CN115145261B - Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine - Google Patents
Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine Download PDFInfo
- Publication number
- CN115145261B CN115145261B CN202210360087.8A CN202210360087A CN115145261B CN 115145261 B CN115145261 B CN 115145261B CN 202210360087 A CN202210360087 A CN 202210360087A CN 115145261 B CN115145261 B CN 115145261B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- grid
- von
- pedestrians
- preference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 241000282414 Homo sapiens Species 0.000 title description 3
- 238000009826 distribution Methods 0.000 claims abstract description 50
- 230000003068 static effect Effects 0.000 claims abstract description 12
- 238000010845 search algorithm Methods 0.000 claims description 9
- 238000013179 statistical model Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 229910003460 diamond Inorganic materials 0.000 description 2
- 239000010432 diamond Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010397 one-hybrid screening Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
Abstract
The invention relates to a global path planning method and device for a mobile robot, comprising the following steps: responding to a path planning request, and acquiring pedestrian information in a target area; classifying pedestrians according to the positions of the pedestrians through a static map to obtain classification results; acquiring pedestrian information of pedestrians in each grid, and performing clustering on the moving direction of the pedestrians to obtain a plurality of clustering results; determining mixed Von-Mises distribution of each grid according to the clustering result, and determining pedestrian moving direction preference of the grids according to the mixed Von-Mises distribution; and determining the optimal global moving path of the mobile robot according to the mixed Von-Mises distribution and the pedestrian moving direction preference of each grid. The beneficial effects of the invention are as follows: the mobile robot can autonomously generate a global path conforming to the walking specification of pedestrians in the scene according to the preference of the walking direction of the pedestrians in the scene, and the influence on surrounding pedestrians and public traffic order is reduced while guiding the movement of the mobile robot.
Description
Technical Field
The invention relates to a mobile robot global path planning method and device, in particular to a mobile robot global path planning method and device which follow the pedestrian walking specification in a man-machine coexisting environment.
Background
Among the service robot autonomous intelligent technologies, the robot autonomous navigation technology is an important point of attention. In recent years, with the development of urban areas in China, the number and population of cities are remarkably increased, and service robots have a plurality of important application scenes, such as express and takeaway collection, building cleaning, file distribution, welcome reception and the like, and the application needs robots to be capable of autonomous navigation in a man-machine coexistence environment.
In order to realize autonomous navigation of a mobile robot in a man-machine coexisting environment, a global path planning is first required, i.e. a collision-free global path from a starting point of the robot to a target point is planned. In the traditional global path planning algorithm of the mobile robot, the influence of the behavior of the robot on surrounding pedestrians is not considered only for obstacle avoidance in a static environment, and the traffic jam is caused, so that the method is not suitable for navigation of the mobile robot in a man-machine coexistence scene. When a mobile robot moves in an environment where man-machine coexistence exists, the robot must be required to follow the walking specification of pedestrians in the navigation process so as to avoid causing retrograde behavior, causing traffic jam and affecting normal walking of pedestrians. The most common pedestrian walking regulations, such as in many countries, are right-to-foot by default.
Disclosure of Invention
The invention provides a global path planning method and device for a mobile robot, and aims to at least solve one of the technical problems in the prior art.
The technical scheme of the invention comprises a global path planning method of a mobile robot, which comprises the following steps:
S100, responding to a path planning request, and acquiring pedestrian information in a target area, wherein the pedestrian information comprises pedestrian positions, pedestrian speeds and pedestrian floor space radiuses;
S200, classifying pedestrians according to the positions of the pedestrians through a static map to obtain classification results, wherein the static map comprises a plurality of grids;
S300, acquiring pedestrian information of pedestrians in each grid, and performing clustering processing on the moving direction of the pedestrians to obtain a plurality of clustering results;
S400, determining mixed Von-Mises distribution of each grid according to the clustering result, and determining pedestrian movement direction preference of the grids according to the mixed Von-Mises distribution;
S500, determining the optimal global moving path of the mobile robot according to the mixed Von-Mises distribution of each grid and the pedestrian moving direction preference.
Further, the step S100 includes: and acquiring the pedestrian information of the target area in the preset time in an image acquisition or near-field acquisition mode to obtain all the pedestrian information of the target area in the preset time.
Further, the step S200 includes: and matching the pedestrian position of each pedestrian with the two-dimensional grid coordinates of the static map, and distributing pedestrian information to the corresponding grid.
Further, the step S300 includes: clustering the moving directions of the pedestrians of each grid through a clustering metric, wherein the clustering metric comprises at least one of elbow, interval statistics, contour coefficients and Canopy.
Further, the step S400 includes:
Taking the clustering results of each grid as
Determining the mixed Von-Mises distribution of the pedestrian moving direction in the grid, and obtaining by a formula:
wherein p θ, alpha, mu and kappa are respectively calculated parameters of the mixed Von-Mises distribution, M is the number of the clustering results, alpha m is a weight parameter of each clustering result and Mu m and kappa m are statistical model parameters for each distribution;
obtaining each independent Von-Mises distribution in the mixed Von-Mises distribution, and obtaining the Von-Mises distribution by a formula:
Wherein J 0 (κ) is a Bessel correction function of order 0, as
Calculating maximum likelihood estimation to obtain statistical model parameters mu and kappa, and determining a weight parameter alpha m when combining each independent Von-Mises distribution into the mixed Von-Mises distribution, wherein the calculation mode is as follows:
Wherein P m is the data quantity of the clustering result, and P is the sum of the data quantity of the clustering result in all grids;
A pedestrian walking preference direction map is generated.
Further, the step S400 includes:
The number likelihood function of each independent Von-Mises distribution is
The statistical model parameters mu and kappa can be obtained by calculating maximum likelihood estimates by
(μ*,κ*)＝argmaxL(μ,κ；D)。
Further, the step S500 includes:
Taking the grid where the mobile robot is located as a starting point, and taking the cost of each grid movement as:
g′(s)＝g(s)+l(s,θ)
Where g(s) is the moving cost of the mobile robot moving one grid, l (s, θ) is the moving cost change due to the influence of the pedestrian moving direction preference, and l (s, θ) is obtained by the following formula:
l(s,θ)＝1-argmaxm∈MVM(θu;μm,κm)
The optimal path is selected by a graph search algorithm based on the pedestrian movement direction preference.
Further, the step S500 includes: and executing iterative calculation of all grids in the target area according to the pedestrian movement direction preference in each grid to obtain a minimum consumption global path conforming to the pedestrian movement preference direction.
The invention also relates to a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, carry out the above-mentioned method.
The technical scheme of the invention also relates to a computer device, which comprises: an image acquisition device and the computer readable storage medium.
The beneficial effects of the invention are as follows: the mobile robot can autonomously generate a global path conforming to the walking specification of pedestrians in the scene according to the preference of the walking direction of the pedestrians in the scene, and the influence on surrounding pedestrians and public traffic order is reduced while guiding the movement of the mobile robot.
Drawings
Fig. 1 is a diagram of a pedestrian walking preference map and a final planned global path according to an embodiment of the present invention.
Fig. 2 is a graph of pedestrian movement direction statistics and clusters for one of the grids according to an embodiment of the present invention.
FIG. 3 is a graph of an optimal cluster number calculation for one of the grids according to an embodiment of the present invention.
Fig. 4a and 4b are schematic diagrams of the mixed Von-Mises distribution and pedestrian movement direction preference of one of the grids according to the embodiment of the present invention, respectively.
Fig. 5 is a schematic diagram of a cost calculation of a conventional graph search algorithm.
FIG. 6 is a schematic diagram of a cost calculation of the graph search algorithm according to an embodiment of the present invention.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present invention.
Referring to fig. 1 to 6, in some embodiments, the present invention discloses a mobile robot global path planning method following a pedestrian walking specification in an environment where man-machine coexistence, the method comprising the steps of:
And S100, responding to the path planning request, and acquiring pedestrian information in the target area, wherein the pedestrian information comprises the pedestrian position, the pedestrian speed and the pedestrian floor area radius.
And S200, classifying pedestrians according to positions of the pedestrians through a static map to obtain classification results, wherein the static map comprises a plurality of grids.
S300, pedestrian information of pedestrians in each grid is obtained, clustering processing is carried out on the moving direction of the pedestrians, and a plurality of clustering results are obtained.
S400, determining mixed Von-Mises distribution of each grid according to the clustering result, and determining pedestrian movement direction preference of the grids according to the mixed Von-Mises distribution.
S500, determining the optimal global moving path of the mobile robot according to the mixed Von-Mises distribution and pedestrian moving direction preference of each grid.
For a further embodiment of step S100
Acquiring pedestrian information of a target area within a preset time in an image acquisition or near-field acquisition mode, acquiring the pedestrian information through equipment such as a camera device or a sensor arranged on a robot, acquiring the pedestrian information through the camera device or the sensor arranged on the target area, and determining the position, the speed and the radius of the occupied area of the pedestrian through space positioning after acquiring new pedestrian information, so as to obtain all the pedestrian information of the target area within the preset time;
Referring to fig. 1, in order to count pedestrian flow direction preference in an area, first, movement information of pedestrians in the area needs to be collected. And collecting pedestrian information of a period of time in the area by a monitoring camera or a mobile robot, and obtaining each piece of pedestrian information of the whole area in the period of time by a pedestrian detection module. The pedestrian information includes the position, speed, and radius of the floor space, i.e., the pedestrian information is denoted (p x,py,pv,pθ,pb)T. Data is assigned to the corresponding grid based on the pedestrian position information. In this figure, the grid size is 1 square meter. For example, a piece of pedestrian information is (2.2,3..31,. 0,0.30.4) T, which is assigned to the grid with the lower left corner coordinates (asterisk pattern) of (2.0, 3.0), "EA" and "EAH" in fig. 1 respectively indicate the possible directions of movement of the pedestrian.
For a further embodiment of step S200
Wherein, step S200 includes: and matching the pedestrian position of each pedestrian with the two-dimensional grid coordinates of the static map, and distributing pedestrian information to the corresponding grid.
Referring to the embodiment of fig. 1, the spatial position of the pedestrian is mapped to a two-dimensional occupied grid map of a static environment, the position of the pedestrian on the grid map is determined, and the position distribution of the pedestrian is completed.
For a further embodiment of step S300
Wherein, step S300 includes: clustering the moving directions of the pedestrians of each grid through a clustering metric, wherein the clustering metric comprises at least one of elbow, interval statistics, contour coefficients and Canopy.
In some embodiments, based on pedestrian information in each grid, a preference of the direction of movement of pedestrians in the grid needs to be determined. Since pedestrians can have multiple walking directions at a certain position, such as at crossroads, pedestrians can walk to four crossroads, the pedestrian information in each grid needs to be clustered by using a K-means clustering method. But the number of clusters in the grid is not a fixed value and therefore the number of clusters needs to be determined.
Specifically, the moving direction of K pedestrians in the gridThe cluster metric is used to select the most suitable cluster. Common metrics include elbow, interval statistics, contour coefficients or Canopy, etc. Taking the circled grid of FIG. 1 as an example, each line of FIG. 2 represents a pedestrian movement direction/>The grid contains the moving directions of K pedestrians. As shown in fig. 3, the optimum number of clusters is determined by taking the elbow metric as an example. The metric is used to determine the number of clusters by minimizing the square error between the samples and the center point, and finding a distortion critical point based on the error. In fig. 3, the distortion critical point can be seen at cluster number 2 based on the elbow metric values at different cluster numbers. Therefore, the pedestrian moving direction in fig. 2 is divided into two clusters, and the two clusters C1 and C2 can be obtained by clustering the data based on the K-means clustering method.
For a further embodiment of step S400
Obtaining mixed Von-Mises distribution in each grid for a plurality of clusters in each grid, and generating a pedestrian walking preference direction map;
From the multiple clusters in the grid, a hybrid Von-Mises distribution of pedestrian movement directions in the grid can be obtained. A mixed Von-Mises distribution can be expressed as
Wherein p θ, α, μ, κ are the calculated parameters of the mixed Von-Mises distribution, M is the number of clusters, α m is the weight parameter of each cluster andMu m and kappa m are statistical model parameters for each distribution. In the mixed Von-Mises distribution, each Von-Mises distribution is independent of the others and can be expressed as
Where J 0 (κ) is a Bessel correction function of order 0, and can be expressed as
Thus, based on the clustering of the data in step S300, each cluster can be built as an independent Von-Mises distribution, with multiple clusters forming a mixed Von-Mises distribution.
Specifically, for a Von-Mises distribution, the statistical model parameters μ and κ can be obtained by maximum likelihood estimation. First, the log likelihood function of equation 1.2 is
The statistical model parameters mu and kappa can be obtained by calculating maximum likelihood estimates
(μ*,κ*)＝argmaxL(μ,κ；D) (1.5)
Then, when multiple independent Von-Mises distributions are combined into one hybrid Von-Mises distribution, the weight parameter α m of each independent distribution needs to be calculated. Because each distribution is independent, the weight parameter can be obtained by the ratio of the number of data in the cluster to the number of all data in the grid
Where P m is the number of data in the cluster and P is the sum of the number of data in all clusters. FIG. 4 is a schematic diagram of the mixed Von-Mises distribution obtained by processing the data in FIG. 2, wherein FIG. 4a is the mixed Von-Mises distribution and FIG. 4b is the directional preference of pedestrian movement in each grid. A directional preference of pedestrian movement within each grid can be obtained.
For a further embodiment of step S500
The step S500 specifically includes: improving a mobile cost function in a graph search algorithm according to the mixed Von-Mises distribution in each grid;
Conventional graph search algorithms such as Astar, hybrid Astar, etc., plan a shortest collision-free path toward the start to the end, but the path does not take into account the impact of robot behavior on pedestrian traffic. The traditional concrete method for searching the shortest path by the mixed Astar algorithm comprises the following steps of
F(s)＝G(s)+H(s) (1.7)
Wherein F(s) is the cost of selecting the whole estimated path of a certain grid, G(s) is the cost from the starting point to the selected grid, and H(s) is the cost from the selected grid to the end point.
As shown in fig. 5, in the conventional graph search algorithm, a path from a circle to a diamond is planned, and only four directions of movement from top to bottom, left to right can be selected, G(s) is the cost from the circle to the triangle, H(s) is the cost from the triangle to the diamond, the cost consumption of each movement is G(s) =1, and finally, a path with the smallest F(s) needs to be found, namely, the optimal global path.
As shown in FIG. 6, taking the grid at the origin with a preferred direction as an example, the cost of moving each grid is rewritten from 1 to
g′(s)＝g(s)+l(s,θ) (1.8)
Where l (s, θ) is the change in the cost of movement due to the influence of the pedestrian's preferred direction, and can be expressed as
l(s,θ)＝1-argmaxm∈MVM(θu;μm,κm) (1.9)
Based on equation 1.9, the cost will be less when moving along the pedestrian preference direction in the grid. As shown in fig. 6, the cost is less when moving along the pedestrian preference direction in the grid, so that the graph search algorithm can select the optimal path based on the pedestrian preference direction.
S6: the least costly global path is calculated from the mobile cost function in the improved graph search algorithm.
And sequentially carrying out iterative computation on the pedestrian preference directions in each grid to finally obtain a global path conforming to the pedestrian movement preference directions. As shown in fig. 1, taking the mixed Astar algorithm as an example, the global path obtained by searching the conventional mixed Astar algorithm (HA) is shorter, but the global path moves against the people stream in a plurality of places, so that the traffic order is easily affected, and the global path does not conform to the common movement habit of human beings. The improved hybrid Astar algorithm based on the people stream preference map enables planning a global path of movement along the people stream. In this way, the robot can be guided to be fused into the stream of people, and normal walking of pedestrians can not be affected.
The mobile robot global path planning method enables the mobile robot to autonomously generate the global path which accords with the walking specification of pedestrians in the scene according to the preference of the walking direction of the pedestrians in the scene, and reduces the influence on surrounding pedestrians and public traffic order while guiding the movement of the mobile robot.
It should be appreciated that the method steps in embodiments of the present invention may be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in non-transitory computer-readable memory. The method may use standard programming techniques. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes (or variations and/or combinations thereof) described herein may be performed under control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications), by hardware, or combinations thereof, collectively executing on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable computing platform, including, but not limited to, a personal computer, mini-computer, mainframe, workstation, network or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and so forth. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and/or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, which when read by a computer, is operable to configure and operate the computer to perform the processes described herein. Further, the machine readable code, or portions thereof, may be transmitted over a wired or wireless network. When such media includes instructions or programs that, in conjunction with a microprocessor or other data processor, implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media. The invention may also include the computer itself when programmed according to the methods and techniques of the present invention.
The computer program can be applied to the input data to perform the functions described herein, thereby converting the input data to generate output data that is stored to the non-volatile memory. The output information may also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.
The present invention is not limited to the above embodiments, but can be modified, equivalent, improved, etc. by the same means to achieve the technical effects of the present invention, which are included in the spirit and principle of the present invention. Various modifications and variations are possible in the technical solution and/or in the embodiments within the scope of the invention.
Claims (7)
1. A method for global path planning for a mobile robot, the method comprising the steps of:
S100, responding to a path planning request, and acquiring pedestrian information in a target area, wherein the pedestrian information comprises pedestrian positions, pedestrian speeds and pedestrian floor space radiuses;
S200, classifying pedestrians according to the positions of the pedestrians through a static map to obtain classification results, wherein the static map comprises a plurality of grids;
S300, acquiring pedestrian information of pedestrians in each grid, and performing clustering processing on the moving direction of the pedestrians to obtain a plurality of clustering results;
S400, determining mixed Von-Mises distribution of each grid according to the clustering result, and determining pedestrian movement direction preference of the grids according to the mixed Von-Mises distribution;
Wherein, the clustering results of each grid are taken as
Determining the mixed Von-Mises distribution of the pedestrian moving direction in the grid, and obtaining by a formula:
wherein p θ, alpha, mu and kappa are respectively calculated parameters of the mixed Von-Mises distribution, M is the number of the clustering results, alpha m is a weight parameter of each clustering result and Mu m and kappa m are statistical model parameters for each distribution;
obtaining each independent Von-Mises distribution in the mixed Von-Mises distribution, and obtaining the Von-Mises distribution by a formula:
Wherein J 0 (κ) is a Bessel correction function of order 0, as
The statistical model parameters mu and kappa are obtained through calculation of maximum likelihood estimation, and the weight parameters alpha m are determined when each independent Von-Mises distribution is combined into the mixed Von-Mises distribution, wherein the calculation mode is as follows:
Wherein P m is the data quantity of the clustering result, and P is the sum of the data quantity of the clustering result in all grids;
Generating a pedestrian walking preference direction map;
S500, determining an optimal global moving path of the mobile robot according to the mixed Von-Mises distribution of each grid and the pedestrian moving direction preference, wherein,
Taking the grid where the mobile robot is located as a starting point, and taking the cost of each grid movement as:
g′(s)＝g(s)+l(s,θ)
Where g(s) is the moving cost of the mobile robot moving one grid, l (s, θ) is the moving cost change due to the influence of the pedestrian moving direction preference, and l (s, θ) is obtained by the following formula:
l(s,θ)＝1-arg maxm∈MVM(θu;μm,κm)
Planning a global path capable of moving along the pedestrian preference direction in the grid based on the pedestrian movement direction preference through a graph search algorithm;
And performing iterative computation of all grids in the target area according to the pedestrian movement preference direction in each grid to obtain a minimum consumption global path conforming to the pedestrian movement preference direction.
2. The method according to claim 1, wherein the step S100 comprises:
And acquiring the pedestrian information of the target area in the preset time in an image acquisition or near-field acquisition mode to obtain all the pedestrian information of the target area in the preset time.
3. The method according to claim 1, wherein the step S200 includes:
And matching the pedestrian position of each pedestrian with the two-dimensional grid coordinates of the static map, and distributing pedestrian information to the corresponding grid.
4. The method according to claim 1, wherein the step S300 includes:
Clustering the moving directions of the pedestrians of each grid through a clustering metric, wherein the clustering metric comprises at least one of elbow, interval statistics, contour coefficients and Canopy.
5. The method according to claim 1, wherein the step S400 includes:
The number likelihood function of each independent Von-Mises distribution is
Statistical model parameters μ and κ can be obtained by computing maximum likelihood estimates in such a way that (μ *,κ*) =argmax L (μ, κ; D).
6. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, implement the method of any of claims 1 to 5.
7. A computer apparatus, comprising:
An image acquisition device;
The computer-readable storage medium of claim 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210360087.8A CN115145261B (en) | 2022-04-07 | 2022-04-07 | Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine |
| PCT/CN2022/128602 WO2023193424A1 (en) | 2022-04-07 | 2022-10-31 | Global navigation method for mobile robot in man-machine coexistence environment following pedestrian norm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210360087.8A CN115145261B (en) | 2022-04-07 | 2022-04-07 | Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115145261A CN115145261A (en) | 2022-10-04 |
| CN115145261B true CN115145261B (en) | 2024-04-26 |
Family
ID=83406378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210360087.8A Active CN115145261B (en) | 2022-04-07 | 2022-04-07 | Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115145261B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023193424A1 (en) * | 2022-04-07 | 2023-10-12 | 哈尔滨工业大学（深圳） | Global navigation method for mobile robot in man-machine coexistence environment following pedestrian norm |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071506A (en) * | 2006-01-25 | 2007-11-14 | 美国西门子医疗解决公司 | System and method for local pulmonary structure classification for computer-aided nodule detection |
| KR20080029239A (en) * | 2006-09-28 | 2008-04-03 | 한국전자통신연구원 | Apparatus and method for building environment map according to optimum path setting in autonomous mobile robot |
| EP2261856A2 (en) * | 2009-06-08 | 2010-12-15 | Siemens Aktiengesellschaft | Method for modelling and calculation of the uncertainty of a pose of an object in space |
| CN103558856A (en) * | 2013-11-21 | 2014-02-05 | 东南大学 | Service mobile robot navigation method in dynamic environment |
| CN105527964A (en) * | 2015-12-28 | 2016-04-27 | 桂林电子科技大学 | Robot path planning method |
| EP3264212A1 (en) * | 2016-06-30 | 2018-01-03 | Advanced Digital Broadcast S.A. | System and method for determining an energy-efficient path of an autonomous device |
| CN108353248A (en) * | 2015-08-27 | 2018-07-31 | Fzc哥络普斯 | Method and apparatus for positioning mobile device |
| WO2019043171A1 (en) * | 2017-09-01 | 2019-03-07 | RobArt GmbH | Movement planning for autonomous mobile robots |
| CN109542117A (en) * | 2018-10-19 | 2019-03-29 | 哈尔滨工业大学（威海） | Based on the submarine navigation device Rolling Planning algorithm for improving RRT |
| CN110039540A (en) * | 2019-05-27 | 2019-07-23 | 聊城大学 | A kind of service robot paths planning method that multiple target optimizes simultaneously |
| CN110097171A (en) * | 2019-06-19 | 2019-08-06 | 吉林大学 | A kind of activity trajectory localization method and system based on scorpion micro-vibration Location Mechanism |
| CN110285813A (en) * | 2019-07-01 | 2019-09-27 | 东南大学 | A kind of man-machine co-melting navigation device of indoor mobile robot and method |
| CN111461447A (en) * | 2020-04-09 | 2020-07-28 | 南方科技大学 | Path planning method and device, electronic equipment and storage medium |
| EP3706034A1 (en) * | 2019-03-06 | 2020-09-09 | Robert Bosch GmbH | Movement prediction of pedestrians useful for autonomous driving |
| WO2021228040A1 (en) * | 2020-05-09 | 2021-11-18 | 苏州宝时得电动工具有限公司 | Path planning method and self-moving device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8866924B2 (en) * | 2011-10-28 | 2014-10-21 | Hewlett-Packard Development Company, L.P. | Local image feature descriptors according to circular distribution information |
| JP6859765B2 (en) * | 2017-03-13 | 2021-04-14 | 株式会社リコー | Image processing equipment, image processing methods and programs |
-
2022
- 2022-04-07 CN CN202210360087.8A patent/CN115145261B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071506A (en) * | 2006-01-25 | 2007-11-14 | 美国西门子医疗解决公司 | System and method for local pulmonary structure classification for computer-aided nodule detection |
| KR20080029239A (en) * | 2006-09-28 | 2008-04-03 | 한국전자통신연구원 | Apparatus and method for building environment map according to optimum path setting in autonomous mobile robot |
| EP2261856A2 (en) * | 2009-06-08 | 2010-12-15 | Siemens Aktiengesellschaft | Method for modelling and calculation of the uncertainty of a pose of an object in space |
| CN103558856A (en) * | 2013-11-21 | 2014-02-05 | 东南大学 | Service mobile robot navigation method in dynamic environment |
| CN108353248A (en) * | 2015-08-27 | 2018-07-31 | Fzc哥络普斯 | Method and apparatus for positioning mobile device |
| CN105527964A (en) * | 2015-12-28 | 2016-04-27 | 桂林电子科技大学 | Robot path planning method |
| EP3264212A1 (en) * | 2016-06-30 | 2018-01-03 | Advanced Digital Broadcast S.A. | System and method for determining an energy-efficient path of an autonomous device |
| WO2019043171A1 (en) * | 2017-09-01 | 2019-03-07 | RobArt GmbH | Movement planning for autonomous mobile robots |
| CN109542117A (en) * | 2018-10-19 | 2019-03-29 | 哈尔滨工业大学（威海） | Based on the submarine navigation device Rolling Planning algorithm for improving RRT |
| EP3706034A1 (en) * | 2019-03-06 | 2020-09-09 | Robert Bosch GmbH | Movement prediction of pedestrians useful for autonomous driving |
| CN110039540A (en) * | 2019-05-27 | 2019-07-23 | 聊城大学 | A kind of service robot paths planning method that multiple target optimizes simultaneously |
| CN110097171A (en) * | 2019-06-19 | 2019-08-06 | 吉林大学 | A kind of activity trajectory localization method and system based on scorpion micro-vibration Location Mechanism |
| CN110285813A (en) * | 2019-07-01 | 2019-09-27 | 东南大学 | A kind of man-machine co-melting navigation device of indoor mobile robot and method |
| CN111461447A (en) * | 2020-04-09 | 2020-07-28 | 南方科技大学 | Path planning method and device, electronic equipment and storage medium |
| WO2021228040A1 (en) * | 2020-05-09 | 2021-11-18 | 苏州宝时得电动工具有限公司 | Path planning method and self-moving device |
Non-Patent Citations (9)
| Title |
|---|
| "测量中方向数据的研究";陶庭叶;中国优秀博硕士学位论文全文数据库 (硕士)基础科学辑(第4期);正文第4, 10-16, 33页 * |
| 一种有限区域运动目标分布模型及计算;陈建勇;熊雄;张丹;;海军航空工程学院学报;20100520(第03期);295-298 * |
| 基于概率栅格地图的移动机器人可定位性估计;王炜;陈卫东;王勇;;机器人;20120715(第04期);485-491+512 * |
| 王耀兵等.空间机器人.北京理工大学出版社,2018,50-53. * |
| 移动机器人运动规划稠密行人行人轨迹预测;陈雨景;万方;20221102;全文 * |
| 自适应偏好半径划分区域的多目标进化方法;王帅发;郑金华;胡建杰;邹娟;喻果;;软件学报;20171015(第10期);2704-2721 * |
| 预测行人运动的服务机器人POMDP导航;钱堃, 马旭东, 戴先中等;机器人;20101231;第32卷(第1期);18-24+33 * |
| 颜虹.中华医学百科全书（公共卫生学·卫生统计学）.中国协和医科大学出版社,107. * |
| 颜虹.中华医学百科全书（公共卫生学·卫生统计学）.中国协和医科大学出版社,2019,107. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115145261A (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3639241B1 (en) | Voxel based ground plane estimation and object segmentation | |
| KR102198724B1 (en) | Method and apparatus for processing point cloud data | |
| Prakash et al. | Multi-modal fusion transformer for end-to-end autonomous driving | |
| CN111523643B (en) | Track prediction method, device, equipment and storage medium | |
| EP3497405B1 (en) | System and method for precision localization and mapping | |
| CN107831765B (en) | Positioning method, device, equipment and storage medium | |
| CN111771141B (en) | LIDAR positioning for solution inference using 3D CNN network in autonomous vehicles | |
| CN111971574B (en) | Deep learning based feature extraction for LIDAR localization of autonomous vehicles | |
| CN111771135B (en) | LIDAR positioning using RNN and LSTM for time smoothing in autonomous vehicles | |
| CN113168717B (en) | Point cloud matching method and device, navigation method and equipment, positioning method and laser radar | |
| CN110531749A (en) | Determine the driving path for avoiding the automatic Pilot of moving obstacle | |
| CN112740268B (en) | Target detection method and device | |
| TW201732739A (en) | Object-focused active three-dimensional reconstruction | |
| US11348276B2 (en) | Mobile robot control method | |
| US20230343222A1 (en) | System for sparsely representing and storing geographic and map data | |
| CN115145261B (en) | Global path planning method of mobile robot conforming to pedestrian specification under coexistence of human and machine | |
| CN113191297A (en) | Pavement identification method and device and electronic equipment | |
| CN112084853B (en) | Footprint prediction method, footprint prediction device and humanoid robot | |
| CN114179788A (en) | Automatic parking method, system, computer readable storage medium and vehicle terminal | |
| CN114343490B (en) | Robot cleaning method, robot, and storage medium | |
| WO2023193424A1 (en) | Global navigation method for mobile robot in man-machine coexistence environment following pedestrian norm | |
| CN112907625A (en) | Target following method and system applied to four-footed bionic robot | |
| CN114740849B (en) | Mobile robot autonomous navigation method and device based on pedestrian walking decision rule | |
| Martinez et al. | Map-based lane identification and prediction for autonomous vehicles | |
| JP2020027443A (en) | Autonomous mobile apparatus, soil detection method for lens of autonomous mobile device and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |