CN114227716B - Robot system supporting control logic cloud call and method thereof - Google Patents
Robot system supporting control logic cloud call and method thereof Download PDFInfo
- Publication number
- CN114227716B CN114227716B CN202111664991.XA CN202111664991A CN114227716B CN 114227716 B CN114227716 B CN 114227716B CN 202111664991 A CN202111664991 A CN 202111664991A CN 114227716 B CN114227716 B CN 114227716B
- Authority
- CN
- China
- Prior art keywords
- control logic
- logic module
- control
- value
- robot
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 15
- 230000007704 transition Effects 0.000 claims abstract description 43
- 230000004044 response Effects 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 abstract description 6
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 25
- 230000003245 working effect Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 206010011409 Cross infection Diseases 0.000 description 1
- 206010029803 Nosocomial infection Diseases 0.000 description 1
- 238000004887 air purification Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
Abstract
The invention provides a cloud call mechanism for robot control logic, which is provided with a control logic module which is richer than the local part of the front end of the robot and can be called, then, according to the distribution domain value of a control factor variable relative to the support domain of each control logic module in a control logic module set, the matching degree of the control logic module and the input control factor variable is determined, and according to the applicable transition probability vector group of the control logic module, the call sequence of the control logic module in the control logic module set is obtained, and the cloud call is carried out in a mode of updating to the front end of the robot or feeding back response output based on the call sequence, so that the cloud call mechanism which is most adaptive to the current control factor variable and has robustness and compatibility is realized.
Description
Technical Field
The invention relates to the field of intelligent robots, in particular to a robot system supporting control logic cloud call and a method thereof.
Background
With the development of the information age and the progress of intelligent robot technology, intelligent robots have been widely used in various fields.
In the field of logistics distribution, the logistics robot can realize logistics distribution of articles such as packages, letters, catering, materials and the like in residential communities, industrial parks and office buildings. In the aspects of sanitation and environmental maintenance, the intelligent robot provided with the cleaning device and the spraying device can realize the functions of garbage cleaning, air purification, epidemic prevention, disinfection and the like. In units of hospitals, quarantine inspection and the like, the intelligent robot can collect and deposit samples and send out the samples in a laboratory, so that the sample distribution management efficiency can be improved, and the cross infection risk of people to people is reduced. The intelligent robot applied in the scenes of large business circles and the like can realize the functions of indoor approach, commodity bearing and advertisement playing.
Reliable and efficient control logic is a main guarantee for the robot to realize the functions. The control logic of the robot mainly refers to the functional logic of the robot in the aspects of path planning, autonomous navigation, target recognition, obstacle avoidance, environment monitoring, working action execution, man-machine interaction, self-checking monitoring and the like. The intelligent hardware of the robot can make logic judgment based on various control factor variables outside and inside the robot according to the setting of the functional logic, and further form and execute control instructions in response to the control factor variables.
The control logic is composed of a plurality of modules, the control logic module provides a logic interface, and the robot can input control factor variables to the control logic module through the logic interface to obtain response output of the control logic module. At present, the intelligent operating system is generally installed on the robot, and the control logic is used as the bottom logic of the operating system and is used for calling an application program of the intelligent robot. The control logic is built into the memory of the robot and is updated periodically as the operating system is upgraded.
With the increasing abundance of application fields, the increasing number and variety of robots and the increasing strong functions of intelligent robots, various actual scenes and environmental factors faced by robots are increasingly diversified, the working action process is increasingly complex and fine, and the requirements on response instantaneity and accuracy are continuously improved. The built-in and solidified control logic module of the robot cannot meet the requirements brought by the conditions, and the periodic version updating of the operating system cannot meet the functional requirements of the robot, so that the problem to be solved newly in the field of intelligent robots is solved.
Disclosure of Invention
The invention provides a robot system supporting control logic cloud call and a method thereof.
The technical scheme for solving the technical problems is as follows:
In a first aspect, the invention provides a robot system supporting control logic cloud invocation, which comprises a cloud server and a robot front end; the method is characterized in that:
The front end of the robot determines an execution function and external and/or internal control factor variables of the robot corresponding to the execution function, and provides the execution function and the control factor variables to the cloud server;
The cloud server includes:
The logic architecture calling module is used for calling a control logic architecture according to the execution function, wherein the control logic architecture consists of a time sequence control logic prototype;
The logic module library is provided with a control logic module which can be called; wherein the control logic module corresponds to at least one control logic prototype;
The calling sequence unit is used for obtaining a control logic module set corresponding to each control logic prototype in the control logic architecture and obtaining a calling sequence of a control logic module in the control logic module set according to the distribution domain of the control factor variable;
And the logic module calling unit calls the control logic module according to the calling sequence of the control logic module.
Preferably, the front end of the robot is provided with a local control logic architecture, and the logic module calling unit updates at least one control logic module in the calling sequence to the front end of the robot, and the front end of the robot calls the control logic module according to the local control logic architecture.
Preferably, the logic module calling unit inputs the control factor variable to at least one control logic module in the calling sequence, obtains the response output of the control logic module, and sends the response output to the front end of the robot.
Preferably, the call sequence unit is configured to calculate a distribution domain value of the control factor variable with respect to a support domain of each control logic module in the set of control logic modules; and for the control logic module set, determining a relation matrix of the control logic module according to the distribution domain value of the control factor variable; determining an applicable transition probability vector group of the control logic module according to the relation matrix of the control logic module; and obtaining a calling sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group of the control logic module.
Preferably, the logic module calling unit selects one or more control logic modules ordered earlier in the calling sequence according to the calling sequence.
In a second aspect, the present invention provides a method for supporting control logic cloud invocation, including:
Step S1: determining an execution function of the robot by the front end of the robot, and controlling factor variables outside and/or inside the robot corresponding to the execution function, and providing the execution function and the controlling factor variables to a cloud server;
step S2: the cloud server calls a control logic architecture according to the execution function, wherein the control logic architecture consists of a time sequence control logic prototype;
step S3: obtaining a control logic module set corresponding to each control logic prototype in the control logic architecture, and obtaining a calling sequence of a control logic module in the control logic module set according to the distribution domain of the control factor variable;
step S4: and calling the control logic module according to the calling sequence of the control logic module.
Preferably, in step S4, at least one control logic module in the call sequence is updated to the front end of the robot, which calls the control logic module according to the local control logic architecture.
Preferably, in step S4, the control factor variable is input to at least one control logic module in the call sequence, a response output of the control logic module is obtained, and the response output is sent to the front end of the robot.
Preferably, in step S3, a distribution domain value of the control factor variable with respect to a support domain of each control logic module in the set of control logic modules is calculated; and for the control logic module set, determining a relation matrix of the control logic module according to the distribution domain value of the control factor variable; determining an applicable transition probability vector group of the control logic module according to the relation matrix of the control logic module; and obtaining a calling sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group of the control logic module.
Preferably, in step S4, one or more control logic modules ordered earlier in the calling sequence are selected from the calling sequence.
The beneficial effects of the invention are as follows:
The invention provides a cloud call mechanism for robot control logic, which is provided with a control logic module which is richer than the local part of the front end of the robot and can be called, then, according to the distribution domain value of a control factor variable relative to the support domain of each control logic module in a control logic module set, the matching degree of the control logic module and the input control factor variable is determined, and according to the applicable transition probability vector group of the control logic module, the call sequence of the control logic module in the control logic module set is obtained, and the cloud call is carried out in a mode of updating to the front end of the robot or feeding back response output based on the call sequence, so that the cloud call mechanism which is most adaptive to the current control factor variable and has robustness and compatibility is realized. The invention fully meets the requirements of various actual scenes and environmental factors faced by intelligent robots on increasing diversity, the working action process on increasing complexity and fineness and continuously improving the requirements of response instantaneity and accuracy.
Drawings
Fig. 1 is a diagram of a robot system supporting control logic cloud invocation according to an embodiment of the present invention;
Fig. 2 is a diagram of a cloud server according to an embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
In order that the above-recited objects, features and advantages of the present application can be more clearly understood, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It is to be understood that the described embodiments are some, but not all, of the embodiments of the present disclosure. The specific embodiments described herein are to be considered in an illustrative rather than a restrictive sense. All other embodiments, which are obtained by a person skilled in the art based on the described embodiments of the application, fall within the scope of protection of the application.
As an embodiment of the first aspect of the present invention, fig. 1 is a schematic diagram of a robot system supporting control logic cloud invocation, which includes a cloud server 1 and one or more robot front ends 2.
The robot front end 2 itself is provided with an independent intelligent terminal device. From the perspective of hardware, intelligent robot has carried laser radar, vision camera, distancer and matches all kinds of sensing device of its function, possesses the chipset that has stronger computational capacity to and possess long-distance communication module of sufficient bandwidth, multiple mode. From the software perspective, the robot is provided with an intelligent operating system, and the control logic is used as the bottom logic of the operating system and is used for calling application programs of the intelligent robot operating system.
The control logic is used as the bottom layer of the robot operating system and controls the robot to complete the functional logic in the aspects of path planning, autonomous navigation, target identification, obstacle avoidance, environment monitoring, working action execution, man-machine interaction, self-checking monitoring and the like. The intelligent hardware of the robot can make logic judgment based on various control factor variables outside and inside the robot according to the setting of the functional logic, and further form and execute control instructions in response to the control factor variables.
The control logic is composed of a plurality of control logic modules. The control logic of the robot front end 2 includes a local control logic architecture defining the timing of the control logic modules, that is, sequentially invoking the control logic modules based on the defined timing according to the execution function of the robot. The control logic module is pre-stored in the memory of the robot. The control logic module provides a logic interface, and the robot can input control factor variables to the control logic module through the logic interface to obtain response output of the control logic module.
As described above, the robot faces various actual scenes and environmental factors, the working action process is complex and fine, and the requirements for real-time performance and accuracy are continuously improved, and the requirements cannot be met simply by means of the local control logic module of the front end 2 of the robot. For this purpose, the cloud server 1 provides control logic cloud calls for the robot front end 2.
Specifically, as shown in fig. 2, the cloud server includes: a logic architecture calling module 11, a logic module library 12, a calling sequence unit 13 and a logic module calling unit 14.
In the control logic cloud invoking process, the front end 2 of the robot determines the execution function and the external and/or internal control factor variable of the robot corresponding to the execution function, and provides the execution function and the control factor variable to the cloud server.
The logic architecture calling module 11 is configured to call a control logic architecture according to the execution function, where the control logic architecture is composed of a time-sequential control logic prototype. Specifically, for different execution functions of the front end 2 of the robot, such as path planning, autonomous navigation, object recognition, obstacle avoidance, environment monitoring, execution of working actions, man-machine interaction, self-checking monitoring, and the like, the logic architecture calling module 11 defines a control logic architecture for each execution function, and the control logic architecture is composed of a time-series control logic prototype. For example, as shown in fig. 2, the control logic architecture is represented by a timing diagram, where the timing diagram includes control logic prototypes S-T-U-V that are sequentially associated in time sequence.
The control logic module library 12 has control logic modules available for invocation. Likewise, the control logic module provides a logic interface, and the control factor variable can be input to the control logic module through the logic interface to obtain the response output of the control logic module. Wherein the control logic module corresponds to at least one control logic prototype. For example, for control logic prototype S, the corresponding control logic module includes { S 1,S2,…Si…Sj…Sn }, and for control logic prototype T, the corresponding control logic module includes { T 1,T2,…Ti…Tj…Tn }.
The call sequence unit 13 obtains a set of control logic modules corresponding to each control logic prototype in the control logic architecture. For example, for control logic prototype S, a corresponding set of control logic modules { S 1,S2,…Si…Sj…Sn } is obtained.
The call sequence unit 13 also obtains the external and/or internal control factor variables of the robot corresponding to the execution function uploaded by the robot front end 2. The control factor variable is denoted as R 1,R2,…Rk,…RM, where R k represents a k-th type of control factor variable, i.e., totaling 1 to M types of control factor variables, and R k＝{rk1,rk2,…rkl, i.e., the sequence of values of the k-th type of control factor variable within the variable window.
Further, the call sequence unit 13 calculates a distribution domain value of the control factor variable with respect to a support domain of each control logic module in the control logic module set. For each control logic module in the control logic module set { S 1,S2,…Si…Sj…Sn }, e.g., S i, which has a support field for each of the 1 st to M-type control factor variables R 1,R2,…Rk,…RM, the support field is a distribution interval for the control logic module for a certain type of control factor variable, e.g., S i, which supports the value of the control factor variable, e.g., for the k-th type control factor variable R k, the control logic module S i supports the value of the control factor variable R k, the distribution interval size being expressed asThat is, the control logic module S i has a support domain of the control factor variable R k of/>And, the number of times the value sequence of each type of control factor variable, for example, the value sequence R k＝{rk1,rk2,…rkl of the control factor variable R k, falls within the value distribution interval supported by the control logic module S i is determined, and the value of this number of times is denoted as F k(Si), so that the distribution domain value of the control factor variable R k for the control logic module S i is expressed as: Where θ is a constant coefficient. Further, for the control logic module S i, the distribution threshold values of all the control factor variables R 1,R2,…Rk,…RM of the 1 st to M th types are expressed as
The call sequence unit 13 determines a relation matrix of the control logic module according to the distribution domain value of the control factor variable for the control logic module set { S 1,S2,…Si…Sj…Sn }:
Wherein, And then, according to the relation matrix of the control logic module, determining an applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn }) of the control logic module: wherein,
P ij denotes the applicable transition probability between the control logic modules S i、Sj. Wherein, according to the iterative formula
Iterating the applicable transition probability vector P i whenAnd/>The value difference of the transition probability vector P i is smaller than a preset threshold value, and the stable transition probability vector P i is obtained. In this formula, P i 0 is the initial value of vector P i, each element of this vector being initially assigned 1/n,/>Is applicable to the transition probability; p i 1 and P i l+1 represent the values of vector P i in the first iteration and the first +1st iteration, respectively; after a certain round of iteration, a stable state can be entered, that is, the value difference between P i 1 and P i l+1 is smaller than a preset threshold value, and the final applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn } of the control logic module is obtained.
Furthermore, the call sequence unit 13 obtains a call sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group p= { P 1、P2...Pi…Pj…Pn }. Specifically, for the control logic module set { S 1,S2,…Si…Sj…Sn }, the distribution threshold value of each control logic module is determined, i.eAnd determining the control logic module with the largest distribution threshold value. And determining a calling sequence of the control logic module according to the arrangement from large to small of transition probabilities in the applicable transition probability vector of the control logic module with the largest distribution threshold value.
The logic module calling unit 14 calls the control logic module according to the calling sequence of the control logic module. Specifically, the logic module calling unit 14 first selects one or more control logic modules ordered first in the calling sequence from among the calling sequences according to the calling sequence.
For a specific call implementation manner, the front end of the robot is provided with a local control logic architecture, and the logic module call unit updates at least one or more control logic modules in the call sequence to the front end of the robot, and the front end of the robot calls the control logic modules according to the local control logic architecture.
As another specific calling implementation manner, the logic module calling unit inputs the control factor variable into at least one control logic module in the calling sequence, obtains the response output of the control logic module, and sends the response output to the front end of the robot.
In a second aspect, the present invention provides a method for supporting control logic cloud invocation, including:
Step S1: determining an execution function of the robot by the front end of the robot, and controlling factor variables outside and/or inside the robot corresponding to the execution function, and providing the execution function and the controlling factor variables to a cloud server;
step S2: the cloud server calls a control logic architecture according to the execution function, wherein the control logic architecture consists of a time sequence control logic prototype;
step S3: obtaining a control logic module set corresponding to each control logic prototype in the control logic architecture, and obtaining a calling sequence of a control logic module in the control logic module set according to the distribution domain of the control factor variable;
step S4: and calling the control logic module according to the calling sequence of the control logic module.
Preferably, in step S4, at least one control logic module in the call sequence is updated to the front end of the robot, which calls the control logic module according to the local control logic architecture.
Preferably, in step S4, the control factor variable is input to at least one control logic module in the call sequence, a response output of the control logic module is obtained, and the response output is sent to the front end of the robot.
Preferably, in step S3, a distribution domain value of the control factor variable with respect to a support domain of each control logic module in the set of control logic modules is calculated; and for the control logic module set, determining a relation matrix of the control logic module according to the distribution domain value of the control factor variable; determining an applicable transition probability vector group of the control logic module according to the relation matrix of the control logic module; and obtaining a calling sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group of the control logic module.
Preferably, in step S4, one or more control logic modules ordered earlier in the calling sequence are selected from the calling sequence.
The invention provides a cloud call mechanism for robot control logic, which is provided with a control logic module which is richer than the local part of the front end of the robot and can be called, then, according to the distribution domain value of a control factor variable relative to the support domain of each control logic module in a control logic module set, the matching degree of the control logic module and the input control factor variable is determined, and according to the applicable transition probability vector group of the control logic module, the call sequence of the control logic module in the control logic module set is obtained, and the cloud call is carried out in a mode of updating to the front end of the robot or feeding back response output based on the call sequence, so that the cloud call mechanism which is most adaptive to the current control factor variable and has robustness and compatibility is realized. The invention fully meets the requirements of various actual scenes and environmental factors faced by intelligent robots on increasing diversity, the working action process on increasing complexity and fineness and continuously improving the requirements of response instantaneity and accuracy.
Those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments.
Those skilled in the art will appreciate that the descriptions of the various embodiments are each focused on, and that portions of one embodiment that are not described in detail may be referred to as related descriptions of other embodiments.
Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and alterations without departing from the spirit and scope of the present application, and such modifications and alterations fall within the scope of the appended claims, which are to be construed as merely illustrative of the present application, but the scope of the application is not limited thereto, and various equivalent modifications and substitutions will be readily apparent to those skilled in the art within the scope of the present application, and are intended to be included within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (4)
1. A robot system supporting control logic cloud invocation comprises a cloud server and a robot front end; the method is characterized in that:
The front end of the robot determines an execution function and external and/or internal control factor variables of the robot corresponding to the execution function, and provides the execution function and the control factor variables to the cloud server;
The cloud server includes:
The logic architecture calling module is used for calling a control logic architecture according to the execution function, wherein the control logic architecture consists of a time sequence control logic prototype;
The logic module library is provided with a control logic module which can be called; wherein the control logic module corresponds to at least one control logic prototype;
The calling sequence unit is used for obtaining a control logic module set corresponding to each control logic prototype in the control logic architecture and obtaining a calling sequence of a control logic module in the control logic module set according to the distribution domain of the control factor variable;
A logic module calling unit for calling the control logic module according to the calling sequence of the control logic module;
the front end of the robot is provided with a local control logic architecture, the logic module calling unit updates at least one control logic module in the calling sequence to the front end of the robot, and the front end of the robot calls the control logic module according to the local control logic architecture;
the logic module calling unit inputs the control factor variable into at least one control logic module in the calling sequence, obtains the response output of the control logic module, and sends the response output to the front end of the robot;
The call sequence unit is used for calculating the distribution domain value of the control factor variable relative to the support domain of each control logic module in the control logic module set; and for the control logic module set, determining a relation matrix of the control logic module according to the distribution domain value of the control factor variable; determining an applicable transition probability vector group of the control logic module according to the relation matrix of the control logic module; obtaining a calling sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group of the control logic module;
The calling sequence unit calculates the distribution domain value of the control factor variable relative to the support domain of each control logic module in the control logic module set; for each control logic module S i in the control logic module set { S 1,S2,…Si…Sj…Sn }, it has a support field for each of the 1 st to M-type control factor variables R 1,R2,…Rk,…RM, the support field being the control logic module S i for a certain type of control factor variable-supporting the value distribution interval of the control factor variable, for the k-th type of control factor variable R k, the control logic module S i supporting the value distribution interval of the control factor variable R k, the size of the distribution interval being expressed as The control logic module S i has a support domain of the control factor variable R k of/>Determining the number of times the value sequence of each type of control factor variable, namely the value sequence R k＝{rk1,rk2,…rkl of the control factor variable R k, falls into the value distribution interval supported by the control logic module S i, and marking the value of the number of times as F k(Si), and for the control logic module S i, representing the distribution domain value of the control factor variable R k as follows: /(I)Wherein θ is a constant coefficient; for the control logic module S i, the distribution threshold values of all the control factor variables R 1,R2,…Rk,…RM of the 1 st to M th types are expressed as
The calling sequence unit determines a relation matrix of the control logic module according to the distributed domain value of the control factor variable for the control logic module set { S 1,S2,…Si…Sj…Sn }:
Wherein, And then, according to the relation matrix of the control logic module, determining an applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn }) of the control logic module: wherein,
P ij denotes the applicable transition probability between the control logic modules S i、Sj; wherein, according to the iterative formula
Iterating the applicable transition probability vector P i whenAnd/>The value difference of the transition probability vector P i is smaller than a preset threshold value, and a stable transition probability vector P i is obtained; in this formula, P i 0 is the initial value of vector P i, each element of the vector is initially assigned a value of 1/n,Is applicable to the transition probability; p i l and P i l+1 represent the values of vector P i in the first iteration and the first +1st iteration, respectively; after a certain round of iteration, a stable state can be entered, namely, the value difference between P i l and P i l+1 is smaller than a preset threshold value, and a final applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn } of the control logic module is obtained;
The call sequence unit obtains a call sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn }; for the set of control logic modules S 1,S2,…Si…Sj…Sn, a distribution threshold is determined for each control logic module, Determining a control logic module with the largest distribution threshold value from the control logic module; and determining a calling sequence of the control logic module according to the arrangement from large to small of transition probabilities in the applicable transition probability vector of the control logic module with the largest distribution threshold value.
2. The robotic system supporting control logic cloud invocation of claim 1, wherein the logic module invocation unit selects one or more control logic modules from the invocation sequence that are ordered first according to the invocation sequence.
3. A method for supporting control logic cloud invocation, comprising:
Step S1: determining an execution function of the robot by the front end of the robot, and controlling factor variables outside and/or inside the robot corresponding to the execution function, and providing the execution function and the controlling factor variables to a cloud server;
step S2: the cloud server calls a control logic architecture according to the execution function, wherein the control logic architecture consists of a time sequence control logic prototype;
step S3: obtaining a control logic module set corresponding to each control logic prototype in the control logic architecture, and obtaining a calling sequence of a control logic module in the control logic module set according to the distribution domain of the control factor variable;
step S4: calling a control logic module according to the calling sequence of the control logic module;
In step S4, at least one control logic module in the calling sequence is updated to the front end of the robot, and the front end of the robot calls the control logic module according to a local control logic architecture;
In step S4, inputting the control factor variable into at least one control logic module in the calling sequence, obtaining the response output of the control logic module, and sending the response output to the front end of the robot;
In step S3, calculating the distribution domain value of the control factor variable relative to the support domain of each control logic module in the control logic module set; and for the control logic module set, determining a relation matrix of the control logic module according to the distribution domain value of the control factor variable; determining an applicable transition probability vector group of the control logic module according to the relation matrix of the control logic module; obtaining a calling sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group of the control logic module;
The calling sequence unit calculates the distribution domain value of the control factor variable relative to the support domain of each control logic module in the control logic module set; for each control logic module S i in the control logic module set { S 1,S2,…Si…Sj…Sn }, it has a support field for each of the 1 st to M-type control factor variables R 1,R2,…Rk,…RM, the support field being the control logic module S i for a certain type of control factor variable-supporting the value distribution interval of the control factor variable, for the k-th type of control factor variable R k, the control logic module S i supporting the value distribution interval of the control factor variable R k, the size of the distribution interval being expressed as The control logic module S i has a support domain of the control factor variable R k of/>Determining the number of times the value sequence of each type of control factor variable, namely the value sequence R k＝{rk1,rk2,…rkl of the control factor variable R k, falls into the value distribution interval supported by the control logic module S i, and marking the value of the number of times as F k(Si), and for the control logic module S i, representing the distribution domain value of the control factor variable R k as follows: /(I)Wherein θ is a constant coefficient; for the control logic module S i, the distribution threshold values of all the control factor variables R 1,R2,…Rk,…RM of the 1 st to M th types are expressed as
The calling sequence unit determines a relation matrix of the control logic module according to the distributed domain value of the control factor variable for the control logic module set { S 1,S2,…Si…Sj…Sn }:
Wherein, And determining an applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn of the control logic module according to the relation matrix of the control logic module: wherein,
P ij denotes the applicable transition probability between the control logic modules S i、Sj; wherein, according to the iterative formula
Iterating the applicable transition probability vector p i whenAnd/>The value difference of the transition probability vector P i is smaller than a preset threshold value, and a stable transition probability vector P i is obtained; in this formula, P i 0 is the initial value of vector P i, each element of the vector is initially assigned a value of 1/n,Is applicable to the transition probability; p i l and P i l+1 represent the values of vector P i in the first iteration and the first +1st iteration, respectively; after a certain round of iteration, a stable state can be entered, namely, the value difference between P i l and P i l+1 is smaller than a preset threshold value, and a final applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn } of the control logic module is obtained;
The call sequence unit obtains a call sequence of the control logic module in the control logic module set according to the final applicable transition probability vector group P= { P 1、P2...Pi…Pj…Pn }; for the set of control logic modules S 1,S2,…Si…Sj…Sn, a distribution threshold is determined for each control logic module, Determining a control logic module with the largest distribution threshold value from the control logic module; and determining a calling sequence of the control logic module according to the arrangement from large to small of transition probabilities in the applicable transition probability vector of the control logic module with the largest distribution threshold value.
4. A method of supporting control logic cloud invocation according to claim 3, wherein in step S4, one or more control logic modules in the invocation sequence that are ordered earlier are selected from among the invocation sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664991.XA CN114227716B (en) | 2021-12-30 | Robot system supporting control logic cloud call and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664991.XA CN114227716B (en) | 2021-12-30 | Robot system supporting control logic cloud call and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114227716A CN114227716A (en) | 2022-03-25 |
| CN114227716B true CN114227716B (en) | 2024-06-04 |
Family
ID=
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4611296A (en) * | 1983-11-11 | 1986-09-09 | Siemens Aktiengesellschaft | Manipulation device such as an industrial robot having at least one sensor |
| JPH02287707A (en) * | 1989-04-28 | 1990-11-27 | Nissan Motor Co Ltd | Generating method for operation program of automatic machine |
| CN1276890A (en) * | 1997-10-23 | 2000-12-13 | 国际商业机器公司 | Method and apparatus for altering thread priorities in multithreaded processor |
| JP2013166222A (en) * | 2012-02-16 | 2013-08-29 | Seiko Epson Corp | Robot control device, robot control method, robot control program, and robot system |
| KR101306556B1 (en) * | 2013-04-08 | 2013-09-09 | 한성대학교 산학협력단 | Robot control system based on smart device |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN107272462A (en) * | 2017-07-26 | 2017-10-20 | 上海与德通讯技术有限公司 | A kind of pure action processing method and device based on multitask |
| CN107608778A (en) * | 2017-09-30 | 2018-01-19 | 广东欧珀移动通信有限公司 | Application program management-control method, device, storage medium and electronic equipment |
| CN107756395A (en) * | 2016-08-19 | 2018-03-06 | 腾讯科技（深圳）有限公司 | Control system, the method and apparatus of intelligent robot |
| EP3351353A1 (en) * | 2017-01-20 | 2018-07-25 | Canon Kabushiki Kaisha | Robot control apparatus, robot system, robot control method and assembly manufacturing method |
| CN109176559A (en) * | 2018-10-24 | 2019-01-11 | 上海思依暄机器人科技股份有限公司 | A kind of robot and control method, system |
| CN110053046A (en) * | 2019-04-09 | 2019-07-26 | 江门市蚂蚁机器人有限公司 | Robot control method and its system based on customized event |
| CN110125930A (en) * | 2019-04-18 | 2019-08-16 | 华中科技大学 | It is a kind of that control method is grabbed based on the mechanical arm of machine vision and deep learning |
| JP2019143979A (en) * | 2018-02-15 | 2019-08-29 | セイコーエプソン株式会社 | Encoder unit, angle detection method, and robot |
| JP2019171498A (en) * | 2018-03-27 | 2019-10-10 | 日本電産株式会社 | Robot program execution device, robot program execution method and program |
| CN110450151A (en) * | 2019-04-30 | 2019-11-15 | 北京云迹科技有限公司 | The configuration method and device of customized behavior for robot |
| CN112123330A (en) * | 2019-06-25 | 2020-12-25 | 发那科株式会社 | Robot programming device |
| CN112454369A (en) * | 2021-01-27 | 2021-03-09 | 苏州盈科电子有限公司 | Robot control method and device |
| CN112969558A (en) * | 2018-06-08 | 2021-06-15 | 米兰理工大学 | Predictive control method of robot and related control system |
| CN113055029A (en) * | 2021-02-09 | 2021-06-29 | 西安电子科技大学 | System polarization code encoding and decoding integrated device capable of multiplexing resources and encoding and decoding method |
| DE102020103853A1 (en) * | 2020-02-14 | 2021-08-19 | Franka Emika Gmbh | Graphically supported adaptation of robot control programs |
| CN113753462A (en) * | 2021-09-14 | 2021-12-07 | 深圳市库宝软件有限公司 | Task allocation method, device, equipment, warehousing system and storage medium |
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4611296A (en) * | 1983-11-11 | 1986-09-09 | Siemens Aktiengesellschaft | Manipulation device such as an industrial robot having at least one sensor |
| JPH02287707A (en) * | 1989-04-28 | 1990-11-27 | Nissan Motor Co Ltd | Generating method for operation program of automatic machine |
| CN1276890A (en) * | 1997-10-23 | 2000-12-13 | 国际商业机器公司 | Method and apparatus for altering thread priorities in multithreaded processor |
| JP2013166222A (en) * | 2012-02-16 | 2013-08-29 | Seiko Epson Corp | Robot control device, robot control method, robot control program, and robot system |
| KR101306556B1 (en) * | 2013-04-08 | 2013-09-09 | 한성대학교 산학협력단 | Robot control system based on smart device |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN107756395A (en) * | 2016-08-19 | 2018-03-06 | 腾讯科技（深圳）有限公司 | Control system, the method and apparatus of intelligent robot |
| EP3351353A1 (en) * | 2017-01-20 | 2018-07-25 | Canon Kabushiki Kaisha | Robot control apparatus, robot system, robot control method and assembly manufacturing method |
| CN107272462A (en) * | 2017-07-26 | 2017-10-20 | 上海与德通讯技术有限公司 | A kind of pure action processing method and device based on multitask |
| CN107608778A (en) * | 2017-09-30 | 2018-01-19 | 广东欧珀移动通信有限公司 | Application program management-control method, device, storage medium and electronic equipment |
| JP2019143979A (en) * | 2018-02-15 | 2019-08-29 | セイコーエプソン株式会社 | Encoder unit, angle detection method, and robot |
| JP2019171498A (en) * | 2018-03-27 | 2019-10-10 | 日本電産株式会社 | Robot program execution device, robot program execution method and program |
| CN112969558A (en) * | 2018-06-08 | 2021-06-15 | 米兰理工大学 | Predictive control method of robot and related control system |
| CN109176559A (en) * | 2018-10-24 | 2019-01-11 | 上海思依暄机器人科技股份有限公司 | A kind of robot and control method, system |
| CN110053046A (en) * | 2019-04-09 | 2019-07-26 | 江门市蚂蚁机器人有限公司 | Robot control method and its system based on customized event |
| CN110125930A (en) * | 2019-04-18 | 2019-08-16 | 华中科技大学 | It is a kind of that control method is grabbed based on the mechanical arm of machine vision and deep learning |
| CN110450151A (en) * | 2019-04-30 | 2019-11-15 | 北京云迹科技有限公司 | The configuration method and device of customized behavior for robot |
| CN112123330A (en) * | 2019-06-25 | 2020-12-25 | 发那科株式会社 | Robot programming device |
| DE102020103853A1 (en) * | 2020-02-14 | 2021-08-19 | Franka Emika Gmbh | Graphically supported adaptation of robot control programs |
| CN112454369A (en) * | 2021-01-27 | 2021-03-09 | 苏州盈科电子有限公司 | Robot control method and device |
| CN113055029A (en) * | 2021-02-09 | 2021-06-29 | 西安电子科技大学 | System polarization code encoding and decoding integrated device capable of multiplexing resources and encoding and decoding method |
| CN113753462A (en) * | 2021-09-14 | 2021-12-07 | 深圳市库宝软件有限公司 | Task allocation method, device, equipment, warehousing system and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 一类逻辑环随机模型的队列与站点状态转移;王思明, 刘金梅, 王键;***工程学报;20040425(第02期);全文 * |
| 基于服务关***计的多粒度服务组合方法;杨浩;徐晖;张瀛;;计算机应用;20100201(第02期);全文 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110471297B (en) | Multi-agent cooperative control method, system and equipment | |
| EP3136304A1 (en) | Methods and systems for performing reinforcement learning in hierarchical and temporally extended environments | |
| Chatterjee et al. | A Geese PSO tuned fuzzy supervisor for EKF based solutions of simultaneous localization and mapping (SLAM) problems in mobile robots | |
| CN103544496A (en) | Method for recognizing robot scenes on basis of space and time information fusion | |
| US11544558B2 (en) | Continual learning of artificial intelligence systems based on bi-level optimization | |
| CN109919431B (en) | Heterogeneous multi-robot task allocation method based on auction algorithm | |
| CN107870810B (en) | Application cleaning method and device, storage medium and electronic equipment | |
| JP2020154785A (en) | Prediction method, prediction program, and model learning method | |
| WO2021058099A1 (en) | Multi-step traffic prediction | |
| CN109523011B (en) | Multi-sensor self-adaptive management method for multi-unmanned aerial vehicle cooperative detection | |
| CN107943582B (en) | Feature processing method, feature processing device, storage medium and electronic equipment | |
| CN114901066B (en) | Auxiliary system and auxiliary method | |
| CN110908384B (en) | Formation navigation method for distributed multi-robot collaborative unknown random maze | |
| CN109657928A (en) | A kind of the closed loop cooperative scheduling frame and dispatching method of onboard sensor system | |
| CN112528730A (en) | Cost matrix optimization method based on space constraint under Hungary algorithm | |
| Fozuni Shirjini et al. | Stability analysis of the particle dynamics in bat algorithm: standard and modified versions | |
| Hoang et al. | A novel time series prediction approach based on a hybridization of least squares support vector regression and swarm intelligence | |
| JP2022514886A (en) | How to Train Neural Networks | |
| CN114227716B (en) | Robot system supporting control logic cloud call and method thereof | |
| Oliehoek et al. | The decentralized POMDP framework | |
| Mohanan et al. | Probabilistic approach to robot motion planning in dynamic environments | |
| EP4176386A1 (en) | Training actor-critic algorithms in laboratory settings | |
| Gros et al. | DSMC evaluation stages: Fostering robust and safe behavior in deep reinforcement learning | |
| CN114227716A (en) | Robot system supporting control logic cloud calling and method thereof | |
| CN112514352A (en) | Method, device, system, storage medium and terminal for updating scheduling rule |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |