CN117346774A - Robot navigation method and system, corresponding robot and storage medium - Google Patents

Abstract

The application discloses a robot navigation method, a system, a corresponding robot and a storage medium, wherein the method comprises the following steps: determining a destination waypoint based on the destination information; determining a road point list of a path from the current road point to the destination road point according to the plane layout, the current road point and the destination road point; generating at least a travel semantic instruction from a current waypoint to a next subsequent waypoint; the robot moves according to the travelling semantic instruction, and meanwhile an RFID reader on the robot works; responsive to scanning at least one RFID tag, determining a corresponding waypoint, determining whether the waypoint is a destination waypoint; and in response to not being the destination waypoint, continuing to navigate the robot according to a predetermined subsequent navigation scheme. The invention only needs the plane layout, has no limit on the scaling, does not need the accurate matching of the map and the actual environment, can better understand and adapt to the environment, and reduces the dependence on high-cost and high-precision hardware.

Description

Robot navigation method and system, corresponding robot and storage medium

Technical Field

The present application relates to the field of electronic digital data processing, and in particular, to a robot navigation method, a system, a corresponding robot, and a storage medium.

Background

In the existing robot navigation technology, distance navigation, for example, 100 meters forward and then to the left is mainly used. This approach requires that the map must be exactly matched to the actual environment. However, in practical applications, it is often difficult to accurately match a map to a real environment. There is thus a need for a new method of robot navigation to overcome this problem.

In addition, the existing robot is usually positioned by adopting GPS or laser radar, and has very high precision requirement. Commercial robot lidar is also costly and has a limited lifetime, typically 1-3 years, because it is an active transmitting device.

Disclosure of Invention

The invention provides a robot navigation method, a system, a corresponding robot and a storage medium, which do not need to match a map with an actual environment accurately, have no limit on scaling, can better understand and adapt to the environment, and have low cost.

In a first aspect of the present invention, there is provided a robot navigation method, the method comprising:

determining destination road points based on destination information, wherein each node of a robot working environment is provided with one or more RFID tags, RFID tag information comprises the node where the RFID tag is located, a plane layout diagram of the robot working environment is also stored in the robot, and each road point comprises the road points, and each road point has coordinates and corresponds to at least one node and/or at least one RFID tag;

step two, determining a road point list of all road points successively passed by a path from the current road point to the destination road point according to the plane layout, the current road point and the destination road point;

step three, at least generating a traveling semantic instruction of the robot from the current road point to the next subsequent road point according to the coordinates of the current road point and the subsequent road points in the road point list, wherein the traveling semantic instruction comprises easting, southward, northward or westward;

step four, the robot moves sequentially according to the travelling semantic instruction, and meanwhile, an RFID reader on the robot works;

step five, responding to the fact that the RFID reader scans at least one RFID label, and determining a road point corresponding to the scanned RFID label by the robot to determine whether the road point is a destination road point;

and step six, responding to the scanned road point corresponding to the RFID label not being the destination road point, and continuing to navigate the robot according to a preset follow-up navigation scheme.

In a second aspect of the invention, there is provided a robotic navigation system, the system comprising:

the system comprises a destination waypoint determining module, a robot working environment determining module and a storage module, wherein the destination waypoint determining module is used for determining destination waypoints based on destination information, each node of the robot working environment is provided with one or more RFID tags, RFID tag information comprises the node where the RFID tag is located, the robot is further stored with a plane layout diagram of the robot working environment, and each path point comprises a waypoint, and each path point has coordinates and corresponds to at least one node and/or at least one RFID tag;

the route point list determining module is used for determining a route point list of all route points which are sequentially passed by a path from the current route point to the destination route point according to the plane layout, the current route point and the destination route point;

the semantic instruction generation module is used for generating at least a traveling semantic instruction of the robot from the current road point to the next subsequent road point according to the coordinates of the current road point and the subsequent road points in the road point list, wherein the traveling semantic instruction comprises easting, southing, northing or westward;

the moving module is used for enabling the robot to sequentially move according to the travelling semantic instruction, and meanwhile, the RFID reader on the robot works;

the current waypoint judging module is used for responding to the fact that the RFID reader scans at least one RFID label, and the robot determines the waypoint corresponding to the scanned RFID label and determines whether the waypoint is a destination waypoint or not;

and the continuing navigation module is used for responding to the fact that the scanned road point corresponding to the RFID tag is not the destination road point, and continuing to navigate the robot according to a preset follow-up navigation scheme.

In a third aspect of the invention, a robot is provided comprising a processor, a memory and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect of the invention or the functions of the system according to the second aspect of the invention when executing the computer program.

