CN111311106B - Method and system for realizing task planning by using non-classical planner on ROS - Google Patents
Method and system for realizing task planning by using non-classical planner on ROS Download PDFInfo
- Publication number
- CN111311106B CN111311106B CN202010136167.6A CN202010136167A CN111311106B CN 111311106 B CN111311106 B CN 111311106B CN 202010136167 A CN202010136167 A CN 202010136167A CN 111311106 B CN111311106 B CN 111311106B
- Authority
- CN
- China
- Prior art keywords
- task
- planning
- planner
- robot
- node
- 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
- 238000013439 planning Methods 0.000 title claims abstract description 151
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000009471 action Effects 0.000 claims abstract description 97
- 230000000694 effects Effects 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013440 design planning Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000003642 reactive oxygen metabolite Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a method and a system for realizing task planning by using a non-classical planner on ROS, wherein the system is used for realizing the method and comprises the steps of establishing a task planning system of a robot, and sending the initial state and the geographic position of the robot to a task planning node by a multi-robot SLAM node; the voice recognition node sends the task target and the constraint of the robot to a task planning node; the task planning node converts an initial state, a geographical position, a task target and a common constraint into a task planning problem; calling a planner to solve the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity; the planner sends the optimal task rule strategy to a task planning node through the robot host; and the task planning node distributes the task to other execution nodes of the robot according to the optimal task rule strategy so as to complete the task. The invention realizes the action parallelism of multiple robots and the action effect is determined by global constraint.
Description
Technical Field
The invention relates to the field of robot task planning systems, in particular to a method and a system for realizing task planning by using a non-classical planner on an ROS.
Background
The goal of mission planning is to coordinate actions and accomplish established goals with respect to an organization given an environmental model by minimizing costs such as time or energy. To do this, the plan must be able to predict the interaction of the agent with the environment while satisfying constraints, avoiding impassement of the agent, and still be able to achieve the goal. The Robot Operating System (ROS) is a set of software libraries and tools used to build robotic systems. Distributed and modular are known to those of skill in the art. ROS have become a popular platform for robot research and are a flexible basis for constructing robot control through mission planning. The requirement for developing a system capable of completing the task planning of the robot is more and more urgent, so that many scholars at home and abroad are interested in researching the multi-robot task planning system, and the research and application of the multi-robot task planning show a flourishing scene in recent years. A classical programming based multi-robot mission planning system ROSPlan on ROS.
ROSPlan is a framework that integrates generic task planning with the execution interface provided by ROS. When the initial environment is known, ROSPlan achieves the goal through a series of task operations. The robot integrates a heuristic search planner to control the behavior of the robot, and when the environment changes or the action execution fails, a re-planning mechanism is used to deal with the dynamic complex environment in the real world. ROSPlan has been successfully applied to underwater automated robots. It integrates two standards together: PDDL2.1 (planning domain description language for timing and numerical standards) and ROS robot operating system. The frame comprises three components: knowledge collection, planning system and action distribution. The ROSPlan framework can operate in conjunction with the PDDL2.1 domain description and planner, and implement auto-planning on the ROS system, coordinating low-level robot controllers. ROSPlan integrates mission planning and execution frameworks. Knowledge collection comes from sensor data that is parsed into a corresponding PDDL domain description as problem input to the planner. And the planner is used for planning by using the received PDDL problem file to generate a planning solution. And the action distribution module receives the planning solution, converts the planning solution into bottom action information in the ROS system, broadcasts the action information to the corresponding robot, and the robot executes the action after receiving the information and completes the task.
Classical planning techniques are embedded on ROS systems and all relevant application areas require domain customization. On the one hand, classical planning techniques cannot cope with real world complications. The real world is full of uncertainty and classical planning techniques are not suitable for solving real world practical problems. On the other hand, the current application field needs to be customized according to the application field, the field of expert design planning is needed, the universalization cannot be achieved at present, and the wider application range of the multi-robot task planning system on the ROS is limited. Although the ROS-based task planning by using the classical planner can unify the bottom-level control and task planning of the robot, the method is based on a deterministic planning method and cannot cope with the complex environment of the real world, for example, the robot fails to execute the action with a certain probability. Secondly, the system has a limit on the concurrency of the action execution of the multi-robot task planning, and cannot cope with the characteristic of the concurrent execution of the action of the multi-robot.
Disclosure of Invention
The invention mainly aims to provide a method and a system for realizing task planning on an ROS (reactive oxygen species) by using a non-classical planner, and aims to overcome the problems.
In order to achieve the purpose, the invention discloses a method for realizing task planning by using a non-classical planner on an ROS, which comprises the following steps:
s10, establishing a distributed task planning system, wherein the distributed task planning system comprises a plurality of robots with built-in ProTaP frameworks, planners for distributing task plans to the robots, and robot hosts responsible for registering and coordinating the robots to communicate, the robots comprise task planning nodes, multi-robot SLAM nodes, voice recognition nodes and other execution nodes, and the ProTaP frameworks are used for calling the planners;
s20, the multi-robot SLAM node sends the initial state and the geographic position of the robot to a task planning node; the voice recognition node sends a task target and constraint of the robot to a task planning node;
s30, the task planning node converts the initial state, the geographic position, the task target and the common constraint into a task planning problem;
s40, calling a planner to solve the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity;
s50, the planner sends the optimal task rule strategy to a task planning node through the robot host;
and S60, distributing the tasks to other execution nodes of the robot by the task planning node according to the optimal task rule strategy so as to complete the tasks.
Preferably, the planner may be an RDDL planner, a PROST planner and/or a SOGBOFA planner.
Preferably, if the planner is an RDDL planner, the RDDL planner regards the task planning problem as a six-tuple Σ= (S, a, T, P, R, γ) using a probabilistic parallel rules algorithm:
s: the set of all possible states s, also called state space;
a: a set of all actions a;
t: for decision periods, each decision period comprises a number of time steps t 1 ,t 2 ,...,t m M is a natural number inFor each decision period T, the system executes all action groups a (S, T);
P：S×A×S×T→[0,1]describing a probability transfer function, the system being at time step t, at state s 1 Performing action a, moving to the next state s 2 Probability P(s) of 1 ,a n ,s 2 ,t m )，s 1 ,s 2 ∈S,a n ∈A,t m E.g. T, probability transfer function
R: s × A × S × T → R is the reward function as the system slave state S at time step T 1 Performing action a evolves to state s 2 Later, agent obtains the value reward;
gamma is the discount coefficient.
Preferably, the probability parallel rule algorithm defines a probability parallel planning solution to a strategy pi, and each time step t in the probability parallel planning solution m E.g. T, state s 1 ,s 2 E, S, the system executes all action groups A (S, t), and the optimal strategy pi * Maximum strategy V for obtaining accumulated reward * And satisfies the following equation:
wherein V * (s, t) represents time t and state s 1 The lower cumulative prize maximum.
Preferably, said set of all actions A (s, t) is { a } 0 ,...,a n N is the number of actions contained in each action group at time step t and state s, and different action groups contain different numbers of actions, so n is a variable.
Preferably, in any state, if two action groups in all the action groups a (s, t) satisfy the following constraint condition, the two action groups cannot be executed simultaneously, and the constraint condition is:
1) The preconditions of the two action groups are not consistent;
2) The effects produced after the two action groups are executed conflict with each other;
3) The preconditions of one action group conflict with the effects of another action group.
Preferably, the RDDL planner describes the mission planning field and the mission planning problem in RDDL language or MA-PDDL language.
Preferably, the ProTaP framework employs the ROS operating system to invoke the planner.
The invention also provides a system for realizing task planning by using a non-classical planner on the ROS, which comprises the following steps:
the system comprises a plurality of robots, a planning system and a planning system, wherein each robot at least comprises a ProTaP framework and is used for calling a planner; the task planning node is used for collecting the task target and the constraint of the robot, converting the task target and the constraint into a task rule problem, sending the task rule problem to the planner, receiving a task planning strategy sent by the planner and distributing tasks to other execution nodes according to the task planning strategy; the multi-robot SLAM node is used for sending the initial state and the geographic position of the robot to the task planning node; the voice recognition node sends the task target and the constraint of the robot to the task planning node; and other execution nodes for executing the tasks assigned by the task planning node;
the planner is used for solving the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity, and sending the optimal task planning strategy to the task planning node;
the robot host is used for being in charge of the node management of the robot, and the node management at least comprises robot registration and communication coordination of all robots;
preferably, the other execution nodes at least comprise a navigation planning node, a motion planning node and other action nodes, and the navigation planning node is used for providing a cost map and navigating the displacement of the robot to the robot; the motion planning node is used for executing motion actions and constraints of the robot; the other action nodes are used to perform other actions of the robot.
The technical scheme of the invention is to provide an intelligent rule method of a task target of multiple robots besides a distributed network system, solve a task planning problem into an optimal task planning strategy which allows multiple concurrent actions to be executed and has the maximum accumulated reward at a decision time through a planner, and realize the effects that actions of multiple robots are parallel, the action effect is determined by global constraint, multiple actions can be executed by one robot at one time step, mutually independent actions (actions not in the same action group) can be executed concurrently, and non-mutual-exclusive actions do not influence each other.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a method flow diagram of one embodiment of a method of the present invention;
FIG. 2 is a system block diagram of an embodiment of the system of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, if directional indications (such as up, down, left, right, front, back, 8230; etc.) are involved in the embodiment of the present invention, the directional indications are only used for explaining the relative positional relationship between the components, the motion situation, etc. in a specific posture (as shown in the figure), and if the specific posture is changed, the directional indications are correspondingly changed.
In addition, if there is a description relating to "first", "second", etc. in the embodiments of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a method for implementing mission planning on an ROS by using a non-classical planner, comprising the following steps:
s10, establishing a distributed task planning system, wherein the distributed task planning system comprises a plurality of robots with built-in ProTaP frames, planners for distributing task plans to the robots, and robot hosts responsible for registering and coordinating the robots to communicate, each robot comprises a task planning node, a multi-robot SLAM node, a voice recognition node and other execution nodes, and the ProTaP frames are used for calling the planners;
s20, the multi-robot SLAM node sends the initial state and the geographic position of the robot to a task planning node; the voice recognition node sends a task target and constraint of the robot to a task planning node;
s30, the task planning node converts the initial state, the geographic position, the task target and the common constraint into a task planning problem;
s40, calling a planner to solve the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated rewards at a decision opportunity;
s50, the planner sends the optimal task rule strategy to a task planning node through the robot host;
and S60, distributing the tasks to other execution nodes of the robot by the task planning node according to the optimal task rule strategy so as to complete the tasks.
Preferably, the planner may be an RDDL planner, a PROST planner and/or a SOGBOFA planner.
Preferably, if the planner is an RDDL planner, the RDDL planner regards the task planning problem as a six-tuple Σ= (S, a, T, P, R, γ) using a probabilistic parallel rules algorithm:
s: the set of all possible states s, also called state space;
a: a set of all actions a;
t: for decision periods, each decision period comprises several time steps t 1 ,t 2 ,...,t m M is a natural number, and in each decision period T, the system executes all action groups A (S, T);
P：S×A×S×T→[0,1]describing a probability transfer function, the system being at time step t, at state s 1 Performing action a, moving to the next state s 2 Probability P(s) of 1 ,a n ,s 2 ,t m )，s 1 ,s 2 ∈S,a n ∈A,t m E.g. T, probability transfer function
R: s × A × S × T → R is the reward function as the system slave state S at time step T 1 Evolution of the execution of action a into state s 2 Later, agent obtains the value reward;
gamma is the discount coefficient.
Preferably, the probability parallel rule algorithm defines a probability parallel planning solution as a strategy pi, and each time step t in the probability parallel planning m E.g. T, state s 1 ,s 2 E.g. S, the system executes all action groups A (S, t), the optimal strategy pi * Maximum strategy V for obtaining accumulated reward * And satisfies the following equation:
wherein V * (s, t) represents time t and state s 1 The lower cumulative prize maximum.
Preferably, said set of all actions A (s, t) is { a } 0 ,...,a n N is the number of actions contained in each action group at time step t and state s, and different action groups contain different numbers of actions, so n is a variable.
Preferably, in any state, if two action groups of all the action groups a (s, t) satisfy the following constraint condition, the two action groups cannot be executed simultaneously, and the constraint condition is:
1) The preconditions of the two action groups are not consistent;
2) The effects generated after the execution of the two action groups conflict with each other;
3) The preconditions of one action group conflict with the effects of another action group.
Preferably, the RDDL planner describes the mission planning field and the mission planning problem in RDDL language or MA-PDDL language.
Preferably, the ProTaP framework employs the ROS operating system call planner.
In the embodiment of the invention, as shown in fig. 1, the technical scheme of the invention realizes an intelligent rule method for a multi-robot task goal based on a distributed network system, and solves a task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward through a planner, so that the action parallelism of multiple robots is realized, and the action effect is determined by global constraint.
The invention realizes the effect that one robot can execute a plurality of actions in one time step, the mutually independent actions (actions not in the same action group) can be executed concurrently, and the non-mutual exclusive actions do not influence each other.
The present invention further provides a system for implementing task planning on an ROS using a non-classical planner, where the system is configured to implement the method, and the specific structure of the system refers to the above embodiments.
Referring to fig. 2, the present invention provides a system for implementing mission planning by using a non-classical planner on an ROS, comprising:
the system comprises a plurality of robots, a planning machine and a planning system, wherein each robot at least comprises a ProTaP framework and is used for calling the planning machine; the task planning node is used for collecting the task target and the constraint of the robot, converting the task target and the constraint into a task rule problem, sending the task rule problem to the planner, receiving a task planning strategy sent by the planner and distributing tasks to other execution nodes according to the task planning strategy; the multi-robot SLAM node is used for sending the initial state and the geographic position of the robot to the task planning node; the voice recognition node sends the task target and the constraint of the robot to the task planning node; and other execution nodes for executing the tasks assigned by the task planning node;
the planner is used for solving the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity, and sending the optimal task planning strategy to the task planning node;
the robot host is used for being responsible for the node management of the robot, and the node management at least comprises robot registration and communication coordination of all robots;
preferably, the other execution nodes at least comprise a navigation planning node, a motion planning node and other action nodes, and the navigation planning node is used for providing a cost map and the displacement of the navigation robot for the robot; the motion planning node is used for executing motion actions and constraints of the robot; the other action nodes are used to perform other actions of the robot.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structural changes made by using the contents of the present specification and the drawings, or any other related technical fields, which are directly or indirectly applied to the present invention, are included in the scope of the present invention.
Claims (8)
1. A method for realizing mission planning by using a non-classical planner on an ROS is characterized by comprising the following steps:
s10, establishing a distributed task planning system, wherein the distributed task planning system comprises a plurality of robots with built-in ProTaP frameworks, planners for distributing task plans to the robots, and robot hosts responsible for registering and coordinating the robots to communicate, the robots comprise task planning nodes, multi-robot SLAM nodes, voice recognition nodes and other execution nodes, and the ProTaP frameworks are used for calling the planners;
s20, the multi-robot SLAM node sends the initial state and the geographic position of the robot to a task planning node; the voice recognition node sends the task target and the constraint of the robot to a task planning node;
s30, the task planning node converts the initial state, the geographic position, the task target and the common constraint into a task planning problem;
s40, calling a planner to solve the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity;
s50, the planner sends the optimal task rule strategy to a task planning node through the robot host;
s60, distributing the tasks to other execution nodes of the robot by the task planning node according to the optimal task rule strategy so as to complete the tasks;
the planner may be an RDDL planner; if the planner is an RDDL planner, the RDDL planner regards the task planning problem as a six-tuple Σ= (S, a, T, P, R, γ) by using a probabilistic parallel rules algorithm:
s: the set of all possible states s, also called state space;
a: a set of all actions a;
t: for decision periods, each decision period comprises a number of time steps t 1 ,t 2 ,...,t m M is a natural number, and in each decision period T, the system executes all action groups A (S, T);
P：S×A×S×T→[0,1]describing a probability transfer function, the system being at time step t, at state s 1 Performing action a, moving to the next state s 2 Probability P(s) of 1 ,a n ,s 2 ,t m )，s 1 ,s 2 ∈S,a n ∈A,t m E.g. T, probability transfer function
R: s × A × S × T → R is the reward function as the system slave state S at time step T 1 Performing action a evolves to state s 2 Later, agent obtains the value reward; gamma is a discount coefficient;
the probability parallel rule algorithm defines the solution of probability parallel planning into a strategy pi, and each time step t in the probability parallel planning m E.g. T, state s 1 ,s 2 E, S, the system executes all action groups A (S, t), and the optimal strategy pi * Maximum strategy V for obtaining accumulated reward * The following equation is satisfied:
wherein V * (s, t) represents time t and state s 1 The lower cumulative prize maximum.
2. The method for mission planning with a non-classical planner on an ROS according to claim 1 wherein the planner can also be a PROST planner and/or a SOGBOFA planner.
3. The method of implementing mission planning on an ROS using a non-classical planner as claimed in claim 1, wherein the set of all actions A (s, t) is { a (a, t) } 0 ,...,a n N is the number of actions contained in each action group at time step t and state s, and different action groups contain different numbers of actions, so n is a variable.
4. The method of claim 1, wherein all action groups A (s, t) are in any state, and two action groups cannot be executed simultaneously if they satisfy the following constraints:
1) The preconditions of the two action groups are not consistent;
2) The effects produced after the two action groups are executed conflict with each other;
3) The preconditions of one action group conflict with the effects of another action group.
5. The method of implementing mission planning on a ROS utilizing a non-classical planner according to claim 1 wherein the RDDL planner describes the mission planning field and mission planning problem in RDDL language or MA-PDDL language.
6. The method of implementing mission planning on an ROS using a non-classical planner as recited in claim 1, wherein the ProTaP framework invokes the planner with the ROS operating system.
7. A system for implementing mission planning on an ROS using a non-classical planner, comprising:
the system comprises a plurality of robots, a planning system and a planning system, wherein each robot at least comprises a ProTaP framework and is used for calling a planner; the task planning node is used for collecting the task target and the constraint of the robot, converting the task target and the constraint into a task rule problem, sending the task rule problem to the planner, receiving a task planning strategy sent by the planner and distributing tasks to other execution nodes according to the task planning strategy; the multi-robot SLAM node is used for sending the initial state and the geographic position of the robot to the task planning node; the voice recognition node sends the task target and the constraint of the robot to the task planning node; and other execution nodes for executing the tasks assigned by the task planning node;
the planner is used for solving the task planning problem into an optimal task planning strategy which allows a plurality of concurrent actions to be executed and has the maximum accumulated reward at a decision opportunity, and sending the optimal task planning strategy to the task planning node;
and the robot host is used for being in charge of the node management of the robot, and the node management at least comprises robot registration and communication coordination of all robots.
8. The system for mission planning with a non-classical planner on an ROS according to claim 7 wherein said other executing nodes include at least a navigation planning node for providing a cost map to the robot and navigating the displacement of the robot, a motion planning node, and other action nodes; the motion planning node is used for executing motion actions and constraints of the robot; the other action nodes are used to perform other actions of the robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136167.6A CN111311106B (en) | 2020-03-02 | 2020-03-02 | Method and system for realizing task planning by using non-classical planner on ROS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136167.6A CN111311106B (en) | 2020-03-02 | 2020-03-02 | Method and system for realizing task planning by using non-classical planner on ROS |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111311106A CN111311106A (en) | 2020-06-19 |
| CN111311106B true CN111311106B (en) | 2023-02-03 |
Family
ID=71147874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010136167.6A Active CN111311106B (en) | 2020-03-02 | 2020-03-02 | Method and system for realizing task planning by using non-classical planner on ROS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111311106B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9272418B1 (en) * | 2014-09-02 | 2016-03-01 | The Johns Hopkins University | System and method for flexible human-machine collaboration |
| CN106931975A (en) * | 2017-04-14 | 2017-07-07 | 北京航空航天大学 | A kind of many strategy paths planning methods of mobile robot based on semantic map |
| CN109753072A (en) * | 2019-01-23 | 2019-05-14 | 西安工业大学 | A kind of mobile robot mixed path planing method |
| CN109978272A (en) * | 2019-03-30 | 2019-07-05 | 华南理工大学 | A kind of path planning system and method based on multiple omni-directional mobile robots |
-
2020
- 2020-03-02 CN CN202010136167.6A patent/CN111311106B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9272418B1 (en) * | 2014-09-02 | 2016-03-01 | The Johns Hopkins University | System and method for flexible human-machine collaboration |
| CN106931975A (en) * | 2017-04-14 | 2017-07-07 | 北京航空航天大学 | A kind of many strategy paths planning methods of mobile robot based on semantic map |
| CN109753072A (en) * | 2019-01-23 | 2019-05-14 | 西安工业大学 | A kind of mobile robot mixed path planing method |
| CN109978272A (en) * | 2019-03-30 | 2019-07-05 | 华南理工大学 | A kind of path planning system and method based on multiple omni-directional mobile robots |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111311106A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cui et al. | Offloading autonomous driving services via edge computing | |
| Carrascosa et al. | Hybrid multi-agent architecture as a real-time problem-solving model | |
| Godoy et al. | Implicit coordination in crowded multi-agent navigation | |
| López et al. | A framework for building mobile single and multi-robot applications | |
| Guo et al. | Multirobot data gathering under buffer constraints and intermittent communication | |
| CN105043379B (en) | A kind of scenic spot browse path planing method based on space-time restriction, device | |
| US20070294662A1 (en) | Integrated Service Method of Distribution Software for Robot Development Based on Open Internet Network | |
| CN102708377A (en) | Method for planning combined tasks for virtual human | |
| Zhu et al. | Deep reinforcement learning for real-time assembly planning in robot-based prefabricated construction | |
| CN108121330A (en) | A kind of dispatching method, scheduling system and map path planing method | |
| KR20100073771A (en) | Method and apparatus for selecting robot in network-based cooperative robot system | |
| CN116540656A (en) | Digital twinning-based multi-AGV collision-free path scheduling method for manufacturing workshops | |
| Kiselev et al. | Hierarchical psychologically inspired planning for human-robot interaction tasks | |
| Kim et al. | Tripodal schematic design of the control architecture for the service robot PSR | |
| CN114047758B (en) | Q-learning-based multi-mobile robot formation method | |
| Weyns et al. | Decentralized control of automatic guided vehicles: applying multi-agent systems in practice | |
| CN111311106B (en) | Method and system for realizing task planning by using non-classical planner on ROS | |
| CN112465148A (en) | Network parameter updating method and device of multi-agent system and terminal equipment | |
| Godwin et al. | Distributed collaboration with limited communication using mission state estimates | |
| Stedl | Managing temporal uncertainty under limited communication: a formal model of tight and loose team coordination | |
| Knoll | Distributed contract networks of sensor agents with adaptive reconfiguration: modelling, simulation, implementation and experiments | |
| Kuhn et al. | Simulating cooperative transportation companies | |
| Diéguez et al. | A global motion planner that learns from experience for autonomous mobile robots | |
| Kostylev et al. | Development of the complex modelling system for intelligent control algorithms testing | |
| Skulimowski et al. | Communication quality in anticipatory vehicle swarms: A simulation-based model |
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 |