Method and equipment for protecting hot-line work robot in moving path

Abstract

The embodiment of the invention provides a method and equipment for protecting a hot-line work robot in a moving path. The method comprises the following steps: acquiring surrounding environment data, and constructing a three-dimensional map; task demand information is acquired; based on the three-dimensional map, planning a first collision-free path from the current position of the robot to the starting point and a second collision-free path from the starting point to the target point; the robot sequentially executes the first collision-free path and the second collision-free path, and when the robot executes the first collision-free path and the second collision-free path, the robot enters a protection state; and when the robot arrives at the target point, the robot releases the protection state and enters the operation state. In this way, the mechanical arm transportation protection mechanism is additionally arranged to ensure that the mechanical arm is prevented from being interfered and damaged by the external environment in the operation process of the robot, the operation safety is improved, and the maintenance cost of the robot is remarkably reduced; the situation that workers directly participate in hot-line work is remarkably reduced, and the safety accident risk caused by manual operation errors is reduced.

Description

Technical Field

[0001] The present invention generally relates to the technical field of power engineering automation, and more specifically, to a protection method and device for a live working robot in a moving path. Background Art

[0002] In the electric power industry, live working is an extremely important and dangerous job, which involves the inspection, replacement and maintenance of electrical equipment in operation. With the continuous growth of electricity demand and the continuous expansion of the scale of the power grid, the traditional manual live working method faces problems such as high labor intensity, high safety risks and low work efficiency.

[0003] In recent years, with the rapid development of robot technology, live-working robots, as a new type of power equipment maintenance tool, have received widespread attention and application; live-working robots can operate in live environments, reducing dependence on manual labor, reducing operating risks, and improving work efficiency; however, existing live-working robots still have some problems in practical applications, such as the transportation and protection of the robotic arm are not stable and reliable enough, and are easily disturbed and damaged by the external environment, thus affecting the robot's operating efficiency and safety; collision damage is prone to occur during long-distance transportation or crossing obstacles; in addition, electrostatic discharge and electromagnetic interference in live environments also pose a threat to the electronic components of the robotic arm. Summary of the invention

[0004] According to an embodiment of the present invention, a protection scheme for a live-line working robot in a moving path is provided. This scheme solves the problem of safety accident risks caused by direct human involvement in live-line working, and the problem of the robot arm being disturbed and damaged by the external environment during the robot operation.

[0005] In a first aspect of the present invention, a method for protecting a live working robot in a moving path is provided. The method comprises:

[0006] Acquire surrounding environment data, and construct a three-dimensional map based on the surrounding environment data;

[0007] Acquiring task requirement information, wherein the task requirement information includes starting point coordinates, target point coordinates, time limit and task content;

[0008] Based on the three-dimensional map, planning a first collision-free path from the current position of the robot to the starting point, and a second collision-free path from the starting point to the target point;

[0009] The robot executes the first collision-free path and the second collision-free path in sequence, and when the robot executes the first collision-free path and the second collision-free path, the robot enters a protection state;

[0010] When the robot reaches the target point, the robot is released from the protection state and enters the working state.

[0011] Furthermore, the acquiring of surrounding environment data and constructing a three-dimensional map based on the surrounding environment data includes:

[0012] Acquire surrounding environment data, wherein the surrounding environment data includes laser radar scanning data and RGB image data;

[0013] Preprocessing the surrounding environment data to obtain first sensor data;

[0014] Use SIFT algorithm to extract visual feature points from image data; and extract geometric features from LiDAR scanning data;

[0015] Use the RANSAC algorithm to match feature points and establish spatial relationships;

[0016] The laser radar scanning data and the RGB image data are fused based on the spatial relationship;

[0017] Generate point cloud data based on the fused data, and convert the point cloud data into a three-dimensional mesh model;

[0018] The RGB image data is mapped to a three-dimensional grid model surface to obtain a three-dimensional map.

[0019] Furthermore, the planning of a first collision-free path from the current position of the robot to the starting point and a second collision-free path from the starting point to the target point based on the three-dimensional map includes:

[0020] The task requirement information is parsed, and if the starting point coordinates and the target point coordinates are both in the three-dimensional map, a parsing result is obtained;

[0021] Based on the three-dimensional map, determining a search space range from the analysis results;

[0022] A first initial planned path from the current position of the robot to the starting point and a second initial planned path from the starting point to the target point are searched within the search space, and the first initial planned path and the second initial planned path are smoothed to obtain a first collision-free path and a second collision-free path.

[0023] Further, the first initial planned path is smoothed to obtain a first collision-free path, including:

[0024] Starting from the node closest to the starting point in the first initial planned path, performing line connection and collision detection with the starting point to obtain a first detection result;

[0025] If the first detection result is that there is no obstacle in the line connecting the starting point and the current node, deleting the node between the current node and the starting point in the first initial planned path;

[0026] If the first detection result is that there is an obstacle in the line connecting the starting point and the current node, the starting point is connected to the next node of the current node and a collision detection is performed;

[0027] Repeat the line connection and collision detection until the current node is the current position of the robot, and obtain a collision-free path from the current position of the robot to the starting point.

[0028] Further, the second initial planned path is smoothed to obtain a second collision-free path, including:

[0029] Starting from the node closest to the target point in the second initial planning path, performing line connection and collision detection with the target point to obtain a second detection result;

[0030] If the second detection result is that there is no obstacle in the line connecting the target point and the current node, then deleting the node between the current node and the target point in the second initial planning path;

[0031] If the second detection result is that there is an obstacle in the line connecting the target point and the current node, connect the target point with the next node of the current node and perform collision detection;

[0032] Repeat the line connection and collision detection until the current node is the starting point, and obtain a collision-free path from the starting point to the target point.

[0033] Furthermore, when the robot executes the first collision-free path and the second collision-free path, it also includes: predicting the motion trajectory of the dynamic obstacle and dynamically adjusting the travel speed and direction of the robot.

[0034] Furthermore, predicting the motion trajectory of the dynamic obstacle and dynamically adjusting the travel speed and direction of the robot includes:

[0035] Acquire dynamic obstacle information, respond to the dynamic obstacle information through the LSTM unit in an empty state, and extract key information after the dynamic obstacle information passes through the forget gate;

[0036] The output of the LSTM unit at the previous moment and the input of the LSTM at the current moment are read, and the output and key information of the LSTM unit are filtered through the sigmoid function. After all obstacle state information is input, a dynamic obstacle state of uniform size is obtained;

[0037] The dynamic obstacle state and the robot state information are sequentially input into three fully connected neural networks, and the information output by the three fully connected neural networks is weighted averaged to obtain a fused decision output; wherein the three fully connected neural networks are a first fully connected neural network, a second fully connected neural network, and a third fully connected neural network;

[0038] Based on the fused decision output, the robot's travel speed and direction are dynamically adjusted.

[0039] Furthermore, the first fully connected neural network is used to predict the safety level of the current path according to the dynamic obstacle state and the state information of the robot; the dynamic obstacle state includes the distance, relative speed and expected collision time between the dynamic obstacle and the robot; the state information of the robot includes the perception range and braking ability of the robot;

[0040] The second fully connected neural network is used to predict the task completion time of the current path according to the length of the path, the estimated passing time, and the number of turns;

[0041] The third fully connected neural network is used to calculate the estimated energy consumption for completing the current path based on the terrain slope, the friction coefficient and the energy consumption of the robot.

[0042] Furthermore, when the robot reaches the target point, the robot releases the protection state and enters the working state, including:

[0043] The robot uses sensors to scan the surrounding environment to determine that it can start working;

[0044] The robot performs a self-check and releases the protection state;

[0045] Determine an execution instruction of the robot arm based on the time limit and task content in the task requirement information, and determine an operation type of the robot arm based on the execution instruction;

[0046] Adjust the robot arm to the operating state according to the operation type and start executing the task.

[0047] In a second aspect of the present invention, an electronic device is provided. The electronic device has at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0048] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description.

[0049] The present invention can significantly reduce the situation of direct manual participation in live operations, thereby reducing the risk of safety accidents caused by human operational errors; adding a robotic arm transportation protection mechanism ensures that the robot arm is protected from interference and damage from the external environment during operation, thereby improving the safety of the operation and significantly reducing the maintenance cost of the robot; the robot's intelligent path planning and obstacle avoidance increase the speed of reaching the operation point and the smoothness of the operation process, shortening the overall operation cycle and improving the operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0051] Figure 1 A flowchart of a method for protecting a live working robot in a moving path according to an embodiment of the present invention is shown;

[0052] Figure 2 A flowchart of constructing a three-dimensional map based on the surrounding environment data according to an embodiment of the present invention is shown;

[0053] Figure 3 A flowchart of planning a collision-free path according to an embodiment of the present invention is shown;

[0054] Figure 4 A block diagram of an exemplary electronic device capable of implementing embodiments of the present invention is shown;

[0055] Among them, 400 is an electronic device, 401 is a computing unit, 402 is a ROM, 403 is a RAM, 404 is a bus, 405 is an I / O interface, 406 is an input unit, 407 is an output unit, 408 is a storage unit, and 409 is a communication unit. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0058] The present invention adds a robotic arm transportation protection mechanism to ensure that the robotic arm is protected from interference and damage from the external environment during operation, thereby improving the safety of operation and significantly reducing the maintenance cost of the robot; furthermore, it can significantly reduce the situation where manual labor is directly involved in live operations, thereby reducing the risk of safety accidents caused by human operational errors; the robot's intelligent path planning and obstacle avoidance improves the speed of reaching the operation point and the smoothness of the operation process, shortens the overall operation cycle, and improves operation efficiency.

[0059] Figure 1 A flow chart of a method for protecting a live-working robot in a moving path according to an embodiment of the present invention is shown.

[0060] The method includes:

[0061] S101. Acquire surrounding environment data, and construct a three-dimensional map based on the surrounding environment data.

[0062] Before acquiring the surrounding environment data, the live working robot is started and the hardware self-check is performed through the component verification module of the live working robot, where the component verification module is used to check the robot arm transportation protection mechanism, sensor calibration and electromagnetic compatibility test of the control circuit. Then the surrounding environment data is collected through the sensors installed on the robot, and a three-dimensional map is constructed based on the surrounding environment data through the map construction module.

[0063] In this embodiment, the sensors installed on the robot include a laser radar, an RGB-D camera, an inertial measurement unit, a positioning system, etc. The surrounding environment data that can be obtained at least by the above sensors include laser radar scanning data and RGB image data.

[0064] In this embodiment, if Figure 2 As shown, the acquiring of surrounding environment data and constructing a three-dimensional map based on the surrounding environment data includes:

[0065] S201. Acquire surrounding environment data, where the surrounding environment data includes laser radar scanning data and RGB image data.

[0066] S202: Preprocess the surrounding environment data to obtain first sensing data. The preprocessing includes removing abnormal points of the laser radar and de-distortion processing of the image data.

[0067] S203, extracting visual feature points from the image data using the SIFT algorithm; and extracting geometric features from the laser radar scanning data;

[0068] S204, using the RANSAC algorithm to match feature points and establish spatial relationships;

[0069] S205, fusing the laser radar scanning data and the RGB image data based on the spatial relationship;

[0070] S206, generating point cloud data based on the fused data, and converting the point cloud data into a three-dimensional mesh model;

[0071] S207: Map the RGB image data to a three-dimensional grid model surface to obtain a three-dimensional map.

[0072] Further, S102, task requirement information is obtained, where the task requirement information includes starting point coordinates, target point coordinates, time limit and task content.

[0073] S103 . Based on the three-dimensional map, plan a first collision-free path from the current position of the robot to the starting point, and a second collision-free path from the starting point to the target point.

[0074] Specifically, Figure 3 As shown, based on the three-dimensional map, planning a first collision-free path from the current position of the robot to the starting point, and a second collision-free path from the starting point to the target point, includes:

[0075] S301, parsing the task requirement information, and obtaining a parsing result if the starting point coordinates and the target point coordinates are both in the three-dimensional map.

[0076] S302, determining a search space range from the analysis result based on the three-dimensional map;

[0077] S303, searching for a first initial planned path from the current position of the robot to the starting point and a second initial planned path from the starting point to the target point within the search space, and smoothing the first initial planned path and the second initial planned path to obtain a first collision-free path and a second collision-free path.

[0078] The step of smoothing the first initial planned path to obtain a first collision-free path includes:

[0079] Starting from the node closest to the starting point in the first initial planning path, connect the line with the starting point and perform collision detection to obtain a first detection result; judge the first detection result, if the first detection result is that there is no obstacle in the line between the starting point and the current node, delete the node between the current node and the starting point in the first initial planning path; if the first detection result is that there is an obstacle in the line between the starting point and the current node, connect the starting point with the next node of the current node, and perform collision detection; repeat the connection and collision detection until the current node is the current position of the robot, and obtain a collision-free path from the current position of the robot to the starting point.

[0080] Smoothing the second initial planned path to obtain a second collision-free path includes:

[0081] Starting from the node closest to the target point in the second initial planning path, connect the target point and perform collision detection to obtain a second detection result; if the second detection result is that there is no obstacle in the connection between the target point and the current node, delete the node between the current node and the target point in the second initial planning path; if the second detection result is that there is an obstacle in the connection between the target point and the current node, connect the target point to the next node of the current node and perform collision detection; repeat the connection and collision detection until the current node is the starting point, and obtain a collision-free path from the starting point to the target point.

[0082] Further, S104, the robot executes the first collision-free path and the second collision-free path in sequence, and when the robot executes the first collision-free path and the second collision-free path, the robot enters a protection state.

[0083] In this embodiment, in the protection state, the robot surrounds the robotic arm through the robotic arm transportation protection mechanism.

[0084] Specifically, the robot arm transport protection mechanism is a retractable protective shell. When the robot is in the process of moving, the protective shell will automatically surround the robot arm through the control system, wherein the protective shell is a shell of a high-strength, low-conductivity composite material.

[0085] In some embodiments, when the robot executes the first collision-free path and the second collision-free path, it also includes: predicting the movement trajectory of the dynamic obstacle and dynamically adjusting the travel speed and direction of the robot.

[0086] Specifically, each dynamic obstacle information is input into the LSTM unit of the path optimization module. The LSTM unit is initially in an empty state and receives the dynamic obstacle information through the forget gate to extract key information; the output of the LSTM unit at the previous moment and the input of the LSTM at the current moment are read and filtered through the sigmoid function. After all obstacle state information is input, the obstacle state of uniform size after being processed by the LSTM unit is obtained; the obstacle state processed by the LSTM unit and the robot's own state information are input into three fully connected neural networks in turn, and the information output by the three fully connected neural networks is weighted averaged and fused; based on the fused decision output, the path optimization module dynamically adjusts the robot's travel speed and direction. Among them, the three fully connected neural networks are the first fully connected neural network, the second fully connected neural network and the third fully connected neural network.

[0087] In this embodiment, the first fully connected neural network is used to predict the safety level of the current path according to the dynamic obstacle state and the state information of the robot; the dynamic obstacle state includes the distance, relative speed and expected collision time between the dynamic obstacle and the robot; the state information of the robot includes the perception range and braking ability of the robot;

[0088] The second fully connected neural network is used to predict the task completion time of the current path based on the length of the path, the estimated passing time, and the number of turns; wherein the length of the path is the total length of the current path; the estimated passing time is the time required for the robot to pass the current path; and the number of turns is the number of times the robot turns at an angle greater than 30 degrees while passing the current path.

[0089] The third fully connected neural network is used to calculate the estimated energy consumption for completing the current path based on the terrain slope, the friction coefficient and the energy consumption of the robot.

[0090] S105: When the robot reaches the target point, the robot is released from the protection state and enters the working state.

[0091] When the robot reaches the target point, the robot is released from the protection state and enters the working state, including:

[0092] The robot uses sensors to scan the surrounding environment to determine that it can start working;

[0093] The robot performs a self-check and releases the protection state;

[0094] Determine an execution instruction of the robot arm based on the time limit and task content in the task requirement information, and determine an operation type of the robot arm based on the execution instruction;

[0095] Adjust the robot arm to the operating state according to the operation type and start executing the task.

[0096] Specifically, the robot determines through sensors that it has reached the preset target point, and uses sensors to scan the surrounding environment to determine that it can start working; it performs a status self-check through the component verification module, and controls the robotic arm's transportation protection mechanism to release the protection status through the control system; determines the execution instructions of the robotic arm based on the task requirement information, and determines the operation type of the robotic arm based on the execution instructions; adjusts the robotic arm to the operating state through the operation execution module according to the operation type, and the robotic arm starts to perform the task; monitors the operation process through sensors, and collects monitoring data in real time, and determines the operation effect based on the monitoring data until the task is completed.

[0097] Optionally, after the task is completed, enter the protection state again and go to the next work point.

[0098] According to the embodiments of the present invention, the situation of direct human participation in live working is significantly reduced, thereby reducing the risk of safety accidents caused by human operational errors; adding a robotic arm transportation protection mechanism ensures that the robot arm is protected from interference and damage from the external environment during operation, thereby improving the safety of the operation and significantly reducing the maintenance cost of the robot; the robot's intelligent path planning and obstacle avoidance improve the speed of reaching the operation point and the smoothness of the operation process, shortening the overall operation cycle and improving the operation efficiency.

[0099] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0100] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0101] According to an embodiment of the present invention, the present invention further provides an electronic device.

[0102] Figure 4A schematic block diagram of an electronic device 400 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0103] The electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0104] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as methods S101 to S105. For example, in some embodiments, methods S101 to S105 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the methods S101 to S105 described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute methods S101 to S105 in any other appropriate manner (eg, by means of firmware).

[0106] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0107] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0108] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0109] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0110] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0111] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for protecting a live working robot in a moving path, characterized in that: include: Acquire surrounding environment data, and construct a three-dimensional map based on the surrounding environment data; Acquiring task requirement information, wherein the task requirement information includes starting point coordinates, target point coordinates, time limit and task content; Based on the three-dimensional map, planning a first collision-free path from the current position of the robot to the starting point, and a second collision-free path from the starting point to the target point; The robot executes the first collision-free path and the second collision-free path in sequence, and when the robot executes the first collision-free path and the second collision-free path, the robot enters a protection state; When the robot reaches the target point, the robot is released from the protection state and enters the working state.

2. The method according to claim 1, characterized in that The acquiring of surrounding environment data and constructing a three-dimensional map based on the surrounding environment data includes: Acquire surrounding environment data, wherein the surrounding environment data includes laser radar scanning data and RGB image data; Preprocessing the surrounding environment data to obtain first sensor data; Use SIFT algorithm to extract visual feature points from image data; and extract geometric features from LiDAR scanning data; Use the RANSAC algorithm to match feature points and establish spatial relationships; The laser radar scanning data and the RGB image data are fused based on the spatial relationship; Generate point cloud data based on the fused data, and convert the point cloud data into a three-dimensional mesh model; The RGB image data is mapped to a three-dimensional grid model surface to obtain a three-dimensional map.

3. The method according to claim 1, characterized in that The planning of a first collision-free path from the current position of the robot to the starting point and a second collision-free path from the starting point to the target point based on the three-dimensional map includes: The task requirement information is parsed, and if the starting point coordinates and the target point coordinates are both in the three-dimensional map, a parsing result is obtained; Based on the three-dimensional map, determining a search space range from the analysis results; A first initial planned path from the current position of the robot to the starting point and a second initial planned path from the starting point to the target point are searched within the search space, and the first initial planned path and the second initial planned path are smoothed to obtain a first collision-free path and a second collision-free path.

4. The method according to claim 3, characterized in that Smoothing the first initial planned path to obtain a first collision-free path includes: Starting from the node closest to the starting point in the first initial planned path, performing line connection and collision detection with the starting point to obtain a first detection result; If the first detection result is that there is no obstacle in the line connecting the starting point and the current node, deleting the node between the current node and the starting point in the first initial planned path; If the first detection result is that there is an obstacle in the line connecting the starting point and the current node, the starting point is connected to the next node of the current node and a collision detection is performed; Repeat the line connection and collision detection until the current node is the current position of the robot, and obtain a collision-free path from the current position of the robot to the starting point.

5. The method according to claim 1, characterized in that Smoothing the second initial planned path to obtain a second collision-free path includes: Starting from the node closest to the target point in the second initial planning path, performing line connection and collision detection with the target point to obtain a second detection result; If the second detection result is that there is no obstacle in the line connecting the target point and the current node, then deleting the node between the current node and the target point in the second initial planning path; If the second detection result is that there is an obstacle in the line connecting the target point and the current node, connect the target point with the next node of the current node and perform collision detection; Repeat the line connection and collision detection until the current node is the starting point, and obtain a collision-free path from the starting point to the target point.

6. The method according to claim 1, characterized in that When the robot executes the first collision-free path and the second collision-free path, the method further includes: predicting the motion trajectory of the dynamic obstacle and dynamically adjusting the travel speed and direction of the robot.

7. The method according to claim 6, characterized in that The predicting the motion trajectory of the dynamic obstacle and dynamically adjusting the traveling speed and direction of the robot includes: Acquire dynamic obstacle information, respond to the dynamic obstacle information through the LSTM unit in an empty state, and extract key information after the dynamic obstacle information passes through the forget gate; The output of the LSTM unit at the previous moment and the input of the LSTM at the current moment are read, and the output and key information of the LSTM unit are filtered through the sigmoid function. After all obstacle state information is input, a dynamic obstacle state of uniform size is obtained; The dynamic obstacle state and the robot state information are sequentially input into three fully connected neural networks, and the information output by the three fully connected neural networks is weighted averaged to obtain a fused decision output; wherein the three fully connected neural networks are a first fully connected neural network, a second fully connected neural network, and a third fully connected neural network; Based on the fused decision output, the robot's travel speed and direction are dynamically adjusted.

8. The method according to claim 7, characterized in that The first fully connected neural network is used to predict the safety level of the current path according to the state of the dynamic obstacle and the state information of the robot; the state of the dynamic obstacle includes the distance, relative speed and expected collision time between the dynamic obstacle and the robot; The robot's status information includes the robot's sensing range and braking capability; The second fully connected neural network is used to predict the task completion time of the current path according to the length of the path, the estimated passing time, and the number of turns; The third fully connected neural network is used to calculate the estimated energy consumption for completing the current path based on the terrain slope, the friction coefficient and the energy consumption of the robot.

9. The method according to claim 1, characterized in that: When the robot reaches the target point, the robot is released from the protection state and enters the working state, including: The robot uses sensors to scan the surrounding environment to determine that it can start working; The robot performs a self-check and releases the protection state; Determine an execution instruction of the robot arm based on the time limit and task content in the task requirement information, and determine an operation type of the robot arm based on the execution instruction; Adjust the robot arm to the operating state according to the operation type and start executing the task.

10. An electronic device comprising at least one processor; and a memory connected in communication with the at least one processor; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

Images