WO2018188200A1 - 机器人的路径规划系统、方法、机器人及存储介质 - Google Patents

机器人的路径规划系统、方法、机器人及存储介质 Download PDF

Info

Publication number
WO2018188200A1
WO2018188200A1 PCT/CN2017/091370 CN2017091370W WO2018188200A1 WO 2018188200 A1 WO2018188200 A1 WO 2018188200A1 CN 2017091370 W CN2017091370 W CN 2017091370W WO 2018188200 A1 WO2018188200 A1 WO 2018188200A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
point
robot
planning
reference positioning
Prior art date
Application number
PCT/CN2017/091370
Other languages
English (en)
French (fr)
Inventor
周宸
周宝
肖京
Original Assignee
平安科技(深圳)有限公司
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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Priority to US16/084,245 priority Critical patent/US11035684B2/en
Priority to EP17899233.5A priority patent/EP3438611B1/en
Priority to JP2018541387A priority patent/JP6800989B2/ja
Priority to KR1020187023692A priority patent/KR102152192B1/ko
Priority to AU2017409109A priority patent/AU2017409109B9/en
Priority to SG11201900262RA priority patent/SG11201900262RA/en
Publication of WO2018188200A1 publication Critical patent/WO2018188200A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3407Route searching; Route guidance specially adapted for specific applications
    • G01C21/343Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3446Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2530/00Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
    • B60W2530/18Distance travelled

Definitions

  • the present invention relates to the field of computer technologies, and in particular, to a path planning system, method, robot, and computer readable storage medium for a robot.
  • autonomous mobile robots can be widely used in many scenes, such as guiding the exhibition hall, leading visitors from one exhibition area to another; the service of the restaurant, actively welcome guests, and lead guests to vacant meals. ; guidance and patrol work in public places, moving along the route set by the program, someone needs help to stop answering questions and so on.
  • the autonomous mobile robot is required to move to one or more designated locations to achieve certain specific functions.
  • the path planning problem of the autonomous mobile robot is involved.
  • the autonomous mobile robot In the prior art, in the path calculation problem, the autonomous mobile robot generally starts to calculate the path of how to move to the target point in real time when receiving the movement instruction. This real-time calculation process needs to consider many factors and is time consuming.
  • the main object of the present invention is to provide a path planning system, method, robot and storage medium for a robot, which aims to improve the efficiency of autonomous mobile robot path planning.
  • a first aspect of the present application provides a path planning system for a robot, where the path planning system includes:
  • a selection module configured to pre-select one or more position points on the path for the robot to move in the predetermined area map as the reference positioning point;
  • a path planning module configured to: if receiving an instruction to move the robot from the first location point to the second location point, analyze the first from the first according to the set reference positioning point and according to a predetermined path analysis rule Positioning a path to the second location point and controlling movement of the robot to the second location point based on the analyzed path.
  • a second aspect of the present application provides a path planning method for a robot, the method comprising the following steps:
  • the path planning system of the robot pre-selects one or more position points on the path for the robot to move in the predetermined area map as the reference positioning point;
  • a third aspect of the present application provides a robot, including a processing device, a storage device, in which a path planning system for a robot is stored, the path planning system of the robot includes at least one computer readable instruction, the at least one computer readable instruction Can be executed by the processing device to:
  • a fourth aspect of the present application provides a computer readable storage medium having stored thereon at least one executable device Computer-readable instructions to implement the following operations:
  • the path planning system, method, robot and storage medium of the robot proposed by the present invention preselect one or more position points as reference positioning points on a path for the robot to move in a predetermined area map; After the robot moves from the first position point to the second position point, the path from the first position point to the second position point is analyzed according to the set reference positioning point and according to a predetermined path analysis rule. And controlling the movement of the robot to the second position point based on the analyzed path. It is not necessary for the robot to calculate the moving path in real time during path planning, but to make corresponding selection from the previously planned path, that is, the path planning process is changed from “calculation” to “selection”, which effectively reduces the real-time calculation amount and improves the path planning. s efficiency.
  • FIG. 1 is a schematic diagram of an operating environment of a preferred embodiment of a path planning system for a robot of the present invention
  • FIG. 2 is a schematic flow chart of an embodiment of a path planning method for a robot according to the present invention
  • FIG. 3 is a schematic diagram of each reference positioning point selected in a public library area map in an embodiment of a path planning method for a robot according to the present invention
  • FIG. 4 is a schematic diagram of a path planning of a point P to a point in a public library area map in an embodiment of a path planning method for a robot according to the present invention
  • FIG. 5 is a schematic diagram of path planning from point A to point B in an embodiment of a path planning method for a robot according to the present invention
  • FIG. 6 is a schematic diagram of quantitative calculation of an obstacle influencing factor in an actual index in an embodiment of a path planning method for a robot according to the present invention
  • FIG. 7 is a schematic diagram of obstacle avoidance of a robot in an embodiment of a path planning method for a robot according to the present invention.
  • FIG. 8 is a schematic diagram showing a division and trigger radius of a reference positioning point in an embodiment of a path planning method for a robot according to the present invention.
  • FIG. 9 is a schematic diagram of functional modules of an embodiment of a path planning system for a robot according to the present invention.
  • FIG. 1 it is a schematic diagram of an operating environment of a preferred embodiment of a road strength planning system for a robot of the present invention.
  • the path planning system 10 of the robot is installed and operated in the robot 1.
  • the robot 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13 that are communicatively coupled to each other through a system bus.
  • Figure 1 shows only the robot 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 includes a memory and at least one type of readable storage medium.
  • the memory provides a cache for the operation of the robot 1;
  • the readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like.
  • the readable storage medium may be an internal storage unit of the robot 1, such as the hard disk of the robot 1; in other embodiments, the non-volatile storage medium may also be an external storage device of the robot 1, For example, a plug-in hard disk equipped with the robot 1, a smart memory card (SMC), a Secure Digital (SD) card, a flash card, and the like.
  • the readable storage medium of the memory 11 is generally used for storage.
  • the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • Processor 12 may, in some embodiments, include one or more microprocessors, microcontrollers, digital processors, and the like. This processor 12 is typically used to control the operation of the robot 1. In the present embodiment, the processor 12 is configured to run program code or process data stored in the memory 11, such as a path planning system 10 that runs a robot, and the like.
  • the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like in some embodiments.
  • the display 13 is used to display information processed in the robot 1 and a user interface for displaying visualizations, such as an application menu interface, an application icon interface, and the like.
  • the components 11-13 of the robot 1 communicate with each other through a system bus.
  • the path planning system 10 of the robot includes at least one computer readable instructions stored in the memory 11, the at least one computer readable instructions being executable by the processor 12 to implement the path planning method of the robot of the various embodiments of the present application.
  • the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.
  • the path planning system 10 of the robot when executed by the processor 12, the following operations are performed: first, one or more position points are preselected as a reference position on a path for the robot 1 to move in a predetermined area map. Point; then, if an instruction to move the robot 1 from the first position point to the second position point is received, analyzing from the first position point to the second position according to the set reference positioning point and according to a predetermined path analysis rule The path of the point, and based on the analyzed path, controls the movement of the robot 1 to the second position point.
  • the path planning system 10 of the robot is stored in the memory 11 and includes at least one computer readable instruction stored in the storage device 11, the at least one computer readable instruction being executable by the processor 12 to implement the present The path planning method of the robot of each embodiment is applied.
  • the invention provides a path planning method for a robot.
  • FIG. 2 is a schematic flowchart diagram of an embodiment of a path planning method for a robot according to the present invention.
  • the path planning method of the robot includes:
  • step S10 the path planning system of the robot preselects one or more position points as reference positioning points on the path for the robot to move in the predetermined area map.
  • one or more position points are preselected on the predetermined area map as the reference positioning points.
  • one or more position points may be selected as reference positioning points on each path that is connected to each other and movable by the robot, as shown in FIG. 3, some small blacks in FIG. Dots are the various datum points selected in the public library area map. Each datum point is located on the path of the public library area map for the robot to move. The larger black dot in Figure 3 is a public book. Obstacle in the museum area map that the robot cannot pass.
  • Step S20 if an instruction to move the robot from the first position point to the second position point is received, analyzing the point from the first position point according to the set reference positioning point and according to a predetermined path analysis rule a path of the second location point and controlling movement of the robot to the second location point based on the analyzed path.
  • the robot needs to move from the first position point (for example, the P point shown in FIGS. 3 and 4) to the second position point.
  • the path planning system of the robot analyzes the path from the first position point to the second position according to the set reference positioning point and according to the predetermined path analysis rule. And controlling the movement of the robot to the second position point based on the analyzed path. For example, for each of the selected reference positioning points in the area map, a plurality of movable paths y1, y2, and y3 between different reference positioning points may be determined in advance, as shown in FIG. 4, the reference positioning point A and the reference positioning point.
  • a plurality of movable paths can be predetermined between B, and a plurality of determined movable paths can bypass a large black dot, that is, an obstacle that cannot be passed by the robot, so that the robot can move normally.
  • the path planning system of the robot can select one of a plurality of predetermined movable paths between the reference positioning point A and the reference positioning point B as needed, and can be used as the moving path of the analyzed robot to complete the robot from The movement of the first position point to the second position point. For example, if the path required for the robot to move is the shortest, a predetermined movable path y1 or y3 between the reference positioning point A and the reference positioning point B may be selected, and the like.
  • one or more position points are preselected as a reference positioning point on a path that can be moved by the robot in a predetermined area map; upon receiving the movement of the robot from the first position point to the second position point After the command, according to the set reference positioning point and according to the predetermined path analysis rule, the path from the first position point to the second position point is analyzed, and the robot movement is controlled based on the analyzed path. Said second location point. It is not necessary for the robot to calculate the moving path in real time during path planning, but to make corresponding selection from the previously planned path, that is, the path planning process is changed from “calculation” to “selection”, which effectively reduces the real-time calculation amount and improves the path planning. s efficiency.
  • the predetermined path analysis rule includes:
  • a first reference positioning point eg, point A shown in FIG. 4
  • a second reference positioning point closest to the second position point eg, point B shown in FIG. 4
  • the path from the first location point to the first reference location point, and the second location point to the second reference location point is planned according to a preset first planning manner
  • the path from the first reference positioning point to the second reference positioning point is planned according to a preset second planning manner to obtain a second planning path.
  • the first planning mode is:
  • the second planning manner includes the following steps:
  • H1 determining an optional planning path corresponding to the first reference positioning point and the second reference positioning point according to a mapping relationship between the first reference positioning point, the second reference positioning point, and the optional planning path;
  • the optional planning path is used as the second planning path of the first reference positioning point to the second reference positioning point;
  • the method further includes the following steps:
  • the optional planning path is filtered by a predetermined filtering method to filter out the optional planning path to be scored.
  • the predetermined screening method includes the following steps:
  • An optional planning path including a predetermined specific reference point is selected from each of the optional planning paths, and the selected optional planning path is used as an optional planning path to be scored. For example, if the robot needs to play an advertisement in the process of moving from point A to point B, the advertisement needs to be played on the path M-N with more crowds. Then the robot must pass through the specific reference positioning points M and N in the path planning process, and the path selectable from A to B must contain the specific reference positioning points M and N, and only the specific reference positioning points M and N can be included.
  • the planning path is selected for score calculation to simplify the path selection process.
  • the total length corresponding to each optional planning path may be separately calculated according to a predetermined calculation formula, and the total length of each optional planning path and the first reference positioning point to the second are respectively calculated.
  • the difference between the total length of the shortest path of the reference positioning point, and the shortest path of the first reference positioning point to the second reference positioning point may be a linear distance between the first reference positioning point and the second reference positioning point, or may be The shortest path among the various optional planning paths from a reference positioning point to a second reference positioning point.
  • the optional planning path whose corresponding difference is less than the preset threshold is filtered out as an optional planning path to be scored. That is, an optional planning path with a short path length is selected to select to improve the efficiency of selecting the optimal planning path.
  • the predetermined calculation formula is:
  • d(path) represents the total length of the path and also includes:
  • the predetermined scoring rule is:
  • the score corresponding to each optional planning path is two out of the optional planning paths.
  • the path between adjacent nodes is the score under the influence of walking distance, the influence factor of walking time or the influencing factors of obstacles.
  • the last selected path can be defined as:
  • Score(path i ) refers to the comprehensive score of the path numbered i, and the comprehensive scoring formula of the path is as follows:
  • Score(path) g[o(1),o(2),...,o(i),...,o(n)]
  • o(i) represents the influencing factors, including the influencing factors of walking distance, the influencing factors of walking time, and the influencing factors of obstacles (for example, difficulty in avoiding obstacles).
  • the whole path The rating value of the influencing factors is the sum of the scores for each segment, ie:
  • L k,k+1 represents the score of the influencing factor of the path between every two adjacent nodes in the path from A to B.
  • path 1 A-L1-L2-L3-B
  • path 2 A-M1-M2-M3-B
  • path 3 A -N1-N2-N3-B
  • the length of the path 1 path is d (path 1 )
  • the length of the path 2 path is d ( Path 2 )
  • the length of the path 3 path is d(path 3 ).
  • the score corresponding to each optional planning path is the score of the path between each two adjacent nodes in the optional planning path, such as the walking distance influencing factor, the walking time influencing factor or the obstacle influencing factor, such as path 1
  • the score corresponding to the path is the path A-L1, L1-L2, L2-L3, and L3-B between each two adjacent nodes in the optional planning path.
  • scoring formula of the optional planning path is as follows:
  • o(t) is the time score of the optional planning path
  • o(d) is the distance score of the optional planning path
  • a and b are predetermined weights
  • the time score of the i-th optional planning path is defined o i (t) is:
  • T(path 1 ), T(path 2 )...T(path n ) are the time used by the robot to move to the target point in different alternative planning paths
  • T(path i ) is the ith optional planning path.
  • the time taken by the lower robot to move to the target point k ti represents the time penalty factor of the i-th optional planning path, which is the time it takes for the robot to bypass the obstacle in the ith optional planning path.
  • d i represents the path length of the i-th optional planning path
  • v i represents the robot speed in the i-th optional planning path
  • P i represents the probability of occurrence of an obstacle in the i-th optional planning path.
  • the distance score o i (d) defining the i-th optional planning path is:
  • d(path 1 ), d(path 2 )...d(path n ) are the distances that the robot travels to the target point in different alternative planning paths
  • k di represents the distance penalty of the i-th alternative planning path.
  • the distance penalty factor is the distance that the robot needs to move more than the obstacle in the ith optional planning path.
  • the obstacle influencing factors include an obstacle avoidance difficulty coefficient and a probability of occurrence of an obstacle.
  • the robot can access the Internet of Things system, and more useful information can be obtained through the system. For example: (1) The robot can get information about the indoor camera of the IoT system server. Because the surveillance camera generally corresponds to a fixed scene. The image processing method is used to process the data of the camera to obtain the number and approximate distribution of dynamic obstacles in a certain area. (2) The Internet of Things system server can statistically organize the data of personnel flow. Through statistical data, it is possible to predict the probability of which people are concentrated in which time periods and in which areas. (3) Further, the robot system can obtain the distribution of indoor dynamic obstacles (such as personnel distribution) through the indoor camera, and refresh the obstacle probability of the path of each section in real time. Therefore, the robot can dynamically select the optimal path according to the existing situation.
  • indoor dynamic obstacles such as personnel distribution
  • FIG. 6 is a schematic diagram of quantitative calculation of an obstacle influencing factor in an actual index, and the walking path of the robot is divided into several regions. Assume that it is known:
  • the corresponding distance penalty coefficient is kd and the time penalty coefficient is kt
  • the time scoring formula and distance scoring formula the time and distance scores of each path after the obstacle factor correction can be calculated.
  • the comprehensive score of each path can be calculated, as shown in the following table. Second:
  • the path with the lowest score is selected, that is, the third path is used as the optimal moving planning path of the robot.
  • the step of controlling the movement of the robot to the second position based on the analyzed path includes:
  • the path planning system of the robot analyzes whether there is an obstacle in the path to be moved in real time or timing, and needs to perform mobile avoidance.
  • the path planning system of the robot acquires obstacle information in the current path to be moved from a predetermined area monitoring server (for example, an Internet of Things system server) in real time or at a time, and analyzes the acquired obstacle information according to the obtained obstacle information. Whether there are obstacles or not needs to be moved to avoid.
  • a predetermined area monitoring server for example, an Internet of Things system server
  • the path planning system of the robot detects the obstacle information in the current path to be moved by the obstacle detecting unit (for example, the radar unit) configured by the robot in real time or timing, and analyzes whether there is an obstacle to be performed. Mobile evasion.
  • the obstacle detecting unit for example, the radar unit
  • the path planning system of the robot takes the current position as the new first position point, and analyzes the new first position point according to the set reference positioning point and according to the predetermined path analysis rule. a path to the second location point and controlling movement of the robot to the second location point based on the analyzed path. (For example, the planned path from point P to point Q shown in Figure 4).
  • FIG. 7 is a schematic diagram of the obstacle avoidance of the robot. It is assumed that the robot is to move from point A to point B, and a dynamic obstacle suddenly appears near the point C during the movement. In the prior art, the robot dynamically bypasses the obstacle according to an algorithm and recalculates the new planned path y4 according to the current position. There are some disadvantages to this approach, such as:
  • the robot In the process of bypassing the obstacle, the robot needs to constantly calculate the avoidance path and continuously calculate the path from the current position to the target point. This process will consume a lot of computing resources and time.
  • the robot cannot know the size of the obstacle in front of the eye, the time it takes to bypass it, and whether there are other obstacles after the bypass. For example, what appears in front of the robot is a long wall of people, using conventional methods. It will take a lot of time to get around this wall.
  • the robot reselects another path by directly selecting other reference positioning points.
  • L1 and L2 are reference positioning points.
  • the robot can re-select another route C-L1-L2-B to reach point B, that is, the robot can choose not to bypass the obstacle, but choose another route, and select the route. It is more efficient to calculate the route in real time, does not take up a lot of computing resources of the robot, and the response is more timely.
  • the path planning system of the robot pre-selects one or more position points as the reference positioning points on the predetermined area map, and also sets the corresponding position at the position corresponding to each of the reference positioning points in the predetermined area map.
  • the location point identifier may be a manual location roadmap, eg, for example, the artificial landmark at the location corresponding to the second reference location of the second layer A3 region may be “L1A3P2”, or “L1A32”;
  • the position road sign eg, for example, the natural road sign at the position corresponding to the second reference point of the second layer A3 area may be " ⁇ A3".
  • the step of controlling the movement of the robot to the second position based on the analyzed path further includes:
  • the path planning system of the robot performs position location in real time or at regular intervals
  • the triggering coordinate area may be a center of the reference positioning point and a preset length of the radius A circular area or a square area, and so on.
  • the open location point identification device (such as a camera) starts detecting the location point identifier
  • the distance and direction of the robot and the detected position point identification are calculated by the sensor of the robot to obtain the current position and posture of the robot, and the forward direction is calibrated according to the current position and posture of the robot.
  • the step of analyzing whether the current position is in the trigger coordinate area of a reference positioning point includes:
  • the current position is in the trigger coordinate area of a target reference positioning point, it is determined that the current position is in the trigger coordinate area of a reference positioning point, or if the current position is not in the trigger coordinate area of a target reference positioning point, then determining The current position is not in the trigger coordinate area of a datum point.
  • the robot During the movement of the robot according to the planned path, the robot needs to determine the position of the current position and the target point by positioning, and also needs to confirm its position during the movement.
  • the combination of relative positioning and absolute positioning is now widely used. Because of the inevitable error accumulation problem of relative positioning, it is necessary to use absolute positioning method for calibration.
  • the robot calculates the relative positioning of the sensor based on the previous positioning result and the relative displacement measured by the inertia sensor. Since there will be some error in each positioning, the error will continue to accumulate and become larger and larger, which will eventually lead to unacceptable positioning errors after a period of time. Therefore, the robot needs to calibrate the positioning information in some way at an appropriate time.
  • the position point identification is used to calibrate in the reference positioning point mode, and the robot can roughly determine the position of the road sign according to its position.
  • the robot recognizes the position point identification, the distance and direction of the robot and the road sign are calculated by the sensor. , get the current position and posture of the robot.
  • the robot needs to open the detecting device at all times to search for a location point identifier nearby and perform calibration. Therefore, it is necessary to arrange a large number of location point identifiers in a wide range, and also waste a large amount of computing resources of the robot.
  • the arrangement range of the position point identification is reduced to the reference setting. Near the site, there is no need to arrange a large number of road signs globally, and it is only necessary to arrange road signs near the reference positioning points, thereby effectively reducing the number of road sign arrangements and preventing confusion of other types of signs caused by the layout of a large number of road signs.
  • the position point of each reference anchor point is identified as a picture corresponding to the unique coordinates (a, b) in the map.
  • a camera is mounted on the top of the robot to identify the location point identification picture.
  • the robot captures the position point identification picture, the relative coordinates (m, n) of the robot relative to the target picture can be obtained, and the robot can obtain its current coordinate (a+m, b+n) and use the coordinate as Current accurate coordinates for coordinate calibration.
  • the robot in order to not miss the location point identification during the movement, the robot will open the top camera in real time and continuously process the video.
  • the camera opens the capturing position point identification for calibration if and only if the robot enters the triggering coordinate area of the reference positioning point, that is, the triggering radius. Therefore, the present embodiment gives the timing of the robot calibration by setting the trigger coordinate area of the reference positioning point, and facilitates the control of the robot, thereby reducing the calculation amount and resource consumption.
  • an implementation manner is that the robot uses the current coordinates and the coordinates of each of the reference positioning points in the database to calculate, and determines the current coordinates and Whether the coordinates of a datum point are smaller than the trigger radius.
  • the map and the reference positioning point are divided and classified, and all the reference positioning points are not queried during the query, but only the area where the area is located is determined, and only the reference positioning points constituting the area are determined. Make queries, which greatly reduces the amount of calculation per query.
  • FIG. 8 is a schematic diagram of a reference positioning area division and a trigger radius.
  • the calibration scheme includes the following steps:
  • the map is segmented into a plurality of polygonal regions 1, 2, ... using a reference positioning point r, each of which has a trigger radius R of a corresponding radius.
  • the robot determines in which region the current coordinates are located. For example, the robot in Figure 8 is currently located in the area numbered 5.
  • the robot when the robot is in a certain polygon area, the robot will query at time interval t to confirm whether its current coordinates are in the trigger radius of the reference point of the corner point of the area.
  • the current coordinates of the robot are located in a square area numbered 5, and the robot will only query the area where the current coordinates are at the reference positioning points of the four corner points constituting the area (ie, numbered A, B, C, D is the area formed by the four reference positioning points).
  • the robot will open the position point identification device (such as the camera) to start detecting the position point identification.
  • the robot will calibrate the current coordinates by the calculated coordinate information.
  • the invention further provides a path planning system for a robot.
  • FIG. 9 is a functional block diagram of a preferred embodiment of the path planning system 10 of the robot of the present invention.
  • the path planning system 10 of the robot may be divided into one or more modules, the one or more modules being stored in the memory 11 and being processed by one or more processors (this embodiment) Executed for the processor 12) to complete the present invention.
  • the path planning system 10 of the robot may be divided into a selection module 01 and a path planning module 02.
  • the term "module" as used in the present invention refers to a series of computer program instruction segments capable of performing a specific function, which is more suitable than the program for describing the execution process of the path planning system 10 of the robot in the robot 1. The following description will specifically describe the functions of the selection module 01 and the path planning module 02.
  • the selection module 01 is configured to pre-select one or more position points on the path for the robot to move in the predetermined area map as the reference positioning point.
  • one or more position points are preselected on the predetermined area map as the reference positioning points.
  • one or more position points may be selected as reference positioning points on each path that is connected to each other and movable by the robot, as shown in FIG. 3, some small blacks in FIG. Dots are the various datum points selected in the public library area map. Each datum point is located on the path of the public library area map for the robot to move. The larger black dot in Figure 3 is a public book. Robots cannot pass through the museum area map Obstacle through.
  • the path planning module 02 is configured to: if receiving an instruction to move the robot from the first location point to the second location point, analyze the rule from the first according to the set reference positioning point and according to a predetermined path analysis rule A location points a path to the second location point and controls movement of the robot to the second location point based on the analyzed path.
  • the robot needs to move from the first position point (for example, the P point shown in FIGS. 3 and 4) to the second position point.
  • the path planning system of the robot analyzes the path from the first position point to the second position according to the set reference positioning point and according to the predetermined path analysis rule. And controlling the movement of the robot to the second position point based on the analyzed path. For example, for each of the selected reference positioning points in the area map, a plurality of movable paths y1, y2, and y3 between different reference positioning points may be determined in advance, as shown in FIG. 4, the reference positioning point A and the reference positioning point.
  • a plurality of movable paths can be predetermined between B, and a plurality of determined movable paths can bypass a large black dot, that is, an obstacle that cannot be passed by the robot, so that the robot can move normally.
  • the path planning system of the robot can select the reference positioning according to the need.
  • One of a plurality of predetermined movable paths between the point A and the reference positioning point B can be used as the moving path of the analyzed robot to complete the movement of the robot from the first position point to the second position point. mobile. For example, if the path required for the robot to move is the shortest, a predetermined movable path y1 or y3 between the reference positioning point A and the reference positioning point B may be selected, and the like.
  • one or more position points are preselected as a reference positioning point on a path that can be moved by the robot in a predetermined area map; upon receiving the movement of the robot from the first position point to the second position point After the command, according to the set reference positioning point and according to the predetermined path analysis rule, the path from the first position point to the second position point is analyzed, and the robot movement is controlled based on the analyzed path. Said second location point. It is not necessary for the robot to calculate the moving path in real time during path planning, but to make corresponding selection from the previously planned path, that is, the path planning process is changed from “calculation” to “selection”, which effectively reduces the real-time calculation amount and improves the path planning. s efficiency.
  • the predetermined path analysis rule includes:
  • a first reference positioning point eg, point A shown in FIG. 4
  • a second reference positioning point closest to the second position point eg, point B shown in FIG. 4
  • the path from the first location point to the first reference location point, and the second location point to the second reference location point is planned according to a preset first planning manner
  • the path from the first reference positioning point to the second reference positioning point is planned according to a preset second planning manner to obtain a second planning path.
  • the first planning mode is:
  • the second planning manner includes the following steps:
  • H1 determining an optional planning path corresponding to the first reference positioning point and the second reference positioning point according to a mapping relationship between the first reference positioning point, the second reference positioning point, and the optional planning path;
  • the optional planning path is used as the second planning path of the first reference positioning point to the second reference positioning point;
  • the method further includes the following steps:
  • the optional planning path is filtered by a predetermined filtering method to filter out the optional planning path to be scored.
  • the predetermined screening method includes the following steps:
  • An optional planning path including a predetermined specific reference point is selected from each of the optional planning paths, and the selected optional planning path is used as an optional planning path to be scored. For example, if the robot needs to play an advertisement in the process of moving from point A to point B, the advertisement needs to be played on the path M-N with more crowds. Then the robot must pass through the specific reference positioning points M and N in the path planning process, and the path selectable from A to B must contain the specific reference positioning points M and N, and only the specific reference positioning points M and N can be included.
  • the planning path is selected for score calculation to simplify the path selection process.
  • the total length corresponding to each optional planning path may be separately calculated according to a predetermined calculation formula, and the total length of each optional planning path and the first reference positioning point to the second are respectively calculated.
  • the difference between the total length of the shortest path of the reference positioning point, and the shortest path of the first reference positioning point to the second reference positioning point may be a linear distance between the first reference positioning point and the second reference positioning point, or may be The shortest path among the various optional planning paths from a reference positioning point to a second reference positioning point.
  • the optional planning path whose corresponding difference is less than the preset threshold is filtered out as an optional planning path to be scored. That is, an optional planning path with a short path length is selected to select to improve the efficiency of selecting the optimal planning path.
  • the predetermined calculation formula is:
  • d(path) represents the total length of the path and also includes:
  • the predetermined scoring rule is:
  • the score corresponding to each optional planning path is two out of the optional planning paths.
  • the path between adjacent nodes is the score under the influence of walking distance, the influence factor of walking time or the influencing factors of obstacles.
  • the last selected path can be defined as:
  • Score(path i ) refers to the comprehensive score of the path numbered i, and the comprehensive scoring formula of the path is as follows:
  • Score(path) g[o(1),o(2),...,o(i),...,o(n)]
  • o(i) represents the influencing factors, including the influencing factors of walking distance, the influencing factors of walking time, and the influencing factors of obstacles (for example, difficulty in avoiding obstacles).
  • the whole path The rating value of the influencing factors is the sum of the scores for each segment, ie:
  • L k,k+1 represents the score of the influencing factor of the path between every two adjacent nodes in the path from A to B.
  • path 1 A-L1-L2-L3-B
  • path 2 A-M1-M2-M3-B
  • path 3 A -N1-N2-N3-B
  • the length of the path 1 path is d (path 1 )
  • the length of the path 2 path is d ( Path 2 )
  • the length of the path 3 path is d(path 3 ).
  • the score corresponding to each optional planning path is the score of the path between each two adjacent nodes in the optional planning path, such as the walking distance influencing factor, the walking time influencing factor or the obstacle influencing factor, such as path 1
  • the score corresponding to the path is the path A-L1, L1-L2, L2-L3, and L3-B between each two adjacent nodes in the optional planning path.
  • scoring formula of the optional planning path is as follows:
  • o(t) is the time score of the optional planning path
  • o(d) is the distance score of the optional planning path
  • a and b are predetermined weights
  • the time score of the i-th optional planning path is defined o i (t) is:
  • T(path 1 ), T(path 2 )...T(path n ) are the time used by the robot to move to the target point in different alternative planning paths
  • T(path i ) is the ith optional planning path.
  • the time taken by the lower robot to move to the target point k ti represents the time penalty factor of the i-th optional planning path, which is the time it takes for the robot to bypass the obstacle in the ith optional planning path.
  • d i represents the path length of the i-th optional planning path
  • v i represents the robot speed in the i-th optional planning path
  • P i represents the probability of occurrence of an obstacle in the i-th optional planning path.
  • the distance score o i (d) defining the i-th optional planning path is:
  • d(path 1 ), d(path 2 )...d(path n ) are the distances that the robot travels to the target point in different alternative planning paths
  • k di represents the distance penalty of the i-th alternative planning path.
  • the distance penalty factor is the distance that the robot needs to move more than the obstacle in the ith optional planning path.
  • the obstacle influencing factors include an obstacle avoidance difficulty coefficient and a probability of occurrence of an obstacle.
  • the robot can access the Internet of Things system, and more useful information can be obtained through the system. For example: (1) The robot can get information about the indoor camera of the IoT system server. Because the surveillance camera generally corresponds to a fixed scene. The image processing method is used to process the data of the camera to obtain the number and approximate distribution of dynamic obstacles in a certain area. (2) The Internet of Things system server can statistically organize the data of personnel flow. Through statistical data, it is possible to predict the probability of which people are concentrated in which time periods and in which areas. (3) Further, the robot system can obtain the distribution of indoor dynamic obstacles (such as personnel distribution) through the indoor camera, and refresh the obstacle probability of the path of each section in real time. Therefore, the robot can dynamically select the optimal path according to the existing situation.
  • indoor dynamic obstacles such as personnel distribution
  • FIG. 6 is a schematic diagram of quantitative calculation of an obstacle influencing factor in an actual index, and the walking path of the robot is divided into several regions. Assume that it is known:
  • the corresponding distance penalty coefficient is kd and the time penalty coefficient is kt
  • the time scoring formula and distance scoring formula the time and distance scores of each path after the obstacle factor correction can be calculated.
  • the comprehensive score of each path can be calculated, as shown in the following table. Four:
  • the path with the lowest score is selected, that is, the third path is used as the optimal moving planning path of the robot.
  • path planning module 02 is further configured to:
  • the path planning system of the robot acquires obstacle information in the current path to be moved from a predetermined area monitoring server (for example, an Internet of Things system server) in real time or at a time, and analyzes the acquired obstacle information according to the obtained obstacle information. Whether there are obstacles or not needs to be moved to avoid. For example, if there is a static obstacle on the path to be moved, it is determined that movement avoidance is required, or if there is a intersection point between the moving path of the dynamic obstacle and the moving path of the robot, it is determined that movement avoidance is required, and the prior art There is a need to analyze whether there is an obstacle based on the acquired obstacle information.
  • a predetermined area monitoring server for example, an Internet of Things system server
  • the path planning system of the robot detects the obstacle information in the current path to be moved by the obstacle detecting unit (for example, the radar unit) configured by the robot in real time or timing, and analyzes whether there is an obstacle to be performed. Mobile evasion.
  • the obstacle detecting unit for example, the radar unit
  • the path planning system of the robot takes the current position as the new first position point, and analyzes the new first position point according to the set reference positioning point and according to the predetermined path analysis rule. a path to the second location point and controlling movement of the robot to the second location point based on the analyzed path. (For example, the planned path from point P to point Q shown in Figure 4).
  • FIG. 7 is a schematic diagram of the obstacle avoidance of the robot. It is assumed that the robot is to move from point A to point B, and a dynamic obstacle suddenly appears near the point C during the movement. In the prior art, the robot dynamically bypasses the obstacle according to an algorithm and recalculates the new planned path y4 according to the current position. There are some disadvantages to this approach, such as:
  • the robot In the process of bypassing the obstacle, the robot needs to constantly calculate the avoidance path and continuously calculate the path from the current position to the target point. This process will consume a lot of computing resources and time.
  • the robot cannot know the size of the obstacle in front of the eye, the time it takes to bypass it, and whether there are other obstacles after the bypass. For example, what appears in front of the robot is a long wall of people, and it takes a lot of time to bypass the wall by conventional methods.
  • the robot reselects another path by directly selecting other reference positioning points.
  • L1 and L2 are reference positioning points.
  • the robot can re-select another route C-L1-L2-B to reach point B, that is, the robot can choose not to bypass the obstacle, but choose another route, and select the route. It is more efficient to calculate the route in real time, does not take up a lot of computing resources of the robot, and the response is more timely.
  • the selection module 01 pre-selects one or more position points as the reference positioning points on the predetermined area map, and also sets the corresponding position points at the positions corresponding to the respective reference positioning points in the predetermined area map.
  • the location point identifier may be a manual location roadmap, eg, for example, the artificial landmark at the location corresponding to the second reference location of the second layer A3 region may be “L1A3P2”, or “L1A32”;
  • the position road sign eg, for example, the natural road sign at the position corresponding to the second reference point of the second layer A3 area may be " ⁇ A3".
  • the path planning module 02 is further configured to:
  • the open location point identification device (such as a camera) starts detecting the location point identifier
  • the distance and direction of the robot and the detected position point identification are calculated by the sensor of the robot to obtain the current position and posture of the robot, and the forward direction is calibrated according to the current position and posture of the robot.
  • the path planning module 02 is further configured to:
  • the current position is in the trigger coordinate area of a target reference positioning point, it is determined that the current position is in the trigger coordinate area of a reference positioning point, or if the current position is not in the trigger coordinate area of a target reference positioning point, then determining The current position is not in the trigger coordinate area of a datum point.
  • the robot During the movement of the robot according to the planned path, the robot needs to determine the current position and the target point by positioning. The location, as well as the location of the move, also needs to be confirmed during the move.
  • the combination of relative positioning and absolute positioning is now widely used. Because of the inevitable error accumulation problem of relative positioning, it is necessary to use absolute positioning method for calibration. In the relative positioning of the robot, the robot calculates the relative positioning of the sensor based on the previous positioning result and the relative displacement measured by the inertia sensor. Since there will be some error in each positioning, the error will continue to accumulate and become larger and larger, which will eventually lead to unacceptable positioning errors after a period of time. Therefore, the robot needs to calibrate the positioning information in some way at an appropriate time.
  • the position point identification is used to calibrate in the reference positioning point mode, and the robot can roughly determine the position of the road sign according to its position.
  • the robot recognizes the position point identification, the distance and direction of the robot and the road sign are calculated by the sensor. , get the current position and posture of the robot.
  • the robot needs to open the detecting device at all times to search for a location point identifier nearby and perform calibration. Therefore, it is necessary to arrange a large number of location point identifiers in a wide range, and also waste a large amount of computing resources of the robot.
  • the arrangement range of the position point identification is reduced to the vicinity of the reference positioning point, and there is no need to arrange a large number of road signs globally, and only the road markings are selectively arranged near the reference positioning point, thereby effectively reducing The number of road signs arranged to prevent confusion of other types of signs caused by the layout of a large number of road signs.
  • the position point of each reference anchor point is identified as a picture corresponding to the unique coordinates (a, b) in the map.
  • a camera is mounted on the top of the robot to identify the location point identification picture.
  • the robot captures the position point identification picture, the relative coordinates (m, n) of the robot relative to the target picture can be obtained, and the robot can obtain its current coordinate (a+m, b+n) and use the coordinate as Current accurate coordinates for coordinate calibration.
  • the robot in order to not miss the location point identification during the movement, the robot will open the top camera in real time and continuously process the video.
  • the camera opens the capturing position point identification for calibration if and only if the robot enters the triggering coordinate area of the reference positioning point, that is, the triggering radius. Therefore, the present embodiment gives the timing of the robot calibration by setting the trigger coordinate area of the reference positioning point, and facilitates the control of the robot, thereby reducing the calculation amount and resource consumption.
  • an implementation manner is that the robot uses the current coordinates and the coordinates of each of the reference positioning points in the database to calculate, and determines the current coordinates and Whether the coordinates of a datum point are smaller than the trigger radius.
  • the map and the reference positioning point are divided and classified, and all the reference positioning points are not queried during the query, but only the area where the area is located is determined, and only the reference positioning points constituting the area are determined. Make queries, which greatly reduces the amount of calculation per query.
  • FIG. 8 is a schematic diagram of a reference positioning area division and a trigger radius.
  • the calibration scheme includes the following steps:
  • the map is segmented into a plurality of polygonal regions 1, 2, ... using a reference positioning point r, each of which has a trigger radius R of a corresponding radius.
  • the robot determines in which region the current coordinates are located. For example, the robot in Figure 8 is currently located in the area numbered 5.
  • the robot when the robot is in a certain polygon area, the robot will query at time interval t to confirm whether its current coordinates are in the trigger radius of the reference point of the corner point of the area.
  • the current coordinates of the robot are located in a square area numbered 5, and the robot will only query the area where the current coordinates are at the reference positioning points of the four corner points constituting the area (ie, numbered A, B, C, D is the area formed by the four reference positioning points).
  • the robot will open the position point identification device (such as the camera) to start detecting the position point identification.
  • the robot will calibrate the current coordinates by the calculated coordinate information.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and can also be implemented by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present invention which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Manipulator (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Navigation (AREA)

Abstract

一种机器人的路径规划系统、方法、机器人及存储介质,该方法包括:机器人的路径规划系统在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点(S10);若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点(S20)。该方法无需机器人在路径规划时实时计算移动路径,而是从事先规划好的路径中进行对应选择,即将路径规划的过程从"计算"转变为"选择",有效减少了实时计算量,提高了路径规划的效率。

Description

机器人的路径规划系统、方法、机器人及存储介质
优先权声明
本申请基于巴黎公约申请享有2017年4月11日递交的申请号为CN201710232929.0、名称为“机器人的路径规划系统及方法”中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本发明涉及计算机技术领域,尤其涉及一种机器人的路径规划系统、方法、机器人及计算机可读存储介质。
背景技术
目前,自主移动机器人能够广泛应用于许多场景,比如担任展览馆的导览工作,带领参观者从一个展区介绍到另一个展区;餐厅的服务工作,主动欢迎客人,并带领客人到空位上点餐;公共场所的引导、巡逻工作,沿着程序设定的路线移动,有人需要帮助停下回答提问等等。
在这些场景下,需要自主移动机器人移动到一个或多个指定的位置,实现某些特定功能,这里涉及到了自主移动机器人的路径规划问题。现有技术中,在路径计算问题上,自主移动机器人一般都是在接受到移动指令时开始实时计算如何移动到目标点的路径,这个实时计算过程需要考虑诸多因素,比较耗时。
发明内容
本发明的主要目的在于提供一种机器人的路径规划系统、方法、机器人及存储介质,旨在提高自主移动机器人路径规划的效率。
为实现上述目的,本申请第一方面提供一种机器人的路径规划系统,所述路径规划系统包括:
选择模块,用于在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
路径规划模块,用于若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
本申请第二方面提供一种机器人的路径规划方法,所述方法包括以下步骤:
机器人的路径规划系统在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
本申请第三方面提供一种机器人,包括处理设备、存储设备,该存储设备中存储有机器人的路径规划系统,该机器人的路径规划系统包括至少一个计算机可读指令,该至少一个计算机可读指令可被所述处理设备执行,以实现以下操作:
在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
本申请第四方面提供一种计算机可读存储介质,其上存储有至少一个可被处理设备执 行,以实现以下操作的计算机可读指令:
在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
本发明提出的机器人的路径规划系统、方法、机器人及存储介质,通过在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;在接收到将所述机器人从第一位置点移动到第二位置点的指令后,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。无需机器人在路径规划时实时计算移动路径,而是从事先规划好的路径中进行对应选择,即将路径规划的过程从“计算”转变为“选择”,有效减少了实时计算量,提高了路径规划的效率。
附图说明
图1是本发明机器人的路径规划系统的较佳实施例的运行环境示意图;
图2为本发明机器人的路径规划方法一实施例的流程示意图;
图3为本发明机器人的路径规划方法一实施例中在公共图书馆区域地图中选择的各个基准定位点的示意图;
图4为本发明机器人的路径规划方法一实施例中在公共图书馆区域地图中P点到Q点的路径规划示意图;
图5为本发明机器人的路径规划方法一实施例中A点到B点的路径规划示意图;
图6为本发明机器人的路径规划方法一实施例中障碍物影响因素在实际指标中的量化计算示意图;
图7为本发明机器人的路径规划方法一实施例中机器人避障示意图;
图8为本发明机器人的路径规划方法一实施例中基准定位点区域划分与触发半径示意图;
图9为本发明机器人的路径规划系统一实施例的功能模块示意图。
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
为了使本发明所要解决的技术问题、技术方案及有益效果更加清楚、明白,以下结合附图和实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
参阅图1所示,是本发明机器人的路劲规划系统较佳实施例的运行环境示意图。在本实施例中,机器人的路径规划系统10安装并运行于机器人1中。该机器人1可包括,但不仅限于通过系统总线相互通信连接的存储器11、处理器12及显示器13。图1仅示出了具有组件11-13的机器人1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
其中,存储器11包括内存及至少一种类型的可读存储介质。内存为机器人1的运行提供缓存;可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器等的非易失性存储介质。在一些实施例中,可读存储介质可以是机器人1的内部存储单元,例如该机器人1的硬盘;在另一些实施例中,该非易失性存储介质也可以是机器人1的外部存储设备,例如机器人1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。本实施例中,存储器11的可读存储介质通常用于存储 安装于机器人1的操作系统和各类应用软件,例如本申请一实施例中的机器人的路径规划系统10的程序代码等。此外,存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器12在一些实施例中可以包括一个或者多个微处理器、微控制器、数字处理器等。该处理器12通常用于控制机器人1的运行。在本实施例中,处理器12用于运行存储器11中存储的程序代码或者处理数据,例如运行机器人的路径规划系统10等。
显示器13在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。显示器13用于显示在所述机器人1中处理的信息以及用于显示可视化的用户界面,例如应用菜单界面、应用图标界面等。机器人1的部件11-13通过系统总线相互通信。
机器人的路径规划系统10包括至少一个存储在存储器11中的计算机可读指令,该至少一个计算机可读指令可被处理器12执行,以实现本申请各实施例的机器人的路径规划方法。如后续所述,该至少一个计算机可读指令依据其各部分所实现的功能不同,可被划为不同的逻辑模块。
在一实施例中,机器人的路径规划系统10被处理器12执行时,实现以下操作:首先在预先确定的区域地图中可供机器人1移动的路径上预先选择一个或多个位置点作为基准定位点;然后若接收到将机器人1从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从第一位置点到第二位置点的路径,并基于分析出的路径控制机器人1运动到第二位置点。在一实施例中,机器人的路径规划系统10存储在存储器11中,包括至少一个存储在存储设备11中的计算机可读指令,该至少一个计算机可读指令可被处理器12执行,以实现本申请各实施例的机器人的路径规划方法。
本发明提供一种机器人的路径规划方法。
参照图2,图2为本发明机器人的路径规划方法一实施例的流程示意图。
在一实施例中,该机器人的路径规划方法包括:
步骤S10,机器人的路径规划系统在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点。
本实施例中,在预先确定的区域地图上预先选择一个或多个位置点作为基准定位点。例如,针对公共图书馆区域地图而言,可在各个相互连通且可供机器人移动的路径上选择一个或多个位置点作为基准定位点,如图3所示,图3中若干较小的黑色圆点即为在公共图书馆区域地图中选择的各个基准定位点,各个基准定位点均位于公共图书馆区域地图中可供机器人移动的路径上,图3中较大的黑色圆点为公共图书馆区域地图中机器人无法通过的障碍物。
步骤S20,若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
若接收到将所述机器人从第一位置点移动到第二位置点的指令,即机器人需要从第一位置点(例如,图3和图4中所示的P点)移动到第二位置点(例如,图3和图4中所示的Q点),则机器人的路径规划系统根据设置的基准定位点并按照预先确定的路径分析规则,分析出从第一位置点到第二位置的路径,并基于分析出的路径控制机器人运动到所述第二位置点。例如,针对区域地图中选定的各个基准定位点,可预先确定不同基准定位点之间的多条可移动的路径y1、y2、y3,如图4所示,基准定位点A与基准定位点B之间可预先确定出多条可移动的路径,确定出的多条可移动的路径均能绕开较大的黑色圆点,也即绕开机器人无法通过的障碍物,以便机器人能正常移动。若第一位置点如P点可顺利移动至其附近的基准定位点A,第二位置点Q点可顺利移动至其附近的基准定位点B,则 机器人的路径规划系统可根据需要选择基准定位点A与基准定位点B之间预先确定好的多条可移动的路径中的一条,即可作为分析出的机器人的移动路径,以完成将机器人从第一位置点运动到第二位置点的移动。例如,若需要机器人移动的路径最短,则可选择基准定位点A与基准定位点B之间预先确定好的可移动的路径y1或y3,等等。
本实施例通过在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;在接收到将所述机器人从第一位置点移动到第二位置点的指令后,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。无需机器人在路径规划时实时计算移动路径,而是从事先规划好的路径中进行对应选择,即将路径规划的过程从“计算”转变为“选择”,有效减少了实时计算量,提高了路径规划的效率。
进一步地,所述预先确定的路径分析规则包括:
确定距离第一位置点最近的第一基准定位点(例如,图4所示的A点),及距离第二位置点最近的第二基准定位点(例如,图4所示的B点);
为所述第一位置点至所述第一基准定位点,以及所述第二位置点至所述第二基准定位点的路径按照预设的第一规划方式进行规划;
为所述第一基准定位点至所述第二基准定位点的路径按照预设的第二规划方式进行规划,得到第二规划路径。
其中,所述第一规划方式为:
若两个位置点之间无障碍物,则取两个位置点之间的直线路径;若两个位置点之间有障碍物,则取两个位置点之间的绕过障碍物的最短路径。具体地,若所述第一位置点与所述第一基准定位点之间无障碍物,则取所述第一位置点与所述第一基准定位点之间的直线路径,如取P点至A点的直线路径。若所述第二位置点与所述第二基准定位点之间无障碍物,则取所述第二位置点与所述第二基准定位点之间的直线路径,如取Q点至B点的直线路径。若所述第一位置点与所述第一基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径;若所述第二位置点与所述第二基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径。
进一步地,所述第二规划方式包括如下步骤:
h1、根据预先确定的第一基准定位点、第二基准定位点及可选规划路径的映射关系,确定第一基准定位点和第二基准定位点对应的可选规划路径;
h2、按照预先确定的评分规则计算出各个可选规划路径对应的分值;
h3、若最高分值的可选规划路径只有一个,则将该可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径;
h4、若最高分值的可选规划路径有多个,则从多个最高分值的可选规划路径中随机选择一个可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径。
进一步地,所述步骤h1和h2之间,还包括如下步骤:
采用预先确定的筛选方式对可选规划路径进行过滤,以筛选出待进行分值计算的可选规划路径。所述预先确定的筛选方式包括如下步骤:
从各个可选规划路径中,筛选出包含预先确定的特定基准定位点的可选规划路径,并将筛选出的可选规划路径作为待进行分值计算的可选规划路径。例如,若机器人需要在从A点移动到B点的过程中播放一段广告,而广告需要在人群较多的路径M-N上进行播放。则机器人在路径规划过程中必须经过特定基准定位点M和N,从A到B可以选择的路径必须包含该特定基准定位点M和N,则只对包含该特定基准定位点M和N的可选规划路径进行分值计算,以简化路径的选择过程。
在另一种筛选方式中,还可根据预先确定的计算公式分别计算出各个可选规划路径对应的总长度,并分别计算出各个可选规划路径的总长度与第一基准定位点至第二基准定位点的最短路径的总长度的差值,第一基准定位点至第二基准定位点的最短路径可以是第一基准定位点与第二基准定位点之间的直线距离,也可以是第一基准定位点至第二基准定位点的各个可选规划路径中的最短路径。将对应的差值小于预设阈值的可选规划路径筛选出来作为待进行分值计算的可选规划路径。即筛选出路径长度较短的可选规划路径来进行选择,以提高选出最优规划路径的效率。
进一步地,在根据预先确定的计算公式来分别计算出各个可选规划路径对应的总长度时,所述预先确定的计算公式为:
Figure PCTCN2017091370-appb-000001
其中,d(path)代表路径的总长度,还包括:
Figure PCTCN2017091370-appb-000002
Figure PCTCN2017091370-appb-000003
Figure PCTCN2017091370-appb-000004
以限定各个可选规划路径中每个基准定位点只能经过一次,最差的情况是每个基准定位点都要经过。定义xij∈{0,1},i,j=1,2,...,n,i≠j,约束条件决策变量xij=1表示机器人选择了这段路径,xij=0表示机器人没有选择这段路径。
进一步地,在按照预先确定的评分规则计算各个可选规划路径对应的分值时,所述预先确定的评分规则为:
根据各个可选规划路径对应的行走距离影响因素、行走时间影响因素和/或障碍物影响因素进行评分;其中,每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
具体地,可定义最后选取的路径为:
min[Score(path1),Score(path2),...,Score(pathi),...,Score(pathn)|n∈N+]
其中,Score(pathi)指的是编号为i的路径的综合评分,路径的综合评分公式如下:
Score(path)=g[o(1),o(2),...,o(i),...,o(n)]
其中o(i)代表的是影响因素,所述影响因素包括行走距离影响因素、行走时间影响因素、障碍物(例如,避障难度)影响因素等,针对某一个影响因素,整条路径的该影响因素的评分值为每一段路径的评分和,即:
Figure PCTCN2017091370-appb-000005
其中Lk,k+1代表着A到B这段路径中每两个相邻节点之间的路径的该影响因素的评分。例如,如图5所示,假设机器人从A点到B点有三条路径,path1=A-L1-L2-L3-B,path2=A-M1-M2-M3-B,path3=A-N1-N2-N3-B,其中Li,Ni,Mi(i=1,2,3)为基准定位点,则path1路径的长度为d(path1),path2路径的长度为d(path2),path3路径的长度为d(path3)。每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和,如path1路径对应的分值为该可选 规划路径中每两个相邻节点之间的路径A-L1、L1-L2、L2-L3、L3-B在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
进一步地,可选规划路径的评分公式如下:
Score(path)=a·o(t)+b·o(d)
其中,o(t)为可选规划路径的时间评分,o(d)为可选规划路径的距离评分,a、b为预先确定的权值;定义第i个可选规划路径的时间评分oi(t)为:
Figure PCTCN2017091370-appb-000006
Figure PCTCN2017091370-appb-000007
其中,T(path1)、T(path2)……T(pathn)是不同可选规划路径下机器人移动到目标点所使用的时间,T(pathi)是第i个可选规划路径下机器人移动到目标点所使用的时间,kti代表第i个可选规划路径的时间惩罚系数,该时间惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多花费的时间,di代表第i个可选规划路径的路径长度,vi代表第i个可选规划路径内的机器人速度,Pi代表第i个可选规划路径内出现障碍物的概率。
定义第i个可选规划路径的距离评分oi(d)为:
Figure PCTCN2017091370-appb-000008
d(pathi)=∑(kdi·di·Pi+di·(1-Pi))
其中,d(path1)、d(path2)……d(pathn)是不同可选规划路径下机器人移动到目标点所行走的距离,kdi代表第i个可选规划路径的距离惩罚系数,该距离惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多移动的距离。
本实施例中,所述障碍物影响因素包括避障难度系数和出现障碍物的概率,在一种实施方式中,可以将机器人接入物联网系统,通过这个系统可以得到更多有用的信息,比如:(1)机器人能够得到物联网系统服务器处理室内摄像头的信息。由于监控摄像头一般对应着某一固定场景。通过图像处理方法对摄像头的数据进行处理能够得到在某一个区域动态障碍物的数量及大致分布。(2)物联网系统服务器能够对人员流动的数据进行统计整理。通过统计数据,可以预测出在哪些时间段,哪些区域内,人员分布较集中的概率。(3)更进一步,机器人系统能够通过室内摄像头得到室内动态障碍物的分布(比如人员分布),并实时对各个区段的路径的障碍物概率进行刷新。因此,机器人能够根据现有情况动态的选取最优路径。
如图6所示,图6为障碍物影响因素在实际指标中的量化计算示意图,将机器人的行走路径分割成若干个区域。假设已知:
(1)每两个“基准定位点”之间的距离d;
(2)每两个“基准定位点”之间的设定移动速度v;
(3)根据室内摄像头得到的实时图片信息以及服务器设定数据等等,可以得到一个当前室内各个区域的避障难度系数k以及障碍物可能出现的概率P,再映射到机器人的路径规划图上。不妨假设在区域III与区域IV中,人员分布比较集中,导致机器人在该区域内躲避障碍物的难度较大,即k(III)=k(IV)>k(I)=k(II)=k(V)=k(VI)。区域I、II与区域V、VI人员分布相近,但是从历史数据来看,区域I与区域II在这个时间段更容易出现障碍物即P(I)=P(II)>P(V)=P(VI)。相应的距离惩罚系数为kd,时间惩罚系数为kt
为计算方便,忽略路径A-L1,A-M1,A-N1之间与路径B-L3,B-M3,B-N3之间的区别,即只对路径L1-L2-L3(路径L),M1-M2-M3(路径M),N1-N2-N3路径(N)进行评分。给定已知条件如下表一所示:
表一
路径 距离d 速度v 时间t kd kt P
L1-L2 55.0 3.0 18.3 1.5 5.0 0.8
L2-L3 55.0 3.0 18.3 1.5 5.0 0.8
M1-M2 50.0 3.0 16.7 2.0 8.0 0.6
M2-M3 50.0 3.0 16.7 2.0 8.0 0.6
N1-N2 70.0 3.0 23.3 1.5 5.0 0.3
N2-N3 70.0 3.0 23.3 1.5 5.0 0.3
根据上述时间评分公式及距离评分公式可计算得到每一条路径经过障碍物因素修正后的时间与距离评分,根据上述对可选规划路径的综合评分公式可计算得到每条路径的综合评分,如下表二所示:
表二
Figure PCTCN2017091370-appb-000009
根据计算结果,即可分析选取评分最低的路径,即第三条路径作为机器人的最优移动规划路径。
进一步地,所述基于分析出的路径控制机器人运动到所述第二位置点的步骤包括:
机器人的路径规划系统实时或者定时分析当前待移动的路径中是否存在障碍物需要进行移动规避。在一种实施方式中,机器人的路径规划系统实时或者定时从预先确定的区域监控服务器(例如,物联网系统服务器)获取当前待移动的路径中的障碍物信息,并根据获取的障碍物信息分析是否存在障碍物需要进行移动规避。例如,若有静态障碍物处于待移动的路径上,则确定需要进行移动规避,或者,若有动态障碍物的移动路径与机器人的移动路径存在交汇点,则确定需要进行移动规避,现有技术中存在根据获取的障碍物信息分析是否存在障碍物需要进行移动规避的算法,在此不做赘述。在另一种实施方式中,机器人的路径规划系统实时或者定时通过机器人配置的障碍物检测单元(例如,雷达单元)检测当前待移动的路径中的障碍物信息,并分析是否存在障碍物需要进行移动规避。
若分析存在障碍物需要进行移动规避,则机器人的路径规划系统将当前位置作为新的第一位置点,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从新的第一位置点到所述第二位置点的路径,并基于分析出的路径控制机器人运动到所述第二位置点。(例如图4所示的P点到Q点的规划路径)。
如图7所示,图7为机器人避障示意图,假设机器人要从A点移动到B点,在运动中在C点附近突然出现一个动态障碍物。现有技术中,机器人会根据某种算法动态地绕过障碍物并根据当前位置重新计算新的规划路径y4。这种方法存在一些不利的地方,比如:
(1)在绕开障碍物的过程中,机器人需要不断地计算躲避路径,并不断计算从当前位置到达目标点的路径。这一过程将耗费大量计算资源与时间。
(2)机器人无法得知眼前的这个障碍物的大小、绕过所需要花费的时间、绕过之后是不是还有其他障碍物。例如,出现在机器人面前的是一堵很长的人墙,采用常规方法将 会花费大量的时间才能绕过这堵人墙。
与其相对的,在本实施例基于基准定位点来规划路径的方式中,机器人通过直接选择其他基准定位点来重新选择另外一条路径。假设L1、L2是基准定位点。当机器人遇到障碍物的时候,机器人能够重新选择另外一条路线C-L1-L2-B来到达B点,即机器人可以不去选择绕过障碍物,而是去选择另外一条路径,而且选择路线相对实时计算路线更有效率,不会占用机器人的大量计算资源,响应更加及时。
进一步地,机器人的路径规划系统在预先确定的区域地图上预先选择一个或多个位置点作为基准定位点的同时,还在预先确定的区域地图中各个基准定位点对应的位置处设置对应的位置点标识。所述位置点标识可以为人工位置路标,e.g.,例如,第二层A3区域的第二个基准定位点对应的位置处的人工路标可以为“L1A3P2”,或者,“L1A3②”;也可以是自然位置路标,e.g.,例如,第二层A3区域的第二个基准定位点对应的位置处的自然路标可以为“→A3”。
所述基于分析出的路径控制机器人运动到所述第二位置点的步骤还包括:
机器人的路径规划系统实时或者定时进行位置定位;
根据预先确定的基准定位点与触发坐标区域的映射关系,分析当前位置是否处于一个基准定位点的触发坐标区域中;所述触发坐标区域可以是以基准定位点为圆心、预设长度为半径的圆形区域或正方形区域,等等。
若当前位置处于一个基准定位点的触发坐标区域中,则开启位置点标识识别设备(如摄像头)开始检测位置点标识;
当检测到位置点标识时,通过机器人的传感器计算出机器人与检测的位置点标识的距离和方向,以得到机器人当前的位置和姿态,并根据机器人当前的位置和姿态对前进方向进行校准。
进一步地,为了大大减小每次查询的计算量,所述根据预先确定的基准定位点与触发坐标区域的映射关系,分析当前位置是否处于一个基准定位点的触发坐标区域中的步骤包括:
根据预先确定的区域与坐标范围的映射关系,确定当前位置所处的区域;
根据预先确定的区域与基准定位点的映射关系,确定当前位置对应的目标基准定位点;
分析当前位置是否处于一个目标基准定位点的触发坐标区域中;
若当前位置处于一个目标基准定位点的触发坐标区域中,则确定当前位置处于一个基准定位点的触发坐标区域中,或者,若当前位置不处于一个目标基准定位点的触发坐标区域中,则确定当前位置不处于一个基准定位点的触发坐标区域中。
在机器人按照规划路径移动过程中,机器人需要通过定位方式确定当前位置与目标点的位置,以及在移动过程中也需要确认自身的位置。现在广泛采用相对定位与绝对定位结合的方式。因为相对定位存在不可避免的误差累计问题,需要采用绝对定位的方法进行校准。在机器人的相对定位中,机器人是在上次定位结果的基础上,通过惯性等传感器测得的相对位移,来计算本次定位的结果。由于每次定位都会有一定误差,误差会不断地累积、越来越大,最终导致一段时间后定位误差大到不可接受。因此,机器人需要在适当的时刻采用某种方法对定位信息进行校准。
本实施例中是在基准定位点模式下采用位置点标识来校准,机器人可以根据自身的位置粗略确定路标的位置,当机器人识别到位置点标识后,通过传感器计算出机器人与路标的距离和方向,得到机器人当前的位置和姿态。
现有的校准方法中,机器人需要时时刻刻打开检测设备去搜寻附近是否有位置点标识,并进行校准。因此,需要在大范围内布置大量的位置点标识,也浪费了机器人大量的计算资源。而本实施例中在基准定位点模式下,将位置点标识的布置范围缩小到了基准定 位点附近,无需全局性地布置大量路标,只需选择性地在基准定位点附近布置路标,从而有效减少路标布置的数量,防止因大量路标的布设引起其他类型标识的混淆。
在以图像识别作为校准方案的实施例中,假设每个基准定位点的位置点标识为一张图片,该图片对应地图中唯一的坐标(a,b)。在机器人头顶安装有一个摄像头,用于识别位置点标识图片。当机器人捕捉到位置点标识图片时,能够获得机器人相对于目标图片的相对坐标(m,n),则机器人可以得到自身的当前坐标为(a+m,b+n),并将该坐标作为当前准确的坐标,实现坐标校准。在一种实施方式中,机器人在移动过程中为了不错过位置点标识,将实时打开顶部摄像头,不断对视频进行处理。而在另一种实施方式的基准定位点模式下,当且仅当机器人进入基准定位点的触发坐标区域即触发半径时,摄像头才打开捕捉位置点标识进行校准。因此,本实施例通过设置基准定位点的触发坐标区域给了机器人校准的时机,并便于机器人的控制,从而减少计算量和资源消耗。
在基准定位点模式下分析机器人当前位置是否处于一个基准定位点的触发坐标区域中时,一种实施方式是机器人实时利用当前坐标和数据库中每一个基准定位点的坐标进行计算,判断当前坐标与某个基准定位点的坐标是否小于触发半径。而为了加速搜索过程,在另一种实施方式中,将地图和基准定位点进行分割分类,查询时不对所有基准定位点进行查询,而是通过判断自身所在区域,只对构成区域的基准定位点进行查询,从而大大减小每次查询的计算量。如图8所示,图8为基准定位点区域划分与触发半径示意图,该校准方案包括如下步骤:
第一,利用基准定位点r将地图分割成多个多边形区域1、2……9,每个基准定位点都有相应半径的触发半径R。
第二,机器人判断当前坐标位于哪个区域内。例如图8中机器人当前位于编号为5的区域内。
第三,当机器人在某个多边形区域中时,机器人将以时间t的间隔查询确认自己当前坐标是否在这个区域角点的基准定位点的触发半径中。例如图8中,机器人当前坐标位于编号为5的方形区域内,机器人将仅会查询确认当前坐标是否在构成该区域的四个角点的基准定位点”的区域(即编号为A,B,C,D四个基准定位点构成的区域)内。
第四,若分析当前坐标已经进入某个基准定位点的触发半径区域,机器人将会打开位置点标识识别设备(如摄像头)开始检测位置点标识。
第五,当检测到位置点标识时,机器人将通过计算出的坐标信息来对当前坐标进行校准。
本发明进一步提供一种机器人的路径规划系统。
请参阅图9,是本发明机器人的路径规划系统10较佳实施例的功能模块图。在本实施例中,机器人的路径规划系统10可以被分割成一个或多个模块,所述一个或者多个模块被存储于所述存储器11中,并由一个或多个处理器(本实施例为所述处理器12)所执行,以完成本发明。例如,在图9中,机器人的路径规划系统10可以被分割成选择模块01、路径规划模块02。本发明所称的模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述机器人的路径规划系统10在所述机器人1中的执行过程。以下描述将具体介绍所述选择模块01、路径规划模块02的功能。
选择模块01,用于在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点。
本实施例中,在预先确定的区域地图上预先选择一个或多个位置点作为基准定位点。例如,针对公共图书馆区域地图而言,可在各个相互连通且可供机器人移动的路径上选择一个或多个位置点作为基准定位点,如图3所示,图3中若干较小的黑色圆点即为在公共图书馆区域地图中选择的各个基准定位点,各个基准定位点均位于公共图书馆区域地图中可供机器人移动的路径上,图3中较大的黑色圆点为公共图书馆区域地图中机器人无法通 过的障碍物。
路径规划模块02,用于若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
若接收到将所述机器人从第一位置点移动到第二位置点的指令,即机器人需要从第一位置点(例如,图3和图4中所示的P点)移动到第二位置点(例如,图3和图4中所示的Q点),则机器人的路径规划系统根据设置的基准定位点并按照预先确定的路径分析规则,分析出从第一位置点到第二位置的路径,并基于分析出的路径控制机器人运动到所述第二位置点。例如,针对区域地图中选定的各个基准定位点,可预先确定不同基准定位点之间的多条可移动的路径y1、y2、y3,如图4所示,基准定位点A与基准定位点B之间可预先确定出多条可移动的路径,确定出的多条可移动的路径均能绕开较大的黑色圆点,也即绕开机器人无法通过的障碍物,以便机器人能正常移动。若第一位置点如P点可顺利移动至其附近的基准定位点A,第二位置点Q点可顺利移动至其附近的基准定位点B,则机器人的路径规划系统可根据需要选择基准定位点A与基准定位点B之间预先确定好的多条可移动的路径中的一条,即可作为分析出的机器人的移动路径,以完成将机器人从第一位置点运动到第二位置点的移动。例如,若需要机器人移动的路径最短,则可选择基准定位点A与基准定位点B之间预先确定好的可移动的路径y1或y3,等等。
本实施例通过在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;在接收到将所述机器人从第一位置点移动到第二位置点的指令后,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。无需机器人在路径规划时实时计算移动路径,而是从事先规划好的路径中进行对应选择,即将路径规划的过程从“计算”转变为“选择”,有效减少了实时计算量,提高了路径规划的效率。
进一步地,所述预先确定的路径分析规则包括:
确定距离第一位置点最近的第一基准定位点(例如,图4所示的A点),及距离第二位置点最近的第二基准定位点(例如,图4所示的B点);
为所述第一位置点至所述第一基准定位点,以及所述第二位置点至所述第二基准定位点的路径按照预设的第一规划方式进行规划;
为所述第一基准定位点至所述第二基准定位点的路径按照预设的第二规划方式进行规划,得到第二规划路径。
其中,所述第一规划方式为:
若两个位置点之间无障碍物,则取两个位置点之间的直线路径;若两个位置点之间有障碍物,则取两个位置点之间的绕过障碍物的最短路径。具体地,若所述第一位置点与所述第一基准定位点之间无障碍物,则取所述第一位置点与所述第一基准定位点之间的直线路径,如取P点至A点的直线路径。若所述第二位置点与所述第二基准定位点之间无障碍物,则取所述第二位置点与所述第二基准定位点之间的直线路径,如取Q点至B点的直线路径。若所述第一位置点与所述第一基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径;若所述第二位置点与所述第二基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径。
进一步地,所述第二规划方式包括如下步骤:
h1、根据预先确定的第一基准定位点、第二基准定位点及可选规划路径的映射关系,确定第一基准定位点和第二基准定位点对应的可选规划路径;
h2、按照预先确定的评分规则计算出各个可选规划路径对应的分值;
h3、若最高分值的可选规划路径只有一个,则将该可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径;
h4、若最高分值的可选规划路径有多个,则从多个最高分值的可选规划路径中随机选择一个可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径。
进一步地,所述步骤h1和h2之间,还包括如下步骤:
采用预先确定的筛选方式对可选规划路径进行过滤,以筛选出待进行分值计算的可选规划路径。所述预先确定的筛选方式包括如下步骤:
从各个可选规划路径中,筛选出包含预先确定的特定基准定位点的可选规划路径,并将筛选出的可选规划路径作为待进行分值计算的可选规划路径。例如,若机器人需要在从A点移动到B点的过程中播放一段广告,而广告需要在人群较多的路径M-N上进行播放。则机器人在路径规划过程中必须经过特定基准定位点M和N,从A到B可以选择的路径必须包含该特定基准定位点M和N,则只对包含该特定基准定位点M和N的可选规划路径进行分值计算,以简化路径的选择过程。
在另一种筛选方式中,还可根据预先确定的计算公式分别计算出各个可选规划路径对应的总长度,并分别计算出各个可选规划路径的总长度与第一基准定位点至第二基准定位点的最短路径的总长度的差值,第一基准定位点至第二基准定位点的最短路径可以是第一基准定位点与第二基准定位点之间的直线距离,也可以是第一基准定位点至第二基准定位点的各个可选规划路径中的最短路径。将对应的差值小于预设阈值的可选规划路径筛选出来作为待进行分值计算的可选规划路径。即筛选出路径长度较短的可选规划路径来进行选择,以提高选出最优规划路径的效率。
进一步地,在根据预先确定的计算公式来分别计算出各个可选规划路径对应的总长度时,所述预先确定的计算公式为:
Figure PCTCN2017091370-appb-000010
其中,d(path)代表路径的总长度,还包括:
Figure PCTCN2017091370-appb-000011
Figure PCTCN2017091370-appb-000012
Figure PCTCN2017091370-appb-000013
以限定各个可选规划路径中每个基准定位点只能经过一次,最差的情况是每个基准定位点都要经过。定义xij∈{0,1},i,j=1,2,...,n,i≠j,约束条件决策变量xij=1表示机器人选择了这段路径,xij=0表示机器人没有选择这段路径。
进一步地,在按照预先确定的评分规则计算各个可选规划路径对应的分值时,所述预先确定的评分规则为:
根据各个可选规划路径对应的行走距离影响因素、行走时间影响因素和/或障碍物影响因素进行评分;其中,每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
具体地,可定义最后选取的路径为:
min[Score(path1),Score(path2),...,Score(pathi),...,Score(pathn)|n∈N+]
其中,Score(pathi)指的是编号为i的路径的综合评分,路径的综合评分公式如下:
Score(path)=g[o(1),o(2),...,o(i),...,o(n)]
其中o(i)代表的是影响因素,所述影响因素包括行走距离影响因素、行走时间影响因素、障碍物(例如,避障难度)影响因素等,针对某一个影响因素,整条路径的该影响因素的评分值为每一段路径的评分和,即:
Figure PCTCN2017091370-appb-000014
其中Lk,k+1代表着A到B这段路径中每两个相邻节点之间的路径的该影响因素的评分。例如,如图5所示,假设机器人从A点到B点有三条路径,path1=A-L1-L2-L3-B,path2=A-M1-M2-M3-B,path3=A-N1-N2-N3-B,其中Li,Ni,Mi(i=1,2,3)为基准定位点,则path1路径的长度为d(path1),path2路径的长度为d(path2),path3路径的长度为d(path3)。每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和,如path1路径对应的分值为该可选规划路径中每两个相邻节点之间的路径A-L1、L1-L2、L2-L3、L3-B在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
进一步地,可选规划路径的评分公式如下:
Score(path)=a·o(t)+b·o(d)
其中,o(t)为可选规划路径的时间评分,o(d)为可选规划路径的距离评分,a、b为预先确定的权值;定义第i个可选规划路径的时间评分oi(t)为:
Figure PCTCN2017091370-appb-000015
Figure PCTCN2017091370-appb-000016
其中,T(path1)、T(path2)……T(pathn)是不同可选规划路径下机器人移动到目标点所使用的时间,T(pathi)是第i个可选规划路径下机器人移动到目标点所使用的时间,kti代表第i个可选规划路径的时间惩罚系数,该时间惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多花费的时间,di代表第i个可选规划路径的路径长度,vi代表第i个可选规划路径内的机器人速度,Pi代表第i个可选规划路径内出现障碍物的概率。
定义第i个可选规划路径的距离评分oi(d)为:
Figure PCTCN2017091370-appb-000017
d(pathi)=∑(kdi·di·Pi+di·(1-Pi))
其中,d(path1)、d(path2)……d(pathn)是不同可选规划路径下机器人移动到目标点所行走的距离,kdi代表第i个可选规划路径的距离惩罚系数,该距离惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多移动的距离。
本实施例中,所述障碍物影响因素包括避障难度系数和出现障碍物的概率,在一种实施方式中,可以将机器人接入物联网系统,通过这个系统可以得到更多有用的信息,比如:(1)机器人能够得到物联网系统服务器处理室内摄像头的信息。由于监控摄像头一般对应着某一固定场景。通过图像处理方法对摄像头的数据进行处理能够得到在某一个区域动态障碍物的数量及大致分布。(2)物联网系统服务器能够对人员流动的数据进行统计整理。 通过统计数据,可以预测出在哪些时间段,哪些区域内,人员分布较集中的概率。(3)更进一步,机器人系统能够通过室内摄像头得到室内动态障碍物的分布(比如人员分布),并实时对各个区段的路径的障碍物概率进行刷新。因此,机器人能够根据现有情况动态的选取最优路径。
如图6所示,图6为障碍物影响因素在实际指标中的量化计算示意图,将机器人的行走路径分割成若干个区域。假设已知:
(1)每两个“基准定位点”之间的距离d;
(2)每两个“基准定位点”之间的设定移动速度v;
(3)根据室内摄像头得到的实时图片信息以及服务器设定数据等等,可以得到一个当前室内各个区域的避障难度系数k以及障碍物可能出现的概率P,再映射到机器人的路径规划图上。不妨假设在区域III与区域IV中,人员分布比较集中,导致机器人在该区域内躲避障碍物的难度较大,即k(III)=k(IV)>k(I)=k(II)=k(V)=k(VI)。区域I、II与区域V、VI人员分布相近,但是从历史数据来看,区域I与区域II在这个时间段更容易出现障碍物即P(I)=P(II)>P(V)=P(VI)。相应的距离惩罚系数为kd,时间惩罚系数为kt
为计算方便,忽略路径A-L1,A-M1,A-N1之间与路径B-L3,B-M3,B-N3之间的区别,即只对路径L1-L2-L3(路径L),M1-M2-M3(路径M),N1-N2-N3路径(N)进行评分。给定已知条件如下表三所示:
表三
路径 距离d 速度v 时间t kd kt P
L1-L2 55.0 3.0 18.3 1.5 5.0 0.8
L2-L3 55.0 3.0 18.3 1.5 5.0 0.8
M1-M2 50.0 3.0 16.7 2.0 8.0 0.6
M2-M3 50.0 3.0 16.7 2.0 8.0 0.6
N1-N2 70.0 3.0 23.3 1.5 5.0 0.3
N2-N3 70.0 3.0 23.3 1.5 5.0 0.3
根据上述时间评分公式及距离评分公式可计算得到每一条路径经过障碍物因素修正后的时间与距离评分,根据上述对可选规划路径的综合评分公式可计算得到每条路径的综合评分,如下表四所示:
表四
Figure PCTCN2017091370-appb-000018
根据计算结果,即可分析选取评分最低的路径,即第三条路径作为机器人的最优移动规划路径。
进一步地,上述路径规划模块02还用于:
实时或者定时分析当前待移动的路径中是否存在障碍物需要进行移动规避。在一种实施方式中,机器人的路径规划系统实时或者定时从预先确定的区域监控服务器(例如,物联网系统服务器)获取当前待移动的路径中的障碍物信息,并根据获取的障碍物信息分析是否存在障碍物需要进行移动规避。例如,若有静态障碍物处于待移动的路径上,则确定需要进行移动规避,或者,若有动态障碍物的移动路径与机器人的移动路径存在交汇点,则确定需要进行移动规避,现有技术中存在根据获取的障碍物信息分析是否存在障碍物需 要进行移动规避的算法,在此不做赘述。在另一种实施方式中,机器人的路径规划系统实时或者定时通过机器人配置的障碍物检测单元(例如,雷达单元)检测当前待移动的路径中的障碍物信息,并分析是否存在障碍物需要进行移动规避。
若分析存在障碍物需要进行移动规避,则机器人的路径规划系统将当前位置作为新的第一位置点,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从新的第一位置点到所述第二位置点的路径,并基于分析出的路径控制机器人运动到所述第二位置点。(例如图4所示的P点到Q点的规划路径)。
如图7所示,图7为机器人避障示意图,假设机器人要从A点移动到B点,在运动中在C点附近突然出现一个动态障碍物。现有技术中,机器人会根据某种算法动态地绕过障碍物并根据当前位置重新计算新的规划路径y4。这种方法存在一些不利的地方,比如:
(1)在绕开障碍物的过程中,机器人需要不断地计算躲避路径,并不断计算从当前位置到达目标点的路径。这一过程将耗费大量计算资源与时间。
(2)机器人无法得知眼前的这个障碍物的大小、绕过所需要花费的时间、绕过之后是不是还有其他障碍物。例如,出现在机器人面前的是一堵很长的人墙,采用常规方法将会花费大量的时间才能绕过这堵人墙。
与其相对的,在本实施例基于基准定位点来规划路径的方式中,机器人通过直接选择其他基准定位点来重新选择另外一条路径。假设L1、L2是基准定位点。当机器人遇到障碍物的时候,机器人能够重新选择另外一条路线C-L1-L2-B来到达B点,即机器人可以不去选择绕过障碍物,而是去选择另外一条路径,而且选择路线相对实时计算路线更有效率,不会占用机器人的大量计算资源,响应更加及时。
进一步地,上述选择模块01在预先确定的区域地图上预先选择一个或多个位置点作为基准定位点的同时,还在预先确定的区域地图中各个基准定位点对应的位置处设置对应的位置点标识。所述位置点标识可以为人工位置路标,e.g.,例如,第二层A3区域的第二个基准定位点对应的位置处的人工路标可以为“L1A3P2”,或者,“L1A3②”;也可以是自然位置路标,e.g.,例如,第二层A3区域的第二个基准定位点对应的位置处的自然路标可以为“→A3”。
上述路径规划模块02还用于:
实时或者定时进行位置定位;根据预先确定的基准定位点与触发坐标区域的映射关系,分析当前位置是否处于一个基准定位点的触发坐标区域中;所述触发坐标区域可以是以基准定位点为圆心、预设长度为半径的圆形区域或正方形区域,等等。
若当前位置处于一个基准定位点的触发坐标区域中,则开启位置点标识识别设备(如摄像头)开始检测位置点标识;
当检测到位置点标识时,通过机器人的传感器计算出机器人与检测的位置点标识的距离和方向,以得到机器人当前的位置和姿态,并根据机器人当前的位置和姿态对前进方向进行校准。
进一步地,为了大大减小每次查询的计算量,上述路径规划模块02还用于:
根据预先确定的区域与坐标范围的映射关系,确定当前位置所处的区域;
根据预先确定的区域与基准定位点的映射关系,确定当前位置对应的目标基准定位点;
分析当前位置是否处于一个目标基准定位点的触发坐标区域中;
若当前位置处于一个目标基准定位点的触发坐标区域中,则确定当前位置处于一个基准定位点的触发坐标区域中,或者,若当前位置不处于一个目标基准定位点的触发坐标区域中,则确定当前位置不处于一个基准定位点的触发坐标区域中。
在机器人按照规划路径移动过程中,机器人需要通过定位方式确定当前位置与目标点 的位置,以及在移动过程中也需要确认自身的位置。现在广泛采用相对定位与绝对定位结合的方式。因为相对定位存在不可避免的误差累计问题,需要采用绝对定位的方法进行校准。在机器人的相对定位中,机器人是在上次定位结果的基础上,通过惯性等传感器测得的相对位移,来计算本次定位的结果。由于每次定位都会有一定误差,误差会不断地累积、越来越大,最终导致一段时间后定位误差大到不可接受。因此,机器人需要在适当的时刻采用某种方法对定位信息进行校准。
本实施例中是在基准定位点模式下采用位置点标识来校准,机器人可以根据自身的位置粗略确定路标的位置,当机器人识别到位置点标识后,通过传感器计算出机器人与路标的距离和方向,得到机器人当前的位置和姿态。
现有的校准方法中,机器人需要时时刻刻打开检测设备去搜寻附近是否有位置点标识,并进行校准。因此,需要在大范围内布置大量的位置点标识,也浪费了机器人大量的计算资源。而本实施例中在基准定位点模式下,将位置点标识的布置范围缩小到了基准定位点附近,无需全局性地布置大量路标,只需选择性地在基准定位点附近布置路标,从而有效减少路标布置的数量,防止因大量路标的布设引起其他类型标识的混淆。
在以图像识别作为校准方案的实施例中,假设每个基准定位点的位置点标识为一张图片,该图片对应地图中唯一的坐标(a,b)。在机器人头顶安装有一个摄像头,用于识别位置点标识图片。当机器人捕捉到位置点标识图片时,能够获得机器人相对于目标图片的相对坐标(m,n),则机器人可以得到自身的当前坐标为(a+m,b+n),并将该坐标作为当前准确的坐标,实现坐标校准。在一种实施方式中,机器人在移动过程中为了不错过位置点标识,将实时打开顶部摄像头,不断对视频进行处理。而在另一种实施方式的基准定位点模式下,当且仅当机器人进入基准定位点的触发坐标区域即触发半径时,摄像头才打开捕捉位置点标识进行校准。因此,本实施例通过设置基准定位点的触发坐标区域给了机器人校准的时机,并便于机器人的控制,从而减少计算量和资源消耗。
在基准定位点模式下分析机器人当前位置是否处于一个基准定位点的触发坐标区域中时,一种实施方式是机器人实时利用当前坐标和数据库中每一个基准定位点的坐标进行计算,判断当前坐标与某个基准定位点的坐标是否小于触发半径。而为了加速搜索过程,在另一种实施方式中,将地图和基准定位点进行分割分类,查询时不对所有基准定位点进行查询,而是通过判断自身所在区域,只对构成区域的基准定位点进行查询,从而大大减小每次查询的计算量。如图8所示,图8为基准定位点区域划分与触发半径示意图,该校准方案包括如下步骤:
第一,利用基准定位点r将地图分割成多个多边形区域1、2……9,每个基准定位点都有相应半径的触发半径R。
第二,机器人判断当前坐标位于哪个区域内。例如图8中机器人当前位于编号为5的区域内。
第三,当机器人在某个多边形区域中时,机器人将以时间t的间隔查询确认自己当前坐标是否在这个区域角点的基准定位点的触发半径中。例如图8中,机器人当前坐标位于编号为5的方形区域内,机器人将仅会查询确认当前坐标是否在构成该区域的四个角点的基准定位点”的区域(即编号为A,B,C,D四个基准定位点构成的区域)内。
第四,若分析当前坐标已经进入某个基准定位点的触发半径区域,机器人将会打开位置点标识识别设备(如摄像头)开始检测位置点标识。
第五,当检测到位置点标识时,机器人将通过计算出的坐标信息来对当前坐标进行校准。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所 固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件来实现,但很多情况下前者是更佳的实施方式。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本发明各个实施例所述的方法。
以上参照附图说明了本发明的优选实施例,并非因此局限本发明的权利范围。上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。另外,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
本领域技术人员不脱离本发明的范围和实质,可以有多种变型方案实现本发明,比如作为一个实施例的特征可用于另一实施例而得到又一实施例。凡在运用本发明的技术构思之内所作的任何修改、等同替换和改进,均应在本发明的权利范围之内。

Claims (20)

  1. 一种机器人的路径规划系统,运行于机器人中,其特征在于,所述路径规划系统包括:
    选择模块,用于在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
    路径规划模块,用于若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
  2. 如权利要求1所述的路径规划系统,其特征在于,所述预先确定的路径分析规则包括:
    确定距离所述第一位置点最近的第一基准定位点,及距离所述第二位置点最近的第二基准定位点;
    为所述第一位置点至所述第一基准定位点,以及所述第二位置点至所述第二基准定位点的路径按照预设的第一规划方式进行规划;
    为所述第一基准定位点至所述第二基准定位点的路径按照预设的第二规划方式进行规划,得到第二规划路径。
  3. 如权利要求2所述的路径规划系统,其特征在于,所述第一规划方式包括:
    若所述第一位置点与所述第一基准定位点之间无障碍物,则取所述第一位置点与所述第一基准定位点之间的直线路径;若所述第二位置点与所述第二基准定位点之间无障碍物,则取所述第二位置点与所述第二基准定位点之间的直线路径;
    若所述第一位置点与所述第一基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径;若所述第二位置点与所述第二基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径。
  4. 如权利要求2所述的路径规划系统,其特征在于,所述第二规划方式包括如下步骤:
    h1、根据预先确定的第一基准定位点、第二基准定位点及可选规划路径的映射关系,确定第一基准定位点和第二基准定位点对应的可选规划路径;
    h2、按照预先确定的评分规则计算出各个可选规划路径对应的分值;
    h3、若最高分值的可选规划路径只有一个,则将该可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径;
    h4、若最高分值的可选规划路径有多个,则从多个最高分值的可选规划路径中随机选择一个可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径。
  5. 如权利要求4所述的路径规划系统,其特征在于,所述步骤h1和h2之间,还包括如下步骤:
    从各个可选规划路径中,筛选出包含预先确定的特定基准定位点的可选规划路径,并将筛选出的可选规划路径作为待计算分值的可选规划路径;及/或,
    根据预先确定的计算公式分别计算出各个可选规划路径对应的总长度,并分别计算出各个可选规划路径的总长度与第一基准定位点至第二基准定位点的最短路径的总长度的差值,将差值小于预设阈值的可选规划路径筛选出来作为待计算分值的可选规划路径。
  6. 如权利要求4所述的路径规划系统,其特征在于,所述步骤h2包括:
    根据各个可选规划路径对应的行走距离影响因素、行走时间影响因素和/或障碍物影响因素进行评分;其中,每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
  7. 如权利要求6所述的路径规划系统,其特征在于,可选规划路径的评分公式如下:
    Score(path)=a·o(t)+b·o(d)
    其中,o(t)为可选规划路径的时间评分,o(d)为可选规划路径的距离评分,a、b为预先确定的权值;定义第i个可选规划路径的时间评分oi(t)为:
    Figure PCTCN2017091370-appb-100001
    Figure PCTCN2017091370-appb-100002
    其中,T(path1)、T(path2)……T(pathn)是不同可选规划路径下机器人移动到目标点所使用的时间,T(pathi)是第i个可选规划路径下机器人移动到目标点所使用的时间,kti代表第i个可选规划路径的时间惩罚系数,该时间惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多花费的时间,di代表第i个可选规划路径的路径长度,vi代表第i个可选规划路径内的机器人速度,Pi代表第i个可选规划路径内出现障碍物的概率;
    定义第i个可选规划路径的距离评分oi(d)为:
    Figure PCTCN2017091370-appb-100003
    d(pathi)=∑(kdi·di·Pi+di·(1-Pi))
    其中,d(path1)、d(path2)……d(pathn)是不同可选规划路径下机器人移动到目标点所行走的距离,kdi代表第i个可选规划路径的距离惩罚系数,该距离惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多移动的距离。
  8. 如权利要求1-7任一项所述的路径规划系统,其特征在于,所述路径规划模块还用于:
    实时或者定时分析当前待移动的路径中是否存在障碍物需要进行移动规避;若分析存在障碍物需要进行移动规避,则将当前位置作为新的第一位置点,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从新的第一位置点到所述第二位置点的路径,并基于分析出的路径控制机器人运动到所述第二位置点。
  9. 如权利要求1-7任一项所述的路径规划系统,其特征在于,所述选择模块还用于:
    在预先确定的区域地图中各个基准定位点对应的位置处设置对应的位置点标识;
    所述路径规划模块还用于:
    实时或者定时进行位置定位;根据预先确定的基准定位点与触发坐标区域的映射关系,分析当前位置是否处于一个基准定位点的触发坐标区域中;若当前位置处于一个基准定位点的触发坐标区域中,则开启位置点标识识别设备开始检测位置点标识;当检测到位置点标识时,通过机器人的传感器计算出机器人与检测的位置点标识的距离和方向,以得到机器人当前的位置和姿态,并根据机器人当前的位置和姿态对前进方向进行校准。
  10. 一种机器人的路径规划方法,其特征在于,所述方法包括以下步骤:
    机器人的路径规划系统在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
    若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
  11. 一种机器人,包括处理设备、存储设备,该存储设备中存储有机器人的路径规划 系统,该机器人的路径规划系统包括至少一个计算机可读指令,该至少一个计算机可读指令可被所述处理设备执行,以实现以下操作:
    在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
    若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
  12. 如权利要求11所述的机器人,其特征在于,所述预先确定的路径分析规则包括:
    确定距离所述第一位置点最近的第一基准定位点,及距离所述第二位置点最近的第二基准定位点;
    为所述第一位置点至所述第一基准定位点,以及所述第二位置点至所述第二基准定位点的路径按照预设的第一规划方式进行规划;
    为所述第一基准定位点至所述第二基准定位点的路径按照预设的第二规划方式进行规划,得到第二规划路径。
  13. 如权利要求12所述的机器人,其特征在于,所述第一规划方式包括:
    若所述第一位置点与所述第一基准定位点之间无障碍物,则取所述第一位置点与所述第一基准定位点之间的直线路径;若所述第二位置点与所述第二基准定位点之间无障碍物,则取所述第二位置点与所述第二基准定位点之间的直线路径;
    若所述第一位置点与所述第一基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径;若所述第二位置点与所述第二基准定位点之间有障碍物,则取所述第一位置点与所述第一基准定位点之间的绕过障碍物的最短路径。
  14. 如权利要求12所述的机器人,其特征在于,所述第二规划方式包括如下操作:
    h1、根据预先确定的第一基准定位点、第二基准定位点及可选规划路径的映射关系,确定第一基准定位点和第二基准定位点对应的可选规划路径;
    h2、按照预先确定的评分规则计算出各个可选规划路径对应的分值;
    h3、若最高分值的可选规划路径只有一个,则将该可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径;
    h4、若最高分值的可选规划路径有多个,则从多个最高分值的可选规划路径中随机选择一个可选规划路径作为第一基准定位点至第二基准定位点的第二规划路径。
  15. 如权利要求14所述的机器人,其特征在于,所述至少一个计算机可读指令还可被所述处理设备执行,在实现所述操作h1和h2之间,还实现如下操作:
    从各个可选规划路径中,筛选出包含预先确定的特定基准定位点的可选规划路径,并将筛选出的可选规划路径作为待计算分值的可选规划路径;及/或,
    根据预先确定的计算公式分别计算出各个可选规划路径对应的总长度,并分别计算出各个可选规划路径的总长度与第一基准定位点至第二基准定位点的最短路径的总长度的差值,将差值小于预设阈值的可选规划路径筛选出来作为待计算分值的可选规划路径。
  16. 如权利要求14所述的机器人,其特征在于,所述至少一个计算机可读指令被所述处理设备执行,实现所述操作h2包括:
    根据各个可选规划路径对应的行走距离影响因素、行走时间影响因素和/或障碍物影响因素进行评分;其中,每一可选规划路径对应的分值为该可选规划路径中每两个相邻节点之间的路径在行走距离影响因素、行走时间影响因素或障碍物影响因素下的评分和。
  17. 如权利要求16所述的机器人,其特征在于,可选规划路径的评分公式如下:
    Score(path)=a·o(t)+b·o(d)
    其中,o(t)为可选规划路径的时间评分,o(d)为可选规划路径的距离评分,a、b为 预先确定的权值;定义第i个可选规划路径的时间评分oi(t)为:
    Figure PCTCN2017091370-appb-100004
    Figure PCTCN2017091370-appb-100005
    其中,T(path1)、T(path2)……T(pathn)是不同可选规划路径下机器人移动到目标点所使用的时间,T(pathi)是第i个可选规划路径下机器人移动到目标点所使用的时间,kti代表第i个可选规划路径的时间惩罚系数,该时间惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多花费的时间,di代表第i个可选规划路径的路径长度,vi代表第i个可选规划路径内的机器人速度,Pi代表第i个可选规划路径内出现障碍物的概率;
    定义第i个可选规划路径的距离评分oi(d)为:
    Figure PCTCN2017091370-appb-100006
    d(pathi)=∑(kdi·di·Pi+di·(1-Pi))
    其中,d(path1)、d(path2)……d(pathn)是不同可选规划路径下机器人移动到目标点所行走的距离,kdi代表第i个可选规划路径的距离惩罚系数,该距离惩罚系数为机器人在第i个可选规划路径内绕过障碍物需要多移动的距离。
  18. 如权利要求11-17任一项所述的机器人,其特征在于,所述至少一个计算机可读指令还可被所述处理设备执行,以实现以下操作:
    实时或者定时分析当前待移动的路径中是否存在障碍物需要进行移动规避;若分析存在障碍物需要进行移动规避,则将当前位置作为新的第一位置点,根据设置的基准定位点并按照预先确定的路径分析规则,分析出从新的第一位置点到所述第二位置点的路径,并基于分析出的路径控制机器人运动到所述第二位置点。
  19. 如权利要求11-17任一项所述的机器人,其特征在于,所述至少一个计算机可读指令还可被所述处理设备执行,以实现以下操作:
    在预先确定的区域地图中各个基准定位点对应的位置处设置对应的位置点标识;
    实时或者定时进行位置定位;根据预先确定的基准定位点与触发坐标区域的映射关系,分析当前位置是否处于一个基准定位点的触发坐标区域中;若当前位置处于一个基准定位点的触发坐标区域中,则开启位置点标识识别设备开始检测位置点标识;当检测到位置点标识时,通过机器人的传感器计算出机器人与检测的位置点标识的距离和方向,以得到机器人当前的位置和姿态,并根据机器人当前的位置和姿态对前进方向进行校准。
  20. 一种计算机可读存储介质,其上存储有至少一个可被处理设备执行,以实现以下操作的计算机可读指令:
    在预先确定的区域地图中可供机器人移动的路径上预先选择一个或多个位置点作为基准定位点;
    若接收到将所述机器人从第一位置点移动到第二位置点的指令,则根据设置的基准定位点并按照预先确定的路径分析规则,分析出从所述第一位置点到所述第二位置点的路径,并基于分析出的路径控制所述机器人运动到所述第二位置点。
PCT/CN2017/091370 2017-04-11 2017-06-30 机器人的路径规划系统、方法、机器人及存储介质 WO2018188200A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
US16/084,245 US11035684B2 (en) 2017-04-11 2017-06-30 Path planning system and method for robot, robot and medium
EP17899233.5A EP3438611B1 (en) 2017-04-11 2017-06-30 Path planning system and method for robot, robot and storage medium
JP2018541387A JP6800989B2 (ja) 2017-04-11 2017-06-30 ロボットの経路計画システム、方法、ロボット及び媒体
KR1020187023692A KR102152192B1 (ko) 2017-04-11 2017-06-30 로봇의 경로 계획 시스템, 방법, 로봇 및 매체
AU2017409109A AU2017409109B9 (en) 2017-04-11 2017-06-30 Path planning system and method for robot, robot and storage medium
SG11201900262RA SG11201900262RA (en) 2017-04-11 2017-06-30 Path planning system and method for robot, robot and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710232929.0 2017-04-11
CN201710232929.0A CN107677285B (zh) 2017-04-11 2017-04-11 机器人的路径规划系统及方法

Publications (1)

Publication Number Publication Date
WO2018188200A1 true WO2018188200A1 (zh) 2018-10-18

Family

ID=61133560

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/091370 WO2018188200A1 (zh) 2017-04-11 2017-06-30 机器人的路径规划系统、方法、机器人及存储介质

Country Status (9)

Country Link
US (1) US11035684B2 (zh)
EP (1) EP3438611B1 (zh)
JP (1) JP6800989B2 (zh)
KR (1) KR102152192B1 (zh)
CN (1) CN107677285B (zh)
AU (1) AU2017409109B9 (zh)
SG (1) SG11201900262RA (zh)
TW (1) TWI639813B (zh)
WO (1) WO2018188200A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111906779A (zh) * 2020-06-30 2020-11-10 珠海市一微半导体有限公司 一种越障结束判断方法、越障控制方法、芯片及机器人
CN112346444A (zh) * 2019-07-21 2021-02-09 长沙智能驾驶研究院有限公司 智慧工地的锥桶控制方法、装置、系统和计算机设备
CN112748733A (zh) * 2020-12-16 2021-05-04 广东电网有限责任公司 电缆放线车路径规划方法、装置、设备及存储介质
CN112947411A (zh) * 2021-01-26 2021-06-11 清华大学深圳国际研究生院 基于RFID与ROS-Slam的博物馆藏品智能巡检系统与方法
US11224972B2 (en) 2019-11-22 2022-01-18 Fanuc Corporation State machine for dynamic path planning
WO2024131052A1 (zh) * 2022-12-23 2024-06-27 广东深蓝水下特种设备科技有限公司 基于水下声呐定位的船舶清洗方法、系统及介质

Families Citing this family (43)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108415436A (zh) * 2018-04-09 2018-08-17 重庆鲁班机器人技术研究院有限公司 机器人引导方法、装置及机器人
CN108717302B (zh) * 2018-05-14 2021-06-25 平安科技(深圳)有限公司 机器人跟随人物方法、装置及存储介质、机器人
WO2019237351A1 (zh) * 2018-06-15 2019-12-19 深圳前海达闼云端智能科技有限公司 机器人运动控制方法、装置、存储介质及机器人
CN109077667B (zh) * 2018-07-16 2020-12-01 广州俊德信息科技有限公司 清洁电器的调整方法、系统、可存储介质和清洁电器
CN109101017A (zh) * 2018-07-27 2018-12-28 江苏盛海智能科技有限公司 一种无人车寻迹路线规划方法及终端
CN109163613A (zh) * 2018-08-28 2019-01-08 联誉信息股份有限公司 一种智能打靶机器人
CN109068278B (zh) * 2018-08-31 2023-02-28 平安科技(深圳)有限公司 室内避障方法、装置、计算机设备及存储介质
WO2020132927A1 (zh) * 2018-12-26 2020-07-02 深圳市柔宇科技有限公司 广告路径规划方法、穿戴装置、服务器及相关装置
US11338438B2 (en) * 2019-01-25 2022-05-24 Bear Robotics, Inc. Method, system and non-transitory computer-readable recording medium for determining a movement path of a robot
CN109933857B (zh) * 2019-02-19 2023-07-04 飞腾信息技术有限公司 感知集成电路布局信息的时钟树主干拓扑生成方法及系统
US11249492B2 (en) * 2019-03-26 2022-02-15 Intel Corporation Methods and apparatus to facilitate autonomous navigation of robotic devices
CN109822597B (zh) * 2019-04-14 2021-01-19 北京中大科慧科技发展有限公司 一种数据中心的全自动智能巡检机器人
CN110221608B (zh) * 2019-05-23 2021-10-01 中国银联股份有限公司 一种巡检设备的方法及装置
JP7124797B2 (ja) * 2019-06-28 2022-08-24 トヨタ自動車株式会社 機械学習方法および移動ロボット
CN110599089B (zh) * 2019-08-30 2020-11-03 北京三快在线科技有限公司 隔离带位置确定方法、装置、存储介质和电子设备
CN112631209A (zh) * 2019-10-08 2021-04-09 北京京东乾石科技有限公司 用于控制无人搬运车的方法和装置
CN112817269A (zh) * 2019-11-15 2021-05-18 深圳拓邦股份有限公司 一种遍历作业方法、系统及机器人设备
CN111177291B (zh) * 2019-12-23 2021-12-14 腾讯科技(深圳)有限公司 一种对象移动方法、装置、设备及介质
JP7487478B2 (ja) * 2020-01-23 2024-05-21 セイコーエプソン株式会社 移動ロボットの制御方法及び制御装置、並びに、ロボットシステム
US11438886B2 (en) * 2020-02-27 2022-09-06 Psj International Ltd. System for establishing positioning map data and method for the same
CN111694353A (zh) * 2020-05-14 2020-09-22 特斯联科技集团有限公司 一种导引控制方法、装置、存储介质及服务机器人
CN111930113A (zh) * 2020-06-30 2020-11-13 创新工场(北京)企业管理股份有限公司 一种为自主导航机器人设置行驶路径的方法与装置
CN111938513B (zh) * 2020-06-30 2021-11-09 珠海市一微半导体有限公司 一种机器人越障的沿边路径选择方法、芯片及机器人
CN111813123A (zh) * 2020-07-17 2020-10-23 徐州泰丰泵业有限公司 一种喷灌机行走控制系统和控制方法
CN111906765B (zh) * 2020-07-31 2022-07-12 平安科技(深圳)有限公司 应用于路径规划的空间采样方法、装置、设备及介质
CN112201072A (zh) * 2020-09-30 2021-01-08 姜锡忠 城市交通路径规划方法及系统
CN112256039B (zh) * 2020-11-05 2023-05-26 深圳市锐曼智能装备有限公司 清洁机器人操控系统及清扫路线的生成方法
CN112370158B (zh) * 2020-11-13 2022-03-11 毕建平 一种机器人骨折复位路径规划方法、规划系统及机器人
CN113156933B (zh) * 2020-12-30 2022-05-03 徐宁 一种机器人行进控制系统和方法
JP2022188993A (ja) * 2021-06-10 2022-12-22 株式会社日立製作所 経路探索情報処理システム、経路探索情報処理方法
CN113807790A (zh) * 2021-09-26 2021-12-17 上海擎朗智能科技有限公司 一种机器人的路径规划方法、装置、电子设备和存储介质
CN113842086B (zh) * 2021-09-28 2022-12-06 深圳市云鼠科技开发有限公司 一种清洁方法、拖地机器人及清洁系统
CN113892863B (zh) * 2021-10-08 2022-11-01 珠海格力电器股份有限公司 路径规划方法、装置、电子设备和存储介质
CN113970321A (zh) * 2021-10-21 2022-01-25 北京房江湖科技有限公司 一种户型动线的计算方法及装置
CN114115239B (zh) * 2021-11-03 2024-04-12 中国科学院重庆绿色智能技术研究院 一种机器人路径规划方法、系统、设备及介质
TWI806237B (zh) * 2021-11-11 2023-06-21 國立虎尾科技大學 機器人系統及機器人控制方法
CN114260891B (zh) * 2021-12-16 2024-06-11 珠海格力电器股份有限公司 一种机器人控制方法、装置、电子设备及存储介质
CN116774686A (zh) * 2022-03-10 2023-09-19 苏州科瓴精密机械科技有限公司 机器人寻路方法、寻路装置、设备和计算机可读存储介质
CN116388691B (zh) * 2023-04-07 2023-10-20 宁夏百川电力股份有限公司 一种光伏发电场智能巡检方法及系统
CN116540709B (zh) * 2023-05-11 2023-11-14 江苏博发机器人智能装备有限公司 一种基于机器人编队的避障路径规划方法
CN117093011B (zh) * 2023-10-20 2024-01-05 苏州德斯米尔智能科技有限公司 一种智能机器人无人清洗控制方法
CN117250965B (zh) * 2023-11-20 2024-02-23 广东电网有限责任公司佛山供电局 一种机器人避障快速路径重构方法和系统
CN118149828B (zh) * 2024-05-10 2024-07-09 君华高科(成都)信息技术有限公司 一种巡检机器人的路径规划系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004067232A2 (en) * 2003-01-31 2004-08-12 Thermo Crs Ltd. Syntactic inferential motion planning method for robotic systems
CN103294054A (zh) * 2012-02-24 2013-09-11 联想(北京)有限公司 一种机器人导航方法及系统
CN103605368A (zh) * 2013-12-04 2014-02-26 苏州大学张家港工业技术研究院 一种动态未知环境中路径规划方法及装置
CN104416569A (zh) * 2013-08-28 2015-03-18 鸿富锦精密工业(深圳)有限公司 机器人控制系统、机器人及机器人控制方法
CN105955267A (zh) * 2016-05-11 2016-09-21 上海慧流云计算科技有限公司 一种移动控制方法及系统

Family Cites Families (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5978730A (en) * 1997-02-20 1999-11-02 Sony Corporation Caching for pathfinding computation
JP3359008B2 (ja) * 1999-08-20 2002-12-24 三菱重工業株式会社 無人搬送車の走行制御システム
JP2002133351A (ja) * 2000-10-25 2002-05-10 Nec Corp 最小コスト経路探索装置及びそれに用いる最小コスト経路探索方法
US6615133B2 (en) * 2001-02-27 2003-09-02 International Business Machines Corporation Apparatus, system, method and computer program product for determining an optimum route based on historical information
US7447593B2 (en) * 2004-03-26 2008-11-04 Raytheon Company System and method for adaptive path planning
KR100745975B1 (ko) 2004-12-30 2007-08-06 삼성전자주식회사 그리드 맵을 사용하여 최소 이동 경로로 이동하는 방법 및장치
JP2007094743A (ja) * 2005-09-28 2007-04-12 Zmp:Kk 自律移動型ロボットとそのシステム
JP4143103B2 (ja) * 2006-12-20 2008-09-03 本田技研工業株式会社 移動装置、ならびにその制御システム、制御プログラムおよび監督システム
JP4661838B2 (ja) * 2007-07-18 2011-03-30 トヨタ自動車株式会社 経路計画装置及び方法、コスト評価装置、並びに移動体
US8825387B2 (en) * 2008-07-25 2014-09-02 Navteq B.V. Positioning open area maps
US8417446B2 (en) 2008-07-25 2013-04-09 Navteq B.V. Link-node maps based on open area maps
JP4745378B2 (ja) * 2008-12-08 2011-08-10 株式会社東芝 移動台車
TWI388956B (zh) * 2009-05-20 2013-03-11 Univ Nat Taiwan Science Tech 行動機器人與其目標物處理路徑的規劃方法
KR100988833B1 (ko) * 2009-07-06 2010-10-20 유티정보 주식회사 신호연동정보를 이용한 네비게이션 시스템
KR101667030B1 (ko) * 2009-08-10 2016-10-17 삼성전자 주식회사 로봇의 경로 계획 장치 및 그 방법
KR101667029B1 (ko) * 2009-08-10 2016-10-17 삼성전자 주식회사 로봇의 경로 계획방법 및 장치
WO2011033100A1 (de) * 2009-09-18 2011-03-24 Deutsches Zentrum Fuer Luft- Und Raumfahrt E.V. Verfahren zur erstellung einer karte bezüglich ortsbezogener angaben über die wahrscheinlichkeit der zukünftigen bewegung einer person
JP2011175393A (ja) * 2010-02-24 2011-09-08 Toyota Motor Corp 経路計画装置、自律移動ロボット、及び移動経路の計画方法
US9323250B2 (en) * 2011-01-28 2016-04-26 Intouch Technologies, Inc. Time-dependent navigation of telepresence robots
JP5776440B2 (ja) * 2011-08-24 2015-09-09 株式会社豊田中央研究所 自律移動体
US20140309789A1 (en) * 2013-04-15 2014-10-16 Flextronics Ap, Llc Vehicle Location-Based Home Automation Triggers
KR20150035745A (ko) 2012-06-26 2015-04-07 더 거버닝 카운실 오브 더 유니버시티 오브 토론토 라디오 맵의 동적 생성을 위한 시스템, 방법 그리고 컴퓨터 프로그램
GB2505464B (en) * 2012-08-31 2019-12-18 Bae Systems Plc Route planning
KR102009482B1 (ko) * 2012-10-30 2019-08-14 한화디펜스 주식회사 로봇의 경로계획 장치와 방법 및 상기 방법을 구현하는 프로그램이 기록된 기록 매체
CN103838240B (zh) * 2012-11-27 2018-02-27 联想(北京)有限公司 控制方法和电子设备
KR101743072B1 (ko) * 2015-06-12 2017-06-15 국방과학연구소 경로 계획 장치 및 그의 제어방법
CN105549585B (zh) * 2015-12-07 2018-03-23 江苏木盟智能科技有限公司 机器人导航方法及系统
CN106168803A (zh) * 2016-04-18 2016-11-30 深圳众为兴技术股份有限公司 一种用于移动机器人的位置感知方法
US10394244B2 (en) * 2016-05-26 2019-08-27 Korea University Research And Business Foundation Method for controlling mobile robot based on Bayesian network learning
CN105974928B (zh) * 2016-07-29 2018-12-07 哈尔滨工大服务机器人有限公司 一种机器人导航路径规划方法
CN106323299B (zh) * 2016-08-09 2021-05-14 Tcl科技集团股份有限公司 一种导航方法、装置和系统
CN106382944B (zh) * 2016-10-08 2019-11-01 浙江国自机器人技术有限公司 一种移动机器人的路线规划方法
CN106547272B (zh) * 2016-10-26 2019-12-03 北京京东尚科信息技术有限公司 确定设备移动路径的方法和装置
CN106444769B (zh) * 2016-10-31 2019-05-21 湖南大学 一种室内移动机器人增量式环境信息采样的最优路径规划方法
JP6640777B2 (ja) * 2017-03-17 2020-02-05 株式会社東芝 移動制御システム、移動制御装置及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004067232A2 (en) * 2003-01-31 2004-08-12 Thermo Crs Ltd. Syntactic inferential motion planning method for robotic systems
CN103294054A (zh) * 2012-02-24 2013-09-11 联想(北京)有限公司 一种机器人导航方法及系统
CN104416569A (zh) * 2013-08-28 2015-03-18 鸿富锦精密工业(深圳)有限公司 机器人控制系统、机器人及机器人控制方法
CN103605368A (zh) * 2013-12-04 2014-02-26 苏州大学张家港工业技术研究院 一种动态未知环境中路径规划方法及装置
CN105955267A (zh) * 2016-05-11 2016-09-21 上海慧流云计算科技有限公司 一种移动控制方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3438611A4

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112346444A (zh) * 2019-07-21 2021-02-09 长沙智能驾驶研究院有限公司 智慧工地的锥桶控制方法、装置、系统和计算机设备
CN112346444B (zh) * 2019-07-21 2023-06-13 长沙智能驾驶研究院有限公司 智慧工地的锥桶控制方法、装置、系统和计算机设备
US11224972B2 (en) 2019-11-22 2022-01-18 Fanuc Corporation State machine for dynamic path planning
CN111906779A (zh) * 2020-06-30 2020-11-10 珠海市一微半导体有限公司 一种越障结束判断方法、越障控制方法、芯片及机器人
CN111906779B (zh) * 2020-06-30 2022-05-10 珠海一微半导体股份有限公司 一种越障结束判断方法、越障控制方法、芯片及机器人
CN112748733A (zh) * 2020-12-16 2021-05-04 广东电网有限责任公司 电缆放线车路径规划方法、装置、设备及存储介质
CN112748733B (zh) * 2020-12-16 2024-05-07 广东电网有限责任公司 电缆放线车路径规划方法、装置、设备及存储介质
CN112947411A (zh) * 2021-01-26 2021-06-11 清华大学深圳国际研究生院 基于RFID与ROS-Slam的博物馆藏品智能巡检系统与方法
CN112947411B (zh) * 2021-01-26 2023-09-12 清华大学深圳国际研究生院 基于RFID与ROS-Slam的博物馆藏品智能巡检系统与方法
WO2024131052A1 (zh) * 2022-12-23 2024-06-27 广东深蓝水下特种设备科技有限公司 基于水下声呐定位的船舶清洗方法、系统及介质

Also Published As

Publication number Publication date
SG11201900262RA (en) 2019-02-27
US20210080272A1 (en) 2021-03-18
AU2017409109B2 (en) 2019-12-05
US11035684B2 (en) 2021-06-15
TW201837428A (zh) 2018-10-16
AU2017409109B9 (en) 2020-04-09
EP3438611A1 (en) 2019-02-06
EP3438611B1 (en) 2020-12-02
JP6800989B2 (ja) 2020-12-16
JP2019521401A (ja) 2019-07-25
TWI639813B (zh) 2018-11-01
EP3438611A4 (en) 2019-09-11
CN107677285B (zh) 2019-05-28
CN107677285A (zh) 2018-02-09
KR102152192B1 (ko) 2020-09-07
AU2017409109A1 (en) 2018-11-08
KR20190019897A (ko) 2019-02-27

Similar Documents

Publication Publication Date Title
WO2018188200A1 (zh) 机器人的路径规划系统、方法、机器人及存储介质
US10953545B2 (en) System and method for autonomous navigation using visual sparse map
Vysotska et al. Lazy data association for image sequences matching under substantial appearance changes
CN109491375A (zh) 用于自动驾驶车辆的基于驾驶场景的路径规划
CN102638675B (zh) 一种利用多视点视频进行目标跟踪的方法和系统
CN109489675A (zh) 用于自动驾驶车辆的基于成本的路径规划
CN107894773A (zh) 一种移动机器人的导航方法、系统及相关装置
Kala Rapidly exploring random graphs: motion planning of multiple mobile robots
US10783363B2 (en) Method of creating map by identifying moving object, and robot implementing the method
CN108152823A (zh) 一种基于视觉的无人驾驶叉车导航系统及其定位导航方法
US20210149413A1 (en) Method for positioning on basis of vision information and robot implementing same
JP2016018540A (ja) 走行区画線認識装置
CN116075818B (zh) 走查视频中的图像搜索
CN110174112B (zh) 一种用于移动机器人自动建图任务的路径优化方法
US20230057965A1 (en) Robot and control method therefor
CN110986945B (zh) 基于语义高度地图的局部导航方法和系统
CN114594772A (zh) 机器人、路径规划方法、装置和存储介质
CN113358118B (zh) 非结构环境中端到端的室内移动机器人自主导航方法
CN109344685A (zh) 一种智慧托盘及其智能定位追踪方法
Japuria et al. CASNSC: A context-based approach for accurate pedestrian motion prediction at intersections
Tas et al. High-definition map update framework for intelligent autonomous transfer vehicles
CN110736465B (zh) 导航方法、装置、机器人及计算机可读存储介质
TWI806237B (zh) 機器人系統及機器人控制方法
CN112859842B (zh) 一种路径跟随导航方法及其系统
Poggenhans et al. Application of line clustering algorithms for improving road feature detection

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018541387

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20187023692

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2017899233

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2017899233

Country of ref document: EP

Effective date: 20180910

ENP Entry into the national phase

Ref document number: 2017409109

Country of ref document: AU

Date of ref document: 20170630

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17899233

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE