First node, second node, wireless communication network, and methods thereby performing a set of objectives in geospatial space.

CN115942875BActive Publication Date: 2026-09-01TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN201980101978.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-10-30
Publication Date
2026-09-01
Estimated Expiration
2039-10-30

AI Technical Summary

Technical Problem

[0016]这类系统可能导致时频资源和电池资源的浪费,进而导致电信网络中延迟增加和容量减少,从而限制了这类方法的适用性

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115942875B_ABST
    Figure CN115942875B_ABST
Patent Text Reader

Abstract

A method executed by a first node (111). The first node (111) determines (302) a plan. The plan is determined based on: i) a first objective to be achieved according to the capabilities of the first node (111), and a first set of first actions to be performed by the first node (111) to achieve the first objective, and ii) for each of one or more second nodes (120): a) a corresponding objective to be achieved according to the corresponding capabilities of each second node, and b) a corresponding set of first actions to be performed individually by each second node to achieve the corresponding objective. The plan is to collaboratively achieve the first objective and each of the corresponding objectives by determining a corresponding set of second actions to be performed by the first node (111) and each second node respectively. The first node (111) sends (303) a corresponding instruction indicating the determined second actions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention generally relates to a first node and a method thereon for achieving a set of objectives in geospatial space. This invention also generally relates to a second node and a method thereon for achieving the same set of objectives in geospatial space. Furthermore, this invention generally relates to a wireless communication network comprising a first node and one or more second nodes, including a second node, to achieve the same set of objectives in geospatial space. Background Technology

[0002] Nodes within a wireless communication network can be wireless devices, such as, for example, user equipment (UE), station (STA), mobile terminal, wireless terminal, terminal, Internet of Things (IoT) device, and / or mobile station (MS). Wireless devices are capable of wireless communication within a cellular communication network or wireless communication network (sometimes also referred to as a cellular radio system, cellular system, or cellular network). For example, communication can occur between two wireless devices, between a wireless device and a regular telephone, and / or between a wireless device and a server via a radio access network (RAN) and possibly one or more core networks included within the wireless communication network. Wireless devices can also be referred to as wirelessly capable mobile phones, cellular phones, laptops, or tablets, with only a few additional examples mentioned. Wireless devices in this context can be, for example, portable, pocket-sized, handheld, computer-integrated, or vehicle-mounted mobile devices capable of voice and / or data communication with another entity (such as another terminal or server) via the RAN.

[0003] The geographical area covered by a wireless communication network can be divided into cell areas, each served by a network node, such as a radio network node or base station (BS), sometimes referred to as, for example, a transport point (TP), radio base station (RBS), gNB, evolved Node B (“eNB”), “eNodeB”, “NodeB”, “B node”, or BTS (Base Transceiver Station), depending on the technology and terminology used. Based on transmission power and therefore also on cell size, base stations can be of different categories, such as, for example, wide-area base stations, mid-range base stations, local base stations, and home base stations. A cell is a geographical area covered by radio coverage provided by a base station at a base station site. A base station located at a base station site can serve one or more cells. Furthermore, each base station can support one or more communication technologies. 3GPP Long Term Evolution (LTE) base stations can be referred to as eNodeBs or even eNBs and can be directly connected to one or more core networks. In the context of this invention, the term downlink (DL) is used to describe a transmission path from a base station to a wireless device. The term uplink (UL) is used to describe a transmission path in the opposite direction, i.e., from the wireless device to the base station.

[0004] NR

[0005] From a radio perspective, the so-called 5G system began standardization in 3GPP, and the so-called New Radio (NR) is simply the name of the radio interface. The NR infrastructure is being discussed within 3GPP. In the current concept, gNB stands for NR BS, where one NR BS can correspond to one or more transmit and / or receive points.

[0006] One of the main goals of NR is to provide operators with more capacity to meet the ever-increasing traffic demands and diverse applications. Because of this, NR will be able to operate at high frequencies, such as frequencies above 6 GHz, up to 60 or even 100 GHz.

[0007] Operating at higher frequencies allows for the use of smaller antenna elements, enabling antenna arrays with numerous antenna elements. Such arrays facilitate beamforming, where multiple antenna elements can be used to form a narrow beam, thereby compensating for challenging propagation characteristics.

[0008] Internet of Things (IoT)

[0009] The Internet of Things (IoT) can be understood as the interconnection of communication devices, such as physical devices, vehicles (also referred to as "connected devices" and "smart devices"), buildings, and other items embedded with electronics, software, sensors, actuators, and network connections that enable these objects to collect and exchange data. IoT can allow for remote control and / or sensing of objects through existing network infrastructure.

[0010] The "things" in the IoT context can refer to a wide variety of devices, such as implantable cardiac monitors, biochip transponders in farm animals, electric clams in coastal waters, cars with built-in sensors, DNA analysis equipment for environmental / food / pathogen monitoring, or field operational equipment that can assist firefighters in search and rescue operations. Examples include home automation devices that control and automate lighting via cameras, light monitors, etc.; heating devices (such as "smart" thermostats); ventilation devices; air conditioners; and appliances such as washing machines, dryers, ovens, refrigerators, or freezers. These devices can be remotely monitored using telecommunications. They can collect data using various existing technologies and then autonomously transmit that data between other devices.

[0011] Machine Type Communication (MTC)

[0012] In recent years, Machine-Type Communication (MTC), particularly in the context of the Internet of Things (IoT), has proven to be an integral part of the growing cellular technology landscape. MTC devices can be communication devices, typically wireless communication devices or simple user equipment, which are self- and / or automatically controlled unattended machines and are generally not associated with active human users to generate data traffic. Compared to regular mobile phones or smartphones, MTC devices are typically simpler and often associated with more specific applications or purposes. MTC involves communication to and / or from wireless communication networks of MTC devices, which can often be entirely different in nature and have additional requirements distinct from those associated with, for example, regular mobile phones and smartphones. In the context of IoT and its development, it is clear that MTC traffic will increase, thus requiring greater support in wireless communication systems.

[0013] An autonomous agent or intelligent autonomous system can be understood as an entity that can interact with its environment and decide on the actions to be performed with a certain degree of independence or autonomy. The actions of an autonomous agent can be based on the knowledge, desires, or goals of the user of the autonomous agent or other entities. The actions that an autonomous agent can perform may depend on the actions that the autonomous agent can support.

[0014] As systems performing Simultaneous Localization and Mapping (SLAM) from a single robot become quite mature, the possibility of using teams of robots to perform tasks collaboratively is attracting increasing interest [1,2]. Autonomous agents can collaborate to leverage each other's capabilities and the resulting artifacts, which can be understood as functional outputs such as images, thermal images, etc. For example, in long-range reconnaissance missions, agents from different organizations may be assigned tasks independently. When they converge on a target area, they can exchange their capabilities, learn about the artifacts produced by one and consumed by another, thereby reducing the overall cost of the mission through collaboration where possible.

[0015] In such cases, each agent can independently explore the environment on which a limited-memory SLAM is running, while sending all the collected information to a central server, which may be a ground station with increased computing resources in a centralized infrastructure [3]. The server can manage the maps of all agents, triggering loop closure, map fusion, optimization, and distributing information back to the agents. This allows agents to incorporate observations from others into their SLAM estimates in real time, thus demonstrating the applicability of such a system in scenarios involving multiple autonomous agents. One such example has been described as performing tasks in forest environments, such as, for example, using a monocular vision system that is easy to mount in a small to medium-sized unmanned aircraft for search and rescue [4].

[0016] Such systems may lead to a waste of time and frequency resources and battery resources, which in turn leads to increased latency and reduced capacity in telecommunications networks, thus limiting the applicability of such methods. Summary of the Invention

[0017] One objective of the embodiments described herein is to improve the processing of tasks to be performed by intelligent autonomous agents in wireless communication networks. More specifically, the objective of the embodiments described herein is to improve the processing of the realization of a set of objectives by nodes in wireless communication networks in geospatial space.

[0018] According to a first aspect of the embodiments herein, this objective is achieved by a method performed by a first node. The method is to achieve a set of objectives in geospatial space. The first node operates in a wireless communication network. The first node determines a plan. The first node determines the plan based on the following: First, a first objective to be achieved by the first node in geospatial space. The first objective is to be achieved according to a first set of capabilities of the first node. Furthermore, a first set of first actions is performed individually by the first node to achieve the first objective. Second, for each of one or more second nodes within the radio coverage area of ​​the first node: a) a corresponding objective to be achieved in geospatial space according to a corresponding set of capabilities of each of the one or more second nodes, and b) a corresponding set of first actions to be performed individually by each of the one or more second nodes to achieve the corresponding objective. The plan is to collaboratively achieve each of the first objective and the corresponding objective in geospatial space. This plan is achieved by determining a corresponding set of second actions to be performed separately by each of the one or more second nodes and the first node. The first node also sends a corresponding instruction to each of the one or more second nodes. The corresponding instruction is used to indicate the determined corresponding set of second actions.

[0019] According to a second aspect of the embodiments herein, this objective is achieved by a method performed by a second node. The method is to achieve the set of objectives in geospatial space. The second node operates in a wireless communication network. The second node sends a corresponding first instruction to a first node. The first node operates in a wireless communication network. The corresponding first instruction is used to instruct the second node on a corresponding objective to be achieved in geospatial space based on a corresponding set of capabilities of the second node. The corresponding first instruction also instructs the corresponding set of capabilities of the second node, and a corresponding set of first actions to be performed individually by the second node to achieve the corresponding objective. The second node receives a corresponding second instruction from the first node. The corresponding second instruction is used to instruct the set of second actions to be performed individually by the second node. The reception of the corresponding second instruction is based on the transmitted corresponding first instruction. The received corresponding second instruction is based on a plan for the first node and one or more second nodes within the radio coverage area of ​​the first node to collaboratively achieve the following: First, a first objective of the first node to be achieved in geospatial space based on the first set of capabilities of the first node. Second, a corresponding objective to be achieved in geospatial space by each of the one or more second nodes based on its corresponding set of capabilities. This plan is based on a corresponding set of second actions to be performed separately by each of the one or more second nodes and the first node.

[0020] According to a third aspect of the embodiments herein, this objective is achieved by a first node. The first node can be considered as being used to achieve the set of objectives in geospatial space. The first node is also configured to determine a plan. The first node is configured to determine the plan based on: First, a first objective of the first node to be achieved in geospatial space according to a first set of capabilities of the first node. Additionally, based on a first set of first actions to be performed individually by the first node to achieve the first objective. Second, for each of one or more second nodes within the radio coverage area of ​​the first node: a) a corresponding objective to be achieved in geospatial space according to a corresponding set of capabilities of each of the one or more second nodes, and b) a corresponding set of first actions to be performed individually by each of the one or more second nodes to achieve the corresponding objective. The plan is to collaboratively achieve each of the corresponding objective and the first objective in geospatial space. The first node is configured to determine the plan by determining a corresponding set of second actions to be performed by each of the one or more second nodes and the first node, respectively. The first node is also configured to send a corresponding instruction to each of the one or more second nodes. The corresponding instruction is configured to indicate a corresponding set of second actions to be determined.

[0021] According to a fourth aspect of the embodiments herein, this objective is achieved by a second node. The second node can be considered as being used to achieve the set of objectives in geospatial space. The second node is configured to operate in a wireless communication network. The second node is also configured to send a corresponding first instruction to a first node configured to operate in the wireless communication network. The corresponding first instruction is configured to instruct the following: First, a) a corresponding objective of the second node to be achieved in geospatial space based on a corresponding set of capabilities of the second node. Second, the corresponding set of capabilities of the second node, and third, a corresponding set of first actions to be performed independently by the second node to achieve the corresponding objective. The second node is also configured to receive a corresponding second instruction from the first node. The corresponding second instruction is configured to instruct the set of second actions to be performed independently by the second node. Receiving the corresponding second instruction is configured based on the corresponding first instruction configured to be sent. The corresponding second instruction configured to be received is configured based on a plan for the first node and one or more second nodes within the radio coverage area of ​​the first node to collaboratively achieve the following: First, a first objective of the first node to be achieved in geospatial space based on a first set of capabilities of the first node. Second, each of the one or more second nodes has a corresponding objective to achieve in geospatial space based on its respective set of capabilities. This plan is configured based on a corresponding set of second actions to be performed by each of the one or more second nodes and the first node, respectively.

[0022] According to a fourth aspect of the embodiments herein, this objective is achieved via a wireless communication network. The wireless communication network is configured to enable communication between a first node and one or more second nodes, including a second node, to achieve a set of objectives in geospatial space. The second nodes are configured to send a corresponding first instruction to the first node. The corresponding first instruction is configured to indicate a corresponding objective of the second node to be achieved in geospatial space based on a corresponding set of capabilities of the second node. The corresponding first instruction is also configured to indicate a corresponding set of capabilities of the second node. The corresponding first instruction is further configured to indicate a corresponding set of first actions to be performed solely by the second node to achieve the corresponding objective. The first node is configured to determine a plan based on: a) a first objective of the first node to be achieved in geospatial space based on a first set of capabilities of the first node, and a first set of first actions to be performed solely by the first node to achieve the first objective. The first node is also configured to determine a plan for each of the one or more second nodes within the radio coverage area of ​​the first node based on: a) a corresponding objective to be achieved in geospatial space based on a corresponding set of capabilities of each of the one or more second nodes, and b) a corresponding set of first actions to be performed solely by each of the one or more second nodes to achieve the corresponding objective. The plan aims to collaboratively achieve a corresponding objective and each of the first objectives in geospatial space by determining a corresponding set of second actions to be performed by each of one or more second nodes and the first node, respectively. The first node is also configured to send a corresponding instruction to each of the one or more second nodes. The corresponding instruction is configured to indicate the corresponding set of second actions to be determined. In this type of embodiment, the second nodes are also configured to receive a corresponding second instruction from the first node. The corresponding second instruction is configured to indicate the set of second actions to be performed individually by the second node.

[0023] By having a first node determine a plan based on its own primary objective and the corresponding objectives of one or more second nodes, and then sending appropriate instructions to each second node, collaborative efforts can be made in geospatial space to achieve both the primary and secondary objectives. This allows for the identification of a common plan that can more effectively achieve all objectives. For example, if two second nodes need to perform a primary action in the same geospatial area, which might involve a 5-kilometer journey between the two second nodes, the first node can determine a plan such that only one of the second nodes needs to travel to the area—for example, the node capable of performing both primary actions. In this way, the other second node can avoid having to travel to that area and instead dedicate its resources to performing secondary actions in different geospatial areas.

[0024] Therefore, the second action to be performed can be determined to achieve the goal, while using resources such as energy resources, time resources, and frequency resources more effectively. Attached Figure Description

[0025] Examples of embodiments described herein are illustrated with reference to the accompanying drawings and the following description.

[0026] Figure 1 This is a schematic diagram illustrating a wireless communication network according to an embodiment of this document.

[0027] Figure 2 This is a schematic diagram illustrating another non-limiting example of a wireless communication network according to embodiments of this article.

[0028] Figure 3 This is a flowchart depicting the method in the first node according to the embodiments herein.

[0029] Figure 4 This is a flowchart depicting the method in the second node according to the embodiments of this article.

[0030] Figure 5 This is a schematic diagram of some aspects of the methods in the first and second nodes according to the embodiments of this article.

[0031] Figure 6 This is a signaling diagram illustrating an example of a method according to embodiments of this document.

[0032] Figure 7 This is a signaling diagram illustrating an example of a method according to embodiments of this document.

[0033] Figure 8 This is a signaling diagram illustrating an example of a method according to embodiments of this document.

[0034] Figure 9 This is a schematic diagram illustrating an example of a method according to embodiments of this document.

[0035] Figure 10 This is a schematic block diagram illustrating two non-limiting examples a) and b) of the first node according to embodiments of this article.

[0036] Figure 11 This is a schematic block diagram illustrating two non-limiting examples a) and b) of the second node according to embodiments of this article.

[0037] Figure 12 This is a schematic block diagram illustrating a non-limiting example of a wireless communication network according to embodiments of this document. Detailed Implementation

[0038] Certain aspects of the present invention and embodiments thereof may provide solutions to the challenges discussed in the background section. Various embodiments are presented herein to address one or more of the problems disclosed herein.

[0039] In the AI ​​planning literature for multi-agent systems, there are general methods for collaborative plan synthesis and execution. The presence of multiple agents can be understood to increase the robustness of the SLAM estimation process due to information sharing across agents. Each agent can benefit from measurements taken by other agents. However, this complicates the implementation of SLAM in multi-agent systems. The SLAM-based work described in the background section may face challenges related to inefficient data management and the inability to effectively share information among agents. Generally, participating agents retain autonomy to run all navigation-critical tasks on-machine, while all computationally expensive data management tasks are pushed to a server. A central server with potentially greater computing power achieves their collaboration by collecting all their experience, merging and optimizing their maps, or relaying information back to them when appropriate. This often leads to information loss and communication delays during actual tasks. Therefore, scalability and robustness in SLAM implementations will also be challenging.

[0040] The embodiments described herein can be understood as addressing some of the challenges by leveraging opportunistic collaboration methods to tackle the challenges between autonomous agents.

[0041] In a general sense, the embodiments described herein can be understood as systems and methods for opportunistic collaboration among autonomous agents. More specifically, the embodiments herein can be understood as relating to a solution that establishes opportunistic collaboration among independent agents based on a knowledge base distributed among agents and their twins at the edge, through protocols for exchanging information, deriving new plans, and executing new plans.

[0042] The collaboration described herein can be understood as not pre-planned, as it may not be known a priori which agents might encounter which other agents and what capabilities those agents might possess. Therefore, dynamic and adaptive orchestration may exist in the embodiments described herein. Self-organizing compilation of knowledge about objects that agents might be able to handle and about their capabilities can be performed. Information exchange requirements may require knowledge about the network topology, which may be taken into account during planning and composition. Embodiments herein may involve new protocols for supporting the collection of new, demand-based knowledge items and their use in planning and composition. Furthermore, since collaboration can be understood as involving new cost elements, such as the ability to use other agents, these costs may be considered for new planning in the embodiments described herein.

[0043] Some of the embodiments under consideration will now be described more fully below with reference to the accompanying drawings (in which examples are shown). In this section, embodiments described herein will be illustrated in more detail by way of several exemplary embodiments. However, other embodiments are included within the scope of the subject matter disclosed herein. The disclosed subject matter should not be construed as being limited to the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. It should be noted that the exemplary embodiments herein are not mutually exclusive. It may be assumed by default that components from one embodiment exist in another embodiment, and how these components can be used in other exemplary embodiments will be apparent to those skilled in the art.

[0044] Note that although terms from LTE / 5G have been used in this invention to illustrate embodiments thereof, this should not be construed as limiting the scope of the embodiments herein to the systems described above. Other wireless systems with similar features may also benefit from utilizing the ideas covered by this invention.

[0045] Figure 1 A non-limiting example of a wireless communication network 100, sometimes referred to as a wireless communication system, cellular radio system, or cellular network, is depicted, in which embodiments of this document may be implemented. The wireless communication network 100 may typically be a 5G system, a 5G network, NR-U or a next-generation system or network, LAA, or MulteFire. Alternatively, the wireless communication network 100 may be a newer system than a 5G system. Wireless communication network 100 may support other technologies, such as, for example, Long Term Evolution (LTE), LTE-Advanced / LTE-Advanced Pro, such as LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), LTE Half-Duplex Frequency Division Duplex (HD-FDD), LTE operating in unlicensed frequency bands, Narrowband Internet of Things (NB-IoT), Wideband Code Division Multiple Access (WCDMA), Universal Terrestrial Radio Access (UTRA) TDD, Global System for Mobile Communications (GSM) network, GSM / Enhanced Data Rate GSM Evolution (EDGE) Radio Access Network (GERAN) network, Ultra Mobile Broadband (UMB), EDGE network, network composed of any combination of Radio Access Technologies (RATs) (such as, for example, Multi-Standard Radio (MSR) base stations, Multi-RAT base stations, etc.), any 3rd Generation Partnership Project (3GPP) cellular network, Wireless Local Area Network (WLAN) or WiFi network, Global Microwave Access Interoperability (WiMax) and / or any cellular network or system.

[0046] Therefore, although terms from 5G / NR and LTE may be used in this invention to illustrate the embodiments herein, this should not be construed as limiting the scope of the embodiments herein to the systems described above.

[0047] Wireless communication network 100 may include multiple nodes, wherein Figure 1 The non-limiting example depicts a first node 111 and one or more second nodes 120. One or more second nodes 120 may include a second node 121. Figure 1 In a particular non-restrictive example, one or more second nodes 120 may also include another second node 122 and yet another second node 123.

[0048] Any of the first node 111 and one or more second nodes 120 can be a wireless device with wireless capabilities, such as a 5G UE, i.e., capable of wireless communication within the wireless communication network 100. Communication can be performed, for example, via a RAN and one or more core networks that may be included within the wireless communication network 100. Any of the first node 111 and one or more second nodes 120 can be an intelligent autonomous system capable of autonomous transmission over the air within the wireless communication network 100, operating without human intervention. Any of the first node 111 and one or more second nodes 120 may also be referred to herein as an agent.

[0049] Any one of the first node 111 and one or more second nodes 120 may be able to transmit voice and / or data via the RAN to another entity, such as a server, laptop computer, personal digital assistant (PDA) or tablet computer, machine-to-machine (M2M) device, device equipped with a wireless interface, such as a printer or file storage device, modem, or any other radio network unit capable of communicating via a radio link in the communication system. Any one of the first node 111 and one or more second nodes 120 may itself have beamforming capabilities. In some examples, any one of the first node 111 and one or more second nodes 120 may be a distributed node, such as a virtual node in cloud 125, and may cooperate with radio network nodes to perform its functions fully or partially on cloud 125.

[0050] The first node 111 and any one of the one or more second nodes 120 can communicate with each other using, for example, IEEE 802.15.4-based low-power short-range networks (such as IPv6 (6LowPAN) on low-power wireless personal area networks), Zigbee, Z-Wave, Bluetooth Low Energy (BLE), and / or any cellular network or system. The first node 111 and any one of the one or more second nodes 120 can also perform communication via a set of protocols. This set of protocols may include protocols for radio-based communication and connectivity to cloud resources. The set of protocols may alternatively or additionally include protocols for LAN / PAN to discover and identify other nearby agents and exchange knowledge.

[0051] Wireless communication network 100 covers geospace 130. Any one of the first node 111 and one or more second nodes 120 can be an intelligent autonomous system capable of navigating geospace 130.

[0052] First node 111 can be configured to communicate with second node 121 in the wireless communication network 100 via a first link 141 (e.g., a radio link). First node 111 can be configured to communicate with another second node 122 in the wireless communication network 100 via a second link 142 (e.g., a radio link). First node 111 can be configured to communicate with another second node 123 in the wireless communication network 100 via a third link 143 (e.g., a radio link). Second node 121 can be configured to communicate with another second node 122 in the wireless communication network 100 via a fourth link 144 (e.g., a radio link). Another second node 112 can be configured to communicate with yet another second node 123 in the wireless communication network 100 via a fifth link 145 (e.g., a radio link).

[0053] To simplify the diagram, Figure 1 The link between the first node 111 and any one of the one or more second nodes 120 is not depicted, such as a radio link.

[0054] Figure 2 Another non-limiting example of a wireless communication network 100 in which embodiments of this invention may be implemented is depicted. For example... Figure 2As depicted, the wireless communication network 100 may also include one or more network nodes 110. Any one of the one or more network nodes 110 may be a radio network node or a radio base station, or any other network node with similar characteristics, capable of serving any one of the first node 111 and one or more second nodes 120, or any other user equipment, such as wireless devices or machine-type communication devices. Any one of the one or more network nodes 110 may typically be a transmission point (TP) or any other network element capable of serving any one of the first node 111 and one or more second nodes 120 in the wireless communication network 100. Any one of the one or more network nodes 110 may be, for example, a gNB, a 4G eNB, or a 5G eNB. Any one of the one or more network nodes 110 may belong to different categories based on transmission power and therefore also based on cell size, such as, for example, a macro base station (BS), a home BS, or a pico BS. For example, any one of the one or more network nodes 110 may belong to, for example, a wide-area base station, a mid-range base station, a local area base station, and a home base station based on transmission power and therefore also based on coverage area size. Any one of the one or more network nodes 110 can be a fixed relay node or a mobile relay node. Any one of the one or more network nodes 110 can support one or more communication technologies, and its name can depend on the technologies and terminology used. Any one of the one or more network nodes 110 can be directly connected to one or more networks and / or one or more core networks. Figure 2 The figures are not depicted for simplicity. Geospace 130 can be divided into cell areas, where each cell area can be served by a network node, but a single radio network node can serve one or more cells. Figure 2 In a specific, non-limiting example, the first node 111 and one or more second nodes 120 are in an area not covered by one or more network nodes 110, such as in a geographic space 130 in which the first node 111 and one or more second nodes 120 can perform operations at a remote location.

[0055] Generally, all terms used herein should be interpreted according to their ordinary meaning in the relevant art, unless explicitly given and / or implied from the context of their use. Unless explicitly stated otherwise, references to "a / an / element, device, component, apparatus, step, etc." are publicly interpreted as referring to at least one instance of the element, device, component, apparatus, step, etc. The steps of any method disclosed herein need not be performed in the exact order disclosed, unless a step is explicitly described as occurring after or before another step and / or implied that a step must occur after or before another step. Any feature of any embodiment disclosed herein may be applied to any other embodiment, where appropriate. Similarly, any advantage of any embodiment may be applied to any other embodiment, and vice versa. Other objects, features, and advantages of the appended embodiments will become apparent from the following description.

[0056] In general, the terms “first,” “second,” “third,” “fourth,” “fifth,” and / or “sixth” used in this document can be understood as referring to different elements or entities in any way, and unless otherwise indicated by the context, can be understood as not giving the nouns they modify a cumulative or chronological characteristic.

[0057] This document includes several embodiments. It should be noted that the examples herein are not mutually exclusive. It may be assumed by default that components from one embodiment exist in another embodiment, and it will be apparent to those skilled in the art how these components can be used in other exemplary embodiments.

[0058] Now refer to Figure 3 The flowchart depicted illustrates an embodiment of the method performed by the first node 111. This method can be understood as achieving a set of objectives in geospatial space 130. The first node 111 operates within a wireless communication network 100.

[0059] This method may include the actions described below. In some embodiments, some actions may be performed. In some embodiments, all actions may be performed. Figure 3 In this document, optional actions are indicated by dashed boxes. Where applicable, one or more embodiments may be combined. For simplicity, not all possible combinations are described. It should be noted that the examples herein are not mutually exclusive. It may be assumed by default that components from one example exist in another, and that it will be apparent to those skilled in the art how these components can be used in other examples.

[0060] Action 301

[0061] Each of the first node 111 and one or more second nodes 120 may have a task to be performed in geospace 130. A task can be understood herein as a goal or objective to be achieved in geospace 130. For example, a task could be “collecting low-resolution images in geospace 130”. The tasks of each of the first node 111 and one or more second nodes 120 may have been set by the corresponding operators of each of the first node 111 and one or more second nodes 120.

[0062] During operation in the wireless communication network 100, the first node 111 and one or more second nodes 120 can thus approach and / or discover that they are in geographic space 130. Any of the first node 111 and one or more second nodes 120 may be able to discover the presence of other nodes in geographic space 130 at the start of its mission.

[0063] The first node 111 and any one of the one or more second nodes 120 can thus discover one or more other nodes in their vicinity. Once they have discovered each other, the first node 111 and the one or more second nodes 120 can elect a leader using, for example, a distributed leader election protocol. For illustrative purposes, in the embodiments herein, the first node 111 may have already been elected as the leader.

[0064] Agent Knowledge Base

[0065] Each of the first node 111 and one or more second nodes 120 may include a database, also referred to herein as a knowledge base, which may include information supporting their operation in, for example, geospatial 130. Due to the need for self-organizing collaboration and the possibility of accessing uncovered areas, any of the first node 111 and one or more second nodes 120 may have to host a knowledge base. Services for providing network topology and coverage information may be hosted in cloud 125. Each of the first node 111 and one or more second nodes 120 may include one or more of the following in their respective knowledge base:

[0066] 1. The topology of geospatial 130, including the location of one or more network nodes 110, such as a relay base station that may be located nearby;

[0067] 2. Autonomous positioning and navigation capabilities;

[0068] 3. The address of the central server in Cloud125;

[0069] 4. A PDDL domain may be included that can execute action models of corresponding nodes, such as the first node 111 and one or more second nodes 120. An action model can be understood as a pair of <precondition, effect>. The precondition and effect can be understood as a set of logical predicates. An action can be understood as enabled in a state only if the precondition predicate is true in that state. When the action is executed, the effect predicate becomes true. In the context of this invention, for ease of describing the embodiments herein, the term capability (or multiple capabilities) is used to refer to one or more actions that a node can support. With respect to the first action, second action, third action, and fourth action described later, the lowercase term "action (or multiple actions)" can be used to refer to a specific supported action (or multiple actions) among all actions supported by the node, such as one performed by the node for a specific task. Examples of capabilities might be high-resolution and low-resolution cameras, soil quality detection, and / or nutrient spraying. In each of the one or more second nodes 120, the firmware can be understood as exposing a set of capabilities through an application programming interface (API). Each of the first node 111 and one or more second nodes 120 can maintain its corresponding capabilities based on <precondition, effect> pairs in the corresponding knowledge base. For example, actions could include capturing high-resolution images, measuring light intensity, capturing low-resolution images, enhancing images, processing images, etc. In some embodiments, actions can include at least one of the following: self-action, proxy action, jump action, and transfer action, such as, for example, replication. A self-action can be understood as an action performed autonomously by the corresponding second node. A proxy action can be understood as an action performed on other second nodes. A jump action can be understood as an action describing a mobility action that moves a specific node from one location to another. A transfer action can be understood as an action describing the transfer of information about an "artifact" from a source (e.g., one of the nodes or a central server) to a target (possibly another node or a central server). This action can free up storage space that the artifact in the source proxy might need. These actions can be modeled as <precondition, effect> pairs. Specifically, the action model can include:

[0070] a. (goto agent from to): describes the action of moving the agent from the location "from" to the location "to";

[0071] b. (transfer agent artifact target): Describes the action of transferring information about the "artifact" from the source (agent or central server) to the target;

[0072] c. (Copy agent artifact target): This can be understood as an action similar to transferring data without releasing its storage. This can be used to transfer the same knowledge to multiple target nodes.

[0073] d. Predicate (know agent artifact): A predicate that asserts the fact that the agent has acquired knowledge about the artifact. This knowledge can be acquired through direct actions (such as (take-image agent artifact)) or through exchange actions from other agents or a central server;

[0074] e. Since storage can be understood as having a limited number of artifacts, direct actions can be understood as having preconditions for availability; and

[0075] f. Cost of each action. Each action can be understood as having an associated cost. Cost can be understood as a function of real numbers appended to each action. This can be used to derive a plan with optimal cost or a plan within a certain cost range. The exact value of an action can be understood as depending on the domain and the operator's intent. For example, cost can be modeled in terms of energy consumption, financial costs, or the distance required to perform the action.

[0076] In a specific example, the corresponding knowledge base may include all the information listed above in project af.

[0077] After discovering each other, the first node 111 and any one of the one or more second nodes 120 can exchange their capabilities. Each of the first node and the one or more second nodes 120 may have already derived a plan, for example, using a corresponding planner, to complete a corresponding task in geospatial space. Each of the first node and the one or more second nodes 120 can analyze their corresponding plans to derive the needs with the desired effect, and the time limits that may be required to produce the effect. The time effect requirements can then be exchanged with other nodes.

[0078] Accordingly, in action 301, the first node 111 may obtain one or more corresponding first instructions from each of the one or more second nodes 120. Each of the one or more corresponding first instructions may instruct, for each of the one or more second nodes 120, respectively: a) a corresponding objective to be achieved in geospatial 130 based on a corresponding set of capabilities of each of the one or more second nodes 120, b) a corresponding set of capabilities, and c) a corresponding set of first actions to be performed individually by each of the one or more second nodes 120 to achieve the corresponding objective.

[0079] As previously mentioned, the objective, also known as the mission objective, can be understood in this paper as the objective to be achieved in geospace 130. The objective can be defined by a "know" predicate, which can specify reconnaissance knowledge about artifacts in geospace 130. For example, the objective can be expressed in PDDL as: (know Agent1 lowres-image1), (know Agent1 lowres-image2), (know Agent1 lowres-image3), and (know Agent1 lowres-image4).

[0080] The objective can be defined by a "task," which can be set by the corresponding operator of each of the one or more second nodes 120 and / or the first node 111. Each of the first node 111 and the one or more second nodes 120 can have a planner capable of generating a plan, given an initial state, i.e., a set of predicates representing the position, battery state, memory, etc., of the corresponding second node and / or first node 111 before initiating the task and encoding the topology, and the final state or "objective." It can be noted that while the objective may have to be achieved through a series of actions, the effect can be understood as being achieved through a single action. The plan can be understood as a series of actions that enable a particular node to achieve one or more objectives. The planner in each of the one or more second nodes 120 and / or the first node 111 can derive the plan using the corresponding PDDL domain of the action model. The plan can be understood as depending on the corresponding set of capabilities of the first node 111 and the one or more second nodes 120.

[0081] In some embodiments, each of one or more corresponding first instructions may be a file in Planning Domain Definition Language (PDDL) format, which may have been output by the corresponding planner in the corresponding second node. In other words, in action 301, one or more second nodes 120 may provide their PDDL domains and objectives to the first node 111, for example, as a leader agent.

[0082] The acquisition in action 301 can be achieved through a peer-to-peer or broadcast protocol, such as via one or more of the first link 141, the second link 142, and the third link 143.

[0083] Action 302

[0084] In action 302, the first node 111 determines a plan. This plan can be understood as providing a series of actions that can move one or more nodes (e.g., the first node 111 and one or more second nodes 120) from their current or initial state to a state that satisfies the task objective. Therefore, the plan can be viewed as the implementation of the task specification. In this case, the task is no longer the corresponding task of a specific individual node, but a global task compiled based on the individual tasks of the first node 111 and one or more second network nodes 120. Therefore, the first node 111 determines the plan based on: a first objective of the first node 111 to be achieved in geospatial 130 according to a first set of capabilities of the first node 111, and a first set of first actions to be performed individually by the first node 111 to achieve the first objective. For each of the one or more second nodes 120 within the radio coverage area of ​​the first node 111, the first node 111 further determines the plan based on: a) a corresponding objective to be achieved in geospatial 130 according to a corresponding set of capabilities of each of the one or more second nodes 120, and b) a corresponding set of first actions to be performed individually by each of the one or more second nodes 120 to achieve the corresponding objective. The plan is to collaboratively achieve each of the corresponding objectives in geospace 130 and each of the first objectives by determining a corresponding set of second actions to be performed by each of the one or more second nodes 120 and the first node 111, respectively. In other words, in action 302, the first node 111 can calculate the plan from a single objective constructed by the first node 111 by considering all the corresponding objectives from the one or more second nodes 120. The first node 111 can construct the single objective by taking the union of all the corresponding objectives of the first node 111 and the one or more second nodes 120.

[0085] Determination can be understood as calculation, derivation, selection, etc. The determination in action 302 can be performed, for example, using the planner in the first node 111. In the example presented here, the planner could be an off-the-shelf artificial intelligence (AI) planner, such as Metric-FF, which might require a Planning Domain Definition Language (PDDL) domain, a PDDL problem, and then a plan can be generated.

[0086] In some embodiments, each of the first node 111 and one or more second nodes 120 can be an intelligent autonomous system. The determination in action 302 can be triggered by mutual discovery between the first node 111 and at least one of the one or more second nodes 120. In some such embodiments, the determination in action 302 can then be based on the first node 111 being selected as the leader of one or more second nodes 120.

[0087] In some embodiments, the determined plan may be based on one or more corresponding first instructions obtained. It can be noted that the predicate “know,” the action “goto,” “copy,” and “transfer” may be common to all one or more second nodes 120 and first nodes 111. In some embodiments, each of the one or more corresponding first instructions may be a file in PDDL format, and the determination in action 302 of the plan may include constructing a single file in PDDL format that includes all the first actions.

[0088] For at least one of the one or more second nodes 120, or for the first node 111, a second action can be understood as an action different from the first action. A corresponding set of second actions may include actions for providing the desired effect to the other second nodes in the one or more second nodes 120. The second action may alternatively or additionally include skipping some actions in the corresponding set of first actions, and / or performing actions to exchange information, which may require moving to a rendezvous point or network coverage area.

[0089] In some embodiments, the determination in action 302 may be based on a first cost of the corresponding set of first actions and a second cost of the corresponding set of second actions. Since one or more second nodes 120 and / or any of the first nodes 111 may be able to provide their own actions to other nodes, each action may have two costs: <actual cost, selling cost>. The first node 111 can be understood as aiming to achieve the task objective while minimizing the task cost. The task cost can be calculated according to the plan, where actions may be annotated with bits: 0 for self-action and 1 for proxy action, and then the actual costs of all actions are added together and the selling cost of the proxy action is subtracted. There may be a limit that the selling cost may be >= the actual cost. That is, actions cannot be provided at a price lower than the actual cost.

[0090] First node 111 can decompose the plan of each of the first node 111 and one or more second nodes 120 by projecting each second action according to the parameters of first node 111 and each of the first node 111 and one or more second nodes 120. In other words, each action can be understood as having parameters that can represent the identifier of a node, such as "nodetid". When projecting for a particular node "N", the plan can be understood as a new plan that only has those actions with nodeid = N.

[0091] Action 303

[0092] In action 303, the first node 111 sends a corresponding instruction to each of the one or more second nodes 120, which can be considered a corresponding second instruction. This corresponding instruction can indicate a determined set of corresponding second actions. The corresponding instruction can be understood as a corresponding second instruction.

[0093] The corresponding instructions can be understood as a decomposition plan for the corresponding second node of one or more second nodes 120. The corresponding instructions can also indicate a new set of requirements. Thus, instead of the original sequence of actions, any one of the first node 111 and one or more second nodes 120 can perform new actions, for example, to provide the effects required by other nodes, and / or they can skip some older tasks whose effects may now be provided by other nodes.

[0094] In this action 310, transmission can be achieved, for example, via one or more of the first link 141, the second link 142, and the third link 143.

[0095] Action 304

[0096] While the first node 111 determines the plan in action 302, each of one or more second nodes 120 can also utilize its own domain and its own planner to compute its own local plan. Each of one or more second nodes 120 can incrementally and independently derive new plans on a best-effort basis and exchange information that they may be able to meet other requirements. In some examples, the best-effort basis might be deriving the plan at the lowest cost. However, this may not be the case. Deriving a plan can take time. Therefore, if the time budget is low, the derived plan may not correspond to the lowest-cost plan.

[0097] After each of the one or more second nodes 120 receives its corresponding second instruction, the second action in the set of second actions can be annotated as a self-action or a proxy action by examining its corresponding original objective and the corresponding first action in its plan. Each of the one or more second nodes 120 can calculate the total planned cost and compare it with the cost of its corresponding local plan. During this calculation, if an exchange action exists, new actions such as moving to a rendezvous point or coverage area of ​​the wireless communication network 100 can be included, and their costs can be taken into account. When there is an operation using the edge for exchange, a digital twin can be used to simulate peer-to-peer information exchange.

[0098] If the cost of the new plan is low, the corresponding second node in one or more second nodes 120 can send an agreement to the first node 111 (e.g., the leader). Otherwise, the corresponding second node in one or more second nodes 120 can send an disagreement.

[0099] Therefore, in action 304, the first node 111 may receive one or more corresponding third instructions from each of the one or more second nodes 120. Each of the one or more corresponding third instructions may respectively indicate to each of the one or more second nodes 120 that it agrees or disagrees to perform the corresponding set of second actions. In other words, each corresponding third instruction may include a response to the corresponding second instruction sent by the first node 111.

[0100] In this action 304, reception can be achieved, for example, via one or more of the first link 141, the second link 142, and the third link 143.

[0101] Action 305

[0102] If there is disagreement, the first node 111 can record only the agreeing second node, and then a new single PDDL field can be reconstructed from all actions from the agreeing second node.

[0103] Various possible alternatives may exist during the collaborative planning process.

[0104] According to the first alternative, the second node's dissent might only apply to a subset of the proxy actions. The first node 111 could then attempt to reschedule, taking this into account. This could result in proxy actions being assigned to different second node schedules. It's understandable that scheduling is always possible because initially, local schedules might achieve the local goals of each second node. Therefore, in the worst case, the first node 111 could produce a set of local schedules. (Later in...) Figure 7 The first alternative is explained in the text.

[0105] According to the second alternative, the first node 111 can partition task objectives and assign them to any one of one or more second nodes 120 that can locally synthesize the plan. They can then annotate these actions as self-actions or proxy actions by examining the dependencies between their original objectives and actions in the plan, calculate the total plan cost, and compare it with the cost of the local plan. If the cost of the new plan is lower, the second node can send an agreement to the first node 111. Otherwise, it can send a disagreement. Second nodes may disagree with the set of objectives assigned to them; in this case, a replanning can begin after the first node 111 may reallocate objectives to second nodes that agree, as later in... Figure 8 As shown in the image.

[0106] A particular node may disagree on executing a given plan or one or more corresponding second actions for various reasons. In some examples, it might be cost-related. In other examples, disagreement might be due to a node's predefined policies. For example, a node might be configured to perform action X only on behalf of others, but not action Y. Similar situations might apply to these objectives. Disagreements regarding actions and objectives can be understood as independent. A node might agree to an objective but disagree with a specific second action. A node might also agree to all second actions but disagree with a newly assigned objective.

[0107] As described above, in some embodiments, at least one of the corresponding third instructions may indicate disagreement with performing the corresponding set of second actions. In some of these embodiments, in action 305, the first node 111 may modify the determined plan based on the received one or more corresponding third instructions. The first node 111 may modify the determined plan by at least one of the following: i) excluding any one of the one or more second nodes 120 that has indicated disagreement with performing the corresponding set of second actions, and ii) assigning any of the second actions that one or more second nodes 120 has disagreed with to other second nodes of the one or more second nodes 120.

[0108] The modification in action 305 can be executed by the planner in a manner similar to the determination in action 302.

[0109] Action 306

[0110] In action 306, the first node 111 may send a corresponding fourth instruction to each of the one or more second nodes 120 that has already indicated agreement to perform at least one action in the corresponding set of second actions. The corresponding fourth instruction may indicate a corresponding set of third actions to be performed according to the modified plan.

[0111] Then, the agreeing second node can follow the new plan suggested by the first node (e.g., the leader). The disagreeing second node can follow its own plan.

[0112] In this action 406, transmission can be achieved, for example, via one or more of the first link 141, the second link 142, and the third link 143.

[0113] Action 307

[0114] During the execution of the method, dangers may arise, potentially requiring rescheduling. The execution unit in each of the first node 111 and any one of the one or more second nodes 120 can track planned execution and mark when preconditions for actions might not be met. For example, when a transfer / replication to a cloud service may be required, the plan could include a "goto" action for any one of the first node 111 and any one of the one or more second nodes 120 to move to a coverage point. However, because coverage status can change dynamically, execution may fail if the specified location is not covered. Planned actions may also fail due to a lack of capability in any of the first node 111 and any one of the one or more second nodes 120. For example, a camera on one of the nodes might malfunction, thus potentially preventing the execution of an agent action requiring image capture. When a transfer / replication to a cloud service might fail due to lack of coverage, one of the nodes can dynamically determine an alternative coverage point using topology knowledge, unless moving to the new point might take a significant amount of time.

[0115] The cloud service can transfer knowledge of artifacts to the target node. If the initial migration / replication to the cloud service fails, the target node can infer this from the cloud service's timeout and reschedule locally to acquire knowledge of the artifacts. If the migration / replication to another node may fail due to a capacity failure, that node can still move to the rendezvous point specified in the plan and notify the target node of the failure. The target agent can then reschedule locally to acquire knowledge of the artifacts in question. Any failure in the local action may subsequently trigger a local rescheduling.

[0116] As described above, in action 307, the first node 111 can receive at least one fifth instruction from any one of one or more second nodes 120. The fifth instruction can indicate the failure of either the execution plan or the modified plan.

[0117] In this action 307, reception can be achieved, for example, via one or more of the first link 141, the second link 142, and the third link 143.

[0118] Action 308

[0119] In this action 308, the first node 111 can modify either the determined plan or the modified plan according to the received fifth instruction.

[0120] Action 309

[0121] In action 309, the first node 111 may send a corresponding sixth instruction to each of the one or more second nodes 120 that has already indicated agreement to perform at least one of the corresponding set of second actions. The corresponding sixth instruction may instruct the execution of a corresponding set of fourth actions according to the modified original plan or the revised plan.

[0122] In summary, the embodiments described herein can be understood as relating to establishing opportunities for collaboration among multiple autonomous agents.

[0123] In this action 309, transmission can be achieved, for example, via one or more of the first link 141, the second link 142, and the third link 143.

[0124] Implementation of the collaborative plan

[0125] At the end of the collaborative plan synthesis phase, all first nodes 111 and one or more second nodes 120 can have corresponding plans, global plans, modified plans, or local plans, which may include self-actions, proxy actions, jumps, and transfer / copy actions. The execution module in each of the first nodes 111 and one or more second nodes 120 can ensure the orderly execution of the plan, with the following considerations:

[0126] 1. Self-action can be understood as a local action that can be performed independently of each of the first node 111 and one or more second nodes 120.

[0127] 2. The transfer / replication between the first node 111 and any of the one or more second nodes 120 can be understood as a joint action, for which the previous local action could be the action of jumping to a common location. It may be necessary for either the first node 111 or any of the one or more second nodes 120 to perform the jump action to go to the common location, wait for the participating nodes to arrive, transfer / replicate artifacts, and then send a completion signal to each other.

[0128] 3. Transfer / replication to the cloud service should only occur if the node is likely within the communication coverage area. If the agent may not be within the required coverage area, this plan can ensure this by issuing a redirect action to the agent.

[0129] 4. The PDDL domain can model strategic actions. The actual implementation of these high-level actions can be performed by low-level routines with further constraints, such as collision avoidance. For example, a PDDL action could instruct a node to "move AB," that is, move from point A to point B. This can be performed by software routines that drive the node's motors and navigation. While doing so, these routines can be interpreted as performing tactical maneuvers if there are obstacles in the path.

[0130] Now refer to Figure 4 The flowchart depicted illustrates an embodiment of the method performed by the second node 121. This method is used to achieve the set of objectives in geospatial space 130. The second node 121 can operate within a wireless communication network 100.

[0131] This method may include the following actions. Several embodiments are included herein. In some embodiments, some actions may be performed; in other embodiments, all actions may be performed. Where applicable, one or more embodiments may be combined. For simplicity, not all possible combinations are described. It should be noted that the examples herein are not mutually exclusive. It may be assumed by default that components from one example exist in another example, and it will be apparent to those skilled in the art how these components can be used in other examples. Figure 4 In the text, dashed boxes represent optional actions.

[0132] The specific implementations described below correspond to the same references provided above regarding the actions described for the first node 111, and will therefore not be repeated here for the sake of simplicity. For example, in some examples, each of the first node 111 and one or more second nodes 120 may be an intelligent autonomous system.

[0133] Action 401

[0134] In action 401, the second node 121 sends a corresponding first instruction to the first node 111 operating in the wireless communication network 100. The corresponding first instruction is used to indicate: a) a corresponding objective of the second node 121 to be achieved in geospatial 130 according to a corresponding set of capabilities of the second node 121, b) the corresponding set of capabilities of the second node 121, and c) a corresponding set of first actions to be performed by the second node 121 alone to achieve the corresponding objective.

[0135] The transmission in action 401 can be performed, for example, via the first link 141.

[0136] An action may include at least one of the following: self-action, proxy action, jump action, and transfer action.

[0137] Action 402

[0138] In action 402, the second node 121 receives a corresponding second instruction from the first node 111, namely its corresponding second instruction. The corresponding second instruction is used to indicate a set of second actions to be performed solely by the second node 121. Receiving the corresponding second instruction in action 402 is based on the transmitted corresponding first instruction. The received corresponding second instruction is based on a plan to be collaboratively implemented by the first node 111 and one or more second nodes 120 within the radio coverage area of ​​the first node 111: i) a first objective of the first node 111 to be achieved in geospatial 130 according to a first set of capabilities of the first node 111, and ii) a corresponding objective to be achieved in geospatial 130 by each of the one or more second nodes 120 according to its corresponding set of capabilities. This plan is based on a corresponding set of second actions to be performed by each of the one or more second nodes 120 and the first node 111, respectively.

[0139] The receiving in action 403 can be performed, for example, via the first link 141.

[0140] In some embodiments, the corresponding first instruction may be a file in PDDL format.

[0141] Each of the first node 111 and one or more second nodes 120 can be an intelligent autonomous system. In some embodiments of these embodiments, the reception in action 402 may be based on the first node 111 being selected as the leader of one or more second nodes 120.

[0142] Action 403

[0143] In action 403, the second node 121 can determine whether to agree or disagree to execute the corresponding set of second actions based on the corresponding first cost of the corresponding set of first actions and the corresponding second cost of the corresponding set of second actions, as described above regarding action 303.

[0144] Determining can be understood as, for example, calculating, estimating, or deriving.

[0145] As previously stated, the determination in action 403 can be achieved by considering the following: a) the cost of the corresponding set of second actions, and / or b) whether the proxy action or new target does not conform to the predefined strategy of the second node 121.

[0146] Action 404

[0147] In action 404, the second node 121 may send a corresponding third instruction to the first node 111. The corresponding third instruction may instruct the determined agreement or disagreement to perform the corresponding set of second actions, that is, based on the result of action 403.

[0148] The transmission in action 404 can be achieved, for example, via the first link 141.

[0149] Action 405

[0150] In action 405, the second node 121 may receive a corresponding fourth instruction from the first node 111. The corresponding fourth instruction may indicate a corresponding set of third actions to be performed according to a plan, the plan being modified based on at least one of the following: i) at least one of one or more second nodes 120 has indicated disagreement with performing the corresponding set of second actions, and ii) at least one of one or more second nodes 120 has disagreed with performing at least one of the corresponding set of second actions.

[0151] The receiving in action 405 can be performed, for example, via the first link 141.

[0152] Action 406

[0153] In action 406, the second node 121 may send a fifth instruction to the first node 111. The fifth instruction may indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions.

[0154] The transmission in action 406 can be performed, for example, via the first link 141.

[0155] Action 407

[0156] In action 407, the second node 121 can receive a corresponding sixth instruction from the first node 111. The corresponding sixth instruction can instruct a corresponding set of fourth actions to be performed according to the modified original plan or the revised plan.

[0157] The receiving in action 407 can be performed, for example, via the first link 141.

[0158] Action 408

[0159] As previously mentioned, in action 408, the second node 121 may perform one or more of the corresponding set of second actions, the corresponding set of third actions, and the corresponding set of fourth actions.

[0160] Figure 5This is a schematic diagram illustrating some aspects of collaboration between autonomous agents according to embodiments of this document. As can be understood from the diagram, there may be three main components in embodiments of this document: a) a knowledge base 501 in each of a first node 111 and one or more second nodes 120 (which may be referred to herein as intelligent autonomous agents, or simply agents, as described above), b) a cloud service 502 for serving network information, and c) a cloud service 503 for facilitating data exchange. Assume underlying network capabilities, wide area and personal area networks (WANs), such as Bluetooth or LAN, and access to the cloud 125. Each of the first node 111 and one or more second nodes 120 may include a planner, a PDDL domain, a set of protocols for performing communication, and a current state. The current state can be understood to include the node's location, available battery power, and memory. The set of protocols may include: 1) protocols for radio-based communication and connection to cloud resources, and / or 2) protocols for local area networks (LANs) / personal area networks (PANs) to discover and identify other nearby agents and exchange knowledge.

[0161] Figure 6This is an illustrative representation of the actions and messages exchanged between a first node 111 and one or more second nodes 120 (including second node 121 and another second node 122) according to an embodiment of this document, using a non-limiting example of a protocol for a collaborative planning synthesis process. In this particular non-limiting example, the method is triggered at 601 by the agent discovering one or more other agents in its vicinity. At 602, the agent elects the first node 111 as the leader using a distributed leader election protocol. At 603, according to action 301, the agent provides its PDDL domain and goal to the leader agent. At 604, the leader agent sets all agents as participating agents. At 605, the leader agent, in agreement with action 302, constructs a single PDDL domain from all actions of the agents. Note that the predicates "know", "goto", "copy", and "transfer" are common to all agents. At 605, the leader agent, also in agreement with action 302, constructs a single goal by obtaining the union of all goals (i.e., all local goals) from the agents. At 606, the leader agent further aligns with action 302 by using its planner to calculate the plan. Simultaneously, at 607, each agent also calculates its own local plan using its own domain. The leader agent decomposes each agent's plan by projecting each action according to the agent parameters. At 608, the leader agent aligns with action 303 by sending the decomposed plan to the corresponding agent in a corresponding second instruction. At 609, each agent annotates an action as either a self-action or an agent action by checking its original goal and the dependencies of actions in the plan. Each agent aligns with action 403 by calculating the total plan cost and comparing it to the cost of the local plan. If the cost of the new plan is lower, at 610, each agent aligns with action 404 by sending consent to the leader, which aligns with action 304 by receiving the consent. Otherwise, it sends disagreement, which can be aligned with action 304 by receiving the disagreement. If disagreement exists, at 611, aligning with action 305, the leader only records the consenting agents and repeats step 605. At point 612, the dissenting agents, exemplified by second node 121, follow their own plans. At point 613, the agreeing agents, exemplified by another second node 122, follow the new plan suggested by the leader.

[0162] Figure 7 This is a schematic diagram of a non-limiting example of a protocol used in a collaborative planning synthesis process when an agent refuses an agent action, according to embodiments of this document. Figure 7In this diagram, an activity graph represents the actions and messages that can be exchanged between a first node 111 and one or more second nodes 120 (including second node 121 and another second node 122). Consistent with action 302, the leader agent (here, the first node 111) constructs a single objective by obtaining the union of all objectives (i.e., all local objectives) from the agents. The leader agent then further calculates the plan using its planner, consistent with action 302, and sends a corresponding second instruction to each of the second nodes 121 and the other second node 122 according to action 303. Meanwhile, at 702, each of the second nodes 121 and the other second node 122 also calculates its own local plan using its own domain. Each agent calculates the total plan cost and compares it with the cost of its local plan. According to the first alternative discussed above, the second node's disagreement with the corresponding plan indicated by the first node 111 in action 303 may only apply to a subset of the proxy actions, which can be indicated by each of the second nodes 121 and 122 in the corresponding third instruction as an agreement state with capability constraints (i.e., with any predefined policy or policy specifying whether a node can agree or disagree to execute an action). The first node 111 then receives the corresponding third instruction in agreement with action 304. Then, in agreement with action 305, the first node 111 can take this into account and attempt to re-plan. The first node 111 can then restart from action 302. This can result in proxy actions being assigned to different second node plans. In agreement with action 306, the first node 111 signals to the agreeing proxy, here exemplified by the other second node 122, to follow the suggested new plan. At 706, the first node 111 signals to the completely disagreeing proxy, here exemplified by the second node 121, to follow their own plan.

[0163] Figure 8 This is a schematic diagram of a non-limiting example of a protocol for a collaborative plan synthesis process having target allocation and distributed plan synthesis, according to embodiments of this document. Figure 8In this context, an activity graph represents the actions and messages that can be exchanged between a first node 111 and one or more second nodes 120 (including second node 121 and another second node 122). Consistent with action 302, the leader agent (here, the first node 111) constructs a single objective by obtaining the union of all objectives (i.e., all local objectives) from the agents. The leader agent then further, consistent with action 302, uses its planner to partition and assign the task objective to any one of the one or more second nodes 120, and, consistent with action 303, sends a corresponding second instruction to each of the second nodes 121 and the other second node 122, instructing each of them to achieve the new objective. Meanwhile, at 803, each of the second nodes 121 and the other second node 122 also locally synthesizes its respective plan. At 804, each agent then annotates an action as a self-action or agent action by checking the dependencies of actions in its original objective and plan, calculates the total plan cost, and compares it with the cost of the local plan. If the cost of the new plan is lower, the second node 121 and another second node 122 can each send an agreement to the first node 111. The second nodes may disagree with the set of goals assigned to them, which can be indicated at 805 by each of the second nodes 121 and another second node 122 in a corresponding third instruction as an agreement state with goal constraints. The first node 111 then receives the corresponding third instruction in accordance with action 304. In this case, after the first node 111 can reallocate goals to the second nodes that agree based on the obtained goal constraints indicated by the second nodes 121 and another second node 122, it can begin replanning in accordance with action 305. The first node 111 can then restart from action 302. In accordance with action 306, the first node 111 signals to the agreeing agents, here another second node 122 for example, to follow the new plan as suggested. At 808, the first node 111 signals to the agents who completely disagree, here second node 121 for example, to follow their own plan.

[0164] Illustrative example

[0165] The embodiments described herein are not intended to illustrate a non-limiting illustrative example of establishing opportunistic collaboration between autonomous agents such as a first node 111, a second node 121, and another second node 122. For that example, [the following will be used]. Figure 9 The scene is illustrated in the diagram. Figure 9In this scenario, one or more network nodes 110 in the wireless communication network 100 include three base stations: BS1, BS2, and BS3, which are located around geographic area 130. The wireless communication network 100 also includes a first node 111 and one or more second nodes 120, including a second node 121 and another second node 122. Geographic space 130 is a large rectangular geographic area with many regions. In this non-limiting example, geographic space 130 is divided into four distinct regions: Region 1, Region 2, Region 3, and Region 4. For the purposes of this example, it is assumed that there is no coverage area within the large interior of geographic space 130. Each of the first node 111, the second node 121, and the other second node 122 is an agent, Agent 1, Agent 2, and Agent 3, respectively, from three different operators with the following capabilities and tasks.

[0166]

[0167] Agent 1 (i.e., the first node 111) may be able to accomplish its task by generating a plan that can cover the best routes in all regions, such as a solution to the traveling salesman problem, and by taking low-resolution photos of all regions.

[0168] The objective of Agent 1 can be expressed as:

[0169] (know Agent1 lowres-image1)

[0170] (know Agent1 lowres-image2)

[0171] (know Agent1 lowres-image3)

[0172] (know Agent1 lowres-image4)

[0173] The plan to achieve the goal is:

[0174] (goto Agent1 start zone1)[3]

[0175] (takeImage Agent1 lowres zone1 lowres-image1)[2]

[0176] (goto Agent1 zone1 zone2)[3]

[0177] (takeImage Agent1 lowres zone2 lowres-image2)[2]

[0178] (goto Agent1 start zone3)[3]

[0179] (takeImage Agent1 lowres zone3 lowres-image3)[2]

[0180] (goto Agent1 start zone4)[3]

[0181] (takeImage Agent1 lowres zone1 lowres-image4)[2]

[0182] The total cost of the plan is 4 × 5 = 20 arbitrary units, such as km, m, etc.

[0183] Agent 2 (i.e., the second node 121) may be able to accomplish its task by generating regional coverage paths, taking high-resolution photos of all regions, determining poor color maps through a classification (e.g., good or bad) model, and then collecting soil quality measurements from the regions with poor color maps.

[0184] The objective of Agent 2 can be expressed as:

[0185] (forall z:zones[implies(not(is-good(colormap z)))(know Agent2 z(soil-quality z))])

[0186] Agent 2 may achieve this goal through the following plan:

[0187] (goto Agent2 start zone1)[3]

[0188] (takeImage Agent2 highres zone1 highres-image1)[2]

[0189] (process Agent2 highres-image1 soil-quality)[2] / / produces a booleancondition B for soil-quality measurement

[0190] (measure-soil-quality Agent2 zone1)[2] / / conditional effect:if B istrue then take soil quality measurement of zone 1 else skip :

[0192] For regions 2, 3, and 4, the total cost of a similar plan is 4 × 9 = 36.

[0193] Agent 3 (i.e. another second node 122) can perform its tasks by generating regional coverage paths, collecting soil quality measurements, identifying areas with quality below a certain level, and spraying nutrients in these areas.

[0194] The objective of Agent 3 can be expressed as:

[0195] (forall z:zones[implies(not(is-good(soil-quality z)))(spray Agent2z)])

[0196] Agent 3 can achieve this goal through the following plan:

[0197] (goto Agent3 start zone1)[5]

[0198] (prepare Agent3 zone1 soil-quality)[2]

[0199] (measure-soil-quality Agent3 zone1)[2] :

[0201] / / The same applies to regions 2, 3, and 4 / /

[0202] (goto Agent3 zone4 start)[5]

[0203] The total cost is 4 × 9 + 5 = 41

[0204] In this example, assume the agent selects Agent 1 as its leader. Agent 1 gathers the capabilities and objectives of Agents 2 and 3 according to Action 301, and then constructs the merge domain and problem according to Action 302. The generation plan for agent decomposition might be:

[0205] Agent 1:

[0206] (goto Agent1 start zone1)

[10]

[0207] (takeImage Agent1 lowres zone1 lowres-image1)[4]

[0208] (goto Agent1 zone1 zone2)[5]

[0209] (takeImage Agent1 lowres zone2 lowres-image2)[4]

[0210] (goto Agent1 start zone3)[5]

[0211] (takeImage Agent1 lowres zone3 lowres-image3)[4]

[0212] (takeImage Agent1 highres zone3 lowres-image3)[-6]

[0213] (goto Agent1 start zone4)[5]

[0214] (takeImage Agent1 lowres zone1 lowres-image4)[4]

[0215] (takeImage Agent1 highres zone3 lowres-image3)[-6]

[0216] (goto Agent1 zone4 BS4)[5]

[0217] (transfer cloud highres-image3)[1]

[0218] (transfer cloud highres-image4)[1]

[0219] (goto Agent1 BS4 start)[5] / / returning to the start point

[0220] Original cost: 46, New cost: 41

[0221] Agent 2:

[0222] (goto Agent2 start zone1)

[10]

[0223] (takeImage Agent2 highres zone1 highres-image1)[4–6=-2]

[0224] (process Agent2 highres-image1 soil-quality)[2]

[0225] (measure-soil-quality Agent2 zone1soil-quality1)[4]

[0226] (goto Agent2 zone1 zone2)[5]

[0227] (takeImage Agent2 highres zone2 highres-image2)[4-6=-2]

[0228] (process Agent2 highres-image2 soil-quality)[2]

[0229] (measure-soil-quality Agent2 zone2 soil-quality2)[4]

[0230] (goto Agent2 zone2 BS2)[5]

[0231] (get Agent2 cloud highres-image3)[1]

[0232] (get Agent2 cloud highres-image4)[1]

[0233] (transfer Agent2 Agent3 soil-quality1)[1]

[0234] (transfer Agent2 Agent3 soil-quality2)[1]

[0235] (process Agent2 highres-image3 soil-quality)[2]

[0236] (goto Agent2 zone3)[5]

[0237] (measure-soil-quality Agent2 zone1)[4]

[0238] (process Agent2 highres-image4 soil-quality)[2]

[0239] (goto Agent2 zone4)[5]

[0240] (measure-soil-quality Agent2 zone4)[4]

[0241] (goto Agent2 zone4 start)[5]

[0242] Original cost: 70, new cost: 59. In fact, if the treated soil quality is good, moving to Region 3 and Region 4 can be completely avoided, thus saving even more costs.

[0243] Agent 2 can use the high-resolution images captured by Agent 1. Note that these are additional or proxy operations performed by Agent 1 for the collaboration plan. To obtain this information, Agents 1 and 2 must, for example, move to the coverage area asynchronously and exchange information via a cloud service. Agents may be understood as not needing to arrive at a point simultaneously. One agent can arrive at the coverage area and upload to Cloud 125, while another agent can travel to another coverage area at a different time to access artifacts from Cloud 125. However, this reduces the overall cost.

[0244] Agent 3:

[0245] (goto Agent3 start zone3)

[10]

[0246] (prepare Agent3 zone3 soil-quality)[2]

[0247] (measure-soil-quality Agent3 zone3 soil-quality3)[2]

[0248] (goto Agent3 zone3 zone4)[5]

[0249] (prepare Agent3 zone4 soil-quality)[2]

[0250] (measure-soil-quality Agent3 zone4 soil-quality4)[2]

[0251] (goto Agent3 zone4 BS2)[5]

[0252] (get Agent3 Agent2 soil-quality1)[1]

[0253] (get Agent3 Agent2 soil-quality2)[1]

[0254] (goto Agent3 BS2 start)[5]

[0255] Original cost: 41, New cost: 35

[0256] Agent 3 can reuse soil quality measurements from Agent 2. There are additional costs associated with movement and data transfer, such as when agents synchronously exchange information upon reaching a common point, but earlier movement and measurement costs are also saved.

[0257] Because the new costs are lower than the original costs, the agents agree to the new plans and execute them to achieve their respective task objectives at a lower cost.

[0258] To summarize the foregoing aspects, the embodiments described herein may involve the following elements: 1) knowledge of the capabilities of representing and reasoning about nearby agents; 2) exchanging required and provided timing predicates; 3) rescheduling using the required and provided timing predicates to help derive a plan with collaborative actions; 4) new action items in the plan to facilitate information exchange that may be needed due to task delegation to other agents; 5) using edge and network topology knowledge to optimize additional mobility that may be needed for information exchange; 6) adding new capabilities from the cloud to replicate / transmit information artifacts, overcome memory limitations, and reduce costs by facilitating information exchange; and 7) leveraging network and cloud features to optimize collaboration.

[0259] One advantage of the embodiments described in this paper is that intelligent autonomous agents may be able to opportunistically optimize their tasks by collaborating with nearby agents, thereby optimizing task costs. Task costs may include runtime and energy consumption. The edge can facilitate the execution of collaborative plans by providing logical aggregation points and ranges for mobility optimization. For example, one agent may be able to transfer knowledge at one node while another agent can acquire that knowledge at another node. The proposed collaboration method can establish robust communication, efficient data management, and effective information sharing among autonomous agents participating in the task.

[0260] Figure 10 Two different examples of arrangements that the first node 111 may include are depicted in panels a) and b), respectively. In some embodiments, the first node 111 may include... Figure 10The following arrangement is described in a). The first node 111 can be understood as being used to achieve this set of objectives in geospatial 130. The first node 111 can be configured to operate in wireless communication network 100.

[0261] This document includes several embodiments. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined where applicable. For simplicity, not all possible combinations have been described. It may be assumed by default that components from one embodiment exist in another embodiment, and it will be apparent to those skilled in the art how these components can be used in other exemplary embodiments. Figure 10 In the diagram, optional units are indicated by dashed boxes.

[0262] The following specific implementations correspond to the same references provided above regarding the actions described for the first node 111, and therefore will not be repeated here. For example, in some examples, each of the first node 111 and one or more second nodes 120 may be an intelligent autonomous system.

[0263] The first node 111 is configured to determine, for example, by a determining unit 1001 within the first node 111, action 302, which is configured to determine a plan based on: i) a first objective of the first node 111 to be achieved in geospace 130 according to a first set of capabilities of the first node 111, and a first set of first actions to be performed by the first node 111 alone to achieve the first objective; and ii) for each of one or more second nodes 120 within the radio coverage area of ​​the first node 111: a) a corresponding objective to be achieved in geospace 130 according to a corresponding set of capabilities of each of the one or more second nodes 120, and b) a corresponding set of first actions to be performed by each of the one or more second nodes 120 alone to achieve the corresponding objective. The plan is to collaboratively achieve each of the corresponding objective and the first objective in geospace 130 by determining a corresponding set of second actions to be performed by each of the one or more second nodes 120 and the first node 111, respectively.

[0264] The first node 111 is also configured to, for example, perform the transmission of action 303 via a transmission unit 1002 within the first node 111, which is configured to send a corresponding indication to each of the one or more second nodes 120. The corresponding indication is configured to indicate the corresponding set of second actions to be determined.

[0265] In some embodiments, a first cost that can be configured to be based on the corresponding set of first actions and a second cost that can be based on the corresponding set of second actions is determined.

[0266] The first node 111 can also be configured, for example, to perform the acquisition of action 301 via an acquisition unit 1003 within the first node 111, which is configured to acquire one or more corresponding first instructions from each of the one or more second nodes 120. Each of the one or more corresponding first instructions can be configured to indicate to each of the one or more second nodes 120: a) a corresponding objective, b) a corresponding set of capabilities, and c) a corresponding set of first actions. The plan to be determined can be configured to be based on the one or more corresponding first instructions to be acquired.

[0267] In some embodiments, each of one or more corresponding first instructions may be a file in PDDL format, and the program is configured to include building a single file in PDDL format that includes all the first actions.

[0268] In some embodiments, the corresponding indication may be a corresponding second indication. In some such embodiments, the first node 111 may also be configured to receive action 304, for example, via a receiving unit 1004 within the first node 111, which is configured to receive one or more corresponding third indications from each of the one or more second nodes 120. Each of the one or more corresponding third indications may be configured to indicate to each of the one or more second nodes 120 that agrees or disagrees to perform the corresponding set of second actions.

[0269] In some embodiments, at least one of the corresponding third instructions may be configured to indicate disagreement with performing the corresponding set of second actions. In some such embodiments, the first node 111 may also be configured to modify action 305, for example, through a modification unit 1005 within the first node 111, which is configured to modify the plan to be determined according to one or more corresponding third instructions configured to be received. The modification may be configured to be performed by at least one of the following: i) excluding any one of the one or more second nodes 120 that has indicated disagreement with performing the corresponding set of second actions, and ii) assigning the second actions that any one of the one or more second nodes 120 has disagreed with performing to other second nodes of the one or more second nodes 120.

[0270] In some embodiments, the first node 111 may also be configured to, for example, perform the transmission of action 306 via a transmission unit 1002 within the first node 111, which is configured to send a corresponding fourth instruction to each of the one or more second nodes 120 that has indicated agreement to perform at least one of the corresponding set of second actions. The corresponding fourth instruction may be configured to indicate a corresponding set of third actions to be performed according to a modified plan.

[0271] In some embodiments, the first node 111 may also be configured to receive action 307, for example, via a receiving unit 1004 within the first node 111, which is configured to receive at least one fifth indication from any one of one or more second nodes 120. The fifth indication may be configured to indicate a failure in either the execution plan or the modified plan.

[0272] In some embodiments, the first node 111 may also be configured to perform a modification of action 308, for example, by a modification unit 1005 within the first node 111, which is configured to modify either the determined plan or the modified plan according to a fifth instruction configured to be received.

[0273] In some embodiments, the first node 111 may also be configured to, for example, send action 309 via a sending unit 1002 within the first node 111, which is configured to send a corresponding sixth instruction to each of the one or more second nodes 120 that has indicated agreement to perform at least one of the corresponding set of second actions. The corresponding sixth instruction may be configured to indicate a corresponding set of fourth actions to be performed according to a modified original or revised plan.

[0274] In some embodiments, each of the first node 111 and one or more second nodes 120 can be configured as an intelligent autonomous system, and can be configured to be based on the first node 111 being selected as the leader of one or more second nodes 120.

[0275] In some embodiments, an action may be configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

[0276] The embodiments in the first node 111 of this document can be used by one or more processors (such as...) Figure 10 The processor 1006 in the first node 111 described in a) is implemented together with computer program code for performing the functions and actions of the embodiments herein. As used herein, a processor can be understood as a hardware component. The program code described above can also be provided as a computer program product, for example in the form of a data carrier carrying the computer program code, for executing the embodiments herein when loaded into the first node 111. One such carrier can be in the form of a CD-ROM. However, it is also feasible for other data carriers such as a memory stick. The computer program code can also be provided as plain program code on a server and downloaded to the first node 111.

[0277] The first node 111 may also include a memory 1007, which includes one or more memory cells. The memory 1007 is arranged to store acquired information, stored data, configurations, scheduling, and applications, etc., when executed in the first node 111, for performing the methods described herein.

[0278] In some embodiments, the first node 111 can receive information via the receive port 1008 from, for example, a second node 121, another second node 122, another second node 123, any other node among one or more second nodes 120, any one or more network nodes 110, and / or any node in the cloud 125. In some embodiments, the receive port 1008 may be connected, for example, to one or more antennas in the first node 111. In other embodiments, the first node 111 can receive information via the receive port 1008 from another structure in the wireless communication network 100. Since the receive port 1008 can communicate with the processor 1006, the receive port 1008 can then send the received information to the processor 1006. The receive port 1008 can also be configured to receive other information.

[0279] The processor 1006 in the first node 111 can also be configured to transmit or send information via a transmit port 1009 that can communicate with the processor 1006 and the memory 1007 to, for example, a second node 121, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one of one or more network nodes 110, any node in the cloud 125, and / or another structure in the wireless communication network 100.

[0280] Those skilled in the art will also understand that the aforementioned units 1001-1005 may refer to a combination of analog and digital circuitry, and / or one or more processors configured with software and / or firmware (e.g., stored in memory), which, when executed by one or more processors such as processor 1006, perform as described above. One or more of these processors, along with other digital hardware, may be included in a single application-specific integrated circuit (ASIC), or multiple processors and various digital hardware may be distributed across several separate components, either individually packaged or assembled into a system-on-a-chip (SoC).

[0281] Furthermore, in some embodiments, the different units 1001-1005 described above can be implemented as one or more applications running on one or more processors, such as processor 1006.

[0282] Therefore, the method according to the embodiments for the first node 111 described herein can be implemented by a computer program product 1010, which includes instructions, i.e., software code portions, that, when executed on at least one processor 1006, cause at least one processor 1006 to perform the actions described herein as performed by the first node 111. The computer program product 1010 may be stored on a computer-readable storage medium 1011. The computer-readable storage medium 1011 on which the computer program 1010 is stored may include instructions that, when executed on at least one processor 1006, cause at least one processor 1006 to perform the actions described herein as performed by the first node 111. In some embodiments, the computer-readable storage medium 1011 may be a non-transitory computer-readable storage medium, such as a CD-ROM or Memory Stick. In other embodiments, the computer program product 1010 may be stored on a carrier containing the computer program 1010 just described, wherein the carrier is one of an electronic signal, an optical signal, a radio signal, or the computer-readable storage medium 1011, as described above.

[0283] The first node 111 may include a communication interface or interface unit configured to facilitate communication between the first node 111 and other nodes or devices (e.g., second node 121, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one of one or more network nodes 110, any node in the cloud 125, and / or another structure). For example, the interface may include a transceiver configured to transmit and receive radio signals over an air interface according to a suitable standard.

[0284] In other embodiments, the first node 111 may include Figure 10 The following arrangement is depicted in b). The first node 111 may include processing circuitry 1006, such as one or more processors (e.g., processor 1006) and memory 1007 within the first node 111. The first node 111 may also include radio circuitry 1012, which may include, for example, a receive port 1008 and a transmit port 1009. The processing circuitry 1006 may be configured or operable to communicate with... Figure 10 The method described in a) is similar to the one described above. Figure 3 and / or Figures 5 to 9 The method of operation. Radio circuit 1012 can be configured to establish and maintain wireless connections with at least the second node 121, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one of one or more network nodes 110, and / or any node in cloud 125. The circuit can be understood herein as a hardware component.

[0285] Therefore, embodiments herein also relate to a first node 111 for operation in a wireless communication network 100. The first node 111 may include processing circuitry 1006 and a memory 1007 containing instructions executable by the processing circuitry 1006, thereby allowing the first node 111 to further operate to perform, for example, the operations described herein in… Figure 3 and / or Figures 5 to 9 The action described in the first node 111.

[0286] Figure 11 Two different examples of arrangements that the second node 121 may include are depicted in panels a) and b), respectively. In some embodiments, the second node 121 may include... Figure 11 The following arrangement is depicted in a). The second node 121 can be understood as being used to achieve this set of objectives in geospatial 130. The second node 121 is configured to operate in wireless communication network 100.

[0287] This document includes several embodiments. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined where applicable. For simplicity, not all possible combinations have been described. It may be assumed by default that components from one embodiment exist in another embodiment, and it will be apparent to those skilled in the art how these components can be used in other exemplary embodiments. Figure 11 In the diagram, optional units are indicated by dashed boxes.

[0288] The following specific implementations correspond to the same references provided above regarding the actions described for the second node 121, and therefore will not be repeated here. For example, in some examples, each of the first node 111 and one or more second nodes 120 may be an intelligent autonomous system.

[0289] The second node 121 is configured to, for example, perform the transmission of action 401 via a transmission unit 1101 within the second node 121, which transmits a corresponding first instruction to the first node 111 configured to operate in the wireless communication network 100. The corresponding first instruction is configured to indicate: a) a corresponding objective of the second node 121 to be achieved in geospatial 130 based on a corresponding set of capabilities of the second node 121, b) the corresponding set of capabilities of the second node 121, and c) a corresponding set of first actions to be performed solely by the second node 121 to achieve the corresponding objective.

[0290] The second node 121 is configured to receive action 402, for example, via a receiving unit 1102 within the second node 121, which is configured to receive a corresponding second instruction from the first node 111. The corresponding second instruction is configured to indicate the set of second actions to be performed solely by the second node 121. Receiving the corresponding second instruction is configured based on a corresponding first instruction configured to be transmitted. The corresponding second instruction configured to be received is configured based on a plan to be collaboratively implemented by the first node 111 and one or more second nodes 120 within the radio coverage area of ​​the first node 111: i) a first objective of the first node 111 to be achieved in geospatial 130 according to a first set of capabilities of the first node 111, and ii) a corresponding objective to be achieved in geospatial 130 by each of the one or more second nodes 120 according to a corresponding set of capabilities of that second node. The plan is configured based on a corresponding set of second actions to be performed by each of the one or more second nodes 120 and the first node 111, respectively.

[0291] In some embodiments, the corresponding first instruction can be configured as a file in PDDL format.

[0292] In some embodiments, the second node 121 may also be configured to, for example, perform the determination of action 403 by a determination unit 1103 within the second node 121, which determines whether to agree or disagree to perform the corresponding set of second actions based on a corresponding first cost of the corresponding set of first actions and a corresponding second cost of the corresponding set of second actions.

[0293] In some embodiments, the second node 121 may also be configured to, for example, send action 404 via a sending unit 1101 within the second node 121, which is configured to send a corresponding third indication to the first node 111. The corresponding third indication may be configured to indicate agreement or disagreement to perform the corresponding set of second actions configured to be determined.

[0294] In some embodiments, the second node 121 may also be configured to receive action 405, for example, via a receiving unit 1102 within the second node 121, which is configured to receive a corresponding fourth instruction from the first node 111. The corresponding fourth instruction may be configured to indicate a corresponding set of third actions to be performed according to a plan. This plan may be configured to be modified based on at least one of the following: i) at least one of one or more second nodes 120 has indicated disagreement with performing the corresponding set of second actions, and ii) at least one of one or more second nodes 120 has disagreed with performing at least one of the corresponding set of second actions.

[0295] In some embodiments, the second node 121 may also be configured to, for example, perform the transmission of action 406 via a transmission unit 1101 within the second node 121, which is configured to send a fifth indication to the first node 111. The fifth indication may be configured to indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions.

[0296] In some embodiments, the second node 121 may also be configured to receive action 407, for example, via a receiving unit 1102 within the second node 121, which is configured to receive a corresponding sixth instruction from the first node 111. The corresponding sixth instruction may be configured to indicate a corresponding set of fourth actions to be performed according to a modified original or revised plan.

[0297] In some embodiments, the second node 121 may also be configured to execute action 408, for example, through an execution unit 1104 within the second node 121, which is configured to execute one or more of a corresponding set of second actions, a corresponding set of third actions, and a corresponding set of fourth actions.

[0298] In some embodiments, each of the first node 111 and one or more second nodes 120 can be configured as an intelligent autonomous system. In some such embodiments, receiving a corresponding second instruction can be configured based on the first node 111 being selected as the leader of one or more second nodes 120.

[0299] In some embodiments, the action may also be configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

[0300] The embodiments in node 121 of this document can be used by one or more processors (such as...) Figure 11 The processor 1105) in the second node 121 described in a) is implemented together with computer program code for performing the functions and actions of the embodiments herein. As used herein, a processor can be understood as a hardware component. The program code described above can also be provided as a computer program product, for example in the form of a data carrier carrying the computer program code, for executing the embodiments herein when loaded into the second node 121. One such carrier can be in the form of a CD-ROM. However, it is also feasible for other data carriers such as a memory stick. The computer program code can also be provided as plain program code on a server and downloaded to the second node 121.

[0301] The second node 121 may also include a memory 1106, which includes one or more memory cells. The memory 1106 is arranged to store acquired information, stored data, configurations, scheduling, and applications, etc., when executed in the second node 121, for performing the methods described herein.

[0302] In some embodiments, the second node 121 can receive information via the receive port 1107 from, for example, the first node 111, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one or more network nodes 110, and / or any node in the cloud 125. In some embodiments, the receive port 1107 can be connected, for example, to one or more antennas in the second node 121. In other embodiments, the second node 121 can receive information via the receive port 1107 from another structure in the wireless communication network 100. Since the receive port 1107 can communicate with the processor 1105, the receive port 1107 can send the received information to the processor 1105. The receive port 1107 can also be configured to receive other information.

[0303] The processor 1105 in the second node 121 can also be configured to transmit or send information via a transmit port 1108 that can communicate with the processor 1105 and the memory 1106 to, for example, the first node 111, another second node 122, yet another second node 123, any other node in one or more second nodes 120, any node in one or more network nodes 110, any node in the cloud 125, and / or another structure in the wireless communication network 100.

[0304] Those skilled in the art will also understand that the aforementioned units 1101-1104 may refer to a combination of analog and digital circuitry, and / or one or more processors configured with software and / or firmware, which are stored, for example, in memory, and executed as described above when executed by one or more processors, such as processor 1105. One or more of these processors, along with other digital hardware, may be included in a single application-specific integrated circuit (ASIC), or multiple processors and various digital hardware may be distributed across several separate components, either individually packaged or assembled into a system-on-a-chip (SoC).

[0305] Furthermore, in some embodiments, the different units 1101-1104 described above can be implemented as one or more applications running on one or more processors, such as processor 1105.

[0306] Therefore, the method according to the embodiments for the second node 121 described herein can be implemented by a computer program product 1109, which includes instructions, i.e., software code portions, that, when executed on at least one processor 1105, cause at least one processor 1105 to perform the actions described herein as performed by the second node 121. The computer program product 1109 may be stored on a computer-readable storage medium 1110. The computer-readable storage medium 1110 on which the computer program 1109 is stored may include instructions that, when executed on at least one processor 1105, cause at least one processor 1105 to perform the actions described herein as performed by the second node 121. In some embodiments, the computer-readable storage medium 1110 may be a non-transitory computer-readable storage medium, such as a CD-ROM or Memory Stick. In other embodiments, the computer program product 1109 may be stored on a carrier containing the computer program 1109 just described, wherein the carrier is one of electronic signals, optical signals, radio signals, or the computer-readable storage medium 1110, as described above.

[0307] The second node 121 may include a communication interface or interface unit configured to facilitate communication between the second node 121 and other nodes or devices (e.g., the first node 111, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one of one or more network nodes 110, any node in the cloud 125, and / or another structure in the wireless communication network 100). For example, the interface may include a transceiver configured to transmit and receive radio signals over an air interface according to a suitable standard.

[0308] In other embodiments, the second node 121 may include Figure 11 The following arrangement is depicted in b). The second node 121 may include processing circuitry 1105, such as one or more processors, like processor 1105, in the second node 121 and memory 1106. The second node 121 may also include radio circuitry 1111, which may include, for example, a receive port 1107 and a transmit port 1108. Processing circuitry 1105 may be configured or operable to communicate with... Figure 11 The method described in a) is similar to the one described above. Figure 4 and / or Figures 5 to 9The method of operation. Radio circuit 1111 can be configured to establish and maintain wireless connections with at least a first node 111, another second node 122, yet another second node 123, any other node among one or more second nodes 120, any one of one or more network nodes 110, any node in cloud 125, and / or another structure. The circuit can be understood herein as a hardware component.

[0309] Therefore, embodiments herein also relate to a second node 121 for operation in a wireless communication network 100. The second node 121 may include processing circuitry 1105 and a memory 1106 containing instructions executable by the processing circuitry 1105, thereby allowing the second node 121 to further operate to perform, for example, the operations described herein in… Figure 4 and / or Figures 5 to 9 The action described in the second node 121.

[0310] Figure 12An example of the arrangement that a wireless communication network 100 may include is depicted. In embodiments herein, the wireless communication network 100 is configured to enable communication between a first node 111 and one or more second nodes 120, including a second node 121, to achieve a set of objectives in geospatial 130. In such embodiments, the second node 121 is configured to send a corresponding first instruction to the first node 111. The corresponding first instruction is configured to instruct: i) a corresponding objective of the second node 121 to be achieved in geospatial 130 based on a corresponding set of capabilities of the second node 121, ii) a corresponding set of capabilities of the second node 121, and iii) a corresponding set of first actions to be performed solely by the second node 121 to achieve the corresponding objective. In this type of embodiment, the first node 111 is configured to determine a plan based on: i) a first objective of the first node 111 to be achieved in geospatial 130 according to a first set of capabilities of the first node 111, and a first set of first actions to be performed by the first node 111 alone to achieve the first objective; and ii) for each of the one or more second nodes 120 within the radio coverage area of ​​the first node 111: a) a corresponding objective to be achieved in geospatial 130 according to the corresponding set of capabilities of each of the one or more second nodes 120, and b) the corresponding set of first actions to be performed by each of the one or more second nodes 120 alone to achieve the corresponding objective. The plan is to collaboratively achieve each of the corresponding objectives and the first objective in geospatial 130 by determining a corresponding set of second actions to be performed by each of the one or more second nodes 120 and the first node 111, respectively. The first node 111 is also configured to send a corresponding instruction to each of the one or more second nodes 120. The corresponding instruction is configured to instruct the corresponding set of second actions to be determined. In this type of embodiment, the second node 121 is also configured to receive a corresponding second instruction from the first node 111. The corresponding second instruction is configured to instruct the second action of the set to be performed solely by the second node 121.

[0311] In some embodiments of the wireless communication network 100, the first node 111 may also be configured to be determined based on a first cost of the corresponding set of first actions and a second cost of the corresponding set of second actions.

[0312] In some embodiments of the wireless communication network 100, the first node 111 may also be configured to obtain one or more corresponding first indications from each of the one or more second nodes 120, each of the one or more corresponding first indications being configured to indicate to each of the one or more second nodes 120: a) a corresponding target, b) a corresponding set of capabilities, and c) a corresponding set of first actions. In such embodiments, the plan to be determined may be configured to be based on the one or more corresponding first indications to be obtained.

[0313] In some embodiments of the wireless communication network 100, each of one or more corresponding first instructions may be a file in PDDL format, and it is determined that the program can be configured to include constructing a single file in PDDL format that includes all the first actions.

[0314] In some embodiments of the wireless communication network 100, the corresponding indication may be a corresponding second indication, and the first node 111 may also be configured to receive one or more corresponding third indications from each of the one or more second nodes 120. Each of the one or more corresponding third indications may be configured to indicate to each of the one or more second nodes 120 that it agrees or disagrees to perform a corresponding set of second actions.

[0315] In some embodiments of the wireless communication network 100, at least one of the corresponding third indications may be configured to indicate disagreement with performing the corresponding set of second actions, and the first node 111 may also be configured to modify the plan to be determined based on one or more corresponding third indications configured to be received. This may be configured to be performed by at least one of the following: i) excluding any one of the one or more second nodes 120 that has indicated disagreement with performing the corresponding set of second actions, and ii) assigning the second action that any one of the one or more second nodes 120 has disagreed with to the other second nodes of the one or more second nodes 120. The first node 111 may also be configured to send a corresponding fourth indication to each of the one or more second nodes 120 that has indicated agreement to perform at least one of the second actions in the corresponding set of second actions. The corresponding fourth indication may be configured to indicate the corresponding set of third actions to be performed according to the modified plan.

[0316] In some embodiments of the wireless communication network 100, the first node 111 may also be configured to receive at least one fifth indication from any one of one or more second nodes 120. The fifth indication may be configured to indicate a failure in the execution of either the original plan or a modified plan. The first node 111 may also be configured to modify either the original plan or the modified plan based on the fifth indication configured to be received. The first node 111 may also be configured to send a corresponding sixth indication to each of the one or more second nodes 120 that has indicated agreement to perform at least one of the corresponding set of second actions. The corresponding sixth indication may be configured to indicate a corresponding set of fourth actions to be performed according to the modified original plan or the revised plan.

[0317] In some embodiments of the wireless communication network 100, each of the first node 111 and one or more second nodes 120 can be configured as an intelligent autonomous system. In such embodiments, determination can be configured based on the first node 111 being selected as the leader of one or more second nodes 120.

[0318] In some embodiments of the wireless communication network 100, the action can be configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

[0319] In some embodiments of the wireless communication network 100, the second node 121 may also be configured to determine whether to agree or disagree to perform a corresponding set of second actions based on a corresponding first cost of a corresponding set of first actions and a corresponding second cost of a corresponding set of second actions. The second node 121 may also be configured to send a corresponding third indication to the first node 111. The corresponding third indication may be configured to indicate agreement or disagreement to perform a corresponding set of second actions configured to be determined.

[0320] In some embodiments of the wireless communication network 100, the second node 121 may also be configured to receive a corresponding fourth instruction from the first node 111. The corresponding fourth instruction may be configured to indicate a corresponding set of third actions to be performed according to a plan, the plan being configured to be modified based on at least one of the following: i) at least one of one or more second nodes 120 has indicated disagreement with performing the corresponding set of second actions, and ii) at least one of one or more second nodes 120 has disagreed with performing at least one of the corresponding set of second actions.

[0321] In some embodiments of the wireless communication network 100, the second node 121 may also be configured to send a fifth indication to the first node 111. The fifth indication may be configured to indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions. The second node 121 may also be configured to receive a corresponding sixth indication from the first node 111. The corresponding sixth indication may be configured to indicate a corresponding set of fourth actions to be performed according to a modified original plan or a revised plan.

[0322] In some embodiments of the wireless communication network 100, the second node 121 may also be configured to perform one or more of a corresponding set of second actions, a corresponding set of third actions, and a corresponding set of fourth actions.

[0323] When the word “includes” is used, it should be interpreted as non-restrictive, meaning “consisting of at least…”.

[0324] The embodiments described herein are not limited to the preferred embodiments described above. Various alternatives, modifications, and equivalents may be used. Therefore, the above embodiments should not be considered as limiting the scope of the invention.

[0325] Generally, all terms used herein should be interpreted according to their ordinary meaning in the relevant art, unless explicitly given and / or implied from the context of their use. Unless explicitly stated otherwise, references to "a / an / element, device, component, apparatus, step, etc." are publicly interpreted as referring to at least one instance of the element, device, component, apparatus, step, etc. The steps of any method disclosed herein need not be performed in the exact order disclosed, unless a step is explicitly described as occurring after or before another step and / or implied that a step must occur after or before another step. Any feature of any embodiment disclosed herein may be applied to any other embodiment, where appropriate. Similarly, any advantage of any embodiment may be applied to any other embodiment, and vice versa. Other objects, features, and advantages of the appended embodiments will become apparent from the following description.

[0326] As used herein, the expression “at least one:” followed by a comma-separated list of alternatives, with the last alternative preceding the term “and”, can be understood to indicate that only one of the alternatives may apply, more than one alternative may apply, or all of the alternatives may apply. This expression can be understood to be equivalent to the expression “at least one:” followed by a comma-separated list of alternatives, with the last alternative preceding the term “or”.

[0327] The terms processor and circuit can be understood as hardware components in this document.

[0328] As used herein, the phrase "in some embodiments" has been used to indicate that features of the described embodiments may be combined with any other embodiments or examples disclosed herein.

[0329] As used herein, the phrase "in some examples" has been used to indicate that the features of the described examples can be combined with any other embodiments or examples disclosed herein.

[0330] References

[0331] 1.Nesrine Mahdoui, Vincent Frémont, Enrico Natalizio, "CooperativeFrontier-Based Exploration Strategy for Multi-Robot System", System of Systems Engineering (SoSE) 2018 13th Annual Conference on, pp. 203-210, 2018.

[0332] 2.Xieyuanli Chen, Huhuimin Lu, Junhao Xiao, Hui Zhang, "DistributedMonocular Multi-Robot SLAM", CYBER Technology in Automation Control and Intelligent Systems (CYBER) 2018 IEEE 8th Annual International Conference on, pages 73-78, 2018.

[0333] 3. Patrik Schmuck and Margarita Chli, “Multi-UAV collaborative monocularSLAM”, 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017.

[0334] 4. André Silva, Ricardo and Pedro Santana, "Monocular Trail Detection and Tracking Aided by Visual SLAM for Small Unmanned Aerial Vehicles", Journal of Intelligent and Robotic Systems, June 2018.

Claims

1. A method performed by a first node (111) for achieving a set of objectives in geospatial space (130), the first node (111) operating in a wireless communication network (100), the method comprising: - The (302) plan will be determined based on the following: i. The first objective of the first node (111) to be achieved in the geospace (130) according to the first set of capabilities of the first node (111); and the first set of first actions determined by the first node to be performed independently by the first node (111) to achieve the first objective, and ii. For each of one or more second nodes (120) within the radio coverage area of ​​the first node (111): a) The corresponding objectives to be achieved in the geospace (130) based on the corresponding set of capabilities of each of the one or more second nodes (120), and b) A set of first actions, determined by each of the one or more second nodes (120), to achieve the corresponding objective, to be executed individually by each second node. The plan is to collaboratively achieve the first objective and each of the corresponding objectives in the geospatial space (130) by determining a corresponding set of second actions to be performed by each of the first node (111) and the one or more second nodes (120), wherein the corresponding set of second actions is determined based on both the first set of first actions determined by the first node and the corresponding set of first actions determined by each second node, and - Send (303) a corresponding instruction to each of the one or more second nodes (120), the corresponding instruction being used to indicate a corresponding set of second actions determined.

2. The method according to claim 1, wherein the determination (302) is based on a first cost of a first action of a corresponding group and a second cost of a second action of a corresponding group.

3. The method according to any one of claims 1 to 2, further comprising: - Obtain (301) one or more corresponding first indications from each of the one or more second nodes (120), each of the one or more corresponding first indications indicating the following for each of the one or more second nodes (120): a) The corresponding objective mentioned above b) the corresponding set of capabilities, and c) The corresponding set of first actions. Furthermore, the plan determined therein is based on one or more corresponding first instructions obtained.

4. The method of claim 3, wherein each of the one or more corresponding first instructions is a file in a Planning Domain Definition Language (PDDL) format, and wherein determining (302) the plan comprises constructing a single file in PDDL format, the file comprising all the first actions.

5. The method according to any one of claims 1 to 4, wherein the corresponding indication is a corresponding second indication, and wherein the method further comprises: - Receive (304) one or more corresponding third instructions from each of the one or more second nodes (120), each of the one or more corresponding third instructions indicating whether each of the one or more second nodes (120) agrees or disagrees to perform the corresponding set of second actions.

6. The method of claim 5, wherein at least one of the corresponding third instructions disagrees with performing the corresponding set of second actions, and wherein the method further comprises: - Modify the plan determined by (305) by at least one of the following, based on one or more corresponding third instructions received: i. Exclude any second node (120) that has indicated disagreement with performing the corresponding set of second actions, and ii. Assign a second action that any of the one or more second nodes (120) has disagreed to perform to the other second nodes in the one or more second nodes (120). - Send (306) a corresponding fourth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding fourth instruction being used to indicate the corresponding set of third actions to be performed according to the modified plan.

7. The method according to claim 6, wherein the method further comprises: - Receive (307) at least one fifth indication from any one of the one or more second nodes (120), the fifth indication being used to indicate a failure in the execution of either the plan or the modified plan. - The plan determined according to the fifth instruction received (308) and any of the plans in the modified plan, and, - Send (309) a corresponding sixth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding sixth instruction being used to indicate the corresponding set of fourth actions to be performed according to the modified original or revised plan.

8. The method according to any one of claims 1 to 7, wherein each of the first node (111) and the one or more second nodes (120) is an intelligent autonomous system, and wherein the determination (302) is based on the first node (111) being selected as the leader of the one or more second nodes (120).

9. The method according to any one of claims 1 to 8, wherein the action includes at least one of the following: self-action, proxy action, jump action, and transfer action.

10. A method performed by a second node (121) for achieving a set of objectives in geospatial space (130), the second node (121) operating in a wireless communication network (100), the method comprising: - Send (401) a corresponding first indication to a first node (111) operating in the wireless communication network (100), the corresponding first indication being used to indicate: a) The corresponding objectives of the second node (121) to be achieved in the geospace (130) according to the corresponding set of capabilities of the second node (121), b) The corresponding set of capabilities of the second node (121), and c) A set of first actions determined by the second node (121) to achieve the corresponding objective, to be executed independently by the second node. - Receive (402) a corresponding second instruction from the first node (111), the corresponding second instruction being used to indicate a set of second actions to be performed solely by the second node (121), receiving (402) the corresponding second instruction based on a transmitted corresponding first instruction, and the received corresponding second instruction based on a plan for the first node (111) and one or more second nodes (120) within the radio coverage area of ​​the first node (111) to collaboratively achieve the corresponding objective: i. The first objective of the first node (111) to be achieved in the geographic space (130) based on the first set of capabilities of the first node (111), and ii. The corresponding objective to be achieved in the geospace (130) by each of the one or more second nodes (120) based on the corresponding set of capabilities of that second node, The plan is based on a corresponding set of second actions to be performed by each of the one or more second nodes (120) and the first node (111), wherein the corresponding set of second actions is determined based on both a first set of first actions determined by the first node and the corresponding set of first actions determined by each second node.

11. The method of claim 10, wherein the corresponding first instruction is a file having a Planning Domain Definition Language (PDDL) format.

12. The method according to any one of claims 10 to 11, wherein the method further comprises: - Based on the corresponding first cost of the corresponding set of first actions and the corresponding second cost of the corresponding set of second actions, determine (403) whether to agree or disagree to perform the corresponding set of second actions, and - Send (404) a corresponding third instruction to the first node (111), the corresponding third instruction being used to indicate whether the determined agreement or disagreement is to perform the corresponding set of second actions.

13. The method of claim 12, further comprising: - Receive (405) a corresponding fourth instruction from the first node (111), the corresponding fourth instruction being used to indicate a corresponding set of third actions to be performed according to a modified plan, the plan being modified based on at least one of the following: i. At least one of the one or more second nodes (120) has indicated disagreement with performing the corresponding set of second actions, and ii. At least one of the one or more second nodes (120) has disagreed to perform at least one of the corresponding set of second actions.

14. The method of claim 13, wherein the method further comprises: - Send a (406) fifth instruction to the first node (111), the fifth instruction being used to indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions, and - Receive (407) a corresponding sixth instruction from the first node (111), the corresponding sixth instruction being used to indicate a corresponding set of fourth actions to be performed according to the modified original or revised plan.

15. The method of claim 14, further comprising: - Perform one or more of the corresponding set of second actions, the corresponding set of third actions and the corresponding set of fourth actions as described in (408).

16. The method according to any one of claims 10 to 14, wherein each of the one or more second nodes (120) and the first node (111) is an intelligent autonomous system, and wherein receiving (402) the corresponding second instruction is based on the first node (111) being selected as the leader of the one or more second nodes (120).

17. The method according to any one of claims 10 to 15, wherein the action comprises at least one of the following: self-action, proxy action, jump action, and transfer action.

18. A first node (111) for achieving a set of objectives in geospatial space (130), the first node (111) being configured to operate in a wireless communication network (100), the first node (111) being further configured to: - The plan will be determined based on the following: i. The first objective of the first node (111) to be achieved in the geospace (130) according to the first set of capabilities of the first node (111); and the first set of first actions determined by the first node to be performed independently by the first node (111) to achieve the first objective, and ii. For each of one or more second nodes (120) within the radio coverage area of ​​the first node (111): a) The corresponding objectives to be achieved in the geospace (130) based on the corresponding set of capabilities of each of the one or more second nodes (120), and b) A set of first actions, determined by each of the one or more second nodes (120), to achieve the corresponding objective, to be executed individually by each second node. The plan is to collaboratively achieve the first objective and each of the corresponding objectives in the geospatial space (130) by determining a corresponding set of second actions to be performed by each of the first node (111) and the one or more second nodes (120), wherein the corresponding set of second actions is determined based on both the first set of first actions determined by the first node and the corresponding set of first actions determined by each second node, and - Send a corresponding instruction to each of the one or more second nodes (120), the corresponding instruction being configured to indicate the corresponding set of second actions to be determined.

19. The first node (111) of claim 18, wherein a first cost configured to be based on a first action of a corresponding group and a second cost of a second action of a corresponding group are determined.

20. The first node (111) according to any one of claims 18 to 19 is further configured to: - Obtain one or more corresponding first indications from each of the one or more second nodes (120), each of the one or more corresponding first indications being configured to indicate the following for each of the one or more second nodes (120): a) The corresponding objective mentioned above b) the corresponding set of capabilities, and c) The corresponding set of first actions. And the plan configured to be determined is configured to be based on one or more corresponding first instructions configured to be obtained.

21. The first node (111) of claim 20, wherein each of the one or more corresponding first instructions is a file in a Planning Domain Definition Language (PDDL) format, and wherein determining the plan is configured to include constructing a single file in PDDL format, the file including all first actions.

22. The first node (111) according to any one of claims 18 to 21, wherein the corresponding indication is a corresponding second indication, and wherein the first node (111) is further configured to: - Receive one or more corresponding third instructions from each of the one or more second nodes (120), each of the one or more corresponding third instructions being configured to instruct each of the one or more second nodes (120) to agree or disagree to perform the corresponding set of second actions.

23. The first node (111) according to claim 22, wherein at least one of the corresponding third instructions is configured to indicate disagreement with performing the corresponding set of second actions, and wherein the first node (111) is further configured to: - Modify the plan to be determined by at least one of the following, based on the one or more corresponding third instructions configured to be received: i. Exclude any second node (120) that has indicated disagreement with performing the corresponding set of second actions, and ii. Assign a second action that any of the one or more second nodes (120) has disagreed to perform to the other second nodes in the one or more second nodes (120). - Send a corresponding fourth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding fourth instruction being configured to indicate a corresponding set of third actions to be performed according to the modified plan.

24. The first node (111) according to claim 23, wherein the first node (111) is further configured to: - Receive at least one fifth indication from any one of the one or more second nodes (120), the fifth indication being configured to indicate a failure in the execution of either the plan or the modified plan. - Modify either the plan determined according to the fifth instruction configured to be received, or the modified plan, and, - Send a corresponding sixth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding sixth instruction being configured to indicate a corresponding set of fourth actions to be performed according to the modified original or revised plan.

25. The first node (111) according to any one of claims 18 to 24, wherein each of the one or more second nodes (120) and the first node (111) is configured as an intelligent autonomous system, and wherein it is determined that the first node (111) is selected as the leader of the one or more second nodes (120).

26. The first node (111) according to any one of claims 18 to 25, wherein the action is configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

27. A second node (121) for achieving a set of objectives in geospatial space (130), the second node (121) being configured to operate in a wireless communication network (100), the second node (121) being further configured to: - Send a corresponding first indication to a first node (111) configured to operate in the wireless communication network (100), the corresponding first indication being configured to indicate: a) The corresponding objectives of the second node (121) to be achieved in the geospace (130) according to the corresponding set of capabilities of the second node (121), b) The corresponding set of capabilities of the second node (121), and c) A set of first actions determined by the second node (121) to achieve the corresponding objective, to be executed independently by the second node. - Receive a corresponding second instruction from the first node (111), the corresponding second instruction being configured to indicate a set of second actions to be performed solely by the second node (121), wherein receiving the corresponding second instruction is configured to be based on the corresponding first instruction configured to be transmitted, and the corresponding second instruction configured to be received is configured to be based on a plan collaboratively implemented by the first node (111) and one or more second nodes (120) within the radio coverage area of ​​the first node (111): i. The first objective of the first node (111) to be achieved in the geographic space (130) based on the first set of capabilities of the first node (111), and ii. The corresponding objectives to be achieved in the geospace (130) by each of one or more second nodes (120) based on a corresponding set of capabilities of that second node (120), The plan is configured to be based on a corresponding set of second actions to be performed by each of the one or more second nodes (120) and the first node (111), wherein the corresponding set of second actions is determined based on both a first set of first actions determined by the first node and the corresponding set of first actions determined by each second node.

28. The second node (121) according to claim 27, wherein the corresponding first instruction is configured as a file in Planning Domain Definition Language (PDDL) format.

29. The second node (121) according to any one of claims 27 to 28, wherein the second node (121) is further configured to: - Based on the corresponding first cost of the corresponding set of first actions and the corresponding second cost of the corresponding set of second actions, determine whether to agree or disagree to execute the corresponding set of second actions, and - Send a corresponding third instruction to the first node (111), the corresponding third instruction being configured to indicate whether to agree or disagree to perform the corresponding set of second actions.

30. The second node (121) according to claim 29 is further configured to: - Receive a corresponding fourth instruction from the first node (111), the corresponding fourth instruction being configured to indicate a corresponding set of third actions to be performed according to a plan configured to be modified based on at least one of the following: i. At least one of the one or more second nodes (120) has indicated disagreement with performing the corresponding set of second actions, and ii. At least one of the one or more second nodes (120) has disagreed to perform at least one of the corresponding set of second actions.

31. The second node (121) according to claim 30, wherein the second node (121) is further configured to: - Send a fifth indication to the first node (111), the fifth indication being configured to indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions, and - Receive a corresponding sixth instruction from the first node (111), the corresponding sixth instruction being configured to indicate a corresponding set of fourth actions to be performed according to the modified original or revised plan.

32. The second node (121) according to claim 31 is further configured to: - Perform one or more of the corresponding set of second actions, the corresponding set of third actions, and the corresponding set of fourth actions.

33. The second node (121) according to any one of claims 27 to 32, wherein each of the one or more second nodes (120) and the first node (111) is configured as an intelligent autonomous system, and wherein receiving the corresponding second indication is configured to be based on the first node (111) being selected as the leader of the one or more second nodes (120).

34. The second node (121) according to any one of claims 27 to 33, wherein the action is further configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

35. A wireless communication network (100) configured to enable communication between a first node (111) and one or more second nodes (120) to achieve a set of targets in geospatial space (130), wherein the one or more second nodes (120) include a second node (121). in: a. The second node (121) is configured as follows: - Send a corresponding first indication to the first node (111), the corresponding first indication being configured to indicate: a) The corresponding objectives of the second node (121) to be achieved in the geospace (130) according to the corresponding set of capabilities of the second node (121), b) The corresponding set of capabilities of the second node (121), and c) A set of first actions, determined by the second node (121), to be executed independently by the second node to achieve the corresponding objective. b. The first node (111) is configured as follows: - The plan will be determined based on the following: i. The first objective of the first node (111) to be achieved in the geospace (130) according to the first set of capabilities of the first node (111); and the first set of first actions determined by the first node to be performed independently by the first node (111) to achieve the first objective, and ii. For each of one or more second nodes (120) within the radio coverage area of ​​the first node (111): a) The corresponding objectives achieved in the geospace (130) based on a corresponding set of capabilities of each of the one or more second nodes (120), and b) A set of first actions, determined by each of the one or more second nodes (120), to achieve the corresponding objective, executed individually by that second node. The plan is to collaboratively achieve each of the first and corresponding objectives in the geospatial space (130) by determining a corresponding set of second actions to be performed by each of the first node (111) and each of the one or more second nodes (120), wherein the corresponding set of second actions is determined based on both the first set of first actions determined by the first node and the corresponding set of first actions determined by each of the second nodes. - Send a corresponding indication to each of the one or more second nodes (120), the corresponding indication being configured to indicate the corresponding set of second actions to be determined, and wherein c. The second node (121) is also configured as follows: - Receive a corresponding second instruction from the first node (111), the corresponding second instruction being configured to indicate a set of second actions to be performed by the second node (121) alone.

36. The wireless communication network (100) according to claim 35, wherein the first node (111) is further configured to be determined based on a first cost of the corresponding set of first actions and a second cost of the corresponding set of second actions.

37. The wireless communication network (100) according to any one of claims 35 to 36, wherein the first node (111) is further configured to: - Obtain one or more corresponding first indications from each of the one or more second nodes (120), each of the one or more corresponding first indications being configured to indicate the following for each of the one or more second nodes (120): a) The corresponding objective mentioned above b) the corresponding set of capabilities, and c) The corresponding set of first actions. And the plan to be determined is configured to be based on one or more corresponding first instructions to be obtained.

38. The wireless communication network (100) of claim 37, wherein each of the one or more respective first indications is a file in a Planning Domain Definition Language, PDDL, format, and wherein determining the plan is configured to comprise: Construct a single file in PDDL format, which includes all the first actions.

39. The wireless communication network (100) according to any one of claims 35 to 38, wherein the corresponding indication is a corresponding second indication, and wherein the first node (111) is further configured to: - Receive one or more corresponding third instructions from each of the one or more second nodes (120), each of the one or more corresponding third instructions being configured to instruct each of the one or more second nodes (120) to agree or disagree to perform the corresponding set of second actions.

40. The wireless communication network (100) of claim 39, wherein at least one of the corresponding third indications is configured to indicate disagreement with performing the corresponding set of second actions, and wherein the first node (111) is further configured to: - Modify the plan to be determined by at least one of the following, based on the one or more corresponding third instructions configured to be received: i. Exclude any second node (120) that has indicated disagreement with performing the corresponding set of second actions, and ii. Assign a second action that any of the one or more second nodes (120) has disagreed to perform to the other second nodes in the one or more second nodes (120). - Send a corresponding fourth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding fourth instruction being configured to indicate a corresponding set of third actions to be performed according to the modified plan.

41. The wireless communication network (100) according to claim 40, wherein the first node (111) is further configured to: - Receive at least one fifth indication from any one of the one or more second nodes (120), the fifth indication being configured to indicate a failure in the execution of either the plan or the modified plan. - Modify either the plan determined according to the fifth instruction configured to be received, or the modified plan, and, - Send a corresponding sixth instruction to each of the one or more second nodes (120) that has been instructed to agree to perform at least one of the corresponding set of second actions, the corresponding sixth instruction being configured to indicate a corresponding set of fourth actions to be performed according to the modified original or revised plan.

42. The wireless communication network (100) according to any one of claims 35 to 41, wherein each of the one or more second nodes (120) and the first node (111) is configured as an intelligent autonomous system, and wherein a determination is made that is configured to be the leader of the one or more second nodes (120) based on the first node (111) being selected.

43. The wireless communication network (100) according to any one of claims 35 to 42, wherein the action is configured to include at least one of the following: self-action, proxy action, jump action, and transfer action.

44. The wireless communication network (100) according to any one of claims 35 to 43, wherein the second node (121) is further configured to: - Based on the corresponding first cost of the corresponding set of first actions and the corresponding second cost of the corresponding set of second actions, determine whether to agree or disagree to execute the corresponding set of second actions, and - Send a corresponding third instruction to the first node (111), the corresponding third instruction being configured to indicate whether to agree or disagree to perform the corresponding set of second actions.

45. The wireless communication network (100) according to claim 44, wherein the second node (121) is further configured to: - Receive a corresponding fourth instruction from the first node (111), the corresponding fourth instruction being configured to indicate a corresponding set of third actions to be performed according to a plan configured to be modified based on at least one of the following: i. At least one of the one or more second nodes (120) has indicated disagreement with performing the corresponding set of second actions, and ii. At least one of the one or more second nodes (120) has disagreed to perform at least one of the corresponding set of second actions.

46. ​​The wireless communication network (100) according to claim 45, wherein the second node (121) is further configured to: - Send a fifth indication to the first node (111), the fifth indication being configured to indicate a failure in performing either the corresponding set of first actions or the corresponding set of second actions, and - Receive a corresponding sixth instruction from the first node (111), the corresponding sixth instruction being configured to indicate a corresponding set of fourth actions to be performed according to the modified original or revised plan.

47. The wireless communication network (100) according to claim 46, wherein the second node (121) is further configured to: - Perform one or more of the corresponding set of second actions, the corresponding set of third actions, and the corresponding set of fourth actions.

Citation Information

Patent Citations

  • Supervision and Control of Heterogeneous Autonomous Operations

    US20100312388A1

  • Autonomous product delivery vehicle fleet master-slave relationship management

    US20190025818A1

  • Method and system for optimally allocating warehouse procurement tasks to distributed robotic agents

    US20190049975A1