According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method according to the first aspect of the present invention or performs the functions of the system according to the second aspect of the present invention.

According to the invention, the destination road points are determined according to the corresponding relation of the node labels and/or the corresponding relation of the road point labels based on the destination information, the road point list of all road points passing through one path from the current road point to the destination road point is determined according to the plane layout diagram, the current road point and the destination road point, and the robot travel semantic instruction between the corresponding road points is generated according to the coordinates of the current road point and the subsequent road points in the road point list, so that the robot sequentially moves according to the travel semantic instruction and simultaneously enables the RFID reader on the robot to work, when the RFID reader scans one or two RFID labels, the robot determines the road point corresponding to the scanned RFID label, determines whether the road point is the destination road point, and when the road point corresponding to the scanned RFID label is not the destination road point, the robot is continuously navigated according to the preset subsequent navigation scheme, so that only the plane layout of the working environment of the robot is required to be known, the scaling ratio is not limited, the robot is required to be accurately matched with the actual environment, and the map can be better understood and the map can be better adapted to the environment. In addition, the dependence on high-cost and high-precision hardware is reduced, and the production and maintenance cost of the robot is reduced.

Compared with the existing meal delivery robots and sweeping robots, the invention has a much wider working range, and the robot can work anywhere on the RFID tag as long as the RFID tag can be installed. Many existing meal delivery robots need to lay magnetic tracks in advance and greatly reform the ground, and only low-cost RFID tags are needed to be installed. In addition, some existing robots use lidar for mapping, but the cost of the laser radar of the commercial robot is thousands of, and because of the active transmitting equipment, the service life is limited, generally 1-3 years. In addition, conventional GPS or current lidar positioning in unmanned situations require very high accuracy Gao Cai. The robot does not need to know the accurate positioning, and can determine the approximate position of the robot according to the peripheral RFID tag. When the RFID reader carried by the robot reads one or two RFID tags, the robot is considered/knows that the robot is at a certain waypoint.

In addition, although "left", "right" and the like in the related art are also used as semantic instructions, such instructions belong to relative instructions, and a robot itself is used as a reference base point, which is liable to cause contradiction. For example, assuming that the robot is facing north, the left is actually moving west, if the robot is facing south, the left is moving east. Once the orientation of the robot is not the correct orientation, wrong movements may result to the left or right. In the invention, the semantic instructions such as eastern and western are based on a certain point of the layout diagram, and the direction is an absolute value, so that no conflict is caused. Even if the robot is misdirected, the correct motion direction of the next step can still be known according to the instructions such as eastern direction or western direction, so that the robot can adjust the robot according to the current direction and the direction of the next step, and then the next step of motion is completed.

Other features and advantages of the present invention will become more apparent from the following detailed description of embodiments of the present invention, which is to be read in connection with the accompanying drawings.

Drawings

Fig. 1 is a schematic plan layout of a robot working environment showing the positional relationship of nodes (rooms, elevators, hallways, stairways, etc.) of floors and schematic positional relationship among nodes, RFID tags, and waypoints;

FIG. 2 is a flow chart of an embodiment of a method of robotic navigation according to the present invention;

FIG. 3 is a block diagram of one embodiment of a robotic navigation system according to the present invention.

For the sake of clarity, these figures are schematic and simplified drawings, which only give details which are necessary for an understanding of the invention, while other details are omitted.

Detailed Description

Embodiments and examples of the present invention will be described in detail below with reference to the accompanying drawings.

The scope of applicability of the present invention will become apparent from the detailed description given hereinafter. It should be understood, however, that the detailed description and specific examples, while indicating preferred embodiments of the invention, are given by way of illustration only.

The present application relates to robotic navigation, and more particularly to robotic navigation in indoor two-dimensional space.

A robot work environment, such as a floor of a building, includes a plurality of nodes (rooms, elevators, hallways, stairways, etc.). To apply the method and system of the present invention, each node is provided with one or more, for example two, RFID (Radio Frequency Identification ) tags. RFID tags are typically placed at a height, for example 1 m 7 or 1 m 8, to prevent the RFID tag from being obscured by the human body. The robot stores a planar layout of the robot working environment, the planar layout comprising waypoints, each waypoint having coordinates and a number and corresponding to at least one node and/or at least one RFID tag. Each waypoint may belong to one RFID tag or two RFID tags facing each other, and mainly depends on the environment layout, and by limiting the read range limitation of the RFID tag reader of the robot, it is ensured that the tags in two rooms in front of each other on the corridor are not read simultaneously. The robot also stores a correspondence between nodes and waypoints (referred to as "node waypoint correspondence"), and/or a correspondence between nodes and RFID tags (referred to as "node tag correspondence"), and/or a correspondence between waypoints and RFID tags (referred to as "waypoint tag correspondence"). The robot includes initialized parameters such as maximum linear velocity, maximum angular velocity, linear velocity step (i.e. the minimum unit of each increase or decrease of linear velocity, the multiple of linear velocity step is the amount of linear velocity that increases), angular velocity step (i.e. the minimum unit of each increase or decrease of angular velocity, the multiple of angular velocity step is the amount of angular velocity that increases), safety distance (i.e. the nearest distance between the robot and an obstacle or wall), turning flag (zero clearing at initialization), etc., which may be default values of factory state of the robot, or may be set through a user interface at actual use.

Fig. 1 shows a schematic plan layout of a floor of a robot work environment, such as a hotel, showing the positional relationship of a room and an elevator of the floor and the schematic positional relationship between the room/elevator, the RFID tag and the waypoint. The middle independent square is an elevator, and the rest square is a room. Each room has 1-2 RFID tags placed on its exterior wall, labeled with a small rectangle. The dots are waypoints. The positions of the waypoints are preset according to the plane layout, and the waypoints exist on the plane layout but do not exist on the actual corridor.

The positions of the node RFID tags are marked on the layout in advance, the real RFID tags are attached to the doors or walls on the outer sides of the rooms, correspondingly, the approximate positions of the RFID tags are marked on the outer sides of the corresponding rooms on the layout, and the positions and the actual positions of the RFID tags on the layout do not need to be accurately and strictly corresponding. If two corresponding rooms are located on both sides of a corridor on the layout, such as a door to door, the midpoint of two corresponding tags on the layout is the location of the waypoint, and is actually the perpendicular intersection of the line connecting two RFID tags and the center line of the corridor. In practice, if the robot's RFID tag reader senses one or two RFID tags, the robot is considered to reach this waypoint. Similar to the previous case, if one side of the map is a wall and one side is a room, the midpoint of the corresponding points on the wall and the RFID tag on the map is a waypoint.

Some preferred embodiments of the robot navigation method and system of the present invention are set forth below. The robot is in a ready state and listens for task inputs.

Fig. 2 shows a flow chart of an embodiment of a method of robot navigation according to the invention.

In step S202, in response to the robot listening to the task input, it is determined whether the input task information contains a destination.

The task source is an external input. In the lan, a remote attendant, such as a hotel operator, selects or inputs a room number, e.g., 1294, for the robot to go through a specially designed web page, and after clicking to determine, the room number is sent to the robot. Upon receipt of the room number, e.g., 1294, the robot compares with the room information stored in the robot to determine if the received room number is a valid room number. When the pre-stored room information contains the received room number, it is determined as a valid room number, that is, it is determined that the input task information contains a destination, and the process proceeds to step S204; otherwise, the process proceeds to step S270, where a prompt for a destination/room number error is sent to the far-end attendant. In other embodiments, other numbers, such as RFID tag numbers, may also be directly selected or entered. In this case, the robot compares the received RFID tag number with the RFID tag list stored in the robot.

In step S204, a destination waypoint is determined based on the destination information.

The node waypoint correspondence may be a direct correspondence between nodes and waypoints, or may be an indirect correspondence between nodes and waypoints, for example, including a node label correspondence and a waypoint label correspondence. In the embodiment, based on the node waypoint correspondence, the corresponding waypoint number, i.e. the destination waypoint, can be directly determined according to the room number (node). In another embodiment, an RFID tag number corresponding to a room may be determined according to the room number based on the node tag correspondence, and then a waypoint number corresponding to the RFID tag may be determined according to the determined RFID tag number based on the waypoint tag correspondence. In still another embodiment, in the case of directly inputting the RFID tag number in the past, the waypoint number corresponding to the RFID tag may be determined according to the RFID tag number based on the waypoint tag correspondence.

In step S206, it is determined whether the waypoint at which the robot is currently located is different from the destination waypoint.

The robot start position is not determined. The robot may determine the current waypoint by scanning the surrounding RFID tags. Of course, the robot may be placed in a certain position in advance, for example, a fixed position of the robot working floor, such as an express point. And determining whether the current road point of the robot is different from the destination road point by comparing whether the number of the current road point is the same as the number of the destination road point. If the robot is currently located at a waypoint different from the destination waypoint, the process proceeds to step S208; otherwise, the process proceeds to step S270, the robot is not operated, and a prompt for a destination/room number error is sent to the far-end attendant.

In step S208, a route point list of all route points that a path from the current location route point to the destination route point passes through in sequence is determined according to the planar layout, the current location route point and the destination route point.

From the waypoint information on the floor plan, a path from the current waypoint to the destination waypoint may be generated that is made up of the waypoints. Depending on the specific layout of the robot working environment, there may be multiple paths from the current waypoint to the destination waypoint, in which case the path with the smallest number of waypoints passed may be selected as the path for determining the waypoint list, since the distance between the waypoints corresponding to the rooms is usually constant except for the waypoints of the elevator, and thus if the number of waypoints on one path is the smallest, meaning that the total length of the path is the shortest, selecting the path will be advantageous for improving the working efficiency of the robot. The waypoint list may be a sequential list of the numbers of waypoints that pass sequentially from the current waypoint to the destination waypoint.

A turn flag may also be generated while determining a path from the current waypoint to the destination waypoint. The turning mark is helpful for secondarily verifying whether turning is needed or not when the robot works later, and the problem caused by program errors is prevented.

In step S210, at least a travel semantic instruction of the robot from the current waypoint to the next subsequent waypoint is generated according to the coordinates of the current waypoint and the subsequent waypoints in the waypoint list, where the travel semantic instruction includes easting, southward, northward, or westward.

In an embodiment, only one travel semantic instruction may be generated from the current waypoint to the next subsequent waypoint. In another embodiment, the travel semantic instructions between all the successive waypoints in the waypoint list may also be generated at one time, including the travel semantic instructions from the current waypoint to the next subsequent waypoint.

In an embodiment, the lower left corner of the planar layout is taken as a reference base point, and the default orientation of the robot is north (of course, the orientation can be adjusted according to the actual layout) to generate four directions of southeast and northwest. Each waypoint has an x-coordinate, a y-coordinate. For example, if only the x direction changes, then an instruction to move to the east or west can be generated for the x and y coordinates of the current road point and the next subsequent road points, such as road points W1 and W2 (the x coordinate of the next road point is larger, an "eastward" semantic instruction is generated, the x coordinate of the next road point is smaller, an "westward" semantic instruction is generated), and if only the x direction changes for the next preceding and following road points, then an instruction to move to the east or west can be continuously generated; if only the y direction changes, then a north or south-going instruction can be generated (the y coordinate of the next waypoint is larger, generating a north semantic instruction, and the y coordinate of the next waypoint is smaller, generating a south semantic instruction). Of course, if the reference base points are different, the definition of the directions may also be different. The prior art uses accurate movement instructions for distance navigation, such as 5 meters, 10 meters, 100 meters forward, etc., which requires that the map must be exactly matched to the actual environment, i.e. that an accurate map be generated. The invention adopts semantic instructions to navigate, abandons distance navigation adopted in the existing navigation, for example, the navigation is eastward, and after touching the next node, the navigation is southward, only the plane layout of the working environment of the robot is needed to be known, and the scaling is not limited.

In other embodiments, when the x and y coordinates of two consecutive waypoints change, a semantic instruction, such as how much to deviate north from north, can be generated according to the difference value of the x and y coordinates of the two waypoints, i.e. the robot can move according to how much to deviate from north to a certain direction if the environment allows.

In step S212, the robot moves according to the travel semantic instruction while the RFID reader on the robot operates.

The RFID tag may store rich information according to actual needs, for example, a certain RFID tag is set to nxxnumber, where N is a tag orientation, XXX is an attribute of a node (location) where the tag is located, such as an elevator, a room, a corridor, etc., and NUMBER is a NUMBER corresponding to the tag. The RFID tag is adopted, so that the navigation method can be better understood and adapted to the environment.

The robot default orientation is north-facing. If the direction of motion corresponding to the next travel semantic instruction to be executed is different from the robot orientation, the robot adjusts the orientation to the direction of motion corresponding to the travel semantic instruction before executing the travel semantic instruction. The robot moves towards the motion direction corresponding to the semantic command according to initialized parameters such as maximum linear velocity, maximum angular velocity, linear velocity step, angular velocity step, safety distance and/or turning flag.

When the robot moves, a distance sensor of the robot, such as a laser radar or sonar, depicts the condition of the periphery of the robot, so that the robot is ensured to execute approximately parallel to a corridor and collision is prevented when steering is ensured. When the robot is straight, the distance sensor adjusts the position/orientation of the robot based on the left and right measurement values (distance between the robot and the wall) so that the robot travels along the wall at a certain distance and approximately parallel to the corridor.

After the robot detects that a transverse corridor exists in front, if the semantic command also requires steering at the road point, the robot talents steer according to the designated direction. The road point is an accurate point on the electronic plane layout diagram, mainly for the convenience of calculating the path. In an actual corridor, the "waypoint" corresponds to a range, and the robot considers itself to be at a certain waypoint after detecting the RFID tag. When the robot can move linearly, the robot can continuously scan to a certain RFID label, and the robot is always considered to be at a certain waypoint. Therefore, after the robot detects the road point at the turning position, the robot still needs to detect the change of the peripheral gallery and then turns. If the distance sensor detects that the distance value on the left or the right is larger than a preset value (for example, 5 meters, the preset value can be changed to be a value which accords with the field reality according to different places), and the movement direction corresponding to the next travelling semantic command is different from the current movement direction, the robot turns towards the movement direction corresponding to the next travelling semantic command. During turning of the robot, the distance detection value of 180 degrees in front is continuously detected, and after the robot rotates 45 degrees, if the distance value in front of the robot is continuously increased, the direction of the robot is determined to be gradually parallel to the front corridor. For example, the angular velocity of the robot is 0.12 radians per second, and a 3 second average can be used to calculate the distance value directly in front (i.e., the distance from the front of the robot to the corridor), the greater the distance value, the more parallel the robot is to the corridor direction. If the distance value is successively greater, for example 5 times, it is indicated that the robot has entered the turned corridor. After determining that the robot enters the turned corridor, the orientation of the robot is adjusted based on the left and right measurements of the distance sensor such that the robot orientation is approximately parallel to the corridor.

During the travel of the robot, if an obstacle to movement is encountered, the robot will stop and send an alarm to the far end. If the moving obstacle leaves, the robot proceeds. If the obstacle is a fixed obstacle, the robot judges whether the robot can bypass, and if the robot can not bypass, the robot stops running and sends a warning to the remote control end. If a detour is possible, after the robot detours around the fixed obstacle, the process returns to step S208, and the robot regenerates a path from the plan layout, the current waypoint and the destination waypoint, thereby ensuring that the destination can be reached.

When an obstacle is present in front of the robot, the robot is stopped first, and then, for example, whether the obstacle is moving or not can be determined based on the partial contour of the obstacle scanned by the distance sensor. For example, if the scanned profile is unchanged for, e.g., 10 seconds or other predetermined time, it may be determined that the obstacle is a fixed or stationary obstacle, otherwise a moving obstacle. In the case of a fixed obstacle, the robot may scan the front 180 degrees, scan the outline of the front obstacle and corridor out, get the approximate clearance distance of the obstacle to the left or right of the corridor, if the clearance distance on the left is greater than the frontal width of the robot by a factor of, for example, 1.2 (for safety reasons), the robot may attempt to bypass from the left, if the right is passable, bypass from the right, otherwise stop and alert the remote control.

When the robot moves according to the motion direction corresponding to the semantic instruction, the RFID tag readers of the robot synchronously start to work, and the surrounding possible RFID tags are continuously scanned. Upon scanning at least one, e.g., one or two, RFID tags, meaning that the robot has reached the waypoint corresponding to the respective RFID tag, the process proceeds to step S214. If the robot does not reach the next waypoint beyond the preset time because of being blocked, an alarm instruction can be sent to the far end.

In step S214, the robot determines a waypoint corresponding to the scanned RFID tag.

In step S216, it is determined whether the waypoint corresponding to the scanned RFID tag is a destination waypoint. If it is determined that the current waypoint is the destination waypoint, this means that the robot has arrived at the destination, the process proceeds to step S280, and navigation ends. If it is determined that the current waypoint is not the destination waypoint, the process proceeds to step S218.

In step S218, navigation of the robot is continued according to a predetermined subsequent navigation scheme.

In an embodiment, the predetermined subsequent navigation scheme may include: it is determined whether the current waypoint is a waypoint in the waypoint list. If it is determined that the current waypoint is a waypoint in the waypoint list, it is indicated that the robot movement direction is correct, further from the destination, the process proceeds to step S210 (in the case where only one travel semantic instruction was previously generated), the next travel semantic instruction is generated and moved in accordance therewith, or the process proceeds to step S212 (in the case where all travel semantic instructions were previously generated at once), the movement in accordance with the following travel semantic instruction is continued. If it is determined that the current waypoint is not the waypoint in the waypoint list, the robot movement direction is wrong, the process proceeds to step S208, and a new waypoint list of all the waypoints passing through one path from the current waypoint to the destination waypoint in sequence is regenerated and started according to the planar layout, the current waypoint and the destination waypoint.

In another embodiment, the predetermined subsequent navigation scheme may include: as long as the scanned waypoint corresponding to the RFID tag is not the destination waypoint, the process proceeds to step S208, and a new waypoint list of all the waypoints successively passed from the current waypoint to the destination waypoint is regenerated and started according to the plan layout, the current waypoint and the destination waypoint, regardless of whether the waypoint is the currently used waypoint in the waypoint list.

When the robot moves, all the waypoints and RFID tags which pass through within a certain time are stored, and then the stored waypoints and RFID tags are compared with the generated waypoint list, so that the robot is ensured to travel according to the waypoint list.

If the road point reached by the robot is not the road point in the road point list, the robot can determine the current direction of the robot according to the movement direction from the previous road point to the current road point. If the current orientation of the robot is different from the direction of motion corresponding to the next travel semantic instruction to be executed, which is generated from the regenerated waypoint list, the robot rotates to adjust the orientation to be consistent with the direction of motion corresponding to the next travel semantic instruction before starting to execute the next travel semantic instruction. The current orientation of the robot may also be determined by comparing RFID tags scanned at different times, such as comparing RFID tags scanned at the current time with RFID tags scanned at a previous time.

The orientation may also be determined by itself if the robot is restarted due to an anomaly, such as a power outage, or before the task is first performed. Firstly, a robot scans peripheral RFID labels, compares the peripheral RFID labels with an electronic map, finds the position of the robot on the electronic map (the current road point), then the robot moves along a wall, records the scanned RFID labels, for example, the robot rotates by itself, is kept parallel to a corridor, then scans opposite RFID labels 1 and 2, moves along a straight line, then scans opposite RFID labels 3 and 4, and can know the direction of the robot by comparing the movement direction from the road point corresponding to the RFID label 1-2 to the road point corresponding to the RFID label 3-4 on the electronic map. For example, when the robot moves from the road point W1 to the road point W2, by determining the difference between the coordinates, such as the y-coordinate being unchanged, the x-coordinate being unchanged, or the x-coordinate being unchanged, the y-coordinate being different, the two points may draw a direction, and then the moving direction of W1 to W2 may be determined based on the reference point positions mentioned above. If the current direction of the robot is consistent with the movement direction to be performed, giving a linear speed instruction, and enabling the robot to move along a straight line at a designed linear speed; otherwise, if the direction at the next moment is inconsistent with the current direction, an angular speed instruction needs to be given to turn the robot.

The adoption of the above logic method to determine the orientation of the robot instead of using an odometer or the like for judgment can reduce the dependence on hardware and reduce the production cost and maintenance cost of the robot, because the high-precision odometer is very expensive. Meanwhile, the problem of accumulated errors of the odometer sensor can be solved by adopting a logic method.

If the robot does not scan the RFID tag, it may be that the RFID tag is artificially blocked or missing, and the robot may proceed in the previous direction. For example, the semantic instructions generated are from waypoint 1 to next waypoint 2, north to next waypoint 3, north to next waypoint 4, then east to next waypoint 5, and so on. If the instructions are all in the same direction, the robot does not detect the road point 2 if the robot starts from the road point 1, but the robot successfully sends the instructions to the road point 3 along the same direction, so that the road point 2 can be ignored, and the robot continues to move from the road point 3 according to the instructions. If the road point corresponding to the RFID label scanned after the road point corresponding to the RRID label is blocked/deleted is not the road point in the semantic instruction, the road point list is regenerated, and then the process is continued according to the new road point list until the destination.

After the robot completes the current task (reaches the destination), it may return to the starting point along the previously generated path, or may receive a new room number in situ, and then go to the new room according to the above method. If the robot receives a plurality of room numbers in sequence, such as if the attendant sent rooms 1301, 1295, 1953, …, the robot can complete the tasks in sequence in the order received.

The method is mainly suitable for indoor and structured environments, such as hotel meal delivery, express delivery service or warehouse storage. For example, after receiving a room number sent by a hotel operator in a local area network, the robot determines the current position according to the RFID tag which is scanned currently, then plans a route from the current position to the target position and consisting of route points according to the target position and all route points on the plane layout, and then can reach a destination along the route.

In other embodiments, the order of the steps described above may be adjusted as appropriate.

In other embodiments, steps S202, S206 described above may be omitted, or may be implemented in conjunction with other suitable steps.

