CN116147637B

CN116147637B - Method, device, equipment and storage medium for generating occupied grid map

Info

Publication number: CN116147637B
Application number: CN202310444024.5A
Authority: CN
Inventors: 林淦斌; 张学彦; 叶航
Original assignee: Fuqin Intelligent Technology Kunshan Co ltd
Current assignee: Fuqin Intelligent Technology Kunshan Co ltd
Priority date: 2023-04-24
Filing date: 2023-04-24
Publication date: 2023-06-30
Anticipated expiration: 2043-04-24
Also published as: CN116147637A

Abstract

The invention discloses a method, a device, equipment and a storage medium for generating an occupied grid map. The method comprises the following steps: acquiring state information and a planned path of the robot, and a grid map of a working area; determining an occupied grid covered by the occupied area of the robot at each sampling moment in the updating period in the grid map according to the state information and the planning path; marking the occupied time mark of the occupied grid corresponding to each sampling time in the updating period in the grid map; marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the update period. The problem that the occupied area of the robot cannot be mastered in time is solved, the conflict of planning paths of different robots in a working area is avoided, the collision of the robots in the operation process is avoided, and the operation safety of the robots is protected.

Description

Method, device, equipment and storage medium for generating occupied grid map

Technical Field

The present invention relates to the field of robot control technologies, and in particular, to a method, an apparatus, a device, and a storage medium for generating an occupied grid map.

Background

With the rising and rapid development of technologies such as artificial intelligence, big data, internet of things and automation technology, research of intelligent robots is receiving more and more attention. Robots often require path planning before performing tasks.

At present, a common path planning mode mainly performs path planning according to a starting point and an ending point of a robot executing a task and obstacles in a working area. This path planning approach is only applicable to scenarios where a single robot is present in the working area. When a plurality of working robots work in one working area at the same time, each robot must occupy a certain area in a static state or a running state, so that the area cannot pass through, and the path planning of other robots is influenced.

Therefore, it is necessary to acquire the area occupied by each robot at a timing. However, the position of the robot changes in real time when the robot runs in the working area, and the area occupied by the robot cannot be stored in advance in the map of the working area, so that the area occupied by the robot cannot be mastered in time, and the planned paths of different robots in the working area can collide, so that property loss is caused when the robot collides in the running process.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for generating an occupied grid map, which are used for reflecting the occupied condition of a robot by generating a self-occupied grid map with each occupied grid marked with an occupied time mark, so as to solve the problem that the occupied area of the robot cannot be mastered in time in the prior art, avoid the collision of planning paths of different robots in a working area, avoid the collision of the robots in the running process and protect the running safety of the robots.

According to an aspect of the present invention, there is provided a method for generating an occupied grid map, including:

acquiring state information and a planned path of the robot, and a grid map of the working area;

determining an occupied grid covered by the occupied area of the robot at each sampling moment in the updating period in the grid map according to the state information and the planning path;

marking an occupied time mark on an occupied grid corresponding to each sampling time in the updating period in the grid map;

marking all occupied grids in the updating period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the updating period.

According to another aspect of the present invention, there is provided a path planning method including:

the self-occupied grid map corresponding to the initial planning path of the robot is determined by adopting the method for generating the occupied grid map;

requesting a server to acquire the total occupied grid map of the working area;

performing conflict verification on the self-occupied grid map by adopting the total occupied grid map;

and if the self-occupied grid map does not have the conflict grid, determining an initial planning path corresponding to the self-occupied grid map as a target planning path of the robot.

According to another aspect of the present invention, there is provided an occupancy grid map generating apparatus, comprising:

the acquisition module is used for acquiring the state information and the planned path of the robot and a grid map of the working area;

the occupation determining module is used for determining an occupation grid covered by the occupation area of the robot at each sampling moment in the updating period in the grid map according to the state information and the planning path;

the grid marking module is used for marking the occupied grids corresponding to each sampling time in the updating period by using the occupied time mark in the grid map;

The map generation module is used for marking all the occupied grids in the update period according to the occupied grid marked occupied time marks corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the update period.

According to another aspect of the present invention, there is provided a path planning apparatus comprising:

the self-occupation map generation module is used for determining the self-occupation grid map corresponding to the initial planning path of the robot by adopting the generation method of the occupation grid map;

the total occupation map acquisition module is used for requesting the server to acquire the total occupation grid map of the working area;

the conflict verification module is used for carrying out conflict verification on the self-occupied grid map by adopting the total occupied grid map;

and the target path planning module is used for determining the initial planning path corresponding to the self-occupied grid map as the target planning path of the robot if the self-occupied grid map does not have a conflict grid.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of generating an occupancy grid map according to any one of the embodiments of the present invention or the method of path planning according to any one of the embodiments.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for generating an occupancy grid map according to any one of the embodiments of the present invention or the method for path planning according to any one of the embodiments, when executed.

The invention provides a method, a device, equipment and a storage medium for generating an occupied grid map, wherein the method comprises the following steps: acquiring state information and a planned path of the robot, and a grid map of a working area; determining an occupied grid covered by the occupied area of the robot at each sampling moment in the updating period in the grid map according to the state information and the planning path; marking the occupied time mark of the occupied grid corresponding to each sampling time in the updating period in the grid map; marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the update period. The occupation condition of the robot is reflected by generating the self-occupation grid map that each occupation grid of the robot is marked with the occupation moment mark, so that the problem that the occupied area of the robot cannot be mastered in time is solved, the conflict of planning paths of different robots in a working area is avoided, the collision of the robots in the operation process is avoided, and the operation safety of the robots is protected.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a method for generating an occupied grid map according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for generating an occupied grid map according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of an occupancy grid map before and after an occupancy grid for each sampling instant expands;

fig. 4 is a flowchart of a method for generating an occupied grid map according to a third embodiment of the present invention;

fig. 5 is a flowchart of a path planning method according to a fourth embodiment of the present invention;

Fig. 6 is a schematic structural diagram of a generating device for occupying a grid map according to a fifth embodiment of the present invention;

fig. 7 is a schematic structural diagram of a path planning apparatus according to a sixth embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device implementing a method for generating an occupied grid map or a method for path planning according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a method for generating an occupied grid map according to an embodiment of the present invention, where the embodiment is applicable to a robot generating a self-occupied grid map according to its own state, so as to reflect the situation of occupying an area in real time within a certain period of time. In the present invention, the robot may include: and the movable robots can automatically guide the transport vehicle, the cleaning robot, the service robot and the like to execute various tasks. The method may be performed by an occupancy grid map generating device, which may be implemented in hardware and/or software, the occupancy grid map generating device being configurable in an electronic device. As shown in fig. 1, the method includes:

s110, acquiring state information and planned paths of the robot and a grid map of a working area.

The state information of the robot refers to information capable of reflecting the current state of the robot, and may include, for example: dynamic and static state information (motion state or static state) and self attribute information (such as body width and body orientation) and dynamic information (such as initial position and motion speed) of the robot. The planned path refers to a path planned from an initial sampling time to an end sampling time in an update period.

The grid map of the work area is a map obtained by grid-forming a map of the work area. The size of each grid in the grid map can be determined according to factors such as the size of the working area, the task type of the robot, the precision requirement of the occupation information and the like, and can be 20cm

20cm, to which the embodiment of the invention is not limited.

Specifically, acquiring a static and dynamic state of the robot, and if the robot is in a motion state in an updating period, acquiring state information in the motion state, wherein the state information is used for determining an occupied area of the robot; and acquiring a grid map of the working area where the robot is located from the server, wherein the grid map is used for marking grids covered by the occupied area in the grid map.

S120, determining an occupied grid covered by the occupied area of the robot at each sampling time in the updating period in the grid map according to the state information and the planning path.

The update period refers to a period of time for the robot to update the occupied grid information, and the period of time may be a fixed period of time or an unfixed period of time. For example, a usage scenario for an unfixed time period may be: when the robot is changed from a static state to a moving state and the occupied area is changed, updating the occupied grid information, wherein the time of two adjacent updating times forms an updating period; or when the planned path of the robot changes, updating the occupied grid information, and forming an updating period by two adjacent updating times. The usage scenario for a fixed time period may be: in the robot motion state, the occupied grid information is updated with a fixed updating period so as to adjust the occupied grid information in time according to the actual motion trail of the robot, so that the occupied grid information is more in line with the actual motion trail of the robot, and the accuracy of the occupied grid information is improved.

Typically, a plurality of sampling moments (the sampling moments may be determined according to a sampling frequency) may be included in one update period, and the occupied area may be determined according to state information of the robot at each sampling moment.

Specifically, since the robot occupies a certain area in the working area regardless of the motion state or the static state, the occupied area of the robot at each sampling time in the update period can be determined according to the state information, and the grid covered by the occupied area at each sampling time is determined as the occupied grid in the grid map, so that the occupied grid corresponding to each sampling time of the robot is determined in the grid map.

S130, marking the occupied time mark of the occupied grid corresponding to each sampling time in the updating period in the grid map.

The time of occupation identifier may be understood as a time for reflecting the occupation of the grid by the robot. The occupied time mark can be directly expressed by a time value of the robot reaching the occupied grid; alternatively, the field representation may be a field representation having an association with the arrival time, such as a natural number sequence, an arithmetic sequence, and a gradation value sequence.

Exemplary, for the robot, each sampling instant in the update period

Corresponding occupied grids are sequentially marked as 10:05:30, 10:05:32, 10:05:35, … …, 10:08:27 and 10:08:28 by arrival time; the natural number sequence is adopted to be marked as follows: 0,1,2, …, n-1, n; the method adopts an arithmetic gray value sequence with gray value interval of 5 to mark as follows: 5,10,15, …,150, 155.

Specifically, in the grid map, the occupied grids corresponding to each sampling time in the update period are respectively marked by using the occupied time mark, the marked occupied grids represent occupied by the robot, and the marked occupied time mark reflects the occupied time of the occupied grids.

And S140, marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the update period.

Among them, the self-occupied grid map may be understood as a grid map for reflecting grid occupancy information of the robot itself. Each grid occupied by the robot in the grid map is marked with an occupied time mark. The grid occupancy information may include: the occupied time mark and the grid position information can also comprise the mark of a robot which occupies the grid.

Specifically, if the robot is in a motion state in the working area, a plurality of grids may be occupied between two sampling moments, and only the mark of the occupied grid corresponding to the sampling moment for marking the occupied moment cannot reflect the real-time occupied grid of the robot, so that all occupied grids in the update period also need to be marked according to the occupied moment mark marked by the occupied grid corresponding to each sampling moment, and a self-occupied grid map of which all occupied grids in the update period are marked with occupied moment marks of the robot is obtained, and the occupied moment of the robot on each occupied grid is reflected in real time.

For example, the manner of marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time may be: determining an intermediate occupation grid of the robot between adjacent sampling moments, determining a target occupation grid which is closest to the intermediate occupation grid and marked with an occupation moment mark, and marking the intermediate occupation grid by adopting the target occupation grid.

Or, for determining the middle occupied grid of the robot between adjacent sampling moments (such as the first moment and the second moment), the middle occupied grid can be marked by adopting the occupied moment identification of the first moment. Or the middle occupied grid can be marked by adopting the occupied time mark of the second time.

By marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, a self-occupied grid map with occupied time marks marked by each occupied grid of the robot can be generated, so that the robot can provide the occupied grids and occupied time.

According to the technical scheme, the occupied grids covered by the occupied areas corresponding to the sampling moments in the updating period are marked with the occupied moment marks in the grid map; all occupied grids in the update period are marked according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and a self-occupied grid map with the occupied time marks marked by each occupied grid of the robot is generated so as to reflect the occupied condition of the robot, solve the problem that the occupied area of the robot cannot be mastered in time, avoid the collision of planning paths of different robots in a working area, avoid the collision of the robots in the operation process, and protect the operation safety of the robots.

Example two

Fig. 2 is a flowchart of a method for generating an occupied grid map according to a second embodiment of the present invention, and the method for generating an occupied grid map by a robot in a motion state in the above embodiment is described in detail in this embodiment. As shown in fig. 2, the method includes:

S210, acquiring state information and a planned path of the robot and a grid map of a working area; if the robot keeps a motion state in the update period, the state information of the robot in the motion state includes: body orientation, body width, initial position, and speed of movement.

The body direction refers to the direction in which the front surface of the robot is directed, the body width refers to the width of the robot projected onto the ground, and the body direction of the automatic guided vehicle (Automated Guided Vehicle, AGV) refers to the head direction, and the body width refers to the body width. The initial position may be an initial position that is a projected point of the center of gravity point of the robot on the ground at an initial time.

S220, determining the position of the robot at each sampling moment in the updating period according to the initial position, the movement speed and the planned path.

Specifically, according to the initial position, the movement speed and the planned path of the robot, the position of the track point at each sampling time in the update period of the robot is calculated, and the position of the track point at each sampling time is determined as the position of the robot at each sampling time in the update period.

S230, for each sampling time, determining the occupied area of the robot according to the position, the body orientation and the body width of the robot.

Specifically, at each sampling time in the update period, the occupied area of the robot in the working area at the sampling time is determined according to the position of the robot and the acquired body orientation and body width of the robot at the sampling time.

S240, determining an occupied grid covered by the occupied area at each sampling time in the grid map.

Specifically, after determining the occupied area of the robot at each sampling time, determining an occupied grid covered by the occupied area of the robot at each sampling time in a grid map.

Illustratively, to maximize the force to protect the robot from damage, the occupancy grid covered by the occupancy zone may be: if the occupied area covers an area of any size within the grid, the grid is determined to be an occupied grid.

S250, marking the occupied time mark of the occupied grid corresponding to each sampling time in the updating period in the grid map.

Specifically, after determining the occupied grids corresponding to each sampling time in the updating period in the grid map, marking the occupied grids by adopting the occupied time marks corresponding to the sampling time when the robot arrives at the occupied grids so as to represent that the grids are occupied and the corresponding occupied time.

Optionally, the occupied time mark corresponding to each sampling time is represented by an arithmetic progression of gray values corresponding to each sampling time.

Specifically, in the gray value range of 0 to 255, a gray value arithmetic progression which is monotonously increased with time or a gray value arithmetic progression which is monotonously decreased with time is selected as the occupied time mark by selecting a preset gray value range and interval difference.

The two-dimensional image is utilized to simultaneously represent the space and time occupied state in the scene, the occupied grid can be visually seen through observing the gray level of the grid, the gray level of the occupied grid has monotonicity with the occupied time, and the early and late of the occupied time of the occupied grid can be reflected through the gray level of the occupied grid.

In a specific example, when the depth value of a grid which is not occupied in the grid map is defaulted to 0, gray values of 5-150 are selected to form monotone increasing gray value arithmetic progression of 5,10,15, …,150, 155 to be used as the occupied time mark of each sampling time. In another specific example, when the depth value of the unoccupied grid of the grid map is 255 by default, a gray value of 250-150 is selected to form a monotonically decreasing gray value arithmetic progression of 250,240,230, …,160,150 as the occupation time identifier of each sampling time. The depth difference between adjacent moments can enable moment information of occupying grids to be more visual.

S260, expanding the occupied grid of the current sampling time along the planned path for each current sampling time except for the ending sampling time in the updating period.

Specifically, for each current sampling time except for the end sampling time in the updating period, searching for the next grid by the body width of the robot according to the motion direction of the occupied grid corresponding to the current sampling time along the planned path; if the next grid is not marked, expanding the occupied grid corresponding to the current sampling time to the unmarked grid. Therefore, the occupied grid of the robot between the current sampling time and the next sampling time is obtained according to the occupied grid prediction of the sampling time.

S270, marking the expanded grids by adopting the occupied time marks corresponding to the occupied grids of the current sampling time until unlabeled grids are not searched.

Specifically, for the grids obtained by expanding the occupied grids according to the current sampling time, the occupied time identification corresponding to the current sampling time is adopted for marking, so as to indicate that the grids are occupied. If the occupied grid corresponding to the current sampling time cannot search for the unlabeled grid along the moving direction of the planning path, the fact that the possibly occupied grid of the planning path between the current sampling time and the next sampling time is marked is indicated, and at the moment, expansion and marking of the occupied grid of the current sampling time are completed. And if the current sampling time is not the ending sampling time, taking the next sampling time as a new current sampling time, repeatedly executing the steps of expanding the occupied grid of the current sampling time along the planning path for the current sampling time, and marking the expanded grid by adopting the occupied time mark corresponding to the occupied grid of the current sampling time until the unlabeled grid is not searched.

Fig. 3 is a schematic diagram of an occupancy grid map before and after the occupancy grid expands for each sampling instant. The left diagram in fig. 3 is a schematic diagram of the occupancy grid map obtained before the occupancy grid at each sampling time expands. For each current sampling time except for the ending sampling time in the updating period, after expanding the occupied grids of the current sampling time along the planning path, marking the expanded grids by adopting the occupied time mark corresponding to the occupied grids of the current sampling time to obtain a schematic diagram of the occupied grid map obtained after expanding the occupied grids of each sampling time shown in the right diagram in fig. 3

S280, obtaining a self-occupied grid map of the planning path of the robot in the updating period.

Specifically, for each current sampling time except for the end sampling time in the update period, steps S260 and S270 are repeatedly executed until the current sampling time is the end sampling time, so as to complete the process of marking the occupied grid of the robot in the update period, and obtain the self-occupied grid map of the planned path of the robot in the update period.

The robot generates the self-occupied grid map for representing the occupied area and occupied time by using the calculation resources of the robot, so that the role of a dispatching center in the dispatching of the robot is weakened, and the dispatching center is mainly used as a relay for message transmission. The design is convenient for utilizing the calculation resources of the robot, is more suitable for intelligent logic of human handling similar problems, and can be applied to a system for dispatching the robot by a central server and a self-organizing distributed robot system.

According to the technical scheme, under the condition that the robot is in a motion state, state information and a planning path of the robot and a grid map of a working area are obtained, and occupation time marks of occupation grids covered by the occupation area corresponding to each sampling time in an updating period are marked in the grid map; marking grids obtained by expanding the occupied grids at the current sampling time along the planning path by adopting the occupied time mark marked by the occupied grids at each sampling time to obtain a self-occupied grid map of the planning path of the robot in an updating period; the problem that the area occupied by the robot cannot be known in time because the position of the robot changes in real time when the robot runs in the working area and the map of the working area cannot be used for storing the area occupied by the robot in advance is solved, and the conflict of planning paths of different robots in the working area is avoided; meanwhile, the occupied time mark of the occupied grid mark at each sampling time is realized by adopting a grid expansion mode, and the grids obtained by expanding the grids at the sampling time along the planned path are marked, so that the calculation complexity of generating a self-occupied grid map is reduced, and the consumption of calculation resources of a robot is reduced.

Example III

Fig. 4 is a flowchart of a method for generating an occupied grid map according to a second embodiment of the present invention, where the method for generating an occupied grid map by a robot in a stationary state in the foregoing embodiment is described in detail. As shown in fig. 4, the method includes:

s310, if the robot keeps a static state in an updating period, acquiring state information of the robot and a grid map of a working area; wherein, the state information of the robot in the stationary state includes: body orientation, body width, and initial position.

S320, determining an occupied grid covered by the occupied area of the robot at the initial sampling moment in the grid map according to the body orientation, the body width and the initial position.

Specifically, at an initial sampling time in the updating period, according to the position of the robot and the acquired body orientation and body width of the robot at the initial sampling time, determining that an occupied area of the robot in a working area at the initial sampling time is in a grid map, and determining that a grid covered by the occupied area corresponding to the initial sampling time is an occupied grid corresponding to the initial sampling time.

If the robot remains stationary during the update period, the occupied area of the robot remains unchanged, so that the occupied grid covered by the occupied area at the initial sampling time in the grid map can be used to represent the occupied grid of the robot at each sampling time during the update period.

S330, marking the occupied grid corresponding to the initial sampling time in the updating period by adopting the target occupied time mark, and obtaining the self-occupied grid map of the robot in the updating period.

The target occupation time mark can be an occupation time mark corresponding to each sampling time, or can be a specific occupation time mark selected for use.

Specifically, when the robot keeps a static state in the update period, the occupied grids corresponding to each sampling time in the update period in the grid map are actually the same occupied grid, so that the occupied grids can be marked by adopting the occupied time marks corresponding to each sampling time.

For example, if the robot is in a stationary state, the occupancy grids corresponding to different sampling moments in the update time period are the same grid, and the occupancy moment mark marked by the occupancy grid may be the whole time period of the update time period, or may be an identification value corresponding to the update time period, such as a specific gray value (e.g. 255), or a specific field (e.g. 1111, or FFFF), which indicates that the robot is always occupied in a new time period. It should be noted that the time stamp used to indicate the occupancy time of the marking occupancy grid in the stationary state can no longer be used to mark the occupancy grid of the robot in the moving state.

Optionally, the target occupation time mark is a target gray value, and the target gray value is not equal to the gray value corresponding to any sampling time; the target gray value characterizes the occupancy grid as being occupied continuously for the time of the update period.

Specifically, if the occupied time mark adopts gray value to represent, and the occupied time mark corresponding to each sampling time is adopted to mark the occupied grid, then one occupied grid is marked with a plurality of gray values, so that the intuitiveness of the occupied grid is not strong enough, therefore, a target gray value which is not equal to the gray value corresponding to any sampling time can be selected as the target occupied time mark, the occupied grid is continuously occupied in the time of the updating period, and the occupied time of the occupied grid can be intuitively judged by observing the gray value of the occupied grid.

According to the technical scheme, under the condition that the robot is in a static state, state information of the robot and a grid map of a working area are obtained; and marking the occupied grid corresponding to the initial sampling time in the updating period by adopting a target occupied time mark in the grid map to obtain the self-occupied grid map of the robot in the updating period. The robot in the static state can determine the area occupation condition of the robot, so that the occupation information of the robot in the static state in the working area can be obtained, the collision of planning paths of different robots in the working area is avoided, the collision of the robots in the running process is avoided, and the running safety of the robots is protected.

Example IV

Fig. 5 is a flowchart of a path planning method provided in a fourth embodiment of the present invention, where the present embodiment may be applicable to a case where a robot uses a total grid occupation map to check whether a conflict occurs in a self-occupation grid map corresponding to a planned path. The method may be performed by a path planning device, which may be implemented in hardware and/or software, which may be configured in an electronic device. As shown in fig. 5, the method includes:

s410, determining a self-occupied grid map corresponding to the initial planning path of the robot by adopting the method for generating the occupied grid map.

The initial planning path can be understood as a planning path determined by the robot by adopting a conventional path planning algorithm according to a map of a working area and received task information. Conventional static obstacles in the map of the work area can be considered when determining the initial planned path, but the occupied area of other robots is not considered, i.e. the initial planned path may have a risk of collision with the motion paths of other robots in the work area. The steps of determining the planned path according to the conventional path planning algorithm are not limited and are not repeated in the embodiments of the present invention.

Specifically, by adopting the method for generating the occupied grid map, the occupied grids covered by the occupied areas of the robots at each sampling moment in the grid map in the updating period are determined according to the state information and the initial planning path; marking the occupied time mark of the occupied grid corresponding to each sampling time in the updating period in the grid map of the working area; marking all the occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the initial planning path of the robot in the update period.

S420, requesting the server to acquire the total occupied grid map of the working area.

After determining the target planning path (i.e. the final planning path which does not conflict with the occupied area of any robot) of the robot in the working area, uploading the self-occupied grid map corresponding to the target planning path to the server. The total occupied grid map is a map obtained by summarizing self-occupied grid maps uploaded by all robots in a working area by a server.

Specifically, after the robot generates the occupied grid map corresponding to the initial planning path, it is further required to determine whether the self-occupied grid map corresponding to the initial planning path conflicts with the occupancy of other robots operating in the working area, so as to determine whether the robot can operate according to the initial planning path. Therefore, it is necessary to request the server to acquire the total occupied grid map of the work area in order to acquire the occupied grids and occupied times of other robots within the work area.

S430, performing conflict verification on the self-occupied grid map by adopting the total occupied grid map.

Specifically, the self-occupied grid map corresponding to the initial planning path is compared with the total occupied grid map, whether the occupied time mark of each occupied grid in the self-occupied grid map conflicts with the occupied time mark of the corresponding grid in the total occupied grid map or not is determined, and therefore conflict verification of the initial planning path is achieved.

S440, if the self-occupied grid map does not have a conflict grid, determining an initial planning path corresponding to the self-occupied grid map as a target planning path of the robot.

The conflict grid is a grid which conflicts with the occupied moment identifiers of the occupied grids of other robots in the total grid map.

Specifically, if the self-occupied grid map does not have a conflict grid, the initial planning path of the robot does not conflict with the motion path of any robot in the working area, so that the initial planning path corresponding to the self-occupied grid map can be determined as the target planning path of the robot, and the robot is controlled to run along the target planning path.

Optionally, after determining the target planned path of the robot, the method further includes:

And uploading the self-occupied grid map corresponding to the target planning path to the server, so that the server updates the total grid map of the working area according to the self-occupied grid map.

Specifically, after each time the robot generates the self-occupied grid map corresponding to the target planning path, the self-occupied grid map is uploaded to the server, so that the server can receive the self-occupied grid maps uploaded by all robots in the working area, and the self-occupied grid maps of all robots are summarized to obtain the total grid map of the working area. The total grid map records the occupancy grid and occupancy time of all stationary or moving robots within the work area.

The method comprises the steps that a self-occupied grid map uploaded by a robot is received at a server, the self-occupied grid map is adopted to update a total grid map of a working area, maintenance of the total grid map is achieved, changes of occupied areas of all robots in the working area are updated in time, an important reference basis is provided for path planning of a plurality of robots existing in the working area at the same time, occupied grids passing in the same time or in a similar time period are avoided during path planning, and the planned paths are prevented from conflicting with planned paths of other robots.

S450, if the conflict grid exists in the self-occupied grid map, setting an area where the conflict grid is located in the grid map of the working area as a forbidden area within forbidden time, wherein the forbidden time is determined according to the occupied time identification corresponding to the conflict grid.

The forbidden area is an area where the robot is forbidden to pass, and the robot can possibly change in position at any time in the running process, so that the forbidden area has certain time limit, and the robot is forbidden to pass only in the forbidden time. The forbidden time is a time corresponding to the occupied time mark of the conflict grid, and the forbidden time can be one time or one time period.

Specifically, the existence of the conflict grid in the self-occupied grid map indicates that the conflict may occur with the motion paths of other robots, and the initial planning path corresponding to the self-occupied grid map is determined as the target planning path of the robot, which may cause the collision between the robot and other robots in the working area. Therefore, the planned path needs to be regenerated avoiding the occupied time of the collision grid.

In order to enable the robot to avoid the conflict grid in the conflict time when regenerating the planned path, setting the area where the conflict grid is located as a forbidden area in the forbidden time, and determining the forbidden time according to the occupied time identification corresponding to the conflict grid.

For example, the manner in which the area where the conflict grid is located is set as the disabled area within the disabled time may be: marked on the conflict grid as a disable flag that can carry a disable time.

S460, updating an initial planning path of the robot based on a non-forbidden area in the grid map of the working area.

Wherein the non-disabled area comprises: areas that are not disabled at any time during the update period, and disabled areas that are outside of the disabled time.

Specifically, after the grid map of the working area sets the forbidden area within the forbidden time, a conventional path planning algorithm is adopted to redetermine a new initial planning path based on the non-forbidden area in the grid map of the working area and the received task information, and the initial planning path of the robot is updated by adopting the new initial planning path.

S470, for the updated initial planning path of the robot, returning to the step of determining the self-occupied grid map of the robot until the target planning path is obtained or the target planning path does not exist.

Specifically, for the updated initial planned path, returning to step S410, and executing the initial planned path determined for the robot, where the self-occupied grid map of the robot is determined by using the method for generating the occupied grid map provided by the present invention. And determining the updated initial planning path corresponding to the self-occupied grid map as a target planning path of the robot until the self-occupied grid map corresponding to the updated initial planning path does not have a conflict grid. Or returning to the execution times to reach the preset times, and determining that the target planning path does not exist in the working area.

Optionally, if the target planned path does not exist, sending indication information to the robot, where the indication information includes: delay planning instructions or path planning failure information.

Specifically, if no target planning path exists in the working area, the fact that a path which does not have conflict cannot be expected is indicated, so that a delay planning instruction is sent to the robot, and path planning is performed after waiting for a period of time; or sending path planning failure information to the robot, informing the robot that the path planning fails, and failing to execute the work task, so that the server can transfer the work task to other robots for completion.

According to the technical scheme, the self-occupied grid map of the robot is determined by adopting the method for generating the occupied grid map, which is determined by the robot, for the initial planning path; requesting a server to acquire a total occupied grid map of a working area; performing conflict verification on the self-occupied grid map corresponding to the initial planning path by adopting the total occupied grid map; if the self-occupied grid map does not have the conflict grid, determining an initial planning path corresponding to the self-occupied grid map as a target planning path of the robot. Under the condition that a plurality of running robots exist in the working area at the same time, the initial planning path is checked according to the self-occupied grid map and the total occupied grid map corresponding to the initial planning path, and then the initial planning path is checked and then is determined to be a target planning path, so that the robots are prevented from colliding in the running process, and the running safety of the robots is protected.

Optionally, if the occupation time mark corresponding to each sampling time is represented by an arithmetic sequence of gray values corresponding to each sampling time, the performing conflict verification on the self-occupation grid map by using the total occupation grid map includes:

calculating the difference value of the occupied moment identifiers corresponding to the same occupied grid in the self-occupied grid map and the total occupied grid map;

if the absolute value of the difference value is smaller than a preset threshold value, determining that the occupied grid is a conflict grid;

and if the absolute value of the difference value is larger than or equal to a preset threshold value, determining that the occupied grid is a non-conflict grid.

Specifically, if the occupied time mark corresponding to each sampling time is represented by an arithmetic sequence of gray values corresponding to each sampling time, the self-occupied grid map can be checked for conflict by comparing the gray values of the occupied grids, and whether the conflict grid exists in the self-occupied grid map is judged. The specific process of conflict verification is as follows: and calculating the difference value of the occupied time marks corresponding to the same occupied grid in the self-occupied grid map and the total occupied grid map, namely the gray level difference value. If the absolute value of the difference is smaller than the preset threshold, the robot is close to the other robots at the occupied time of the occupied grid, and the risk of collision possibly exists, so that the occupied grid is determined to be a collision grid. If the absolute value of the difference value is larger than the preset threshold value, the fact that the difference between the occupied time of the occupied grid of the robot and the occupied time of other robots in the occupied grid is longer is indicated, and the risk of collision does not exist, so that the occupied grid is determined to be a non-collision grid.

By calculating whether the difference value of the occupied time marks corresponding to the same occupied grid in the self-occupied grid map and the total occupied grid map is within a threshold range or not, whether the occupied grid is a conflict grid or not is judged, a certain prediction error exists in the occupied time marks of the grids, the influence on conflict verification of an initial planning path caused by the prediction error of the occupied time of the occupied grid is reduced, and the running safety of the robot is further ensured.

Example five

Fig. 6 is a schematic structural diagram of a generating device for an occupied grid map according to a fifth embodiment of the present invention. As shown in fig. 6, the apparatus includes:

an obtaining module 510, configured to obtain state information and a planned path of the robot, and a grid map of the working area;

the occupation determining module 520 is configured to determine an occupation grid covered by the occupation area of the robot at each sampling time in the update period in the grid map according to the state information and the planned path;

a grid marking module 530, configured to mark, in the grid map, an occupation time identifier for an occupation grid corresponding to each sampling time in the update period;

the map generating module 540 is configured to mark all the occupied grids in the update period according to the occupied time identifiers marked by the occupied grids corresponding to each sampling time, and obtain a self-occupied grid map of the planned path of the robot in the update period.

Optionally, if the robot maintains the motion state in the update period, the state information of the robot in the motion state includes: body orientation, body width, initial position, and speed of movement; accordingly, the occupancy determination module 520 is specifically configured to:

determining the position of the robot at each sampling moment in an updating period according to the initial position, the movement speed and the planning path;

for each sampling moment, determining an occupied area of the robot according to the position, the body orientation and the body width of the robot;

and determining an occupied grid covered by the occupied area at each sampling time in the grid map.

Optionally, the grid marking module 530 is specifically configured to:

expanding an occupied grid of the current sampling time along a planning path for each current sampling time except for the ending sampling time in the updating period;

marking the expanded grids by adopting the occupied time mark corresponding to the occupied grid at the current sampling time until unlabeled grids are not searched.

Optionally, if the robot remains in a stationary state in the update period, the state information of the robot in the stationary state includes: body orientation, body width, and initial position; correspondingly, the device further comprises:

the occupied area determining module is used for determining an occupied grid covered by the occupied area of the robot at the initial sampling moment in a grid map according to the body orientation, the body width and the initial position if the robot body keeps a static state in the updating period;

and the occupied grid marking module is used for marking the occupied grid corresponding to the initial sampling time by adopting a target occupied time mark to obtain a self-occupied grid map of the robot in the updating period.

The generation device of the occupied grid map provided by the embodiment of the invention can execute the generation method of the occupied grid map provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example six

Fig. 7 is a schematic structural diagram of a generating device for an occupied grid map according to a sixth embodiment of the present invention. As shown in fig. 7, the apparatus includes:

the self-occupation map generation module 610 is configured to determine a self-occupation grid map corresponding to an initial planning path of the robot by using the generation method of the occupation grid map provided by the present invention;

a total occupation map obtaining module 620, configured to request a server to obtain a total occupation grid map of the working area;

the conflict verification module 630 is configured to perform conflict verification on the self-occupied grid map by using the total occupied grid map;

and the target path planning module 640 is configured to determine an initial planned path corresponding to the self-occupied grid map as a target planned path of the robot if the self-occupied grid map does not have a conflict grid.

Optionally, if the occupied time mark corresponding to each sampling time is represented by an arithmetic progression of gray values corresponding to each sampling time, the conflict verification module 630 is specifically configured to:

Optionally, the method further comprises:

the forbidden area setting module is used for setting an area where the conflict grid is located in the grid map of the working area as a forbidden area within forbidden time after the conflict verification is carried out on the self-occupied grid map by adopting the total occupied grid map, and the forbidden time is determined according to the occupied time mark corresponding to the conflict grid if the conflict grid exists in the self-occupied grid map;

the planning path updating module is used for updating the initial planning path of the robot based on a non-forbidden area in the grid map of the working area;

and the return execution module is used for returning to the step of determining the self-occupied grid map of the robot for the updated initial planning path of the robot until the target planning path is obtained or the target planning path does not exist.

Optionally, the method further comprises:

and the map uploading module is used for uploading the self-occupied grid map corresponding to the target planning path of the robot to the server after the target planning path of the robot is determined, so that the server updates the total grid map of the working area according to the self-occupied grid map.

The path planning device provided by the embodiment of the invention can execute the path planning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example seven

Fig. 8 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, for example, the generation method of the occupancy grid map or the path planning method.

In some embodiments, the method of generating an occupancy grid map or the method of path planning may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described occupancy grid map generation method or the route planning method may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the occupancy grid map generation method or the path planning method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of generating an occupancy grid map, applied to a robot operating within a work area, the method comprising:

marking all occupied grids in the updating period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the updating period;

if the robot keeps a motion state in the update period, the state information of the robot in the motion state includes: body orientation, body width, initial position, and speed of movement; correspondingly, determining an occupied grid covered by the occupied area of the robot at each sampling time in the updating period in the grid map according to the state information and the planning path comprises the following steps:

2. The method according to claim 1, wherein marking all occupancy grids in the update period according to the occupancy time identifiers marked by the occupancy grids corresponding to the sampling times comprises:

3. A method according to any one of claims 1-2, characterized in that the time-of-occupation identification for each sample time is represented by an arithmetic progression of the gray values for each sample time.

4. The method of claim 1, wherein if the robot remains stationary for the update period, the state information of the robot in the stationary state comprises: body orientation, body width, and initial position; the method further comprises the steps of:

determining an occupied grid covered by the occupied area of the robot at the initial sampling moment in a grid map according to the body orientation, the body width and the initial position;

And marking the occupied grid corresponding to the initial sampling time by adopting a target occupied time mark to obtain a self-occupied grid map of the robot in the updating period.

5. The method of claim 4, wherein the target occupancy time is identified as a target gray value, and the target gray value is not equal to a gray value corresponding to any sampling time; the target gray value characterizes the occupancy grid as being occupied continuously for the time of the update period.

6. A path planning method applied to a robot operating in a work area, the method comprising:

determining a self-occupation grid map corresponding to an initial planning path of the robot by adopting the generation method of the occupation grid map of any one of claims 1-3;

requesting a server to acquire the total occupied grid map of the working area;

7. The method of claim 6, wherein if the occupancy time identifiers corresponding to the respective sampling times are represented by an arithmetic progression of gray values corresponding to the respective sampling times, the performing the collision check on the self-occupied grid map using the total occupied grid map comprises:

8. The method of claim 6, wherein after performing collision verification on the self-occupied grid map using the total occupied grid map, further comprising:

if the self-occupied grid map has conflict grids, setting an area where the conflict grids are located in a grid map of the working area as a forbidden area within forbidden time, wherein the forbidden time is determined according to an occupied time mark corresponding to the conflict grids;

updating an initial planned path of the robot based on a non-forbidden area within a grid map of the work area;

and returning to the step of determining the self-occupied grid map of the robot for the updated initial planning path of the robot until the target planning path is obtained or the target planning path does not exist.

9. The method of claim 6, wherein if there is no target planned path, sending indication information to the robot, the indication information comprising: delay planning instructions or path planning failure information.

10. The method of claim 6, further comprising, after determining the target planned path for the robot:

11. An occupied grid map generating apparatus, characterized by being applied to a robot operating in a work area, comprising:

the map generation module is used for marking all occupied grids in the update period according to the occupied time marks marked by the occupied grids corresponding to each sampling time, and obtaining a self-occupied grid map of the planning path of the robot in the update period;

If the robot keeps a motion state in the update period, the state information of the robot in the motion state includes: body orientation, body width, initial position, and speed of movement; correspondingly, the occupation determining module is specifically configured to:

12. A path planning apparatus for use with a robot operating within a work area, the apparatus comprising:

the self-occupation map generation module is used for determining a self-occupation grid map corresponding to the initial planning path of the robot by adopting the generation method of the occupation grid map according to any one of claims 1-3;

13. An electronic device, the electronic device comprising:

at least one processor; and

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of generating an occupancy grid map of any one of claims 1-5 or the method of path planning of any one of claims 6-10.

14. A computer readable storage medium storing computer instructions for causing a processor to implement the method of generating an occupancy grid map of any one of claims 1-5 or the method of path planning of any one of claims 6-10 when executed.