CN115629612A - Obstacle avoidance method, device, equipment and storage medium - Google Patents
Obstacle avoidance method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115629612A CN115629612A CN202211631479.XA CN202211631479A CN115629612A CN 115629612 A CN115629612 A CN 115629612A CN 202211631479 A CN202211631479 A CN 202211631479A CN 115629612 A CN115629612 A CN 115629612A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- contour
- target
- target obstacle
- expanded
- 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 68
- 230000033001 locomotion Effects 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004140 cleaning Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000002411 adverse Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000010813 municipal solid waste Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 235000015243 ice cream Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 235000013555 soy sauce Nutrition 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer 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
- G05D1/0212—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
- G05D1/0231—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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides an obstacle avoidance method, an obstacle avoidance device, equipment and a storage medium, wherein the obstacle avoidance method comprises the following steps: when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle; determining the outline of the target obstacle relative to the ground and the danger level of the target obstacle; expanding the determined contour based on the danger level of the target obstacle to obtain an expanded contour, wherein the distance between the expanded contour and the contour before expansion is in direct proportion to the danger level of the target obstacle; and controlling the movable equipment to move based on the expanded contour so as to realize obstacle avoidance. The obstacle avoidance method provided by the invention has a good obstacle avoidance effect.
Description
Technical Field
The invention relates to the technical field of intelligent obstacle avoidance, in particular to an obstacle avoidance method, device, equipment and storage medium.
Background
With the development of artificial intelligence technology, functions such as intelligent obstacle avoidance, automatic charging, autonomous navigation path planning and the like are added to the movable equipment (such as a cleaning robot), and the increase of the functions greatly improves the intelligent degree of the movable equipment. The intelligent obstacle avoidance means that the movable equipment can be automatically controlled to avoid the obstacle if the movable equipment meets the obstacle in the moving process of the movable equipment.
The current obstacle avoidance scheme mainly comprises the steps of detecting the distance between movable equipment and an obstacle after the obstacle is detected, and controlling the movable equipment to avoid obstacle movement when the distance between the movable equipment and the obstacle reaches a set distance. Although the existing obstacle avoidance scheme can realize the obstacle avoidance reaction when encountering an obstacle, the obstacle avoidance effect is not good.
Disclosure of Invention
In view of this, the present invention provides an obstacle avoidance method, apparatus, device and storage medium, so as to solve the problem that the current obstacle avoidance scheme has a poor obstacle avoidance effect, and the technical scheme is as follows:
an obstacle avoidance method, comprising:
when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle;
determining the outline of the target obstacle relative to the ground and the danger level of the target obstacle;
expanding the contour based on the danger level of the target obstacle to obtain an expanded contour, wherein the distance between the expanded contour and the contour before expansion is in direct proportion to the danger level of the target obstacle;
controlling the movable device to move based on the expanded profile.
Optionally, the identifying the detected obstacle, where the identified obstacle is used as a target obstacle, includes:
acquiring relevant data of the detected obstacle, wherein the relevant data comprises an obstacle image and a depth map corresponding to the obstacle image;
recognizing an obstacle in the obstacle image, wherein the recognized obstacle is used as a target obstacle;
determining a profile of the target obstacle relative to a ground surface, comprising:
and determining the outline of the target obstacle relative to the ground based on the obstacle image and the depth map corresponding to the obstacle image.
Optionally, the determining a contour of the target obstacle with respect to the ground based on the obstacle image and a depth map corresponding to the obstacle image includes:
determining distance information of the movable device and the target obstacle based on the obstacle image and a depth map corresponding to the obstacle image;
determining a profile of the target obstacle relative to a ground surface based on the distance information of the movable device to the target obstacle.
Optionally, the determining the profile of the target obstacle relative to the ground based on the distance information between the movable device and the target obstacle includes:
determining an actual contour of the target obstacle relative to the ground based on distance information of the movable device and the target obstacle, wherein the actual contour of the target obstacle relative to the ground is a contour formed by projection of part or all of the target obstacle in a direction vertical to the ground;
and processing the actual contour of the target obstacle relative to the ground into a contour of a specified shape as a final contour of the target obstacle relative to the ground.
Optionally, the expanding the contour based on the risk level of the target obstacle includes:
determining a contour expansion distance based on the danger level of the target obstacle, a preset expansion distance coefficient and the radius of the movable equipment;
expanding the contour based on the contour expansion distance.
Optionally, determining the risk level to which the target obstacle belongs includes:
determining the danger level of the target obstacle based on the pre-constructed obstacle level information;
the obstacle grade information comprises a plurality of obstacles and danger grades to which the obstacles belong respectively, and the obstacles comprise the target obstacle.
Optionally, the obstacle avoidance method further includes:
and in the process of controlling the movable equipment to move based on the expanded contour, if the movable equipment is detected to touch the target obstacle, adjusting the danger level of the target obstacle in the obstacle level information.
Optionally, the controlling the movable device to move based on the expanded profile includes:
determining whether there are invalid profile segments in the expanded profile;
if not, planning a movement route of the movable equipment in a map based on the expanded contour;
if yes, planning a movement route of the movable equipment in a map based on the effective contour segment in the expanded contour;
and controlling the movable equipment to move according to the movement route planned in the map.
Optionally, the obstacle avoidance method further includes:
after determining the dilated contour, generating the dilated contour in a map.
An obstacle avoidance apparatus comprising: the system comprises an obstacle identification module, an obstacle outline determination module, an obstacle grade determination module, an obstacle outline expansion module and an equipment control module;
the obstacle identification module is used for identifying the detected obstacle when the obstacle exists in the advancing direction of the movable equipment, and the identified obstacle is used as a target obstacle;
the obstacle contour determination module is used for determining the contour of the target obstacle relative to the ground;
the obstacle grade determining module is used for determining the danger grade of the target obstacle;
the obstacle profile expansion module is used for expanding the profile based on the risk level of the target obstacle to obtain an expanded profile, wherein the distance between the expanded profile and the expanded profile is in direct proportion to the risk level of the target obstacle;
the device control module is configured to control the movable device to move based on the expanded profile.
A mobile device, comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement each step of the obstacle avoidance method described in any one of the above.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the obstacle avoidance method of any one of the above.
The invention provides an obstacle avoidance method, an obstacle avoidance device, equipment and a storage medium. The obstacle avoidance method provided by the invention can expand outlines with different expansion distances aiming at the obstacles with different belonging danger levels, and can control the movable equipment to move based on the expanded outlines, and different obstacle avoidance feedbacks can be executed aiming at the obstacles with different belonging danger levels through the obstacle avoidance strategy, so that the adverse effect caused by the fact that the movable equipment touches the high-risk obstacle can be effectively avoided, and for the movable equipment with the cleaning function, the obstacle avoidance strategy can refine the cleaning details and avoid large-area cleaning dead corners.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of an obstacle avoidance method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a process of determining a contour of a target obstacle relative to the ground based on an obstacle image and a depth map corresponding to the obstacle image in the obstacle avoidance method according to the embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating that, in the obstacle avoidance method according to the embodiment of the present invention, the contour of the target obstacle relative to the ground is expanded based on the risk level of the target obstacle, so as to obtain an expanded contour;
FIG. 4 is a schematic view of the expansion of the contour of a target obstacle relative to the ground based on the contour expansion distance provided by an embodiment of the present invention;
fig. 5 is a schematic flow chart illustrating a process of controlling a movable device to move based on an expanded contour in the obstacle avoidance method according to the embodiment of the present invention;
FIG. 6 is a schematic illustration of an expanded profile including inactive profile segments provided by an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an obstacle avoidance device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a mobile device according to an embodiment of the present 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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
The existing obstacle avoidance method can execute the same obstacle avoidance feedback for different obstacles, for example, no matter what kind of obstacles, the movable equipment is controlled to carry out obstacle avoidance movement based on the set same distance.
However, for some obstacles, some adverse effects may be caused after obstacle avoidance by using the current obstacle avoidance method, and for a movable device (such as a cleaning robot) having a cleaning function, performing the same obstacle avoidance feedback for different obstacles may cause a large cleaning dead angle of the movable device during cleaning. Therefore, the existing obstacle avoidance method has poor effect.
In view of the defects of the existing obstacle avoidance method, the invention tries to provide an obstacle avoidance method capable of overcoming the defects of the existing obstacle avoidance method, for this reason, research is carried out, and through continuous research, an obstacle avoidance method with better effect is finally provided.
Before introducing the obstacle avoidance method provided by the present invention, a hardware architecture related to the present invention is explained.
The hardware architecture to which the present invention relates may include: a mobile device.
By way of example, the movable device may be, but is not limited to, a cleaning robot.
The movable equipment can move, and if the movable equipment meets an obstacle in the moving process, the obstacle avoidance method provided by the invention is adopted to carry out obstacle avoidance motion.
It will be understood by those skilled in the art that the above described removable devices are merely exemplary and that other removable devices, now known or later developed, that may be suitable for use with the present invention are also included within the scope of the present invention and are hereby incorporated by reference.
The following embodiments are provided to describe the obstacle avoidance method according to the present invention.
Referring to fig. 1, a schematic flow chart of an obstacle avoidance method according to an embodiment of the present invention is shown, which may include:
step S101: when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle.
The movable device may be a cleaning robot, but the embodiment is not limited thereto, and the movable device may also be other devices, such as a transfer robot.
In step S101, the detected obstacle is identified, that is, what obstacle the detected obstacle is.
Optionally, the process of identifying the detected obstacle may include: acquiring data related to the detected obstacle, wherein the data related to the detected obstacle may include an obstacle image; the obstacle in the obstacle image is recognized, and the recognized obstacle is taken as a target obstacle. It should be noted that the obstacle in the obstacle image is recognized, that is, the specific type of the obstacle in the obstacle image is recognized.
Alternatively, an image capturing device may be provided on the movable device, and the above-described obstacle image may be captured based on the image capturing device provided on the movable device.
Alternatively, the obstacle in the obstacle image may be identified based on an obstacle identification model obtained through pre-training. The obstacle identification model is obtained by training the training obstacle images marked with the types of obstacles, for example, if an obstacle in a training obstacle image is a sofa, the training obstacle image is marked with sand, and if the obstacle in the training obstacle image is a trash can, the training obstacle image is marked with the trash can.
Step S102: the contour of the target obstacle relative to the ground and the hazard level to which the target obstacle belongs are determined.
The "data related to the detected obstacle" may include, in addition to the obstacle image, a depth map corresponding to the obstacle image, and when determining the contour of the target obstacle with respect to the ground, the contour of the target obstacle with respect to the ground may be determined based on the obstacle image and the depth map corresponding to the obstacle image.
Optionally, a depth camera may be disposed on the mobile device, and a depth map corresponding to the obstacle image may be obtained based on the depth camera disposed on the mobile device.
According to the invention, a plurality of danger levels are preset, and after the target obstacle is identified, the danger level of the target obstacle can be determined from the plurality of danger levels.
Illustratively, the preset risk levels include a risk level 1, a risk level 2, a risk level 3, a risk level 4 and a risk level 5, and after the target obstacle is identified, the risk level to which the target obstacle belongs is determined from the risk level 1, the risk level 2, the risk level 3, the risk level 4 and the risk level 5.
It is noted that a higher risk rating of the target obstacle indicates a higher probability of the mobile device contacting the target obstacle, whereas a lower risk rating of the target obstacle indicates a lower probability of the mobile device contacting the target obstacle.
For the above example, it is assumed that 5 danger levels are a danger level 1, a danger level 2, a danger level 3, a danger level 4 and a danger level 5 in sequence from low to high, that is, the danger level 1 is the lowest danger level, and the danger level 5 is the highest danger level, and if the danger level to which the target obstacle belongs is determined to be the danger level 1, it is determined that the movable device has a low possibility of having a bad influence on touching the target obstacle, and if the danger level to which the target obstacle belongs is determined to be the danger level 5, it is determined that the movable device has a high possibility of having a bad influence on touching the target obstacle.
Step S103: and expanding the outline of the target obstacle relative to the ground based on the danger level of the target obstacle to obtain an expanded outline.
Illustratively, the preset danger levels comprise a danger level 1, a danger level 2, a danger level 3, a danger level 4 and a danger level 5, and if the danger level to which the target obstacle belongs is determined to be the danger level 4, the contour of the target obstacle relative to the ground is expanded based on the danger level 4, so as to obtain an expanded contour.
When the contour of the target obstacle relative to the ground is expanded based on the risk level to which the target obstacle belongs, the contour expansion distance may be determined based on the risk level to which the target obstacle belongs, and then the contour of the target obstacle relative to the ground is expanded based on the determined contour expansion distance to obtain the expanded contour. Wherein the profile expansion distance refers to the distance between the expanded profile and the pre-expanded profile.
It should be noted that the expansion distance of the contour is proportional to the danger level of the target obstacle, that is, the distance between the expanded contour and the pre-expanded contour of the target obstacle is larger as the danger level of the target obstacle is higher.
In addition, it should be noted that, a plurality of obstacles may exist in a scene where the mobile device is located, such as sofas, tables, keys, slippers and the like, and sizes, heights and the like of different obstacles are different, which results in that when the image capturing device captures an image of an obstacle, the image capturing device can capture a full view of some obstacles, only a partial view of some obstacles can be captured, and for the obstacle that can capture a full view, a complete contour can be determined based on a depth map corresponding to the obstacle image and the obstacle image, while for the obstacle that can only capture a partial obstacle, a complete contour can be determined and only a partial contour can be determined based on the depth map corresponding to the obstacle image and the obstacle image, and for this case, in one possible implementation manner, another partial contour can be predicted by using the determined contour (for example, a contour prediction model that can predict another contour based on a partial contour can be trained in advance), so as to obtain a complete contour, in another possible implementation manner, an obstacle image can be obtained in real time during the movement of the mobile device, and the image of the obstacle can be obtained in a real-time mode, that the image of the obstacle and the depth map of the obstacle are updated, and the real-time determination of the obstacle image, and the image, that the image of the obstacle are updated, and the updated real-based on the updated real-time determination, and the updated image, and the updated real-time determination of the updated image, and the updated image of the updated obstacle.
Step S104: the movable device is controlled to move based on the expanded profile.
There are various ways of controlling the movable device to move based on the expanded profile, and in one possible way, the movable device may be controlled to track the expanded profile, i.e. the expanded profile is used as the movement path of the movable device to control the movable device to move along the expanded profile, and in another possible way, the movable device may be controlled to move at a set distance from the expanded profile, e.g. the movable device may be controlled to move at a set distance from the expanded profile outside the expanded profile.
It should be noted that there may be invalid contour segments (contour segments that the movable device cannot reach) in the expanded contour, and therefore, when the movable device is controlled to move based on the expanded contour, the validity of the contour segments in the expanded contour may be determined, and the movable device is controlled to move based on only the valid contour segments.
According to the obstacle avoidance method provided by the embodiment of the invention, when the obstacle exists in the advancing direction of the movable equipment, the detected obstacle is firstly identified, the identified obstacle is used as a target obstacle, then the outline of the target obstacle relative to the ground and the danger level of the target obstacle are determined, then the determined outline is expanded based on the danger level of the target obstacle to obtain the expanded outline, and finally the movable equipment is controlled to move based on the expanded outline to realize obstacle avoidance. The obstacle avoidance method provided by the embodiment of the invention can expand the outlines with different expansion distances aiming at the obstacles with different belonging danger levels, can control the movable equipment to move based on the expanded outlines, and can realize different obstacle avoidance feedbacks aiming at the obstacles with different belonging danger levels through the obstacle avoidance strategy, thereby effectively avoiding the adverse effect caused by the fact that the movable equipment touches the high-risk obstacle.
In another embodiment of the present invention, for the "step S102: the specific implementation process of determining the contour of the target obstacle relative to the ground and the danger level to which the target obstacle belongs is described.
An implementation of determining the contour of a target obstacle relative to the ground will first be described.
The above embodiments mention that the contour of the target obstacle with respect to the ground can be determined based on the obstacle image and the depth map corresponding to the obstacle image, and this process is described next.
Referring to fig. 2, a schematic flow chart of determining a contour of a target obstacle relative to a ground surface based on an obstacle image and a depth map corresponding to the obstacle image is shown, which may include:
step S201: and determining distance information of the movable equipment and the target obstacle based on the obstacle image and the depth map corresponding to the obstacle image.
Specifically, the process of determining the distance information between the movable device and the target obstacle based on the obstacle image and the depth map corresponding to the obstacle image may include:
step S2011, a region where the target obstacle is located from the obstacle image as a target obstacle region.
Optionally, the region where the target obstacle is located, that is, the target obstacle region, may be segmented from the obstacle image based on an obstacle segmentation model obtained through pre-training. The obstacle segmentation model is obtained by training an obstacle training image marked with indication information of an area where an obstacle is located.
It should be noted that the present embodiment is not limited to the positioning of the target obstacle region based on the obstacle segmentation model, and other methods capable of positioning the target obstacle region from the obstacle image are also applicable to the present invention.
Step S2012, a pixel value of a pixel point in a region corresponding to the target obstacle region is obtained from the depth map corresponding to the obstacle image, and the pixel value is used as distance information between the mobile device and the target obstacle.
After a target obstacle area is positioned from the obstacle image, distance information corresponding to each pixel point in the target obstacle area (namely the pixel value of each pixel point in the area corresponding to the target obstacle area in the depth image corresponding to the obstacle image) can be acquired from the depth image corresponding to the obstacle image, and the distance information corresponding to each pixel point in the target obstacle area is the distance information between the movable equipment and the target obstacle.
Step S202: and determining the profile of the target obstacle relative to the ground based on the distance information of the movable equipment and the target obstacle.
After obtaining the distance information between the movable device and the target obstacle, the actual contour of the target obstacle relative to the ground may be determined based on the distance information between the movable device and the target obstacle, and for convenience of subsequent operations, after determining the actual contour of the target obstacle relative to the ground, the determined contour may be further processed into a contour of a specified shape, such as a circular contour. Wherein, the actual contour of the target obstacle relative to the ground is a contour formed by the projection of part or all of the target obstacle along the direction vertical to the ground.
The implementation of determining the risk level to which the target obstacle belongs will be described next.
The implementation of determining the hazard level to which the target obstacle belongs may include: and determining the danger level of the target obstacle based on the pre-constructed obstacle level information.
The pre-constructed obstacle grade information comprises a plurality of obstacles and danger grades to which the obstacles belong respectively, and the obstacles comprise target obstacles.
Illustratively, the pre-constructed obstacle level information is as follows:
assuming that the target obstacle is the obstacle 2 in the above table, the danger level to which the target obstacle belongs is determined to be the danger level 3, and assuming that the target obstacle is the obstacle 5 in the above table, the danger level to which the target obstacle belongs is determined to be the danger level 4.
Obstacles in the pre-constructed obstacle level information cover all possible obstacles in the application scene of the movable equipment as much as possible, and the danger level of the obstacles in the obstacle level information can be set by considering the following factors: the harmful effect that the obstacle may cause, the attribute of the obstacle, the scene in which the obstacle is located, the shape volume of the obstacle, etc., for example, for the obstacle such as pet excrement, ice cream, soy sauce, etc., the obstacle can cause large-area pollution by touching, so the obstacle can be set with a high danger level.
The user may supplement the obstacle and the risk level to which the obstacle belongs with respect to the constructed obstacle level information, or may adjust the risk level to which the obstacle belongs in the obstacle level information.
In another embodiment of the present invention, as for the "step S103: and based on the danger level of the target obstacle, expanding the outline of the target obstacle relative to the ground to obtain an expanded outline, and introducing the implementation process.
Referring to fig. 3, a schematic flow chart of expanding the contour of the target obstacle relative to the ground based on the risk level of the target obstacle to obtain an expanded contour is shown, and the method may include:
step S301: determining the contour expansion distance based on the danger level of the target obstacle.
Specifically, the contour expansion distance may be determined based on the danger level to which the target obstacle belongs, the set expansion distance coefficient, and the radius of the movable device. The expansion distance coefficient is a fixed value, and can be set according to a specific application scenario.
Further, if the danger level to which the target obstacle belongs is expressed asLevelThe set expansion distance coefficient is expressed asαThe radius of the movable device is expressed asrThe profile expansion distance is expressed asdThen the profile expands by the distancedThe calculation method of (c) is as follows:
d= Level*α+r (1)
illustratively, the danger level to which the target obstacle belongs is a danger level 1, thend=1*α+r，The danger grade of the target obstacle is 3, thend=3*α+rIf the risk level of the target obstacle is 5, thend=5*α+r。
Step S302: and expanding the outline of the target obstacle relative to the ground on the basis of the determined outline expansion distance to obtain an expanded outline.
Referring to FIG. 4, a graph illustrating expansion distance based on contour is showndA schematic diagram of expanding the contour of the target obstacle with respect to the ground surface, wherein 401 in fig. 4 is the contour of the target obstacle with respect to the ground surface, and 402 in fig. 4 is the expansion distance based on the contourdThe profile 401 is expanded to obtain the profile. The distance between the pre-expansion contour 401 and the post-expansion contour 402 is the contour expansion distanced。
In another embodiment of the present invention, as for the "step S104: the implementation of controlling the movable device to move based on the expanded profile is described.
Referring to FIG. 5, a flow diagram illustrating a process for controlling movement of a movable device based on an expanded profile may include:
step S501: and detecting whether an invalid contour segment exists in the expanded contour, if not, executing the step S502a, and if so, executing the step S502b.
Illustratively, as shown in fig. 6, an obstacle is close to a wall, 601 is the outline of the obstacle relative to the ground, 602 is the outline after the outline 601 is expanded, 603 is the wall, and as can be seen from fig. 6, a part of the expanded outline 602 is inside the wall, namely, the part below 603, which is an invalid outline segment, and the part above 603 in the expanded outline 602 is an effective outline segment.
The purpose of step S501 is to check the validity of the contour segment in order to plan the movement path of the mobile device.
Step S502a: and planning a movement route of the movable equipment in the map based on the expanded contour.
And if the expanded contour does not have the invalid contour segment, directly planning the movement route of the movable equipment in the map based on the expanded contour.
In one possible implementation, the expanded contour may be planned as a movement route of the movable device in the map, and in another possible implementation, a route that maintains a set distance from the expanded contour may be planned as a movement route of the movable device in the map.
Step S502b: and planning a movement route of the movable equipment in the map based on the effective contour segment in the expanded contour.
And if the invalid contour segment exists in the expanded contour, planning the movement route of the movable equipment in the map based on the valid contour segment in the expanded contour. As shown in fig. 6, the movement path of the movable equipment is planned based on the portion above 603 in the expanded contour 602.
Also, in one possible implementation, the active contour segment in the expanded contour may be planned in the map as the movement route of the movable device, and in another possible implementation, a route that is kept at a set distance from the active contour segment in the expanded contour may be planned in the map as the movement route of the movable device.
Step S503: and controlling the movable equipment to move according to the movement route planned in the map.
And controlling the movable equipment to move according to the movement route planned in the map so as to realize obstacle avoidance.
Optionally, after the expanded contour is determined, the expanded contour can be generated in a map, and the expanded contour is generated in the map, so that on one hand, when the subsequent movable device moves to a position nearby, the movement route can be rapidly planned, and on the other hand, when the user watches the map, the obstacle avoidance condition of the movable device can be known conveniently.
In another embodiment of the present invention, the obstacle avoidance method may include, in addition to the steps S101 to S104 in the above embodiments, further include:
and in the process of controlling the movable equipment to move based on the expanded contour, if the movable equipment touches the target obstacle, adjusting the danger level of the target obstacle in the pre-constructed obstacle level information.
In actual use, the movable device may touch the target obstacle during the process of controlling the movable device to move based on the expanded contour, if the situation occurs, the setting of the danger level to which the target obstacle belongs in the pre-constructed obstacle level information may not be appropriate, and in order to avoid the situation appearing later, the danger level to which the target obstacle belongs in the obstacle level information may be adjusted.
For example, the risk level to which the target obstacle belongs in the constructed obstacle level information may be increased, so that when the target obstacle appears again in the advancing direction of the mobile device, the contour of the target obstacle with respect to the ground may be expanded based on the increased risk level, and the mobile device may be controlled to move based on the expanded contour.
Illustratively, the danger level of the target obstacle is danger level 2, when the movable device touches the target obstacle in the process of expanding the contour of the target obstacle relative to the ground based on the danger level 2 and controlling the movable device to move based on the expanded contour, the level of the target obstacle in the constructed obstacle level information is adjusted from danger level 2 to danger level 3, when the movable device encounters the target obstacle again, the contour of the target obstacle relative to the ground is expanded based on the danger level 3, and then the movable device is controlled to move based on the expanded contour.
Alternatively, the movable device may be provided with a collision sensor, and whether the movable device touches an obstacle may be detected based on the collision sensor in controlling the movable device to move based on the expanded contour.
The following describes the obstacle avoidance apparatus provided in the embodiment of the present invention, and the obstacle avoidance apparatus described below and the obstacle avoidance method described above may be referred to in a mutually corresponding manner.
Referring to fig. 7, a schematic structural diagram of an obstacle avoidance device according to an embodiment of the present invention is shown, which may include: an obstacle identification module 701, an obstacle profile determination module 702, an obstacle level determination module 703, an obstacle profile expansion module 704 and a device control module 705.
And an obstacle identifying module 701, configured to identify a detected obstacle when it is detected that an obstacle exists in a forward direction of the mobile device, where the identified obstacle is a target obstacle.
An obstacle profile determination module 702 for determining a profile of the target obstacle relative to the ground.
An obstacle level determining module 703, configured to determine a risk level to which the target obstacle belongs.
And an obstacle contour expansion module 704, configured to expand the contour based on the risk level to which the target obstacle belongs, so as to obtain an expanded contour.
Wherein a distance between the post-dilation profile and the pre-dilation profile is proportional to a hazard level to which the target obstacle belongs.
A device control module 705 for controlling the movable device to move based on the expanded profile.
Optionally, the obstacle identifying module 701 may include: an obstacle data acquisition sub-module and an obstacle identification sub-module.
And the obstacle data acquisition sub-module is used for acquiring the related data of the detected obstacle.
Wherein the relevant data comprises an image of an obstacle and a depth map corresponding to the image of the obstacle.
And the obstacle identification submodule is used for identifying the obstacles in the obstacle image, and the identified obstacles are used as target obstacles.
The obstacle contour determination module 702 is specifically configured to determine the contour of the target obstacle with respect to the ground based on the obstacle image and the depth map corresponding to the obstacle image when determining the contour of the target obstacle with respect to the ground.
Optionally, the obstacle contour determining module 702 includes: a distance information determination sub-module and a contour determination sub-module.
The distance information determining submodule is used for determining the distance information between the movable equipment and the target obstacle based on the obstacle image and the depth map corresponding to the obstacle image;
a contour determination submodule for determining a contour of the target obstacle relative to the ground based on distance information of the movable device from the target obstacle.
Optionally, when determining the contour of the target obstacle relative to the ground based on the distance information between the movable device and the target obstacle, the contour determination sub-module is specifically configured to:
determining an actual contour of the target obstacle relative to the ground based on distance information of the movable device and the target obstacle, wherein the actual contour of the target obstacle relative to the ground is a contour formed by projection of part or all of the target obstacle in a direction vertical to the ground;
and processing the actual contour of the target obstacle relative to the ground into a contour of a specified shape as a final contour of the target obstacle relative to the ground.
Optionally, the obstacle profile expansion module 704 may include: a contour expansion distance determination sub-module and a contour expansion sub-module.
And the contour expansion distance determining submodule is used for determining the contour expansion distance based on the danger level of the target obstacle, a preset expansion distance coefficient and the radius of the movable equipment.
A contour expansion submodule to expand the contour based on the contour expansion distance.
Optionally, when determining the risk level of the target obstacle, the obstacle level determining module 703 is specifically configured to:
determining the danger level of the target obstacle based on the pre-constructed obstacle level information;
the obstacle grade information comprises a plurality of obstacles and danger grades to which the obstacles respectively belong, and the obstacles comprise the target obstacle.
Optionally, the obstacle avoidance device provided in the embodiment of the present invention may further include: and an obstacle level adjusting module.
And the obstacle grade adjusting module is used for adjusting the danger grade of the target obstacle in the obstacle grade information if the movable equipment is detected to touch the target obstacle in the process of controlling the movable equipment to move based on the expanded contour.
Optionally, the device control module 705 may include: the contour validity detection sub-module, the route planning sub-module and the equipment control sub-module.
And the contour validity detection submodule is used for detecting whether invalid contour segments exist in the expanded contour or not.
And the route planning submodule is used for planning the movement route of the movable equipment in the map based on the expanded contour when no invalid contour segment exists in the expanded contour, and planning the movement route of the movable equipment in the map based on the valid contour segment in the expanded contour when the invalid contour segment exists in the expanded contour.
And the device control sub-module is used for controlling the movable device to move according to the movement route planned in the map.
Optionally, the obstacle avoidance apparatus provided in the embodiment of the present invention may further include: and a contour generation module.
A contour generation module configured to generate the expanded contour in the map after the expanded contour is determined by the obstacle contour determination module 702.
According to the obstacle avoidance device provided by the embodiment of the invention, when the obstacle existing in the advancing direction of the movable equipment is detected, the detected obstacle is firstly identified, the identified obstacle is used as a target obstacle, then the outline of the target obstacle relative to the ground and the danger level of the target obstacle are determined, then the determined outline is expanded based on the danger level of the target obstacle to obtain the expanded outline, and finally the movable equipment is controlled to move based on the expanded outline to realize obstacle avoidance. The obstacle avoidance device provided by the embodiment of the invention can expand the outlines with different expansion distances aiming at the obstacles with different belonging danger levels, and can control the movable equipment to move based on the expanded outlines, and different obstacle avoidance feedbacks aiming at the obstacles with different belonging danger levels can be realized through the obstacle avoidance strategy, so that the adverse effect caused by the fact that the movable equipment touches the high-risk obstacle can be effectively avoided, and for the movable equipment with the cleaning function, the obstacle avoidance strategy can refine the cleaning details and avoid large-area cleaning dead corners.
An embodiment of the present invention further provides a mobile device, please refer to fig. 8, which shows a schematic structural diagram of the mobile device, where the mobile device may include: at least one processor 801, at least one communication interface 802, at least one memory 803, and at least one communication bus 804;
in the embodiment of the present invention, the number of the processor 801, the communication interface 802, the memory 803, and the communication bus 804 is at least one, and the processor 801, the communication interface 802, and the memory 803 complete the communication with each other through the communication bus 804;
the processor 801 may be a central processing unit CPU, or an Application Specific Integrated Circuit ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 803 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle;
determining the outline of the target obstacle relative to the ground and the danger level of the target obstacle;
expanding the contour based on the danger level of the target obstacle to obtain an expanded contour, wherein the distance between the expanded contour and the contour before expansion is in direct proportion to the danger level of the target obstacle;
controlling the movable device to move based on the expanded profile.
Alternatively, the detailed function and the extended function of the program may be as described above.
An embodiment of the present invention further provides a readable storage medium, where the readable storage medium may store a program adapted to be executed by a processor, where the program is configured to:
when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle;
determining the outline of the target obstacle relative to the ground and the danger level of the target obstacle;
expanding the contour based on the risk level of the target obstacle to obtain an expanded contour, wherein the distance between the expanded contour and the contour before expansion is in direct proportion to the risk level of the target obstacle;
controlling the movable device to move based on the expanded profile.
Alternatively, the detailed function and the extended function of the program may refer to the above description.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (12)
1. An obstacle avoidance method, comprising:
when the obstacle in the advancing direction of the movable equipment is detected, the detected obstacle is identified, and the identified obstacle is used as a target obstacle;
determining the outline of the target obstacle relative to the ground and the danger level to which the target obstacle belongs;
expanding the contour based on the risk level of the target obstacle to obtain an expanded contour, wherein the distance between the expanded contour and the contour before expansion is in direct proportion to the risk level of the target obstacle;
controlling the movable device to move based on the expanded profile.
2. An obstacle avoidance method according to claim 1, wherein the identifying the detected obstacle, the identified obstacle being a target obstacle, comprises:
acquiring related data of the detected obstacle, wherein the related data comprises an obstacle image and a depth map corresponding to the obstacle image;
recognizing an obstacle in the obstacle image, wherein the recognized obstacle is used as a target obstacle;
determining a profile of the target obstacle relative to a ground surface, comprising:
and determining the outline of the target obstacle relative to the ground based on the obstacle image and the depth map corresponding to the obstacle image.
3. An obstacle avoidance method according to claim 2, wherein the determining the contour of the target obstacle with respect to the ground based on the obstacle image and the depth map corresponding to the obstacle image comprises:
determining distance information between the movable equipment and the target obstacle based on the obstacle image and a depth map corresponding to the obstacle image;
determining a profile of the target obstacle relative to a ground surface based on the distance information of the movable device to the target obstacle.
4. An obstacle avoidance method according to claim 3, wherein the determining the profile of the target obstacle relative to the ground based on the distance information of the movable device from the target obstacle comprises:
determining an actual contour of the target obstacle relative to the ground based on distance information of the movable device and the target obstacle, wherein the actual contour of the target obstacle relative to the ground is a contour formed by projecting part or all of the target obstacle in a direction vertical to the ground;
and processing the actual contour of the target obstacle relative to the ground into a contour of a specified shape as a final contour of the target obstacle relative to the ground.
5. An obstacle avoidance method according to claim 1, wherein the expanding the contour based on the risk level to which the target obstacle belongs comprises:
determining a contour expansion distance based on the danger level of the target obstacle, a preset expansion distance coefficient and the radius of the movable equipment;
expanding the contour based on the contour expansion distance.
6. An obstacle avoidance method according to claim 1, wherein determining the risk level to which the target obstacle belongs comprises:
determining the danger level of the target obstacle based on pre-constructed obstacle level information;
the obstacle grade information comprises a plurality of obstacles and danger grades to which the obstacles belong respectively, and the obstacles comprise the target obstacle.
7. An obstacle avoidance method according to claim 6, further comprising:
and in the process of controlling the movable equipment to move based on the expanded contour, if the movable equipment is detected to touch the target obstacle, adjusting the danger level of the target obstacle in the obstacle level information.
8. An obstacle avoidance method according to any one of claims 1 to 7, wherein the controlling the movable equipment to move based on the expanded contour comprises:
determining whether there are invalid profile segments in the expanded profile;
if not, planning a movement route of the movable equipment in a map based on the expanded contour;
if yes, planning a movement route of the movable equipment in a map based on the effective contour segment in the expanded contour;
and controlling the movable equipment to move according to the movement route planned in the map.
9. An obstacle avoidance method according to claim 8, further comprising:
after determining the dilated contour, generating the dilated contour in a map.
10. An obstacle avoidance device, comprising: the device comprises an obstacle identification module, an obstacle outline determination module, an obstacle grade determination module, an obstacle outline expansion module and a device control module;
the obstacle identification module is used for identifying the detected obstacle when the obstacle exists in the advancing direction of the movable equipment, and the identified obstacle is used as a target obstacle;
the obstacle contour determination module is used for determining the contour of the target obstacle relative to the ground;
the obstacle grade determining module is used for determining the danger grade of the target obstacle;
the obstacle profile expansion module is used for expanding the profile based on the danger level of the target obstacle to obtain an expanded profile, wherein the distance between the expanded profile and the expanded profile is in direct proportion to the danger level of the target obstacle;
the device control module is configured to control the movable device to move based on the expanded profile.
11. A mobile device, comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the obstacle avoidance method according to any one of claims 1 to 9.
12. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the obstacle avoidance method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211631479.XA CN115629612A (en) | 2022-12-19 | 2022-12-19 | Obstacle avoidance method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211631479.XA CN115629612A (en) | 2022-12-19 | 2022-12-19 | Obstacle avoidance method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115629612A true CN115629612A (en) | 2023-01-20 |
Family
ID=84910301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211631479.XA Pending CN115629612A (en) | 2022-12-19 | 2022-12-19 | Obstacle avoidance method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115629612A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797817A (en) * | 2023-02-07 | 2023-03-14 | 科大讯飞股份有限公司 | Obstacle identification method, obstacle display method, related equipment and system |
| CN115993830A (en) * | 2023-03-21 | 2023-04-21 | 佛山隆深机器人有限公司 | Path planning method and device based on obstacle avoidance and robot |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108253968A (en) * | 2017-12-08 | 2018-07-06 | 国网浙江省电力公司温州供电公司 | Based on three-dimensional laser around barrier method |
| CN108344414A (en) * | 2017-12-29 | 2018-07-31 | 中兴通讯股份有限公司 | A kind of map structuring, air navigation aid and device, system |
| CN108646765A (en) * | 2018-07-25 | 2018-10-12 | 齐鲁工业大学 | Based on the quadruped robot paths planning method and system for improving A* algorithms |
| CN108775902A (en) * | 2018-07-25 | 2018-11-09 | 齐鲁工业大学 | The adjoint robot path planning method and system virtually expanded based on barrier |
| CN110522359A (en) * | 2019-09-03 | 2019-12-03 | 深圳飞科机器人有限公司 | The control method of clean robot and clean robot |
| CN110658819A (en) * | 2019-09-30 | 2020-01-07 | 北京猎户星空科技有限公司 | Obstacle avoidance method and device, electronic equipment and storage medium |
| CN110696823A (en) * | 2019-10-15 | 2020-01-17 | 浙江吉利汽车研究院有限公司 | Method and system for predicting collision time of vehicle and vehicle |
| CN112066976A (en) * | 2020-09-07 | 2020-12-11 | 北京信息科技大学 | Self-adaptive expansion processing method and system, robot and storage medium |
| CN112539531A (en) * | 2020-12-08 | 2021-03-23 | 青岛海尔空调器有限总公司 | Obstacle avoidance control method and device and air conditioner |
| CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
| CN114545940A (en) * | 2022-02-21 | 2022-05-27 | 北京三快在线科技有限公司 | Unmanned equipment control method and device and electronic equipment |
| CN114610016A (en) * | 2022-01-25 | 2022-06-10 | 合肥工业大学 | Intelligent vehicle collision avoidance path planning method based on dynamic virtual expansion of barrier |
-
2022
- 2022-12-19 CN CN202211631479.XA patent/CN115629612A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108253968A (en) * | 2017-12-08 | 2018-07-06 | 国网浙江省电力公司温州供电公司 | Based on three-dimensional laser around barrier method |
| US20200340826A1 (en) * | 2017-12-29 | 2020-10-29 | Zte Corporation | Map construction and navigation method, and device and system |
| CN108344414A (en) * | 2017-12-29 | 2018-07-31 | 中兴通讯股份有限公司 | A kind of map structuring, air navigation aid and device, system |
| CN108646765A (en) * | 2018-07-25 | 2018-10-12 | 齐鲁工业大学 | Based on the quadruped robot paths planning method and system for improving A* algorithms |
| CN108775902A (en) * | 2018-07-25 | 2018-11-09 | 齐鲁工业大学 | The adjoint robot path planning method and system virtually expanded based on barrier |
| CN110522359A (en) * | 2019-09-03 | 2019-12-03 | 深圳飞科机器人有限公司 | The control method of clean robot and clean robot |
| CN110658819A (en) * | 2019-09-30 | 2020-01-07 | 北京猎户星空科技有限公司 | Obstacle avoidance method and device, electronic equipment and storage medium |
| CN110696823A (en) * | 2019-10-15 | 2020-01-17 | 浙江吉利汽车研究院有限公司 | Method and system for predicting collision time of vehicle and vehicle |
| CN112066976A (en) * | 2020-09-07 | 2020-12-11 | 北京信息科技大学 | Self-adaptive expansion processing method and system, robot and storage medium |
| CN112539531A (en) * | 2020-12-08 | 2021-03-23 | 青岛海尔空调器有限总公司 | Obstacle avoidance control method and device and air conditioner |
| CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
| CN114610016A (en) * | 2022-01-25 | 2022-06-10 | 合肥工业大学 | Intelligent vehicle collision avoidance path planning method based on dynamic virtual expansion of barrier |
| CN114545940A (en) * | 2022-02-21 | 2022-05-27 | 北京三快在线科技有限公司 | Unmanned equipment control method and device and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797817A (en) * | 2023-02-07 | 2023-03-14 | 科大讯飞股份有限公司 | Obstacle identification method, obstacle display method, related equipment and system |
| CN115797817B (en) * | 2023-02-07 | 2023-05-30 | 科大讯飞股份有限公司 | Obstacle recognition method, obstacle display method, related equipment and system |
| CN115993830A (en) * | 2023-03-21 | 2023-04-21 | 佛山隆深机器人有限公司 | Path planning method and device based on obstacle avoidance and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210109537A1 (en) | Autonomous exploration framework for indoor mobile robotics using reduced approximated generalized voronoi graph | |
| CN115629612A (en) | Obstacle avoidance method, device, equipment and storage medium | |
| CN106796434B (en) | Map generation method, self-position estimation method, robot system, and robot | |
| JP6898442B2 (en) | Obstacle detection system and method | |
| JP6455113B2 (en) | Object tracking method and apparatus | |
| CN113483747B (en) | Improved AMCL (advanced metering library) positioning method based on semantic map with corner information and robot | |
| KR20220083666A (en) | Constrained Mobility Mapping | |
| CN113110482B (en) | Indoor environment robot exploration method and system based on priori information heuristic method | |
| CN112180931B (en) | Cleaning path planning method and device of sweeper and readable storage medium | |
| JP7199937B2 (en) | parking assist device | |
| CN112075879A (en) | Information processing method, device and storage medium | |
| US11562524B2 (en) | Mobile robots to generate occupancy maps | |
| CN115423972A (en) | Closed scene three-dimensional reconstruction method based on vehicle-mounted multi-laser radar fusion | |
| US11948312B2 (en) | Object detection/tracking device, method, and program recording medium | |
| WO2022217794A1 (en) | Positioning method of mobile robot in dynamic environment | |
| KR20160044316A (en) | Device and method for tracking people based depth information | |
| CN111612823A (en) | Robot autonomous tracking method based on vision | |
| JP2021022315A (en) | Image processing apparatus, image processing method, and program | |
| KR100994367B1 (en) | Method for tracking a movement of a moving target of image tracking apparatus | |
| CN103198491A (en) | Indoor visual positioning method | |
| CN114967698A (en) | Cleaning method, cleaning device, electronic apparatus, and storage medium | |
| CN114740867A (en) | Intelligent obstacle avoidance method and device based on binocular vision, robot and medium | |
| CN116958927A (en) | Method and device for identifying short column based on BEV (binary image) graph | |
| CN110826495A (en) | Body left and right limb consistency tracking and distinguishing method and system based on face orientation | |
| Zheng et al. | Automatic detection technique of preceding lane and vehicle |
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: 20230120 |