data through the OCU by the diagnosis center, generates an instruction package containing “grabbing coordinates, clamping jaw force, and movement speed”, sends the encrypted instruction package to the OCU, the OCU decrypts and checks the authority and forwards it to the robot arm controller, the controller drives the joint motor to execute the action, and at the same time feeds back the joint angle to the OCU, and the OCU returns to the diagnosis center to form a closed loop.

[0122] When the communication is interrupted or the diagnostic center issues a "local control" instruction, the robot arm automatically switches to the local control mode, and the OCU makes independent decisions based on real-time data from the environmental perception system.

[0123] When repetitive and standardized tasks need to be performed, such as detecting each rail bolt (the robot arm needs to carry an ultrasonic probe and align it with the bolt position one by one) or scanning the inner wall of a pipeline (the robot arm's end rotates 360° around its own axis), the preset trajectory control mode is used. The robot arm works with the mobile platform through the built-in controller in the chassis. For example, in a narrow pipeline environment, the bionic mobile platform cooperates with the robot arm to achieve precise grabbing and cleaning.

[0124] In one embodiment, the fault types of the target to be detected include a first type of fault and a second type of fault. In this embodiment, the first type of fault is a fault with lower severity, and the second type of fault is a fault with higher severity. The inspection control method provided in this embodiment further includes:

[0125] If the first type of fault is detected and it is determined according to the ground environment parameters that the ground environment does not belong to the third road surface condition, the target detection parameters are uploaded to the diagnostic center in real time.

[0126] In this embodiment, the target data collected by the sensor (such as track gauge, crack width, and equipment temperature) is preprocessed by the operation control unit and can be uploaded to the diagnostic center every 2 seconds through the 5G network. It should be noted that the specific method and parameters of real-time uploading to the diagnostic center can be determined according to the needs of the actual application scenario.

[0127] If the second type of fault is detected and it is determined according to the ground environment parameters that the ground environment belongs to the third road surface condition, the target detection parameters are stored in the local storage, and after the ground environment changes to the first road surface condition or the second road surface condition, the target detection parameters in the local storage are uploaded to the diagnostic center.

[0128] In this embodiment, if the robot is in a narrow pipeline environment (5G signal is weak), the operation control unit locally stores the inspection data, and uploads the data to the diagnostic center in batches after leaving the pipeline.

[0129] If the second type of fault is detected, the fault position movement trajectory, the alarm instruction, and the position upload instruction are generated in real time, the chassis driving system is controlled to drive the target mobile platform to move to the fault point position according to the fault position movement trajectory, sound and light alarm is performed according to the alarm instruction, and the fault position, fault type, and image data are uploaded to the diagnostic center according to the position upload instruction.

[0130] In this embodiment, if a fault is detected (such as a track gauge deviation of ±3 mm, a crack width of ≥10 cm, or a device temperature of ≥60℃), the operation control unit triggers a local audible and visual alarm, controls the robot to stop within 1 m of the fault point, and uploads the fault location, type, and image data.

[0131] In one embodiment, after the inspection task is completed, the operation control unit can also generate an energy consumption report (including the energy consumption of each module and the remaining endurance) and upload it to the diagnosis center, so that the staff can real-time master the state information of the inspection robot.

[0132] In summary, the inspection robot control method provided in this embodiment can realize quick replacement of the mobile platform through modular design, and realize multi-scene adaptive inspection in combination with the environment perception system and the operation control unit (OCU).

[0133] The following describes the specific implementation process in combination with three typical environments and Figure 9 The inspection task execution program is shown in FIG. 5, and the specific implementation process is described in detail.

[0134] In a more detailed embodiment, the inspection scheme of the wheeled mobile platform on the flat road surface (taking the maintenance passage of the high-speed railway station as an example) is described. This embodiment is aimed at the concrete maintenance passage in the high-speed railway station, the square in the station, and the flat transition section connecting the track. This scene is open and unobstructed, and it is required to quickly cover a large area. The main inspection targets are: ground cracks in the passage, appearance damage of peripheral facilities (cable trough, signal box), surface foreign matters (scattered parts, accumulated water), and device temperature abnormalities (such as signal box heat dissipation failure).

[0135] During the equipment preparation and installation stage, it is checked that the wheels of the wheeled mobile platform are not worn, the universal coupling is flexible in rotation, and the positioning pin and the bolt hole have normal matching accuracy. The wheeled platform is installed, the platform positioning part is aligned with the common chassis positioning hole, after preliminary positioning, the driven interface of the universal coupling is aligned with the flange type standard interface of the transmission motor shaft, the bolt is fastened with a torque wrench, and the power connection is completed. The OCU is activated, the OCU is started, the connection with the diagnosis center 5G encrypted link is completed, the default remote control mode is set, the wheeled platform is automatically identified, and the “wheeled algorithm library” is loaded.

[0136] During the environment perception system startup stage, the laser radar and the IMU are started to cooperatively build a three-dimensional environment map, and a cruise path along the center line of the passage is planned. The inspection sensors are activated, the high-definition camera is installed at the front end of the chassis, one frame of image is shot every 0.5 seconds, the ground cracks and the foreign matters with a diameter of ≥5 mm are identified through an edge detection algorithm, the infrared thermal imager focuses on the peripheral devices, the temperature measurement range is -20℃~150℃, and the over-temperature threshold is set to 60℃ (the upper limit of the normal working temperature of the signal box).

[0137] During the inspection execution phase, the robot travels along the planned path. The universal coupling synchronously transmits motor power to the wheels, and steering is achieved through differential control. The IMU corrects the driving trajectory in real time. The obstacle avoidance logic includes that when the lidar detects a dynamic obstacle (such as a person) within 10m ahead, the OCU instructs the robot to decelerate to 0.5m / s and detour (the detour distance is ≥ 1.5 times the diameter of the obstacle). After the sensor data is preprocessed by the OCU, it is uploaded to the diagnostic center every 2 seconds via 5G. If a ground crack ≥ 10cm wide is detected, the OCU triggers a local audible and visual alarm and stops within 1m of the potential hazard point.

[0138] After receiving the "Stop Inspection" instruction from the diagnostic center at the end of the mission, the robot travels to the endpoint and brakes. The OCU generates an energy consumption report and uploads it to the diagnostic center for reference in the next use.

[0139] Based on the above steps, the wheeled platform achieves efficient inspection of large flat areas by combining high-speed cruising (3km / h) with wide-field sensors, while taking into account driving stability and energy consumption optimization (range ≥4h).

[0140] In another more detailed embodiment, the inspection scheme of tracked mobile platform on train track and gravel road surface (taking outdoor railway section as an example) is described. This embodiment is for outdoor high-speed rail track, gravel track bed between tracks and transition gravel section, and needs to detect track cracks, track gauge deviation, missing / loose fasteners and track bed accumulation.

[0141] During the equipment preparation and installation phase, the tracked mobile platform was inspected. The tracks were found to be free of tears, the track wheels and auxiliary wheels rotated smoothly, and the angle sensor of the linkage obstacle-crossing mechanism was calibrated correctly. The tracked platform was installed, initially positioned with the chassis through the positioning holes. The driven interface of the track drive wheel and the flange of the transmission motor shaft were aligned, and the bolts were tightened. The tracks were then wrapped around the track wheels and auxiliary wheels, and the tension was adjusted. The OCU was activated, the "track algorithm library" was loaded, the cruising speed was 1.5 km / h, and the initial angle of the linkage obstacle-crossing mechanism was set to 0° (auxiliary wheel in contact with the ground). The angle data was uploaded to the diagnostic center in real time.

[0142] During the environmental perception system startup phase, a 3D map of the track is constructed using LiDAR and IMU, with a positioning accuracy of ±5cm, ensuring the robot travels along the track centerline (5cm±2cm from the inner side of the rail). Dedicated sensors are deployed: an ultrasonic detector emits a signal every 0.1 seconds to detect internal cracks in the rail; a dual-line laser displacement meter is installed on the side of the connecting rod, measuring the track gauge at a 10mm sampling interval, with an out-of-tolerance threshold set at ±3mm.

[0143] In the inspection execution phase, the tracked platform increases the ground contact area to adapt to the gravel bed; when encountering a depression between the sleepers, the OCU instructs the middle motor to rotate, and the connecting rod lifts the auxiliary wheel to realize obstacle crossing. The laser displacement meter calculates the track gauge value in real time, and when the deviation exceeds the limit, the OCU triggers an audible alarm and stops. The high-definition camera takes pictures of the abnormal area. The camera identifies missing / lazy fasteners, and the infrared thermal imager monitors the track surface temperature difference; when the track surface is found to be gravel, the OCU instructs the three-axis mechanical arm to pick up and remove it, and the operation image is transmitted back to the diagnosis center.

[0144] In the task end phase, the robot returns to the starting point and brakes, and the OCU uploads the track gauge deviation statistics, crack distribution and energy consumption data for reference for the next use.

[0145] The tracked platform adapts to complex terrain on the track and gravel road surface through differential control and connecting rod obstacle crossing mechanism, and realizes high-precision quantitative evaluation of track parameters through special track gauge measurement and ultrasonic detection modules.

[0146] In another detailed embodiment, the inspection scheme of a bionic mobile platform in a narrow pipeline (taking the drainage pipe under the track as an example) is described. This embodiment is aimed at the reinforced concrete drainage pipe under the track, which is narrow in space and needs to detect wall corrosion, blockages and interface leaks.

[0147] In the equipment preparation and installation phase, the bionic mobile platform is checked, the "C" shaped bionic foot is made of polyurethane material, the contact surface has no deformation, the joint bearing is well lubricated. The bionic platform is installed by positioning the hole and the chassis, aligning the bionic foot from the driven interface and the transmission motor shaft flange plate, tightening the bolts, and completing power transmission. The OCU is activated, the "bionic algorithm library" is loaded, and the IMU starts posture monitoring.

[0148] In the environment perception system startup phase, the laser radar and camera are used to build a map of the inside of the pipeline. The camera is installed at the end of the mechanical arm and takes pictures of the inner wall every 0.3 seconds. The image segmentation algorithm is used to identify corrosion areas and cracks; the miniature ultrasonic detector is close to the inner wall to detect the wall thickness. A wall thickness reduction of ≥20% is considered to be excessive corrosion.

[0149] In the inspection execution phase, when the laser radar detects an obstruction in front, the OCU instructs the machine to stop, the mechanical arm extends to the obstruction, and the camera determines whether the obstruction can be removed. If it can be removed, it is picked up and removed. When the 5G signal in the pipeline is weak, the OCU stores the data locally and uploads it to the diagnosis center in batches after leaving the pipeline.

[0150] In the task end phase, after the robot leaves the pipeline, the OCU uploads the corrosion area distribution map, crack location and energy consumption report for reference for the next use.

[0151] The bionic platform rolls over by the "C" shaped foot and the miniaturized sensor, adapts to the limited space of the narrow pipeline, combines with the end operation of the mechanical arm, and realizes the integrated operation of the pipeline inner wall defect detection and the small blockage removal.

[0152] It should be understood that, although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0153] Based on the same inventive concept, the embodiments of the present application also provide a kind of inspection robot control device for realizing the control method of the above-mentioned inspection robot. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitation in one or more inspection robot control device embodiments provided below can refer to the limitation of the inspection robot control method in the above, which will not be repeated here.

[0154] In one embodiment, as shown in Figure 10 A control device 1000 of an intelligent inspection robot for rail transit is provided, comprising: a task acquisition module 1010, an environment perception module 1020, a platform determination module 1030 and an inspection execution module 1040, wherein:

[0155] The task acquisition module 1010 is configured to acquire a preset inspection task, wherein the preset inspection task comprises an inspection route, a target to be detected and a target detection parameter.

[0156] The environment perception module 1020 is configured to control the environment perception system to collect a ground environment parameter.

[0157] The platform determination module 1030 is configured to determine a target mobile platform according to the ground environment parameter, wherein the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform and a bionic mobile platform.

[0158] The inspection execution module 1040 is configured to, in a case where the detachable mobile platform connected with the chassis driving system is the target mobile platform, load a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform, control the chassis driving system to drive the target mobile platform to move along the inspection route according to the mobile control algorithm, control the environment perception system to collect target detection parameters of the target to be detected and perform fault detection according to the inspection control algorithm, and control the inspection execution system to perform auxiliary tasks according to the mobile control algorithm or the inspection control algorithm; in a case where the detachable mobile platform connected with the chassis driving system is not the target mobile platform, control the chassis driving system to stop, generate a platform replacement prompt information and upload the platform replacement prompt information to the diagnosis center until the detachable mobile platform connected with the chassis driving system is replaced by the target mobile platform.

[0159] The above-mentioned various modules in the inspection robot control device can be realized by software, hardware, or a combination thereof, in whole or in part. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0160] In an embodiment, a computer device, which can be a terminal, has an internal structure as shown in Figure 11 The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program is executed by the processor to implement a control method of an intelligent inspection robot for rail transit. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, a trackball, or a touchpad arranged on the shell of the computer device. The input device can also be an external keyboard, a touchpad, or a mouse, etc.

[0161] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. It should be understood that, Figure 11 The solid line block in the figure represents a device with a physical entity. The dashed line block represents an operating system and a computer program without a physical entity.

[0162] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0163] Obtaining a preset inspection task; wherein the preset inspection task comprises an inspection route, a target to be detected, and a target detection parameter;

[0164] Controlling the environment perception system to collect a ground environment parameter;

[0165] Determining a target mobile platform according to the ground environment parameter; the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform, and a bionic mobile platform;

[0166] In a case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, loading a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform, and controlling the chassis driving system to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, controlling the environment perception system to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and controlling the inspection execution system to perform an auxiliary task according to the mobile control algorithm or the inspection control algorithm;

[0167] In a case where the detachable mobile platform connected to the chassis driving system is not the target mobile platform, controlling the chassis driving system to stop, generating a platform replacement prompt information and uploading it to a diagnosis center, until the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform.

[0168] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0169] Obtaining a preset inspection task; wherein the preset inspection task comprises an inspection route, a target to be detected, and a target detection parameter;

[0170] Controlling the environment perception system to collect a ground environment parameter;

[0171] The target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform, and a bionic mobile platform;

[0172] In a case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform are loaded, the chassis driving system is controlled to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, the environment sensing system is controlled to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and the auxiliary task is performed by the inspection execution system according to the mobile control algorithm or the inspection control algorithm;

[0173] In a case where the detachable mobile platform connected to the chassis driving system is not the target mobile platform, the chassis driving system is controlled to stop, platform replacement prompt information is generated and uploaded to the diagnosis center, and the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform.

[0174] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0175] A preset inspection task is acquired; wherein the preset inspection task comprises an inspection route, a target to be detected, and a target detection parameter;

[0176] The environment sensing system is controlled to collect a ground environment parameter;

[0177] The target mobile platform is determined according to the ground environment parameter; the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform, and a bionic mobile platform;

[0178] In a case where the detachable mobile platform connected to the chassis driving system is the target mobile platform, a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform are loaded, the chassis driving system is controlled to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, the environment sensing system is controlled to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and the auxiliary task is performed by the inspection execution system according to the mobile control algorithm or the inspection control algorithm;

[0179] In a case where the detachable mobile platform connected to the chassis driving system is not the target mobile platform, the chassis driving system is controlled to stop, platform replacement prompt information is generated and uploaded to the diagnosis center, and the detachable mobile platform connected to the chassis driving system is replaced by the target mobile platform.

[0180] 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, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0181] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0182] 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 of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A control method of a rail transit intelligent inspection robot, characterized in that, The rail transit intelligent inspection robot comprises an operation control system, an environment perception system, a chassis driving system, an inspection execution system, a shared chassis and a plurality of detachable mobile platforms, wherein the chassis driving system is in driving connection with the detachable mobile platforms; the method comprises: acquiring a preset inspection task; wherein the preset inspection task comprises an inspection route, a target to be detected and a target detection parameter; controlling the environment perception system to collect ground environment parameters; determining a target mobile platform according to the ground environment parameters; the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform and a bionic mobile platform; the chassis driving system comprises a driving motor, the driving motor is arranged on the shared chassis, a standardized connection interface is arranged on a driving motor shaft of the driving motor, and each mobile platform is provided with a driving connection piece matched with the connection interface; in the case that the detachable mobile platform connected with the chassis driving system is the target mobile platform, loading a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform, controlling the chassis driving system to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm, controlling the environment perception system to collect the target detection parameter of the target to be detected and to perform fault detection according to the inspection control algorithm, and controlling the inspection execution system to perform an auxiliary task according to the mobile control algorithm or the inspection control algorithm; in the case that the detachable mobile platform connected with the chassis driving system is not the target mobile platform, controlling the chassis driving system to stop, generating platform replacement prompt information and uploading the platform replacement prompt information to a diagnosis center until the detachable mobile platform connected with the chassis driving system is replaced by the target mobile platform; the determination of the target mobile platform according to the ground environment parameters comprises: if it is determined according to the ground environment parameters that the ground environment belongs to a first road surface condition, determining that the target mobile platform is a wheeled mobile platform; the first road surface condition is a flat road surface; if it is determined according to the ground environment parameters that the ground environment belongs to a second road surface condition, determining that the target mobile platform is a tracked mobile platform; the second road surface condition is a train track or a gravel road surface; if it is determined according to the ground environment parameters that the ground environment belongs to a third road surface condition, determining that the target mobile platform is a bionic mobile platform; the third road surface condition is a narrow pipeline; the method further comprises: generating a platform replacement instruction in the case that the environment perception system detects a change in the ground environment, a change in the preset inspection task or a change in the self-checking state of the robot; redetermining the target mobile platform according to the platform replacement instruction.

2. The method of claim 1, wherein, The environment perception system comprises at least one of a visual perception component, an infrared perception component, an ultrasonic perception component, a laser perception component and an inertial measurement component; the ground environment parameters comprise ground texture, ground material, ground fluctuation standard deviation and spatial size data.

3. The method of claim 2, wherein, the control of the chassis driving system to drive the target mobile platform to move according to the inspection route according to the mobile control algorithm comprises: In a case where the target mobile platform is a wheeled mobile platform, the chassis driving system is controlled to drive the wheeled mobile platform to move along the inspection route according to a first mobile control algorithm; the first mobile control algorithm comprises a first obstacle avoidance strategy; In a case where the target mobile platform is a tracked mobile platform, the chassis driving system is controlled to drive the tracked mobile platform to move along the inspection route according to a second mobile control algorithm; the second mobile control algorithm comprises a second obstacle avoidance strategy; In a case where the target mobile platform is a bionic mobile platform, the chassis driving system is controlled to drive the wheeled mobile platform to move along the inspection route according to a third mobile control algorithm; the third mobile control algorithm comprises a third obstacle avoidance strategy.

4. The method of claim 1, wherein, The inspection execution system comprises a three-axis mechanical arm, a base of the three-axis mechanical arm is fixedly installed at a front end of the common chassis, and a grabbing mechanism is arranged at an end of the three-axis mechanical arm, the grabbing mechanism is used to assist in removing track obstacles or grabbing a target to be detected; The control of the inspection execution system according to the mobile control algorithm or the inspection control algorithm to perform an auxiliary task comprises: The three-axis mechanical arm is controlled according to the mobile control algorithm to assist in removing track obstacles; The three-axis mechanical arm is controlled according to the inspection control algorithm to grab a target to be detected.

5. The method of claim 4, wherein, The working mode of the inspection execution system comprises a remote instruction control mode, a local autonomous control mode and a preset trajectory control mode; The method further comprises: In a case where a grabbing control instruction is received from the diagnosis center, the working mode of the inspection execution system is determined as the remote instruction control mode, and the auxiliary task is performed according to the grabbing control instruction; the grabbing control instruction comprises grabbing coordinates, a clamping force and a movement speed; In a case where communication with the diagnosis center is interrupted or a local control instruction is triggered, the working mode of the inspection execution system is determined as the local autonomous control mode, a real-time grabbing trajectory is autonomously planned based on real-time environmental data collected by an environmental perception system, and the auxiliary task is performed according to the real-time grabbing trajectory; In a case where a standard task on the inspection route is triggered, the working mode of the inspection execution system is determined as the preset trajectory control mode, a preset grabbing trajectory corresponding to the standard task is loaded, and the auxiliary task is performed according to the preset grabbing trajectory.

6. The method of claim 1, wherein, The fault type of the target to be detected comprises a first type fault and a second type fault; The method further comprises: If a first type fault is detected and it is determined according to the ground environmental parameters that the ground environment does not belong to a third road surface, the target detection parameters are uploaded to the diagnosis center in real time; If a second type fault is detected and it is determined according to the ground environmental parameters that the ground environment belongs to a third road surface, the target detection parameters are stored in a local storage, and after the ground environment changes to a first road surface or a second road surface, the target detection parameters in the local storage are uploaded to the diagnosis center. If the second type of fault is detected, a real-time fault location moving track, an alarm instruction and a location uploading instruction are generated, the chassis driving system is controlled to drive the target mobile platform to move to the fault point position according to the fault location moving track, sound and light alarm is performed according to the alarm instruction, and the fault location, the fault type and image data are uploaded to the diagnosis center according to the location uploading instruction.

7. A control device of a rail transit intelligent inspection robot, characterized in that, The track intelligent inspection robot comprises an operation control system, an environment perception system, a chassis driving system, an inspection execution system, a common chassis and a plurality of detachable mobile platforms, wherein the chassis driving system is in transmission connection with the detachable mobile platforms; the device comprises: a task acquisition module configured to acquire a preset inspection task; wherein the preset inspection task comprises an inspection route, a target to be detected and a target detection parameter; an environment perception module configured to control the environment perception system to collect a ground environment parameter; a platform determination module configured to determine a target mobile platform according to the ground environment parameter; the target mobile platform comprises any one of a wheeled mobile platform, a tracked mobile platform and a bionic mobile platform; an inspection execution module configured to, in a case where the detachable mobile platform connected with the chassis driving system is the target mobile platform, load a mobile control algorithm and an inspection control algorithm corresponding to the target mobile platform, control the chassis driving system to drive the target mobile platform to move along the inspection route according to the mobile control algorithm, control the environment perception system to collect the target detection parameter of the target to be detected and perform fault detection according to the inspection control algorithm, and control the inspection execution system to perform an auxiliary task according to the mobile control algorithm or the inspection control algorithm; in a case where the detachable mobile platform connected with the chassis driving system is not the target mobile platform, control the chassis driving system to stop, generate platform replacement prompt information and upload the platform replacement prompt information to a diagnosis center until the detachable mobile platform connected with the chassis driving system is replaced by the target mobile platform; the platform determination module is further configured to, in a case where the ground environment belongs to a first road surface condition according to the ground environment parameter, determine the target mobile platform as the wheeled mobile platform; the first road surface condition is a flat road surface; in a case where the ground environment belongs to a second road surface condition according to the ground environment parameter, determine the target mobile platform as the tracked mobile platform; the second road surface condition is a train track or a gravel road surface; in a case where the ground environment belongs to a third road surface condition according to the ground environment parameter, determine the target mobile platform as the bionic mobile platform; the third road surface condition is a narrow pipeline; the platform determination module is further configured to, in a case where the environment perception system detects a ground environment change, a preset inspection task change or a robot self-checking state change, generate a platform replacement instruction; and redetermine the target mobile platform according to the platform replacement instruction.

8. A rail transit intelligent inspection robot, characterized in that, comprise: The operation control system, the environment perception system, the chassis driving system, the inspection execution system, the shared chassis and the plurality of detachable mobile platforms, wherein the operation control system, the environment perception system, the chassis driving system and the inspection execution system are arranged on the shared chassis; the operation control system is connected with the environment perception system, the chassis driving system and the inspection execution system respectively, and the chassis driving system is drivingly connected with the detachable mobile platforms. The operation control system is used for executing the steps of the control method of the rail transit intelligent inspection robot according to any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the control method of the rail transit intelligent inspection robot according to any one of claims 1 to 6.

Images