WO2022083292A1 - 一种智能移动机器人全局路径规划方法和系统 - Google Patents
一种智能移动机器人全局路径规划方法和系统 Download PDFInfo
- Publication number
- WO2022083292A1 WO2022083292A1 PCT/CN2021/115501 CN2021115501W WO2022083292A1 WO 2022083292 A1 WO2022083292 A1 WO 2022083292A1 CN 2021115501 W CN2021115501 W CN 2021115501W WO 2022083292 A1 WO2022083292 A1 WO 2022083292A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- mobile robot
- global
- grid
- grid map
- path planning
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 235000001275 Bouea macrophylla Nutrition 0.000 description 1
- 240000001160 Bouea macrophylla Species 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Definitions
- the invention relates to the field of intelligent control of mobile robots, in particular to a global path planning method and system for an intelligent mobile robot.
- mobile robots have served all walks of life in social development, and can replace manual tasks with high execution efficiency and low error rate, which can effectively reduce labor costs and operating costs, such as factories, hospitals, families, hotels, exhibition halls, restaurants. It mainly performs tasks such as logistics, handling and distribution.
- Mobile robots need to navigate autonomously within work scenarios, be able to locate accurately and travel safely.
- the movement of the mobile robot needs to abide by the traffic rules similar to motor vehicles, such as no-going area, right-handing area, boycotting area, no-going line and one-way line.
- a mobile robot When a mobile robot operates in a work scene, it generally builds a global map of the surrounding work scene in advance, and realizes safe travel from the starting point to the target point according to the requirements of the job task.
- the global path planning algorithm of an ordinary mobile robot will only search for the nearest or the shortest time-consuming shortcut, and will not follow the traffic rules of the drivable passage, which will lead to more dynamic objects and narrow drivable areas.
- the smoothness of travel in other scenes is very poor.
- the invention provides a global path planning method and system for an intelligent mobile robot, which enables the mobile robot to realize autonomous navigation when operating in complex dynamic scenes, has good safety and order and high real-time performance, and solves the problem of many applications in different complex dynamic scenes. Traffic congestion in narrow work areas for mobile robots.
- the present invention provides a global path planning method for an intelligent mobile robot, including:
- S1 determine the global information of the job, and obtain a global grid map after gridizing the global scene of the job;
- S3 discretize the grid value of the global grid map, and define that the distance between the area passed by the mobile robot and the obstacle is greater than the radius of the circumcircle of the mobile robot;
- the special area includes at least one of a no-going area, a right-handing area, a boycotting area, a no-going line and a one-way line.
- the S2 includes:
- the no-going area, the right-handing area, the resisting area, and the no-going line are obtained in the first predetermined area, and by restricting the grid diffusion of the global grid map in the second predetermined area Set a single line.
- the grid value of the global grid map ranges from 0 to 255 or 0 to 1023.
- the surrounding environment information is sensed in real time through laser sensors and Doppler radar, and the mobile robot is globally positioned in the grid map.
- an embodiment of the present invention also discloses a global path planning system for an intelligent mobile robot, including:
- the grid map conversion module is used to output a grid map after gridding according to the input global scene of the job;
- a driving rule and special area setting module connected with the grid map conversion module, for setting driving rules and special areas on the grid map;
- the map discretization module is connected to the grid map conversion module, the driving rules and the special area setting module, and is used to discretize the grid values of the global grid map to define the area and obstacles that the mobile robot passes through The spacing is greater than the radius of the circumcircle of the mobile robot;
- the A* algorithm path planning module is connected to the map discretization module, receives the starting point and the target point of the mobile robot, uses the A* algorithm to define the pass value for the global grid map, and outputs to the mobile robot A series of consecutive coordinate values of waypoints in the grid map from the starting point to the target point.
- a grid value setting module connected with the map discretization module, for receiving a grid value adjustment instruction, and adjusting the grid value of the global grid map.
- a travel speed limit module connected with the A* algorithm path planning module, for setting the travel speed of the mobile robot according to the passing value of the current grid passed by the mobile robot.
- the method and system for global path planning of an intelligent mobile robot provided by the embodiments of the present invention have the following beneficial effects:
- the method and system for global path planning of an intelligent mobile robot are based on a pre-built global grid map of the scene, set based on traffic rules similar to motor vehicles, and define a pass value on the global grid map to improve the A* global path search algorithm, and generate an output
- the continuous path point coordinate value realizes navigation, which enables the mobile robot to realize autonomous navigation in complex dynamic scenes, with good safety and order and high real-time performance. Traffic congestion problem.
- FIG. 1 is a schematic flowchart of steps of an embodiment of a global path planning method for an intelligent mobile robot provided by the present application
- FIG. 2 is a schematic flowchart of steps of another embodiment of a global path planning method for an intelligent mobile robot provided by the present application;
- FIG. 3 is a schematic structural diagram of an embodiment of an intelligent mobile robot global path planning system provided by the present application.
- FIG. 4 is a schematic structural diagram of another embodiment of the global path planning system for an intelligent mobile robot provided by the present application.
- Figure 1 is a schematic flowchart of steps of an embodiment of a global path planning method for an intelligent mobile robot provided by the application
- Figure 2 is another embodiment of the global path planning method for an intelligent mobile robot provided by the application
- Fig. 3 is a schematic structural diagram of an embodiment of an intelligent mobile robot global path planning system provided by the application
- Fig. 4 is a structural schematic diagram of another embodiment of an intelligent mobile robot global path planning system provided by the application.
- the present invention provides a global path planning method for an intelligent mobile robot, including:
- S1 determine the job global information, gridize the job global scene to obtain a global grid map; that is, determine the entire environment in which the mobile robot works, set its allowable activity range as the job global, and then perform gridding. Obtain a global grid map after rasterization;
- S2 setting driving rules and setting special areas on the global grid map; the purpose of setting formal rules and special areas is to enable the mobile robot to follow certain rules during the traveling process, which may be the use of current traffic rules, or Other self-defined traffic rules may be adopted, which is not limited in the present invention.
- the conventional global grid map method discretizes the real environment and divides it into a square grid with a certain resolution, such as a width of 20cm, where 1 means there is an obstacle, 0 means no obstacle, and -1 means unknown.
- a certain resolution such as a width of 20cm
- 1 means there is an obstacle
- 0 means no obstacle
- -1 means unknown.
- such a single representation often does not take the safety size information of the mobile robot into account, and will plan a path very close to the obstacle, while taking into account the constraints of certain traffic rules set, which is easy to happen in actual operation.
- a logic error occurs when the mobile robot collides with the obstacle area.
- the A* algorithm is a heuristic algorithm, which is composed of a cost function and a heuristic function.
- the cost function represents the cost from the starting grid to the target grid, which is usually calculated from the cost value of walking through the grid.
- the heuristic function represents the estimated cost from the starting point to the target point, usually calculated by the current grid. The Manhattan distance from the grid to the target grid is calculated.
- the setting is based on the traffic rules similar to the motor vehicle, and the global grid map is defined to define the passing value to improve the A* global path search algorithm, and generate and output continuous coordinate values of the waypoints to realize autonomous navigation, so that the mobile The robot realizes autonomous navigation when operating in complex dynamic scenes, with good safety and order and high real-time performance, and solves the problem of traffic congestion in the narrow operating area of multi-mobile robots in different complex dynamic scenes.
- the present invention does not limit the setting method, type and quantity of the special area. It may be a special area that only includes the actual terrain, or a special area formed due to communication signals such as electromagnetic interference or other reasons.
- the special area includes prohibited areas. At least one of the line area, the right line area, the boycott area, the forbidden line and the one-way line.
- the S2 includes:
- the no-going area, the right-handing area, the resisting area, and the no-going line are obtained in the first predetermined area, and by restricting the grid diffusion of the global grid map in the second predetermined area Set a single line.
- the present invention is not limited to the above-mentioned special area setting method, and can also be set by using a model, that is, classifying the special area, using the keyboard or mouse to select the area and then selecting the type to realize the setting of the special area. , and can also be assigned to a specific area, so that in the identification process, the specific assignment area can be defined as the required type.
- the present invention does not limit the range of grid values of the global grid map, which can be set according to the actual path planning accuracy and data processing capability.
- the grid values of the global grid map range from 0 to 255 or 0 to 1023.
- the position of the mobile robot changes continuously during the traveling process, so it is necessary to continuously position the mobile robot to realize that the mobile robot travels according to the predetermined path.
- the S5 after the S5, it also includes:
- the surrounding environment information is sensed in real time by a laser sensor and a Doppler radar, and the mobile robot is globally positioned in the grid map.
- the present invention does not limit the way of sensing the surrounding environment information, and is not limited to the above-mentioned ways, and other ways can also be used, such as using a trigger to trigger after the mobile robot reaches a designated position, so as to realize position perception, and even further It can be combined with satellite positioning system to realize positioning and so on.
- the present invention does not limit the method of adjusting the grid value of the global grid map, which can be directly inputted by keyboard, or implemented by mode selection, or other methods, such as increasing or decreasing one step.
- the following steps are further included:
- the present invention does not limit the way of controlling the traveling speed of the mobile robot, and the access can be corresponding to the passing value in real time, and the speed can also be limited similarly to each road section of a train.
- the traversal modification of the grid cost value of the conventional grid map, the global path planning of the mobile robot is based on a constructed global grid map, combined with the real-time perception of the surrounding environment information by the laser, to find a path from the starting point to the A safe, collision-free, continuous path point to a target point, which is usually the shortest or least time-executed path.
- the present invention expands the range of each grid value in the conventional global grid map from 0, 1, -1 to 0 to 255, where 0 represents complete freedom, 254 represents complete occupation, and 255 represents unknown.
- 0 represents complete freedom
- 254 represents complete occupation
- 255 represents unknown.
- a new value of 1 to 253 has been added, and the closer to the obstacle, the higher the value.
- 253 is defined as the grid value of the distance from the obstacle within the radius of the inscribed circle of the mobile robot.
- the mobile robot can pass the grid with the value of 1 to 252, but cannot pass the grid with the value of 253 or 254, whether it can pass the grid with the value of 255 to see the configuration parameters.
- the size of the grid value outside the radius of the circumcircle of the obstacle can be calculated by the following formula:
- d is the distance to the nearest obstacle
- r is the radius of the circumcircle of the mobile robot
- w is the adjustment coefficient
- forbidden area, forbidden line and boycott area set the cost value to 253 or 254 in the specified area of the grid map, among which the forbidden area is set to 253, the forbidden line is set to 254, and the value of the boycott area can be specified as 1 to 252.
- the right-handed area setting the right-handed area is used in some specific situations, especially when dealing with multiple robots seems important.
- the A* algorithm will expand from the grid with the smallest current objective function value in each iteration (4-connected or 8-connected), and the grid with cost value of 253 or 254 will not be expanded until Expand to the target point, then start from the target point, and go back to the starting point in the direction with the fastest potential energy reduction. At this point, the one-time path planning is completed.
- Each point of the grid map is set with a cost value, the present invention defines a new pass value P, which has 5 values in the 4-connected system, namely NONE, LEFT, RIGHT, UP and DOWN, respectively representing no Restrict, restrict expansion left, restrict expansion right, restrict expansion up and restrict expansion down.
- a series of continuous path point coordinate values from the starting point S to the target point E in the raster map are output.
- E with coordinates [x y] and angle ⁇ values.
- the mobile robot realizes autonomous navigation from the starting point S to the target point E by passing through these intermediate path points continuously and accurately.
- the mobile robot can automatically stop or avoid obstacles autonomously, which will involve the local path planning algorithm of the mobile robot.
- an embodiment of the present invention also discloses a global path planning system for an intelligent mobile robot, including:
- the grid map conversion module 10 is used for outputting the grid map after gridizing according to the input global scene of the job;
- the driving rule and special area setting module 20 is connected to the grid map conversion module 10, and is used for setting driving rules and special areas on the grid map;
- the map discretization module 30 is connected to the grid map conversion module 10, the driving rules and the special area setting module 20, and is used to discretize the grid values of the global grid map to define the area that the mobile robot passes through The distance from the obstacle is greater than the radius of the circumcircle of the mobile robot;
- the A* algorithm path planning module 40 is connected to the map discretization module 30, receives the starting point and the target point of the mobile robot, uses the A* algorithm to define the pass value for the global grid map, and moves to the The robot outputs a series of consecutive path point coordinate values from the starting point to the target point in the grid map.
- the intelligent mobile robot global path planning system further includes a grid value setting module 50 connected to the map discretization module 30 , which is used to receive a grid value adjustment instruction and adjust the grid value of the global grid map.
- the present invention does not limit the method of adjusting the grid value of the global grid map, which can be directly inputted by keyboard, or implemented by mode selection, or other methods, such as increasing or decreasing one step.
- the global path planning method and system for an intelligent mobile robot further includes a travel speed limit module 30 connected to the A* algorithm path planning module 40, It is used to set the traveling speed of the mobile robot according to the passing value of the current grid that the mobile robot passes through.
- the method and system for global path planning of an intelligent mobile robot define a traffic value for the global grid map based on a pre-built scene global grid map, based on traffic rules similar to those of motor vehicles.
- To improve the A* global path search algorithm generate and output continuous path point coordinate values to achieve autonomous navigation, so that mobile robots can achieve autonomous navigation in complex dynamic scenes, with good safety and order and high real-time performance. Traffic congestion in narrow operating areas of multi-mobile robots in complex dynamic scenes.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
一种智能移动机器人全局路径规划方法和系统，方法包括：确定作业全局信息，对作业全局的场景进行格栅化后获得全局栅格地图（S1）；对全局栅格地图设置行驶规则以及设置特殊区域（S2）；将全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于移动机器人的外接圆半径（S3）；采用A*算法对全局栅格地图定义通行值（S4）；根据通行值以及移动机器人的起始点和目标点，输出栅格地图中一系列连续的路径点坐标值（S5）。通过预先构建的场景全局栅格地图，设置基于类似于机动车交通规则，对全局栅格地图定义通行值来改进A*全局路径搜索算法，生成输出连续的路径点坐标值实现自主导航。
Description
本申请要求于2020年10月23日提交中国专利局、申请号为202011147139.0、发明名称为“一种智能移动机器人全局路径规划方法和系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及移动机器人智能控制领域，具体地涉及一种智能移动机器人全局路径规划方法和系统。
目前移动机器人已经服务于社会发展的各行各业，能够代替人工执行任务，执行效率高、误差率低，能够有效地降低人工成本以及经营成本，如工厂、医院、家庭、酒店、展览馆、餐厅等，主要执行物流、搬运和配送等作业任务。
移动机器人需要在工作场景内自主导航，能够准确定位和安全行进。而当作业场景比较复杂，如动态物体比较多、可行驶区域比较狭窄等，移动机器人的运动需要遵守类似于机动车交通规则，如禁行区、右行区、抵制区、禁行线和单行线等，才能保证移动机器人在复杂作业场景中有序通行，解决移动机器人与动态物体之间以及多移动机器人之间可能出现的交通卡顿甚至拥堵问题。
移动机器人在工作场景中作业，一般都是提前构建周围工作场景全局地图，根据作业任务要求，实现从起始点到目标点的安全行进。而普通的移动机器人的全局路径规划算法则只会搜索最近的或者耗时最短的捷径，而不会遵从可行驶通道行驶的交通规则，就会导致在如动态物体比较多、可行驶区域比较狭窄等场景中行进的顺畅性很差。
为了保证移动机器人的通行效率和安全性，需要在移动机器人预 先构建的场景地图上进行一定的交通规则设置，类似于人类机动车的交通规则标识出哪些区域能行走，哪些区域不能行走，以及哪些区域只能单向行走等约束。移动机器人基于这些交通规则约束条件，因此，如何实现机器人安全高效的运行，是本领域技术人员的工作重点。
发明内容
本发明提供了一种智能移动机器人全局路径规划方法和系统，使得移动机器人在复杂动态场景作业时的实现自主导航，安全有序性好且实时性较高，解决应用于不同复杂动态场景中多移动机器人狭窄作业区域内的交通拥堵问题。
为解决上述技术问题，本发明提供了一种智能移动机器人全局路径规划方法，包括：
S1，确定作业全局信息，对所述作业全局的场景进行格栅化后获得全局栅格地图；
S2，对所述全局栅格地图设置行驶规则以及设置特殊区域；
S3，将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；
S4，采用A*算法对所述全局栅格地图定义通行值；
S5，根据所述通行值以及所述移动机器人的起始点和目标点，输出所述栅格地图中一系列连续的路径点坐标值。
其中，所述特殊区域包括禁行区、右行区、抵制区、禁行线和单行线中至少一种。
其中，所述S2，包括：
通过设置所述全局栅格地图的栅格值在第一预定区域获得禁行区、右行区、抵制区、禁行线，通过限制所述全局栅格地图的栅格扩散在第二预定区域设置单行线。
其中，所述全局栅格地图的栅格值的范围为0～255或0～1023。
其中，在所述S5之后，还包括：
通过激光传感器、多普勒雷达实时感知周围环境信息，对所述移 动机器人在所述栅格地图中进行全局定位。
其中，在所述S5之后，还包括：
接收栅格值调整指令，调整所述全局栅格地图的栅格值。
其中，在所述S5之后，还包括：
S6，检测所述移动机器人当前所处的栅格的通行值，设置所述移动机器人的行进速度。
除此之外，在本发明的实施例中还公开了一种智能移动机器人全局路径规划系统，包括：
栅格地图转换模块，用于根据输入的作业全局场景进行格栅化后，输出格栅化地图；
行驶规则与特殊区域设置模块，与所述栅格地图转换模块连接，用于对所述格栅化地图设置行驶规则以及设置特殊区域；
地图离散化模块，与所述栅格地图转换模块、所述行驶规则与特殊区域设置模块连接，用于将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；
A*算法路径规划模块，与所述地图离散化模块连接，接收所述移动机器人的起始点和目标点，采用A*算法对所述全局栅格地图定义通行值后，向所述移动机器人输出所述栅格地图中从所述起始点到所述目标点一系列连续的路径点坐标值。
其中，还包括与所述地图离散化模块连接的栅格值设置模块，用于接收栅格值调整指令，调整所述全局栅格地图的栅格值。
其中，还包括与所述A*算法路径规划模块连接的行进速度限制模块，用于根据所述移动机器人通过的当前栅格的通行值，设定所述移动机器人的行进速度。
本发明实施例提供的智能移动机器人全局路径规划方法和系统，与现有技术相比较具有以下有益效果：
所述智能移动机器人全局路径规划方法和系统，通过预先构建的场景全局栅格地图，设置基于类似于机动车交通规则，对全局栅格地 图定义通行值来改进A*全局路径搜索算法，生成输出连续的路径点坐标值实现导航，使得移动机器人在复杂动态场景作业时的实现自主导航，安全有序性好且实时性较高，解决应用于不同复杂动态场景中多移动机器人狭窄作业区域内的交通拥堵问题。
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1为本申请提供的智能移动机器人全局路径规划方法的一个实施例的步骤流程示意图；
图2为本申请提供的智能移动机器人全局路径规划方法的另一个实施例的步骤流程示意图；
图3为本申请提供的智能移动机器人全局路径规划系统的一个实施例的结构示意图；
图4为本申请提供的智能移动机器人全局路径规划系统的另一个实施例的结构示意图。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
如图1-4所示，图1为本申请提供的智能移动机器人全局路径规划方法的一个实施例的步骤流程示意图；图2为本申请提供的智能移动 机器人全局路径规划方法的另一个实施例的步骤流程示意图；图3为本申请提供的智能移动机器人全局路径规划系统的一个实施例的结构示意图；图4为本申请提供的智能移动机器人全局路径规划系统的另一个实施例的结构示意图。
在一种具体实施方式中，本发明提供了一种智能移动机器人全局路径规划方法，包括：
S1，确定作业全局信息，对所述作业全局的场景进行格栅化后获得全局栅格地图；即确定移动机器人工作的整个环境，将其能够允许的活动范围设定为作业全局，然后进行格栅化后获得全局栅格地图；
S2，对所述全局栅格地图设置行驶规则以及设置特殊区域；设置形式规则以及特殊区域的目的，是使得在移动机器人行进过程中，能够遵循确定的规则，可以是采用现行的交通规则，也可以是采用其它的自定义的交通规则，本发明对此不作限定。
S3，将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；采用栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径，使得与常规的全局栅格化地图有较大的区别，考虑了移动机器人本身的尺寸。
例如，常规全局栅格地图法是把真实环境离散化，分成了具有一定分辨率，如20cm宽度的一个正方形栅格，其中1表示有障碍物，0表示无障碍物，-1表示未知。但这样单一化的表示方式往往没有把移动机器人的安全尺寸信息考虑在内，会规划出离障碍物很近的路径，同时考虑所设置的一定交通规则约束条件，这样在实际操作中很容易发生移动机器人与障碍区域发生碰撞发生逻辑错误的情况。
S4，采用A*算法对所述全局栅格地图定义通行值；A*算法是一种启发式算法，由代价函数和启发式函数两部分组成。代价函数表示从起始栅格开始到目标栅格所花费的代价，通常由走过栅格cost值计算得到，启发式函数表示从起始点到目标点预估需要的代价值，通常由当前栅格到目标栅格的曼哈顿距离计算得到。
S5，根据所述通行值以及所述移动机器人的起始点和目标点，输出所述栅格地图中一系列连续的路径点坐标值。
通过预先构建的场景全局栅格地图，设置基于类似于机动车交通规则，对全局栅格地图定义通行值来改进A*全局路径搜索算法，生成输出连续的路径点坐标值实现自主导航，使得移动机器人在复杂动态场景作业时的实现自主导航，安全有序性好且实时性较高，解决应用于不同复杂动态场景中多移动机器人狭窄作业区域内的交通拥堵问题。
本发明对于特殊区域的设置方式以及类型、数量不做限定，可以是仅仅包括实际地形造成的特殊区域，也可以是由于电磁干扰等通信信号或者其它原因形成的特殊区域，所述特殊区域包括禁行区、右行区、抵制区、禁行线和单行线中至少一种。
需要指出的是，即使是有实际地形形成的特殊区域，在本发明对移动机器人进行路径规划时也可以适当的进行调整，即可以完全相同，也可以是有一定的调整。
本发明对于实现特殊区域的设置方式不做限定，一个实施例中，所述S2，包括：
通过设置所述全局栅格地图的栅格值在第一预定区域获得禁行区、右行区、抵制区、禁行线，通过限制所述全局栅格地图的栅格扩散在第二预定区域设置单行线。
需要指出的是，本发明并不局限于上述的特殊区域设置方式，还可以是采用模型的方式进行设置，即将特殊区域进行分类，采用键盘或者鼠标选定区域然后选择类型，实现特殊区域的设置，还可以是对特定的区域进行赋值，这样在识别过程中，就可以对特定的赋值区域定义为需要的类型。
本发明对于全局栅格地图的栅格值的范围不做限定，可以根据实际的路径规划精度以及数据处理能力进行设定，一般所述全局栅格地图的栅格值的范围为0～255或0～1023。
本发明中在完成对移动机器人的路径规划之后，在移动机器人行 进过程中其位置不断发生变化，因此需要不断的进行定位，实现移动机器人按照预定的路径进行行进，本发明对于其定位方式不做限定，在一个实施例中，在所述S5之后，还包括：
通过激光传感器、多普勒雷达实时感知周围环境信息，对所述移动机器人在所述栅格地图中进行全局定位。
本发明对感知周围环境信息的方式不做限定，并不局限于上述的方式，也可以采用其它的方式，如采用触发器，在移动机器人到达指定位置之后进行触发，实现位置感知，甚至于还可以与卫星定位系统进行结合实现定位等。
由于对于不同的场景，需要采用的栅格地图的精确度不同，为了实现灵活使用，降低使用成本，在一个实施例中，在所述S5之后，还包括：
接收栅格值调整指令，调整所述全局栅格地图的栅格值。
本发明对于调整所述全局栅格地图的栅格值的方式不做限定，可以采用键盘等直接输入，也可以采用模式选择实现，或者其它的方式，如增加一档或减少一档等方式。
由于在移动机器人行进过程中，如果只有一个移动机器人既可以自由行使，但是如果有多个移动机器人，可能会发生交通拥堵的情况，而在多数情况下，移动机器人的数量会较多，因此需要对此移动机器人进行速度设置，提高通行安全性，因此，在一个实施例中，在所述S5之后，还包括：
S6，检测所述移动机器人当前所处的栅格的通行值，设置所述移动机器人的行进速度。
本发明对于控制移动机器人的行进速度的方式不做限定，可以通入与通行值进行实时对应，也可以类似火车的各个路段进行速度限制。
在一个实施例中，常规栅格地图栅格cost值的遍历修改，移动机器人全局路径规划是在一张已构建的全局栅格地图上，结合激光实时感知周围环境信息，找到一条从起始点到目标点的安全无碰撞连续的 路径点，这条路径通常是最短或者时间执行最少的。
本发明把常规全局栅格地图中每个栅格值的范围从0、1、-1扩大为从0到255，其中0表示完全自由，254表示完全占用，255表示未知。和原先的占用栅格法相比新增了1到253的值，离障碍物越近，其值就越高。由于移动机器人有一定尺寸，所以它的中心到障碍物的距离不可能比移动机器人的内切圆半径小，故这里把253定义为距离障碍物在移动机器人内切圆半径之内的栅格值，移动机器人可以通过值为1到252的栅格，不能通过值为253或254的栅格，能否通过值为255的栅格看配置参数。在距离障碍物外接圆半径之外的栅格值大小可用下式计算：
f
cost＝e
-w(d-r)·252(d>r)
其中，d为到最近障碍物的距离，r为移动机器人的外接圆半径，w为调节系数。
对于禁区、禁线和抵制区的设置：在栅格地图的指定区域把cost值设置成253或254，其中禁区设置成253，禁线设置成254，抵制区的值可以指定成1到252任意一个，当设置小时会穿过抵制区，当设置大时会选择一条代价更小的路；对于右行区设置：靠右行区域是在一些特定的情况下使用的，尤其是应对多机器人时显得很重要。它假设移动机器人能够看到靠右行区域的中线，把它当作一个虚拟的“障碍物”，然后总是向左膨胀这个障碍物，使这个“障碍物”左边的栅格总是有很大的值(但也可通行)，从而让移动机器人规划出总是在这个“障碍物”右边的路径；对于单行区设置：与上述区域不同的是，这个是通过限制移动机器人规划而实现的。
改进A*全局路径规划算法：A*算法每次迭代都会从当前目标函数值最小的栅格进行扩展(4连通或8连通)，cost值为253或254的栅格将不会被扩展，直到扩展到目标点，然后从目标点开始，按照势能减小最快的方向一直回溯到起点，至此，一次路径规划完毕。栅格地图的每个点都设置了cost值，本发明定义一个新的通行值P，它在4连通的系统中有5个值，分别是NONE、LEFT、RIGHT、UP 和DOWN，分别代表无限制，限制向左扩展，限制向右扩展，限制向上扩展和限制向下扩展。
经过上述改进A*全局路径规划算法之后，即输出栅格地图中从起始点S到目标点E一系列连续的路径点坐标值，其中中间的坐标值只有坐标[x y]信息，最终目标点E带有坐标[x y]和角度θ值。移动机器人通过连续准确经过这些中间的路径点即实现从起始点S到目标点E的自主导航。当然，对于行驶过程中有动态的、在地图中不存在的障碍物出现，移动机器人可以自动停止或自主避障等方式进行自主导航，这会涉及移动机器人的局部路径规划算法。
除此之外，在本发明的实施例中还公开了一种智能移动机器人全局路径规划系统，包括：
栅格地图转换模块10，用于根据输入的作业全局的场景进行格栅化后，输出格栅化地图；
行驶规则与特殊区域设置模块20，与所述栅格地图转换模块10连接，用于对所述格栅化地图设置行驶规则以及设置特殊区域；
地图离散化模块30，与所述栅格地图转换模块10、所述行驶规则与特殊区域设置模块20连接，用于将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；
A*算法路径规划模块40，与所述地图离散化模块30连接，接收所述移动机器人的起始点和目标点，采用A*算法对所述全局栅格地图定义通行值后，向所述移动机器人输出所述栅格地图中从所述起始点到所述目标点一系列连续的路径点坐标值。
由于上述的智能移动机器人全局路径规划系统为上述的智能移动机器人全局路径规划方法对应的系统，具有相同的有益效果，本发明对此不作赘述。
本发明中由于需要在不同的场景下进行调整栅格值，因此在一个实施例中，所述智能移动机器人全局路径规划系统还包括与所述地图 离散化模块30连接的栅格值设置模块50，用于接收栅格值调整指令，调整所述全局栅格地图的栅格值。
本发明对于调整所述全局栅格地图的栅格值的方式不做限定，可以采用键盘等直接输入，也可以采用模式选择实现，或者其它的方式，如增加一档或减少一档等方式。
由于在移动机器人行进过程中，如果只有一个移动机器人既可以自由行使，但是如果有多个移动机器人，可能会发生交通拥堵的情况，而在多数情况下，移动机器人的数量会较多，因此需要对此移动机器人进行速度设置，提高通行安全性，在一个实施例中，所述智能移动机器人全局路径规划方法和系统还包括与所述A*算法路径规划40模块连接的行进速度限制模块30，用于根据所述移动机器人通过的当前栅格的通行值，设定所述移动机器人的行进速度。
综上所述，本发明实施例提供的所述智能移动机器人全局路径规划方法和系统，通过预先构建的场景全局栅格地图，设置基于类似于机动车交通规则，对全局栅格地图定义通行值来改进A*全局路径搜索算法，生成输出连续的路径点坐标值实现自主导航，使得移动机器人在复杂动态场景作业时的实现自主导航，安全有序性好且实时性较高，解决应用于不同复杂动态场景中多移动机器人狭窄作业区域内的交通拥堵问题。
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似部分互相参见即可。
对所公开的实施例的上述说明，使本领域专业技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下，在其它实施例中实现。因此，本发明将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。
Claims (10)
- 一种智能移动机器人全局路径规划方法，其特征在于，包括：S1，确定作业全局信息，对所述作业全局的场景进行格栅化后获得全局栅格地图；S2，对所述全局栅格地图设置行驶规则以及设置特殊区域；S3，将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；S4，采用A*算法对所述全局栅格地图定义通行值；S5，根据所述通行值以及所述移动机器人的起始点和目标点，输出所述栅格地图中一系列连续的路径点坐标值。
- 如权利要求1所述智能移动机器人全局路径规划方法，其特征在于，所述特殊区域包括禁行区、右行区、抵制区、禁行线和单行线中至少一种。
- 如权利要求2所述智能移动机器人全局路径规划方法，其特征在于，所述S2，包括：通过设置所述全局栅格地图的栅格值在第一预定区域获得禁行区、右行区、抵制区、禁行线，通过限制所述全局栅格地图的栅格扩散在第二预定区域设置单行线。
- 如权利要求3所述智能移动机器人全局路径规划方法，其特征在于，所述全局栅格地图的栅格值的范围为0～255或0～1023。
- 如权利要求4所述智能移动机器人全局路径规划方法，其特征在于，在所述S5之后，还包括：通过激光传感器、多普勒雷达实时感知周围环境信息，对所述移动机器人在所述栅格地图中进行全局定位。
- 如权利要求5所述智能移动机器人全局路径规划方法，其特征在于，在所述S5之后，还包括：接收栅格值调整指令，调整所述全局栅格地图的栅格值。
- 如权利要求6所述智能移动机器人全局路径规划方法，其特征在于，在所述S5之后，还包括：S6，检测所述移动机器人当前所处栅格的通行值，设置所述移动机器人的行进速度。
- 一种智能移动机器人全局路径规划系统，其特征在于，包括：栅格地图转换模块，用于根据输入的作业全局的场景进行格栅化后，输出格栅化地图；行驶规则与特殊区域设置模块，与所述栅格地图转换模块连接，用于对所述格栅化地图设置行驶规则以及设置特殊区域；地图离散化模块，与所述栅格地图转换模块、所述行驶规则与特殊区域设置模块连接，用于将所述全局栅格地图的栅格值离散化，定义移动机器人通过的区域与障碍物的间距大于所述移动机器人的外接圆半径；A*算法路径规划模块，与所述地图离散化模块连接，接收所述移动机器人的起始点和目标点，采用A*算法对所述全局栅格地图定义通行值后，向所述移动机器人输出所述栅格地图中从所述起始点到所述目标点一系列连续的路径点坐标值。
- 如权利要求8所述智能移动机器人全局路径规划系统，其特征在于，还包括与所述地图离散化模块连接的栅格值设置模块，用于接收栅格值调整指令，调整所述全局栅格地图的栅格值。
- 如权利要求9所述智能移动机器人全局路径规划系统，其特征在于，还包括与所述A*算法路径规划模块连接的行进速度限制模块，用于根据所述移动机器人通过的当前栅格的通行值，设定所述移动机器人的行进速度。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011147139.0A CN112284393B (zh) | 2020-10-23 | 2020-10-23 | 一种智能移动机器人全局路径规划方法和系统 |
| CN202011147139.0 | 2020-10-23 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022083292A1 true WO2022083292A1 (zh) | 2022-04-28 |
Family
ID=74423730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/115501 WO2022083292A1 (zh) | 2020-10-23 | 2021-08-31 | 一种智能移动机器人全局路径规划方法和系统 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112284393B (zh) |
| WO (1) | WO2022083292A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114755373A (zh) * | 2022-06-16 | 2022-07-15 | 西安工业大学 | 一种基于多机器人编队的空气污染源预警定位方法 |
| CN115930933A (zh) * | 2022-09-20 | 2023-04-07 | 江苏海洋大学 | 一种基于集群控制的多智能体协同建图方法 |
| CN116540747A (zh) * | 2023-07-06 | 2023-08-04 | 中国科学技术大学 | 一种避停优先的移动机器人运动规划与避障决策方法 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112284393B (zh) * | 2020-10-23 | 2022-12-23 | 苏州大学 | 一种智能移动机器人全局路径规划方法和系统 |
| CN113284240B (zh) * | 2021-06-18 | 2022-05-31 | 深圳市商汤科技有限公司 | 地图构建方法及装置、电子设备和存储介质 |
| CN113485378B (zh) * | 2021-08-18 | 2024-01-16 | 昆山市工研院智能制造技术有限公司 | 基于交通规则的移动机器人路径规划方法、系统及存储介质 |
| CN114326717A (zh) * | 2021-12-13 | 2022-04-12 | 中国科学院计算技术研究所 | 一种智能农机转场与作业的融合路径规划方法及系统 |
| CN114518760B (zh) * | 2022-02-16 | 2024-06-25 | 北京航空航天大学 | 一种基于风险区管理的无人车导航方法以及系统服务器 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109059924A (zh) * | 2018-07-25 | 2018-12-21 | 齐鲁工业大学 | 基于a*算法的伴随机器人增量路径规划方法及系统 |
| CN109443364A (zh) * | 2018-11-13 | 2019-03-08 | 国网浙江宁波市鄞州区供电有限公司 | 基于a*算法的路径规划方法 |
| WO2020041817A1 (de) * | 2018-08-31 | 2020-03-05 | RobArt GmbH | Exploration eines robotereinsatzgebietes durch einen autonomen mobilen roboter |
| CN111272186A (zh) * | 2020-03-04 | 2020-06-12 | 广东博智林机器人有限公司 | 机器人路径的配置方法及装置、可读存储介质 |
| CN111538343A (zh) * | 2020-06-22 | 2020-08-14 | 天津联汇智造科技有限公司 | 一种机器人设置交通规则的系统、方法及存储介质 |
| CN111543908A (zh) * | 2020-05-15 | 2020-08-18 | 弗徕威智能机器人科技（上海）有限公司 | 一种行进路径、智能设备行进路径规划方法和装置 |
| WO2020197126A1 (ko) * | 2019-03-25 | 2020-10-01 | 주식회사 트위니 | 빅셀그리드맵을 이용한 이동체의 자세 추정 방법, 이를 구현하기 위한 프로그램이 저장된 기록매체 및 이를 구현하기 위해 매체에 저장된 컴퓨터프로그램 |
| CN112284393A (zh) * | 2020-10-23 | 2021-01-29 | 苏州大学 | 一种智能移动机器人全局路径规划方法和系统 |
-
2020
- 2020-10-23 CN CN202011147139.0A patent/CN112284393B/zh active Active
-
2021
- 2021-08-31 WO PCT/CN2021/115501 patent/WO2022083292A1/zh active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109059924A (zh) * | 2018-07-25 | 2018-12-21 | 齐鲁工业大学 | 基于a*算法的伴随机器人增量路径规划方法及系统 |
| WO2020041817A1 (de) * | 2018-08-31 | 2020-03-05 | RobArt GmbH | Exploration eines robotereinsatzgebietes durch einen autonomen mobilen roboter |
| CN109443364A (zh) * | 2018-11-13 | 2019-03-08 | 国网浙江宁波市鄞州区供电有限公司 | 基于a*算法的路径规划方法 |
| WO2020197126A1 (ko) * | 2019-03-25 | 2020-10-01 | 주식회사 트위니 | 빅셀그리드맵을 이용한 이동체의 자세 추정 방법, 이를 구현하기 위한 프로그램이 저장된 기록매체 및 이를 구현하기 위해 매체에 저장된 컴퓨터프로그램 |
| CN111272186A (zh) * | 2020-03-04 | 2020-06-12 | 广东博智林机器人有限公司 | 机器人路径的配置方法及装置、可读存储介质 |
| CN111543908A (zh) * | 2020-05-15 | 2020-08-18 | 弗徕威智能机器人科技（上海）有限公司 | 一种行进路径、智能设备行进路径规划方法和装置 |
| CN111538343A (zh) * | 2020-06-22 | 2020-08-14 | 天津联汇智造科技有限公司 | 一种机器人设置交通规则的系统、方法及存储介质 |
| CN112284393A (zh) * | 2020-10-23 | 2021-01-29 | 苏州大学 | 一种智能移动机器人全局路径规划方法和系统 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114755373A (zh) * | 2022-06-16 | 2022-07-15 | 西安工业大学 | 一种基于多机器人编队的空气污染源预警定位方法 |
| CN115930933A (zh) * | 2022-09-20 | 2023-04-07 | 江苏海洋大学 | 一种基于集群控制的多智能体协同建图方法 |
| CN116540747A (zh) * | 2023-07-06 | 2023-08-04 | 中国科学技术大学 | 一种避停优先的移动机器人运动规划与避障决策方法 |
| CN116540747B (zh) * | 2023-07-06 | 2023-10-20 | 中国科学技术大学 | 一种避停优先的移动机器人运动规划与避障决策方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112284393A (zh) | 2021-01-29 |
| CN112284393B (zh) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022083292A1 (zh) | 一种智能移动机器人全局路径规划方法和系统 | |
| US10802494B2 (en) | Method for motion planning for autonomous moving objects | |
| JP6494872B2 (ja) | 車両の運動を制御する方法、及び車両の制御システム | |
| Kuwata et al. | Motion planning for urban driving using RRT | |
| CN110333714A (zh) | 一种无人驾驶汽车路径规划方法和装置 | |
| CN113710431B (zh) | 使用基于采样的最优树的路径规划方法以及记录介质 | |
| CN106873599A (zh) | 基于蚁群算法和极坐标变换的无人自行车路径规划方法 | |
| WO2020136978A1 (ja) | 経路決定方法 | |
| WO2021037071A1 (zh) | 一种飞行控制方法及相关装置 | |
| KR20150084143A (ko) | 다양한 주행 환경 기반의 차량 자율 주행 장치 및 그 경로 계획 방법 | |
| Bonetto et al. | irotate: Active visual slam for omnidirectional robots | |
| Zhu et al. | A hierarchical deep reinforcement learning framework with high efficiency and generalization for fast and safe navigation | |
| Chen et al. | Path Planning for Autonomous Vehicle Based on a Two‐Layered Planning Model in Complex Environment | |
| CN114527753A (zh) | 人机共融的楼宇间路径规划方法、计算机装置及程序产品 | |
| WO2023147769A1 (en) | Systems, methods, and computer-readable media for spatio-temporal motion planning | |
| Kenk et al. | Human-aware Robot Navigation in Logistics Warehouses. | |
| CN114200945A (zh) | 一种移动机器人的安全控制方法 | |
| Zaki et al. | A navigation strategy for an autonomous patrol vehicle based on multi-fusion planning algorithms and multi-paradigm representation schemes | |
| Sundarraj et al. | Route planning for an autonomous robotic vehicle employing a weight-controlled particle swarm-optimized Dijkstra algorithm | |
| Kakoty et al. | Mobile robot navigation in unknown dynamic environment inspired by human pedestrian behavior | |
| CN114237237A (zh) | 一种无人驾驶汽车自主转向控制的路径优化方法 | |
| CN116795108B (zh) | 基于多源感知信号的智能无人车配送方法 | |
| Kala et al. | Multi-vehicle planning using RRT-connect | |
| Yu et al. | A time dimension-added multiple obstacles avoidance approach for unmanned surface vehicles | |
| CN115416693A (zh) | 一种基于时空走廊的自动驾驶轨迹规划方法及系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21881711 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21881711 Country of ref document: EP Kind code of ref document: A1 |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19/09/2023) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21881711 Country of ref document: EP Kind code of ref document: A1 |