CN111103801B - Mobile robot repositioning method based on genetic algorithm and mobile robot - Google Patents
Mobile robot repositioning method based on genetic algorithm and mobile robot Download PDFInfo
- Publication number
- CN111103801B CN111103801B CN201911404486.4A CN201911404486A CN111103801B CN 111103801 B CN111103801 B CN 111103801B CN 201911404486 A CN201911404486 A CN 201911404486A CN 111103801 B CN111103801 B CN 111103801B
- Authority
- CN
- China
- Prior art keywords
- individual
- mobile robot
- optimal
- probability
- fitness
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention is suitable for the technical field of relocation, and provides a mobile robot positioning method based on a genetic algorithm and a mobile robot, comprising the following steps: s1, loading a global map, and taking the idle area as an effective area; s2, initializing a population; s3, calculating the fitness of the initial individual based on the likelihood value of the nearest obstacle distance; s4, selecting the optimal individual from the initialized individuals; s5, adding one to the iteration number, and performing iteration operation, namely sequentially performing selection, intersection, variation and optimal particle updating operation; s6, detecting whether the iteration number reaches the set iteration number, if so, outputting the current optimal individual, decoding the floating point number code of the optimal individual, acquiring the pose, namely the optimal pose, of the mobile robot in the global map based on the optimal pose, and if not, executing the step S5. The robustness and the efficiency of the relocation system are improved through the excellent global search capability of the genetic algorithm.
Description
Technical Field
The invention belongs to the technical field of robot positioning, and provides a mobile robot repositioning method based on a genetic algorithm and a mobile robot.
Background
Positioning is one of the most basic problems in the research field of mobile robots, has become the basis of the autonomous ability of mobile robots to realize navigation, motion planning and the like, and is the determination of the pose of the mobile robot in the environment by means of sensors. In the fields of automatic factories, intelligent warehouse logistics, home service and the like, when a mobile robot is restarted or suddenly tied to other positions, the robot cannot position the pose of the mobile robot, and the current position of the robot needs to be repositioned at the moment. In the existing solutions for robot relocation, some robots are positioned by arranging auxiliary equipment in the environment, which increases the cost and has more limitations; some positioning methods adopting particle filtering have better performance in solving the problems of global positioning and robot 'kidnapping', but the method also has the problems of low convergence speed and easy degradation of the algorithm.
Disclosure of Invention
The embodiment of the invention provides a mobile robot repositioning method based on a genetic algorithm, which improves the robustness and the high efficiency of a positioning system through the excellent global search capability of the genetic algorithm and does not need to arrange auxiliary equipment in the environment.
The invention is realized in such a way that a mobile robot positioning method based on genetic algorithm specifically comprises the following steps:
s1, loading a global map, and taking the idle area as an effective area;
s2, initializing a population, namely setting the size, the iteration times, the cross probability and the variation probability of the population;
s3, calculating the fitness of the initial individual based on the likelihood value of the nearest obstacle distance;
s4, taking the initial individual with the maximum initial fitness as the optimal individual in the initialized individuals;
s5, adding one to the iteration number, and performing iteration operation, namely sequentially selecting, crossing, mutating and updating the optimal particles;
s6, selecting: calculating the selection probability of individuals, selecting the probability by adopting a roulette selection method, and selecting two individuals from a population as a father party and a mother party;
s7, crossing: detecting whether the randomly generated probability value is greater than the crossing probability, if so, randomly exchanging floating point codes of a father party and a mother party at the crossing point to generate a new individual;
s8, mutation: detecting whether the random generation probability is smaller than the mutation probability, if so, performing mutation operation, wherein the mutation operation is as follows: randomly selecting variant individuals, increasing or decreasing a small random number for the floating point number codes of the variant individuals, and generating new individuals;
s9, updating the optimal individual: calculating the fitness value of each individual, comparing the maximum fitness value in the iteration with the fitness value of the optimal individual of the previous iteration, and taking the individual with a large fitness value as the current optimal individual;
s10, detecting whether the current iteration number reaches the set iteration number, if so, outputting the current optimal individual, decoding the floating point number code of the optimal individual, acquiring the pose, namely the optimal pose, of the mobile robot in the global map based on the optimal pose, and if not, executing the step S5.
Further, the calculation formula of the individual fitness is specifically as follows:
wherein F (n) represents the fitness of the nth individual in the current laser radar frame, dist represents the distance between the individual and the nearest obstacle, M represents the number of the individuals in the current laser radar frame data, (x, y) represents the coordinate of the nearest obstacle in the map, and (x, y) represents the coordinate of the nearest obstacle in the mapk,yk) Representing the coordinates of the individual in a map, q (n) representing the individual fitness value of the nth individual, zhit、zranddomAnd zmaxRespectively representing different parts of the mixed weight of the ranging error, respectively representing measurement noise, unexplained random measurements and measurement failures, sigmahitTo measure the standard deviation of the noise.
The present invention is achieved in such a way that a mobile robot includes: the laser radar is connected with the processor, the processor is connected with the memory,
the laser radar scans environment information, sends the scanned environment information to a processor, the processor performs relocation of the mobile robot based on the mobile robot relocation method based on genetic algorithm as claimed in claim 1 or claim 2, and a global map is stored in the memory.
The invention realizes the relocation of the mobile robot based on the genetic algorithm, improves the robustness and the high efficiency of the positioning system through the excellent global search capability of the genetic algorithm, and can realize the relocation of the mobile robot without arranging auxiliary equipment in a positioning area.
Drawings
Fig. 1 is a flowchart of a mobile robot repositioning method based on a genetic algorithm.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention aims to solve the problem of positioning failure caused by slipping drift, artificial movement, restart or shutdown of the robot, and realize high-precision positioning of the mobile robot.
Fig. 1 is a flowchart of a mobile robot repositioning method based on a genetic algorithm, which specifically includes the following steps:
s1, initializing a map: loading a global map, and taking an idle area as an effective area;
the global map consists of an idle area, an occupied area and an unknown area, wherein the occupied area is an area where the laser radar detects that the laser radar has obstacles, the idle area is an area where the laser radar detects that the laser radar does not have the obstacles, and the unknown area is an area which cannot be detected by the laser radar;
s2, initializing population: setting the size of a population, iteration times, cross probability and variation probability;
s3, calculating individual fitness: selecting the likelihood value of the distance to the nearest obstacle as a fitness function of the individual, wherein the fitness function is expressed as follows:
wherein F (n) represents the fitness of the nth individual in the current laser radar frame, dist represents the distance between the individual and the nearest obstacle, M represents the number of the individuals in the current laser radar frame data, (x, y) represents the coordinate of the nearest obstacle in the map, and (x, y) represents the coordinate of the nearest obstacle in the mapk,yk) Representing the coordinates of the individual in a map, q (n) representing the individual fitness value of the nth individual, zhit、zranddomAnd zmaxRespectively representing different parts of the mixed weight of the ranging error, respectively representing measurement noise, unexplained random measurements and measurement failures, sigmahitTo measure the standard deviation of the noise.
S4, selecting the optimal individual from the particles: and taking the initial individual with the maximum fitness as the optimal individual in the initialized individuals.
And S5, adding one to the iteration number, and performing iterative calculation, namely selecting, crossing, mutating and updating the optimal particle operation.
S6, selection: calculating the selection probability of each individual, adopting a roulette selection method to perform probability selection according to the principle that the higher the fitness is and the higher the selection probability is, selecting two individuals from a population as a father party and a mother party, wherein the father party and the mother party are used for breeding offspring, and the probability of each individual being selected is as follows:
wherein n represents the size of the population, fiIndicating the fitness of the ith individual.
S7, crossing: detecting whether the randomly generated probability value is larger than the crossing probability, if so, exchanging floating point codes of a father party and a mother party at the crossing point randomly to generate a new individual, and if not, not performing crossing operation, and encoding the individual pose to form a floating point code of the individual;
in the embodiment of the invention, the probability generated randomly based on the random function is called the random generation probability, and the data bits with the same floating point code numerical value are the intersection point of two floating point codes.
S8, mutation: detecting whether the random generation probability is smaller than the mutation probability, if so, performing mutation operation, and if not, performing mutation operation, wherein the mutation operation specifically comprises the following steps: and randomly selecting variant individuals, increasing or decreasing a small random number for encoding floating point numbers of the variant individuals, and generating new individuals.
S9, updating the optimal individual: calculating individual fitness of each individual, comparing the maximum fitness value in the iteration with the fitness value of the optimal individual of the previous iteration, and taking the individual with the large fitness value as the current best individual;
s10, detecting whether the iteration number reaches the set iteration number, if so, outputting the current optimal individual, decoding the floating point number code of the optimal individual, acquiring the pose, namely the optimal pose, of the mobile robot in the global map based on the optimal pose, and if not, executing the step S5.
The present invention also provides a mobile robot including: the method comprises the following steps that a laser radar is connected with a processor, the processor is connected with a memory, the laser radar scans environment information and sends the scanned environment information to the processor, the processor performs relocation of the mobile robot based on the mobile robot relocation method based on the genetic algorithm according to claim 1 or claim 2, and a global map is stored in the memory.
The invention realizes the relocation of the mobile robot based on the genetic algorithm, improves the robustness and the high efficiency of the positioning system through the excellent global search capability of the genetic algorithm, and can realize the relocation of the mobile robot without arranging auxiliary equipment in a positioning area.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (2)
1. A mobile robot relocation method based on genetic algorithm is characterized by specifically comprising the following steps:
s1, loading a global map, and taking the idle area as an effective area;
s2, initializing a population, namely setting the size, the iteration times, the cross probability and the variation probability of the population;
s3, calculating the fitness of the initial individual based on the likelihood value of the nearest obstacle distance;
s4, taking the initial individual with the maximum initial fitness as the optimal individual in the initialized individuals;
s5, adding one to the iteration number, and performing iteration operation, namely sequentially selecting, crossing, mutating and updating the optimal particles;
s6, selecting: calculating the selection probability of individuals, selecting the probability by adopting a roulette selection method, and selecting two individuals from a population as a father party and a mother party;
s7, crossing: detecting whether the randomly generated probability value is greater than the crossing probability, if so, randomly exchanging floating point codes of a father party and a mother party at the crossing point to generate a new individual;
s8, mutation: detecting whether the random generation probability is smaller than the mutation probability, if so, performing mutation operation, wherein the mutation operation is as follows: randomly selecting variant individuals, increasing or decreasing a small random number for the floating point number codes of the variant individuals, and generating new individuals;
s9, updating the optimal individual: calculating the fitness value of each individual, comparing the maximum fitness value in the iteration with the fitness value of the optimal individual of the previous iteration, and taking the individual with a large fitness value as the current optimal individual;
s10, detecting whether the iteration number reaches the set iteration number, if so, outputting the current optimal individual, decoding the floating point number code of the optimal individual, acquiring the pose, namely the optimal pose, acquiring the pose of the mobile robot in the global map based on the optimal pose, otherwise, executing the step S5;
the calculation formula of the individual fitness is as follows:
wherein F (n) represents the fitness of the nth individual in the current laser radar frame, dist represents the distance between the individual and the nearest obstacle, and M represents the current laser radarUp to the number of individuals in the frame data, (x, y) represents the coordinates of the nearest obstacle in the map, (x)k,yk) Representing the coordinates of the individual in a map, q (n) representing the individual fitness value of the nth individual, zhit、zranddomAnd zmaxRespectively representing different parts of the mixed weight of the ranging error, respectively representing measurement noise, unexplained random measurements and measurement failures, sigmahitTo measure the standard deviation of the noise.
2. A mobile robot, characterized in that the mobile robot comprises: the laser radar is connected with the processor, the processor is connected with the memory,
the laser radar scans environment information and sends the scanned environment information to the processor, the processor performs relocation of the mobile robot based on the mobile robot relocation method based on genetic algorithm as claimed in claim 1, and the memory stores a global map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404486.4A CN111103801B (en) | 2019-12-31 | 2019-12-31 | Mobile robot repositioning method based on genetic algorithm and mobile robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404486.4A CN111103801B (en) | 2019-12-31 | 2019-12-31 | Mobile robot repositioning method based on genetic algorithm and mobile robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111103801A CN111103801A (en) | 2020-05-05 |
| CN111103801B true CN111103801B (en) | 2022-05-17 |
Family
ID=70424707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911404486.4A Active CN111103801B (en) | 2019-12-31 | 2019-12-31 | Mobile robot repositioning method based on genetic algorithm and mobile robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111103801B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914068A (en) * | 2013-01-07 | 2014-07-09 | 中国人民解放军第二炮兵工程大学 | Service robot autonomous navigation method based on raster maps |
| CN105737820A (en) * | 2016-04-05 | 2016-07-06 | 芜湖哈特机器人产业技术研究院有限公司 | Positioning and navigation method for indoor robot |
| CN107246873A (en) * | 2017-07-03 | 2017-10-13 | 哈尔滨工程大学 | A kind of method of the mobile robot simultaneous localization and mapping based on improved particle filter |
| CN107368076A (en) * | 2017-07-31 | 2017-11-21 | 中南大学 | Robot motion's pathdepth learns controlling planning method under a kind of intelligent environment |
| CN107436604A (en) * | 2017-07-31 | 2017-12-05 | 中南大学 | Controlling planning method is intelligently decomposed in carrying robot path under a kind of intelligent environment |
| CN107609650A (en) * | 2017-09-20 | 2018-01-19 | 河南理工大学 | Based on the particle genetic algorithm optimization method, apparatus and system that time load is balanced |
| CN108180912A (en) * | 2017-12-31 | 2018-06-19 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot positioning system and method based on hybrid navigation band |
| CN109084777A (en) * | 2018-09-13 | 2018-12-25 | 黎建军 | Particle filtering and map constructing method based on self-adapted genetic algorithm |
| CN110221604A (en) * | 2019-05-16 | 2019-09-10 | 浙江工业大学 | A kind of quick global paths planning method based on genetic algorithm |
| CN110598832A (en) * | 2019-08-22 | 2019-12-20 | 西安理工大学 | Character perspective correction method based on genetic optimization algorithm |
-
2019
- 2019-12-31 CN CN201911404486.4A patent/CN111103801B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914068A (en) * | 2013-01-07 | 2014-07-09 | 中国人民解放军第二炮兵工程大学 | Service robot autonomous navigation method based on raster maps |
| CN105737820A (en) * | 2016-04-05 | 2016-07-06 | 芜湖哈特机器人产业技术研究院有限公司 | Positioning and navigation method for indoor robot |
| CN107246873A (en) * | 2017-07-03 | 2017-10-13 | 哈尔滨工程大学 | A kind of method of the mobile robot simultaneous localization and mapping based on improved particle filter |
| CN107368076A (en) * | 2017-07-31 | 2017-11-21 | 中南大学 | Robot motion's pathdepth learns controlling planning method under a kind of intelligent environment |
| CN107436604A (en) * | 2017-07-31 | 2017-12-05 | 中南大学 | Controlling planning method is intelligently decomposed in carrying robot path under a kind of intelligent environment |
| CN107609650A (en) * | 2017-09-20 | 2018-01-19 | 河南理工大学 | Based on the particle genetic algorithm optimization method, apparatus and system that time load is balanced |
| CN108180912A (en) * | 2017-12-31 | 2018-06-19 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot positioning system and method based on hybrid navigation band |
| CN109084777A (en) * | 2018-09-13 | 2018-12-25 | 黎建军 | Particle filtering and map constructing method based on self-adapted genetic algorithm |
| CN110221604A (en) * | 2019-05-16 | 2019-09-10 | 浙江工业大学 | A kind of quick global paths planning method based on genetic algorithm |
| CN110598832A (en) * | 2019-08-22 | 2019-12-20 | 西安理工大学 | Character perspective correction method based on genetic optimization algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111103801A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dames et al. | Autonomous localization of an unknown number of targets without data association using teams of mobile sensors | |
| Fox | Markov localization-a probabilistic framework for mobile robot localization and navigation. | |
| Manikas et al. | Genetic algorithms for autonomous robot navigation | |
| CN111401531A (en) | Trajectory prediction method and system | |
| CN106647744B (en) | Robot path planning method and device | |
| Meyer-Delius et al. | Using artificial landmarks to reduce the ambiguity in the environment of a mobile robot | |
| CN106471338A (en) | Determine position in geographic area for the mobile device | |
| CN111061276B (en) | Mobile robot repositioning method based on dynamic area division | |
| CN112033413A (en) | Improved A-algorithm combined with environmental information | |
| Chung et al. | Multiscale search using probabilistic quadtrees | |
| Ma et al. | Optimized BP neural network algorithm for predicting ship trajectory | |
| CN107422326B (en) | Underwater target tracking method based on Bayesian estimation | |
| CN111103801B (en) | Mobile robot repositioning method based on genetic algorithm and mobile robot | |
| CN114594772A (en) | Robot, path planning method, device and storage medium | |
| CN113985894A (en) | Autonomous obstacle avoidance path planning method, device, equipment and storage medium | |
| Liu | A faster algorithm for the constrained minimum covering circle problem to expedite solving p‐center problems in an irregularly shaped area with holes | |
| CN116805047A (en) | Uncertainty expression method and device for multi-sensor fusion positioning and electronic equipment | |
| JP2021135473A (en) | Search support system, search support method | |
| Xie et al. | Weight‐Aware Sensor Deployment in Wireless Sensor Networks for Smart Cities | |
| Arndt et al. | Optimized mobile indoor robot navigation through probabilistic tracking of people in a wireless sensor network | |
| US20150127302A1 (en) | Method and apparatus for optimized routing | |
| Wang et al. | SRM: An efficient framework for autonomous robotic exploration in indoor environments | |
| Feng et al. | A global localization system for mobile robot using lidar sensor | |
| Chatterjee et al. | Simultaneous Localization and Mapping (SLAM) in mobile robots | |
| CN114610027B (en) | Ship navigation path planning method |
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 |