Real-time control system and method for humanoid robot cluster based on mobile ad hoc network

Abstract

The embodiment of the invention discloses a humanoid robot cluster real-time control system and method based on a mobile ad hoc network. The system comprises an equipment layer which comprises an operation system and equipment of the humanoid robot; the device comprises an ad hoc network module. The edge layer comprises a server and a humanoid robot; and the platform layer is used for controlling and managing the humanoid robot in real time. The method has the advantages that under the environment that a traditional wireless cellular network cannot be accessed, data sharing of all humanoid robots in the network can be achieved, and therefore tasks of different robots are arranged according to an intelligent scheduling algorithm in combination with the current states, environment information and the like of the robots; based on an efficient communication protocol, robot states and surrounding environment factors can be quickly obtained, after tasks of the robots are arranged, different task instructions are respectively issued to different robots in the network, and the robots at different nodes in the network can respond to the instructions in real time, so that real-time control of the system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of humanoid robots, and in particular to a real-time control system and method for a humanoid robot cluster based on a mobile ad hoc network. Background Art

[0002] As humanoid robots gradually become a reality, they have many applications in industrial automation, service industry, etc. At present, the application of humanoid robots cannot be separated from the operation of technicians, including but not limited to the background control system and the remote control to operate the robot. The communication between multiple devices requires the use of wireless local area network or cellular mobile communication system to ensure the real-time and security monitoring of the instructions issued during communication.

[0003] Current wireless LANs or cellular mobile communication systems all rely on central access points. For example, to control a robot's movement or voice interaction in an exhibition hall, the robot and the main control computer or controller need to be connected to the same LAN. Once the central access point is lost or the base station signal is lost due to the gathering of people and equipment, communication will be interrupted, and in some emergency situations, it is impossible to quickly establish an effective basic network.

[0004] As a new type of network, mobile ad hoc networks, including mobile Ad Hoc networks, wireless sensor networks and other technologies, do not require any infrastructure support. Nodes form multi-hop wireless networks through self-organization. Currently, communication and data transmission between terminals have been realized in the fields of industrial manufacturing, warehousing and logistics. In the field of drones, ad hoc networks can also perceive network changes in a timely manner, automatically configure or reconstruct the network, and ensure real-time connectivity of data links. At the same time, they have a high degree of autonomy and self-adaptation. However, in the field of humanoid robots, there is no cluster management of a collaborative working group composed of multiple robots, so as to achieve rapid task allocation, execution and feedback through a unified scheduling system, efficient communication protocols and intelligent decision-making algorithms. Summary of the invention

[0005] In view of the technical deficiencies pointed out in the background technology, an object of the embodiments of the present invention is to provide a real-time control system and method for a humanoid robot cluster based on a mobile ad hoc network.

[0006] To achieve the above-mentioned objectives, in the first aspect, an embodiment of the present application provides a real-time control system for a humanoid robot cluster based on a mobile self-organizing network, including a server and multiple humanoid robots, the server and each of the humanoid robots including a self-organizing network module, the server and the multiple humanoid robots quickly network and establish a network topology through the self-organizing network module, the server is used to obtain the current status data of all humanoid robots in the network, and perform real-time control of the humanoid robots based on the current status data.

[0007] As a specific implementation of the present application, the server includes:

[0008] A data receiving unit, used to obtain current status data of all humanoid robots in the network;

[0009] An instruction generation unit, for generating control instructions for each of the humanoid robots in the network based on the current state data and according to the current overall task scheduling and intelligent scheduling algorithm;

[0010] The instruction sending unit is used to distribute the control instruction to the self-organizing network module of each humanoid robot in the network based on the self-organizing network communication protocol.

[0011] Furthermore, as a preferred implementation of the present application, each of the humanoid robots further comprises:

[0012] The operating system is used to receive the control instructions sent by the self-organizing network module, and realize the action control of the humanoid robot through the control instructions.

[0013] In a second aspect, the embodiment of the present application further provides another real-time control system for a humanoid robot cluster based on a mobile ad hoc network, comprising:

[0014] The device layer includes an operating system and devices of the humanoid robot; the devices include a self-organizing network module; each of the humanoid robots completes network communication and data reception and forwarding through the self-organizing network module;

[0015] The edge layer includes a plurality of ad hoc network nodes, each of which is a server or a humanoid robot; the server is used to collect current state data sent by all humanoid robots and forward the current state data;

[0016] The platform layer is used to control the humanoid robot in real time based on the current state data.

[0017] The equipment also includes the robot's dexterous hands, mechanical arms, sensors, leg motors and batteries.

[0018] As a specific implementation of the present application, the platform layer is specifically used for:

[0019] Get the current status data of all humanoid robots in the network;

[0020] Based on the current state data, according to the current overall task scheduling and intelligent scheduling algorithm, generate control instructions for each of the humanoid robots in the network;

[0021] Based on the self-organizing network communication protocol, the control instruction is distributed to the self-organizing network module of each humanoid robot in the network, so that the operating system of the humanoid robot can control each device in real time according to the control instruction.

[0022] In a third aspect, an embodiment of the present invention further provides a method for real-time control of a humanoid robot cluster based on a mobile ad hoc network, which is applicable to the system described in the second or third aspect above, comprising the steps of:

[0023] The server and multiple humanoid robots quickly form a network and establish a network topology through the self-organizing network module;

[0024] The operating system of each humanoid robot obtains the current state data of the humanoid robot and forwards the current state data;

[0025] The server collects the current status data of all humanoid robots in the network, performs task scheduling and intelligent scheduling based on the current status data, and generates control instructions;

[0026] The self-organizing network module of each humanoid robot receives the control instruction;

[0027] The operating system of each humanoid robot realizes the motion control of the humanoid robot through control instructions.

[0028] The implementation of the embodiment of the present invention has the following advantages:

[0029] 1. Based on mobile self-organizing networks, humanoid robots can quickly establish an effective basic network when the base station signal is lost or the central access point is lost. Each humanoid robot in the network can act as a node to distribute its own data and the node data with which it has established communication to neighboring nodes, thereby quickly establishing a network topology.

[0030] 2. In an environment where traditional wireless cellular networks cannot be accessed, the humanoid robot cluster control system based on a mobile self-organizing network can realize data sharing among all humanoid robots in the network, thereby choreographing the tasks of different robots based on the intelligent scheduling algorithm, combined with the current status and environmental information of the robots. In the cluster, each robot makes independent decisions by sensing the environment and exchanging information with surrounding nodes, while maintaining the consistency of group behavior. When choreographing robot tasks, the dynamic allocation of tasks and the dynamic adjustment of priorities enable each robot to complete the tasks step by step.

[0031] 3. Based on an efficient communication protocol, the cluster control system of humanoid robots can quickly obtain the robot status and surrounding environmental factors. After arranging the robot's tasks, different task instructions are issued to different robots in the network. Robots at different nodes in the network can respond to instructions in real time, thereby realizing real-time control of the system.

[0032] 4. The humanoid robot cluster control system based on mobile self-organizing network has no central node. Nodes within the network can join and leave the network at any time. The failure of any node will not affect the operation of the entire network, and it has strong anti-destruction capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for use in the specific implementation or the description of the prior art are briefly introduced below.

[0034] Figure 1 This is an architecture diagram of a real-time control system for a humanoid robot cluster based on a mobile ad hoc network provided by an embodiment of the present invention;

[0035] Figure 2 is a flow chart of a real-time control method for a humanoid robot cluster based on a mobile ad hoc network provided by an embodiment of the present invention;

[0036] Figure 3 It is a network diagram composed of multiple humanoid robots. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0038] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0039] The first embodiment of the present application provides a real-time control system for a humanoid robot cluster based on a mobile self-organizing network, including a server and multiple humanoid robots, wherein the server and each of the humanoid robots include a self-organizing network module, and the server and the multiple humanoid robots quickly form a network and establish a network topology through the self-organizing network module. The server is used to obtain current status data of all humanoid robots in the network, and perform real-time control of the humanoid robots based on the current status data.

[0040] Specifically, the server includes:

[0041] A data receiving unit, used to obtain current status data of all humanoid robots in the network;

[0042] An instruction generation unit, for generating control instructions for each of the humanoid robots in the network based on the current state data and according to the current overall task scheduling and intelligent scheduling algorithm;

[0043] The instruction sending unit is used to distribute the control instruction to the self-organizing network module of each humanoid robot in the network based on the self-organizing network communication protocol.

[0044] Furthermore, each of the humanoid robots further comprises:

[0045] The operating system is used to receive the control instructions sent by the self-organizing network module, and realize the action control of the humanoid robot through the control instructions.

[0046] It should be noted that the cluster control of humanoid robots is inseparable from the real-time transmission of various data, including data from various sensors, the current position and posture of the robot, battery data, etc. If real-time cluster control is to be achieved, the rapid distribution and acquisition of these key information are essential. To this end, the networking communication module needs to quickly send this data to the network topology through a defined communication protocol, so that each node in the network can obtain the relevant data of other nodes in real time. After the server in the edge layer obtains the data of all humanoid robots in the self-organizing network, it issues control instructions to all humanoid robots in the edge layer according to the intelligent scheduling algorithm and communication protocol.

[0047] Please refer to Figure 1The second embodiment of the present application provides another real-time control system for a humanoid robot cluster based on a mobile ad hoc network, including a platform layer, an edge layer and a device layer. The following are respectively described:

[0048] (1) Equipment layer

[0049] The device layer includes the operating system and devices of the humanoid robot. Each humanoid robot is a collection of devices, including the robot's dexterous hands, mechanical arms, sensors, leg motors, batteries, etc. The core self-organizing network module is also a device on the robot. The robot relies on this self-organizing network module for network communication and data reception and forwarding.

[0050] In the device layer, sensors include various perception modules of humanoid robots, such as cameras, microphone arrays, speakers, IMU modules, lidar, etc.

[0051] (2) Edge layer

[0052] The edge layer includes multiple ad hoc network nodes, each of which is a server or a humanoid robot; the server is used to collect the current state data sent by all humanoid robots and forward the current state data. It should be noted that the edge layer is all ad hoc network nodes in the network, including servers and all humanoid robots in the network.

[0053] In the edge layer, efficient real-time communication protocols are the basis for ensuring the stable and efficient operation of humanoid robot clusters. They also need to follow three principles: 1. Low latency: ensure the real-time transmission of control signals to ensure the movement and task coordination of humanoid robots; 2. High reliability: maintain stable communication links when the network topology changes frequently; 3. Fault tolerance: support dynamic joining and leaving of nodes to prevent local node failures from affecting the overall network.

[0054] At the same time, data packets are prioritized based on the characteristics of humanoid robots. The first-tier priority is: control instructions such as walking, gait adjustment, and alarm signals; the second-tier priority is: environmental perception data such as robot vision and touch, map sharing, etc.; the third-tier priority is: non-real-time data such as status logs, monitoring information, etc.

[0055] (3) Platform layer

[0056] The server in the network is a management platform. Since the mobile ad hoc network is decentralized and has no central node, the server side also has an ad hoc network module, which is also a node in the ad hoc network. It is just because it needs to perform overall task scheduling and intelligent real-time scheduling for other robot nodes in the network, and has high requirements on computing power in terms of scheduling delay and control accuracy. Therefore, it is used as a platform layer and has functions such as user authority management, device management, energy consumption management, historical records and data dashboards.

[0057] In the platform layer, the dynamic task allocation of robots is realized through intelligent scheduling algorithms to improve the overall efficiency and completion rate. It mainly follows three core principles: 1. Load balancing: avoid too many tasks being concentrated on a few robots; 2. Position priority: assign tasks according to the distance between the current position of different robots and the task target, reducing commuting time and response time. 3. Capability matching: assign appropriate tasks according to the hardware and software capabilities of the robot.

[0058] The above-mentioned real-time control system of humanoid robot cluster based on mobile self-organizing network includes the following specific control steps:

[0059] (1) After all devices are powered on, the self-organizing network module is automatically activated.

[0060] (2) The robot operating system sends data on the current state of the humanoid robot to the self-organizing network module of the main body.

[0061] (3) Based on the routing protocol, data about the current status of other humanoid robots is collected at the edge network layer and the optimal transmission path is found.

[0062] (4) Create and maintain routing tables and forward data packets at the edge network layer.

[0063] (5) The server at the edge layer obtains the current status data of all humanoid robots in the network and generates control instructions for each humanoid robot in the network based on the current overall task scheduling and intelligent scheduling algorithm.

[0064] (6) Based on the self-organizing network communication protocol, the control instruction data is distributed to the self-organizing network module of each robot in the network.

[0065] (7) After receiving the control command, the self-organizing network module of each robot in the network sends the corresponding command data to the operating system of the robot body. Through the node subscription and forwarding in the robot operating system, the rotation of the motor on the humanoid robot is controlled, thereby realizing the motion control of the humanoid robot.

[0066] The advantages of implementing the real-time control system of humanoid robot cluster based on mobile ad hoc network provided by the embodiment of the present invention are as follows:

[0067] 1. Based on mobile self-organizing networks, humanoid robots can quickly establish an effective basic network when the base station signal is lost or the central access point is lost. Each humanoid robot in the network can act as a node to distribute its own data and the node data with which it has established communication to neighboring nodes, thereby quickly establishing a network topology.

[0068] 2. In an environment where traditional wireless cellular networks cannot be accessed, the humanoid robot cluster control system based on a mobile self-organizing network can realize data sharing among all humanoid robots in the network, thereby choreographing the tasks of different robots based on the intelligent scheduling algorithm, combined with the current status and environmental information of the robots. In the cluster, each robot makes independent decisions by sensing the environment and exchanging information with surrounding nodes, while maintaining the consistency of group behavior. When choreographing robot tasks, the dynamic allocation of tasks and the dynamic adjustment of priorities enable each robot to complete the tasks step by step.

[0069] 3. Based on an efficient communication protocol, the cluster control system of humanoid robots can quickly obtain the robot status and surrounding environmental factors. After arranging the robot's tasks, different task instructions are issued to different robots in the network. Robots at different nodes in the network can respond to instructions in real time, thereby realizing real-time control of the system.

[0070] 4. The humanoid robot cluster control system based on mobile self-organizing network has no central node. Nodes within the network can join and leave the network at any time. The failure of any node will not affect the operation of the entire network, and it has strong anti-destruction capabilities.

[0071] Based on the same inventive concept, an embodiment of the present invention provides a real-time control method for a humanoid robot cluster based on a mobile ad hoc network, such as Figure 2 As shown, the following steps are included:

[0072] S1, the server and multiple humanoid robots quickly form a network through the self-organizing network module and establish a network topology. Among them, the network topology established by multiple humanoid robots is as follows Figure 3 shown.

[0073] S2, the operating system of the humanoid robot obtains the current state data of the humanoid robot body and forwards the current state data;

[0074] S3, the humanoid robot collects the current status data of other humanoid robots in the network and forwards it.

[0075] S4, the server collects the current status data of all humanoid robots in the network, performs task scheduling and intelligent scheduling based on the current status data to generate control instructions.

[0076] Specifically, based on the current state data, control instructions for each humanoid robot in the network are generated according to the current overall task scheduling and intelligent scheduling algorithm.

[0077] S5, the self-organizing network module of the humanoid robot body receives the control instruction from the server.

[0078] S6, the operating system of the humanoid robot body realizes the motion control of the humanoid robot through control instructions.

[0079] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A real-time control system for a humanoid robot cluster based on a mobile ad hoc network, characterized in that: It includes a server and multiple humanoid robots, the server and each of the humanoid robots include a self-organizing network module, the server and the multiple humanoid robots quickly network and establish a network topology through the self-organizing network module, the server is used to obtain the current status data of all humanoid robots in the network, and control the humanoid robots in real time based on the current status data.

2. The system according to claim 1, characterized in that The server comprises: A data receiving unit, used to obtain current status data of all humanoid robots in the network; An instruction generation unit, for generating control instructions for each of the humanoid robots in the network based on the current state data and according to the current overall task scheduling and intelligent scheduling algorithm; The instruction sending unit is used to distribute the control instruction to the self-organizing network module of each humanoid robot in the network based on the self-organizing network communication protocol.

3. The system according to claim 3, characterized in that Each of the humanoid robots further comprises: The operating system is used to receive the control instructions sent by the self-organizing network module, and realize the action control of the humanoid robot through the control instructions.

4. A real-time control system for a humanoid robot cluster based on a mobile ad hoc network, characterized in that: include: The device layer includes an operating system and devices of the humanoid robot; the devices include a self-organizing network module; each of the humanoid robots completes network communication and data reception and forwarding through the self-organizing network module; The edge layer includes a plurality of ad hoc network nodes, each of which is a server or a humanoid robot; the server is used to collect current state data sent by all humanoid robots and forward the current state data; The platform layer is used to control the humanoid robot in real time based on the current state data.

5. The system according to claim 4, characterized in that The device also includes the robot's dexterous hands, mechanical arms, sensors, leg motors and batteries.

6. The system according to claim 4, characterized in that The edge layer is also used for: The data is prioritized based on the characteristics of the humanoid robot; the first priority includes control instructions, the second priority includes environmental perception data, and the third priority includes status logs and monitoring signals.

7. The system according to claim 4, characterized in that The platform layer is specifically used for: Get the current status data of all humanoid robots in the network; Based on the current state data, according to the current overall task scheduling and intelligent scheduling algorithm, generate control instructions for each of the humanoid robots in the network; Based on the self-organizing network communication protocol, the control instruction is distributed to the self-organizing network module of each humanoid robot in the network, so that the operating system of the humanoid robot can control each device in real time according to the control instruction.

8. A real-time control method for a humanoid robot cluster based on a mobile ad hoc network, characterized in that: The method is applicable to the system according to any one of claims 1 to 3, comprising: The server and multiple humanoid robots quickly form a network and establish a network topology through the self-organizing network module; The operating system of each humanoid robot obtains the current state data of the humanoid robot and forwards the current state data; The server collects the current status data of all humanoid robots in the network, performs task scheduling and intelligent scheduling based on the current status data, and generates control instructions; The self-organizing network module of each humanoid robot receives the control instruction; The operating system of each humanoid robot realizes the motion control of the humanoid robot through the control instructions.

Images