CN113741422A - Robot topology map generation system, method, computer device and storage medium - Google Patents
Robot topology map generation system, method, computer device and storage medium Download PDFInfo
- Publication number
- CN113741422A CN113741422A CN202110874201.4A CN202110874201A CN113741422A CN 113741422 A CN113741422 A CN 113741422A CN 202110874201 A CN202110874201 A CN 202110874201A CN 113741422 A CN113741422 A CN 113741422A
- Authority
- CN
- China
- Prior art keywords
- track
- distance
- map
- obstacle
- topological
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009471 action Effects 0.000 claims abstract description 63
- 238000013507 mapping Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 238000000265 homogenisation Methods 0.000 claims description 14
- 230000004048 modification Effects 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000009877 rendering Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 19
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001172 regenerating effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the field of robot navigation, and discloses a robot topological map generation system, a robot topological map generation method, a robot topological map generation computer device and a storage medium, wherein the robot topological map generation system comprises a memory, a processor and computer readable instructions which are stored in the memory and can run on the processor, and the following steps are realized when the processor executes the computer readable instructions: acquiring an action track of the robot in a mapping scene; filtering the action track to generate a uniform point track; acquiring depth image data corresponding to the homogenized point track; generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map; and in the feasible region, processing the action track through a preset algorithm to generate a topological map of the mapping scene. The invention greatly improves the drawing efficiency of the topological map and reduces the artificial errors of the topological map.
Description
Technical Field
The invention relates to the field of robot navigation, in particular to a robot topological map generation system, a robot topological map generation method, computer equipment and a storage medium.
Background
In the automatic navigation process of the robot, a pre-drawn topological map is usually relied on. Topological maps are typically drawn by human beings. However, for a complex scene, the process of drawing the topological map is complicated, time and labor are wasted, and the situation that the topological map is not matched with the actual scene exists, which affects the normal operation of the robot.
Disclosure of Invention
Therefore, in order to solve the above technical problems, it is necessary to provide a robot topology map generation system, a robot topology map generation method, a computer device, and a storage medium, so as to improve the drawing efficiency of the topology map and reduce the human error of the topology map.
A robotic topology map generation system comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor when executing the computer readable instructions implementing the steps of:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
A robot topological map generation method comprises the following steps:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
A computer device comprising a memory, a processor and computer readable instructions stored in the memory and executable on the processor, the processor implementing the robot topology map generation method when executing the computer readable instructions.
One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the robot topology map generation method as described above.
According to the robot topological map generation system, the robot topological map generation method, the computer equipment and the storage medium, the action track of the robot in the map construction scene is obtained, the difficulty in obtaining the action track is low, and the drawing cost of the topological map is favorably reduced. And filtering the action track to generate a uniform point track so as to standardize the action track and improve the accuracy of image processing. And acquiring depth image data corresponding to the homogenization point track to determine the distance of the obstacle. And generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map so as to ensure that the topological path is in the feasible region. And processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene, wherein the preset algorithm can process the track of the approximate curve into a plurality of track line segments in a segmented manner to further form a path of the topological map. The method can automatically generate the topological map only by acquiring the action track, greatly improves the drawing efficiency of the topological map, and reduces the human errors of the topological map.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a robot topology map generation system according to an embodiment of the present invention;
FIG. 2 is a simplified diagram of a robot entering a mapping scenario in accordance with an embodiment of the present invention;
FIG. 3 is an image including a trajectory of uniformized points after filtering processing according to an embodiment of the present invention;
FIG. 4 is a local obstacle distance map in accordance with an embodiment of the present invention;
FIG. 5 is a topological map after inversion processing in accordance with an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a path of a topological map generated according to an action trajectory according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a robot topology map generation system includes a memory, a processor, and computer program computer readable instructions stored in the memory and executable on the processor, wherein the processor is configured to execute the computer readable instructions to implement the following steps:
and S10, acquiring the action track of the robot in the mapping scene.
Understandably, the mapping scenario may be a work scenario of the robot, such as a restaurant, hotel, hospital, or other indoor or outdoor scenario. The action track may be a walking track of the robot in a mapping scenario. The action trajectory comprises a point trajectory of several robots. In an example, the point trajectories may be acquired at preset time intervals. The preset time interval can be set according to actual needs. For example, the preset time interval may be 1s to 10 s. In other examples, the point trajectories may be collected according to a preset displacement interval and/or an angle interval, for example, the point trajectories are collected once every 0.2m of movement, or once every 20 degrees of change of the angle, and the like, and the specific numerical values are not limited herein.
In one example, as shown in FIG. 2, the mapping scenario may be a restaurant. When the robot enters the restaurant, a worker can push the robot to travel along the pedestrian path of the restaurant to form a movement track, and meanwhile, the laser radar on the robot body can acquire depth image data along the pedestrian path. Repeating the steps for several times, a plurality of action tracks can be collected.
And S20, performing filtering processing on the action track to generate a uniform point track.
Understandably, in the action track, the time intervals of the acquisition of the adjacent track points are equal, and the distances between the adjacent track points have certain difference. The spacing is related to the speed of movement of the robot over the time interval. The motion trajectory needs to be filtered, so that the difference of the distances is reduced, and a uniform point trajectory is obtained. The uniform point track means that the distance between adjacent track points is within a distance range, so that the uniform distance is ensured, and the condition of overlarge or undersize does not occur. As shown in fig. 3, fig. 3 is an image including the homogenized point tracks after the filtering process. The linear curve in fig. 3 is a uniform point trajectory.
And S30, acquiring depth image data corresponding to the homogenization point track.
Understandably, the depth image data may be depth information data acquired by a depth camera and/or a lidar mounted on the robot body. The uniformization point track comprises a plurality of track points, and each track point at least collects one frame of depth image data. The depth image data corresponding to the trajectory of the uniformization point refers to a set of depth image data collected at each trajectory point.
And S40, generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map.
Understandably, after obtaining the depth image data of each track point, the depth image data can be spliced according to the position of the track point to form a three-dimensional point cloud (obstacle point). Projecting the three-dimensional point cloud onto a ground plane (which may be a horizontal plane) of the mapping scene may generate a two-dimensional obstacle map. And respectively calculating the minimum distance from each position point on the initial map to the obstacle point. And setting the pixel value of each position point of the initial map according to the size of the minimum distance. As shown in fig. 4, the pixel value of the obstacle point may be set to 0, and the pixel values of other position points increase as the minimum distance to the obstacle point increases. In the obstacle distance map, the lighter the color (the larger the pixel value), the larger the distance from the obstacle. A limit pixel value may be set, and a region having a pixel value larger than the limit pixel value may be set as a feasible region.
In other examples, the pixel value of the obstacle point may be set to 255, and the pixel values of other position points decrease as the minimum distance to the obstacle point increases. The darker the color (the larger the pixel value) in the obstacle distance map, the larger the distance from the obstacle. A limit pixel value may be set, and a region having a pixel value smaller than the limit pixel value may be set as a feasible region.
And step S50, processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
Understandably, the preset algorithm is an algorithm that approximately represents a curve as a series of points and reduces the number of points. The algorithm has translation and rotation invariance, and after a curve and a threshold value are given, a sampling result is constant. Here, the action track is segmented by a plurality of tracks, and the segments of the tracks can be represented by curves. Through the processing of a preset algorithm, the tracks can be linearized in a segmented manner to generate a plurality of track line segments. And connecting all the track line segments to form a path consisting of a plurality of straight line segments, namely the topological map of the mapping scene. When drawing a topological map, it is necessary to ensure that any point on all paths is within a feasible region. If any point on all the paths is not in the feasible region, the topological paths need to be re-planned until any point on all the paths is in the feasible region. As shown in fig. 5, fig. 5 is a topology map processed by inversion.
In the steps S10-S50, the action track of the robot in the map building scene is obtained, wherein the difficulty in obtaining the action track is low, and the drawing cost of the topological map is favorably reduced. And filtering the action track to generate a uniform point track so as to standardize the action track and improve the accuracy of image processing. And acquiring depth image data corresponding to the homogenization point track to determine the distance of the obstacle. And generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map so as to ensure that the topological path is in the feasible region. And processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene, wherein the preset algorithm can process the track of the approximate curve into a plurality of track line segments in a segmented manner to further form a path of the topological map. In the embodiment, the topological map can be automatically generated only by acquiring the action track, so that the drawing efficiency of the topological map is greatly improved, and the artificial errors of the topological map are reduced.
Optionally, in step S20, the filtering the action trajectory to generate a homogenized point trajectory includes:
s201, interpolating the action track, and then performing median filtering and mean value smoothing to generate the homogenization point track; in the uniformization point track, the distance between adjacent track points is larger than a first threshold value and smaller than a second threshold value.
Understandably, the motion track can be interpolated, the number of track points is increased, and the distance between all adjacent track points is smaller than a first threshold value. And then removing track points with undersized intervals through median filtering, and then performing mean value smoothing treatment to enable the intervals of the adjacent track points to be approximately equal, thereby obtaining a uniform point track. In the uniformization point track, the distance between the adjacent track points is larger than a first threshold value and smaller than a second threshold value.
Optionally, the first threshold includes 0.25m, and the second threshold includes 1 m.
Understandably, the first threshold and the second threshold can be set according to actual needs. In an example, the first threshold comprises 0.25m and the second threshold comprises 1 m.
Optionally, in step S40, the generating an obstacle distance map of the mapping scene according to the depth image data includes:
s401, splicing the depth image data according to the position of the robot in the homogenization point track to generate an obstacle map containing the position of an obstacle;
s402, calculating a distance value between an idle position and an obstacle position, rendering the obstacle map according to the distance value, and generating the obstacle distance map.
Understandably, the depth image data on each track point can be spliced according to the positions of the track points to form a three-dimensional point cloud containing the barrier points. Projecting the three-dimensional point cloud onto a ground plane (which may be a horizontal plane) of the mapping scene may generate a two-dimensional obstacle map. The position points of the obstacle positions may be marked in black. The idle position refers to a position point having no obstacle. The distance value of the idle position from the obstacle position may refer to the distance of the idle position from the nearest obstacle position, i.e. the minimum distance. Each free position may get a unique distance value. The pixel value of the free position can be set according to the distance value. In one example, the pixel value of a location point that is more than or 2 meters from the obstacle may be set to 255 (i.e., white). As shown in fig. 4, fig. 4 is a local obstacle distance map in one example. Fig. 4 contains three obstacle points. Wherein the pixel value of the obstacle point is set to 0, and the pixel values of the other position points increase with increasing distance from the obstacle point.
Optionally, step S40, that is, the generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map includes:
s403, acquiring a limit distance of the obstacle;
s404, acquiring a limit pixel value corresponding to the limit distance;
s405, if the pixel value of the obstacle is 0, setting the area, with the pixel value larger than the limiting pixel value, in the obstacle distance map as the feasible area;
and S406, if the pixel value of the obstacle is 255, setting the area, with the pixel value smaller than the limiting pixel value, in the obstacle distance map as the feasible area.
Understandably, the limit distance is the minimum distance between the robot and the obstacle. The limiting distance can be set according to actual needs. In one example, the restriction distance may be set to 0.5 m. A correspondence between the distance and the pixel value may be set. For example, the pixel value of the position where the obstacle is located (distance is 0) is 0, the pixel values of the positions 3m and 3m away from the obstacle are set to 255, and the pixel values of the positions between 0 and 3m away are positively correlated with the distance, and may be linearly or nonlinearly changed, and each distance has a unique corresponding pixel value.
In one example, the pixels of the location points increase with increasing distance from the obstacle point in the obstacle distance map. Therefore, the pixel value of the distance limit may be determined first and recorded as the pixel value threshold, and the region where the pixel value is greater than the pixel value threshold is the feasible region.
In another example, the pixels of the location point decrease with increasing distance from the obstacle point in the obstacle distance map. Therefore, the pixel value of the distance limit may be determined first and recorded as the pixel value threshold, and the region where the pixel value is smaller than the pixel value threshold is the feasible region.
Optionally, the action track includes a plurality of track segments;
step S50, namely, processing the action trajectory through a preset algorithm in the feasible region to generate a topological map of the mapping scene, including:
s501, acquiring a first track node and a second track node corresponding to track segmentation, and generating a first connection line between the first track node and the second track node;
s502, calculating the distance between the track point on the track segment and the first connecting line, and setting the track point which has the shortest curve distance with the first track node and the distance with the first connecting line which is greater than or equal to the distance threshold value as a first middle node;
s503, connecting the first intermediate node and the second track node to generate a second connecting line;
s504, calculating the distance between the track point between the first intermediate node and the second track node and the second connecting line, and setting the track point which has the shortest curve distance with the first intermediate node and the distance with the second connecting line which is greater than or equal to the distance threshold value as the second intermediate node;
s505, repeating the steps until the distances between all the track points on the remaining curves and the corresponding middle connecting lines are smaller than a distance threshold;
s506, sequentially connecting the first track node, the intermediate nodes and the second track node to generate a plurality of track line segments, wherein the intermediate nodes comprise the first intermediate node and the second intermediate node.
And S507, splicing the plurality of track segments to generate a topological path, wherein the topological map comprises the topological path.
Understandably, several trajectory segments can be divided from the action trajectory. Each trajectory segment may generate at least one trajectory line segment. The first and second track nodes corresponding to the track segment may be acquired from the node setting information, respectively. Here, the first track node and the second track node are two end points of the track segment. Connecting the first track node and the second track node may form a connection line between the first track node and the second track node. And calculating the distances between all track points and the connecting line in the track segmentation, selecting the track point with the distance greater than the distance threshold value and the shortest curve distance with the first track node, and marking as a first middle node. Here, the curve distance refers to the length of the curve between two points.
Connecting the first intermediate node and the first track node may form a second connection between the first intermediate node and the first track node. And calculating the distance between the track point between the first intermediate node and the second track node and the second connecting line, selecting the track point with the distance greater than the distance threshold value and the shortest curve distance with the first intermediate node, and marking as the second intermediate node.
The above steps may be repeated to form new intermediate links and intermediate nodes until the distances between all the trajectory points on the remaining curve (the curve after the second intermediate node) and the corresponding intermediate links are less than the distance threshold. The detailed steps can refer to steps S501-S504, which are not described herein.
The first trajectory node, the intermediate node, and the second trajectory node are connected in sequence, and a plurality of trajectory line segments can be generated. If no intermediate node exists, a trajectory segment between the first trajectory node and the second trajectory node may be generated. If there are N intermediate nodes (N is a positive integer), then N +1 trajectory segments may be generated.
And splicing all track segments according to a sequence, specifically splicing according to common track nodes, and forming a mutually communicated topological path. At the moment, the action track is converted into a topological path, and a topological map is further generated.
In one example, as shown in fig. 6, fig. 6 is a schematic diagram of a path for generating a topological map from a trajectory of action. In the example of fig. 6, a plurality of trajectory segments represented by curves, DA, DB, DC, respectively, are included. Taking the trajectory segment DA (which may also be represented as a curve DA) as an example, a connecting line DA (shown by a dotted line) may be generated between the first trajectory node D and the second trajectory node a by connecting them. And (3) calculating the distance from the point on the curve DA to the connecting line DA from the point D, and selecting a track point with the first distance being greater than the distance threshold value, namely the first intermediate node H.
Connecting the first intermediate node H and the second track node a, a connecting line HA (indicated by a dashed line) can be generated therebetween. And starting from the point H, calculating the distance from the point on the curve HA to the connection line HA, and selecting a track point with the first distance larger than the distance threshold value, namely the second intermediate node G.
Connecting the second intermediate node G and the second trace node a, a connecting line GA (shown by a dotted line) can be generated therebetween. And (4) calculating the distance from the point on the curve GA to the connecting line GA from the point G, and selecting a track point with the first distance being larger than the distance threshold value, namely the third intermediate node K.
Connecting the third intermediate node K and the second track node a may generate a connection KA therebetween. Starting from point K, the distance from a point on the curve KA to the connecting line KA is calculated. Since the distances from the points on the curve to the connecting line KA are all smaller than the distance threshold, all the steps of setting the intermediate nodes are completed. At this time, the trajectory line segments DH, HG, GK, KA (the schematic diagram in the lower right corner of fig. 6) connected in sequence can be formed by connecting D, H, G, K, A in sequence.
Optionally, after step S507, that is, after the step of stitching the plurality of track segments to generate a topological path, the method further includes:
s5071, judging whether the topological path is in the feasible region;
s5072, if the topological path is in the feasible region, determining that the topological path is feasible;
s5073, if the topological path is not within the feasible region, receiving a distance modification instruction;
s5074, adjusting the limiting distance according to the distance modifying instruction to obtain a modified limiting distance;
and S5075, generating a modified feasible region according to the modified limit distance.
Understandably, if all the path points on the topological path fall within the feasible region, the topological path is determined to be within the feasible region. And if the existing part of path points on the topological path are not in the feasible region, judging that the topological path is not in the feasible region. When the topological path is in the feasible region, the topological path does not conflict with the feasible region, and therefore the topological path is available. At this time, a topological map may be generated in combination with the topological path and the feasible region.
When the topological path is not in the feasible region, the topological path collides/collides with the feasible region, and thus, the topological path or the feasible region needs to be adjusted. In one example, the feasible region may be changed by modifying the restriction distance.
The distance modification instruction may be an instruction input by a user. Typically, the distance modification instruction is used to reduce the value of the limit distance. For example, the original restriction distance is 0.5m, and the modified restriction distance is 0.3 m. After determining the modified bounding distance, a modified feasible region may be generated based on the modified bounding distance. In one example, the original feasible region refers to a region having a pixel value greater than 200, and the modified feasible region may be a region having a pixel value greater than 180.
After obtaining the modified feasible region, it may be continuously determined that the topological path is within the modified feasible region. If the topological path is in the modified feasible region, the topological map can be generated by combining the topological path and the modified feasible region. If the topological path is not in the modified feasible region, the limit distance can be selected to be continuously adjusted or the topological path can be adjusted. In some examples, conflicting path portions may be flagged, the topological paths may be automatically revised by a path modification program, or the paths may be revised manually.
Optionally, after step S507, that is, after the step S507, the plurality of track segments are spliced to generate a topological path, where the topological map includes the topological path, the method further includes:
and judging whether the track line segment is in a feasible region, if not, reducing the numerical value of the distance threshold to obtain a new distance threshold, specifically, halving the distance threshold, and executing the action track in the feasible region by using the new distance threshold through a preset algorithm to generate the topological map of the mapping scene. I.e., the steps of S501-507 are repeatedly performed. And regenerating a new track line segment.
In an actual scene, whether the track line segment is located in the feasible region or not can be judged in real time, if the track line segment is not located in the feasible region, the distance threshold value can be directly adjusted to obtain a new distance threshold value, then the new distance threshold value is used for regenerating the track line segment, and other track line segments are generated according to the original distance threshold value.
The modules in the robot topology map generation system can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In an embodiment, a robot topological map generation method is provided, and the robot topological map generation method corresponds to the robot topological map generation system in the embodiment one to one. As shown in fig. 1, the robot topology map generation method provided in this embodiment includes the following steps:
s10, acquiring an action track of the robot in the mapping scene;
s20, filtering the action track to generate a uniform point track;
s30, obtaining depth image data corresponding to the homogenization point track;
s40, generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and S50, processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
Optionally, in step S20, the filtering the action trajectory to generate a homogenized point trajectory includes:
s201, interpolating the action track, and then performing median filtering and mean value smoothing to generate the uniform point track, wherein in the uniform point track, the distance between adjacent track points is greater than a first threshold value and smaller than a second threshold value.
Optionally, the first threshold includes 0.25m, and the second threshold includes 1 m.
Optionally, in step S40, the generating an obstacle distance map of the mapping scene according to the depth image data includes:
s401, splicing the depth image data according to the position of the robot in the homogenization point track to generate an obstacle map containing the position of an obstacle;
s402, calculating a distance value between an idle position and an obstacle position, rendering the obstacle map according to the distance value, and generating the obstacle distance map.
Optionally, step S40, that is, the generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map includes:
s403, acquiring a limit distance of the obstacle;
s404, acquiring a limit pixel value corresponding to the limit distance;
s405, if the pixel value of the obstacle is 0, setting the area, with the pixel value larger than the limiting pixel value, in the obstacle distance map as the feasible area;
and S406, if the pixel value of the obstacle is 255, setting the area, with the pixel value smaller than the limiting pixel value, in the obstacle distance map as the feasible area.
Optionally, the action track includes a plurality of track segments;
step S50, namely, processing the action trajectory through a preset algorithm in the feasible region to generate a topological map of the mapping scene, including:
s501, acquiring a first track node and a second track node corresponding to track segmentation, and generating a first connection line between the first track node and the second track node;
s502, calculating the distance between the track point on the track segment and the first connecting line, and setting the track point which has the shortest curve distance with the first track node and the distance with the first connecting line which is greater than or equal to the distance threshold value as a first middle node;
s503, connecting the first intermediate node and the second track node to generate a second connecting line;
s504, calculating the distance between the track point between the first intermediate node and the second track node and the second connecting line, and setting the track point which has the shortest curve distance with the first intermediate node and the distance with the second connecting line which is greater than or equal to the distance threshold value as the second intermediate node;
s505, repeating the steps until the distances between all the track points on the remaining curves and the corresponding middle connecting lines are smaller than a distance threshold;
s506, sequentially connecting the first track node, the intermediate nodes and the second track node to generate a plurality of track line segments, wherein the intermediate nodes comprise the first intermediate node and the second intermediate node;
and S507, splicing the plurality of track segments to generate a topological path, wherein the topological map comprises the topological path.
Optionally, after step S507, that is, after the step of stitching the plurality of track segments to generate a topological path, the method further includes:
s5071, judging whether the topological path is in the feasible region;
s5072, if the topological path is in the feasible region, determining that the topological path is feasible;
s5073, if the topological path is not within the feasible region, receiving a distance modification instruction;
s5074, adjusting the limiting distance according to the distance modifying instruction to obtain a modified limiting distance;
and S5075, generating a modified feasible region according to the modified limit distance.
Optionally, after step S507, that is, after the step of stitching the plurality of track segments to generate a topological path, the method further includes:
judging whether the track line segment is in the feasible region;
if the track line segment is not in the feasible region, reducing the numerical value of the distance threshold value to obtain a new distance threshold value;
and executing the step of processing the action track in the feasible region through a preset algorithm by using the new distance threshold value to generate a topological map of the mapping scene.
For specific limitations of the robot topology map generation method, reference may be made to the above limitations of the robot topology map generation system, which are not described herein again. It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the readable storage medium. The database of the computer device is used for storing data related to the robot topology map generation method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by a processor, implement a robot topology map generation method. The readable storage media provided by the present embodiment include nonvolatile readable storage media and volatile readable storage media.
In one embodiment, a computer device is provided, comprising a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor when executing the computer readable instructions implementing the steps of:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided, the readable storage media provided by the embodiments including non-volatile readable storage media and volatile readable storage media. The readable storage medium has stored thereon computer readable instructions which, when executed by one or more processors, perform the steps of:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware related to computer readable instructions, which may be stored in a non-volatile readable storage medium or a volatile readable storage medium, and when executed, the computer readable instructions may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; 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; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (11)
1. A robotic topology map generation system comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor is configured to execute the computer readable instructions to implement the steps of:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
2. The robot topology map generating system according to claim 1, wherein the filtering the action trajectory to generate a homogenized point trajectory includes:
and interpolating the action track, and then performing median filtering and mean value smoothing to generate the homogenized point track, wherein in the homogenized point track, the distance between adjacent track points is greater than a first threshold value and smaller than a second threshold value.
3. The robotic topological map generation system of claim 2, wherein said first threshold comprises 0.25m and said second threshold comprises 1 m.
4. The robot topology map generation system of claim 1, said generating an obstacle distance map of said mapping scene from said depth image data comprising:
splicing the depth image data according to the position of the robot in the homogenization point track to generate an obstacle map containing the position of an obstacle;
and calculating a distance value between an idle position and an obstacle position, rendering the obstacle map according to the distance value, and generating the obstacle distance map.
5. The robot topology map generation system of claim 1, wherein said generating an obstacle distance map of said mapping scene from said depth image data, setting feasible regions from said obstacle distance map, comprises:
acquiring a limit distance of an obstacle;
acquiring a limit pixel value corresponding to the limit distance;
if the pixel value of the obstacle is 0, setting the area, with the pixel value larger than the limiting pixel value, in the obstacle distance map as the feasible area;
and if the pixel value of the obstacle is 255, setting the area of which the pixel value is smaller than the limit pixel value in the obstacle distance map as the feasible area.
6. The robot topology map generation system of claim 5, in which said action trajectory comprises a number of trajectory segments;
processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene, wherein the topological map comprises the following steps:
acquiring a first track node and a second track node corresponding to track segmentation, and generating a first connecting line between the first track node and the second track node;
calculating the distance between the track point on the track segment and the first connecting line, and setting the track point which has the shortest curve distance with the first track node and the distance with the first connecting line is greater than or equal to the distance threshold value as a first middle node;
connecting the first intermediate node with the second track node to generate a second connecting line;
calculating the distance between the track point between the first intermediate node and the second track node and the second connecting line, and setting the track point which has the shortest curve distance with the first intermediate node and the distance with the second connecting line which is greater than or equal to the distance threshold value as the second intermediate node;
repeating the steps until the distances between all the track points on the remaining curves and the corresponding middle connecting lines are smaller than a distance threshold;
sequentially connecting the first track node, the intermediate nodes and the second track node to generate a plurality of track line segments, wherein the intermediate nodes comprise the first intermediate node and the second intermediate node;
and splicing the track line segments to generate a topological path, wherein the topological map comprises the topological path.
7. The robot topology map generating system of claim 6, said stitching said plurality of trajectory segments to generate a topological path, said topological map including said topological path, further comprising:
judging whether the topological path is in the feasible region;
if the topological path is in the feasible region, judging that the topological path is available;
if the topological path is not in the feasible region, receiving a distance modification instruction;
adjusting the limiting distance according to the distance modification instruction to obtain a modified limiting distance;
and generating a modified feasible region according to the modified limiting distance.
8. The robot topology map generating system of claim 6, said stitching said plurality of trajectory segments to generate a topological path, said topological map including said topological path, further comprising:
judging whether the track line segment is in the feasible region;
if the track line segment is not in the feasible region, reducing the numerical value of the distance threshold value to obtain a new distance threshold value;
and executing the step of processing the action track in the feasible region through a preset algorithm by using the new distance threshold value to generate a topological map of the mapping scene.
9. A robot topological map generation method is characterized by comprising the following steps:
acquiring an action track of the robot in a mapping scene;
filtering the action track to generate a uniform point track;
acquiring depth image data corresponding to the homogenization point track;
generating an obstacle distance map of the mapping scene according to the depth image data, and setting a feasible region according to the obstacle distance map;
and processing the action track in the feasible region through a preset algorithm to generate a topological map of the mapping scene.
10. A computer device, wherein the processor, when executing the computer readable instructions, implements the robot topology map generation method of any of claim 9.
11. One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the robot topology map generation method of any of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874201.4A CN113741422B (en) | 2021-07-30 | 2021-07-30 | Robot topology map generation system, method, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874201.4A CN113741422B (en) | 2021-07-30 | 2021-07-30 | Robot topology map generation system, method, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113741422A true CN113741422A (en) | 2021-12-03 |
| CN113741422B CN113741422B (en) | 2024-04-12 |
Family
ID=78729596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110874201.4A Active CN113741422B (en) | 2021-07-30 | 2021-07-30 | Robot topology map generation system, method, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113741422B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100611328B1 (en) * | 2005-06-30 | 2006-08-11 | 고려대학교 산학협력단 | Method and apparatus for building of a thinning-based topological map, method and apparatus for building of thinning-based topological map using topological exploration for a mobile robot |
| CN106643721A (en) * | 2016-10-11 | 2017-05-10 | 北京工业大学 | Construction method of environmental topological map |
| CN107329476A (en) * | 2017-08-02 | 2017-11-07 | 珊口（上海）智能科技有限公司 | A kind of room topology map construction method, system, device and sweeping robot |
| WO2018121448A1 (en) * | 2016-12-30 | 2018-07-05 | 深圳市杉川机器人有限公司 | Topology map creation method and navigation method for mobile robot, programmable device, and computer readable medium |
| US20190286122A1 (en) * | 2018-03-19 | 2019-09-19 | Shenzhen Xiluo Robot Co., Ltd. | Method and System for Presenting Trajectory of Robot and Environmental Map |
| US20190310653A1 (en) * | 2018-04-05 | 2019-10-10 | Electronics And Telecommunications Research Institute | Topological map generation apparatus for navigation of robot and method thereof |
| CN110361009A (en) * | 2019-07-12 | 2019-10-22 | 深圳市银星智能科技股份有限公司 | A kind of paths planning method, path planning system and mobile robot |
| CN111158384A (en) * | 2020-04-08 | 2020-05-15 | 炬星科技（深圳）有限公司 | Robot mapping method, device and storage medium |
| CN111366163A (en) * | 2018-12-25 | 2020-07-03 | 北京欣奕华科技有限公司 | Topological map processing method and device and storage medium |
-
2021
- 2021-07-30 CN CN202110874201.4A patent/CN113741422B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100611328B1 (en) * | 2005-06-30 | 2006-08-11 | 고려대학교 산학협력단 | Method and apparatus for building of a thinning-based topological map, method and apparatus for building of thinning-based topological map using topological exploration for a mobile robot |
| CN106643721A (en) * | 2016-10-11 | 2017-05-10 | 北京工业大学 | Construction method of environmental topological map |
| WO2018121448A1 (en) * | 2016-12-30 | 2018-07-05 | 深圳市杉川机器人有限公司 | Topology map creation method and navigation method for mobile robot, programmable device, and computer readable medium |
| CN107329476A (en) * | 2017-08-02 | 2017-11-07 | 珊口（上海）智能科技有限公司 | A kind of room topology map construction method, system, device and sweeping robot |
| US20190286122A1 (en) * | 2018-03-19 | 2019-09-19 | Shenzhen Xiluo Robot Co., Ltd. | Method and System for Presenting Trajectory of Robot and Environmental Map |
| US20190310653A1 (en) * | 2018-04-05 | 2019-10-10 | Electronics And Telecommunications Research Institute | Topological map generation apparatus for navigation of robot and method thereof |
| CN111366163A (en) * | 2018-12-25 | 2020-07-03 | 北京欣奕华科技有限公司 | Topological map processing method and device and storage medium |
| CN110361009A (en) * | 2019-07-12 | 2019-10-22 | 深圳市银星智能科技股份有限公司 | A kind of paths planning method, path planning system and mobile robot |
| CN111158384A (en) * | 2020-04-08 | 2020-05-15 | 炬星科技（深圳）有限公司 | Robot mapping method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王娜;马昕;: "基于细化算法的移动机器人拓扑地图创建", 计算机技术与发展, no. 10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113741422B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108958233B (en) | Perception simulation method and device | |
| US20220198688A1 (en) | Laser coarse registration method, device, mobile terminal and storage medium | |
| CN109598744B (en) | Video tracking method, device, equipment and storage medium | |
| CN107742304B (en) | Method and device for determining movement track, mobile robot and storage medium | |
| CN109186618B (en) | Map construction method and device, computer equipment and storage medium | |
| CN109543634B (en) | Data processing method and device in positioning process, electronic equipment and storage medium | |
| CN111985300B (en) | Automatic driving dynamic target positioning method and device, electronic equipment and storage medium | |
| CN115609594B (en) | Planning method and device for mechanical arm path, upper control end and storage medium | |
| CN110253579B (en) | Robot positioning method, device, equipment and medium based on arc feature extraction | |
| EP4239596A1 (en) | Method and apparatus for detecting drivable area, mobile device and storage medium | |
| CN115782867A (en) | Track collision risk assessment method and device, electronic equipment and storage medium | |
| CN112700516A (en) | Video rendering method and device based on deep learning, computer equipment and storage medium | |
| CN115143951A (en) | Grid map updating system, method, computer device and storage medium | |
| CN110717141A (en) | Lane line optimization method and device and storage medium | |
| CN113741422B (en) | Robot topology map generation system, method, computer device and storage medium | |
| CN113724383A (en) | Robot topology map generation system, method, computer device and storage medium | |
| CN113724384A (en) | Robot topology map generation system, method, computer device and storage medium | |
| CN111882494A (en) | Pose graph processing method and device, computer equipment and storage medium | |
| CN109360215B (en) | Method, device and equipment for searching outer contour of three-dimensional model and storage medium | |
| CN114459483B (en) | Landmark navigation map construction and application method and system based on robot navigation | |
| CN113932825A (en) | Robot navigation path width acquisition system, method, robot and storage medium | |
| CN115641436A (en) | Region segmentation method and device and robot device | |
| CN114723917A (en) | Pose optimization method, device, medium and equipment of laser odometer | |
| CN114274117A (en) | Robot, robot interaction method and device based on obstacle and medium | |
| CN112529943A (en) | Object detection method, object detection device and intelligent equipment |
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 |