CN116358555A - Autonomous construction and maintenance method and system for indoor environment model - Google Patents
Autonomous construction and maintenance method and system for indoor environment model Download PDFInfo
- Publication number
- CN116358555A CN116358555A CN202310339805.8A CN202310339805A CN116358555A CN 116358555 A CN116358555 A CN 116358555A CN 202310339805 A CN202310339805 A CN 202310339805A CN 116358555 A CN116358555 A CN 116358555A
- Authority
- CN
- China
- Prior art keywords
- environment model
- indoor environment
- path
- mobile robot
- explored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The disclosure provides an autonomous construction and maintenance method and system for an indoor environment model, which relate to the technical field of mobile robots and are used for describing an indoor scene by using graph structures of different levels to construct a three-dimensional scene map environment model of the mobile robot; generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework; determining a target point to be explored, calculating information gain and path cost from the current position of the mobile robot to the target point to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model; and solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment, and maintaining and updating the indoor environment model. The present disclosure enables autonomous updating and self-maintenance of long-term autonomous and environmental models of robots.
Description
Technical Field
The disclosure relates to the technical field of mobile robots, in particular to an autonomous construction and maintenance method and system for an indoor environment model.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
A scene graph is a data structure representing scene content, and a three-dimensional scene graph environmental model is a scene graph-based environmental representation method that can be used to enhance the performance of autonomous navigation of a robot. At present, environmental models based on scene graphs are less in research, the environmental models based on the scene graphs are often constructed by manual operation, and the environmental models lack the capability of dynamic active update, so that the long-term operation of the robot in a dynamic complex environment is not facilitated.
Disclosure of Invention
In order to solve the problems, the disclosure provides an autonomous construction and maintenance method and system for an indoor environment model, which combine a scene map and a part of observable circulating reinforcement learning algorithm to realize long-term autonomous construction model targets of a mobile robot, actively explore the indoor environment, continuously update the model and the scene map, and promote rapid deployment and long-term operation of the robot in a complex unknown environment.
According to some embodiments, the present disclosure employs the following technical solutions:
an autonomous construction and maintenance method for an indoor environment model, comprising the following steps:
describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
based on the three-dimensional scene map environment model, generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework;
determining a target point to be explored, calculating information gain and path cost from the current position of the mobile robot to the target point to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
and solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment, and maintaining and updating the indoor environment model.
According to some embodiments, the present disclosure employs the following technical solutions:
an autonomous construction and maintenance system for an indoor environment model, based on a mobile robot, a control platform of the mobile robot comprising:
the three-dimensional scene map environment construction module: the method comprises the steps of describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
and a path planning module: the method comprises the steps of generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework based on a three-dimensional scene map environment model;
the active exploration module is used for determining target points to be explored, calculating information gain and path cost from the current position of the mobile robot to the target points to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
the autonomous patrol module is used for solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment and carrying out maintenance and update of the indoor environment model.
According to some embodiments, the present disclosure employs the following technical solutions:
a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement the method of autonomous construction and maintenance of an indoor environment model.
According to some embodiments, the present disclosure employs the following technical solutions:
an electronic device, comprising: a processor, a memory, and a computer program; the processor is connected with the memory, the computer program is stored in the memory, and when the electronic equipment runs, the processor executes the computer program stored in the memory so that the electronic equipment executes the method for realizing autonomous construction and maintenance of the indoor environment model.
Compared with the prior art, the beneficial effects of the present disclosure are:
the method and the system for autonomously constructing and maintaining the indoor environment model are based on the wheeled mobile robot for autonomously constructing and updating the indoor environment model, and comprise a three-dimensional scene map environment constructing module, a path planning module, an active exploration module, an autonomous patrol module and a robot body. The three-dimensional scene map environment construction module of the system can construct the collected RGBD image and inertial sensor information increment into a three-dimensional hierarchical scene map in real time, is convenient for pertinently providing different information aiming at task demands (conversation level, task level, navigation level and the like) of different levels of the robot, and can be used for loop detection, task planning, hierarchical path planning and navigation of the robot;
the path planning module can construct a collision-free safety path between the departure point and the end point according to the requirement. The active exploration module may direct the robot to explore toward a map boundary information gain maximum direction until the indoor map is all known. The autonomous patrol module can guide the robot to move and observe between different indoor rooms or places so as to achieve the purpose of actively updating the environment model, and has the advantages of high efficiency and high automation degree compared with the manual environment model updating.
The method and the system can plan the movement strategy of the robot in the indoor complex environment through the environment sensing and modeling of the mobile robot, and realize the long-term autonomy of the robot and the autonomous updating and self-maintenance of the environment model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
FIG. 1 is a diagram of an autonomous construction and maintenance system of an indoor environment model of the present disclosure;
FIG. 2 is a system simulation diagram of the generation of a three-dimensional scene graph environmental model of the present disclosure;
fig. 3 is a schematic diagram of hierarchical path planning of the present disclosure.
The specific embodiment is as follows:
the disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
An embodiment of the present disclosure provides an autonomous indoor environment model construction and maintenance method, including:
step one: describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
step two: based on the three-dimensional scene map environment model, generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework;
step three: determining a target point to be explored, calculating information gain and path cost from the current position of the mobile robot to the target point to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
step four: and solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment, and maintaining and updating the indoor environment model.
As one embodiment, in step one, a hierarchical environment representation is used to describe an indoor scene using different levels of graph structures, nodes in the scene graph structure representing object, place, room and building information in the indoor environment, and edges of the graph structure representing conceptual attribute relationships between the nodes. The three-dimensional scene graph generation algorithm of the present disclosure can be deployed on a robot and can generate a high-precision scene graph in real time.
Based on the mobile robot, the mobile robot body is provided with a three-dimensional laser camera, a color depth camera, an inertial sensor measuring unit, an odometer and other sensors, and the three-dimensional laser camera, the color depth camera, the inertial sensor measuring unit, the odometer and other sensors are used for acquiring external environment images and the pose of the robot.
In the second step, the graph structures of the different levels are respectively a scene graph layer, a navigation layer and a dynamic layer, and the three-layer structures of the scene graph layer, the navigation layer and the dynamic layer form a layered three-dimensional scene graph environment model.
As an embodiment, the method for constructing the scene map layer comprises the following steps: the method comprises the steps of respectively acquiring an indoor environment image and the pose of a mobile robot through an RGBD camera and an inertial measurement unit, transmitting the acquired indoor environment image into a semantic segmentation module for recognition, converting the recognized object into point clouds through an open source PCL point cloud library, clustering the point clouds into different object nodes, performing point cloud expansion operation on the recognized obstacle to separate room nodes, organizing the object and the room nodes through a scene map generating method (scene graph generation), and dividing connecting edges in the scene map into passable paths and non-passable paths according to the obstacle relation in a navigation layer.
The navigation layer is based on an incremental grid map, is static, and after a mobile robot determines a target to be explored, a path planning algorithm A can be utilized to calculate the priority of each node in the grid map by using a heuristic function, and the optimal node is traversed to obtain a shortest path which is used as a global navigation path; the dynamic layer is used for describing dynamic factors in the environment, the dynamic factors are used as dynamic layers, a local navigation path is generated based on the dynamic layer, wherein the local navigation path represents the maximum range which can be perceived by the robot currently, a DWA algorithm and the like is adopted to generate the local path in the perceived range, and the path is directly used for navigation of the mobile robot.
Adopting a hierarchical path planning framework to realize path planning in a dynamic environment with large indoor crowd flow and large object position change rate, generating a global navigation path by using a path planning algorithm such as A after a robot determines a target point to be explored based on a static navigation layer,
the construction of the navigation layer is based on an incremental grid map and is given by a synchronous map construction and positioning module (Simultaneously Localization and Mapping, SLAM), wherein the grid map can be constructed by adopting a laser SLAM algorithm commonly used in Gmaging and the like;
the robot generates a local navigation path based on the dynamic layer by adopting algorithms such as DWA and the like, and the local path considers dynamic obstacles reflected in the dynamic layer, so that the robot can flexibly avoid the obstacles in a dynamic complex environment.
As an embodiment, in order to enable the mobile robot to quickly realize the exploration of the whole unknown environment, a mobile robot quick unknown environment exploration method is designed. Robots need to move all the way to the direction of high comprehensive yields to explore unknown boundaries.
In the third step, the method for determining the target point to be explored comprises the following steps:
the method comprises the steps of firstly extracting boundaries from a grid map based on a navigation layer, then aggregating boundary points, traversing the found boundary points by adopting a point query mode, searching a neighborhood of the boundary points, continuing searching the neighborhood if the neighborhood points are still boundary points, and repeatedly carrying out the process until the boundary points cannot be found, wherein all the found boundary points are aggregated into a class, and the central point of the class is determined as a target point to be explored.
After determining the target point to be explored, calculating the information gain and path cost from the current position of the mobile robot to the target point to be explored, evaluating a plurality of target points to be explored by adopting an evaluation function, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point by using a path planning algorithm, repeatedly performing the process, continuously acquiring environment information by using an instant positioning and mapping algorithm in the moving process, and realizing the positioning of the mobile robot in the environment until the boundary point does not exist in the whole navigation layer, thereby completing the preliminary construction of the whole environment model.
Specifically, the information gain I and the path cost C from the current position of the robot to the target point to be explored are calculated. The information gain I is calculated by searching all boundary points belonging to the target point class near the target point to be explored, assigning a probability of 0.5, and calculating the information entropy of the boundary points, wherein the information entropy is used as the information gain. C may be derived from a equal path planning algorithm. Using an evaluation function g=ce λI To evaluate a plurality of target points, where λ is considered an adjustable coefficient.
And selecting a better target point, and searching a collision-free path from the current position to the optimal target point in the grid map by using an A-path planning algorithm. The process is repeatedly carried out, the robot utilizes an instant positioning and mapping algorithm (SLAM) (such as Gmaging and other existing algorithms) in the moving process, the environment model is updated through environment information acquired by a sensor carried by the robot, the positioning of the robot in an environment map is realized, and the preliminary construction of the whole environment model is completed until no boundary point exists in the whole navigation layer.
In the fourth step, the optimal action of the mobile robot under the current observation is solved by using a part of observable circulating reinforcement learning algorithm, the change of multiple objects in the indoor environment is obtained, and the maintenance and the update of the indoor environment model are carried out.
After the indoor environment model of the mobile robot is constructed, the environment model of the mobile robot may be continuously changed during long-term service of the mobile robot. The mobile robot can not observe objects in all rooms repeatedly and continuously, so that computing resources are wasted, errors exist in robot body recognition, and therefore along with the continuous increase of the service process of the robot, the POMDP (partially observable Markov decision process) framework and algorithm proposed by the present disclosure control the strategy that the robot patrol between different rooms and places in a room, so that the robot can patrol in the room or place where the objects change frequently, so that the environment model can be updated stably and rapidly for a long time.
And abstracting object distribution and update frequency in the environment into a state space based on a partially observable Markov decision process to model, constructing belief functions, state transfer functions and the like, and solving the problem by using a Monte Carlo tree search method to control a strategy of updating an environment model of a patrol room of the robot. The system parameters are assumed to be known in the POMDP planning process. The POMDP module can simplify an environment model, accept target detection observation values of the robot, update belief values of real states, and determine the sequence of patrol rooms or places of the robot.
Specifically, by constructing a three-dimensional scene map, analyzing the position change of the object node and the update time and frequency, establishing a state space S, a belief state B, an action set A, a state transfer function T, an observation function O, a return function R and a discount factor gamma, solving the optimal action under the current observation by using a part of observable cyclic reinforcement learning algorithm, so that the robot can observe more object changes, and the environment model can be updated rapidly.
The state space S is divided into two systems, including the state S of object change in each room room And robot pose state S robot . Action set a refers to actions that can be taken by a robot to patrol indoors, a= (Move) i Unseerve), where Move i Representative moves to the ith room and Observe represents the view room. Observation space O t The distribution and update conditions of the objects observed by the robot in the current room at the moment t through the sensors and the positions of the robots are defined. Due to distance, occlusion and sensor fine reading problems, the observation of the robot contains noise, and the observation function can be expressed as
O(a t ,S t+1 ,O t+1 )＝Pro(o t+1 |S t+1 ,a t )+Err,
Wherein O (S) t+1 ,a t ,O t+1 ) Indicating that the robot takes action a at time t t The observation amount at time t+1 is O t+1 And the environmental state is S t+1 Is S t+1 And a t The sum of conditional probability and observation error probability in the case. Err is sensor noise and is inversely proportional to the distance of the robot from the object. The state transfer function is defined as T (s, a, s ')=p (s' |s, a), and the state changes after the Move action or after the unserve action is performed. Belief state B t+1 ＝Pro(S t+1 |B t ,o t A+t), representing the posterior probability distribution for each state, with markov, calculated from historical observations and actions. The reward function R represents the reward value of the robot taking action a in state s, if the robot observes an object change, then reward +10. To prevent the robot from observing only one room, a threshold is set so that the robot has a chance to search for other rooms or places where there may be object changes.
Example 2
In one embodiment of the present disclosure, an autonomous indoor environment model building and maintaining system is provided, based on a mobile robot, a control platform of the mobile robot includes:
the three-dimensional scene map environment construction module: the method comprises the steps of describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
and a path planning module: the method comprises the steps of generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework based on a three-dimensional scene map environment model;
the active exploration module is used for determining target points to be explored, calculating information gain and path cost from the current position of the mobile robot to the target points to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
the autonomous patrol module is used for solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment and carrying out maintenance and update of the indoor environment model.
The body of the mobile robot is also provided with a three-dimensional laser camera, a depth camera, an inertial sensor measuring unit, an odometer and other sensors.
The three-dimensional scene map environment model construction module of the system can construct the collected RGBD image and inertial sensor information increment into a three-dimensional hierarchical scene map in real time. The path planning module can construct a collision-free safety path between the departure point and the end point according to the requirement. The active exploration module may direct the robot to explore toward a map boundary information gain maximum direction until the indoor map is all known. The autonomous patrol module can guide the robot to move and observe in different rooms or places in the room so as to achieve the purpose of actively updating the environment model. The mobile robot needs to travel in an environment with dynamic change of indoor dense crowd and higher object density, and the rapid and stable path planning capability is not only a basis that the robot can traverse a plurality of navigation points, but also a precondition for realizing autonomous exploration environment and active patrol.
Example 3
In one embodiment of the disclosure, a non-transitory computer readable storage medium is provided for storing computer instructions that, when executed by a processor, implement the method steps of autonomous construction and maintenance of an indoor environment model.
Example 4
In one embodiment of the present disclosure, there is provided an electronic device including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the steps of the method for realizing autonomous construction and maintenance of the indoor environment model.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the specific embodiments of the present disclosure have been described above with reference to the drawings, it should be understood that the present disclosure is not limited to the embodiments, and that various modifications and changes can be made by one skilled in the art without inventive effort on the basis of the technical solutions of the present disclosure while remaining within the scope of the present disclosure.
Claims (10)
1. An autonomous construction and maintenance method for an indoor environment model is characterized by comprising the following steps:
describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
based on the three-dimensional scene map environment model, generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework;
determining a target point to be explored, calculating information gain and path cost from the current position of the mobile robot to the target point to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
and solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment, and maintaining and updating the indoor environment model.
2. An autonomous building and maintenance method for an indoor environment model as claimed in claim 1, wherein the nodes in the graph structure represent objects, places, rooms and building information in the indoor environment, and the edges of the graph structure represent conceptual attribute relationships between the nodes.
3. The method for autonomously constructing and maintaining an indoor environment model according to claim 1, wherein the graph structures of different levels are a path layer, a navigation layer and a dynamic layer respectively, and the three-layer structures of the path layer, the navigation layer and the dynamic layer form a layered three-dimensional scene map environment model.
4. The method for autonomously constructing and maintaining an indoor environment model according to claim 3, wherein the path layer constructing method comprises the steps of: the method comprises the steps of acquiring an indoor environment image and a mobile robot pose, identifying the acquired indoor environment image, converting an identified object into point clouds, clustering the point clouds into different object nodes, performing expansion operation on the identified obstacle to serve as separated room nodes, dividing communicable path points into place nodes, connecting the room nodes to building nodes, extracting the robot IMU information into paths and storing the paths as path layers.
5. The method for autonomously constructing and maintaining an indoor environment model according to claim 3, wherein the navigation layer is based on an incremental grid map, the navigation layer is static, and a global navigation path can be generated by using a path planning algorithm after a mobile robot determines a target to be explored; the dynamic layer is used for describing dynamic factors in the environment, the dynamic factors are used as dynamic levels, and a local navigation path of the neighborhood is generated based on the dynamic layer.
6. The method for autonomously constructing and maintaining an indoor environment model according to claim 1, wherein the method for determining the target point to be explored is as follows: based on the grid map of the navigation layer, firstly extracting boundaries from the grid map, and then aggregating boundary points to determine target points to be explored.
7. The autonomous construction and maintenance method for an indoor environment model according to claim 1, wherein after determining target points to be explored, calculating information gain and path cost from a current position of a mobile robot to the target points to be explored, evaluating a plurality of target points to be explored by using an evaluation function, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point by using a path planning algorithm, repeatedly performing the process, continuously acquiring environment information and realizing positioning of the mobile robot in the environment by using an instant positioning and mapping algorithm in a moving process until no boundary point exists in the whole navigation layer, and completing preliminary construction of the whole environment model.
8. An autonomous construction and maintenance system for an indoor environment model, wherein a control platform of a mobile robot comprises:
the three-dimensional scene map environment construction module: the method comprises the steps of describing an indoor scene by using graph structures of different levels, and constructing a three-dimensional scene map environment model of the mobile robot;
and a path planning module: the method comprises the steps of generating a global navigation path and a local navigation path of a neighborhood by adopting a hierarchical path planning framework based on a three-dimensional scene map environment model;
the active exploration module is used for determining target points to be explored, calculating information gain and path cost from the current position of the mobile robot to the target points to be explored, selecting an optimal target point, searching a collision-free path from the current position to the optimal target point, and continuously iterating until the conditions are met, so as to complete autonomous construction of an indoor environment model;
the autonomous patrol module is used for solving the optimal action of the mobile robot under the current observation by utilizing a part of observable circulating reinforcement learning algorithm, acquiring the change of multiple objects in the indoor environment and carrying out maintenance and update of the indoor environment model.
9. A non-transitory computer readable storage medium storing computer instructions which, when executed by a processor, implement a method of autonomous construction and maintenance of an indoor environment model according to any of claims 1-7.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and wherein the computer program is stored in the memory, said processor executing said computer program stored in the memory when the electronic device is running, to cause the electronic device to perform an autonomous construction and maintenance method for implementing an indoor environment model according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310339805.8A CN116358555A (en) | 2023-03-31 | 2023-03-31 | Autonomous construction and maintenance method and system for indoor environment model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310339805.8A CN116358555A (en) | 2023-03-31 | 2023-03-31 | Autonomous construction and maintenance method and system for indoor environment model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116358555A true CN116358555A (en) | 2023-06-30 |
Family
ID=86931086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310339805.8A Pending CN116358555A (en) | 2023-03-31 | 2023-03-31 | Autonomous construction and maintenance method and system for indoor environment model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116358555A (en) |
-
2023
- 2023-03-31 CN CN202310339805.8A patent/CN116358555A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dai et al. | Fast frontier-based information-driven autonomous exploration with an mav | |
| Schmid et al. | An efficient sampling-based method for online informative path planning in unknown environments | |
| Bircher et al. | Receding horizon path planning for 3D exploration and surface inspection | |
| CN113110457B (en) | Autonomous coverage inspection method for intelligent robot in indoor complex dynamic environment | |
| EP3384360B1 (en) | Simultaneous mapping and planning by a robot | |
| Hoppe et al. | Photogrammetric camera network design for micro aerial vehicles | |
| Kaufman et al. | Autonomous exploration by expected information gain from probabilistic occupancy grid mapping | |
| Respall et al. | Fast sampling-based next-best-view exploration algorithm for a MAV | |
| CN113110455B (en) | Multi-robot collaborative exploration method, device and system for unknown initial state | |
| Saulnier et al. | Information theoretic active exploration in signed distance fields | |
| CN103901891A (en) | Dynamic particle tree SLAM algorithm based on hierarchical structure | |
| Guizilini et al. | Dynamic hilbert maps: Real-time occupancy predictions in changing environments | |
| CN114119920A (en) | Three-dimensional point cloud map construction method and system | |
| Chen et al. | Multilayer mapping kit for autonomous UAV navigation | |
| CN113433937B (en) | Hierarchical navigation obstacle avoidance system and hierarchical navigation obstacle avoidance method based on heuristic exploration | |
| Hauer et al. | Multi-scale perception and path planning on probabilistic obstacle maps | |
| Li et al. | Learning-augmented model-based planning for visual exploration | |
| Bouman et al. | Adaptive coverage path planning for efficient exploration of unknown environments | |
| Leung et al. | Evaluating set measurement likelihoods in random-finite-set slam | |
| CN116358555A (en) | Autonomous construction and maintenance method and system for indoor environment model | |
| Iser et al. | AntSLAM: global map optimization using swarm intelligence | |
| CN115993817A (en) | Autonomous exploration method, device and medium for tensor field driven hierarchical path planning | |
| Zhang et al. | Exploration with global consistency using real-time re-integration and active loop closure | |
| Li et al. | Object-Aware View Planning for Autonomous 3D Model Reconstruction of Buildings Using a Mobile Robot | |
| Ryu et al. | Local map-based exploration for mobile robots |
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 |