Fig. 3 shows a block diagram of an embodiment of a robotic navigation system according to the invention. The robot navigation system of this embodiment includes:

a destination waypoint determining module 302, configured to determine a destination waypoint based on destination information, where each node of the robot working environment is provided with one or more RFID tags, the RFID tag information includes a node where the RFID tag is located, and a plane layout of the robot working environment is stored in the robot, where the plane layout includes waypoints, and each waypoint has coordinates and corresponds to at least one node and/or at least one RFID tag;

the waypoint list determining module 304 is configured to determine, according to the planar layout, the current waypoint and the destination waypoint, a waypoint list of all waypoints that a path from the current waypoint to the destination waypoint sequentially passes through;

the semantic instruction generating module 306 is configured to at least generate a travelling semantic instruction of the robot from the current waypoint to a next subsequent waypoint according to coordinates of the current waypoint and the subsequent waypoints in the waypoint list, where the travelling semantic instruction includes easting, southing, northing or westward;

a moving module 308, configured to move the robot according to the travelling semantic instruction, while the RFID reader on the robot works;

the current waypoint judging module 310 is configured to determine, in response to the at least one RFID tag being scanned by the RFID reader, a waypoint corresponding to the scanned RFID tag by the robot, and determine whether the waypoint is a destination waypoint;

and a continuing navigation module 312, configured to continue navigating the robot according to a predetermined subsequent navigation scheme in response to the scanned waypoint corresponding to the RFID tag being not the destination waypoint.

In another embodiment, the present invention provides a robot, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps of the method embodiment or other corresponding method embodiments described in connection with fig. 2 or implements the functions of the system embodiment or other corresponding system embodiments described in connection with fig. 3 when executing the computer program, which are not described herein.

In another embodiment, the present invention provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method embodiment or other corresponding method embodiments described in connection with fig. 2 or implements the functions of the system embodiment or other corresponding system embodiments described in connection with fig. 3, which are not described herein.

The various embodiments described herein, or particular features, structures, or characteristics thereof, may be combined as suitable in one or more embodiments of the invention. In addition, in some cases, the order of steps described in the flowcharts and/or flow-line processes may be modified as appropriate and need not be performed in exactly the order described. Additionally, various aspects of the invention may be implemented using software, hardware, firmware, or a combination thereof and/or other computer-implemented modules or devices that perform the described functions. A software implementation of the present invention may include executable code stored in a computer readable medium and executed by one or more processors. The computer-readable medium may include a computer hard drive, ROM, RAM, flash memory, a portable computer storage medium such as CD-ROM, DVD-ROM, flash drives and/or other devices having a Universal Serial Bus (USB) interface, and/or any other suitable tangible or non-transitory computer-readable medium or computer memory on which executable code may be stored and executed by a processor. The invention may be used in connection with any suitable operating system.

As used herein, the singular forms "a", "an" and "the" include plural referents (i.e., having the meaning of "at least one") unless otherwise indicated. It will be further understood that the terms "has," "comprises," "including" and/or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and/or groups thereof. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

While the foregoing is directed to some preferred embodiments of the present invention, it should be emphasized that the present invention is not limited to these embodiments, but may be embodied in other forms within the scope of the inventive subject matter. Various changes and modifications may be made by one skilled in the art without departing from the spirit of the invention, and these changes or modifications still fall within the scope of the invention.

Claims (10)

1. A method of robotic navigation, the method comprising:

determining destination road points based on destination information, wherein each node of a robot working environment is provided with one or more RFID tags, RFID tag information comprises the node where the RFID tag is located, a plane layout diagram of the robot working environment is also stored in the robot, and each road point comprises the road points, and each road point has coordinates and corresponds to at least one node and/or at least one RFID tag;

step two, determining a road point list of all road points successively passed by a path from the current road point to the destination road point according to the plane layout, the current road point and the destination road point;

step three, at least generating a traveling semantic instruction of the robot from the current road point to the next subsequent road point according to the coordinates of the current road point and the subsequent road points in the road point list, wherein the traveling semantic instruction comprises easting, southward, northward or westward;

step four, the robot moves according to the travelling semantic instruction, and meanwhile an RFID reader on the robot works;

step five, responding to the fact that the RFID reader scans at least one RFID label, and determining a road point corresponding to the scanned RFID label by the robot to determine whether the road point is a destination road point;

and step six, responding to the scanned road point corresponding to the RFID label not being the destination road point, and continuing to navigate the robot according to a preset follow-up navigation scheme.

2. The method of claim 1, wherein the predetermined subsequent navigation scheme comprises:

determining whether the road point corresponding to the scanned RFID tag is a road point in a road point list;

responding to the scanned road points corresponding to the RFID tags as the road points in the road point list, and returning to execute the step III; a kind of electronic device with high-pressure air-conditioning system

And responding to the scanned road point corresponding to the RFID label not being the road point in the road point list, returning to execute the step II, and generating and starting a new road point list.

3. The method according to claim 2, wherein the method further comprises:

determining the current direction of the robot according to the movement direction from the previous road point to the current road point;

in response to the current orientation of the robot being different from the direction of motion corresponding to the next travel semantic instruction to be executed generated from the new waypoint list, the robot rotates to adjust its orientation to be consistent with the direction of motion corresponding to the next travel semantic instruction before starting to execute the next travel semantic instruction.

4. The method of claim 1, wherein the predetermined subsequent navigation scheme comprises:

and responding to the scanned route point corresponding to the RFID label not being the destination route point, returning to execute the step two, and generating and starting a new route point list.

5. The method of claim 1, wherein determining a waypoint list of all waypoints traversed in succession from a path currently located to a destination waypoint comprises:

in response to there being multiple paths from the current point to the destination point, the path that has the least number of points traversed is selected as the path for determining the list of points.

6. The method of claim 1, wherein generating the robot travel semantic instructions between successive waypoints comprises:

comparing (x, y) coordinates of two successive waypoints when the lower left corner of the planar layout is taken as a reference base point, and generating an eastward semantic instruction in response to only x coordinate changes and the x coordinate of the next waypoint is larger; generating a western semantic instruction in response to only the x coordinate change and the x coordinate of the next waypoint being smaller; generating a north semantic instruction in response to only the y coordinate change and the y coordinate of the next waypoint being greater; in response to only the y-coordinate change and the y-coordinate of the next waypoint being smaller, a "southward" semantic instruction is generated.

7. The method of claim 1, wherein the robot moving according to travel semantic instructions comprises:

responding to the fact that a distance sensor of the robot detects that the left or right distance value is larger than a preset value and the motion direction corresponding to the next travelling semantic command is different from the current motion direction, and turning the robot towards the motion direction corresponding to the next travelling semantic command;

during turning of the robot, detecting a distance detection value of 180 degrees in front of the robot continuously, and determining that the direction of the robot is gradually parallel to a front corridor after the robot rotates 45 degrees and in response to the fact that the distance value of the front of the robot is continuously increased;

responsive to the robot entering the turned corridor, adjusting an orientation of the robot based on the left and right measurements of the distance sensor such that the robot orientation is substantially parallel to the corridor;

in response to the robot traveling straight, the distance sensor adjusts the position of the robot according to the distance of the robot from the wall so that the robot travels along the wall at a distance.

8. The method of claim 7, wherein the robot moving according to travel semantic instructions further comprises:

in response to detecting the fixed obstacle, determining whether a detour is possible;

in response to determining that the detour is not possible, stopping the robot and sending a warning to the remote control terminal;

in response to determining that the detour can be performed, the robot returns to perform step two after detouring the fixed obstacle.

9. The method of claim 1, wherein the RFID tag information further comprises an orientation and/or number of the RFID tag.

10. A robotic navigation system, the system comprising:

the system comprises a destination waypoint determining module, a robot working environment determining module and a storage module, wherein the destination waypoint determining module is used for determining destination waypoints based on destination information, each node of the robot working environment is provided with one or more RFID tags, RFID tag information comprises the node where the RFID tag is located, the robot is further stored with a plane layout diagram of the robot working environment, and each path point comprises a waypoint, and each path point has coordinates and corresponds to at least one node and/or at least one RFID tag;

the route point list determining module is used for determining a route point list of all route points which are sequentially passed by a path from the current route point to the destination route point according to the plane layout, the current route point and the destination route point;

the semantic instruction generation module is used for generating at least a traveling semantic instruction of the robot from the current road point to the next subsequent road point according to the coordinates of the current road point and the subsequent road points in the road point list, wherein the traveling semantic instruction comprises easting, southing, northing or westward;

the mobile module is used for enabling the robot to move according to the travelling semantic instruction and simultaneously enabling the RFID reader on the robot to work;

the current waypoint judging module is used for responding to the fact that the RFID reader scans at least one RFID label, and the robot determines the waypoint corresponding to the scanned RFID label and determines whether the waypoint is a destination waypoint or not;

and the continuing navigation module is used for responding to the fact that the scanned road point corresponding to the RFID tag is not the destination road point, and continuing to navigate the robot according to a preset follow-up navigation scheme.