Unmanned operation sewage vehicle for airplane

Abstract

The invention relates to the technical field of airport ground service equipment, and discloses an unmanned operation sewage vehicle for airplanes, which comprises a vehicle body with an unmanned system and an operation system, the operation system comprises a lifting platform, a distance measuring part, an operation part, an operation controller and a visual system; a depth camera is arranged on the operation part; the operation controller receives distance information measured by the distance measuring part and adjusts the height of the lifting platform according to the distance information, and the visual system is used for recognizing the sewage cleaning interface cover plate, the sewage cleaning interface and the sewage discharge valve according to information collected by the depth camera and estimating three-dimensional poses; the control system is used for controlling the operation part through the operation controller according to the three-dimensional pose information so as to realize opening of the clean sewage interface cover plate, butt joint of the clean sewage interface, opening of the sewage discharge valve, releasing of connection of the clean sewage interface, closing of the sewage discharge valve and closing of the clean sewage interface cover plate; the vehicle has unmanned and intelligent characteristics, and people are liberated from an unfriendly working environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of airport ground service equipment, in particular to an unmanned operation sewage vehicle for aircraft. BACKGROUND

[0002] With the vigorous promotion of smart airports and green airport construction, civil aviation ground support operations are gradually transforming and upgrading towards automation and intelligence.

[0003] Most of the current airports in China still use the traditional manual mode for aircraft sewage service support: the sewage vehicle is driven into the parking position by the driver, and the service personnel need to manually complete the steps of sewage pipe docking, sewage pumping, cleaning and disinfection throughout the process. Not only does it take 15-20 minutes on average per flight, but during peak hours, multiple people and vehicles are required to coordinate, which is highly dependent on manpower, costs are rising, and it is difficult to match the high-density support demand brought by the continuous growth of flights. More seriously, the operation site is often accompanied by toxic and harmful gases such as hydrogen sulfide, ammonia, and pathogenic microorganisms, combined with harsh weather such as high temperature, severe cold, rain and snow, and low visibility at night, which can cause chronic damage to the respiratory, nervous and immune systems of personnel exposed for a long time, with high labor intensity and health risks.

[0004] Therefore, the development of unmanned sewage vehicles has become an urgent choice to break free from manual operation difficulties and promote the intelligent upgrading of airport ground support equipment. SUMMARY

[0005] The present application proposes an unmanned operation sewage vehicle for aircraft to solve the above-mentioned deficiencies in the prior art. The unmanned operation sewage vehicle for aircraft solves the problems of high labor costs and damage to the human body system in the existing operation mode, and liberates people from the environment that is not friendly to the human body.

[0006] The technical solution of the present application is: an unmanned operation sewage vehicle for aircraft, comprising a vehicle body, the vehicle body having an unmanned driving system and an operation system, the operation system comprising: a lifting platform arranged on the vehicle body, a distance measuring part arranged on the lifting platform for measuring the vertical distance between the lifting platform and the sewage panel, an operation part, an operation controller and a vision system; the operation part is provided with a depth camera; the operation controller is signal connected with the lifting platform, the distance measuring part and the operation part respectively; the operation controller receives the distance information measured by the distance measuring part and adjusts the height of the lifting platform according to the distance information; the vision system is signal connected with the depth camera, and the vision system is used for identifying the sewage cleaning interface cover plate, the sewage cleaning interface and the sewage discharge valve according to the collection information of the depth camera, and estimating the three-dimensional pose of the sewage cleaning interface cover plate, the sewage cleaning interface and the sewage discharge valve; A control system is in signal connection with the unmanned system, the vision system and the operation controller respectively, receives the estimated three-dimensional pose information from the vision system, and controls the operation part through the operation controller according to the three-dimensional pose information, so as to realize the opening of the sewage interface cover plate, the docking of the sewage interface, the opening of the sewage discharge valve, the disconnection of the sewage interface, the closing of the sewage discharge valve and the closing of the sewage interface cover plate.

[0007] In at least one embodiment of the present application, the operation part includes a first mechanical arm and a second mechanical arm arranged on the lifting platform, and an operating member is arranged on each of the first mechanical arm and the second mechanical arm, and two depth cameras are arranged on the first mechanical arm and the second mechanical arm respectively; the first mechanical arm, the second mechanical arm and the operating member are in signal connection with the operation controller.

[0008] In at least one embodiment of the present application, the control system is further in signal connection with a remote control end, the remote control end is used for data interaction with the control system, and the remote control end is further used for sending control instructions of the unmanned system and the operation system to the control system.

[0009] In at least one embodiment of the present application, the operating member includes a universal clamping mechanism and a sewage port external special clamping mechanism; the first mechanical arm and the second mechanical arm are respectively provided with the universal clamping mechanism or the first mechanical arm and the second mechanical arm are respectively provided with the universal clamping mechanism and the sewage port external special clamping mechanism, and the universal clamping mechanism and the sewage port external special clamping mechanism are in signal connection with the operation controller.

[0010] In at least one embodiment of the present application, the universal gripping mechanism is a finger-shaped gripping mechanism, and the work system further comprises a force sensing system, the force sensing system comprising a body sensing system and an environment sensing system arranged on each finger of the universal gripping mechanism, the body sensing system comprising a multi-degree-of-freedom motion detection system for measuring the torque of the joint transmission chain of each finger in real time and a driving load detection unit for measuring the bending moment composite parameter of the finger, and the environment sensing system comprising a distributed contact feedback unit for three-dimensional vector detection of the contact force of each finger and a surface feature recognition module for realizing the classification of the material or roughness of the gripped object; the distributed contact feedback unit, the surface feature recognition module, the multi-degree-of-freedom motion detection system, and the driving load detection unit are signal connected with a control system, the control system being configured to receive the transmission chain torque of each joint of the universal gripping mechanism and the bending moment composite parameter of each finger and to realize real-time sensing of the posture of the universal gripping mechanism according to the transmission chain torque and the bending moment composite parameter; the control system being configured to receive the three-dimensional vector of the contact force and the classification of the material or roughness and to realize sensing of the interactive force and the gripping position of the universal gripping mechanism according to the three-dimensional vector of the contact force and the classification of the material or roughness; and the control system being configured to adjust the posture, the interactive force, and the gripping position of the universal gripping mechanism through the work controller according to the sensed posture information, the interactive force, and the gripping position information.

[0011] In at least one embodiment of the present application, the special gripping mechanism connected with the sewage outlet comprises: The base is arranged on the second mechanical arm, and a laser range finder is arranged on the base, the laser range finder being configured to measure the aperture of the sewage interface; The two horizontal moving members are arranged on the base; The two lifting members are arranged on the two horizontal moving members, respectively; The two telescopic members are arranged on the opposite sides of the movable ends of the two lifting members, respectively, and the movable ends of the two telescopic members are provided with embedding modules; The central jacking mechanism is arranged between the two horizontal moving members on the base; the opposite sides of the movable ends of the two lifting members, the embedding modules, and the movable end of the jacking mechanism are provided with force sensors, and the two horizontal moving members, the two lifting members, the two telescopic members, and the central jacking mechanism are signal connected with the work system.

[0012] In at least one embodiment of the present application, the operation system comprises a vision system, which is used for identifying the aircraft sewage panel, sensor fault light, sewage interface and sewage discharge valve according to the collection information of the depth camera, and is also used for estimating the three-dimensional pose of the sewage interface and the sewage discharge valve and sending the three-dimensional pose estimation information of the sewage interface and the sewage discharge valve to the control system, so that the control system controls the first mechanical arm, the second mechanical arm and the clamping mechanism through the three-dimensional pose information.

[0013] In at least one embodiment of the present application, an alarm system is further included, which is respectively connected with the unmanned system, the operation system, the control system and the remote control end; the alarm system is used for sending alarm information to the remote control end when the unmanned system cannot drive the vehicle body to the operation area of the aircraft or the operation system cannot complete the entire sewage service work, so that the staff manually intervenes through the remote control end.

[0014] In at least one embodiment of the present application, the ranging part is a laser range finder or a laser radar, and the lifting platform is further provided with a lighting lamp.

[0015] In at least one embodiment of the present application, the distributed contact feedback unit is integrated with an array type piezoresistive film sensor and a temperature compensation circuit, the surface feature recognition module group comprises an integrated micron level texture recognition sensor and a vibration feedback unit, the multi-degree-of-freedom motion detection system comprises a nine-axis MEMS inertial measurement unit and a pose solving device fused with a Hall encoder, and the driving load detection unit group is composed of a strain transmission structure based on a fiber Bragg grating.

[0016] Compared with the prior art, the present application has the following beneficial effects: 1. The sewage vehicle of the present application can realize unmanned operation of aircraft sewage service, solve the problems of labor cost and harm to human body system in the existing operation mode, liberate people from the environment that is not friendly to human body, realize full-process automation, and adapt to the development direction of future airports.

[0017] 2. The universal clamping mechanism with the operation part designed in the form of fingers, the sewage port external special clamping mechanism including the base with the laser range finder, the two horizontal moving parts, the two lifting parts, the two telescopic parts, and the central tightening mechanism, and the integration of the environmental perception system and the body perception system on each finger of the universal clamping mechanism can accurately perceive the state and operation interaction force in the interactive process of operation, thereby realizing fine, safe, and intelligent operation, better adapting to the opening and closing operations of the sewage discharge valve and the sewage interface cover plate, and stably fixing the sewage pipes of various aperture sizes from four directions through the sewage port external special clamping mechanism and stably completing the docking, greatly ensuring the safety and accuracy of operation. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 The composition framework diagram of the unmanned operation system of the present application; Figure 2 The composition device diagram of the unmanned driving system of the present application; Figure 3 The composition device diagram of the operation system of the present application; Figure 4 The overall structure schematic diagram of the operation system of the present application; Figure 5It is the schematic diagram of the working part structure of the application; Figure 6 It is the schematic diagram of the special clamping mechanism structure of the application connected with the sewage outlet; Figure 7 It is the schematic diagram of the special clamping mechanism structure of the application connected with the sewage outlet; Figure 8 It is the schematic diagram of the working system structure of the application.

[0019] Mark explanation: 1, vehicle body; 11, unmanned system; 2, lifting platform; 21, mechanical arm mounting point; 3, distance measuring part; 4, working part, 41, first mechanical arm; 42, second mechanical arm; 411, depth camera; 412, operating part; 43, general clamping mechanism; 44, special clamping mechanism connected with sewage outlet; 441, base; 442, horizontal moving part; 443, lifting part; 444, telescopic part; 445, embedded module; 446, central tightening mechanism; 45, six-dimensional sensor; 5, working system; 6, control system; 7, alarm system; 8, remote control end. DETAILED DESCRIPTION

[0020] The drawings in the application are not strictly drawn according to the actual proportion, and the specific size and quantity of each structure can be determined according to the actual needs. The drawings described in the application are only structural schematic diagrams.

[0021] In order to make the purpose, technical scheme and advantages of the embodiments of the application clearer, the technical scheme of the embodiments of the application will be described clearly and completely below in combination with the drawings of the embodiments of the application. Obviously, the described embodiments are part of the embodiments of the application, not all the embodiments. Based on the described embodiments of the application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the application.

[0022] Unless otherwise defined, the technical terms or scientific terms used herein should be understood as the usual meaning understood by those skilled in the art. The "first", "second" and similar words used in the application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "In", "out", "up", "down", "far", "near", "front", "back" and the like are only used to represent the relative positional relationship, when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0023] With the vigorous promotion of smart airports and green airport construction, civil aviation ground support operations are gradually transforming and upgrading towards automation and intelligence.

[0024] However, most airports in China still generally use the traditional manual operation mode in the aircraft sewage service support link. The sewage truck needs to be driven to the designated position by the driver, and the connection of the sewage pipe, sewage pumping, cleaning and disinfection, etc. are manually completed by the service personnel. This mode has the following significant problems:

[0025] Poor working environment: During the process of aircraft sewage discharge, toxic and harmful gases (such as hydrogen sulfide, ammonia, pathogenic microorganisms, etc.) are accompanied, which may cause chronic damage to the respiratory system, nervous system and immune system of the operating personnel. In addition, complex weather conditions such as high temperature, severe cold, rain and snow, and low visibility at night further increase the labor intensity and health risks of manual operation.

[0026] High risk of human operation: During the manual connection of the sewage pipe, there is a risk of misoperation, such as sewage leakage due to loose interface, which may contaminate the airport pavement, even cause corrosion of the aircraft cabin or safety hazards on the taxiway. At the same time, personnel working near the aircraft also increase the safety risk of the airport.

[0027] Efficiency and cost bottleneck: Manual sewage service operation takes about 15-20 minutes per flight on average, and multiple people and vehicles need to be coordinated during peak hours, which is highly dependent on manpower. With the continuous growth of flight volume, the traditional mode has been difficult to meet the needs of high-density flight support in large airports, and the cost of manpower is rising year by year.

[0028] Therefore, for the aircraft sewage service operation scenario, the development of unmanned sewage trucks is not only a key means to solve the current difficulties of manual operation, but also an urgent need to promote the intelligent upgrading of airport ground support equipment.

[0029] By introducing unmanned vehicles into civil aviation airports to control the driving of special vehicles, the efficiency of the airport can be effectively improved, and the cost of manpower can be reduced. Through the deep integration of dual operation device architecture, intelligent sensing and collaborative control technology, unmanned, high-precision and all-weather adaptation of aircraft sewage discharge operations are realized, which conforms to the green operation and digital transformation trend of the civil aviation industry.

[0030] The aircraft sewage service unmanned operation system has the characteristics of unmanned and intelligent, and reduces labor costs. The data sensing of the multiple sensors can adjust the control of the action according to the real-time data feedback, has the characteristics of high sensing and high sensitivity, and greatly guarantees the safety and accuracy of the operation; starting from the control system, the unmanned system and the sewage service operation system, the disadvantages of the traditional operation mode are solved, the labor costs are reduced, the people are liberated from the unfriendly working environment, the whole process automation is realized, the development direction of the future airport is adapted, and good market popularization and use are achieved.

[0031] In combination Figures 1 to 8 As shown in the figure, an unmanned operation sewage vehicle for an aircraft includes a vehicle body 1, the vehicle body 1 has an unmanned driving system 11 and an operation system 5; The unmanned driving system 11 is used for collecting surrounding environment data in real time through the fusion technology of multiple sensors during the driving process of the vehicle body 1, and constructing a high-precision environment map; based on real-time image acquisition and processing technology, dynamically identifying road obstacles, traffic signs, other vehicle equipment, personnel, aircraft, and combining global path planning, traffic operation planning to generate an optimal driving path; through real-time trajectory planning, dynamically adjusting the driving trajectory of the vehicle, ensuring safe and efficient automatic driving in complex environments.

[0032] The operation system 5 includes a lifting platform 2 arranged on the vehicle body 1, a distance measuring part 3 arranged on the lifting platform 2 for measuring the vertical distance between the lifting platform 2 and the sewage panel, an operation part 4, an operation controller and a visual system; specifically, the lifting platform 2 includes a platform and a motor or a hydraulic control system installed at the bottom of the platform for driving lifting, which can adjust the position of the platform for operation according to the position of the sewage panel of different models.

[0033] The operation part 4 includes a first mechanical arm 41 and a second mechanical arm 42 arranged on the lifting platform 2, and a depth camera 411 and an operating part 412 are arranged on the first mechanical arm 41 and the second mechanical arm 42; the operation controller is signal connected with the lifting platform 2, the distance measuring part 3, the first mechanical arm 41, the second mechanical arm 42 and the two operating parts 412 respectively; the operation controller is used for receiving the distance information measured by the distance measuring part 3, and adjusting the height of the lifting platform 2 according to the distance information; the visual system is signal connected with the two depth cameras 411, and the visual system is used for identifying the sewage interface cover plate, the sewage interface and the sewage discharge valve according to the collection information of the two depth cameras 411, and estimating the three-dimensional pose of the sewage interface cover plate, the sewage interface and the sewage discharge valve.

[0034] The control system 6 is signal connected with the unmanned system 11, the vision system and the operation controller respectively, used for receiving the three-dimensional pose information estimated by the vision system, and controlling the first mechanical arm 41, the second mechanical arm 42 and the clamping mechanism 4121 through the operation controller according to the three-dimensional pose information, so as to realize opening the sewage interface cover plate, docking the sewage interface, opening the sewage discharge valve, disconnecting the sewage interface, closing the sewage discharge valve and closing the sewage interface cover plate. The control system 5 is used for sensor data acquisition, data uploading and data analysis of the unmanned system 11 and the operation system 5, and is a core platform of control decision. The control system 6 is also signal connected with the remote control end 8; the control system 6 is used for data interaction control with the sensing sensor in the unmanned system 11 and the operation system 5, and uploads the obtained data information to the remote control end 8; the remote control end 8 can also send command information to the local terminal through wireless communication, and then the unmanned system 11 and the operation system 5 are commanded by the control system 5 to perform remote control operation.

[0035] As an alternative embodiment, the operating part 412 includes a general clamping mechanism 43 and a sewage port external special clamping mechanism 44; the first mechanical arm 41 and the second mechanical arm 42 are both installed with the general clamping mechanism 43, or the first mechanical arm 41 and the second mechanical arm 42 are respectively installed with the general clamping mechanism 43 and the sewage port external special clamping mechanism 44; the end of the second mechanical arm 42 is installed with a six-dimensional sensor 45; the general clamping mechanism 43 and the sewage port external special clamping mechanism 44 are signal connected with the operation controller.

[0036] As an alternative embodiment, the universal gripping mechanism 43 is a finger-shaped gripping mechanism, and the work system 5 further comprises a force sensing system, which comprises a body sensing system and an environment sensing system arranged on each finger of the universal gripping mechanism 43, the body sensing system comprises a multi-degree-of-freedom motion detection system for measuring the torque of the joint transmission chain of each finger in real time and a driving load detection unit for measuring the bending moment composite parameter of the finger, and the environment sensing system comprises a distributed contact feedback unit for three-dimensional vector detection of the contact force of each finger and a surface feature recognition module for realizing the classification of the material or roughness of the gripped object; the distributed contact feedback unit, the surface feature recognition module, the multi-degree-of-freedom motion detection system and the driving load detection unit are signal connected with the control system 6, the control system 6 receives the transmission chain torque of each joint of the universal gripping mechanism 43 and the bending moment composite parameter of each finger, and senses the posture of the universal gripping mechanism 43 in real time according to the transmission chain torque and the bending moment composite parameter; the control system 6 receives the three-dimensional vector of the contact force and the classification of the material or roughness, and senses the interactive force and the gripping position of the universal gripping mechanism 43 according to the three-dimensional vector of the contact force and the classification of the material or roughness; the control system 6 is further used for adjusting the posture, the interactive force and the gripping position of the universal gripping mechanism 43 through the work controller according to the sensed posture information, the interactive force and the gripping position information; the body sensing system can obtain the torque data, the angle or the position information measured in real time at the joint; the environment sensing system can obtain the information such as contact, pressure, friction and vibration of the surface of the object; and the six-dimensional force sensor can measure the data information of the force and the torque received in three directions. These sensors can accurately sense the state and the operation interactive force in the interactive process of the work, so as to realize fine, safe and intelligent work.

[0037] As an alternative embodiment, the special gripping mechanism 44 connected with the sewage outlet comprises: The base 441 is arranged on the second mechanical arm 42, and a laser range finder is arranged on the base 441, and the laser range finder is used for measuring the aperture of the sewage interface; Two horizontal moving parts 442 are arranged on the base 441; Two lifting parts 443 are arranged on the two horizontal moving parts 442 respectively; Two telescopic parts 444 are arranged on the opposite sides of the movable ends of the two lifting parts 443 respectively, and the movable ends of the two telescopic parts 444 are provided with embedding modules 445; The central tightening mechanism 446 is arranged between the two horizontal moving pieces 442 on the base 441; the opposite side of the movable end of the two lifting pieces 443, the two embedded modules 445 and the movable end of the tightening mechanism 446 are each provided with a force sensor, and the two horizontal moving pieces 442, the two lifting pieces 443, the two telescopic pieces 444 and the central tightening mechanism 446 are all signal connected with the operation system 5; specifically, the force sensor has a measuring contact range and force size information sensor device, for example, a strain gauge type force sensor converts contact force into an electric signal, a force sensor based on a piezoresistive or capacitive principle sensor array measures multi-dimensional contact information, a force sensor is used to sense the force of the force point, and a force sensor is used to sense the size of the contact surface; and the material on the movable end of the lifting piece 443 is set as replaceable flexible material, such as silica gel, which can increase the friction. Figure 6 The black dots on the base 441 represent the installation range of the distance measuring laser device, and the other black dots represent the installation range of the measuring contact range and force device. When clamping interfaces of different hole diameters and sizes, the two lifting pieces 443 are elongated by a certain distance, then the outer interface is fixed by automatically moving left and right through the horizontal moving piece 442, then the two embedded modules 445 are combined by extending left and right through the telescopic piece 444, and then the interface is fixed from the front by the central tightening mechanism 446 in the middle, so as to stably support the clean water interface from four directions.

[0038] As an alternative embodiment, the distributed contact feedback unit adopts an array type piezoresistive film sensor integrated with a temperature compensation circuit, the surface feature recognition module group includes an integrated micron level texture recognition sensor and a vibration feedback unit, the multi-degree-of-freedom motion detection system includes a nine-axis MEMS inertial measurement unit and a pose solving device fused with a Hall encoder, and the driving load detection unit group is composed of a strain transmission structure based on a fiber Bragg grating.

[0039] As an alternative embodiment, the job system 5 includes a vision system for identifying the aircraft sewage panel, sensor fault light, sewage interface and sewage discharge ball valve handle, and identifying the surrounding environment objects according to the identification information of the depth camera 411. Specifically, the vision system uses a target detection algorithm of deep learning (such as YOLO, Faster R-CNN, etc.) combined with an instance segmentation technology (such as Mask R-CNN) to accurately identify the category, position and contour of the above-mentioned targets. The vision system is also used to synchronously collect the depth information, color image information and point cloud data of the target area through the depth camera. The depth information, color information and point cloud data are pre-processed and used as the input of a deep learning pose estimation algorithm (such as PoseNet, PointNet or a self-defined multi-modal fusion network) or a traditional pose estimation algorithm to accurately estimate the three-dimensional pose (including spatial position and attitude angle) of the key components such as the sewage interface, so that the control system 6 controls the first mechanical arm 41, the second mechanical arm 42 and the clamping mechanism 4121 through the three-dimensional pose information.

[0040] As an alternative embodiment, the job system 5 is built-in with an imitation learning and reinforcement learning algorithm for policy learning and optimization of the switch operation of the operating device. The system can use a deep learning target detection algorithm and an instance segmentation algorithm to identify and pixel-level segment the target button, and extract its three-dimensional spatial coordinates combined with depth information to achieve accurate differentiation and positioning of the target button. During the operation of the sewage panel switch, the imitation learning and reinforcement learning method can be used to learn and optimize the policy of the switch operation of the operating device. By imitating the expert demonstration action, the operating device can initially master the switch operation process, and then use reinforcement learning to further optimize the action policy to improve the accuracy and robustness of the operation.

[0041] As an alternative embodiment, an alarm system 7 is further included, which is signal connected with the unmanned system 11, the job system 5 and the control system 6. When the system cannot work normally, the alarm system 7 automatically feeds back an alarm to the remote control end. In addition, a master-slave control can be set to control the equipment in the actual job sewage treatment system in real time through the manual operating device of the remote end when encountering complex situations to achieve accurate and safe operation.

[0042] As an alternative embodiment, the distance measuring part 3 is a laser range finder or a laser radar, and a lighting lamp is further arranged on the lifting platform 2. The lighting lamp is used for lighting in the case of insufficient light such as night or fog. The distance measuring device is used to measure the distance between the lifting platform and the job panel, thereby facilitating safe and accurate operation.

[0043] As an alternative embodiment, the vehicle body 1 is provided with a laser radar, a millimeter wave radar, a camera, a global positioning module and a warning light; wherein the laser radar is installed on the front roof of the vehicle, used for scanning the surrounding environment of the vehicle to provide data information for establishing a local map; the camera and the millimeter wave radar are installed around the vehicle, the camera is used for observing the real-time situation around the vehicle, and the millimeter wave radar is used for measuring the distance, speed and angular velocity of the surrounding objects, so as to adjust the trajectory of the vehicle and realize real-time vehicle obstacle avoidance; the global positioning module is used for obtaining the real-time position information of the vehicle in the environment of the airport, so that the terminal knows the position information of the vehicle; the warning light is installed on the top of the vehicle, used for reminding pedestrians and vehicles passing by at night.

[0044] The working principle and use method of the embodiment are as follows: The unmanned operation sewage vehicle for aircraft proposed in the application, when receiving an operation task, the unmanned driving system first starts operation. The remote terminal sends the target position, aircraft model and other operation information to the control system, the control system plans a path from the starting point to the target point, and the vehicle starts driving. The laser radar in the unmanned driving system sends the detected information to the control system to provide data information for establishing a local map around the vehicle. During driving, the camera and the millimeter wave radar are used to detect dynamic obstacles randomly appearing in the driving process, so as to transmit to the control system and facilitate planning of a real-time vehicle trajectory. When driving at night, the warning light is used to remind pedestrians and vehicles passing by around. When the vehicle reaches the target operation aircraft, the sewage panel position of the operation is identified by the camera on the top of the rear of the vehicle, and the vehicle is guided to back up to the working area below the sewage panel.

[0045] Then the operation system works, and the specific operation steps are as follows: According to the aircraft model information fed back by the control system and the distance measured by the ranging device in the lifting platform of the sewage service operation system from the sewage panel, the lifting platform is lifted to an appropriate position height, and waits for the operation device to start operation. The laser range finder and the laser radar can measure the distance from the lifting platform to the sewage panel, and the laser radar can also scan the information of the sewage operation area to establish map information, so as to prevent collision between the operation devices and collision on the surface of the aircraft during operation;

[0046] When the first mechanical arm and the second mechanical arm are provided with a universal clamping mechanism, the depth cameras on the first mechanical arm and the second mechanical arm respectively identify the positions of the two buttons of the sewage panel, and then feed back to the control system, and the control system commands the opening switch of the double operation devices, and then releases the sewage panel. The depth camera of the first mechanical arm and the depth camera of the second mechanical arm respectively identify the cover plates of the sewage interface and the clean water interface, and then respectively open the cover plates of the sewage interface and the clean water interface.

[0047] The first mechanical arm and the second mechanical arm pick up the sewage external interface from the placement point for docking operation, during which the gripping force is adjusted according to the force information of the joint torque sensor and the tactile sensor. After the docking is completed, the operating device releases the hands, and the clean water external interface docking operation is performed. According to the information of the six-dimensional force sensor, the position information of the operating device is adjusted in real time to achieve successful docking, the joint of the operating device is rotated to achieve installation and fixation, and the external clamping mechanism is released. Next, the clean water external interface docking operation is performed. In the method of positioning the sewage interface and the clean water interface, the ICP or deep learning pose estimation algorithm can be used to obtain the pose information of the target object, that is, the position information and the pitch angle, yaw angle and rotation angle information of the target. The main function of the ICP algorithm is to align two point clouds (or three-dimensional models), that is, through iteration, a rigid transformation (rotation + translation) is found to make the source point cloud and the target point cloud coincide as much as possible. The target point cloud is the object model point cloud to be registered, and the source point cloud is the real-time point cloud data obtained by the camera. The deep learning pose estimation algorithm mainly refers to using a deep neural network (such as CNN, Transformer, etc.) to automatically learn and predict the spatial pose (position + attitude) of an object or a camera from image, point cloud or multi-modal sensor data.

[0048] The depth camera of the first mechanical arm identifies the inner one-way valve wrench of the sewage interface, and opens the inner one-way valve wrench of the sewage interface. The depth camera of the first mechanical arm identifies the position of the sewage discharge spherical valve control handle, and twists the handle using the clamping mechanism to start the sewage discharge operation.

[0049] After the sewage discharge is completed, the clamping mechanism of the first mechanical arm twists the sewage discharge handle to close it. The clamping mechanism of the first mechanical arm closes the inner valve wrench of the sewage interface. The first mechanical arm and the second mechanical arm withdraw the sewage external interface from the aircraft sewage interface and place it to the initial position. Next, the clean water external interface is withdrawn from the aircraft clean water interface and placed to the initial position.

[0050] The first mechanical arm and the second mechanical arm respectively close the cover plates of the sewage interface and the clean water interface. When the installed clamping mechanism is the second type, the clamping mechanism of the first mechanical arm closes the cover plate of the sewage interface, and then closes the cover plate of the clean water interface.

[0051] The first mechanical arm and the second mechanical arm respectively close the two buttons of the sewage panel. The double operating device returns to the initial position, the lifting platform returns to the initial position, and the sewage service operation system ends.

[0052] Subsequently, the unmanned system starts operation, drives away from the current area to perform operation at the next target point or returns to the sewage treatment point.

[0053] When the first mechanical arm and the second mechanical arm are respectively provided with a general clamping mechanism and a special clamping mechanism for the sewage interface, the sewage service operation process is as follows: The depth camera of the first mechanical arm of the sewage service operation system identifies the position information of the two buttons of the sewage panel, and then feeds back to the control system, which commands the clamping mechanism of the first mechanical arm to first open the switch on one side, and then open the switch on the other side, and then release the sewage panel.

[0054] The depth camera of the first mechanical arm first identifies and opens the cover plate of the sewage interface, and then identifies and opens the cover plate of the clean water interface. In this step, the depth learning target detection algorithm, as well as the imitation learning and reinforcement learning, are also used to complete the execution action.

[0055] The depth camera of the second mechanical arm identifies the sewage interface, and the special clamping mechanism for the sewage interface clamps the sewage interface and performs docking operation. The multi-agent neural network (MLP) sensing or traditional spiral search is used to adjust the position of the interface. In the docking process, the adaptive admittance control algorithm is used. The use of multi-modal fusion can improve the accuracy of the entire docking process. The input of the multi-agent neural network is the force information of the relative position relationship between the clean sewage interface and the clean sewage port during the docking process. The position information of the clean sewage interface can be adjusted according to the force information of different positions. The traditional spiral search algorithm adjusts the interface position along the spiral path step by step according to the set step and angle parameters until the docking is successful. The adaptive admittance control algorithm dynamically adjusts the admittance control parameters (such as virtual mass, damping, stiffness) according to the real-time feedback of the six-dimensional force sensor force / torque information, to realize the flexibility and stability in the docking process.

[0056] The special clamping mechanism of the second mechanical arm clamps the sewage interface and exits the aircraft sewage interface, and returns to the initial position. Next, the special clamping mechanism of the second mechanical arm clamps the clean water interface and exits the aircraft clean water interface, and places it to the initial position. The double operating device returns to the initial position, the lifting platform returns to the initial position, and the sewage service operation system work is completed.

[0057] The above embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can make modifications or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some technical features. The modifications, changes or replacements do not change the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the present application, and should be covered within the protection scope of the present application.

Claims

1. An unmanned sewage treatment vehicle for aircraft, comprising a vehicle body (1), characterized in that, The vehicle body (1) has an unmanned driving system (11) and an operation system (5). The operation system (5) includes: a lifting platform (2) installed on the vehicle body (1), a distance measuring unit (3) installed on the lifting platform (2) for measuring the vertical distance between the lifting platform (2) and the sewage panel, an operation unit (4), an operation controller, and a vision system. The operation unit (4) is equipped with a depth camera (411). The operation controller is connected to the lifting platform (2), the distance measuring unit (3), and the operation unit (4) respectively. The operation controller receives the distance information measured by the distance measuring unit (3) and adjusts the height of the lifting platform (2) according to the distance information. The vision system is connected to the depth camera (411). The vision system identifies the clean and sewage interface cover, the clean and sewage interface, and the sewage discharge valve according to the information collected by the depth camera (411), and estimates the three-dimensional pose of the clean and sewage interface cover, the clean and sewage interface, and the sewage discharge valve. The control system (6) is connected to the unmanned driving system (11), the vision system and the operation controller respectively. The control system (6) receives the three-dimensional pose information estimated by the vision system and controls the operation unit (4) through the operation controller according to the three-dimensional pose information, so as to realize the opening of the clean and sewage interface cover, the docking of the clean and sewage interface, the opening of the sewage discharge valve, the disconnection of the clean and sewage interface, the closing of the sewage discharge valve and the closing of the clean and sewage interface cover.

2. The unmanned sewage treatment vehicle for aircraft as described in claim 1, characterized in that, The work unit (4) includes a first robotic arm (41) and a second robotic arm (42) mounted on a lifting platform (2). Both the first robotic arm (41) and the second robotic arm (42) are equipped with operating components (412). There are two depth cameras (411), which are respectively mounted on the first robotic arm (41) and the second robotic arm (42). The first robotic arm (41), the second robotic arm (42) and the operating components (412) are all connected to the work controller.

3. The unmanned sewage treatment vehicle for aircraft as described in claim 1, characterized in that, The control system (6) is also connected to a remote control terminal (8), which is used to interact with the control system (6) and to send control commands to the control system (6) for the unmanned driving system (11) and the operation controller.

4. The unmanned sewage treatment vehicle for aircraft as described in claim 2, characterized in that, The operating component (412) includes a universal clamping mechanism (43) and a special clamping mechanism (44) for external connection of clean and wastewater outlets; the first robotic arm (41) and the second robotic arm (42) are both equipped with the universal clamping mechanism (43) or the first robotic arm (41) and the second robotic arm (42) are respectively equipped with the universal clamping mechanism (43) and the special clamping mechanism (44) for external connection of clean and wastewater outlets, and the universal clamping mechanism (43) and the special clamping mechanism (44) for external connection of clean and wastewater outlets are connected to the operation controller via signals.

5. The unmanned sewage treatment vehicle for aircraft as described in claim 4, characterized in that, The universal clamping mechanism (43) is a finger-shaped clamping mechanism. The working system (5) also includes a force sensing system. The force sensing system includes a body sensing system and an environmental sensing system installed on each finger of the universal clamping mechanism (43). The body sensing system includes a multi-degree-of-freedom motion detection system and a drive load detection unit. The multi-degree-of-freedom motion detection system is used to measure the torque of the transmission chain of each finger joint in real time. The drive load detection unit is used to measure the bending moment composite parameters of the finger. The environmental sensing system includes a distributed contact feedback unit and a surface feature recognition module. The distributed contact feedback unit is used to perform three-dimensional vector detection of the contact force of each finger. The surface feature recognition module is used to realize the classification of the material or roughness of the clamped object. The separate module, the multi-degree-of-freedom motion detection system, and the drive load detection unit are all connected to the control system (6) via signals. The control system (6) is used to receive the combined parameters of the transmission chain torque and bending moment of each joint of the universal clamping mechanism (43) and to sense the posture of the universal clamping mechanism (43) in real time based on the combined parameters of the transmission chain torque and bending moment. The control system (6) is used to receive the three-dimensional vector of the contact force and the grade of the material or roughness, and to sense the interaction force and clamping part of the universal clamping mechanism (43) based on the three-dimensional vector of the contact force and the grade of the material or roughness. The control system (6) adjusts the posture, interaction force, and clamping part of the universal clamping mechanism (43) through the operation controller based on the sensed posture information, interaction force, and clamping part information.

6. The unmanned sewage treatment vehicle for aircraft as described in claim 4, characterized in that, The special clamping mechanism (44) for external connection of the clean water outlet includes: A base (441) is mounted on a second robotic arm (42). A laser rangefinder is mounted on the base (441) and is used to measure the aperture of the clean water and sewage interface. Both horizontal moving parts (442) are mounted on the base (441); Two lifting components (443) are respectively mounted on the two horizontal moving components (442); Two telescopic components (444) are respectively set on opposite sides of the movable ends of the two lifting components (443), and each movable end of the two telescopic components (444) is provided with an embedded module (445). The central tightening mechanism (446) is located on the base (441) between the two horizontal moving parts (442); force sensors are provided on the opposite side of the movable ends of the two lifting parts (443), on the two embedded modules (445), and on the movable end of the tightening mechanism (446). The two horizontal moving parts (442), the two lifting parts (443), the two telescopic parts (444), and the central tightening mechanism (446) are all connected to the operation controller.

7. The unmanned sewage treatment vehicle for aircraft as described in claim 3, characterized in that, It also includes an alarm system (7), which is connected to the unmanned driving system (11), the operation system (5), the control system (6) and the remote control terminal (8) respectively. The alarm system (7) is used to send an alarm message to the remote control terminal (8) when the unmanned driving system (11) is unable to drive the vehicle (1) to the operation area of ​​the aircraft or the operation system (5) is unable to complete the entire sewage service work, so that the staff can make manual intervention through the remote control terminal (8).

8. The unmanned sewage treatment vehicle for aircraft as described in claim 1, characterized in that, The ranging unit (3) is a laser rangefinder or a lidar, and the lifting platform (2) is equipped with lighting.

Images