CN114942639A

CN114942639A - Self-adaptive path planning method and device for mobile robot

Info

Publication number: CN114942639A
Application number: CN202210601269.XA
Authority: CN
Inventors: 龚汉越; 支涛
Original assignee: Henan Yunji Intelligent Technology Co Ltd
Current assignee: Henan Yunji Intelligent Technology Co Ltd
Priority date: 2022-05-30
Filing date: 2022-05-30
Publication date: 2022-08-26

Abstract

The disclosure relates to the technical field of robots, and provides a mobile robot self-adaptive path planning method and device. The method comprises the following steps: determining a target moving path of a mobile robot for executing a service task; acquiring real-time environment information of a mobile robot in the process of executing a service task in a mobile manner; determining a dynamic barrier and a motion track route of the dynamic barrier within preset time according to the real-time environment information; determining the positioning precision of the real-time position of the mobile robot in the process of executing the service task in a mobile manner; if the positioning accuracy is lower than a preset accuracy threshold value, starting a preset path local adjustment mode; the target moving path is adjusted according to the path local adjustment mode and the motion trail path to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path, the self-adaptive path planning requirement of the mobile robot in a changeable environment can be met, and the path planning efficiency is improved.

Description

Self-adaptive path planning method and device for mobile robot

Technical Field

The disclosure relates to the technical field of robots, in particular to a mobile robot adaptive path planning method and device.

Background

With the continuous development of artificial intelligence technology, the intelligent mobile robot is more and more widely applied and has more and more diversified functions. The mobile path planning is one of the key technologies for the navigation of the intelligent mobile robot.

When a mobile robot performs various service tasks (e.g., goods/delivery, inspection, etc.), its moving path may face a variety of different scenarios (e.g., indoor scenarios, outdoor scenarios, etc.). This complicates the path planning of mobile robots due to the variability of the environment and the need to take into account a large number of factors. However, the existing robot path planning methods (such as neural network, etc.) often cannot meet the requirement of the mobile robot for adaptive path planning in a changeable environment, and the efficiency of path planning is also low.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide a method and an apparatus for adaptive path planning of a mobile robot, so as to solve the problems that the existing method for robot path planning often cannot meet the requirement of adaptive path planning of a mobile robot in a changeable environment, and the efficiency of path planning is low.

In a first aspect of the embodiments of the present disclosure, a method for planning a self-adaptive path of a mobile robot is provided, including:

determining a target moving path of a mobile robot for executing a service task;

acquiring real-time environment information of a mobile robot in the process of mobile execution of a service task;

determining a dynamic barrier and a motion track route of the dynamic barrier within preset time according to the real-time environment information;

determining the positioning precision of the real-time position of the mobile robot in the process of executing the service task in a mobile manner;

if the positioning accuracy is lower than a preset accuracy threshold value, starting a preset path local adjustment mode;

and adjusting the target moving path according to the path local adjustment mode and the motion trail path to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path.

In a second aspect of the embodiments of the present disclosure, there is provided a mobile robot adaptive path planning apparatus, including:

a path determination module configured to determine a target movement path for the mobile robot to perform the service task;

the information acquisition module is configured to acquire real-time environment information of the mobile robot in the process of executing the service task in a mobile manner;

the information extraction module is configured to determine a dynamic barrier and a motion track route of the dynamic barrier within preset time according to the real-time environment information;

an accuracy determination module configured to determine a positioning accuracy of a real-time position of the mobile robot in the course of mobile execution of the service task;

the starting module is configured to start a preset path local adjustment mode if the positioning precision is lower than a preset precision threshold;

and the path adjusting module is configured to adjust the target moving path according to the path local adjusting mode and the motion trail path to obtain an adjusting moving path, so that the mobile robot continues to execute the service task according to the adjusting moving path.

In a third aspect of the disclosed embodiments, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program, which when executed by a processor, implements the steps of the above-mentioned method.

Compared with the prior art, the beneficial effects of the embodiment of the disclosure at least comprise: determining a target moving path of the mobile robot for executing the service task; acquiring real-time environment information of a mobile robot in the process of executing a service task in a mobile manner; determining a dynamic barrier and a motion track route of the dynamic barrier within preset time according to the real-time environment information; determining the positioning precision of the real-time position of the mobile robot in the process of executing the service task in a mobile manner; if the positioning accuracy is lower than a preset accuracy threshold value, starting a preset path local adjustment mode; the target moving path is adjusted according to the path local adjustment mode and the movement track line to obtain an adjusted moving path, so that the mobile robot can continuously execute the service task according to the adjusted moving path, the self-adaptive path planning requirement of the mobile robot under a changeable environment can be met, and the path planning efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a scenario diagram of an application scenario of an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of a method for adaptive path planning of a mobile robot according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of path planning in an adaptive path planning method for a mobile robot according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an adaptive path planning apparatus for a mobile robot according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. It will be apparent, however, to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

An adaptive path planning method and an adaptive path planning device for a mobile robot according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 is a scene schematic diagram of an application scenario of an embodiment of the present disclosure. The application scenario may include mobile robot 101, server 102, and network 103.

The mobile robot 101 may be integrated with a camera device (such as a monocular/binocular camera), a communication device, a moving mechanism, a controller (such as an MCU (micro control unit), a single chip microcomputer), a positioning and navigation device (such as a GPS (global positioning system), a combined navigation device, an inertial measurement unit, and the like).

The server 102 may be a server that provides various services, for example, a backend server that receives a request transmitted by the mobile robot 101 to which a communication connection is established, and the backend server may receive and analyze the request transmitted by the terminal device, and generate a processing result. The server 102 may be a server, may also be a server cluster composed of several servers, or may also be a cloud computing service center, which is not limited in this disclosure.

The server 102 may be hardware or software. When the server 102 is hardware, it may be various electronic devices that provide various services to the mobile robot 101. When the server 102 is software, it may be a plurality of software or software modules providing various services for the mobile robot 101, or may be a single software or software module providing various services for the mobile robot 101, which is not limited in the embodiment of the present disclosure.

The network 103 may be a wired network connected by a coaxial cable, a twisted pair and an optical fiber, or may be a wireless network that can interconnect various Communication devices without wiring, for example, Bluetooth (Bluetooth), Near Field Communication (NFC), Infrared (Infrared), and the like, which is not limited in the embodiment of the present disclosure.

The execution main body of the mobile robot adaptive path planning method provided by the embodiment of the disclosure may be the server 102, or may be a controller of the mobile robot. The following describes the execution agent as the server 102 in detail. The server 102 may first determine a target movement path for the mobile robot to perform the service task; then, collecting real-time environment information of the mobile robot in the process of executing the service task in a mobile mode; determining a dynamic barrier and a motion track route of the dynamic barrier within a preset time according to the real-time environment information; then, determining the positioning precision of the real-time position of the mobile robot in the process of executing the service task in a moving way; if the positioning accuracy is lower than a preset accuracy threshold value, starting a preset path local adjustment mode; and adjusting the target moving path according to the path local adjustment mode and the motion trail path to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path. The method and the device can meet the self-adaptive path planning requirement of the mobile robot in a changeable environment, and improve the path planning efficiency.

It should be noted that the specific types, numbers and combinations of the mobile robot 101, the server 102 and the network 103 may be adjusted according to the actual requirements of the application scenario, and the embodiment of the present disclosure does not limit this.

Fig. 2 is a schematic flowchart of a method for planning an adaptive path of a mobile robot according to an embodiment of the present disclosure. The mobile robot adaptive path planning method of fig. 2 may be performed by the server 102 of fig. 1. As shown in fig. 2, the method for adaptive path planning of a mobile robot includes:

in step S201, a target movement path of the mobile robot for executing the service task is determined.

The service tasks can be takeout delivery, cargo delivery, hotel inspection, construction site inspection and the like.

In an exemplary embodiment, a mapping relationship between the service task and the target moving path may be established in advance, for example, a mapping relationship table between the service task and the target moving path as shown in table 1 below may be established.

Table 1 mapping relation table of service task and target moving path

ServiceTask	Moving path of target
		XX cell takeaway delivery	A→B→C→D→E
XX site inspection	a→b→c→d→e→f
		…	…

Step S202, collecting real-time environment information of the mobile robot in the process of mobile execution of the service task.

The real-time environment information refers to sensing information of surrounding environment acquired by various sensors (such as laser radar, camera, millimeter wave radar and the like) in the process of executing the service task by the mobile robot. The perception information includes surrounding images and position information of obstacles collected by the mobile robot in a moving area.

Step S203, determining the dynamic barrier and the motion trail route of the dynamic barrier in the preset time according to the real-time environment information.

In practical applications, during the service task, the mobile robot may encounter various obstacles in the way of moving, including static obstacles (such as buildings fixed at a certain place, etc.) and dynamic obstacles (such as pedestrians, other mobile robots, vehicles, animals, etc.). Due to certain uncertainty in the moving speed, the position and the like of the dynamic obstacle, the influence of the dynamic obstacle on the safety of the driving route of the mobile robot is larger than the influence of the static obstacle on the driving safety of the mobile robot. Also, such uncertainty of the dynamic obstacle is likely to affect the safety of the traveling route of the mobile robot. Accordingly, the present disclosure primarily considers the effect of dynamic obstacles on the target movement path of a mobile robot in performing a service task.

In an exemplary embodiment, the real-time environment information collected in step S202 may be input into a preset prediction model, and information of various obstacles in the prediction model is extracted, such as the size and type of the obstacle (for example, the probability value of the obstacle being a vehicle, a pedestrian, or another object (for example, an animal)), the current position of the obstacle, and the like. The prediction model may be a prediction model obtained by training in advance a sensing data set of various obstacles in the driving area acquired by the mobile robot. The prediction model may be a YOLO series algorithm model (e.g., Yolov3, Yolov4 algorithm, Yolov5 algorithm, Yolox algorithm), or may be other prediction algorithm models. The sensing data set comprises information of volume size, type, position and the like of various obstacles.

Further, according to the information of various obstacles obtained in the above steps, dynamic obstacles (such as objects with speed variation value larger than the preset allowable variation threshold) are found out. Then, the possible movement speed and the probability value of each dynamic obstacle at each moment in the preset time length and the movement route of each dynamic obstacle from the position of the previous moment to the position of the next moment in each moment in the preset time length can be further estimated according to the prediction model. The preset time duration generally refers to a time span in which it is desired to predict a motion state of the dynamic obstacle for how long in the future. The value of the time span may be set according to actual conditions, and for example, may be set to 8 seconds, 10 seconds, or the like.

And step S204, determining the positioning precision of the real-time position of the mobile robot in the process of mobile execution of the service task.

The positioning accuracy refers to an offset value of a real-time position of the mobile robot deviating from a target moving path in the process of executing a service task.

In step S205, if the positioning accuracy does not meet the preset accuracy range, a preset local path adjusting mode is started.

The preset precision range can be flexibly set according to actual conditions, generally, the precision range can be set to be less than or equal to 2m, less than or equal to 3m, less than or equal to 4m, less than or equal to 5m, and the like, and is not limited herein.

The path local adjustment mode is a mode that the mobile robot is allowed to perform local adjustment of the intermediate path node when the mobile robot moves to execute the service task according to the target moving path and the positioning accuracy of the mobile robot is found to be not in accordance with the preset accuracy range.

And step S206, adjusting the target moving path according to the path local adjustment mode and the motion trail path to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path.

In an exemplary embodiment, it is assumed that the service task received by the mobile robot is a "XX cell takeaway delivery" task, and the corresponding target moving path is a → B → C → D → E. If the mobile robot moves and walks to the point (r) in fig. 3 currently, and the dynamic obstacle on the traveling path of the mobile robot is determined to be an electric trolley S through the above steps, and the motion trajectory route of the electric trolley S within the future 8 seconds is predicted by the prediction model to be as shown by the dotted line in fig. 3.

Nodes

01, 02, 03, 04, 05, 06, 07, 08 in the dashed lines are the positions to which the motorized trolley will move for each of the next 8 seconds, respectively. Then, the target moving path can be adjusted according to the path local adjustment mode and the movement track route of the electric trolley to obtain an adjusted moving path, so that the mobile robot can continue to execute the service task according to the adjusted moving path.

According to the technical scheme provided by the embodiment of the disclosure, a target moving path of a mobile robot for executing a service task is determined; acquiring real-time environment information of a mobile robot in the process of executing a service task in a mobile manner; determining a dynamic barrier and a motion track route of the dynamic barrier within preset time according to the real-time environment information; determining the positioning precision of the real-time position of the mobile robot in the process of executing the service task in a mobile manner; if the positioning accuracy is lower than a preset accuracy threshold value, starting a preset path local adjustment mode; the target moving path is adjusted according to the path local adjustment mode and the motion trail path to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path, the self-adaptive path planning requirement of the mobile robot in a changeable environment can be met, and the path planning efficiency is improved.

In some embodiments, the step S201 may specifically include the following steps:

acquiring a service task, wherein the service task comprises a task end point;

collecting an initial position point of the mobile robot before executing the service task, determining the initial position point as a path starting point, and determining a task end point as a path end point;

acquiring a global map comprising a route starting point and a route end point;

and determining a target moving path according to the path starting point, the path end point and the global map.

The task end point is the execution place of the service task. For example, if the service task is to deliver cargo A to the XX room of the X building of the XX hotel, the task destination is the XX room of the XX building of the XX hotel.

In an exemplary embodiment, a starting location point of the mobile robot before performing a service task may be acquired by a positioning device (e.g., GPS, integrated navigation, etc.) installed on the mobile robot. For example, the service task is to deliver the cargo a to the XX building XX room of the XX hotel, the mobile robot is located in the XX street XX cell before performing the service task, and then the starting location point is the XX street XX cell.

Then, the XX cell of the XX starting position point, the XX street, is determined as the starting point of the path, and the XX room of the XX hotel is determined as the ending point of the path. For convenience of description, the XX street XX cell is simply referred to as point a, and the XX room of the XX building of the XX hotel is simply referred to as point B.

Then, a global map including the points a and B, that is, a surrounding area of the points a and B to be covered by the global map, is acquired. The global map may be an electronic drawing containing detailed information such as traffic lights around point B, lane markers (such as white lines, yellow lines, double lanes or single lanes, solid lines, dotted lines), curbs, obstacles, telegraph poles, overpasses, underpasses, and an internal design drawing of the XX hotel at point a, where objects such as traffic lights on the drawing all have corresponding geocodes.

In some embodiments, determining the target moving path according to the path starting point, the path ending point and the global map may specifically include the following steps:

performing rasterization processing on the global map to obtain a rasterized map;

calculating a passable probability value of each grid in the grid map;

removing grids with passable probability values lower than a preset probability threshold value in the grid map to obtain a target grid map;

generating a plurality of alternative paths according to the target raster map, the path starting point and the path end point, wherein each alternative path is an ordered point set with variable length and comprising the path starting point, the path end point and a plurality of intermediate path nodes;

and screening out a target moving path which meets a preset target function from the multiple alternative paths.

And performing rasterization processing on the global map, specifically, dividing the global map into a series of grid areas with the same size to obtain the rasterized map. For example, assuming that the global map is a 100 × 100 map, the 100 × 100 global map is divided into a series of 10 × 10 grid regions (total 100 grids), so as to obtain a grid map, and each grid may be respectively numbered as grid 01 and grid 02 … … grid 100.

If an obstacle is contained in the range of a certain grid area, the passable probability value of the obstacle can be determined by calculating the area proportion of the obstacle occupying the grid area. The passable probability value generally refers to the probability value that the mobile robot can pass through the grid. Generally, a 100% area of the grid area occupied by the obstacles is likely to be a wall, and is 100% infeasible. That is, the larger the proportion of the area of the grid area occupied by the obstacle, the smaller the probability value that the obstacle can pass through.

In an exemplary embodiment, a corresponding relation between the occupied area proportion of the obstacles and the passable probability value can be established in advance; and then, calculating the occupied area ratio of the obstacles in each grid, and further determining the passable probability value of the grid according to the occupied area ratio and the corresponding relation. For example, the obstacle occupying area ratio is 5%, the passable probability value is 95%, the obstacle occupying area ratio is 10%, the passable probability value is 90%, the obstacle occupying area ratio is 50%, and the passable probability value is 50%. It can be seen that the sum of the obstacle-occupied area ratio and the passable probability value is 1.

The probability threshold is preset, and can be flexibly set according to actual conditions. In general, the mobile robot has better trafficability in a grid with an obstacle occupying area ratio of 20% or less, so the preset probability threshold may be set to 80%.

As an example, assuming that the preset probability threshold is 80%, the grid with a passable probability value lower than 80% in the obtained grid map may be used to obtain the target grid map.

In an exemplary embodiment, assuming that a path starting point is a point a, a path end point is a point B, and a target grid map is a drawing from which grids 01, 20, 24, 63, 78, 90, and 100 in a global map 100 × 100 are removed, a series of intermediate path nodes may be generated based on a gaussian probability model according to the target grid map, and the point a, the series of intermediate path nodes, and the point B are connected in a certain connection order to form a plurality of candidate paths. Each alternative path is an ordered set of points of variable length.

The optimization objectives of path planning for mobile robots generally include three criteria of quickness (i.e., path length), safety, and smoothness. Therefore, the preset target condition may be any one of shortest path length, highest path safety and best path smoothness, or any two or three of path length, path safety and path smoothness.

In an exemplary embodiment, a firefly algorithm, an adaptive particle swarm algorithm, and the like may be adopted to screen one target moving path that meets a preset target condition from multiple candidate paths.

For example, assuming that the target conditions include expected values of path length, path security, and path smoothness, a safe candidate path with the shortest path may be selected from the multiple candidate paths based on the adaptive particle swarm optimization, and then the candidate path is smoothed by using the bezier curve to obtain the target movement path.

In some embodiments, the step S204 may specifically include the following steps:

if the scene type corresponding to the initial position point of the mobile robot is a first scene type, configuring the positioning mode of the mobile robot as a first positioning mode;

judging whether the scene type corresponding to the real-time position of the mobile robot in the process of executing the service task in a mobile mode is still the first scene type;

if the scene type corresponding to the real-time position of the mobile robot in the process of executing the service task in a moving mode is still the first scene type, determining a real-time position coordinate point of the mobile robot by adopting a first positioning mode;

and determining the positioning precision of the mobile robot at the real-time position according to the real-time position coordinate point and the target moving path.

The first scene type may refer to an indoor scene. Indoor scenes may typically include office building scenes, hotel scenes, tunnel construction scenes, underground work scenes, and the like.

The first positioning mode generally refers to a combined positioning mode that employs an indoor positioning tag installed in an indoor scene and an inertial measurement unit installed on the mobile robot. And the indoor positioning label can be a positioning two-dimensional code/bar code, an RFID label and the like.

As an example, a mapping relationship between the indoor positioning tag and the indoor location (e.g., indoor location coordinates) information may be pre-established, and the mapping relationship may be stored in a memory of the robot, a memory of the remote server, or a cloud server. When indoor positioning of the mobile robot needs to be performed subsequently, corresponding indoor position information can be called from the places. Then, the indoor position information is corrected by combining inertial measurement data (including the angular velocity or the three-axis attitude angle of the robot) of the mobile robot moving to the real-time position, so as to obtain a real-time position coordinate point.

In an exemplary embodiment, in conjunction with fig. 3, assume that the mobile robot moves from point a (the starting position point, the scene type belongs to an indoor scene) to walk to point (r) in fig. 3, i.e., the real-time position is point (r). And judging whether the scene type corresponding to the real-time position of the mobile robot in the process of executing the service task in a moving way is still the first scene type. Specifically, the real-time environment information around the point (i) acquired when the mobile robot moves to the point (i) can be analyzed, so that the scene type of the mobile robot at the point (i) can be determined. If the scene type of the mobile robot at the point I is still an indoor scene (namely, a first scene type), a first positioning mode is adopted to determine a real-time position coordinate point (namely, a coordinate point of the point I) of the mobile robot at the point I.

Then, according to the real-time position coordinate point and the target moving path, determining the positioning accuracy of the mobile robot at the real-time position, specifically comprising the following steps:

calculating a distance value between the real-time position coordinate point and the target moving path;

and determining the positioning accuracy of the mobile robot at the real-time position according to the distance value.

Following the above example, a distance value between the coordinate point of (r) and the target movement path is calculated. Since the target moving path is usually a curved path, a path node closest to the point (r) in the target moving path may be found first, and then a distance value between the coordinate point (r) of the point (r) and the path node may be calculated. Then, the corresponding positioning precision is found according to the distance value.

In practical application, the corresponding relationship between the distance value and the positioning accuracy can be established in advance. Generally, the smaller the distance value, the higher the positioning accuracy. For example, the correspondence between the distance value and the positioning accuracy may be: the distance value is 0-10 cm, and the positioning precision is more than or equal to 95%; the distance value is 11-30 cm, and the positioning precision is more than or equal to 60% and less than 95%; if the distance value is more than 30cm, the positioning fails, and the positioning precision cannot be predicted.

In some embodiments, after determining whether the scene type corresponding to the real-time position of the mobile robot in the process of performing the service task in the mobile manner is still the first scene type, the method further includes:

if the scene type corresponding to the real-time position of the mobile robot in the process of mobile service task execution is not the first scene type, judging whether the scene type corresponding to the real-time position of the mobile robot in the process of mobile service task execution is the second scene type;

and if the scene type is the second scene type, determining the real-time position coordinate point of the mobile robot by adopting a second positioning mode.

The second scene type may refer to an outdoor scene. An outdoor scene generally refers to an open space relative to an indoor scene.

With reference to fig. 3, assuming that the mobile robot moves from point a (the starting position point, and the scene type belongs to an indoor scene) to point (c) in fig. 3, and the scene type corresponding to point (c) is not an indoor scene, it is further determined whether the scene type corresponding to point (c) is a second scene type; and if so, determining the real-time position coordinate point of the mobile robot by adopting a second positioning mode.

The second positioning mode is generally referred to as a GPS positioning mode or a combined positioning mode of GPS and an inertial measurement unit mounted on the mobile robot.

As an example, if the mobile robot moves to the point iii and the scene type corresponding to the point iii is an outdoor scene, it is further determined whether the signal strength of the GPS signal currently received by the mobile robot satisfies a preset strength range (which can be flexibly set according to actual conditions), and if the signal strength of the GPS signal currently received by the mobile robot satisfies the preset strength range, the real-time position coordinate point (i.e., the point iii coordinate point) of the mobile robot can be determined by using an independent GPS positioning method. If the signal intensity of the current GPS signal received by the mobile robot does not meet the preset intensity range, the real-time position coordinate point (namely the coordinate point III) of the mobile robot can be determined by adopting a combined positioning mode of the GPS and an inertial measurement unit installed on the mobile robot.

According to the embodiment of the disclosure, the real-time position coordinate point of the mobile robot can be determined by adopting the corresponding positioning model according to the scene type corresponding to the real-time position of the mobile robot in the process of executing the service task in a moving manner, so that the adaptability of the mobile robot to positioning and navigation in different scenes can be improved, the reliability and accuracy of the subsequent calculation result of the positioning accuracy can be ensured, and the efficiency and accuracy of path planning can be improved.

In some embodiments, the adjusting the target moving path according to the path local adjustment mode and the motion trajectory path in step S206 to obtain an adjusted moving path may specifically include the following steps:

calculating a local moving path of the mobile robot moving to the next path node according to the path local adjustment mode;

and adjusting the target moving path according to the local moving path and the motion trail path to obtain an adjusted moving path.

In connection with fig. 3, in an exemplary embodiment, it is assumed that the mobile robot moves from point a to point (r), which is between points a and B. According to the steps, the positioning accuracy when the mobile robot moves to the point I is determined to be more than 60% and less than 95%, and at the moment, the path local adjustment mode can be started. It is assumed that in this path local adjustment mode, the tolerance that allows the mobile robot to perform local adjustment of the intermediate path node is 0.2 m. Then, a local movement path for the mobile robot to move to the next path node (i.e., B point) may be calculated based on the tolerance.

Suppose that the local moving path of the mobile robot moving to the next path node (i.e. point B) is calculated according to the above tolerance, such as the route from point (c) to point B' in fig. 3. If the dynamic obstacle on the traveling path of the mobile robot is determined to be a motor-driven vehicle S according to the above steps, and the path of the movement locus of the motor-driven vehicle S in the next 8 seconds is predicted by the prediction model, as shown by the dotted line (the path connected by the

nodes

01, 02, 03, 04, 05, 06, 07, 08) in fig. 3.

Nodes

01, 02, 03, 04, 05, 06, 07, 08 in the dashed lines are positions to which the motorized trolley will move for each of the next 8 seconds, respectively.

Then, whether a crossing point exists between the route of the mobile robot moving from the point (c) to the point (B') and the motion trail route of the dynamic obstacle within the preset time (i.e. the route connected by the

nodes

01, 02, 03, 04, 05, 06, 07 and 08) is judged. If there is no intersecting point, the target movement path a → B → C → D → E is adjusted to the adjustment movement path (i → B' → C → D → E). If there is an intersection point, the tolerance range of the path local adjustment mode can be properly increased, and the local moving path (such as a route from a point III to a point B ") of the mobile robot moving to the next path node (i.e. the point B) is calculated; then, it is determined whether or not there is an intersection between the route from the point C to the point B "and the route connected by the

nodes

01, 02, 03, 04, 05, 06, 07, 08, and if there is no intersection, the target movement path a → B → C → D → E is adjusted to the adjusted movement path (i → B" → C → D → E).

In an exemplary embodiment, if the tolerance range of the path local adjustment mode is properly increased, and a point where the local movement path of the mobile robot moving to the next path node (i.e., point B) and the route connected by the

nodes

01, 02, 03, 04, 05, 06, 07, 08 still intersect is calculated, the mobile robot may be controlled to stop moving at a time before the intersection point occurs, wait for the movement obstacle to pass, restart the mobile robot, continue to move according to the adjustment movement path (i → B' → C → D → E), and execute its service task.

According to the embodiment of the disclosure, according to the local path adjustment mode, the local moving path of the mobile robot moving to the next path node is calculated, and the target moving path is adjusted by combining the local moving path and the motion trajectory path to obtain the adjusted moving path, so that not only is the adaptivity of the path planning of the mobile robot improved, but also the planning time spent by the mobile robot in re-planning the path when the mobile robot encounters a dynamic obstacle at the middle path node and the positioning accuracy is low is reduced, and the efficiency of the path planning is improved.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

Fig. 4 is a schematic diagram of an adaptive path planning apparatus for a mobile robot according to an embodiment of the present disclosure. As shown in fig. 4, the mobile robot adaptive path planning apparatus includes:

a path determination module 401 configured to determine a target movement path for the mobile robot to perform the service task;

an information acquisition module 402 configured to acquire real-time environment information of the mobile robot in the process of performing the service task in a mobile manner;

an information extraction module 403, configured to determine a dynamic obstacle and a movement trajectory route of the dynamic obstacle within a preset time according to the real-time environment information;

an accuracy determination module 404 configured to determine a positioning accuracy of a real-time position of the mobile robot in the course of mobile execution of the service task;

a starting module 405 configured to start a preset path local adjustment mode if the positioning accuracy is lower than a preset accuracy threshold;

and the path adjusting module 406 is configured to adjust the target moving path according to the path local adjusting mode and the motion trajectory path, so as to obtain an adjusted moving path, so that the mobile robot continues to execute the service task according to the adjusted moving path.

In some embodiments, the path determining module 401 includes:

the task acquisition unit is configured to acquire a service task, and the service task comprises a task terminal;

the mobile robot system comprises a collecting unit, a processing unit and a processing unit, wherein the collecting unit is configured to collect a starting position point of the mobile robot before executing a service task, determine the starting position point as a path starting point, and determine a task end point as a path end point;

a map acquisition unit configured to acquire a global map including a route start point and a route end point;

and a path determination unit configured to determine a target moving path according to the path starting point, the path ending point and the global map.

In some embodiments, the path determining unit may be specifically configured to:

calculating a passable probability value of each grid in the grid map;

and screening out a target moving path meeting preset target conditions from the multiple alternative paths.

In some embodiments, the accuracy determination module 404 includes:

the mobile robot positioning system comprises a configuration unit, a positioning unit and a control unit, wherein the configuration unit is configured to configure a positioning mode of the mobile robot to be a first positioning mode if a scene type corresponding to an initial position point of the mobile robot is the first scene type;

the first judging unit is configured to judge whether a scene type corresponding to a real-time position of the mobile robot in the process of mobile execution of the service task is still a first scene type;

the first positioning unit is configured to determine a real-time position coordinate point of the mobile robot by adopting a first positioning mode if a scene type corresponding to a real-time position of the mobile robot in the process of executing the service task in a moving way is still a first scene type;

and the accuracy determining unit is configured to determine the positioning accuracy of the mobile robot at the real-time position according to the real-time position coordinate point and the target moving path.

In some embodiments, the accuracy determination unit may be specifically configured to:

In some embodiments, the accuracy determining module 404 further comprises:

the second judging unit is configured to judge whether the scene type corresponding to the real-time position of the mobile robot in the process of movably executing the service task is a second scene type or not if the scene type corresponding to the real-time position of the mobile robot in the process of movably executing the service task is not the first scene type;

and the second positioning unit is configured to determine the real-time position coordinate point of the mobile robot in a second positioning mode if the scene type is the second scene type.

In some embodiments, the path adjusting module 406 includes:

a calculation unit configured to calculate a local movement path along which the mobile robot moves to a next path node according to the path local adjustment mode;

and the adjusting unit is configured to adjust the target moving path according to the local moving path and the motion trail path to obtain an adjusted moving path.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

Fig. 5 is a schematic diagram of an electronic device 5 provided in an embodiment of the present disclosure. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and operable on the processor 501. The steps in the various method embodiments described above are implemented when the processor 501 executes the computer program 503. Alternatively, the processor 501 implements the functions of the respective modules/units in the above-described respective apparatus embodiments when executing the computer program 503.

The electronic device 5 may be a desktop computer, a notebook, a palm computer, a cloud server, or other electronic devices. The electronic device 5 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that fig. 5 is merely an example of the electronic device 5, and does not constitute a limitation of the electronic device 5, and may include more or less components than those shown, or different components.

The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like.

The storage 502 may be an internal storage unit of the electronic device 5, for example, a hard disk or a memory of the electronic device 5. The memory 502 may also be an external storage device of the electronic device 5, such as a plug-in hard disk provided on the electronic device 5, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. The memory 502 may also include both internal and external storage units of the electronic device 5. The memory 502 is used for storing computer programs and other programs and data required by the electronic device.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method in the above embodiments, and may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the above methods and embodiments. The computer program may comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain suitable additions or additions that may be required in accordance with legislative and patent practices within the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals or telecommunications signals in accordance with legislative and patent practices.

The above examples are only intended to illustrate the technical solution of the present disclosure, not to limit it; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and they should be construed as being included in the scope of the present disclosure.

Claims

1. A mobile robot adaptive path planning method is characterized by comprising the following steps:

acquiring real-time environment information of the mobile robot in the process of executing the service task in a moving way;

determining the positioning accuracy of the real-time position of the mobile robot in the process of executing the service task in a moving way;

if the positioning precision does not accord with the preset precision range, starting a preset path local adjustment mode;

2. The method of claim 1, wherein determining a target movement path for the mobile robot to perform the service task comprises:

acquiring a service task, wherein the service task comprises a task end point;

collecting a starting position point of the mobile robot before executing the service task, determining the starting position point as a path starting point, and determining a task end point as a path end point;

acquiring a global map comprising the starting point and the end point of the path;

3. The method of claim 2, wherein determining a target movement path based on the path start point, the path end point, and the global map comprises:

calculating a passable probability value of each grid in the grid map;

generating a plurality of alternative paths according to the target grid map, the path starting point and the path end point, wherein each alternative path is an ordered point set with variable length and comprising the path starting point, the path end point and a plurality of intermediate path nodes;

4. The method of claim 2, wherein determining the positional accuracy of the real-time location of the mobile robot while moving to perform the service task comprises:

judging whether the scene type corresponding to the real-time position of the mobile robot in the process of executing the service task in a moving way is still the first scene type;

5. The method of claim 4, wherein determining the positioning accuracy of the mobile robot at the real-time location according to the real-time location coordinate point and the target movement path comprises:

and determining the positioning precision of the mobile robot at the real-time position according to the distance value.

6. The method of claim 4, wherein after determining whether the scene type corresponding to the real-time position of the mobile robot during the moving process of executing the service task is still the first scene type, further comprising:

if the scene type corresponding to the real-time position of the mobile robot in the process of moving and executing the service task is not the first scene type, judging whether the scene type corresponding to the real-time position of the mobile robot in the process of moving and executing the service task is the second scene type;

7. The method of claim 1, wherein adjusting the target moving path according to the path local adjustment mode and the motion trajectory line to obtain an adjusted moving path comprises:

8. A mobile robot adaptive path planning device is characterized by comprising:

the information acquisition module is configured to acquire real-time environment information of the mobile robot in the process of executing the service task in a moving way;

the information extraction module is configured to determine a dynamic obstacle and a motion track route of the dynamic obstacle within a preset time according to the real-time environment information;

an accuracy determination module configured to determine a positioning accuracy of a real-time location of the mobile robot in moving to perform the service task;

a starting module configured to start a preset path local adjustment mode if the positioning accuracy is lower than a preset accuracy threshold;

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method according to any one of claims 1 to 7.