WO2025035676A1 - 机器人任务状态监测方法、装置以及相关设备 - Google Patents

机器人任务状态监测方法、装置以及相关设备 Download PDF

Info

Publication number
WO2025035676A1
WO2025035676A1 PCT/CN2023/140529 CN2023140529W WO2025035676A1 WO 2025035676 A1 WO2025035676 A1 WO 2025035676A1 CN 2023140529 W CN2023140529 W CN 2023140529W WO 2025035676 A1 WO2025035676 A1 WO 2025035676A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
robot
executed
information
attribute information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2023/140529
Other languages
English (en)
French (fr)
Inventor
李伟
杨明川
王羽培
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Telecom Corp Ltd Technology Innovation Center
China Telecom Corp Ltd
Original Assignee
China Telecom Corp Ltd Technology Innovation Center
China Telecom Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Telecom Corp Ltd Technology Innovation Center, China Telecom Corp Ltd filed Critical China Telecom Corp Ltd Technology Innovation Center
Publication of WO2025035676A1 publication Critical patent/WO2025035676A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1679—Program controls characterised by the tasks executed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1602—Program controls characterised by the control system, structure, architecture

Definitions

  • the present disclosure relates to the technical field of Internet of Things, and in particular to a robot task status monitoring method, device and related equipment.
  • Smart space is a typical environment for studying the principles and technologies of harmonious human-computer interaction.
  • users can interact with various information sources (including devices and data).
  • information sources including devices and data.
  • artificial intelligence technology the integration of man, machine and object in space will become closer and closer.
  • robots In smart spaces, robots have the ability to interact intelligently with other devices and objects and can perform complex tasks. In the actual task execution process, due to the numerous elements in smart spaces and the complex and changeable environment, the task execution status depends not only on the status of the robot and the target object itself, but also on many factors, especially sudden situations from the environment. Therefore, in related technologies, when the robot is performing a task, the system cannot adjust the robot's task status in time due to sudden changes in the environment.
  • the present disclosure provides a robot task status monitoring method, device and related equipment, which at least to a certain extent overcome the problem that related technologies cannot timely monitor changes in element attributes in a task due to sudden changes in the task execution environment.
  • a method for monitoring the task status of a robot comprising: obtaining task information of a task instance to be performed by the robot; processing the task information of the task instance to be performed, and determining an action sequence of the robot according to the task information; determining a first key element corresponding to the task instance to be performed according to the action sequence of the robot; searching a first associated element having an associated relationship with the key element in a pre-established ontology knowledge base, the ontology knowledge base comprising: a plurality of key elements and associated elements having an associated relationship with each key element; determining the first key element of the robot to be performed according to the first key element and the first associated element.
  • the first attribute information of the task instance to be executed; and the task state information of the task instance to be executed by the robot is determined according to the first attribute information of the task instance to be executed by the robot.
  • the task information of the task instance to be executed is processed, and the action sequence of the robot is determined according to the task information, including: generating an action sequence corresponding to the task instance to be executed according to the task information of the task instance to be executed, wherein the action sequence includes multiple actions to be executed by the robot.
  • the key elements corresponding to the task instance to be executed are determined according to the action sequence of the robot, including: inputting multiple action sequences to be executed by the robot into a pre-trained element processing model, and outputting the key elements corresponding to the task instance to be executed, wherein the element processing model is used to analyze the action sequence to be executed by the robot and extract the key elements corresponding to the task instance to be executed.
  • the method before determining the first attribute information of the robot's task instance to be performed according to the first key element and the first associated element, the method also includes: obtaining target attribute information of all corresponding associated elements in the robot's task instance to be performed.
  • the task status information includes: a normal state and an abnormal state
  • the task status information of the robot task instance to be performed is determined according to the first attribute information of the robot task instance to be performed, including: when the first attribute information of the robot task instance to be performed is consistent with the target attribute information, determining that the task status information of the robot task instance to be performed is a normal state; when the first attribute information of the robot task instance to be performed is inconsistent with the target attribute information, determining that the task status information of the robot task instance to be performed is an abnormal state.
  • the abnormal state of the task status information includes: an interruption state or a failure state, and when the first attribute information of the robot task instance to be executed is inconsistent with the target attribute information, determining that the task status information of the robot task instance to be executed is an abnormal state, including: when the first attribute information of the robot task instance to be executed is inconsistent with the target attribute information, determining that the task status information of the robot task instance to be executed is an interruption state; when the task status information of the robot task instance to be executed is an interruption state, repeating the following steps until a preset stop condition is met, determining that the task status information of the robot task instance to be executed is a failure state, wherein the preset stop condition is that the second attribute information is inconsistent with the target attribute information and the preset stop condition when the number of repetitions is greater than a preset threshold; when the task state information of the robot's task instance to be executed is an interrupted state, determining the interruption position of the robot in the interrupted state; updating the task
  • the method after determining the task status information of the robot's task instance to be performed according to the first attribute information of the robot's task instance to be performed, the method also includes: when the task status information of the robot's task instance to be performed is in a normal state, generating a first monitoring instruction, the first monitoring instruction is used to continue monitoring the first attribute information of the robot's task instance to be performed; when the task status information of the robot's task instance to be performed is in an interrupted state, generating a second monitoring instruction, the second monitoring instruction is used to monitor the second attribute information of the robot's updated task instance to be performed.
  • a robot task status monitoring device which includes: a task information acquisition module, configured to acquire task information of the robot's task instance to be performed; an action sequence processing module, configured to process the task information of the task instance to be performed, and determine the action sequence of the robot according to the task information; a key element determination module, configured to determine a first key element corresponding to the task instance to be performed according to the action sequence of the robot; an associated element determination module, configured to find an associated element having an associated relationship with the key element in a pre-established ontology knowledge base, the ontology knowledge base comprising: multiple key elements and a first associated element having an associated relationship with each key element; an attribute information determination module, configured to determine the first attribute information of the robot's task instance to be performed according to the first key element and the first associated element; a task status determination module, configured to determine the task status information of the robot's task instance to be performed according to the first attribute information of the robot's task instance to be performed.
  • an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned robot task status monitoring methods by executing the executable instructions.
  • a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, any one of the above-mentioned robot task status monitoring methods is implemented.
  • a computer program product including a computer program, wherein when the computer program is executed by a processor, the robot task state monitoring method described above is implemented.
  • the robot task status monitoring method, device and related equipment provided in the embodiments of the present invention first obtain the task information of the robot's task instance to be executed; secondly, process the task information of the task instance to be executed, and determine the robot's action sequence according to the task information; then, determine the first key element corresponding to the task instance to be executed according to the robot's action sequence; then, find out the first associated element that has an association relationship with the first key element in a pre-established ontology knowledge base; then, determine the first attribute information of the robot's task instance to be executed according to the first key element and the first associated element; finally, determine the task status information of the robot's task instance to be executed according to the first attribute information of the robot's task instance to be executed.
  • robots cannot respond in time during the actual task execution due to sudden changes in the environment. Changes in the attributes of elements in the task status are monitored, resulting in the robot being unable to adjust the task status in time.
  • the disclosed embodiment monitors the attribute information of the robot in the execution of the task, and determines the attribute information of the robot's task instance to be executed based on the first key element and the first associated element that has an associated relationship with the robot's task instance to be executed.
  • the task status information of the robot's task instance to be executed is determined, so as to timely correct and improve the task execution decision, improve the defects of insufficient intelligence, real-time and task integrity encountered in task execution, and make the intelligent service robots in the intelligent space more efficient and intelligent when performing tasks.
  • FIG1 is a schematic diagram showing a system architecture of a method for monitoring robot task status in an embodiment of the present disclosure
  • FIG2 is a schematic diagram showing a method for monitoring a robot task state in an embodiment of the present disclosure
  • FIG3 is a schematic diagram showing a method for obtaining key elements corresponding to and associated with a task instance to be executed in an embodiment of the present disclosure
  • FIG4 shows a schematic diagram of a robot task status monitoring system flow in an embodiment of the present disclosure
  • FIG5 shows a schematic diagram of adjusting task planning according to task status information in an embodiment of the present disclosure
  • FIG6 shows a schematic diagram of a robot task status monitoring device in an embodiment of the present disclosure
  • FIG. 7 shows a schematic diagram of an electronic device to which a method for monitoring robot task status is applied in an embodiment of the present disclosure.
  • Fig. 1 shows a schematic diagram of an exemplary application system architecture to which the robot task state monitoring method in the embodiment of the present disclosure can be applied.
  • the system architecture may include a monitoring device 101 , a network 102 , and a robot 103 .
  • the network 102 is a medium for providing a communication link between the monitoring device 101 and the robot 103, and can be a wired network or a wireless network.
  • the wireless network or wired network described above uses standard communication technologies and/or protocols.
  • the network is typically the Internet, but may be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of virtual private networks.
  • technologies and/or formats including Hypertext Markup Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network.
  • conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPsec) may be used to encrypt all or some links.
  • SSL Secure Socket Layer
  • TLS Transport Layer Security
  • VPN Virtual Private Network
  • IPsec Internet Protocol Security
  • customized and/or dedicated data communication technologies may be used to replace or supplement the above-mentioned data communication technologies.
  • the monitoring device 101 may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.
  • the client of the application installed in different monitoring devices 101 is the same, or the client of the same type of application based on different operating systems.
  • the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.
  • the robot 103 may be a robot that provides various services, such as a background management robot that provides support for the device operated by the user using the monitoring device 101.
  • the background management robot may analyze and process the received request and other data, and feed back the processing results to the monitoring device.
  • the robot can be an independent physical robot, or a robot cluster or distributed system composed of multiple physical robots, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
  • the monitoring device can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to this.
  • the monitoring device and the robot can be directly or indirectly connected by wired or wireless communication, and this application does not limit this.
  • monitoring devices 101, networks 102, and robots 103 in FIG1 is merely illustrative, and any number of monitoring devices, networks, and robots may be provided according to actual needs, which is not limited in the embodiments of the present disclosure.
  • a robot task status monitoring method is provided in the embodiment of the present disclosure.
  • the method can be executed by any electronic device with computing processing capabilities.
  • the robot task status monitoring method provided in the embodiments of the present disclosure can be executed by the monitoring device of the above-mentioned system architecture; in other embodiments, the robot task status monitoring method provided in the embodiments of the present disclosure can be executed by the robot in the above-mentioned system architecture; in other embodiments, the robot task status monitoring method provided in the embodiments of the present disclosure can be implemented by the monitoring device and the robot in the above-mentioned system architecture through interaction.
  • a control method is provided in the disclosed embodiments for monitoring the task status of a robot in an intelligent space, which can be applied but is not limited to.
  • the task execution status depends not only on the status of the robot and the target object itself, but also on many factors, especially emergencies from the environment.
  • the following method of the present application can effectively avoid the problem in the related art that changes in the attributes of the elements in the task cannot be monitored in time when the task execution environment changes.
  • FIG2 shows a schematic diagram of a robot task state monitoring method in an embodiment of the present disclosure.
  • the robot task state monitoring method provided in an embodiment of the present disclosure includes the following steps:
  • the task information of the robot's task instance to be performed acquired in the embodiments of the present disclosure may be the task information generated by receiving a task instruction from a user terminal and then querying the relevant static knowledge defined by the current task instance in the knowledge base according to the received task instruction, wherein the static knowledge is constructed through common sense knowledge and task background, and is used to describe concepts such as abstract categories, inherent attributes, and relationships between categories, as well as relationships between concepts.
  • the task information of the robot's task instance to be performed is "get a glass of water from the kitchen.”
  • the robot in the disclosed embodiments receives task instructions from the user end, and generates task information by querying the relevant static knowledge defined in the current task instance in the knowledge base.
  • the disclosed embodiments process the generated task information to obtain the robot's action sequence. For example, the task information “get a glass of water from the kitchen” is processed to obtain the action sequence “walk through the living room”, “walk through the corridor", “find the table where the glass of water is placed”, etc.
  • S203 Determine a first key element corresponding to the task instance to be executed according to the action sequence of the robot.
  • the first key element in the embodiment of the present disclosure can be a noun in any action sequence. For example, according to the action sequences "walk through the living room”, “walk through the corridor”, “reach the kitchen”, “find the table for the cup of water”, etc., determine the first key elements such as “living room”, “corridor”, “kitchen”, “table”, “cup of water” corresponding to the task instance to be executed.
  • the ontology knowledge base contains: multiple key elements and associated elements that have an associated relationship with each key element.
  • the disclosed embodiment obtains the first key element corresponding to the task instance to be executed by processing the task information obtained by the robot.
  • the other symbiotic elements associated with the key element in the spatial environment will also affect the task execution. Therefore, the disclosed embodiment matches the obtained first key element with a pre-established ontology knowledge base including multiple key elements and associated elements having an associated relationship with each key element, so as to determine the first associated element having an associated relationship with the first key element. For example, whether there are obstacles in the corridor that prevent the robot from continuing to execute the task instance, the switch state of the study door can affect the robot's range of activities, and the items on the desk can affect the taking of the water cup, etc. Therefore, the first associated element having an associated relationship with the first key element is determined to be the "obstacle" in the corridor, the "door” in the study, the "item” on the desk, etc.
  • S205 Determine first attribute information of the task instance to be performed by the robot according to the first key element and the first associated element.
  • the first attribute information in the embodiments of the present disclosure may be the attribute information of any first key element and/or any first associated element.
  • the embodiments of the present disclosure may input the first key element and the first associated element into a pre-built neural network model, and output the attribute information of the key element associated elements. For example, "obstacles" in the corridor, "doors” in the study, and “items” on the desk may be input into the neural network model to determine whether the obstacles in the corridor hinder the robot's movement, the "switch status" of the study door, and whether the items on the desk hinder the water cup, etc.
  • S206 Determine task state information of the task instance to be performed by the robot according to the first attribute information of the task instance to be performed by the robot.
  • the task execution can be changed or optimized. For example, if it is determined that the door of the study is closed, or if an obstacle appears during the robot's navigation process, the navigation route needs to be changed. If a cup is suddenly hit the ground and broken during the execution of the task, the task can be stopped.
  • the robot task status monitoring method in the disclosed embodiment first obtains the task information of the robot's task instance to be executed; secondly, processes the task information of the task instance to be executed, and determines the robot's action sequence according to the task information; then, determines the first key element corresponding to the task instance to be executed according to the robot's action sequence; thereafter, finds the first associated element having an associated relationship with the first key element in a pre-established ontology knowledge base; then, determines the first attribute information of the robot's task instance to be executed according to the first key element and the first associated element; finally, determines the task status information of the robot's task instance to be executed according to the first attribute information of the robot's task instance to be executed.
  • the robot cannot timely monitor the changes in the element attributes in the task state due to sudden changes in the environment, resulting in the robot being unable to adjust the task state in time.
  • the attribute information of the robot in the task execution is monitored, and the first key element and the attribute information of the robot are adjusted according to the first key element and the attribute information of the robot.
  • the robot's task instance to be executed has a first associated element of an associated relationship to determine the attribute information of the robot's task instance to be executed.
  • the task status information of the robot's task instance to be executed is determined, so as to timely correct and improve the task execution decision, improve the defects of insufficient intelligence, real-time and task integrity encountered in task execution, and make the intelligent service robots in the intelligent space more efficient and intelligent when performing tasks.
  • the method for obtaining the first key element in the embodiment of the present disclosure includes the following steps:
  • the first key element in the embodiment of the present disclosure is some spatial elements that the robot may encounter during the execution of the task.
  • the embodiment of the present disclosure can decompose the task information of the task instance to be executed according to a pre-built action extraction model, and obtain the action sequence corresponding to the task instance to be executed.
  • the action sequence corresponding to the task instance to be executed in the embodiment of the present disclosure can be: starting from the living room, crossing the corridor, entering the study, picking up the water cup on the desk, and returning to the living room.
  • the action sequence of the above robot is input into the pre-trained element processing model, and the key elements corresponding to the task instance to be executed are output, and the key elements "living room”, “corridor”, “desk” and “water cup” corresponding to the task instance to be executed are obtained.
  • the first key element corresponding to the task instance to be executed is determined according to the robot's action sequence, including: inputting multiple action sequences to be executed by the robot into a pre-trained element processing model, and outputting the key elements corresponding to the task instance to be executed, wherein the element processing model is used to analyze the action sequence to be executed by the robot and extract the first key element corresponding to the task instance to be executed.
  • the element processing model in the embodiments of the present disclosure can be but is not limited to a semantic model.
  • the embodiments of the present disclosure take the semantic model as an example, combine the action sequence corresponding to the task instance to be executed with the action extraction model, and then extract the first key element that is consistent with the task instance to be executed.
  • the action sequence starting from the living room, crossing the corridor, entering the study, picking up the water cup on the desk, and returning to the living room is input into the pre-trained semantic model, and combined with the semantics, the key elements "living room”, “corridor", "desk” and "water cup” in the above action sequence that are consistent with the robot's task instance to be executed are extracted.
  • the robot task status monitoring method in the disclosed embodiment before determining the first attribute information of the robot's task instance to be performed based on the first key element and the first associated element, the robot task status monitoring method in the disclosed embodiment also includes: obtaining target attribute information of all corresponding associated elements in the robot's task instance to be performed.
  • the robot task status monitoring method in the embodiment of the present disclosure can be completed by a pre-built task monitoring model.
  • the task monitoring model includes: a task monitoring management layer, a key element
  • the present invention comprises an element extraction layer, an associated element analysis layer, an associated attribute extraction layer and an associated attribute monitoring layer. Specifically, after acquiring the task information, the embodiment of the present invention outputs the created task instance to the task monitoring management layer for monitoring and management.
  • the task monitoring management layer mainly tracks, monitors and manages the current task instance, including decomposing the task instance into an action sequence, binding element attributes related to the task instance, evaluating the element attributes, and updating the task status in real time when the element attributes change.
  • the task monitoring management layer in the embodiment of the present disclosure receives a task instance and preliminarily decomposes the task into an action sequence;
  • the key element extraction layer extracts the first key element involved in completing the task instance based on the task action sequence and in combination with the element processing model (for example, the semantic model) of the current space;
  • the associated element analysis layer extracts the first associated element having an associated relationship with the task instance based on the first key element and in combination with the ontology knowledge base of the current space;
  • the associated attribute extraction layer determines the first attribute information of the robot's task instance to be executed based on the input first key element and the first associated element;
  • the associated attribute extraction layer outputs the first attribute information of the robot's task instance to be executed to the associated attribute monitoring layer to complete the monitoring of the first attribute information of the robot's task instance to be executed;
  • the associated attribute extraction layer outputs the first attribute information of the robot's task instance to be executed to the task monitoring management layer to complete the binding of the task instance with the action attribute
  • the disclosed embodiments decompose the task information of the task instance to be performed by the robot to obtain an action sequence, and obtain the first associated element having an associated relationship with each first key element through the first key element involved in the task instance, and record the first attribute information that can complete the task instance as target attribute information.
  • the disclosed embodiments can record the door of the study in an open state as target attribute information, etc.
  • the task status information in the embodiments of the present disclosure includes: a normal state and an abnormal state.
  • the task status information of the robot's task instance to be executed is determined based on the first attribute information of the robot's task instance to be executed, including: when the first attribute information of the robot's task instance to be executed is consistent with the target attribute information, determining that the task status information of the robot's task instance to be executed is a normal state; when the first attribute information of the robot's task instance to be executed is inconsistent with the target attribute information, determining that the task status information of the robot's task instance to be executed is an abnormal state.
  • the disclosed embodiments compare the determined first attribute information of the robot's task instance to be executed with the target attribute information to determine whether the acquired first attribute information of the robot's task instance to be executed can complete the robot's task instance to be executed. If the first attribute information of the robot's task instance to be executed is inconsistent with the target attribute information, it is determined that the element attributes in the robot's task instance to be executed have changed and the task instance cannot be completed. It is determined that the task status information of the robot's task instance to be executed is in an abnormal state, and the task plan can be adjusted in time according to the task status information of the task instance to be executed.
  • the target attribute information in the embodiment of the present disclosure is a preset range generated by the key elements determined according to the action sequence of the robot and the corresponding associated elements found in the ontology knowledge base. For example, according to the key element "study" and the associated element "door", a range of "when the robot can pass through the study, The first attribute information of the robot's task instance to be performed collected on-site is compared with the above-mentioned target attribute information. If the first attribute information of the robot's task instance to be performed collected on-site is within the range of the target attribute information, it is determined that the robot can normally complete the task instance to be performed.
  • the first attribute information of the robot's task instance to be performed collected on-site is not within the range of the target attribute information, it is determined that the robot cannot normally complete the task instance to be performed.
  • the first attribute information of the robot's task instance to be performed collected on-site is "the door opening angle is 0 (the door is closed)", the first attribute information (0°) is not between 45° and 90°, and the robot cannot normally complete the task instance to be performed.
  • the abnormal state of the task status information in the embodiments of the present disclosure includes: an interruption state and a failure state.
  • the task status information of the robot's task instance to be executed is determined to be an abnormal state, including: when the first attribute information of the robot's task instance to be executed is inconsistent with the target attribute information, the task status information of the robot's task instance to be executed is determined to be an interruption state; when the task status information of the robot's task instance to be executed is an interruption state, repeatedly execute the following steps until the preset stop condition is met, and determine that the task status information of the robot's task instance to be executed is a failure state, wherein the preset stop condition is that the second attribute information is inconsistent with the target attribute information and the preset stop condition is that the number of repetitions is greater than a preset threshold; when the task status information of the robot's task instance to be executed is an interruption state, determine the interruption position of the robot in the interruption state;
  • the task state information of the robot's task instance to be executed is determined to be an interrupted state, and the interruption position of the robot in the interrupted state is determined, and the task information of the robot's task instance to be executed is redetermined at the interrupted position, and the robot's action sequence is updated according to the updated task information, and the second key element and the second associated element are re-determined according to the updated work sequence, and the second attribute information of the updated task instance to be executed is determined according to the updated second key element and the second associated element, and it is judged whether the second attribute information is consistent with the target attribute information.
  • the robot's updated task instance to be executed is determined.
  • the task status information is in a normal state, and the task instance continues to be executed; if the second attribute information of the updated robot's task instance to be executed is inconsistent with the target attribute information, the interruption position of the robot in the interruption state is repeatedly determined, and the second attribute information of the robot's updated task instance to be executed is compared with the target attribute information to obtain a comparison result. If the second attribute information is inconsistent with the target attribute information and the number of repetitions is greater than a preset threshold, the task status information of the robot's task instance to be executed is determined to be a failed state.
  • the method after determining the task status information of the robot's task instance to be executed based on the status attribute information of the associated elements, the method also includes: when the task status information of the robot's task instance to be executed is in a normal state, generating a first monitoring instruction, the first monitoring instruction is used to continue monitoring the status attribute information of the associated elements; when the task status information of the robot's task instance to be executed is in an interrupted state, generating a second monitoring instruction, the second monitoring instruction is used to monitor the second attribute information of the robot's updated task instance to be executed.
  • the task status information in the embodiment of the present disclosure includes a normal state, an interrupted state and a failed state. If the monitored task status information is a normal state, the robot will continue to execute the task instance; if the monitored task status information is an interrupted state, the robot will first suspend the execution of the above task instance, re-plan the action sequence of the task and issue a request to resume the execution of the above task instance. If the number of repetitions is within the preset threshold and it is judged that the updated second attribute information is consistent with the target attribute information, it can be determined that the action sequence of the re-planned task can execute the task normally.
  • the robot continues to execute the task according to the re-planned action sequence, and monitors the updated second attribute information of the task instance to be executed in real time. If the number of requests for recovery exceeds the preset threshold, it is determined that the task status information is a failed state; if the monitored task status information is a failed state, all corresponding associated elements in the robot's task instance to be executed are unbound from their corresponding target attribute information, and the monitoring resources are released to control the robot to stop executing the task instance.
  • the present disclosure also provides a robot task state monitoring device, such as the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.
  • FIG6 shows a schematic diagram of a robot task status monitoring device in an embodiment of the present disclosure. As shown in FIG6 , the device includes:
  • the task information acquisition module 601 is used to acquire the task information of the task instance to be performed by the robot;
  • An action sequence processing module 602 is used to process the task information of the task instance to be executed and determine the action sequence of the robot according to the task information;
  • a key element determination module 603 is used to determine a first key element corresponding to the task instance to be executed according to the action sequence of the robot;
  • the associated element determination module 604 is used to find out the first associated element associated with the first key element in a pre-established ontology knowledge base, wherein the ontology knowledge base includes: a plurality of key elements and associated elements associated with each key element;
  • An attribute information determination module 605 is used to determine first attribute information of the robot's task instance to be performed according to the first key element and the first associated element;
  • the task status determination module 606 is used to determine the task status information of the task instance to be performed by the robot according to the first attribute information of the task instance to be performed by the robot.
  • the robot task status monitoring device obtains the task information of the robot's task instance to be executed through a task information acquisition module; processes the task information of the task instance to be executed through an action sequence processing module, and determines the robot's action sequence according to the task information; determines the first key element corresponding to the task instance to be executed according to the robot's action sequence through a key element determination module; finds out the first associated element having an associated relationship with the first key element in a pre-established ontology knowledge base through an associated element determination module; determines the first attribute information of the robot's task instance to be executed according to the first key element and the first associated element through an attribute information determination module; and determines the task status information of the robot's task instance to be executed according to the first attribute information of the robot's task instance to be executed through a task status determination module.
  • the robot In the actual task execution process, the robot cannot timely monitor the changes in the element attributes in the task state due to sudden changes in the environment, resulting in the robot being unable to adjust the task state in time.
  • the disclosed embodiment monitors the attribute information of the robot in the task execution, and determines the attribute information of the robot's task instance to be executed based on the first key element and the first associated element that has an association relationship with the robot's task instance to be executed.
  • the task state information of the robot's task instance to be executed is determined, so as to timely correct and improve the task execution decision, improve the defects of insufficient intelligence, real-time and task integrity encountered in task execution, and make the intelligent service robot in the intelligent space more efficient and intelligent when performing tasks.
  • the action sequence processing module in the embodiments of the present disclosure is also used to generate an action sequence corresponding to the task instance to be executed based on the task information of the task instance to be executed, and the action sequence includes multiple actions to be executed by the robot.
  • the key element determination module in the embodiments of the present disclosure is also used to input multiple action sequences to be executed by the robot into a pre-trained element processing model, and output key elements corresponding to the task instances to be executed, wherein the element processing model is used to analyze the action sequences to be executed by the robot and extract the first key element corresponding to the task instances to be executed.
  • the robot task status monitoring device in the embodiment of the present disclosure further includes, before determining the first attribute information of the robot's task instance to be performed based on the first key element and the first associated element: a target attribute information acquisition module, configured to obtain the target attribute information of all corresponding associated elements in the robot's task instance to be performed.
  • the task status information in the embodiments of the present disclosure includes: normal state and abnormal state.
  • the above-mentioned task status determination module is also used to determine that the task status information of the robot's task instance to be executed is a normal state when the first attribute information of the robot's task instance to be executed is consistent with the target attribute information; when the first attribute information of the robot's task instance to be executed is inconsistent with the target attribute information, determine that the task status information of the robot's task instance to be executed is an abnormal state.
  • the abnormal state of the task status information in the embodiment of the present disclosure includes: interrupt state and a failure state
  • the task state determination module is also used to determine that the task state information of the robot's task instance to be executed is an interrupted state when the first attribute information of the robot's task instance to be executed is inconsistent with the target attribute information; when the task state information of the robot's task instance to be executed is an interrupted state, repeatedly execute the following steps until a preset stop condition is met, and determine that the task state information of the robot's task instance to be executed is a failure state, wherein the preset stop condition is that the second attribute information is inconsistent with the target attribute information and the preset stop condition is that the number of repetitions is greater than a preset threshold; when the task state information of the robot's task instance to be executed is an interrupted state, determine the interruption position of the robot in the interrupted state; update the task information of the robot's task instance to be executed according to the interruption position; determine the updated action sequence of the robot according to the updated task information; and determine the updated action sequence
  • Action sequence determine the second key element corresponding to the updated task instance to be executed; find out the second associated element associated with the second key element in the ontology knowledge base; determine the second attribute information of the task instance to be executed after the robot is updated according to the second key element and the second associated element; judge whether the second attribute information of the task instance to be executed after the robot is updated is consistent with the target attribute information; if the second attribute information of the task instance to be executed after the robot is updated is consistent with the target attribute information, determine that the task state information of the task instance to be executed after the robot is updated is a normal state; if the second attribute information of the task instance to be executed after the robot is updated is inconsistent with the target attribute information, re-determine the interruption position of the robot in the interruption state, compare the second attribute information of the task instance to be executed after the robot is updated with the target attribute information, and obtain the comparison result.
  • the device after determining the task status information of the robot's task instance to be performed based on the first attribute information of the robot's task instance to be performed, the device also includes: a first monitoring module, configured to generate a first monitoring instruction when the task status information of the robot's task instance to be performed is in a normal state, the first monitoring instruction being used to continue monitoring the first attribute information of the robot's task instance to be performed; and a second monitoring module, configured to generate a second monitoring instruction when the task status information of the robot's task instance to be performed is in an interrupted state, the second monitoring instruction being used to monitor the second attribute information of the robot's task instance to be performed after the update.
  • a first monitoring module configured to generate a first monitoring instruction when the task status information of the robot's task instance to be performed is in a normal state, the first monitoring instruction being used to continue monitoring the first attribute information of the robot's task instance to be performed
  • a second monitoring module configured to generate a second monitoring instruction when the task status information of the robot's task instance to be performed
  • the electronic device 700 according to this embodiment of the present disclosure is described below with reference to Fig. 7.
  • the electronic device 700 shown in Fig. 7 is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present disclosure.
  • the electronic device 700 is in the form of a general computing device.
  • the components of the electronic device 700 may include but are not limited to: at least one processing unit 701, at least one storage unit 702, and a bus 703 connecting different system components (including the storage unit 702 and the processing unit 701).
  • the storage unit stores program codes, which can be executed by the processing unit 701 so that the processing Unit 701 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.
  • the processing unit 701 may perform the following steps of the above method embodiment:
  • the task information of the task instance to be executed is processed, and the action sequence of the robot is determined according to the task information.
  • a first key element corresponding to the task instance to be executed is determined according to the action sequence of the robot.
  • a first associated element having an associated relationship with the first key element is found in a pre-established ontology knowledge base, wherein the ontology knowledge base includes: a plurality of key elements and associated elements having an associated relationship with each key element.
  • task state information of the task instance to be performed by the robot is determined.
  • the storage unit 702 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7021 and/or a cache storage unit 7022 , and may further include a read-only storage unit (ROM) 7023 .
  • RAM random access storage unit
  • ROM read-only storage unit
  • the storage unit 702 may also include a program/utility 7024 having a set (at least one) of program modules 7025, such program modules 7025 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
  • program modules 7025 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
  • Bus 703 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
  • the electronic device 700 may also communicate with one or more external devices 704 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and/or may communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input/output (I/O) interface 705.
  • the electronic device 700 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and/or public networks, such as the Internet) through a network adapter 706.
  • networks e.g., local area networks (LANs), wide area networks (WANs), and/or public networks, such as the Internet
  • the network adapter 706 communicates with other modules of the electronic device 700 through a bus 703. It should be understood that, although not shown in the figure, other hardware and/or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
  • the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in A non-volatile storage medium (which may be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network includes several instructions to enable a computing device (which may be a personal computer, server, terminal device, or network device, etc.) to execute a method according to an embodiment of the present disclosure.
  • a non-volatile storage medium which may be a CD-ROM, USB flash drive, mobile hard disk, etc.
  • a computing device which may be a personal computer, server, terminal device, or network device, etc.
  • the process described above with reference to the flowchart may be implemented as a computer program product, which includes: a computer program, which implements the above-mentioned robot task state monitoring method when the computer program is executed by a processor.
  • a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium.
  • a program product capable of implementing the above-mentioned method of the present disclosure is stored thereon.
  • various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a monitoring device, the program code is used to cause the monitoring device to execute the steps according to various exemplary implementations of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.
  • Computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
  • the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages.
  • the program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
  • the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).
  • LAN local area network
  • WAN wide area network
  • the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
  • a non-volatile storage medium which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.
  • a computing device which can be a personal computer, a server, a mobile terminal, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Numerical Control (AREA)
  • Manipulator (AREA)

Abstract

一种机器人（103）任务状态监测方法、装置以及相关设备，机器人（103）任务状态监测方法包括：获取机器人（103）待执行任务实例的任务信息；对待执行任务实例的任务信息进行处理，根据任务信息确定机器人（103）的动作序列；根据机器人（103）的动作序列确定与待执行任务实例对应关联的第一关键元素；在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素；根据第一关键元素与第一关联元素，确定机器人（103）待执行任务实例的第一属性信息；根据机器人（103）待执行任务实例的第一属性信息，确定机器人（103）待执行任务实例的任务状态信息。

Description

机器人任务状态监测方法、装置以及相关设备
相关申请的交叉引用
本公开要求于2023年8月14日提交的申请号为202311021508.5、名称为“机器人任务状态监测方法、装置以及相关设备”的中国专利申请的优先权，该中国专利申请的全部内容通过引用全部并入本文。
技术领域
本公开涉及物联网技术领域，尤其涉及一种机器人任务状态监测方法、装置以及相关设备。
背景技术
智能空间是研究和谐人机交互原理与技术的典型环境。在智能空间中，用户可以与各种信息源(包括设备和数据)进行交互。随着人工智能技术的发展，空间中人机物三元融合会越来越紧密。
智能空间中，机器人具备与其他设备及物品智能交互的能力，可执行复杂的任务。在实际任务执行过程中，由于智能空间中元素繁多，环境复杂多变，因此任务执行状态不止取决于机器人与目标物品本身状态，还会受诸多因素影响，特别是来自环境的突发情况等，因此，在相关技术中，机器人在任务执行时，由于环境突然发生变化，导致系统不能及时调整机器人的任务状态。
需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。
发明内容
本公开提供一种机器人任务状态监测方法、装置以及相关设备，至少在一定程度上克服相关技术由于任务执行环境突变而不能及时监测出任务中的元素属性发生的变化。
本公开的其他特性和优点将通过下面的详细描述变得显然，或部分地通过本公开的实践而习得。
根据本公开的一个方面，提供了一种机器人任务状态监测方法，该方法包括：获取所述机器人待执行任务实例的任务信息；对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列；根据所述机器人的动作序列确定与所述待执行任务实例对应关联的第一关键元素；在预先建立的本体知识库中查找出与所述关键元素具有关联关系的第一关联元素，所述本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素；根据所述第一关键元素与所述第一关联元素，确定所述机器人待 执行任务实例的第一属性信息；根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息。
在本公开的一些示例性实施例中，基于前述方案，对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列，包括：根据所述待执行任务实例的任务信息，生成所述待执行任务实例对应的动作序列，所述动作序列中包含所述机器人待执行的多个动作。
在本公开的一些示例性实施例中，基于前述方案，根据所述机器人的动作序列确定与所述待执行任务实例对应关联的关键元素，包括：将所述机器人待执行的多个动作序列输入至预先训练好的元素处理模型中，输出与所述待执行任务实例对应关联的关键元素，其中，所述元素处理模型用于对所述机器人待执行的动作序列进行分析，提取与所述待执行任务实例对应关联的关键元素。
在本公开的一些示例性实施例中，基于前述方案，在根据所述第一关键元素与所述第一关联元素，确定所述机器人待执行任务实例的第一属性信息之前，所述方法还包括：获取所述机器人待执行任务实例中对应关联的所有元素的目标属性信息。
在本公开的一些示例性实施例中，基于前述方案，所述任务状态信息包括：正常状态以及非正常状态，根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息，包括：在所述机器人待执行任务实例的第一属性信息与所述目标属性信息一致的情况下，确定所述机器人待执行任务实例的任务状态信息为正常状态；在所述机器人待执行任务实例的第一属性信息与所述目标属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为非正常状态。
在本公开的一些示例性实施例中，基于前述方案，所述任务状态信息的非正常状态包括：中断状态或失败状态，在所述机器人待执行任务实例的第一属性信息与所述目标属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为非正常状态，包括：在所述机器人待执行任务实例的第一属性信息与所述目标属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为中断状态；当所述机器人待执行任务实例的任务状态信息为中断状态时，重复执行如下步骤，直到满足预设停止条件，确定所述机器人待执行任务实例的任务状态信息为失败状态，其中，所述预设停止条件为第二属性信息与目标属性信息不一致且所述预设停止条件为重复次数大于预设阈值；当所述机器人待执行任务实例的任务状态信息为中断状态时，确定所述机器人在中断状态时的中断位置；根据所述中断位置更新所述机器人待执行任务实例的任务信息；根据更新后的所述任务信息确定所述机器人更新后的动作序列；根据所述机器人更新后的动作序列，确定与更新后的所述待执行任务实例对应关联的第二关键元素；在所述本体知识库中查找出与所述第二关键元素具有关联关系的第二关联元素；根据所述第二关键元素与所述第二关联元素，确定所述机器人更新后的待执行任务实例的第二属性信息；判断所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息是否一致；若所述机器人更新后的待执行任 务实例的第二属性信息与所述目标属性信息一致，则确定所述机器人更新后的待执行任务实例的任务状态信息为正常状态；若所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息不一致，重新确定所述机器人在中断状态时的中断位置，将所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息进行比对，得到比对结果。
在本公开的一些示例性实施例中，基于前述方案，在根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息之后，所述方法还包括：在所述机器人待执行任务实例的任务状态信息为正常状态的情况下，生成第一监测指令，所述第一监测指令用于继续监测所述机器人待执行任务实例的第一属性信息；在所述机器人待执行任务实例的任务状态信息为中断状态的情况下，生成第二监测指令，所述第二监测指令用于监测所述机器人更新后的待执行任务实例的第二属性信息。
根据本公开的另一个方面，还提供了一种机器人任务状态监测装置，该装置包括：任务信息获取模块，设置为获取所述机器人待执行任务实例的任务信息；动作序列处理模块，设置为对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列；关键元素确定模块，设置为根据所述机器人的动作序列确定与所述待执行任务实例对应关联的第一关键元素；关联元素确定模块，设置为在预先建立的本体知识库中查找出与所述关键元素具有关联关系的关联元素，所述本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的第一关联元素；属性信息确定模块，设置为根据所述第一关键元素与所述第一关联元素，确定所述机器人待执行任务实例的第一属性信息；任务状态确定模块，设置为根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息。
根据本公开的再一个方面，还提供了一种电子设备，包括：处理器；以及存储器，用于存储所述处理器的可执行指令；其中，所述处理器配置为经由执行所述可执行指令来执行上述任意一种机器人任务状态监测方法。
根据本公开的又一个方面，还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述任意一种机器人任务状态监测方法。
根据本公开的另一个方面，还提供了一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现上述任意一项的机器人任务状态监测方法。
本公开的实施例中提供的机器人任务状态监测方法、装置以及相关设备，首先，获取机器人待执行任务实例的任务信息；其次，对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列；然后，根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素；之后，在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素；然后，根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息；最后，根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
相较于相关技术中机器人在实际任务执行过程中，由于环境突然发生变化，不能及时 监测到任务状态中的元素属性发生的变化，导致机器人不能及时调整任务状态，本公开实施例通过监测机器人在执行任务中的属性信息，并根据第一关键元素以及与机器人待执行任务实例具有关联关系的第一关联元素，来确定机器人待执行任务实例的属性信息，通过实时监测机器人待执行任务实例的属性信息，确定机器人待执行任务实例的任务状态信息，以便及时修正和完善任务执行决策，改善任务执行中遇到的智能性、实时性和任务完整性不足的缺陷，让在智能空间中的智能服务机器人在执行任务时更高效，更智能。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出本公开实施例中一种应用机器人任务状态监测方法的系统架构示意图；
图2示出本公开实施例中一种机器人任务状态监测方法示意图；
图3示出本公开实施例中一种获得与待执行任务实例对应关联的关键元素的方法示意图；
图4示出本公开实施例中一种机器人任务状态监测系统流程示意图；
图5示出本公开实施例中一种根据任务状态信息调整任务规划示意图；
图6示出本公开实施例中一种机器人任务状态监测装置示意图；
图7示出本公开实施例中一种应用机器人任务状态监测方法的电子设备示意图。
具体实施方式
现在将参考附图更全面地描述示例实施方式。然而，示例实施方式能够以多种形式实施，且不应被理解为限于在此阐述的范例；相反，提供这些实施方式使得本公开将更加全面和完整，并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。
此外，所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施例中。在下面的描述中，提供许多具体细节从而给出对本公开的实施例的充分理解。然而，本领域技术人员将意识到，可以实践本公开的技术方案而没有特定细节中的一个或更多，或者可以采用其它的方法、组元、装置、步骤等。在其它情况下，不详细示出或描述公知方法、装置、实现或者操作以避免模糊本公开的各方面。
附图中所示的流程图仅是示例性说明，不是必须包括所有的内容和操作/步骤，也 不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解，而有的操作/步骤可以合并或部分合并，因此实际执行的顺序有可能根据实际情况改变。
图1示出了可以应用本公开实施例中机器人任务状态监测方法的示例性应用系统架构示意图。如图1所示，该系统架构可以包括监测设备101、网络102和机器人103。
网络102用以在监测设备101和机器人103之间提供通信链路的介质，可以是有线网络，也可以是无线网络。
可选地，上述的无线网络或有线网络使用标准通信技术和/或协议。网络通常为因特网、但也可以是任何网络，包括但不限于局域网(Local Area Network，LAN)、城域网(Metropolitan Area Network，MAN)、广域网(Wide Area Network，WAN)、移动、有线或者无线网络、专用网络或者虚拟专用网络的任何组合)。在一些实施例中，使用包括超文本标记语言(Hyper Text Mark-up Language，HTML)、可扩展标记语言(Extensible MarkupLanguage，XML)等的技术和/或格式来代表通过网络交换的数据。此外还可以使用诸如安全套接字层(Secure Socket Layer，SSL)、传输层安全(Transport Layer Security，TLS)、虚拟专用网络(Virtual Private Network，VPN)、网际协议安全(Internet ProtocolSecurity，IPsec)等常规加密技术来加密所有或者一些链路。在另一些实施例中，还可以使用定制和/或专用数据通信技术取代或者补充上述数据通信技术。
监测设备101可以是各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机、台式计算机、可穿戴设备、增强现实设备、虚拟现实设备等。
可选地，不同的监测设备101中安装的应用程序的客户端是相同的，或基于不同操作系统的同一类型应用程序的客户端。基于终端平台的不同，该应用程序的客户端的具体形态也可以不同，比如，该应用程序客户端可以是手机客户端、PC客户端等。
机器人103可以是提供各种服务的机器人，例如对用户利用监测设备101所进行操作的装置提供支持的后台管理机器人。后台管理机器人可以对接收到的请求等数据进行分析等处理，并将处理结果反馈给监测设备。
可选地，机器人可以是独立的物理机器人，也可以是多个物理机器人构成的机器人集群或者分布式系统，还可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、CDN(Content Delivery Network，内容分发网络)、以及大数据和人工智能平台等基础云计算服务的云服务器。监测设备可以是智能手机、平板电脑、笔记本电脑、台式计算机、智能音箱、智能手表等，但并不局限于此。监测设备以及机器人可以通过有线或无线通信方式进行直接或间接地连接，本申请在此不做限制。
本领域技术人员可以知晓，图1中的监测设备101、网络102和机器人103的数量仅仅是示意性的，根据实际需要，可以具有任意数目的监测设备、网络和机器人。本公开实施例对此不作限定。
在上述系统架构下，本公开实施例中提供了一种机器人任务状态监测方法，该方 法可以由任意具备计算处理能力的电子设备执行。
在一些实施例中，本公开实施例中提供的机器人任务状态监测方法可以由上述系统架构的监测设备执行；在另一些实施例中，本公开实施例中提供的机器人任务状态监测方法可以由上述系统架构中的机器人执行；在另一些实施例中，本公开实施例中提供的机器人任务状态监测方法可以由上述系统架构中的监测设备和机器人通过交互的方式来实现。
下面，将结合附图及实施例对本示例实施方式中的机器人任务状态监测方法的各个步骤进行更详细的说明。
首先，本公开实施例中提供了一种可以应用但不限于在智能空间中对机器人的任务状态进行监测的控制方法，其中，在相关技术中机器人在实际任务执行过程中，由于智能空间中元素繁多，环境复杂多变，因此任务执行状态不止取决于机器人与目标物品本身状态，还会受诸多因素影响，特别是来自环境的突发情况等，而本申请下述方法，可以有效避免相关技术中在任务执行环境发生变化时不能及时监测出任务中的元素属性发生的变化的问题。
图2示出本公开实施例中一种机器人任务状态监测方法示意图，如图2所示，本公开实施例中提供的机器人任务状态监测方法，该方法包括如下步骤：
S201，获取机器人待执行任务实例的任务信息。
在一些实施例中，本公开实施例中的获取的机器人待执行任务实例的任务信息可以是从用户端接收任务指令，然后，根据接收任务指令通过查询知识库中当前任务实例定义的相关静态知识生成的任务信息，其中，静态知识通过常识知识和任务背景构建，用于描述抽象类别、固有属性和类别间关系等概念及概念间关系，例如，机器人待执行任务实例的任务信息为“从厨房拿杯水”。
S202，对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列。
在一些实施例中，本公开实施例中的机器人从用户端接收到的任务指令，并通过查询知识库中当前任务实例定义的相关静态知识生成的任务信息，本公开实施例对生成的任务信息进行处理，从而获得机器人的动作序列，例如，对任务信息“从厨房拿杯水”进行处理，获得动作序列“穿过客厅”，“穿过走廊”，“找到放水杯的桌子”等等。
S203，根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素。
需要说明的是，本公开实施例中的第一关键元素可以是任意动作序列中的名词，例如，根据动作序列“穿过客厅”，“穿过走廊”，“达到厨房”，“找到放水杯的桌子”等，确定“客厅”、“走廊”、“厨房”、“桌子”、“水杯”等与待执行任务实例对应关联的第一关键元素。
S204，在预先建立的本体知识库中查找出与关键元素具有关联关系的第一关联元 素，本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素。
在一些实施例中，本公开实施例通过将机器人获得任务信息进行处理，从而获得与待执行任务实例对应关联的第一关键元素，而影响任务执行的除了第一关键元素之外，在空间环境中，其余与关键元素相关联的共生元素也会对任务执行造成影响，因此，本公开实施例再将获取的第一关键元素与预先建立的，包括多个关键元素以及与每个关键元素具有关联关系的关联元素的本体知识库进行匹配，从而确定与第一关键元素具有关联关系的第一关联元素，例如，走廊是否有障碍物阻碍机器人继续执行任务实例，书房的门的开关状态可影响机器人的活动范围，书桌上的物品可影响水杯的拿取等，因此，确定与第一关键元素具有关联关系的第一关联元素为走廊的“障碍物”，书房的“门”，书桌上的“物品”等。
S205，根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息。
在一些实施例中，本公开实施例中的第一属性信息可以是任意第一关键元素和/或任意第一关联元素的属性信息，具体地，本公开实施例可以将第一关键元素和第一关联元素输入至预先构建好的神经网络模型，输出关键元素关联元素的属性信息，例如，将走廊的“障碍物”，书房的“门”，书桌上的“物品”，输入值神经网络模型，确定走廊的障碍物是否阻碍机器人行进，书房的门的“开关状态”，书桌上的物品是否阻碍水杯等。
S206，根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
在一些实施例中，由于智能空间中元素繁多，环境复杂多变，为保障任务的执行，需要对机器人待执行任务实例的第一属性信息进行实时监测，以便在机器人待执行任务实例的第一属性信息发生变化时，对任务执行进行变更或优化，例如，确定书房的门的是关闭的状态，又或者是在机器人行进导航过程中出现障碍物时，则需要变更导航路线，如果在任务执行过程中，杯子被突然碰到地上摔碎，则可以停止任务。
本公开实施例中的机器人任务状态监测方法，首先，获取机器人待执行任务实例的任务信息；其次，对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列；然后，根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素；之后，在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素；然后，根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息；最后，根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
相较于相关技术中机器人在实际任务执行过程中，由于环境突然发生变化，不能及时监测到任务状态中的元素属性发生的变化，导致机器人不能及时调整任务状态，本公开实施例通过监测机器人在执行任务中的属性信息，并根据第一关键元素以及与 机器人待执行任务实例具有关联关系的第一关联元素，来确定机器人待执行任务实例的属性信息，通过实时监测机器人待执行任务实例的属性信息，确定机器人待执行任务实例的任务状态信息，以便及时修正和完善任务执行决策，改善任务执行中遇到的智能性、实时性和任务完整性不足的缺陷，让在智能空间中的智能服务机器人在执行任务时更高效，更智能。
在一些实施例中，如图3所示，本公开实施例获取第一关键元素的方法，包括如下步骤：
S301，根据待执行任务实例的任务信息，生成待执行任务实例对应的动作序列，动作序列中包含机器人待执行的多个动作；
S302，将机器人待执行的多个动作序列输入至预先训练好的元素处理模型中，输出与待执行任务实例对应关联的关键元素，其中，元素处理模型用于对机器人待执行的动作序列进行分析，提取与待执行任务实例对应关联的第一关键元素。
在一些实施例中，本公开实施例中的第一关键元素是机器人执行任务过程中可能碰到的一些空间元素，具体地，本公开实施例可以根据预先构建好的动作提取模型，将待执行任务实例的任务信息进行拆解，得到待执行任务实例对应的动作序列，举例来说，本公开实施例中的待执行任务实例对应的动作序列可以为：从客厅出发，穿过走廊，进入书房，在书桌上拿上水杯，返回客厅，根据上述动作序列，并将上述机器人的动作序列输入至预先训练好的元素处理模型中，输出与待执行任务实例对应关联的关键元素，获得与待执行任务实例对应关联的关键元素“客厅”、“走廊”、“书桌”以及“水杯”。
在一些实施例中，根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素，包括：将机器人待执行的多个动作序列输入至预先训练好的元素处理模型中，输出与待执行任务实例对应关联的关键元素，其中，元素处理模型用于对机器人待执行的动作序列进行分析，提取与待执行任务实例对应关联的第一关键元素。
更为详细地，本公开实施例中的元素处理模型可以但不限于是语义模型，本公开实施例以语义模型为例，将待执行任务实例对应的动作序列结合动作提取模型，进而提取出符合待执行任务实例涉及的第一关键元素，例如，将动作序列：从客厅出发，穿过走廊，进入书房，在书桌上拿上水杯，返回客厅，输入至预先训练好的语义模型中，结合语义，提取出上述动作序列中符合机器人待执行任务实例涉及的关键元素“客厅”、“走廊”、“书桌”以及“水杯”。
在一些实施例中，在根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息之前，本公开实施例中的机器人任务状态监测方法还包括：获取机器人待执行任务实例中对应关联的所有元素的目标属性信息。
在一些实施例中，本公开实施例中的机器人任务状态监测方法可以通过预先构建好的任务监测模型完成，如图4所示，任务监测模型包括：任务监测管理层、关键元 素提取层、关联元素分析层、关联属性提取层以及关联属性监测层，具体地，本公开实施例在获取任务信息之后将的创建任务实例输出至任务监测管理层进行监测管理，其中，任务监测管理层主要进行当前任务实例的跟踪监控及管理，包括将任务实例拆解为动作序列，绑定与该任务实例相关的元素属性，进行元素属性评估，当元素属性发生变化时能实时更新任务状态等。
具体地，本公开实施例中的任务监测管理层接收任务实例，并将任务初步拆解为动作序列；关键元素提取层根据任务动作序列，结合当前空间的元素处理模型(例如，语义模型)，提取完成该任务实例所涉及的第一关键元素；关联元素分析层会基于第一关键元素并结合当前空间的本体知识库，提取与任务实例具有关联关系的第一关联元素；而关联属性提取层则会基于输入的第一关键元和第一关联元素确定机器人待执行任务实例的第一属性信息；关联属性提取层向关联属性监测层输出机器人待执行任务实例的第一属性信息，完成对该机器人待执行任务实例的第一属性信息的监测；关联属性提取层向任务监测管理层输出机器人待执行任务实例的第一属性信息，完成任务实例与众元素动作属信息的绑定；关联属性监测层将机器人待执行任务实例的第一属性信息的监测结果输出至任务监测管理层；任务监测管理层根据当前机器人待执行任务实例的第一属性信息判断机器人待执行任务实例的任务状态信息。
在一些实施例中，本公实施例将机器人待执行任务实例的任务信息进行拆解，得到动作序列，并通过该任务实例中涉及的第一关键元素，获得与每个第一关键元素具有关联关系的第一关联元素，并将可以完成该任务实例的第一属性信息记为目标属性信息，例如，本公开实施例可以将书房的门在开启状态记为目标属性信息等。
在一些实施例中，本公开实施例中的任务状态信息包括：正常状态以及非正常状态，根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息，包括：在机器人待执行任务实例的第一属性信息与目标属性信息一致的情况下，确定机器人待执行任务实例的任务状态信息为正常状态；在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为非正常状态。
在一些实施例中，本公开实施例将确定出的机器人待执行任务实例的第一属性信息与目标属性信息做比对，判断获取到的机器人待执行任务实例的第一属性信息是否能够完成机器人待执行任务实例，若机器人待执行任务实例的第一属性信息与目标属性信息不一致，则确定机器人待执行任务实例中的元素属性发生的变化，不能完成该任务实例，确定机器人待执行任务实例的任务状态信息为非正常状态，后续能够根据待执行任务实例的任务状态信息及时调整任务规划。
需要说明的是，本公开实施例中的目标属性信息是根据机器人的动作序列确定出的关键元素与在本体知识库中查找出的对应关联元素生成一个预先设置的范围，例如，根据上述关键元素“书房”和关联元素“门”，生成一个“在机器人能够通过书房时， 门打开的角度范围(45°～90°)”的范围”，将现场采集到的机器人待执行任务实例的第一属性信息与上述目标属性信息进行比较，若现场采集到的机器人待执行任务实例的第一属性信息处于该目标属性信息的范围内，则确定机器人能够正常完成待执行任务实例，若现场采集到的机器人待执行任务实例的第一属性信息不处于该目标属性信息的范围内，则确定机器人不能正常完成待执行任务实例，例如，现场采集到的机器人待执行任务实例的第一属性信息是“门打开角度为0(门是关闭的)”，第一属性信息(0°)并不在45°～90°之间，机器人不能正常完成待执行任务实例。
在一些实施例中，本公开实施例中任务状态信息的非正常状态包括：中断状态以及失败状态，在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为非正常状态，包括：在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为中断状态；当机器人待执行任务实例的任务状态信息为中断状态时，重复执行如下步骤，直到满足预设停止条件，确定机器人待执行任务实例的任务状态信息为失败状态，其中，预设停止条件为第二属性信息与目标属性信息不一致且预设停止条件为重复次数大于预设阈值；当机器人待执行任务实例的任务状态信息为中断状态时，确定机器人在中断状态时的中断位置；根据中断位置更新机器人待执行任务实例的任务信息；根据更新后的任务信息确定机器人更新后的动作序列；根据机器人更新后的动作序列，确定与更新后的待执行任务实例对应关联的第二关键元素；在本体知识库中查找出与第二关键元素具有关联关系的第二关联元素；根据第二关键元素与第二关联元素，确定机器人更新后的待执行任务实例的第二属性信息；判断机器人更新后的待执行任务实例的第二属性信息与目标属性信息是否一致；若机器人更新后的待执行任务实例的第二属性信息与目标属性信息一致，则确定机器人更新后的待执行任务实例的任务状态信息为正常状态；若机器人更新后的待执行任务实例的第二属性信息与目标属性信息不一致，重新确定机器人在中断状态时的中断位置，将机器人更新后的待执行任务实例的第二属性信息与目标属性信息进行比对，得到比对结果。
更为详细地，若本公开实施例中的机器人待执行任务实例的第一属性信息与目标属性信息不一致，则说明机器人不能正常完成待执行的任务实例，因此，在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为中断状态，并确定在中断状态时机器人的中断位置，并在中断位置重新确定机器人待执行任务实例的任务信息，根据更新后的任务信息来更新机器人的动作序列，重新根据更新后的工作序列确定第二关键元素和第二关联元素，并根据更新后的第二关键元素和第二关联元素确定更新后的待执行任务实例的第二属性信息，判断第二属性信息与目标属性信息是否一致，若更新后的机器人待执行任务实例的第二属性信息与目标属性信息一致，则确定机器人更新后的待执行任务实例的 任务状态信息为正常状态，继续执行任务实例；若更新后的机器人待执行任务实例的第二属性信息与目标属性信息不一致，则重复确定机器人在中断状态时的中断位置，将机器人更新后的待执行任务实例的第二属性信息与目标属性信息进行比对，得到比对结果，若第二属性信息与目标属性信息不一致且重复次数大于预设阈值，则确定机器人待执行任务实例的任务状态信息为失败状态。
在一些实施例中，在根据关联元素的状态属性信息，确定机器人待执行任务实例的任务状态信息之后，该方法还包括：在机器人待执行任务实例的任务状态信息为正常状态的情况下，生成第一监测指令，第一监测指令用于继续监测关联元素的状态属性信息；在机器人待执行任务实例的任务状态信息为中断状态的情况下，生成第二监测指令，第二监测指令用于监测机器人更新后的待执行任务实例的第二属性信息。
更为具体地，如图5所示，本公开实施例中的任务状态信息包括正常状态、中断状态以及失败状态，若监测到的任务状态信息为正常状态，则机器人将继续执行任务实例；若监测到的任务状态信息为中断状态，机器人会先暂停执行上述任务实例，重新规划任务的动作序列并发出请求恢复继续执行上述任务实例，若重复次数在预设阈值内判断更新后的第二属性信息与目标属性信息一致，就可以确定重新规划任务的动作序列可以正常执行任务，则机器人根据重新规划出的动作序列继续执行任务，并对更新后的待执行任务实例的第二属性信息进行实时监测，若请求恢复的次数超过预设阈值，则确定任务状态信息为失败状态；若监测到的任务状态信息为失败状态，则将机器人待执行任务实例中对应关联的所有元素与其对应的目标属性信息进行解绑，并释放监测资源，控制机器人停止执行该任务实例。
基于同一发明构思，本公开实施例中还提供了一种机器人任务状态监测装置，如下面的实施例。由于该装置实施例解决问题的原理与上述方法实施例相似，因此该装置实施例的实施可以参见上述方法实施例的实施，重复之处不再赘述。
图6示出本公开实施例中一种机器人任务状态监测装置示意图，如图6所示，该装置包括：
任务信息获取模块601，用于获取机器人待执行任务实例的任务信息；
动作序列处理模块602，用于对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列；
关键元素确定模块603，用于根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素；
关联元素确定模块604，用于在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素，本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素；
属性信息确定模块605，用于根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息；
任务状态确定模块606，用于根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
本公开的实施例中提供的机器人任务状态监测装置，通过任务信息获取模块，获取机器人待执行任务实例的任务信息；通过动作序列处理模块，对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列；通过关键元素确定模块，根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素；通过关联元素确定模块，在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素；通过属性信息确定模块，根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息；通过任务状态确定模块，根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
相较于相关技术中机器人在实际任务执行过程中，由于环境突然发生变化，不能及时监测到任务状态中的元素属性发生的变化，导致机器人不能及时调整任务状态，本公开实施例通过监测机器人在执行任务中的属性信息，并根据第一关键元素以及与机器人待执行任务实例具有关联关系的第一关联元素，来确定机器人待执行任务实例的属性信息，通过实时监测机器人待执行任务实例的属性信息，确定机器人待执行任务实例的任务状态信息，以便及时修正和完善任务执行决策，改善任务执行中遇到的智能性、实时性和任务完整性不足的缺陷，让在智能空间中的智能服务机器人在执行任务时更高效，更智能。
在一些实施例中，本公开实施例中的动作序列处理模块还用于根据待执行任务实例的任务信息，生成待执行任务实例对应的动作序列，动作序列中包含机器人待执行的多个动作。
在一些实施例中，本公开实施例中的关关键元素确定模块还用于将机器人待执行的多个动作序列输入至预先训练好的元素处理模型中，输出与待执行任务实例对应关联的关键元素，其中，元素处理模型用于对机器人待执行的动作序列进行分析，提取与待执行任务实例对应关联的第一关键元素。
在一些实施例中，本公开实施例中的机器人任务状态监测装置在根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息之前，还包括：目标属性信息获取模块，设置为获取机器人待执行任务实例中对应关联的所有元素的目标属性信息。
在一些实施例中，本公开实施例中的任务状态信息包括：正常状态以及非正常状态，上述任务状态确定模块还用于在机器人待执行任务实例的第一属性信息与目标属性信息一致的情况下，确定机器人待执行任务实例的任务状态信息为正常状态；在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为非正常状态。
在一些实施例中，本公开实施例中的任务状态信息的非正常状态包括：中断状态 以及失败状态，上述任务状态确定模块还用于在机器人待执行任务实例的第一属性信息与目标属性信息不一致的情况下，确定机器人待执行任务实例的任务状态信息为中断状态；当机器人待执行任务实例的任务状态信息为中断状态时，重复执行如下步骤，直到满足预设停止条件，确定机器人待执行任务实例的任务状态信息为失败状态，其中，预设停止条件为第二属性信息与目标属性信息不一致且预设停止条件为重复次数大于预设阈值；当机器人待执行任务实例的任务状态信息为中断状态时，确定机器人在中断状态时的中断位置；根据中断位置更新机器人待执行任务实例的任务信息；根据更新后的任务信息确定机器人更新后的动作序列；根据机器人更新后的动作序列，确定与更新后的待执行任务实例对应关联的第二关键元素；在本体知识库中查找出与第二关键元素具有关联关系的第二关联元素；根据第二关键元素与第二关联元素，确定机器人更新后的待执行任务实例的第二属性信息；判断机器人更新后的待执行任务实例的第二属性信息与目标属性信息是否一致；若机器人更新后的待执行任务实例的第二属性信息与目标属性信息一致，则确定机器人更新后的待执行任务实例的任务状态信息为正常状态；若机器人更新后的待执行任务实例的第二属性信息与目标属性信息不一致，重新确定机器人在中断状态时的中断位置，将机器人更新后的待执行任务实例的第二属性信息与目标属性信息进行比对，得到比对结果。
在一些实施例中，本公开实施例中在根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息之后，该装置还包括：第一监测模块，设置为在机器人待执行任务实例的任务状态信息为正常状态的情况下，生成第一监测指令，第一监测指令用于继续监测机器人待执行任务实例的第一属性信息；第二监测模块，设置为在机器人待执行任务实例的任务状态信息为中断状态的情况下，生成第二监测指令，第二监测指令用于监测机器人更新后的待执行任务实例的第二属性信息。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述方法实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以在诸如一组计算机可执行指令的计算机系统中执行。
所属技术领域的技术人员能够理解，本公开的各个方面可以实现为系统、方法或程序产品。因此，本公开的各个方面可以具体实现为以下形式，即：完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等)，或硬件和软件方面结合的实施方式，这里可以统称为“电路”、“模块”或“系统”。
下面参照图7来描述根据本公开的这种实施方式的电子设备700。图7显示的电子设备700仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图7所示，电子设备700以通用计算设备的形式表现。电子设备700的组件可以包括但不限于：上述至少一个处理单元701、上述至少一个存储单元702、连接不同系统组件(包括存储单元702和处理单元701)的总线703。
其中，存储单元存储有程序代码，程序代码可以被处理单元701执行，使得处理 单元701执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。
在一些实施例中，当电子设备用于控制例如本公开上述基于知识图谱的问答方法时，处理单元701可以执行上述方法实施例的如下步骤：
获取机器人待执行任务实例的任务信息。
对待执行任务实例的任务信息进行处理，根据任务信息确定机器人的动作序列。
根据机器人的动作序列确定与待执行任务实例对应关联的第一关键元素。
在预先建立的本体知识库中查找出与第一关键元素具有关联关系的第一关联元素，本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素。
根据第一关键元素与第一关联元素，确定机器人待执行任务实例的第一属性信息。
根据机器人待执行任务实例的第一属性信息，确定机器人待执行任务实例的任务状态信息。
存储单元702可以包括易失性存储单元形式的可读介质，例如随机存取存储单元(RAM)7021和/或高速缓存存储单元7022，还可以进一步包括只读存储单元(ROM)7023。
存储单元702还可以包括具有一组(至少一个)程序模块7025的程序/实用工具7024，这样的程序模块7025包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。
总线703可以为表示几类总线结构中的一种或多种，包括存储单元总线或者存储单元控制器、外围总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
电子设备700也可以与一个或多个外部设备704(例如键盘、指向设备、蓝牙设备等)通信，还可与一个或者多个使得用户能与该电子设备700交互的设备通信，和/或与使得该电子设备700能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口705进行。并且，电子设备700还可以通过网络适配器706与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器706通过总线703与电子设备700的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备700使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
通过以上的实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在 一个非易失性存储介质(可以是CD-ROM，U盘，移动硬盘等)中或网络上，包括若干指令以使得一台计算设备(可以是个人计算机、服务器、终端装置、或者网络设备等)执行根据本公开实施方式的方法。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机程序产品，该计算机程序产品包括：计算机程序，计算机程序被处理器执行时实现上述机器人任务状态监测方法。
在本公开的示例性实施例中，还提供了一种计算机可读存储介质，该计算机可读存储介质可以是可读信号介质或者可读存储介质。其上存储有能够实现本公开上述方法的程序产品。在一些可能的实施方式中，本公开的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当程序产品在监测设备上运行时，程序代码用于使监测设备执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。
本公开中的计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
在本公开中，计算机可读存储介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
可选地，计算机可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。
在具体实施时，可以以一种或多种程序设计语言的任意组合来编写用于执行本公开操作的程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
应当注意，尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元，但是这种划分并非强制性的。实际上，根据本公开的实施方式，上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之，上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体 化。
此外，尽管在附图中以特定顺序描述了本公开中方法的各个步骤，但是，这并非要求或者暗示必须按照该特定顺序来执行这些步骤，或是必须执行全部所示的步骤才能实现期望的结果。附加的或备选的，可以省略某些步骤，将多个步骤合并为一个步骤执行，以及/或者将一个步骤分解为多个步骤执行等。
通过以上实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM，U盘，移动硬盘等)中或网络上，包括若干指令以使得一台计算设备(可以是个人计算机、服务器、移动终端、或者网络设备等)执行根据本公开实施方式的方法。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由所附的权利要求指出。

Claims (11)

  1. 一种机器人任务状态监测方法，包括：
    获取所述机器人待执行任务实例的任务信息；
    对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列；
    根据所述机器人的动作序列确定与所述待执行任务实例对应关联的第一关键元素；
    在预先建立的本体知识库中查找出与所述第一关键元素具有关联关系的第一关联元素，所述本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素；
    根据所述第一关键元素与所述第一关联元素，确定所述机器人待执行任务实例的第一属性信息；
    根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息。
  2. 根据权利要求1所述的机器人任务状态监测方法，对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列，包括：
    根据所述待执行任务实例的任务信息，生成所述待执行任务实例对应的动作序列，所述动作序列中包含所述机器人待执行的多个动作。
  3. 根据权利要求1所述的机器人任务状态监测方法，根据所述机器人的动作序列确定与所述待执行任务实例对应关联的第一关键元素，包括：
    将所述机器人待执行的多个动作序列输入至预先训练好的元素处理模型中，输出与所述待执行任务实例对应关联的关键元素，其中，所述元素处理模型用于对所述机器人待执行的动作序列进行分析，提取与所述待执行任务实例对应关联的第一关键元素。
  4. 根据权利要求1所述的机器人任务状态监测方法，在根据所述第一关键元素与所述第一关联元素，确定所述机器人待执行任务实例的第一属性信息之前，所述方法还包括：
    获取所述机器人待执行任务实例中对应关联的所有元素的目标属性信息。
  5. 根据权利要求4所述的机器人任务状态监测方法，所述任务状态信息包括：正常状态以及非正常状态，根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息，包括：
    在所述机器人待执行任务实例的第一属性信息与所述目标属性信息一致的情况下，确定所述机器人待执行任务实例的任务状态信息为正常状态；
    在所述机器人待执行任务实例的第一属性信息与所述目标属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为非正常状态。
  6. 根据权利要求5所述的机器人任务状态监测方法，所述任务状态信息的非正常状态包括：中断状态或失败状态，在所述机器人待执行任务实例的第一属性信息与所述目标 属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为非正常状态，包括：
    在所述机器人待执行任务实例的第一属性信息与所述目标属性信息不一致的情况下，确定所述机器人待执行任务实例的任务状态信息为中断状态；
    当所述机器人待执行任务实例的任务状态信息为中断状态时，重复执行如下步骤，直到满足预设停止条件，确定所述机器人待执行任务实例的任务状态信息为失败状态，其中，所述预设停止条件为第二属性信息与目标属性信息不一致且所述预设停止条件为重复次数大于预设阈值；
    当所述机器人待执行任务实例的任务状态信息为中断状态时，确定所述机器人在中断状态时的中断位置；
    根据所述中断位置更新所述机器人待执行任务实例的任务信息；
    根据更新后的所述任务信息确定所述机器人更新后的动作序列；
    根据所述机器人更新后的动作序列，确定与更新后的所述待执行任务实例对应关联的第二关键元素；
    在所述本体知识库中查找出与所述第二关键元素具有关联关系的第二关联元素；
    根据所述第二关键元素与所述第二关联元素，确定所述机器人更新后的待执行任务实例的第二属性信息；
    判断所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息是否一致；
    若所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息一致，则确定所述机器人更新后的待执行任务实例的任务状态信息为正常状态；
    若所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息不一致，重新确定所述机器人在中断状态时的中断位置，将所述机器人更新后的待执行任务实例的第二属性信息与所述目标属性信息进行比对，得到比对结果。
  7. 根据权利要求6所述的机器人任务状态监测方法，在根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息之后，所述方法还包括：
    在所述机器人待执行任务实例的任务状态信息为正常状态的情况下，生成第一监测指令，所述第一监测指令用于继续监测所述机器人待执行任务实例的第一属性信息；
    在所述机器人待执行任务实例的任务状态信息为中断状态的情况下，生成第二监测指令，所述第二监测指令用于监测所述机器人更新后的待执行任务实例的第二属性信息。
  8. 一种机器人任务状态监测装置，包括：
    任务信息获取模块，设置为获取所述机器人待执行任务实例的任务信息；
    动作序列处理模块，设置为对所述待执行任务实例的任务信息进行处理，根据所述任务信息确定所述机器人的动作序列；
    关键元素确定模块，设置为根据所述机器人的动作序列确定与所述待执行任务实例对应关联的第一关键元素；
    关联元素确定模块，设置为在预先建立的本体知识库中查找出与所述关键元素具有关联关系的关联元素，所述本体知识库包含：多个关键元素以及与每个关键元素具有关联关系的关联元素；
    属性信息确定模块，设置为根据所述第一关键元素与所述第一关联元素，确定所述机器人待执行任务实例的第一属性信息；
    任务状态确定模块，设置为根据所述机器人待执行任务实例的第一属性信息，确定所述机器人待执行任务实例的任务状态信息。
  9. 一种电子设备，包括：
    处理器；以及
    存储器，用于存储所述处理器的可执行指令；
    其中，所述处理器配置为经由执行所述可执行指令来执行权利要求1～7中任意一项所述的机器人任务状态监测方法。
  10. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1～7中任意一项所述的机器人任务状态监测方法。
  11. 一种计算机程序产品，包括计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1～7任意一项所述的机器人任务状态监测方法。
PCT/CN2023/140529 2023-08-14 2023-12-21 机器人任务状态监测方法、装置以及相关设备 Pending WO2025035676A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202311021508.5A CN117021088B (zh) 2023-08-14 2023-08-14 机器人任务状态监测方法、装置以及相关设备
CN202311021508.5 2023-08-14

Publications (1)

Publication Number Publication Date
WO2025035676A1 true WO2025035676A1 (zh) 2025-02-20

Family

ID=88634973

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/140529 Pending WO2025035676A1 (zh) 2023-08-14 2023-12-21 机器人任务状态监测方法、装置以及相关设备

Country Status (2)

Country Link
CN (1) CN117021088B (zh)
WO (1) WO2025035676A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117021088B (zh) * 2023-08-14 2025-01-03 中国电信股份有限公司技术创新中心 机器人任务状态监测方法、装置以及相关设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012115913A (ja) * 2010-11-29 2012-06-21 Toyota Motor Corp ロボットによるサービス提供システム、ロボット管理装置及びロボット管理方法
CN109202882A (zh) * 2017-06-29 2019-01-15 深圳模德宝科技有限公司 一种机器人的控制方法及其装置
CN113190012A (zh) * 2021-05-10 2021-07-30 山东大学 一种机器人任务自主规划方法及系统
CN113821648A (zh) * 2021-11-23 2021-12-21 中国科学院自动化研究所 基于本体知识表示的机器人任务处理方法及系统
CN114201594A (zh) * 2021-12-10 2022-03-18 深圳大学 基于参数表达知识库的机器人技能操作方法、终端及介质
CN116476063A (zh) * 2023-04-23 2023-07-25 深圳大学 一种机器人操作任务实例化方法及相关装置
CN117021088A (zh) * 2023-08-14 2023-11-10 中国电信股份有限公司技术创新中心 机器人任务状态监测方法、装置以及相关设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111745636B (zh) * 2019-05-15 2022-01-07 北京京东乾石科技有限公司 机器人控制方法及控制系统、存储介质及电子设备
CN117881506A (zh) * 2021-08-31 2024-04-12 西门子股份公司 机器人任务规划
US12157226B2 (en) * 2021-10-06 2024-12-03 Sanctuary Cognitive Systems Corporation Expedited robot teach-through initialization from previously trained system
CN116276952B (zh) * 2022-09-09 2026-04-10 武汉东湖大数据交易中心股份有限公司 一种机器人可解释性智能计算方法及其系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012115913A (ja) * 2010-11-29 2012-06-21 Toyota Motor Corp ロボットによるサービス提供システム、ロボット管理装置及びロボット管理方法
CN109202882A (zh) * 2017-06-29 2019-01-15 深圳模德宝科技有限公司 一种机器人的控制方法及其装置
CN113190012A (zh) * 2021-05-10 2021-07-30 山东大学 一种机器人任务自主规划方法及系统
CN113821648A (zh) * 2021-11-23 2021-12-21 中国科学院自动化研究所 基于本体知识表示的机器人任务处理方法及系统
CN114201594A (zh) * 2021-12-10 2022-03-18 深圳大学 基于参数表达知识库的机器人技能操作方法、终端及介质
CN116476063A (zh) * 2023-04-23 2023-07-25 深圳大学 一种机器人操作任务实例化方法及相关装置
CN117021088A (zh) * 2023-08-14 2023-11-10 中国电信股份有限公司技术创新中心 机器人任务状态监测方法、装置以及相关设备

Also Published As

Publication number Publication date
CN117021088B (zh) 2025-01-03
CN117021088A (zh) 2023-11-10

Similar Documents

Publication Publication Date Title
US10972954B2 (en) System for connection channel adaption using robotic automation
JP2024023311A (ja) 限られた知識ドメイン内でナレッジグラフを構築するための技術
CN111857794A (zh) 机器人可扩展性基础设施
CN104765621B (zh) 一种在集群节点中部署程序的方法和系统
JP2019536185A (ja) コンピュータおよびネットワーク活動を監視および分析するためのシステムおよび方法
CN108431793B (zh) 使用词汇表生成流分析应用
US20080010229A1 (en) Intelligent agent based development platform
EP4044173A2 (en) Method and apparatus for text to speech, electronic device and storage medium
US10248441B2 (en) Remote technology assistance through dynamic flows of visual and auditory instructions
CA2791743C (en) Private web browsing using encrytion
CN114881170B (zh) 用于对话任务的神经网络的训练方法和对话任务处理方法
CN111200595A (zh) 一种访问容器的权限管理方法、装置和电子设备
US11941414B2 (en) Unstructured extensions to rpa
US20260012539A1 (en) Communication Session Interruption and Dynamic Learning System
WO2025035676A1 (zh) 机器人任务状态监测方法、装置以及相关设备
US20250348578A1 (en) Integrated development environment extension for developing information technology and security operations application apps
CN117648386A (zh) 检测方法、装置、设备及存储介质
US20240296157A1 (en) Pre-fetch engine for mesh data network having date micro silos
CN113741887B (zh) 模型生产方法、系统、装置及电子设备
CN117950481A (zh) 交互信息生成方法、装置、系统、电子设备及介质
CN115396436B (zh) 服务访问方法、装置、电子设备及介质
US11811896B1 (en) Pre-fetch engine with security access controls for mesh data network
US12301761B1 (en) Intelligent routing signaling system
US12432192B2 (en) Combined mobile applications
US20240386311A1 (en) Self-evolving virtual twins

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23949092

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE