Transportation unmanned aerial vehicle autonomous loading system based on low earth orbit satellite network

Abstract

The invention provides a transportation unmanned aerial vehicle autonomous loading system based on a low-orbit satellite network, and the system comprises a satellite communication module, an intelligent sensing system, an intelligent decision and control module, and a mechanical execution module. A loading and unloading mechanism in the mechanical execution module executes operation; wherein the mechanical execution module is provided with a safety and fault tolerance module, and the safety and fault tolerance module comprises multiple locking mechanisms, real-time fault detection and recovery and emergency strategies. The communication reliability among the ground, the unmanned aerial vehicle and the satellite network chain is guaranteed by adopting low-orbit satellite network communication; in an autonomous loading and unloading system, a safety fault-tolerant mechanism is adopted, and potential safety hazards caused by multiple emergencies between the environment and loaded goods are overcome.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of transport unmanned aerial vehicles, in particular to a transport unmanned aerial vehicle autonomous loading system based on a low-orbit satellite network. BACKGROUND

[0002] A transport unmanned aerial vehicle is a kind of unmanned aerial vehicle specially used for transporting goods, packages or other materials; through autonomous flight or remote control, it can transport goods from the starting point to the destination, and is widely used in the fields of logistics, medical emergency and disaster relief. The low-orbit satellite network function carried by the transport unmanned aerial vehicle can provide stronger signals for long-distance transport communication of the transport unmanned aerial vehicle. The low-orbit satellite communication can provide network transmission services for ground or air terminals through a star network composed of multiple satellites running at 500 km to 1000 km.

[0003] The transport unmanned aerial vehicle autonomous loading system carrying the low-orbit satellite communication is a highly integrated intelligent system, which aims to realize the full-process automatic task execution from the task allocation of remote communication to the cargo identification, grabbing and loading of the unmanned aerial vehicle autonomous execution of cargo loading. The safety guarantee is the necessary execution standard in each link. SUMMARY

[0004] In view of the above existing intelligent system to be further improved, the application provides a transport unmanned aerial vehicle autonomous loading system based on a low-orbit satellite network, which adopts a low-orbit satellite network to provide reliable communication, navigation and positioning services, and identifies, grabs and executes a safety fault tolerance module set in each intelligent module in the unmanned aerial vehicle, so as to guarantee the safety and system reliability of the autonomous loading system.

[0005] In the first aspect, the application provides a transport unmanned aerial vehicle autonomous loading system based on a low-orbit satellite network, which comprises a satellite communication module, an intelligent perception system, an intelligent decision and control module and a mechanical execution module. After receiving the decision and control instructions issued by the intelligent decision and control module, the mechanical execution module executes the operation of the loading and unloading mechanism in the mechanical execution module. The mechanical execution module has a safety and fault tolerance module, which comprises a multiple locking mechanism, real-time fault detection and recovery and an emergency strategy.

[0006] Further, the multiple locking mechanism comprises a mechanical locking mechanism and an electromagnetic locking mechanism, and a sensor is arranged to monitor the locking state in real time.

[0007] Further, the real-time fault detection and recovery adopts a redundant control mechanism.

[0008] Further, the emergency strategy comprises an emergency release system, which cuts off the power supply of the main lock and intelligently executes the release mechanism after triggering the emergency condition.

[0009] Further, the loading and unloading mechanism comprises a multi-degree-of-freedom mechanical arm or a sliding rail system.

[0010] Further, the satellite communication module acquires a loading task instruction, and performs data interaction and cooperation between the unmanned aerial vehicle, the ground station and the satellite network to obtain parsed loading task information; wherein the data interaction comprises unmanned aerial vehicle loading and unloading state and position information sharing.

[0011] Further, the intelligent perception system identifies appearance attributes and environmental information of the target goods to obtain sensor information; wherein the appearance attributes comprise goods type, size and weight, which are respectively monitored in real time by a camera, a radar and a weight sensor in the intelligent perception system.

[0012] Further, the intelligent decision and control module plans a loading path in combination with real-time monitoring of the sensor information according to the loading task information, and transmits decision and control instructions to the unmanned aerial vehicle mechanical execution module according to visual guidance in the intelligent perception system.

[0013] The above-mentioned embodiments have the following advantages or beneficial effects, (1) The low-orbit satellite network communication is adopted to guarantee the communication reliability between the ground, the unmanned aerial vehicle and the satellite network chain; (2) In the autonomous loading and unloading system, a safety fault-tolerant mechanism is adopted to overcome safety hazards caused by multiple sudden conditions between the environment and the loading goods.

[0014] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the embodiment or related art description. Obviously, the drawings in the following description are only part of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0016] Figure 1 A flowchart of a transport unmanned aerial vehicle autonomous loading system based on a low-orbit satellite network is provided. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0018] Low-orbit satellite network: A low-orbit satellite network is composed of a large number of small communication satellites, with an orbital height of about 500-1200 kilometers. Compared with traditional communication satellites, it has the advantages of wide coverage, low transmission delay (20-40 milliseconds), high communication rate (more than 100 Mbps), etc., and can provide high-speed stable communication services for unmanned aerial vehicles in a global range. An unmanned aerial vehicle based on a low-orbit satellite network can communicate with the low-orbit satellite network.

[0019] As shown in Figure 1 , the autonomous loading system of the transport unmanned aerial vehicle based on the low-orbit satellite network includes a satellite communication module that acquires the loading task instructions sent by the ground base station and transmits them to the unmanned aerial vehicle through satellite network communication. The ground base station establishes a communication connection with the unmanned aerial vehicle and receives the sharing of the loading and unloading status and position information of the unmanned aerial vehicle. The satellite communication module uses a low-delay communication link. In specific implementation, the short-time delay characteristic is about 20-50 ms to meet the requirements of real-time control of the unmanned aerial vehicle.

[0020] The intelligent perception system includes various sensor devices. The transport unmanned aerial vehicle is equipped with various sensors to assist the autonomous loading of the unmanned aerial vehicle, including cameras, radars and weight sensors, etc. The camera is used to acquire images of the external environment and conditions to provide perception feature information to the intelligent decision and control module. In some implementations, the camera acquires appearance images of the to-be-loaded cargo, including regular and irregular external shape judgment, and position images of the to-be-loaded area, and uses an intelligent recognition detection model to analyze and judge the size and type of the to-be-loaded cargo to obtain the perception feature information. The weight sensor is used to acquire the weight information of the to-be-loaded cargo to estimate the loading of the cargo.

[0021] The radar is used to construct a 3D point cloud map of the loading and unloading scene to avoid obstacles. The positioning system is also included to accurately position the loading area. In specific implementation, data acquisition and preprocessing are performed first. The laser radar emits laser pulses through rotation or multi-beam to measure the return time in each direction to obtain distance data.

[0022] Then, the polar coordinate system is converted into Cartesian coordinates through coordinate conversion, and the conversion formula is as follows:

[0023]

[0024]

[0025] Then, data preprocessing is performed through denoising and filtering, and a statistical outlier removal method is adopted. The principle is as follows: outliers are detected and removed based on statistical analysis. If the average distance of a point exceeds a certain standard deviation range, it is determined to be an outlier.

[0026] The intelligent decision-making and control module further processes the feature information perceived by the intelligent sensing system, including path planning, AI decision-making, and dynamic balance control. In specific implementations, this is combined with perceived feature information, including the size of the cargo, the characteristics of the cargo's gripping points, the weight of the cargo, and obstacle recognition in the loading area.

[0027] Deep learning models are used for cargo classification and gripping point identification. In some implementations, models such as YOLO and Faster R-CNN are used to learn and extract features of cargo type and gripping points.

[0028] Each module utilizes feature information to fulfill its functional requirements. In specific implementation, the path planning function, by acquiring the feature information and location of the loaded goods, determines the loading tools, loading methods, and loading areas to be used by the actuator. The loading tools include multi-degree-of-freedom robotic arms, various grippers, and other tools.

[0029] For goods of different shapes, a suitable gripping method is adapted; in some implementations, the loading tool adopts a top-down gripping method or a left-to-right gripping method.

[0030] Upon reaching the designated loading area, the loading tool performs path planning to arrive at the loading area. In some implementations, the RRT-Connect algorithm is used for path planning of multi-degree-of-freedom robotic arms to reach the loading point of the cargo within the loading area. Specifically, the RRT-Connect algorithm, starting from the origin (…),… ) and target point ( Simultaneously construct two random trees ( and The algorithm alternately expands to random sampling points and attempts to connect two trees to quickly find a feasible path. Specific implementation steps include: Initialize the configuration space and define two trees with a start point and a target point. and Information such as the number of sampling points and step size t; Generate random points in space ; From the tree Find the nearest node to the random point Nearest node And expand one step δ in the direction To Generate a new node If the path is collision-free, add To the tree ; From the nearest node in the tree Step by step expansion to Until reaching Or encountering obstacles; If the two trees And Successfully connected, merge the path, and the algorithm terminates; If not connected, exchange And Continue the next iteration; Finally, when the two trees are connected, the path from the starting point ( ) and the target point ( ) is composed of the merged path of And . After receiving the decision and control instructions, the loading and unloading mechanism in the UAV mechanical execution module performs the operation.

[0031] The loading and unloading system is provided with a safety and fault tolerance module, including a multiple locking mechanism, real-time fault detection and recovery, and emergency strategies. The multiple locking mechanism includes a mechanical locking mechanism and an electromagnetic locking mechanism, and a sensor is provided to monitor the locking state in real time. In some implementations, a mechanical buckle lock including an alloy buckle is used, which is closed by a spring or electromagnetic force; there is also an electromagnetic lock that attracts and fixes the cargo box when powered on; in specific implementations, electromagnetic lock points are symmetrically distributed in the UAV to balance the stress. The sensor monitors in real time, and in some embodiments, a Hall sensor, pressure sensor, etc. are provided to detect whether the locking point of the cargo is still closed or detect the pressure of the cargo box on the locking point, whether it is fixed firmly; there is also a vibration sensor to detect whether the frequency of vibration in the flight jolt causes mechanical fatigue and other conditions.

[0032] The loading and unloading system is provided with a safety and fault tolerance module, including a multiple locking mechanism, real-time fault detection and recovery, and emergency strategies. The multiple locking mechanism includes a mechanical locking mechanism and an electromagnetic locking mechanism, and a sensor is provided to monitor the locking state in real time. In some implementations, a mechanical buckle lock including an alloy buckle is used, which is closed by a spring or electromagnetic force; there is also an electromagnetic lock that attracts and fixes the cargo box when powered on; in specific implementations, electromagnetic lock points are symmetrically distributed in the UAV to balance the stress. The sensor monitors in real time, and in some embodiments, a Hall sensor, pressure sensor, etc. are provided to detect whether the locking point of the cargo is still closed or detect the pressure of the cargo box on the locking point, whether it is fixed firmly; there is also a vibration sensor to detect whether the frequency of vibration in the flight jolt causes mechanical fatigue and other conditions.

[0033] ​The emergency strategy includes an emergency release system, which cuts off the main lock power supply and intelligently executes the release mechanism after triggering an emergency condition; in specific implementations, when encountering an obstacle that cannot be avoided, the emergency release system is preferentially triggered, and the cargo is released in the optimal way, the optimal release angle is dynamically calculated according to the height and speed of the incident point, and the landing point of the cargo is ensured to be accurate. In some other implementations, when the unmanned aerial vehicle starts, the control system checks the sensor feedback in turn, monitors whether there is an abnormality in real time, and triggers an alarm to start the emergency process.

[0034] In fault detection and recovery, a self-checking system is used; in specific implementations, the state of the mechanical arm joints and sensors is checked regularly; a redundant control mechanism is used, and in specific implementations, if the main control chip fails, the backup controller must be switched to; in some other implementations, the electromagnetic lock is powered by a super capacitor and a battery, and after the main power fails, the capacitor maintains the lock for at least 10 seconds.

[0035] Through the above scheme, the following advantages or beneficial effects are achieved: (1) The low-orbit satellite network communication guarantees the ground, and the communication reliability between the unmanned aerial vehicle and the satellite network chain; (2) In the autonomous loading and unloading process, a safe fault-tolerant mechanism is used to overcome the safety hazards caused by sudden conditions between the environment and the loaded cargo.

[0036] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A low-orbit satellite network-based autonomous loading system for transport drones, comprising a satellite communication module, an intelligent perception system, an intelligent decision-making and control module, and a mechanical execution module, characterized in that, The mechanical execution module executes the operation of the loading and unloading mechanism after receiving the decision and control instruction issued by the intelligent decision and control module; wherein the mechanical execution module has a safety and fault-tolerant module, the safety and fault-tolerant module includes a multiple locking mechanism, real-time fault detection and recovery and emergency strategy.

2. The low earth orbit satellite network based autonomous loading system for transport drones as claimed in claim 1 wherein, The multiple locking mechanism includes a mechanical locking mechanism and an electromagnetic locking mechanism, and a sensor is arranged to monitor the locking state in real time.

3. The low earth orbit satellite network based autonomous loading system for transport drones as claimed in claim 1 wherein, The real-time fault detection and recovery adopts a redundant control mechanism.

4. The low earth orbit satellite network based autonomous loading system for transport drones as claimed in claim 1 wherein, The emergency strategy includes an emergency release system, which cuts off the power supply of the main lock after triggering the emergency condition, and intelligently executes the release mechanism.

5. The low earth orbit satellite network based transport drone autonomous loading system of claim 1, wherein, The loading and unloading mechanism includes a multi-degree-of-freedom mechanical arm or a slide rail system.

6. The low earth orbit satellite network based transport drone autonomous loading system of claim 1, wherein, The satellite communication module obtains the loading task instruction, and performs data interaction and cooperation among the unmanned aerial vehicle, the ground station and the satellite network to obtain the parsed loading task information; wherein the data interaction includes sharing of the loading and unloading state and position information of the unmanned aerial vehicle.

7. The low earth orbit satellite network based transport drone autonomous loading system of claim 1, wherein, The intelligent sensing system identifies the appearance attribute and environmental information of the target cargo through the intelligent sensing system to obtain sensor information; wherein the appearance attribute includes cargo type, size and weight, which are monitored in real time by a camera, a radar and a weight sensor in the intelligent sensing system.

8. The low earth orbit satellite network based autonomous loading system for transport drones as claimed in claim 1 wherein, The intelligent decision and control module plans a loading path according to the real-time monitoring of the loading task information and the sensor information, and transmits a decision and control instruction to the unmanned aerial vehicle mechanical execution module according to the visual guidance in the intelligent sensing system.

Images