CN112235419A - Robot cloud platform execution engine and execution method based on behavior tree - Google Patents
Robot cloud platform execution engine and execution method based on behavior tree Download PDFInfo
- Publication number
- CN112235419A CN112235419A CN202011430124.5A CN202011430124A CN112235419A CN 112235419 A CN112235419 A CN 112235419A CN 202011430124 A CN202011430124 A CN 202011430124A CN 112235419 A CN112235419 A CN 112235419A
- Authority
- CN
- China
- Prior art keywords
- robot
- module
- behavior tree
- cloud platform
- execution engine
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1682—Dual arm manipulator; Coordination of several manipulators
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4633—Interconnection of networks using encapsulation techniques, e.g. tunneling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/146—Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
Abstract
The invention provides a robot cloud platform execution engine and an execution method based on a behavior tree, wherein the robot cloud platform execution engine comprises a server application cluster, a robot and a middleware, and the server application cluster consists of a plurality of server applications; the server application generates a robot instruction, the robot instruction is sent to the robot through the middleware, the robot analyzes the generated robot instruction to generate a behavior, and the execution result of the robot instruction is fed back to the server application through the middleware. The robot cloud platform execution engine has the characteristics of high intelligent degree, strong applicability, flexible work, convenience in access and low maintenance cost.
Description
Technical Field
The invention relates to the technical field of intelligent robots and cloud computing, in particular to a robot cloud platform execution engine and method based on a behavior tree.
Background
The intelligent robot technology is being applied to various scenes in life more and more, but most robots can only execute a single preset task, and another robot may be needed when changing a scene, for example, a navigation robot can only work in a certain venue, the action path and the navigation content are preset and cannot be changed, and the robot cannot be used when changing a venue. Moreover, the degree of intellectualization is low, appropriate behaviors cannot be made when special scenes are met, and targeted services cannot be provided when different service objects are met. Usually, a Finite State Machine (FSM) is used for robot decision making, but in the face of a complex scenario, the states of the robot are very many, the changing relationship between the states is very complex, a very large cost is required to be invested in development, and the reusability is poor, so that the robot-like development is difficult to reuse.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a robot cloud platform execution engine based on a behavior tree. The robot cloud platform execution engine adopts the behavior tree as a decision structure, combines the expansion capability and artificial intelligence of the cloud platform, and has the characteristics of low maintenance cost, flexible work, convenient access, high intelligence degree and the like.
In order to achieve the purpose, the invention adopts the following technical scheme: a behavior tree based robotic cloud platform execution engine, the robotic cloud platform execution engine comprising: the robot system comprises a server application cluster, a robot and a middleware, wherein the server application cluster consists of a plurality of server applications; the server application generates a robot instruction, the robot instruction is sent to the robot through the middleware, the robot analyzes the generated robot instruction to generate a behavior, and the execution result of the robot instruction is fed back to the server application through the middleware.
Further, the server application is divided into an infrastructure layer, a function module layer and an interaction layer.
Further, the infrastructure layer comprises a behavior tree module, a robot communication module and a session module, wherein the behavior tree module has functions of sequentially executing nodes, selecting executing nodes, parallelly executing nodes, conditional nodes and executing nodes; meanwhile, the behavior tree module is used for defining interfaces of specific condition logic and behavior logic; the robot communication module is used for packaging a receiving and sending mechanism based on MQTT messages and a message auditing function; the session module is used for packaging read-write logic functions of all state data in the robot session.
Furthermore, the function module layer comprises a behavior tree analysis module, an instruction distribution module, a session management module, a data source management module, an equipment control module and a scene configuration module; the behavior tree analysis module processes the generation of the behavior tree by adopting a behavior tree schema based on json; the instruction distribution module is used for processing communication between the server application and the robot; the session management module is responsible for state data maintenance in a scene, including the realization of a memory function based on redis; the scene configuration module is used for managing global parameters under each scene, and loading and storing the global parameters during operation through json file configuration; the data source management module adopts a monitor mode and is responsible for data input and output.
Further, the interaction layer comprises an API, a console and a client; the API is used for controlling the opening and closing of the scene session; the control console displays and monitors the execution condition of the robot cloud platform execution engine based on log collection and point burying; the client is used for providing basic development SDK and supporting python and c + + languages.
Further, the robot cloud platform execution engine controls and manages the camera and the large screen display through http and udp protocols.
The invention also provides an execution method of the robot cloud platform execution engine, which specifically comprises the following steps: when the robot cloud platform execution engine runs, an interaction layer receives a request, a session management module starts a session and generates a globally unique session id, and according to a requested scene, a scene configuration module loads prefabricated configuration parameters including the type of robots, the number of the robots, data sources to be monitored and environmental parameters; and the session id is used as a key, a corresponding data structure is saved and used, a behavior tree is generated according to scene configuration, and finally the control of the robot is realized by circularly executing the behavior tree.
Further, the method for generating the behavior tree specifically comprises the following steps: and the behavior tree analysis module generates a behavior tree according to the configuration file.
Further, the method for generating the behavior tree specifically comprises the following steps: and after receiving the task plan, the behavior tree analysis module analyzes the task plan to generate a behavior tree.
Compared with the prior art, the invention has the following beneficial effects: the invention reduces the maintenance cost and improves the flexibility through the behavior tree module. Firstly, the tree structure is very clear, each child node represents a child function module, and each leaf node represents a condition or a behavior; secondly, the behavior tree is very quick to respond to scene changes, different states can be executed by different behaviors through continuous cycle traversal, and different situations in the scene can be flexibly responded. And the behavior tree is easy to maintain, the subtree structure can be modularized and multiplexed, and the development cost is reduced.
The behavior tree is placed in the cloud end, and can act on a plurality of robots simultaneously, so that the cooperation capability among the robots is enhanced, and a better overall decision is made. In the execution process, the behavior tree can conveniently acquire the states and environmental data of all robots to carry out overall planning.
The invention comprises robot clients to facilitate access of different types of robots. The client supports multiple languages including the mainstream languages such as python, java, c + +, and the like. A set of SDK API is abstracted by the client, the robot only needs to realize the service logic of instruction receiving and sending, and does not need to pay attention to the realization and analysis of the communication protocol, so that the access cost is reduced.
In addition, the robot is connected with the cloud platform through the execution engine by applying a cloud computing technology, and the characteristics of strong computing capability and strong expansion capability of the cloud platform can be fully exerted. Through the data source management module, the execution engine can transmit the data collected by the robot to the cloud platform, and compared with the local computing capacity of the robot, the cloud platform is faster in execution and can provide faster response to control the robot. The cloud platform can load different scene information according to scenes, generate different behavior trees and complete different scene tasks. The cloud platform provides a stronger contextual model database, and an artificial intelligence technology is added, so that the task planning can be continuously learned and optimized, and the intelligent advantage is exerted. Through the updating of the server application, the robot control can be upgraded to adapt to and meet the new requirements in the scene.
Drawings
FIG. 1 is a structural deployment diagram of a behavior tree based robot cloud platform execution engine according to the present invention;
FIG. 2 is a system architecture diagram of a behavior tree based robot cloud platform execution engine according to the present invention;
fig. 3 is a flowchart of a control method of the robot cloud platform execution engine according to the present invention.
Detailed Description
As shown in fig. 1, the present invention provides a structural deployment diagram of a robot cloud platform execution engine based on a behavior tree, where the robot cloud platform execution engine includes: the robot system comprises a server application cluster, a robot and a middleware, wherein the server application cluster consists of a plurality of server applications; the server application generates a robot instruction, the robot instruction is sent to the robot through the middleware, the robot analyzes the generated robot instruction to generate a behavior, and the execution result of the robot instruction is fed back to the server application through the middleware. The server application can communicate with an algorithm knowledge base provided by the cloud platform through the middleware to acquire task planning and artificial intelligence services. Referring to fig. 2, which is a structural diagram of the behavior tree based robot cloud platform execution engine according to the present invention, it can be seen that the server application is divided into an infrastructure layer, a function module layer, and an interaction layer, where the infrastructure layer includes a behavior tree module, a robot communication module, and a session module, and the behavior tree module has functions of sequentially executing nodes, selecting execution nodes, concurrently executing nodes, conditional nodes, executing nodes, and the like. Meanwhile, the behavior tree module is used for defining interfaces of specific condition logic and behavior logic; the robot communication module is used for packaging a receiving and sending mechanism based on MQTT messages and a message auditing function; the session module is used for packaging read-write logic functions of all state data in the robot session.
The function module layer comprises a behavior tree analysis module, an instruction distribution module, a session management module, a data source management module, an equipment control module and a scene configuration module; the behavior tree analysis module processes the generation of the behavior tree by adopting a behavior tree schema based on json; through the configuration of the json file, the behavior tree analysis module can generate a behavior tree in the memory and circularly trigger execution. Meanwhile, the behavior tree analysis module also supports receiving task planning from an external system, and then adapts to the defined schema to generate the behavior tree. Based on the expansion mode, the advantages of a cloud platform can be fully used, algorithm modules such as a knowledge base and robot cooperation are integrated, and a more intelligent and flexible behavior tree is generated to control the robot and the robot cluster. The instruction distribution module is used for processing communication between the server application and the robot, on one hand, according to the specific logic of the execution node, generating an instruction sent to the robot, sending a message to the robot through a communication SDK packet, and simultaneously monitoring the message fed back by the robot. The session management module is responsible for state data maintenance in a scene, including the realization of a memory function based on redis; the scene configuration module is used for managing global parameters under each scene, and loading and storing the global parameters during operation through json file configuration; the data source management module adopts a monitor mode and is responsible for data input and output. Meanwhile, the robot cloud platform execution engine is used for controlling and managing equipment such as a camera, a large screen display and the like through http, udp and other protocols.
The interaction layer comprises an API, a console and a client; the API is used for controlling the opening and closing of the scene session; the control console displays and monitors the execution condition of the robot cloud platform execution engine based on log collection and point burying; the client is used for providing basic development SDK, supporting multiple languages such as python, c + + and the like, packaging a communication protocol applied by the server, and having the functions of message format, connection establishment, connection closing process, heartbeat connection and the like. The robot only needs to receive, analyze and send the instruction by using the function of the SDK.
As shown in fig. 3, a flowchart of an execution method of the robot cloud platform execution engine of the present invention is provided, and specifically includes: when the robot cloud platform execution engine runs, an interaction layer in the server application receives a request, and the session management module starts a session and generates a globally unique session id. According to the requested scene, the scene configuration module initializes the scene, loads the prefabricated configuration parameters including the type of the robot, the number of the robots, the data source to be monitored and the environmental parameters, and initializes the robot. And the session id is used as a key, and a corresponding data structure is saved and used. According to the scene configuration, an algorithm knowledge base provided by the cloud platform is called, the algorithm knowledge base obtains a corresponding task plan according to the context in the session, after the task plan is received by the behavior tree analysis module, the task plan is analyzed, a behavior tree is constructed, finally the behavior tree is executed circularly, an instruction is sent to the robot, and the feedback is received, so that the control of the robot is realized.
The method for generating the behavior tree in the invention can also comprise the following steps: and generating the behavior tree according to the configuration file through a behavior tree analysis module.
The robot cloud platform execution engine has the characteristics of high intelligent degree, strong applicability, flexible work, convenient access and low maintenance cost. By utilizing the computing power of the cloud platform, the execution engine can be used for docking various intelligent algorithms, and the quick response is obtained, so that the advantages of artificial intelligence are brought into play. Meanwhile, the execution engine maintains the behavior tree at the server, can integrate the state and environmental data of the robot under all scenes, is favorable for multi-robot cooperative operation, and makes overall decision. The robot body can load different scene configurations through the execution engine and can also download intelligent scenes from the cloud platform, so that different kinds of tasks are completed, and the robot body is suitable for various scenes. The execution engine also completely inherits the superior characteristics of the behavior tree, and the robot can flexibly make execution decisions on different conditions in a scene to meet the scene needs. The modular structure of the behavior tree enables the execution plan to be updated and maintained easily, and further reduces the use cost. The robot can be quickly and conveniently accessed to the execution engine through the multi-language SDK development kit provided by the execution engine.
Claims (9)
1. A behavior tree based robot cloud platform execution engine, the robot cloud platform execution engine comprising: the robot system comprises a server application cluster, a robot and a middleware, wherein the server application cluster consists of a plurality of server applications; the server application generates a robot instruction, the robot instruction is sent to the robot through the middleware, the robot analyzes the generated robot instruction to generate a behavior, and the execution result of the robot instruction is fed back to the server application through the middleware.
2. The robotic cloud platform execution engine of claim 1, wherein the server application is divided into an infrastructure layer, a function module layer, and an interaction layer.
3. The robotic cloud platform execution engine of claim 2, wherein the infrastructure layer includes a behavior tree module having sequential execution nodes, selection execution nodes, parallel execution nodes, conditional nodes, execution node functionality, a robotic communication module, and a session module; meanwhile, the behavior tree module is used for defining interfaces of specific condition logic and behavior logic; the robot communication module is used for packaging a receiving and sending mechanism based on MQTT messages and a message auditing function; the session module is used for packaging read-write logic functions of all state data in the robot session.
4. The robot cloud platform execution engine of claim 2, wherein the functional module layer comprises a behavior tree parsing module, an instruction distribution module, a session management module, a data source management module, a device control module, and a scene configuration module; the behavior tree analysis module processes the generation of the behavior tree by adopting a behavior tree schema based on json; the instruction distribution module is used for processing communication between the server application and the robot; the session management module is responsible for state data maintenance in a scene, including the realization of a memory function based on redis; the scene configuration module is used for managing global parameters under each scene, and loading and storing the global parameters during operation through json file configuration; the data source management module adopts a monitor mode and is responsible for data input and output.
5. The robotic cloud platform execution engine of claim 2, wherein the interaction layer includes an API, a console, and a client; the API is used for controlling the opening and closing of the scene session; the control console displays and monitors the execution condition of the robot cloud platform execution engine based on log collection and point burying; the client is used for providing basic development SDK and supporting python and c + + languages.
6. The robot cloud platform execution engine of claim 1, wherein the robot cloud platform execution engine controls and manages a camera and a large screen display through http and udp protocols.
7. An execution method of the robot cloud platform execution engine according to claim 1, specifically comprising: when the robot cloud platform execution engine runs, an interaction layer receives a request, a session management module starts a session and generates a globally unique session id, and according to a requested scene, a scene configuration module loads prefabricated configuration parameters including the type of robots, the number of the robots, data sources to be monitored and environmental parameters; and the session id is used as a key, a corresponding data structure is saved and used, a behavior tree is generated according to scene configuration, and finally the control of the robot is realized by circularly executing the behavior tree.
8. The execution method according to claim 7, wherein the method for generating the behavior tree specifically comprises: and the behavior tree analysis module generates a behavior tree according to the configuration file.
9. The execution method according to claim 7, wherein the method for generating the behavior tree specifically comprises: and after receiving the task plan, the behavior tree analysis module analyzes the task plan to generate a behavior tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430124.5A CN112235419B (en) | 2020-12-09 | 2020-12-09 | Robot cloud platform execution engine and execution method based on behavior tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430124.5A CN112235419B (en) | 2020-12-09 | 2020-12-09 | Robot cloud platform execution engine and execution method based on behavior tree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112235419A true CN112235419A (en) | 2021-01-15 |
| CN112235419B CN112235419B (en) | 2021-03-09 |
Family
ID=74124700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011430124.5A Active CN112235419B (en) | 2020-12-09 | 2020-12-09 | Robot cloud platform execution engine and execution method based on behavior tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112235419B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113391801A (en) * | 2021-06-11 | 2021-09-14 | 斑马网络技术有限公司 | Recommendation engine architecture based on cloud service |
| CN117400243A (en) * | 2023-10-26 | 2024-01-16 | 南京天创电子技术有限公司 | Autonomous task scheduling system and method for inspection robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838563A (en) * | 2012-11-27 | 2014-06-04 | 台博机器人股份有限公司 | Program developing method for automatic device |
| CN107770271A (en) * | 2017-10-20 | 2018-03-06 | 南方电网科学研究院有限责任公司 | Clustered machine people's cloud control method, device and system |
| CN108780303A (en) * | 2016-03-03 | 2018-11-09 | 玛格兹诺有限公司 | The control process of robot with behavior tree framework |
| CN109249381A (en) * | 2017-07-13 | 2019-01-22 | 鸿富锦精密工业（深圳）有限公司 | robot |
| CN109807903A (en) * | 2019-04-10 | 2019-05-28 | 博众精工科技股份有限公司 | A kind of robot control method, device, equipment and medium |
| CN111476337A (en) * | 2020-04-02 | 2020-07-31 | 中国人民解放军国防科技大学 | Group robot mode generation and conversion method of multistage variable gene regulation and control network |
-
2020
- 2020-12-09 CN CN202011430124.5A patent/CN112235419B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838563A (en) * | 2012-11-27 | 2014-06-04 | 台博机器人股份有限公司 | Program developing method for automatic device |
| CN108780303A (en) * | 2016-03-03 | 2018-11-09 | 玛格兹诺有限公司 | The control process of robot with behavior tree framework |
| CN109249381A (en) * | 2017-07-13 | 2019-01-22 | 鸿富锦精密工业（深圳）有限公司 | robot |
| CN107770271A (en) * | 2017-10-20 | 2018-03-06 | 南方电网科学研究院有限责任公司 | Clustered machine people's cloud control method, device and system |
| CN109807903A (en) * | 2019-04-10 | 2019-05-28 | 博众精工科技股份有限公司 | A kind of robot control method, device, equipment and medium |
| CN111476337A (en) * | 2020-04-02 | 2020-07-31 | 中国人民解放军国防科技大学 | Group robot mode generation and conversion method of multistage variable gene regulation and control network |
Non-Patent Citations (1)
| Title |
|---|
| ALEJANDRO MARZINOTTO等: "Towards a Unified Behavior Trees Framework for Robot Control", 《2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS & AUTOMATION (ICRA)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113391801A (en) * | 2021-06-11 | 2021-09-14 | 斑马网络技术有限公司 | Recommendation engine architecture based on cloud service |
| CN113391801B (en) * | 2021-06-11 | 2024-03-01 | 斑马网络技术有限公司 | Recommendation engine architecture based on cloud service |
| CN117400243A (en) * | 2023-10-26 | 2024-01-16 | 南京天创电子技术有限公司 | Autonomous task scheduling system and method for inspection robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112235419B (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112235419B (en) | Robot cloud platform execution engine and execution method based on behavior tree | |
| CN109408500B (en) | Artificial intelligence operation platform | |
| CN112272234B (en) | Platform management system and method for realizing edge cloud cooperation intelligent service | |
| US7127701B2 (en) | Computer processing and programming method using autonomous data handlers | |
| CN109159125B (en) | Cloud service system based on ROS system robot | |
| McKee | What is networked robotics? | |
| Chen et al. | Fogros: An adaptive framework for automating fog robotics deployment | |
| CN115115329A (en) | Manufacturing middleware and cloud manufacturing framework for intelligent production line | |
| EP0926590A1 (en) | Component-based control structure for wireless communication | |
| US6658491B1 (en) | System and method for constructing an ole process control compliant data server from a noncompliant user application | |
| Ledeczi et al. | Model-integrated embedded systems | |
| Barata et al. | Integrated and distributed manufacturing, a multi-agent perspective | |
| Calisi et al. | Design choices for modular and flexible robotic software development: the OpenRDK viewpoint | |
| Bouassida Rodriguez et al. | A rule-driven approach for architectural self adaptation in collaborative activities using graph grammars | |
| CN112817581A (en) | Lightweight intelligent service construction and operation support method | |
| CN111858260A (en) | Information display method, device, equipment and medium | |
| Andreasson et al. | Software Architecture for Mobile Robots | |
| KR20210111516A (en) | Configuration of Real-Time Intellectual Platform for Customized AI services | |
| Huybrechts et al. | DUST Initializr—Graph-based platform for designing modules and applications in the revised DUST framework | |
| Khan et al. | From Mainframe to Cloud Computing: A Study of Programming Paradigms with the Evolution of Client-Server Architecture | |
| RU2815598C1 (en) | Method of creating robotic systems | |
| CN114371938B (en) | Space-based intelligent networking edge computing framework | |
| Vijeth et al. | Review on Robot Operating System | |
| Parker et al. | The SCIJump Framework for Parallel and Distributed Scientific Computing | |
| Li et al. | Autonomic computing for spacecraft ground systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |