CN113359758A - Environment cost map generation method and system based on artificial potential field method - Google Patents
Environment cost map generation method and system based on artificial potential field method Download PDFInfo
- Publication number
- CN113359758A CN113359758A CN202110736905.5A CN202110736905A CN113359758A CN 113359758 A CN113359758 A CN 113359758A CN 202110736905 A CN202110736905 A CN 202110736905A CN 113359758 A CN113359758 A CN 113359758A
- Authority
- CN
- China
- Prior art keywords
- potential field
- obstacle
- information
- weight
- environment
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 45
- 230000004888 barrier function Effects 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000005855 radiation Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an environment cost map generation method and system based on an artificial potential field method, and belongs to the field of robot application; the method comprises the following specific steps: s1, acquiring an information vector of the position of an obstacle in the environment; s2 designing potential field strength weight according to the type of the obstacle; s3, calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight; s4, local potential fields generated by different barrier types are superposed to generate a global artificial potential field capable of reflecting the environment and generate a cost map; the invention can convert the information of different sensors into vectors correspondingly containing the position information of the obstacles, and endows potential field strength weight to the position information vectors of the obstacles obtained by different sensors, and the weight value reflects the importance degree of different types of obstacles; and finally, establishing a virtual artificial potential field according to the position information and the weight of different obstacles to obtain a cost map, wherein the potential field value reflects the passable condition of the area, and the more dangerous the area is, the higher the potential field value is.
Description
Technical Field
The invention discloses an environment cost map generation method and system based on an artificial potential field method, and relates to the technical field of robot application.
Background
The robot teleoperation system can replace human beings to complete operation tasks in dangerous and extreme environments, and is widely applied to the fields of space, deep sea, nuclear environment, disasters and the like.
The remote robot working in a complex environment needs to avoid extreme zones harmful to the robot, such as high temperature, high radiation and the like, besides the obstacle avoidance. At this time, the information obtained by the single sensor cannot comprehensively reflect the real situation of the environment. Therefore, the robot needs to have a plurality of sensors, such as a vision sensor, a radiation detector, a gas detector, a smoke detector, a thermo-hygrometer, an infrared distance measurement, etc., to solve the problem of insufficient description capability of a single sensor on a complex system.
During teleoperation, the teleoperator will be in a highly mental state. Environmental information from numerous sensors not only burdens the operator, but may also result in key information being ignored and false operations occurring.
The artificial potential field method is a virtual force method, proposed by Khatib. The basic idea is to design the motion of the robot in the surrounding environment as an abstract motion in a virtual potential field. The artificial potential field method is a common, mature and effective method in path planning and charting. The method has the advantages of simple mathematical principle, small calculated amount, high response speed, good real-time control performance and the like. The artificial potential field diagram generated by the method can reflect the basic information of the environment and can provide support for teleoperation. In addition, the method does not need global information and is very suitable for a nuclear environment lacking in environmental information.
The invention provides an environment cost map generation method and system based on an artificial potential field method, and aims to solve the problems that key information is ignored and misoperation is caused due to large working information.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an environment cost map generation method and system based on an artificial potential field method, and the adopted technical scheme is as follows: an environment cost map generation method based on an artificial potential field method comprises the following specific steps:
s1, acquiring an information vector of the position of an obstacle in the environment;
s2 designing potential field strength weight according to the type of the obstacle;
s3, calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
s4 superimposes the local potential fields generated by different obstacle types to generate a global artificial potential field that can reflect the environment and generate a cost map.
The specific step of S1 obtaining the information vector of the obstacle position in the environment includes:
s101, acquiring position information of an obstacle in a multi-dimensional mode by using a sensor;
s102 converts the environment information into a vector containing the position information.
The specific step of designing the potential field strength weight according to the type of the obstacle by the S2 comprises the following steps:
s201, judging the type of the obstacle;
s202 gives the sensor potential field strength information weight according to the type of the obstacle.
And S3, calculating potential field initial strength according to the position information of the obstacle, and multiplying the potential field initial strength by the weight to obtain local potential field values corresponding to different obstacles. And superposing different local potential fields to obtain a global potential field.
An environment cost map generation system based on an artificial potential field method specifically comprises a vector acquisition module, a weight assignment module, a field value calculation module and a map generation module:
a vector acquisition module: acquiring an information vector of the position of an obstacle in the environment;
a weight assignment module: designing potential field strength weight according to the type of the obstacle;
a field value calculation module: calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
a map generation module: and overlapping the local potential fields generated by different obstacle types to generate a global artificial potential field capable of reflecting the environment and generating a cost map.
The vector acquisition module specifically comprises an information acquisition module and a vector conversion module:
an information acquisition module: obtaining the position information of the barrier in a multi-dimensional way by using a sensor;
a vector conversion module: the environment information is converted into a vector containing the location information.
The weight assignment module specifically comprises an obstacle judgment module and a weight assignment module:
an obstacle judgment module: judging the type of the obstacle;
a weight assignment module: and giving potential field strength information weight to the sensor according to the type of the obstacle.
And the field value calculation module calculates potential field initial strength according to the position information of the obstacles, and multiplies the potential field initial strength by weight to obtain local potential field values corresponding to different obstacles.
The invention has the beneficial effects that: the invention provides an environment cost map generation method based on an artificial potential field method, namely a method for synthesizing information from different sensors into a cost map for comprehensively reflecting environment conditions based on the artificial potential field method; firstly, converting different sensor information into vectors correspondingly containing position information and potential field strength information, wherein the potential field strength information reflects the passable condition of a region, and the more dangerous the region is, the higher the potential field value is; then, giving weights to potential field intensity information of different sensors, wherein the magnitude of the weights reflects the importance degree of different types of obstacles; and finally, according to the position information of the obstacles of different sensors, superposing the potential field strength information of different obstacles and establishing a virtual artificial potential field to obtain a cost map.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow diagram of the process of the present invention; FIG. 2 is a schematic diagram of the system of the present invention; FIG. 3 is a schematic diagram of map generation according to an embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The first embodiment is as follows:
an environment cost map generation method based on an artificial potential field method comprises the following specific steps:
s1, acquiring an information vector of the position of an obstacle in the environment;
s2 designing potential field strength weight according to the type of the obstacle;
s3, calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
s4 superimposes the local potential fields generated by different obstacle types to generate a global artificial potential field that can reflect the environment and generate a cost map.
Further, the specific step of S1 acquiring the information vector of the position of the obstacle in the environment includes:
s101, acquiring position information of an obstacle in a multi-dimensional mode by using a sensor;
s102, converting the environment information into a vector containing position information;
further, the step S2 of designing the potential field strength weight according to the type of the obstacle includes:
s201, judging the type of the obstacle;
s202, giving potential field strength information weight to the sensor according to the type of the obstacle;
further, in step S3, the potential field initial strength is calculated according to the obstacle position information, and the local potential field values corresponding to different obstacles are obtained by multiplying the potential field initial strength by the weight. Superposing different local potential fields to obtain a global potential field;
combining the steps, when the method is used for generating the environmental cost map, firstly, converting different sensor information into vectors correspondingly containing position information of obstacles, endowing potential field strength weights to the position information vectors of the obstacles obtained by different sensors, and reflecting the importance degrees of the different types of obstacles according to the weight values; and finally, establishing a virtual artificial potential field according to the position information and the weight of different obstacles to obtain a cost map, wherein the potential field value reflects the passable condition of the region, and the more dangerous the region is, the higher the potential field value is, so that the problems of neglected key information and misoperation caused by larger working information are solved.
Example two:
an environment cost map generation system based on an artificial potential field method specifically comprises a vector acquisition module, a weight assignment module, a field value calculation module and a map generation module:
a vector acquisition module: acquiring an information vector of the position of an obstacle in the environment;
a weight assignment module: designing potential field strength weight according to the type of the obstacle;
a field value calculation module: calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
a map generation module: and overlapping the local potential fields generated by different obstacle types to generate a global artificial potential field capable of reflecting the environment and generating a cost map.
Further, the vector acquisition module specifically includes an information acquisition module and a vector conversion module:
an information acquisition module: obtaining the position information of the barrier in a multi-dimensional way by using a sensor;
a vector conversion module: converting the environment information into a vector containing position information;
further, the weight assignment module specifically includes an obstacle judgment module and a weight assignment module:
an obstacle judgment module: judging the type of the obstacle;
a weight assignment module: giving potential field strength information weight to the sensor according to the type of the obstacle;
further, the field value calculation module calculates potential field initial strength according to the position information of the obstacles, and multiplies the potential field initial strength by weight to obtain local potential field values corresponding to different obstacles;
combining the steps, when the system is used for generating the environmental cost map, firstly, the information of different sensors is converted into vectors correspondingly containing the position information of the obstacles, potential field strength weights are given to the position information vectors of the obstacles obtained by the different sensors, and the magnitude of the weight values reflects the importance degrees of the different types of obstacles; and finally, establishing a virtual artificial potential field according to the position information and the weight of different obstacles to obtain a cost map, wherein the potential field value reflects the passable condition of the region, and the more dangerous the region is, the higher the potential field value is, so that the problems of neglected key information and misoperation caused by larger working information are solved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. An environment cost map generation method based on an artificial potential field method is characterized by comprising the following specific steps:
s1, acquiring an information vector of the position of an obstacle in the environment;
s2 designing potential field strength weight according to the type of the obstacle;
s3, calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
s4 superimposes the local potential fields generated by different obstacle types to generate a global artificial potential field that can reflect the environment and generate a cost map.
2. The method as claimed in claim 1, wherein the step of S1 obtaining the information vector of the position of the obstacle in the environment comprises:
s101, acquiring position information of an obstacle in a multi-dimensional mode by using a sensor;
s102 converts the environment information into a vector containing the position information.
3. The method as claimed in claim 2, wherein said step of designing S2 a potential field strength weight according to the type of the obstacle comprises:
s201, judging the type of the obstacle;
s202 gives the sensor potential field strength information weight according to the type of the obstacle.
4. The method according to claim 3, wherein said S3 calculates the initial strength of the potential field according to the position information of the obstacle, and multiplies the initial strength of the potential field by the weight to obtain the local potential field values corresponding to different obstacles. And superposing different local potential fields to obtain a global potential field.
5. An environment cost map generation system based on an artificial potential field method is characterized by specifically comprising a vector acquisition module, a weight assignment module, a field value calculation module and a map generation module:
a vector acquisition module: acquiring an information vector of the position of an obstacle in the environment;
a weight assignment module: designing potential field strength weight according to the type of the obstacle;
a field value calculation module: calculating a local potential field value according to the information vector of the position of the obstacle and the potential field strength weight;
a map generation module: and overlapping the local potential fields generated by different obstacle types to generate a global artificial potential field capable of reflecting the environment and generating a cost map.
6. The system of claim 5, wherein the vector obtaining module specifically comprises an information obtaining module and a vector converting module:
an information acquisition module: obtaining the position information of the barrier in a multi-dimensional way by using a sensor;
a vector conversion module: the environment information is converted into a vector containing the location information.
7. The system according to claim 6, wherein the weight assignment module specifically comprises an obstacle determination module and a weight assignment module:
an obstacle judgment module: judging the type of the obstacle;
a weight assignment module: and giving potential field strength information weight to the sensor according to the type of the obstacle.
8. The system according to claim 7, wherein said field value calculation module calculates a potential field initial strength based on the obstacle position information, and multiplies the potential field initial strength by a weight to obtain local potential field values corresponding to different obstacles.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110736905.5A CN113359758A (en) | 2021-06-30 | 2021-06-30 | Environment cost map generation method and system based on artificial potential field method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110736905.5A CN113359758A (en) | 2021-06-30 | 2021-06-30 | Environment cost map generation method and system based on artificial potential field method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113359758A true CN113359758A (en) | 2021-09-07 |
Family
ID=77537620
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110736905.5A Pending CN113359758A (en) | 2021-06-30 | 2021-06-30 | Environment cost map generation method and system based on artificial potential field method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113359758A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105511478A (en) * | 2016-02-23 | 2016-04-20 | 百度在线网络技术(北京)有限公司 | Robot cleaner, control method applied to same and terminal |
CN108508900A (en) * | 2018-05-10 | 2018-09-07 | 同济大学 | A kind of wall-surface mobile robot wall detection autonomous path planning method |
CN110979321A (en) * | 2019-12-30 | 2020-04-10 | 北京深测科技有限公司 | Obstacle avoidance method for unmanned vehicle |
CN111626314A (en) * | 2019-02-28 | 2020-09-04 | 深圳市速腾聚创科技有限公司 | Point cloud data classification method and device, computer equipment and storage medium |
CN111857160A (en) * | 2020-08-17 | 2020-10-30 | 武汉中海庭数据技术有限公司 | Unmanned vehicle path planning method and device |
WO2021085109A1 (en) * | 2019-10-31 | 2021-05-06 | ソニー株式会社 | Trajectory planning device, trajectory planning method, and program |
-
2021
- 2021-06-30 CN CN202110736905.5A patent/CN113359758A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105511478A (en) * | 2016-02-23 | 2016-04-20 | 百度在线网络技术(北京)有限公司 | Robot cleaner, control method applied to same and terminal |
CN108508900A (en) * | 2018-05-10 | 2018-09-07 | 同济大学 | A kind of wall-surface mobile robot wall detection autonomous path planning method |
CN111626314A (en) * | 2019-02-28 | 2020-09-04 | 深圳市速腾聚创科技有限公司 | Point cloud data classification method and device, computer equipment and storage medium |
WO2021085109A1 (en) * | 2019-10-31 | 2021-05-06 | ソニー株式会社 | Trajectory planning device, trajectory planning method, and program |
CN110979321A (en) * | 2019-12-30 | 2020-04-10 | 北京深测科技有限公司 | Obstacle avoidance method for unmanned vehicle |
CN111857160A (en) * | 2020-08-17 | 2020-10-30 | 武汉中海庭数据技术有限公司 | Unmanned vehicle path planning method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mitchell et al. | Symbiotic system of systems design for safe and resilient autonomous robotics in offshore wind farms | |
Maurtua et al. | MAINBOT–mobile robots for inspection and maintenance in extensive industrial plants | |
Jassemi-Zargani et al. | Extended Kalman filter-based sensor fusion for operational space control of a robot arm | |
Rezazadegan et al. | Risked-based design for the physical human-robot interaction (pHRI): An overview | |
CN105004368A (en) | Collision detection method, device and system for autonomous robot | |
CN113359758A (en) | Environment cost map generation method and system based on artificial potential field method | |
Zapata et al. | Reactive behaviors of fast mobile robots in unstructured environments: Sensor-based control and neural networks | |
Guan et al. | Intelligent obstacle avoidance algorithm for mobile robots in uncertain environment | |
Li et al. | Research on path planning for robot based on improved design of non-standard environment map with ant colony algorithm | |
Sharma et al. | Mobile Robot for Security Applications in Remotely Operated Advanced Reactors | |
Chen et al. | Multisensor based autonomous mobile robot through Internet control | |
Li et al. | A Review of Mobile Robots in Extreme Environments | |
Ko et al. | 3-Dimensional simulator for multiple robot system using TCP-IP | |
Choi et al. | Development of safety diagnostic robot for industrial plant environment | |
Salmanipour et al. | Teleoperation of a mobile robot with model-predictive obstacle avoidance control | |
Nguyen et al. | RC Auto Mapper: Remote Controlled Robotic Vehicle for Autonomous Area Mapping | |
Ishikawa et al. | Development of a human collaborative mobile robot system | |
Liu et al. | Multi-Mode Perception for Human-Robot Collaborative Manufacturing: Framework and Enabling Technologies | |
Connette et al. | Efficient Monitoring of Process Plants by Telepresence and Attention Guidance | |
Wood et al. | Emerging technologies in instrumentation and controls | |
Büskens et al. | Higher order real-time approximations in optimal control of multibody-systems for industrial robots | |
MacDonald et al. | Software environments for robot programming | |
Kottayam Viswanathan et al. | FLIE: First-Look Enabled Inspect-Explore Autonomy Toward Visual Inspection of Unknown Distributed and Discontinuous Structures | |
Chalfant | Planning in subsumption architectures(for robotic and control systems) | |
GORSKY | AUTOMATION OF THE RUSSIAN ACADEMY OF SCIENCES (SPIIRAS) |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |