CN113688496B - Precision simulation evaluation method for robot mapping algorithm - Google Patents
Precision simulation evaluation method for robot mapping algorithm Download PDFInfo
- Publication number
- CN113688496B CN113688496B CN202110757015.2A CN202110757015A CN113688496B CN 113688496 B CN113688496 B CN 113688496B CN 202110757015 A CN202110757015 A CN 202110757015A CN 113688496 B CN113688496 B CN 113688496B
- Authority
- CN
- China
- Prior art keywords
- algorithm
- simulation
- robot
- point
- precision
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 82
- 238000004088 simulation Methods 0.000 title claims abstract description 77
- 238000013507 mapping Methods 0.000 title claims abstract description 30
- 238000011156 evaluation Methods 0.000 title claims abstract description 20
- 230000004888 barrier function Effects 0.000 claims description 2
- 210000001503 joint Anatomy 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 12
- 238000010276 construction Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010408 sweeping Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001417527 Pempheridae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
Abstract
The invention relates to a precision simulation evaluation method of a robot map building algorithm, which comprises the steps of building a robot simulation environment comprising a simulation robot, a simulation sensor and a simulation scene, and butting the robot map building algorithm with a simulation system; randomly selecting a plurality of key points in a simulation scene as comparison points; and extracting corresponding key point position coordinates in the drawing construction algorithm after drawing construction of the drawing construction algorithm, carrying out precision comparison on the key point position coordinates and a true value in a simulation system, and taking an average value as a drawing construction precision value of the drawing construction algorithm. The method realizes the evaluation of the precision of the mapping algorithm by using a simulation means, solves the evaluation problem of the precision of the mapping algorithm of different types of robots, and particularly provides a fairness scheme and means for mutually comparing and avoiding cheating for different mapping algorithms of different manufacturers or brands of robots of the same type, and improves the evaluation efficiency and saves the evaluation time and cost.
Description
Technical Field
The invention relates to a testing technology, in particular to a precision simulation evaluation method for a robot mapping algorithm.
Background
With the rapid development of the robot industry, the robot algorithm is also rapidly developed, the same type of robot algorithm is different, the performance of the robot algorithm may be different, for example, a floor sweeping robot is subjected to iteration from random movement to ESLAM, to different algorithms and technologies such as laser SLAM, VSLAM and the like. The improvement and optimization of the algorithm have the advantages that the improvement of the performance of the robot has higher and higher proportion, and the evaluation work of the algorithm has become more and more important.
However, the evaluation means of the algorithm are always lagged relative to the rapid development of the algorithm. Many robotic products perform well in laboratories and factories, but various errors occur as soon as they reach the actual user's working environment. On the one hand, the method is because of the lag and incompleteness of the evaluation means, and on the other hand, the enterprise cannot cover the complex and diverse actual working environments of users during the test.
In the robot SLAM algorithm, the mapping algorithm is the basis of other algorithms such as navigation and positioning, and is particularly important. Robots of different purposes have different requirements on a mapping algorithm due to different working environments, for example, a household floor sweeper only needs to work in a small-area environment in a household room, the mapping algorithm does not have bad consequences even if the precision is low, while industrial robots, such as industrial AGVs, need to work in a large-area environment such as a factory building and the like, and because equipment is heavy and has high value, if the mapping precision is low, serious consequences such as personal safety and property loss can be caused. Finding a simple, general and efficient evaluation method to evaluate the precision of the mapping algorithm becomes an urgent problem to be solved.
Disclosure of Invention
Aiming at the problem of how to accurately evaluate after the drawing algorithm is applied, a robot drawing algorithm accuracy simulation evaluating method is provided.
The technical scheme of the invention is as follows: the robot mapping algorithm precision simulation evaluation method specifically comprises the following steps:
1) Constructing a robot simulation environment comprising a simulation robot, a simulation sensor and a simulation scene, and butting a robot map building algorithm with a simulation system;
2) Randomly selecting a plurality of key points in a simulation scene as comparison points;
3) The robot in the simulation system moves according to the output information of the mapping algorithm, the simulation system provides various sensor information for the mapping algorithm, and the mapping algorithm performs movement mapping according to the received sensor information and the algorithm;
4) And after the drawing is built by the drawing building algorithm, the coordinates of the corresponding key points in the algorithm are fed back to the simulation system, the simulation system compares the coordinate values of each key point in the received drawing building algorithm with the true values in precision, and the average value is taken as the drawing building precision value of the drawing building algorithm.
Further, the key points in the step 2) are determined according to the simulation scene space and the obstacle positions, all the key points are selected randomly only in the following three types,
first category: the intersection point of two walls or the point on the intersection line;
second category: points on the intersection or intersection line of two right-angle outer planes of the rectangular barrier;
third category: the center of the circle or a point on the circumference of the circular obstacle.
Further, the method for calculating the map precision value of the map construction algorithm in the step 4) is as follows:
calculating the distance difference between the algorithm coordinates and the actual coordinates of each key point according to the following formula:
wherein: the Xi point is the X-axis real coordinate value of the point i; yi point is the Y-axis real coordinate value of point i; the Xi' point is the X-axis map coordinate value of the point i; yi is the Y-axis map coordinate value of the point i;
the drawing precision value E of the drawing algorithm is calculated according to the following formula:
wherein: n is the total number of randomly selected key points.
The invention has the beneficial effects that: the method for evaluating the precision simulation of the drawing algorithm of the robot realizes the evaluation of the precision of the drawing algorithm by using a simulation means, solves the evaluation problem of the precision of the drawing algorithm of different types of robots, and particularly provides a fair scheme and means for comparing different drawing algorithms of different manufacturers or brands of robots with the same type and avoiding cheating, and simultaneously improves the evaluation efficiency and saves the evaluation time and cost.
Drawings
FIG. 1 is a schematic diagram of a simulation scenario according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a key point selection location and a mark according to the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
The robot simulation related by the invention is to simulate the body, the sensor and the physical environment of the robot, and the simulation environment is in butt joint with the real algorithm of the robot, so as to realize the algorithm control of the simulation robot to move in the simulation environment. Since robotic simulation techniques are not the focus of the present invention, a brief description will be provided only when the present invention is concerned.
The method comprises the steps of constructing a robot simulation environment, comprising a simulation robot, a simulation sensor and a simulation scene, butting a robot mapping algorithm with a simulation system, enabling the robot in the simulation system to move according to output information of the mapping algorithm, providing various sensor information of the mapping algorithm by the simulation system, and enabling the mapping algorithm to move and map according to the received sensor information and the algorithm.
And randomly selecting a plurality of key points in the simulation scene as comparison points, extracting corresponding key point position coordinates in the drawing algorithm after drawing construction of the drawing algorithm, feeding back the corresponding key point position coordinates to the simulation system, and carrying out precision comparison on the coordinate values of each key point in the received drawing algorithm and the true value by the simulation system, and taking an average value as a precision value of the drawing algorithm. It can be seen that the more key points are selected, the closer the accuracy value is to the overall accuracy value.
Aiming at robots with different working environments and purposes, the drawing algorithm can carry out precision evaluation according to the method only by selecting proper simulation scenes and moderate key point quantity. The mapping algorithm of the same type of robot, such as a sweeping robot, uses the same simulation scene and the same number of key points at the same position for evaluation, and the result can be used for comparing the advantages and disadvantages of different mapping algorithms of the same type of robot.
The technical scheme of selecting key points in a simulation scene, calculating the coordinates of the key points by an algorithm and comparing the coordinates with real coordinates in the simulation environment is as follows:
in the simulation scenario, as shown in the schematic diagram of the simulation scenario in the embodiment of fig. 1, a certain number of key points are determined according to the simulation scenario space and the obstacle positions. All key points are selected only among the following three types, as shown in fig. 2:
1. the intersection point of two walls or the point on the intersection line;
2. points on the intersection or line of two right-angle outer planes of rectangular furniture or objects;
3. a point on the center or circumference of a circular piece of furniture or object.
The keypoints are marked in the scene. The marking method comprises the following steps: for example, the key points on the intersection line of two walls are marked on the wall body in a certain range (for example, within 10 cm) near the intersection point, and the area formed by the intersection line of the thick line of the wall corner and the point 1 in fig. 2 is marked. When the sensor of the robot scans the wall body with the mark near the key point, the sensor sends the mark information to the algorithm together with normal data in the JSON format.
Taking 2D lidar as an example, the sensor scan data with the markers is:
{ "Angle": -1.570796, "distance": 0, "info": 1, "angle": -1.562070, "distance": 0.665, "info": 0, … … }
The angle value in the JSON format data is the scanning angle of the current laser point, the distance value is the obstacle distance value fed back by the laser point, and the information value is the information of the key point. If the scanned area is a non-key point marked area, the information value is 0, otherwise, the information value is the number of the key point. Such as 1 in the data, represents that the current scan point is near the key point No. 1.
After the robot finishes the drawing in the simulation scene, the algorithm can take the information values (distance and angle) of all the key point positions, calculate the key point coordinates based on the information values, feed back the calculated key point coordinates to the simulation system, obtain the distance difference between the calculated key point coordinates and the real coordinates of the key points in the scene by the simulation system, and then calculate the average value, thus obtaining the precision of the drawing algorithm.
In the process, because the scene and the key point position are randomly selected in the simulation scene by the simulation system, when different algorithms are compared by using the method, the algorithm cannot acquire the accurate coordinates of the key point in advance, and thus cheating cannot be realized.
The invention builds a family simulation scene in the robot simulation system, and sets 12 key points in the simulation scene, see fig. 1. Marking 12 key points and walls or vertical faces in areas not exceeding 10cm nearby, and butting a robot mapping algorithm with a simulation system through a network interface to realize data intercommunication.
And (3) installing a laser sensor for the robot, controlling the robot to move along the wall in the simulation scene, simultaneously acquiring laser sensor data while moving, and synchronously transmitting the laser sensor data to a mapping algorithm. The robot moves two circles in the scene, so that the movement is stopped after the laser scans all walls and objects.
The mapping algorithm completes mapping according to the received laser data, and sends coordinate values of 12 key points to a simulation system, the simulation system calculates distance difference between the 12 coordinate values fed back by the algorithm and real coordinate values in a scene, and then the average value is obtained as follows:
calculating the distance difference between the algorithm coordinates and the actual coordinates of each key point according to the following formula (1):
and (3) calculating a final map building precision result according to the following formula (2):
wherein: the Xi point is the X-axis real coordinate value of the point i; yi point is the Y-axis real coordinate value of point i; the Xi' point is the X-axis map coordinate value of the point i; yi is the Y-axis map coordinate value of the point i; e is the drawing construction precision.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (1)
1. The robot map building algorithm precision simulation evaluation method is characterized by comprising the following steps of:
1) The robot simulation is to simulate a body and a sensor of the robot and a physical environment where the robot is located, wherein the robot simulation environment comprises a simulation robot, a simulation sensor and a simulation scene, the simulation scene is built in a robot simulation system, and a robot map building algorithm is in butt joint with the simulation system;
2) Randomly selecting a plurality of key points in a simulation scene as comparison points;
the key points are determined according to the simulation scene space and the obstacle positions, all the key points are selected randomly only in the following three types,
first category: the intersection point of two walls or the point on the intersection line;
second category: points on the intersection or intersection line of two right-angle outer planes of the rectangular barrier;
third category: a point on the center or circumference of a circular obstacle;
3) The robot in the simulation system moves according to the output information of the mapping algorithm, the simulation system provides various sensor information for the mapping algorithm, and the mapping algorithm performs movement mapping according to the received sensor information and the algorithm;
4) The coordinates of the corresponding key points in the algorithm after the drawing is built by the drawing building algorithm are extracted and fed back to the simulation system, the simulation system compares the received coordinate values of each key point in the drawing building algorithm with the true values in precision, and the average value is taken as the drawing building precision value of the drawing building algorithm, and the drawing building precision value calculation method of the drawing building algorithm is as follows:
calculating the distance difference between the algorithm coordinates and the actual coordinates of each key point according to the following formula:
wherein: the Xi point is the X-axis real coordinate value of the point i; yi point is the Y-axis real coordinate value of point i; the Xi' point is the X-axis map coordinate value of the point i; yi is the Y-axis map coordinate value of the point i;
the drawing precision value E of the drawing algorithm is calculated according to the following formula:
wherein: n is the total number of randomly selected key points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757015.2A CN113688496B (en) | 2021-07-05 | 2021-07-05 | Precision simulation evaluation method for robot mapping algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757015.2A CN113688496B (en) | 2021-07-05 | 2021-07-05 | Precision simulation evaluation method for robot mapping algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688496A CN113688496A (en) | 2021-11-23 |
| CN113688496B true CN113688496B (en) | 2024-04-12 |
Family
ID=78576651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110757015.2A Active CN113688496B (en) | 2021-07-05 | 2021-07-05 | Precision simulation evaluation method for robot mapping algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688496B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262283A (en) * | 2019-06-11 | 2019-09-20 | 远形时空科技（北京）有限公司 | A kind of the vision robot's emulation platform and method of more scenes |
| CN110587606A (en) * | 2019-09-18 | 2019-12-20 | 中国人民解放军国防科技大学 | Open scene-oriented multi-robot autonomous collaborative search and rescue method |
| CN111496848A (en) * | 2020-03-19 | 2020-08-07 | 中山大学 | Mobile robot repeated positioning precision test based on Euclidean distance |
| WO2021016807A1 (en) * | 2019-07-29 | 2021-02-04 | 西门子股份公司 | Context awareness device simulation method, device, and system |
| CN112947081A (en) * | 2021-02-05 | 2021-06-11 | 浙江大学 | Distributed reinforcement learning social navigation method based on image hidden variable probability model |
-
2021
- 2021-07-05 CN CN202110757015.2A patent/CN113688496B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262283A (en) * | 2019-06-11 | 2019-09-20 | 远形时空科技（北京）有限公司 | A kind of the vision robot's emulation platform and method of more scenes |
| WO2021016807A1 (en) * | 2019-07-29 | 2021-02-04 | 西门子股份公司 | Context awareness device simulation method, device, and system |
| CN110587606A (en) * | 2019-09-18 | 2019-12-20 | 中国人民解放军国防科技大学 | Open scene-oriented multi-robot autonomous collaborative search and rescue method |
| CN111496848A (en) * | 2020-03-19 | 2020-08-07 | 中山大学 | Mobile robot repeated positioning precision test based on Euclidean distance |
| CN112947081A (en) * | 2021-02-05 | 2021-06-11 | 浙江大学 | Distributed reinforcement learning social navigation method based on image hidden variable probability model |
Non-Patent Citations (1)
| Title |
|---|
| 熊有伦等编著.机器人学：建模、控制与视觉 第2版.华中科技大学出版社,2020,第402-404页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688496A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Becker et al. | Reliable navigation using landmarks | |
| US11243540B2 (en) | System and method for complete coverage of unknown environments | |
| Diosi et al. | Laser scan matching in polar coordinates with application to SLAM | |
| Zaman et al. | ROS-based mapping, localization and autonomous navigation using a Pioneer 3-DX robot and their relevant issues | |
| CN103895023A (en) | Mechanical arm tail end tracking and measuring system and method based on coding azimuth device | |
| CN104457755B (en) | A kind of location acquiring method | |
| CN111522022B (en) | Dynamic target detection method of robot based on laser radar | |
| CN111428578B (en) | Self-body and positioning method and device thereof | |
| Kato et al. | Identifying and localizing robots in a multi-robot system environment | |
| Zhou | A closed-form algorithm for the least-squares trilateration problem | |
| CN111238366A (en) | Three-dimensional scanning path planning method and device | |
| Weber et al. | APR-global scan matching using anchor point relationships | |
| CN113688496B (en) | Precision simulation evaluation method for robot mapping algorithm | |
| Zunino | Simultaneous localization and mapping for navigation in realistic environments | |
| Jung et al. | Structured light 2D range finder for simultaneous localization and map-building (SLAM) in home environments | |
| CN114995459A (en) | Robot control method, device, equipment and storage medium | |
| Rupp et al. | Optimized landmark arrangement for absolute localization-a practical approach | |
| Yamanaka et al. | Mobile robot navigation using hybrid simplified map with relationships between places and grid maps | |
| CN110007680B (en) | Robot obstacle avoidance algorithm based on topological relation | |
| Legowik et al. | Sensor calibration and registration for mobile manipulators | |
| CN112731434A (en) | Positioning method and system based on laser radar and marker | |
| Chen et al. | A simple and generic method for real-time accurate hand-eye calibration using a 3D vision sensor | |
| Miah et al. | Mobile robot navigation using direction-sensitive RFID reader | |
| Zou et al. | A robot navigation method based on laser and 2D code | |
| Worcester et al. | 3-dimensional tiling for distributed assembly by robot teams |
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 |