CN109048910B - Robot avoidance pre-judging method and device - Google Patents

Robot avoidance pre-judging method and device Download PDF

Info

Publication number
CN109048910B
CN109048910B CN201810998485.6A CN201810998485A CN109048910B CN 109048910 B CN109048910 B CN 109048910B CN 201810998485 A CN201810998485 A CN 201810998485A CN 109048910 B CN109048910 B CN 109048910B
Authority
CN
China
Prior art keywords
robot
avoidance
distance
interference
path
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810998485.6A
Other languages
Chinese (zh)
Other versions
CN109048910A (en
Inventor
刘亚军
谢庆华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Liu Yajun
Original Assignee
Guangzhou Dreamone Robot Automation Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Dreamone Robot Automation Co ltd filed Critical Guangzhou Dreamone Robot Automation Co ltd
Priority to CN201810998485.6A priority Critical patent/CN109048910B/en
Publication of CN109048910A publication Critical patent/CN109048910A/en
Application granted granted Critical
Publication of CN109048910B publication Critical patent/CN109048910B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1656Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B25J9/1666Avoiding collision or forbidden zones
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00Controls for manipulators

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)
  • Numerical Control (AREA)

Abstract

The invention provides a robot avoidance prejudging method and a device, wherein the robot avoidance prejudging method comprises the following steps: predicting at least one group of interference section combination; respectively calculating a first priority factor corresponding to the first robot and a first priority factor corresponding to the second robot; determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority of the first robot and the first priority of the second robot respectively; and pre-judging the avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority so as to facilitate timely avoidance when the avoidance robot reaches the interference road section combination. And determining an avoidance scheme in advance so as to avoid in time when the avoidance robot reaches the interference road section combination and avoid mutual blocking.

Description

Robot avoidance pre-judging method and device
Technical Field
The invention relates to the technical field of robot movement, in particular to a robot avoidance pre-judging method and device.
Background
With the advancement of technology, robots are no longer merely characters in science and technology movies, but are really appearing in real life. The robot is a machine device that automatically performs work. It can accept human command, run the program programmed in advance, and also can operate according to the principle outline action made by artificial intelligence technology. It can bear a lot of work in life, has realized saving to the manpower cost.
However, current robotics is not mature enough and there are many problems. For example, when a plurality of moving robots are operated in the same communicated space, the problem that the robots cannot block each other is always avoided, and particularly, in a narrow space, the robots are deadlocked or blocked.
Therefore, it is very important how to pre-determine the avoidance scheme in advance.
Disclosure of Invention
The invention aims to provide a robot avoidance pre-judging method and device, which are used for improving the problems.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a robot avoidance pre-judging method, which is applied to a server, where the server is in communication connection with a first robot and a second robot, respectively, and the robot avoidance pre-judging method includes: predicting at least one set of interference section combinations where a first remaining path of the first robot and a second remaining path of the second robot have interference, wherein the interference section combinations comprise a first interference section belonging to the first remaining path and a second interference section belonging to the second remaining path; calculating a first priority factor corresponding to the first robot according to a first ideal passing time and a first predicted passing time of the first robot, wherein the first ideal passing time is a time length for the first robot to pass through the first remaining path at an average speed; the first predicted route time is the sum of the first ideal route time and the waiting time of each first interference section; calculating a first priority factor corresponding to the second robot according to a second ideal route time of the second robot and a second predicted route time, wherein the second ideal route time is a time length for the second robot to pass through the second surplus route at an average speed; the second predicted route time is the sum of the second ideal route time and the waiting time of each second interference section; determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority of the first robot and the first priority of the second robot respectively; and pre-judging the avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority so as to facilitate timely avoidance when the avoidance robot reaches the interference road section combination.
In a second aspect, an embodiment of the present invention provides a robot avoidance pre-judging device, which is applied to a server, where the server is in communication connection with a first robot and a second robot, respectively, and the robot avoidance pre-judging device includes: the prediction module is used for predicting at least one group of interference section combinations with interference between a first residual path of the first robot and a second residual path of the second robot, wherein the interference section combinations comprise a first interference section belonging to the first residual path and a second interference section belonging to the second residual path; the calculation module is used for calculating a first priority factor corresponding to the first robot according to a first ideal passing time and a first predicted passing time of the first robot, wherein the first ideal passing time is the time length of the first robot passing through the first remaining path according to the average speed; the first predicted route time is the sum of the first ideal route time and the waiting time of each first interference section; the calculation module is further configured to calculate a first priority factor corresponding to the second robot according to a second ideal route time of the second robot and a second predicted route time, where the second ideal route time is a time length for the second robot to pass through the second remaining path at an average speed; the second predicted route time is the sum of the second ideal route time and the waiting time of each second interference section; the determining module is used for determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority factor of the first robot and the first priority factor of the second robot respectively; and the prejudging module is used for prejudging an avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority so as to avoid in time when the avoidance robot reaches the interference road section combination.
Compared with the prior art, the robot avoidance pre-judging method provided by the invention has the advantages that at least one group of interference section combination with interference between the first surplus path of the first robot and the second surplus path of the second robot is predicted, then the first priority factor corresponding to the first robot is calculated according to the first ideal passing time and the first predicted passing time of the first robot passing through the first surplus path at the average speed, and the first priority factor corresponding to the second robot is obtained in the same way. And determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority of the first robot and the first priority of the second robot. The first priority factor generated by the ideal transit time and the predicted transit time is used as an estimate of the priority to make the obtained priority more representative. And finally, pre-judging an avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority, and determining an avoidance scheme in advance so as to avoid timely avoiding when the avoidance robot reaches the interference road section combination and avoid mutual blocking.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic diagram of an application environment according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of the server shown in fig. 1.
Fig. 3 is a flowchart illustrating steps of a method for predicting avoidance of a robot according to an embodiment of the present invention.
Fig. 4 is another part of a flowchart of steps of a method for predicting avoidance of a robot according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a robot avoidance pre-judging device according to an embodiment of the present invention.
Icon: 100-a server; 111-a memory; 112-a processor; 113-a communication unit; 200-a robot; 300-a robot avoidance pre-judging device; 301-a prediction module; 302-a calculation module; 303-a determination module; 304-a prejudgment module; 305 — an acquisition module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The following embodiments of the present invention can be applied to an environment shown in fig. 1 without particular description, and as shown in fig. 1, a server 100 is connected to a plurality of mobile robots 200 in a communication manner. For convenience of description, in the embodiment of the present invention, one robot 200 is used as the first robot, and the other robot 200 communicating with the server 100 is used as the second robot.
A map of the operation site is preset in the robot 200, and a real-time position of the robot 200 may be determined by using a sensor provided in combination with the map of the operation site, for example, the real-time position may be grid coordinates on the map. The robot 200 may plan a path to the destination according to the current position information, which meets the user's expectation. The path may be a set of raster path points. The size of the robot 200, the safety distance, may be pre-configured within the robot 200, such as the height and width of the robot 200. The robot 200 may also identify obstacles in the direction of motion (e.g., other robots 200 in operation).
Referring to fig. 2, the server 100 includes a robot avoidance prediction device 300, a memory 111, a processor 112, and a communication unit 113.
The memory 111, the processor 112 and the communication unit 113 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The robot avoidance prediction device 300 includes at least one software functional module which can be stored in the memory 111 in the form of software or Firmware (Firmware) or is solidified in an Operating System (OS) of the robot 200. The processor 112 is configured to execute executable modules stored in the memory 111, such as software functional modules and computer programs included in the robot avoidance prediction apparatus 300.
The Memory 111 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 111 is used to store programs or data. The communication unit 113 is configured to establish a communication connection between the robot 200 and another communication terminal via the network, and to transmit and receive data via the network.
It should be understood that the configuration shown in fig. 2 is merely a schematic diagram of the configuration of the server 100, and that the server 100 may include more or less components than those shown in fig. 2, or have a different configuration than that shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
First embodiment
Referring to fig. 3, fig. 3 is a flowchart of a robot avoidance prediction method according to a preferred embodiment of the present invention. Applied to the server 100 in fig. 1. The robot avoidance pre-judging method comprises the following steps:
step S101, predicting at least one group of interference section combination where the first residual path of the first robot and the second residual path of the second robot have interference.
In an embodiment of the invention, the combination of interference segments comprises a first interference segment belonging to the first remnant path and a second interference segment belonging to the second remnant path. It should be noted that when the first robot needs to initiate displacement along the first displacement path, the existing interference section combination is predicted. Specifically, the server 100 acquires a first remnant path and a second remnant path of a second robot that is in operation, respectively, from a first robot.
The displacement path generated in advance by the first robot is the first displacement path, and the displacement path generated by the second robot is the second displacement path. The first remnant path belongs to a first displacement path, and the second remnant path belongs to a second displacement path. The displacement path is composed of a plurality of raster path points, and when the robot 200 generates the displacement path, the raster path points on the displacement path are sequenced according to the sequence of predicted arrival of each raster path point, so that each raster path point on the displacement path executed or to be executed by each robot 200 corresponds to a sequence number. It will also be appreciated that the displacement path may be a set of a plurality of ordered raster path points.
In this embodiment of the present invention, the manner of obtaining the first remnant path and the second remnant path may be: respectively acquiring the first displacement path and the second displacement path; receiving current first position information of the first robot and current second position information of the second robot; dividing the first remnant path from the first displacement path according to the first position information and dividing the second remnant path from the second displacement path according to the second position information. Specifically, the manner of acquiring the first remaining path from the first displacement path according to the first position information includes: matching a first target raster path point on the first displacement path according to the first position information. Generally, the position information of the robot 200 after each movement is substantially consistent with one raster path point on the displacement path, and the substantial consistency can be understood as that the distance between the two is not different from the preset error threshold. Optionally, the first target raster path point is selected as the raster path point whose distance from the first location information satisfies a predetermined error threshold. It can also be understood that when the actual position of the first robot is the first position information, the corresponding position of the first robot on the first displacement path is the first target raster path point. And forming a first residual path by the raster path points in the first displacement path, the serial numbers of which are arranged behind the first target raster path point. For example, if the ranking numbers of the corresponding raster path points in the first shift path are 1 to 100 in order, and the first target raster path point matching the first position information is the raster path point listed at position 20 on the first shift path, the raster path points listed at positions 20 to 100 on the first shift path are taken as the first remaining path. The principle of the second remnant path is the same as that of the first remnant path, and is not described herein again.
In an embodiment of the present invention, the real-time status of the robot 200 may be expressed as:
Figure BDA0001782403130000071
where A is a displacement path generated in advance by the robot 200, which may be a set of a plurality of raster path point position information, wA(xi,yi) A grid position coordinate value representing the ith grid-path point on the displacement path, L represents the actual position of the robot 200,w*(x*,y*) Grid coordinate value l representing the actual position of the robot 200i(xi,yi) Representing the distance between the ith raster path point on the displacement path and the position immediately before the last move.
Further, the implementation of step S101 may be as follows:
(1) and according to a preset safety distance and a preset multiple of the robot, dividing the first surplus path into a plurality of first road sections and dividing the second surplus path into a plurality of second road sections respectively. Preferably, the first remaining path is divided into a plurality of first segments having a length equal to a preset multiple of the safety distance; and dividing the second remnant path into a plurality of second road segments with the length equal to the preset multiple of the safety distance.
(2) And sequencing the first path according to the expected arrival sequence of the first robot, and sequencing the second path according to the expected arrival sequence of the second robot.
(3) And sequentially comparing each section of the first road section with the corresponding second road section with the same serial number until the first road section and the second road section with the same serial number do not exist so as to obtain the comparison result. Alternatively, the comparison may be performed by calculating a distance length value between each corresponding raster path point in the first road segment and the second road segment with the same sequence number. And comparing the distance length value corresponding to each raster path point with a preset multiple of the safety distance to obtain a comparison result corresponding to the first path segment. It should be noted that, when the number of the first road section is the same as that of the second road section, each first road section corresponds to a second road section with the same serial number; when the number of the sections of the first road section is less than that of the second road section, each section of the first road section corresponds to the second road section with the same serial number, and the second road section with the serial number greater than the maximum serial number in the first road section does not have the first road section with the same serial number; when the number of the segments of the second road segment is less than that of the first road segment, each segment of the second road segment corresponds to the first road segment with the same serial number, and the first road segment with the serial number greater than the maximum serial number in the second road segment does not have the first road segment with the same serial number. Optionally, when the first road segment and the second road segment are performed, only the first road segment and the second road segment having the same sequence number are compared. In the above example, when comparing the first road segment with the corresponding serial number of 1-7 with the second road segment with the corresponding serial number of 1-6, the first road segment with the corresponding serial number of 1-6 and the second road segment with the corresponding serial number of 1-6 are only needed to be compared once.
As an implementation manner, the following algorithm may be adopted to implement step S103, specifically:
Figure BDA0001782403130000081
wherein the content of the first and second substances,
Figure BDA0001782403130000082
representing sequence number i on a first path with sequence number njThe raster path point and the second path with the sequence number n have the sequence number ikDistance length value of raster path point(s).
Figure BDA0001782403130000083
Representing a sequence number i on the first pathjThe first direction coordinate values of the raster path points,
Figure BDA0001782403130000091
representing a sequence number i on the first pathjA second direction coordinate value of the raster path point of (1).
Figure BDA0001782403130000092
Sequence number i on the second pathkThe first direction coordinate values of the raster path points,
Figure BDA0001782403130000093
sequence number i on the second pathkA second direction coordinate value of the raster path point of (1). In addition, i isjThe value of (d) may be the sequence number of the raster path point of the first path belonging to the nth segment. i.e. ikThe value of the grid of the second path belonging to the nth segmentThe number of lattice path points. q represents the number of the grid data points corresponding to each first segment, k represents a preset multiple, and lqRepresenting the safety distance, s representing the distance between two adjacent raster path points, mjRepresenting the total number of raster path points on the first remnant path of the first robot, mkRepresenting the total number of raster path points on the second remnant path of the second robot. A. thejRepresenting raster path points on a first displacement path, AkRepresenting raster data points on the second path of displacement, wj(xj,yj) Raster coordinate information, w, representing raster path points on the first displacement pathk(xk,yk) Raster coordinate information representing raster path points on the second displacement path.
(4) When the comparison result between the first road section and the second road section with the same corresponding serial number meets the preset requirement, taking the first road section as a first interference road section corresponding to the interference road section combination; and taking the second road section as a second interference road section corresponding to the interference road section combination.
In the embodiment of the present invention, the way in which the comparison result meets the preset requirement may be: at least one distance length value between the first road section and the second road section is smaller than a preset multiple of the safety distance.
Step S102, calculating a first priority factor corresponding to the first robot according to the first ideal passing time and the first predicted passing time of the first robot. And calculating a first priority factor corresponding to the second robot according to the second ideal passing time and the second predicted passing time of the second robot.
In this embodiment of the present invention, the first ideal passing time is a time length during which the first robot passes through the first remaining path at an average speed. The second ideal passing time is a time length for the second robot to pass through the second remaining path at the average speed. That is, it can be understood that the ideal passing time is a time length during which the robot 200 smoothly passes through the corresponding remaining path at the average speed when there is no interference.
The first predicted route time is a sum of the first ideal route time and a waiting time of each of the first interference sections, and the second predicted route time is a sum of the second ideal route time and a waiting time of each of the second interference sections. That is, it can be understood that the predicted passing time is the total time consumed for waiting for each interference section in the process of the robot 200 walking the surplus path. Optionally, the waiting time corresponding to each interference section is a time length for the robot 200 to walk through the interference section; the waiting time corresponding to each interference section can also be a preset duration.
Alternatively, the first predicted transit time may be obtained by:
according to the first interference section, the average speed, the safety distance and the preset multiple corresponding to the first surplus path, utilizing a formula:
Figure BDA0001782403130000101
calculating the first predicted transit time; wherein S represents the first predicted transit time,/qRepresents said safety distance, k represents said preset multiple, klqRepresents the length of the first interference section, s represents the average speed, CiRepresenting the interference factor of the first road section with the serial number i, and when the first road section with the serial number i is the first interference road section, corresponding CiThe value is 1, when the first road section with the serial number i is not the first interference road section, the corresponding CiThe value is 0.
It should be noted that the obtaining manner of the second predicted passing time is the same as the obtaining manner of the first predicted passing time, and details are not repeated here.
Step S103, determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority of the first robot and the first priority of the second robot respectively.
In the embodiment of the invention, the second priority factor of the first robot on the first interference section is determined according to the first raster path point listed at the first position of the first interference section in the running direction of the first robot and the second raster path point listed at the first position of the second interference section in the running direction of the second robot, and then the first priority factor of the first robot is combined to obtain the corresponding first priority of the first robot on the first interference section. And determining a second priority factor of the second robot on the second interference road section according to the first raster path point and the second raster path point, and combining the first priority factor of the second robot to obtain a second priority corresponding to the second robot on the second interference road section.
Optionally, the second priority factor of the first robot may be obtained by:
(1) a first raster path point of the first interference path segment listed first in the travel direction of the first robot and a second raster path point of the second interference path segment listed first in the travel direction of the second robot are obtained.
(2) And calculating a corresponding intersection angle according to the first raster path point and the second raster path point.
In the embodiment of the present invention, the intersection angle may be an included angle between a connection line between the first raster path point and the path intersection point and a connection line between the second raster path point and the path intersection point, and the intersection angle may be calculated by the following formula:
Figure BDA0001782403130000111
wherein x iscAnd ycRespectively representing the abscissa and ordinate of the path intersection, xs1And ys1Respectively representing the abscissa and ordinate, x, of the first raster path points2And ys2Respectively, the abscissa and ordinate of the second raster-path point, and α the intersection angle.
It should be noted that the path intersection may be an intersection between the first interference section and the second interference section. After the server 100 determines the first interference section and the second interference section, it may directly extract a raster path point with the closest position coordinate between the first interference section and the second interference section as a path intersection.
(3) And calculating an initial avoidance distance according to the intersection angle.
In the embodiment of the present invention, the initial avoidance distance may be calculated by the following formula:
Figure BDA0001782403130000121
k2≥k1≥3
wherein the content of the first and second substances,
Figure BDA0001782403130000122
denotes the initial avoidance distance, α denotes the intersection angle, k1Representing a first safety factor, k2Indicating a second safety factor,/qIndicating a preset safe distance. k is a radical of1And k2May be a preselected value.
(3) A first physical distance between the first raster path point and the path intersection point is calculated.
In the embodiment of the present invention, the position information of the first raster path point and the path intersection may be calculated by the following formula:
l1=|xs1-xc|+|ys1-yc|
wherein x iscAnd ycRespectively representing the abscissa and ordinate, x, of the path intersections1And ys1Respectively, the abscissa and ordinate of the first raster-path point.
(4) And obtaining a second priority factor of the first robot on the first interference road section according to the first physical distance and the initial avoidance distance.
In the embodiment of the present invention, obtaining the second priority factor of the first robot according to the first physical distance and the initial avoidance distance may specifically be implemented by: firstly, judging whether a first physical distance is greater than an initial avoidance distance, and when the first physical distance is greater than the initial avoidance distance, taking the first physical distance as a first final avoidance distance; when the first physical distance is smaller than or equal to the initial avoidance distance, taking the initial avoidance distance as a first final avoidance distance; then, the ratio of the first physical distance to the first final avoidance distance is used as a second priority factor for the first robot.
The same principle as calculating the second priority factor of the first robot, the second priority factor of the second robot may be calculated by: calculating a second physical distance between the second raster path point and the path intersection point; and obtaining the second priority factor of the second robot on the second interference road section according to the second physical distance and the initial avoidance distance.
Further, the first priority corresponding to the first robot on the first interference road section is calculated according to the first priority factor and the second priority factor.
In one embodiment, a first priority of the first robot is calculated based on the first priority factor and the second priority factor of the first robot. Specifically, it is calculated by the following formula:
R1=a1*P11+a2*P12
wherein R is1Representing a first priority of the first robot; a is1The weight representing the first priority factor may be preset; p11Representing a first priority factor, a, of the first robot2The weight indicating the second priority factor may be preset, and it should be noted that a1+a2=1,P12Representing a second priority factor of the first robot.
The principle of calculating the second priority of the second robot is the same as that of calculating the first priority of the first robot, and will not be described herein again.
And step S104, pre-judging an avoidance robot corresponding to the interference road section combination from the first robot and the second robot by using the first priority and the second priority so as to avoid in time when the avoidance robot reaches the interference road section combination.
In an embodiment of the present invention, when the first priority is greater than the second priority, the first robot is determined as an avoided robot, and the second robot is determined as an avoided robot, and vice versa. The avoidance robot reaching the interference road section combination means that the real-time position of the avoidance robot is initially overlapped with the raster path point corresponding to the first interference road section or the second interference road section corresponding to the interference road section combination, or the distance between the first interference road section and the second interference road section meets a preset threshold value. Specifically, when the avoidance robot is the first robot, the avoidance robot may arrive at the interference road section combination such that a distance between a real-time position of the first robot and the first raster path point satisfies a preset threshold or overlaps; when the avoidance robot is the second robot, the avoidance robot may arrive at the interference section combination such that a distance between a real-time position of the second robot and the second raster path point satisfies a preset threshold or overlaps.
Further, as shown in fig. 4, the method for predicting avoidance of a robot according to the embodiment of the present invention may further include the following steps:
step S201, a path intersection corresponding to the interference road section combination, a first raster path point listed in the first position of the first interference road section in the running direction of the first robot, and a second raster path point listed in the first position of the second interference road section in the running direction of the second robot are obtained.
Step S202, calculating an avoidance waiting time length and an avoidance point corresponding to the avoidance robot in the interference road section combination according to the path intersection, the first raster path point and the second raster path point, so that the avoidance robot moves to the avoidance point to pause the avoidance waiting time length for avoidance when reaching the interference road section combination.
In the embodiment of the present invention, the manner of calculating the avoidance waiting duration is as follows: and acquiring a physical distance between an avoidance raster path point corresponding to the avoidance robot and the position of the path intersection, and calculating a first avoidance duration of the avoidance robot according to the physical distance and the average speed. It should be noted that, when the first robot is the robot, the avoidance raster path point is the first raster path point, and when the second robot is the robot, the avoidance raster path point is the second raster path point.
And acquiring the final avoidance distance of the avoidance robot, and calculating a second avoidance duration of the avoidance robot according to the final avoidance distance and the average speed. It should be noted that, when the first robot is the robot, the final avoidance distance is the first final avoidance distance, and when the second robot is the robot, the final avoidance distance is the second final avoidance distance.
And taking the sum of the first avoidance duration and the second avoidance duration as the avoidance waiting duration of the avoidance robot.
In the embodiment of the present invention, the avoidance waiting duration may be calculated by the following formula:
Figure BDA0001782403130000141
wherein, t1Denotes a first avoidance period, t2Indicating a second avoidance time period, v an average speed, s a first raster path point of the interference route section in the direction of travel of the robot 200, c a path intersection point, liIndicates the distance between the corresponding ith raster path point on the interference route and the corresponding (i-1) th raster path point on the interference route, ldAnd representing the final avoidance distance of the avoidance robot.
Specifically, the manner of determining the avoidance point according to the avoidance raster path point and the final avoidance distance is as follows: and determining an avoidance point according to the final avoidance distance and the current position of the avoidance robot.
In the embodiment of the present invention, the avoidance point is a grid point having a length from a first grid path point of the interference road section of the avoidance robot as a final avoidance distance, where the grid point may be located on a first displacement path of the first robot or a second displacement path of the second robot, or may be another grid point outside the displacement path, and the distance between the avoidance point and the first grid path point of the interference road section of the avoidance robot is the final avoidance distance, and is not necessarily the distance between the avoidance point and the first grid path point of the interference road section of the avoidance robot is exactly equal to the final avoidance distance, or may be the distance between the avoidance point and the first grid path point of the interference road section of the avoidance robot is within a preset range of the final avoidance distance. For example, the avoidance robot is a first robot, the first interference section of the first robot includes A, B, C three raster path points, the final avoidance distance, that is, the first final avoidance distance is 5, the first raster path point a of the first interference section of the first robot is 3, the next raster path point B adjacent to a is 6, the next raster path point C adjacent to B is 9, and the preset range is (the final avoidance distance is-1, and the final avoidance distance is +1), and the navigation point B is determined to be an avoidance point. For another example, the avoidance robot is a first robot, the first interference route of the first robot includes A, B, C three raster path points, the final avoidance distance, that is, the first final avoidance distance is 5, the first raster path point a of the first robot is 3, the next raster path point B adjacent to a is 9, the next raster path point C adjacent to B is 12, and the first raster path point a is 5 from the raster point D, the navigation point D is an avoidance point.
In the embodiment of the invention, the priorities of the first robot and the second robot on the first interference road section and the second interference road section are reasonably determined, and the avoidance robot, the avoidance waiting time and the avoidance point are determined from the first robot and the second robot according to the priorities, so that compared with the prior art, the method has the following beneficial effects:
first, the distance between the robot 200 and the route intersection is used as the second priority factor of the priority, and the robot 200 that is closer to the route intersection at the first raster path point corresponding to the interference link is set with a higher priority, so that the robot 200 that will reach the route intersection first passes through the intersection as soon as possible, thereby reducing the influence on the moving efficiency of the robots 200 at both sides of the route intersection.
Secondly, the percentage of the ideal passing time length and the predicted passing time of the robot 200 is used as a first priority factor of the avoidance priority, and a higher priority is set for the robot 200 which is expected to be less affected by the interfered road section, so that the robot 200 which is expected to finish the preset path firstly finishes the preset path as soon as possible, and the influence on the moving efficiency of the robots 200 of both sides with crossed paths is reduced.
Thirdly, different weights are set for the first priority factor and the second priority factor according to different scenes, so that the determined avoidance robot is more reasonable on one hand, and the robot avoidance pre-judging method in the embodiment of the invention is more applicable to more scenes on the other hand.
Further, the robot avoidance pre-judging method provided by the embodiment of the invention further comprises the following steps:
and respectively calculating a first total time length of the first robot passing through the first surplus path and a second total time length of the second robot passing through the second surplus path according to the avoidance robot and the avoidance waiting time length corresponding to each interference road section combination.
In an embodiment of the present invention, the first total duration is a sum of the first ideal passing time and the avoidance waiting duration corresponding to when the first robot is used as the avoidance robot. And the second total duration is the sum of the second ideal passing time and the corresponding avoidance waiting duration when the second robot is used as the avoidance robot.
As an embodiment, the first total duration may be calculated by using the following formula:
Figure BDA0001782403130000161
wherein T represents a first total time length, m represents the total number of segments of a first interference road section for avoiding the robot by the first robot, and TiRepresenting avoidance or the like corresponding to the ith section in the first interference section in which the first robot is the avoidance robotThe length of the waiting time is long,
Figure BDA0001782403130000171
representing a first desired transit time.
Second embodiment
Referring to fig. 5, fig. 5 is a functional module schematic diagram of a robot avoidance pre-judging device 300 according to a preferred embodiment of the present invention. The apparatus is applied to the server 100 in fig. 1. The robot avoidance prediction device 300 may include: the prediction module 301, the calculation module 302, the determination module 303, the anticipation module 304 and the acquisition module 305.
A predicting module 301, configured to predict at least one set of interference section combinations where a first remaining path of the first robot and a second remaining path of the second robot have interference, where the interference section combinations include a first interference section belonging to the first remaining path and a second interference section belonging to the second remaining path.
A calculating module 302, configured to calculate a first priority factor corresponding to the first robot according to a first ideal route time of the first robot and a first predicted route time, where the first ideal route time is a time length for the first robot to pass through the first remaining path at an average speed; the first predicted route time is a sum of the first ideal route time and a waiting time of each of the first interference sections.
The calculating module 302 is further configured to calculate a first priority factor corresponding to the second robot according to a second ideal route time of the second robot and a second predicted route time, where the second ideal route time is a time length for the second robot to pass through the second remaining path at an average speed; the second predicted route time is a sum of the second ideal route time and a waiting time of each of the second interference sections.
The determining module 303 is configured to determine a first priority of the first robot on the first interference section and a second priority of the second robot on the second interference section according to the first priority factor of the first robot and the first priority factor of the second robot, respectively.
A pre-judging module 304, configured to pre-judge, by using the first priority and the second priority, an avoidance robot corresponding to the interference road section combination from the first robot and the second robot, so as to avoid in time when the avoidance robot reaches the interference road section combination.
An obtaining module 305, configured to obtain a path intersection corresponding to the interference section combination, a first raster path point listed in a first position of the first interference section in the operation direction of the first robot, and a second raster path point listed in a first position of the second interference section in the operation direction of the second robot.
The calculating module 302 is further configured to calculate an avoidance waiting duration and an avoidance point corresponding to the interference road section combination of the avoidance robot according to the path intersection, the first raster path point, and the second raster path point, so that the avoidance robot moves to the avoidance point when reaching the interference road section combination and suspends the avoidance waiting duration for avoidance.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
In summary, the robot avoidance pre-judging method and apparatus provided by the present invention are applied to a server, where the server is in communication connection with a first robot and a second robot respectively, and the robot avoidance pre-judging method includes: predicting at least one set of interference section combinations where a first remaining path of the first robot and a second remaining path of the second robot have interference; calculating a first priority factor corresponding to the first robot according to the first ideal passing time and the first predicted passing time of the first robot; calculating a first priority factor corresponding to the second robot according to a second ideal passing time and a second predicted passing time of the second robot; determining a first priority corresponding to the first robot on the first interference section and a second priority corresponding to the second robot on the second interference section according to the first priority of the first robot and the first priority of the second robot respectively; and pre-judging the avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority so as to facilitate timely avoidance when the avoidance robot reaches the interference road section combination. And determining an avoidance scheme in advance so as to avoid in time when the avoidance robot reaches the interference road section combination and avoid mutual blocking.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (4)

1. A robot avoidance pre-judging method is applied to a server, wherein the server is respectively in communication connection with a first robot and a second robot, and the robot avoidance pre-judging method is characterized by comprising the following steps:
predicting at least one set of interference section combinations where a first remaining path of the first robot and a second remaining path of the second robot have interference, wherein the interference section combinations comprise a first interference section belonging to the first remaining path and a second interference section belonging to the second remaining path;
calculating a first priority factor corresponding to the first robot according to a first ideal passing time and a first predicted passing time of the first robot, wherein the first ideal passing time is a time length for the first robot to pass through the first remaining path at an average speed; the first predicted route time is the sum of the first ideal route time and the waiting time of each first interference section;
calculating a first priority factor corresponding to the second robot according to a second ideal route time of the second robot and a second predicted route time, wherein the second ideal route time is a time length for the second robot to pass through the second surplus route at an average speed; the second predicted route time is the sum of the second ideal route time and the waiting time of each second interference section;
acquiring path intersection points corresponding to the interference section combination, a first raster path point listed at a first position of the first interference section in the running direction of the first robot, and a second raster path point listed at a first position of the second interference section in the running direction of the second robot;
calculating a corresponding intersection angle according to the first raster path point and the second raster path point;
calculating an initial avoidance distance according to the intersection angle;
calculating a first physical distance between the first raster path point and the path intersection point;
when the first physical distance is larger than the initial avoidance distance, taking the first physical distance as a first final avoidance distance; when the first physical distance is smaller than or equal to the initial avoidance distance, taking the initial avoidance distance as a first final avoidance distance; taking the ratio of the first physical distance to the first final avoidance distance as a second priority factor of the first robot on the first interference road section;
calculating a second physical distance between the second raster path point and the path intersection point;
when the second physical distance is larger than the initial avoidance distance, taking the second physical distance as a second final avoidance distance; when the second physical distance is smaller than or equal to the initial avoidance distance, taking the initial avoidance distance as a second final avoidance distance; taking the ratio of the second physical distance to the second final avoidance distance as a second priority factor of the second robot on the second interference road section;
calculating a first priority corresponding to the first robot on the first interference section according to the first priority factor and a second priority factor of the first robot;
calculating a second priority corresponding to the second robot on the second interference road section according to the first priority factor and the second priority factor of the second robot;
pre-judging an avoidance robot corresponding to the interference road section combination from the first robot and the second robot by using the first priority and the second priority so as to avoid in time when the avoidance robot reaches the interference road section combination;
acquiring a physical distance between an avoidance raster path point corresponding to the avoidance robot and the position of the path intersection point, and calculating a first avoidance duration of the avoidance robot according to the physical distance and the average speed; when the first robot is the avoidance robot, the avoidance raster path point is the first raster path point, and when the second robot is the avoidance robot, the avoidance raster path point is the second raster path point;
acquiring a final avoidance distance of the avoidance robot, and calculating a second avoidance duration of the avoidance robot according to the final avoidance distance and the average speed; when the first robot is the avoidance robot, the final avoidance distance is the first final avoidance distance, and when the second robot is the avoidance robot, the final avoidance distance is the second final avoidance distance;
taking the sum of the first avoidance duration and the second avoidance duration as an avoidance waiting duration of the avoidance robot;
and determining an avoidance point according to the avoidance raster path point and the final avoidance distance, so that the avoidance robot moves to the avoidance point when reaching the interference road section combination and suspends the avoidance waiting time for avoidance.
2. The robot avoidance anticipation method of claim 1, further comprising:
respectively calculating a first total time length of the first robot passing through the first surplus path and a second total time length of the second robot passing through the second surplus path according to the avoidance robot and the avoidance waiting time length corresponding to each interference section combination; the first total duration is the sum of the first ideal passing time and the avoidance waiting duration corresponding to the first robot serving as the avoidance robot; and the second total duration is the sum of the second ideal passing time and the corresponding avoidance waiting duration when the second robot is used as the avoidance robot.
3. The robot avoidance prediction method according to claim 1, wherein the step of predicting at least one set of interference section combinations where the first remaining path of the first robot interferes with the second remaining path of the second robot includes:
according to a preset safety distance and a preset multiple of the robot, dividing the first surplus path into a plurality of first road sections and dividing the second surplus path into a plurality of second road sections respectively;
sequencing the first sections according to the sequence of the predicted arrival of the first robot;
sequencing the second path according to the sequence of the expected arrival of the second robot;
sequentially comparing each section of the first road section with the corresponding second road section with the same serial number until the first road section and the second road section with the same serial number do not exist so as to obtain a comparison result;
when the comparison result between the first road section and the second road section with the same corresponding serial number meets a preset requirement, taking the first road section as a first interference road section corresponding to the interference road section combination; and taking the second road section as a second interference road section corresponding to the interference road section combination.
4. The utility model provides a robot dodges and judges device in advance, is applied to the server, the server respectively with first robot, second robot communication connection, its characterized in that, the robot dodges and judges the device in advance and includes:
the prediction module is used for predicting at least one group of interference section combinations with interference between a first residual path of the first robot and a second residual path of the second robot, wherein the interference section combinations comprise a first interference section belonging to the first residual path and a second interference section belonging to the second residual path;
the calculation module is used for calculating a first priority factor corresponding to the first robot according to a first ideal passing time and a first predicted passing time of the first robot, wherein the first ideal passing time is the time length of the first robot passing through the first remaining path according to the average speed; the first predicted route time is the sum of the first ideal route time and the waiting time of each first interference section;
the calculation module is further configured to calculate a first priority factor corresponding to the second robot according to a second ideal route time of the second robot and a second predicted route time, where the second ideal route time is a time length for the second robot to pass through the second remaining path at an average speed; the second predicted route time is the sum of the second ideal route time and the waiting time of each second interference section;
the acquisition module is used for acquiring path intersections corresponding to the interference section combination, a first raster path point listed in a first position of the first interference section in the running direction of the first robot, and a second raster path point listed in a first position of the second interference section in the running direction of the second robot;
a determining module, configured to calculate a corresponding intersection angle according to the first raster path point and the second raster path point;
the determining module is further used for calculating an initial avoidance distance according to the intersection angle;
the determination module is further configured to calculate a first physical distance between the first raster path point and the path intersection point;
the determining module is further configured to take the first physical distance as a first final avoidance distance when the first physical distance is greater than the initial avoidance distance; when the first physical distance is smaller than or equal to the initial avoidance distance, taking the initial avoidance distance as a first final avoidance distance; taking the ratio of the first physical distance to the first final avoidance distance as a second priority factor of the first robot on the first interference road section;
the determination module is further to calculate a second physical distance between the second raster path point and the path intersection point;
the determining module is further configured to take the second physical distance as a second final avoidance distance when the second physical distance is greater than the initial avoidance distance; when the second physical distance is smaller than or equal to the initial avoidance distance, taking the initial avoidance distance as a second final avoidance distance; taking the ratio of the second physical distance to the second final avoidance distance as a second priority factor of the second robot on the second interference road section;
the determining module is further used for calculating a first priority corresponding to the first robot on the first interference section according to the first priority factor and the second priority factor of the first robot;
the determining module is further configured to calculate a second priority corresponding to the second robot on the second interference road section according to the first priority factor and the second priority factor of the second robot;
the pre-judging module is used for pre-judging an avoidance robot corresponding to the interference road section combination from the first robot and the second robot by utilizing the first priority and the second priority so as to avoid in time when the avoidance robot reaches the interference road section combination;
the calculation module is further configured to obtain a physical distance between an avoidance grid path point corresponding to the avoidance robot and a position of the path intersection, and calculate a first avoidance duration of the avoidance robot according to the physical distance and the average speed; when the first robot is the avoidance robot, the avoidance raster path point is the first raster path point, and when the second robot is the avoidance robot, the avoidance raster path point is the second raster path point;
the calculation module is further used for acquiring a final avoidance distance of the avoidance robot and calculating a second avoidance duration of the avoidance robot according to the final avoidance distance and the average speed; when the first robot is the avoidance robot, the final avoidance distance is the first final avoidance distance, and when the second robot is the avoidance robot, the final avoidance distance is the second final avoidance distance;
the calculation module is further configured to use the sum of the first avoidance duration and the second avoidance duration as an avoidance waiting duration of the avoidance robot;
the calculation module is further used for determining an avoidance point according to the avoidance raster path point and the final avoidance distance, so that the avoidance robot moves to the avoidance point when reaching the interference road section combination and suspends the avoidance waiting time for avoidance.
CN201810998485.6A 2018-08-29 2018-08-29 Robot avoidance pre-judging method and device Active CN109048910B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810998485.6A CN109048910B (en) 2018-08-29 2018-08-29 Robot avoidance pre-judging method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810998485.6A CN109048910B (en) 2018-08-29 2018-08-29 Robot avoidance pre-judging method and device

Publications (2)

Publication Number Publication Date
CN109048910A CN109048910A (en) 2018-12-21
CN109048910B true CN109048910B (en) 2020-08-14

Family

ID=64757931

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810998485.6A Active CN109048910B (en) 2018-08-29 2018-08-29 Robot avoidance pre-judging method and device

Country Status (1)

Country Link
CN (1) CN109048910B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110182527B (en) * 2019-04-11 2021-03-23 上海快仓智能科技有限公司 Warehouse-in and warehouse-out control method and conveying system for shelf array

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2388926A (en) * 2001-02-19 2003-11-26 Honda Motor Co Ltd Setting method and setting apparatus for operation path for articulated robot
CN107168337A (en) * 2017-07-04 2017-09-15 武汉视览科技有限公司 A kind of mobile robot path planning and dispatching method of view-based access control model identification
CN107225570A (en) * 2017-04-20 2017-10-03 深圳前海勇艺达机器人有限公司 The barrier-avoiding method and device of intelligent robot

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2388926A (en) * 2001-02-19 2003-11-26 Honda Motor Co Ltd Setting method and setting apparatus for operation path for articulated robot
CN107225570A (en) * 2017-04-20 2017-10-03 深圳前海勇艺达机器人有限公司 The barrier-avoiding method and device of intelligent robot
CN107168337A (en) * 2017-07-04 2017-09-15 武汉视览科技有限公司 A kind of mobile robot path planning and dispatching method of view-based access control model identification

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
多机器人停驻任务相关方法的研究与实现;黎陟;《中国硕士学位论文全文数据库 信息科技辑》;20071215(第06期);第60-64页 *
群机器人狭窄通道相遇问题的解决方法;董百超等;《科学技术与工程》;20170731;第17卷(第19期);第7-33页 *
董百超等.群机器人狭窄通道相遇问题的解决方法.《科学技术与工程》.2017,第17卷(第19期), *

Also Published As

Publication number Publication date
CN109048910A (en) 2018-12-21

Similar Documents

Publication Publication Date Title
CN110955242B (en) Robot navigation method, system, robot and storage medium
Jin et al. A group-based traffic signal control with adaptive learning ability
CN101943916B (en) Kalman filter prediction-based robot obstacle avoidance method
JP2018534205A (en) Method for controlling vehicle motion and vehicle control system
Shang et al. Deep reinforcement learning with reference system to handle constraints for energy-efficient train control
CN109540136A (en) A kind of more unmanned boat collaboration paths planning methods
CN113682318B (en) Vehicle running control method and device
CN111638717A (en) Design method of distributed autonomous robot traffic coordination mechanism
CN111308996A (en) Training device and cooperative operation control method thereof
CN109991963A (en) Speed planning method and terminal device
Cai et al. Prediction-based path planning for safe and efficient human–robot collaboration in construction via deep reinforcement learning
CN112415997B (en) Path planning method and system for multi-robot cooperation
CN109048909A (en) Minor matters formula path dispatching method, device, background server and the first robot
CN109164807B (en) Robot path interference prejudging method and device
CN109048910B (en) Robot avoidance pre-judging method and device
Shi et al. Task allocation and path planning of many robots with motion uncertainty in a warehouse environment
Chen et al. Autonomous port management based AGV path planning and optimization via an ensemble reinforcement learning framework
CN113375686A (en) Path planning method and device and intelligent conveying system
CN114740849B (en) Mobile robot autonomous navigation method and device based on pedestrian walking decision rule
CN111427368A (en) Improved multi-target collision-prevention driving method for unmanned intelligent vehicle
Zhu et al. A decentralized multi-criteria optimization algorithm for multi-unmanned ground vehicles (mugvs) navigation at signal-free intersection
Kalweit et al. Q-learning with long-term action-space shaping to model complex behavior for autonomous lane changes
US20220300002A1 (en) Methods and systems for path planning in a known environment
KR20230024392A (en) Driving decision making method and device and chip
Neuman et al. Anytime policy planning in large dynamic environments with interactive uncertainty

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230919

Address after: Room B1005, No. 228, Qiaotou Street, Beishan Village, Xinjiao South Road, Haizhu District, Guangzhou, Guangdong 510000

Patentee after: Liu Yajun

Address before: 510000 Guangzhou high tech Industrial Development Zone, Guangdong Province, 31 Kefeng Road, No. a220, building G1, Zhongchuang space, South China new materials innovation park, 49

Patentee before: GUANGZHOU DREAMONE ROBOT AUTOMATION Co.,Ltd.