CN110799989A - Obstacle detection method, equipment, movable platform and storage medium - Google Patents
Obstacle detection method, equipment, movable platform and storage medium Download PDFInfo
- Publication number
- CN110799989A CN110799989A CN201980002940.5A CN201980002940A CN110799989A CN 110799989 A CN110799989 A CN 110799989A CN 201980002940 A CN201980002940 A CN 201980002940A CN 110799989 A CN110799989 A CN 110799989A
- Authority
- CN
- China
- Prior art keywords
- movable platform
- point cloud
- grid
- obstacle
- determining
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000001914 filtration Methods 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims description 39
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013519 translation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000012217 deletion Methods 0.000 description 16
- 230000037430 deletion Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 3
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method, equipment, a movable platform and a storage medium for detecting obstacles, wherein the method comprises the following steps: acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located; filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud; projecting the second point cloud to a two-dimensional plane to obtain at least one projection image; determining obstacle information of the environment around which the movable platform is located according to the at least one projection image. By the method, the calculation complexity can be reduced, and the efficiency and the accuracy of obstacle detection can be improved.
Description
Technical Field
The present invention relates to the field of control technologies, and in particular, to a method and an apparatus for detecting an obstacle, a movable platform, and a storage medium.
Background
At present, with the development of movable platforms such as unmanned vehicles and mobile robots, the safety of the movable platforms in the moving process is more and more concerned, and the detection of obstacles is particularly important. Taking the example of a moving robot, for the moving robot, the obstacle detection on the moving path can be performed by adopting a ray query mode at present. The method comprises the steps of establishing a ray between a robot and a position to be inquired, and starting from the position of a moving robot, searching and counting the number of points in a certain radius range around the ray in a point cloud so as to judge whether an obstacle exists on a path.
However, such query methods often have the defects of low computational efficiency and low accuracy, thereby resulting in low safety of the movable platform during the moving process. Therefore, how to better improve the safety of the movable platform is of great significance.
Disclosure of Invention
The embodiment of the invention provides a method, equipment, a movable platform and a storage medium for detecting obstacles, which can improve the efficiency of detecting the obstacles and reduce the complexity.
In a first aspect, an embodiment of the present invention provides an obstacle detection method applied to a movable platform, where the method includes:
acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located;
filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud;
projecting the second point cloud to a two-dimensional plane to obtain at least one projection image;
determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
In a second aspect, an embodiment of the present invention provides an obstacle detection apparatus, including a memory and a processor;
the memory to store program instructions;
the processor, configured to invoke the program instructions, and when the program instructions are executed, configured to:
acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located;
filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud;
projecting the second point cloud to a two-dimensional plane to obtain at least one projection image;
determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
In a third aspect, an embodiment of the present invention provides a movable platform, including:
a body;
the power system is arranged on the machine body and used for providing power for moving the movable platform;
the obstacle detecting device according to the second aspect described above.
In a fourth aspect, an embodiment of the present invention provides an obstacle detection system, including: an obstacle detection device and a movable platform;
the obstacle detection device is used for acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located; filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud; projecting the second point cloud to a two-dimensional plane to obtain at least one projection image; determining obstacle information of the environment around which the movable platform is located according to the at least one projection image; and sending the obstacle information to a movable platform;
and the movable platform is used for moving by bypassing the obstacle according to the received obstacle information.
In a fifth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method according to the first aspect.
In the embodiment of the invention, the obstacle detection equipment filters the first point cloud to obtain the second point cloud by acquiring the first point cloud corresponding to the surrounding environment where the movable platform is located according to the size information of the movable platform, so that the calculation complexity is reduced; and projecting the second point cloud to a two-dimensional plane to obtain at least one projection image, and determining obstacle information of the surrounding environment where the movable platform is located according to the at least one projection image, so that the obstacle detection efficiency and accuracy are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described 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 to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of a point cloud provided by an embodiment of the present invention;
FIG. 2 is a schematic side view of a point cloud filter according to an embodiment of the present invention;
FIG. 3a is a schematic plan view of a point cloud provided by an embodiment of the present invention;
FIG. 3b is a schematic plan view of a defined area provided by an embodiment of the present invention;
FIG. 3c is a schematic plan view of another defined area provided by an embodiment of the present invention;
FIG. 4a is a diagram illustrating a vote count provided by an embodiment of the present invention;
FIG. 4b is a diagram illustrating a region partition according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an obstacle detection system according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a method for detecting an obstacle according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an obstacle detection device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly 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 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.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
The obstacle detection method provided in the embodiment of the present invention may be executed by an obstacle detection system, and specifically, may be executed by an obstacle detection device in the obstacle detection system. Wherein the obstacle detection system comprises an obstacle detection device and a movable platform. In some embodiments, the obstacle detection device may be mounted on a movable platform; in some embodiments, the obstacle detection device may be spatially independent of the movable platform; in some embodiments, the obstacle detecting device may be a component of a movable platform, i.e. the movable platform comprises the obstacle detecting device.
In other embodiments, the obstacle detection method may also be applied to other mobile devices, such as a robot, an unmanned vehicle, an unmanned ship, and other mobile devices capable of autonomous movement.
The obstacle detection device in the obstacle detection system may obtain a first point cloud corresponding to an ambient environment where the movable platform is located, as shown in fig. 1, fig. 1 is a schematic view of a point cloud provided in an embodiment of the present invention, where the point cloud in fig. 1 is the obtained first point cloud corresponding to the ambient environment where the movable platform 11 is located. In some embodiments, the first point cloud may be obtained by a laser radar, or may be obtained by a camera on a movable platform, which is not specifically limited in the embodiments of the present invention.
In the embodiment of the invention, the motion plane constraint of the movable platform on the plane is considered, and the acquired point cloud contains a considerable part of redundant information, so after the first point cloud is acquired, the obstacle detection equipment can preprocess the first point cloud. When the obstacle detection device preprocesses the first point cloud, the obstacle detection device can acquire the size information of the movable platform, and filter the first point cloud according to the size information of the movable platform to obtain a second point cloud.
In an embodiment, the size information of the movable platform includes a height of the movable platform, and the obstacle detection device may acquire the height of the movable platform when filtering the first point cloud to obtain a second point cloud according to the size information of the movable platform, determine an area above the height of the movable platform as a deletion area according to the height of the movable platform, and delete the point cloud in the deletion area to obtain the second point cloud.
In one embodiment, the size information of the movable platform includes a safe crossing height of the movable platform, and the obstacle detection device may acquire the safe crossing height of the movable platform when filtering the first point cloud to obtain a second point cloud according to the size information of the movable platform, determine an area below the safe crossing height of the movable platform as a deletion area according to the safe crossing height of the movable platform, and delete the point cloud in the deletion area to obtain the second point cloud.
In one embodiment, the size information of the movable platform includes a height of the movable platform and a safe crossing height, and the obstacle detection device may acquire the height of the movable platform and the safe crossing height when filtering the first point cloud to obtain the second point cloud according to the size information of the movable platform, determine an area above the height of the movable platform as a first deletion area, determine an area below the safe crossing height as a second deletion area, and delete the point clouds in the first deletion area and the second deletion area to obtain the second point cloud.
Specifically, as illustrated in fig. 2 by way of example, fig. 2 is a schematic side view of a point cloud filtering according to an embodiment of the present invention, and as shown in fig. 2, according to a safe crossing height position 22 and a height position 23 of a movable platform 20, a first deletion area 24 and a second deletion area 25 outside an area between the safe crossing height position 22 and the height position 23 of the movable platform may be determined, point clouds in the first deletion area 24 and the second deletion area 25 are deleted to obtain a second point cloud area 26 between the safe crossing height position 22 and the height position 23 of the movable platform, and the point cloud in the second point cloud area 26 is determined to be a second point cloud.
Alternatively, taking the unmanned vehicle as an example, the safe crossing height may be the chassis height of the unmanned vehicle, or a height determined based on the chassis height of the unmanned vehicle.
For a planar motion robot, obstacles above the height position 23 of the movable platform will not affect the motion of the movable platform; obstacles between the ground position 21 and the safe crossing height position 22 can be smoothly passed by the movable platform, the point clouds corresponding to the obstacles belong to redundant point clouds, and the complexity of calculating the point clouds can be reduced by deleting the part of the point clouds, so that the obstacle detection efficiency is improved. Therefore, redundant point clouds can be filtered out by filtering the acquired first point cloud of the surrounding environment of the movable platform, so that the complexity of calculating the point clouds in the subsequent obstacle detection is reduced, and the obstacle detection accuracy is improved.
In the embodiment of the invention, after the obstacle detection device obtains the second point cloud through filtering, the obstacle detection device can project the second point cloud to the two-dimensional plane to obtain at least one projection image. Specifically, the description may be made with reference to fig. 2 and fig. 3a, where fig. 3a is a schematic plan view of a point cloud provided in an embodiment of the present invention, and after the obstacle detecting device obtains the second point cloud in the second point cloud area 26 shown in fig. 2 through filtering, the obstacle detecting device may project the second point cloud in the second point cloud area 26 onto the two-dimensional plane shown in fig. 3a to obtain the projection image 31.
In an embodiment of the present invention, the obstacle detecting device may determine obstacle information of an environment around which the movable platform is located according to the at least one projection image.
In one embodiment, when determining obstacle information of an environment around the movable platform from the projection image, the obstacle detecting device may determine an appropriate area from the projection image according to a type of the movable platform and divide the area into a plurality of grid areas. The obstacle detection apparatus may determine whether each grid region is an obstacle region according to the number of point clouds and/or depth information in each grid region. In certain embodiments, the depth information is a distance of the second point cloud to a movable platform.
In certain embodiments, the types of movable platforms include, but are not limited to, omnidirectional exercise robots, non-omnidirectional exercise robots (e.g., three-wheeled mobile robots), and the like. If the type of the movable platform is the omnidirectional moving robot, the obstacle detection device may determine the area by using the position of the omnidirectional moving robot as a geometric center. If the type of the movable platform is a non-omnidirectional moving robot, the obstacle detection device may determine the area by using the position of the non-omnidirectional moving robot as a bottom boundary point.
Specifically, as an example, fig. 3b is a schematic plan view of determining an area, provided by an embodiment of the present invention, where it is assumed that the type of the movable platform is an omnidirectional moving robot, and if the obstacle detection device acquires the current position 32 of the omnidirectional moving robot, the current position 32 of the omnidirectional moving robot may be a geometric center, an area 33 is determined from the projection image 31, and the area 33 is divided into a plurality of grid areas.
Taking fig. 3c as an example, fig. 3c is a schematic plan view of another determined area provided in the embodiment of the present invention, and assuming that the type of the movable platform is a non-omnidirectional moving robot, if the obstacle detecting device acquires the current position 34 of the non-omnidirectional moving robot, the current position 34 of the non-omnidirectional moving robot may be a boundary point at the bottom of the area, an area 35 is determined from the projection image 31, and the area 35 is divided into a plurality of grid areas.
In one embodiment, the obstacle detecting device may divide the area into a plurality of grid areas according to size information of the movable platform. The grid area is not much valuable smaller than the size of the movable platform, and thus the grid area can be divided by information larger than the size of the movable platform.
In one embodiment, if a point cloud exists in the grid area, it represents that an obstacle exists, but in reality, a considerable portion of the point cloud in the grid area does not represent an actual obstacle due to noise and false detection.
In one embodiment, when point clouds are acquired through a camera, due to the characteristic that an object in an image is large and small, for an obstacle a and an obstacle B with the same size, the number of the point clouds corresponding to the obstacle a at a far position is small, the number of the point clouds corresponding to the obstacle B at a near position is large, and if the number of the point clouds is used as an obstacle judgment standard, the obstacle a at the far position may be detected by mistake. Therefore, in the embodiment of the present invention, the obstacle detecting device may determine voting information of each point cloud in each grid region according to the depth information of the point clouds, determine an evaluation parameter of each grid region according to the number of the point clouds and the voting information, and compare the evaluation parameter with a preset parameter, so as to determine that a grid region where the evaluation parameter is greater than the preset parameter is the obstacle region. In some embodiments, the evaluation parameters may include, but are not limited to, numbers, percentages, etc. determined from the voting information.
In some embodiments, the obstacle detecting device may determine, according to the evaluation parameter, an area such as an idle area and an unknown area in the grid area, and the division of the area is not specifically limited in the embodiments of the present invention. In some embodiments, the unknown region may be a grid region without a second point cloud; in some embodiments, the free area may be a grid area where the evaluation parameter is smaller than the preset parameter.
Specifically, the description may be made with reference to fig. 4a and fig. 4b, where fig. 4a is a schematic diagram of a vote count according to an embodiment of the present invention, and fig. 4b is a schematic diagram of a region division according to an embodiment of the present invention. As shown in fig. 4a, the voting information of the grid area 411, the grid area 412, the grid area 413, and the grid area 414 are all 6, that is, the voting number of each point cloud in each grid is 6 votes, 5 point clouds in the grid area 411 total 5 points, and then 30 votes are cast by the 5 point clouds, and the evaluation parameter of the grid area 411 is 30; if the grid area 412 has 6 point clouds, the 6 point clouds cast 36 tickets, and the evaluation parameter of the grid area 412 is 36; if 8 point clouds are arranged in the grid area 413, 48 tickets are cast by the 6 point clouds, and the evaluation parameter of the grid area 413 is 48; if there are 9 point clouds in the grid area 414, 54 votes are cast from the 9 point clouds, and the evaluation parameter of the grid area 414 is 54. The voting information of the grid area 415 is 5, that is, the number of votes of each point cloud in the grid area 415 is 5 votes, and 1 point cloud in the grid area 415 is total, so that 5 votes are cast by 1 point cloud, and the evaluation parameter of the grid area 415 is 5. If the preset parameter is 25, it may be determined that grid area 411, grid area 412, grid area 413, and grid area 414 are all obstacle areas, and grid area 415 is a free area. This allows the determination of the obstacle area 41 (black marked area), the free area 42 (light gray marked area), and the unknown area 43 (dark gray marked area) as shown in fig. 4 b.
According to the embodiment of the invention, the first point cloud corresponding to the acquired surrounding environment of the movable platform is filtered to obtain the second point cloud according to the size information of the movable platform, so that redundant point cloud can be filtered, the efficiency of point cloud processing is improved, and the computational complexity is reduced; by projecting the second point cloud to a two-dimensional plane, at least one projection image is obtained, and the distribution of the point cloud can be viewed from the two-dimensional plane more intuitively and conveniently; according to the at least one projection image, a plurality of grid areas are determined, and further, according to the point cloud number and/or depth information of each grid area, obstacle information is determined, so that the obstacle detection efficiency and accuracy can be improved.
An obstacle detection system provided by an embodiment of the present invention is schematically described below with reference to fig. 5.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an obstacle detection system according to an embodiment of the present invention. The obstacle detection system includes: obstacle detection device 51, movable platform 52. Wherein a communication connection can be established between the movable platform 52 and the obstacle detecting device 51 by means of a wireless communication connection. In some scenarios, the movable platform 52 and the obstacle detecting device 51 may also be connected in communication via a wired communication connection. The movable platform 52 may be a movable device such as an unmanned vehicle, an unmanned ship, a movable robot, etc. The movable platform 52 includes a power system 521, and the power system 521 is used for providing power for the movable platform 52 to move. In other embodiments, the movable platform 52 and the obstacle detecting device 51 are independent of each other, for example, the obstacle detecting device 51 is disposed in a cloud server, and the communication connection with the movable platform 52 is established by a wireless communication connection.
In the embodiment of the present invention, the obstacle detecting device 51 may obtain a first point cloud corresponding to an ambient environment where the movable platform 52 is located; filtering the first point cloud according to the size information of the movable platform 52 to obtain a second point cloud; projecting the second point cloud to a two-dimensional plane to obtain at least one projection image; according to the at least one projection image, obstacle information of the surrounding environment where the movable platform 52 is located is determined, so that the obstacle detection efficiency and accuracy are improved, and the safety of the movable platform 52 in the moving process is improved.
The obstacle detection method provided by the embodiment of the invention is schematically described below with reference to fig. 6 and 7.
Referring to fig. 6 in detail, fig. 6 is a schematic flowchart of an obstacle detection method according to an embodiment of the present invention, which may be executed by an obstacle detection apparatus, where the specific explanation of the obstacle detection apparatus is as described above. Specifically, the method of the embodiment of the present invention includes the following steps.
S601: the method comprises the steps of obtaining a first point cloud corresponding to the surrounding environment where the movable platform is located.
In the embodiment of the invention, the obstacle detection equipment can acquire the first point cloud corresponding to the surrounding environment where the movable platform is located. Taking fig. 1 as an example, the point cloud shown in fig. 1 is the first point cloud of the acquired surrounding environment where the movable platform 11 is located.
In one embodiment, when the obstacle detecting device acquires the first point cloud corresponding to the surrounding environment where the movable platform is located, the obstacle detecting device may acquire the first point cloud corresponding to the surrounding environment where the movable platform is located by using a laser radar.
In some embodiments, the lidar is a perceptual sensor that may obtain three-dimensional information of a scene. The basic principle is that a laser pulse signal is actively emitted to a detected object, a pulse signal reflected by the detected object is obtained, and the depth information of a distance detector of the detected object is calculated according to the time difference between the emitted signal and the received signal; based on the known transmitting direction of the laser radar, obtaining the angle information of the measured object relative to the laser radar; and combining the depth information and the angle information to obtain massive detection points (called point clouds), and reconstructing the spatial three-dimensional information of the detected object relative to the laser radar based on the point clouds.
In one embodiment, when the obstacle detecting device acquires the first point cloud corresponding to the surrounding environment where the movable platform is located, the first point cloud corresponding to the surrounding environment where the movable platform is located may be acquired by a camera. In some embodiments, the camera may be mounted on the movable platform. In some embodiments, the camera may also be mounted independently of the movable platform in the environment in which the movable platform is located. In some embodiments, the camera includes, but is not limited to, a binocular camera, a monocular camera, a TOF camera, and the like.
In some embodiments, when the obstacle detection device obtains a first point cloud corresponding to an ambient environment where the movable platform is located through a camera, the obstacle detection device may convert the point cloud obtained by the camera into a world coordinate system based on a preset conversion matrix to obtain the first point cloud corresponding to the ambient environment where the movable platform is located; the preset conversion matrix comprises an internal reference matrix and an external reference matrix, and the external reference matrix comprises a rotation matrix and/or a translation vector. In certain embodiments, the external reference matrix comprises only a rotation matrix when the origin of the world coordinate system is set on the movable platform.
In some embodiments, the internal parameter matrix is determined according to a plurality of internal parameters, and the internal parameters are parameters obtained by calibrating the camera, such as a focal length, an image principal point coordinate, and the like. In some embodiments, the external reference matrix may include a rotation matrix and/or a translation vector, wherein the rotation matrix may be determined by the pose of the camera and the translation vector may be determined by the positioning information of the camera.
Therefore, the first point cloud is obtained by converting the point cloud acquired by the camera into the world coordinate system, and the point cloud acquired by the camera can be subjected to distortion removal and other processing in the process of converting the point cloud acquired by the camera into the world coordinate system, so that the accuracy of the first point cloud is improved.
S602: and filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud.
In the embodiment of the invention, the obstacle detection device can filter the first point cloud according to the size information of the movable platform to obtain the second point cloud.
In one embodiment, the size information includes a height of the movable platform, and the obstacle detecting device may filter the first point cloud to obtain the second point cloud according to the height of the movable platform when filtering the first point cloud to obtain the second point cloud according to the size information of the movable platform.
In one embodiment, the size information of the movable platform includes a safe crossing height of the movable platform, and the obstacle detecting device may filter the first point cloud to obtain the second point cloud according to the safe crossing height of the movable platform when filtering the first point cloud to obtain the second point cloud according to the size information of the movable platform.
In one embodiment, the size information of the movable platform includes a height of the movable platform and a safe crossing height, and the obstacle detecting device may filter the first point cloud to obtain the second point cloud according to the height of the movable platform and the safe crossing height when filtering the first point cloud to obtain the second point cloud according to the size information of the movable platform.
Taking fig. 2 as an example, according to the safe crossing height position 22 and the height position 23 of the movable platform 20, a first deletion area 24 and a second deletion area 25 outside the area between the safe crossing height position 22 and the height position 23 of the movable platform may be determined, the point clouds in the first deletion area 24 and the second deletion area 25 may be deleted to obtain a second point cloud area 26 between the safe crossing height position 22 and the height position 23 of the movable platform, and the point cloud in the second point cloud area 26 may be determined to be a second point cloud. Therefore, the first point cloud is filtered through the size information of the movable platform, redundant point clouds can be deleted, and the number of the point clouds and the complexity of depth information in subsequent calculation are reduced.
S603: and projecting the second point cloud to a two-dimensional plane to obtain at least one projection image.
In the embodiment of the present invention, the obstacle detecting device may project the second point cloud to a two-dimensional plane to obtain at least one projection image.
In one embodiment, the two-dimensional plane may include a horizontal plane, and the obstacle detecting device may project the second point cloud to the horizontal plane, resulting in at least one projected image. In some embodiments, the horizontal plane is a plane parallel to the position of the movable platform. Taking an unmanned vehicle as an example, assuming that the unmanned vehicle is currently climbing a slope, the horizontal plane is a plane parallel to the slope where the unmanned vehicle is currently located.
In one embodiment, the two-dimensional plane may include a ground surface, and the obstacle detection device may project the second point cloud onto the ground surface, resulting in at least one projected image, which in some embodiments is the ground surface parallel to the movable platform. Taking an unmanned vehicle as an example, the two-dimensional plane may be the ground when the unmanned vehicle is traveling on a level ground.
Therefore, the embodiment of the invention meets the plane mobility of the movable platform by projecting the second point cloud in the world coordinate system to the two-dimensional plane, and is convenient for intuitively calculating the point cloud on the plane.
S604: determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
In an embodiment of the present invention, the obstacle detecting device may determine obstacle information of an environment around which the movable platform is located, according to the at least one projection image.
In an embodiment, when determining the obstacle information of the environment around the movable platform according to the projection image, the obstacle detecting device may divide the projection image into a plurality of grid regions, and determine whether each grid region is an obstacle region according to the point cloud in each grid region, which is described in the foregoing specific embodiments and is not described herein again.
In an embodiment, when the obstacle detecting device divides the projection image into a plurality of grid areas, the type of the movable platform may be obtained, and the positions of the plurality of grid areas may be determined according to the type of the movable platform.
In one embodiment, the type of the movable platform includes an omnidirectional moving robot, and the obstacle detection device may acquire a current position of the omnidirectional moving robot when determining the positions of the plurality of grid areas according to the type of the movable platform, and determine the positions of the plurality of grid areas with the current position of the omnidirectional moving robot as a geometric center.
Specifically, as shown in fig. 3b as an example, assuming that the movable platform is an omnidirectional moving robot, if the current position 32 of the omnidirectional moving robot is located, the obstacle detection device may determine that the current position 32 of the omnidirectional moving robot is a geometric center, determine an area 33 from the projection image 31, and divide the area 33 into a plurality of grid areas.
In one embodiment, the type of the movable platform includes a non-omnidirectional moving robot, and the obstacle detection device may acquire a current position of the non-omnidirectional moving robot when determining the positions of the plurality of grid areas according to the type of the movable platform, and determine the positions of the plurality of grid areas with the current position of the non-omnidirectional moving robot as a boundary point. In some embodiments, the boundary point may be a boundary point of any one of the edges of the determined area, and the boundary point of which edge is determined according to the type of the non-omnidirectional moving robot.
Specifically, as an example in fig. 3c, assuming that the movable platform is a non-omnidirectional moving robot and the non-omnidirectional moving robot is a three-wheeled moving robot, if the current position 34 of the three-wheeled moving robot is detected, the obstacle detection device may determine that the current position 34 of the three-wheeled moving robot is a boundary point in the bottom boundary line, determine an area 33 in which the current position 34 of the three-wheeled moving robot is the boundary point in the bottom boundary line from the projection image 31, and divide the area 33 into a plurality of grid areas.
Therefore, the positions of the grid areas are determined according to the types of the movable platforms, the grid areas can be determined according to the motion characteristics of the movable platforms of different types, the main moving areas of the movable platforms of different types are ensured to be in the grid areas, the moving areas of the movable platforms are prevented from being out of the grid areas and colliding with undetected obstacles outside the grid areas, and therefore safety of the movable platforms of different types in the moving process is improved.
In one embodiment, the obstacle detecting device may acquire a size of the movable platform when dividing the projection image into the plurality of grid regions, and determine a size of each of the plurality of grid regions according to the size of the movable platform. The division of the grid areas smaller than the size of the movable platform is not of great practical value, and therefore, the embodiment of the present invention divides the plurality of grid areas in such a manner that the size of each grid area is larger than the size of the movable platform. The specific embodiments are as described above and will not be described herein.
Therefore, the grid areas are divided according to the fact that the size of each grid area is larger than that of the movable platform, calculation amount required by obstacle detection can be further reduced, and obstacle detection efficiency is improved.
In one embodiment, the obstacle detection device may obtain the number of point clouds in each grid region when determining whether each grid region is an obstacle region according to the point clouds in each grid region, and may determine that the grid region is an obstacle region when the number of point clouds is greater than a preset number threshold.
Taking fig. 4a as an example, assuming that the preset number threshold is 10, if the number of point clouds in grid area 411 is 15, the number of point clouds in grid area 412 is 16, the number of point clouds in grid area 413 is 18, and the number of point clouds in grid area 414 is 20, it may be determined that the number of point clouds in grid area 411, grid area 412, grid area 413, and grid area 414 is greater than the preset number threshold 10, and therefore, it may be determined that the area composed of grid area 411, grid area 412, grid area 413, and grid area 414 is an obstacle area.
Therefore, the embodiment of the invention determines whether the grid area is the obstacle area by judging whether the data of the point clouds in each grid area is larger than the preset number threshold, so that the grid area is determined as the obstacle area under the condition that enough point clouds exist, and the accuracy of obstacle detection is improved.
In one embodiment, when determining whether each grid region is an obstacle region according to the point clouds in each grid region, the obstacle detecting device may acquire the number and depth information of the point clouds in each grid region, and determine whether the grid region is an obstacle region according to the number and depth information of the point clouds.
In one embodiment, when determining whether the grid region is an obstacle region according to the number and depth information of the point clouds, the obstacle detecting device may determine voting information of each point cloud in each grid region according to the depth information of the point clouds, determine an evaluation parameter of each grid region according to the number and the voting information of the point clouds, and compare the evaluation parameter with a preset parameter, thereby determining that the grid region whose evaluation parameter is greater than the preset parameter is the obstacle region. In some embodiments, the obstacles may include, but are not limited to, fixed buildings, other movable equipment, ground facilities, and any one or more objects that impede movement of the movable platform. In some embodiments, the grid area may include, but is not limited to, any one or more of an obstacle area, a free area, an unknown area.
In one embodiment, the obstacle detection device may obtain depth information of each point cloud in each grid region, calculate a depth average value of each point cloud in each grid region, and determine a vote number corresponding to the depth average value according to a preset correspondence between a depth and a vote number, so as to determine a total vote number obtained by all the point clouds in each grid region according to the vote number corresponding to the depth average value. The obstacle detection device may determine an evaluation parameter corresponding to the total number of votes according to a corresponding relationship between a preset total number of votes and the evaluation parameter, compare the evaluation parameter with a preset parameter, and determine that the grid area is an obstacle area if the evaluation parameter is greater than the preset parameter.
Specifically, as an example in fig. 4a, it is assumed that there are point clouds a, B, and C in the grid area 411 and the depths are 1.5m, 1.6m, and 1.7m, the obstacle detection device may average the depths of the point clouds a, B, and C in the grid area 411, and calculate to obtain a depth average value of 1.6m, if the depth average value of 1.6m may correspond to a vote number, such as 2 votes, then the three point clouds a, B, and C in the grid area 411 cast 6 votes in total, and if the evaluation parameter corresponding to the 6 votes is 6 and the preset parameter is 5, it may be determined that the grid area 411 is an obstacle area.
In one embodiment, the obstacle detection device may obtain depth information of each point cloud in each grid region, and determine a vote count corresponding to the depth information of each point cloud according to a preset correspondence between depth and vote count, so as to determine a total vote count obtained by all the point clouds in each grid region according to the vote count corresponding to the depth information of each point cloud. The obstacle detection device may determine an evaluation parameter corresponding to the total number of votes according to a corresponding relationship between a preset total number of votes and the evaluation parameter, compare the evaluation parameter with a preset parameter, and determine that the grid area is an obstacle area if the evaluation parameter is greater than the preset parameter.
Taking fig. 4a as an example, assuming that there are point clouds a, B, C in a grid area 411 and the depths are 1.5m, 1.6m, and 1.7m, if the number of votes corresponding to the depth 1.5m is 1 vote, the number of votes corresponding to the depth 1.6m is 2 votes, and the number of votes corresponding to the depth 1.7m is 3 votes, it may be determined that three point clouds a, B, and C in the grid area 411 cast 6 votes in total, and if the evaluation parameter corresponding to 6 votes is 6 and the preset parameter is 5, it may be determined that the grid area 411 is an obstacle area.
In certain embodiments, the evaluation parameters may include, but are not limited to, numerical, percentage, and the like. For example, if the evaluation parameter is represented by a number, the greater the probability that the area is an obstacle. For another example, if the evaluation parameter is expressed as a percentage, the larger the probability that the area is an obstacle. In other embodiments, the evaluation parameter may also be determined by identifying the type of the obstacle, and is not specifically limited herein.
Therefore, the voting information is determined according to the depth information of the point cloud, the distance between the point cloud and the movable platform is considered, and the accuracy of obstacle detection is improved; and determining evaluation parameters by combining the number of the point clouds, and determining whether the grid area is the obstacle area or not by the evaluation parameters, so that the obstacle detection accuracy can be improved.
In the embodiment of the invention, the obstacle detection equipment filters the first point cloud to obtain the second point cloud by acquiring the first point cloud corresponding to the surrounding environment where the movable platform is located according to the size information of the movable platform, so that the calculation complexity is reduced; and projecting the second point cloud to a two-dimensional plane to obtain at least one projection image, and determining obstacle information of the surrounding environment where the movable platform is located according to the at least one projection image, so that the obstacle detection efficiency and accuracy are improved.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an obstacle detecting device according to an embodiment of the present invention. Specifically, the obstacle detecting device includes: memory 701, processor 702.
In an embodiment, the obstacle detecting device further comprises a data interface 703, the data interface 703 being configured to communicate data information between the obstacle detecting device and other devices.
The memory 701 may include a volatile memory (volatile memory); the memory 701 may also include a non-volatile memory (non-volatile memory); the memory 701 may also comprise a combination of memories of the kind described above. The processor 702 may be a Central Processing Unit (CPU). The processor 702 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), or any combination thereof.
The memory 701 is used for storing program instructions, and the processor 702 may call the program instructions stored in the memory 701 to execute the following steps:
acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located;
filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud;
projecting the second point cloud to a two-dimensional plane to obtain at least one projection image;
determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
Further, the size information includes a height and/or a safe crossing height of the movable platform, and when the processor 702 filters the first point cloud to obtain the second point cloud according to the size information of the movable platform, the processor is specifically configured to:
and filtering the first point cloud according to the height and/or the safe crossing height of the movable platform to obtain a second point cloud.
Further, the two-dimensional plane includes a horizontal plane, and when the processor 702 projects the second point cloud onto the two-dimensional plane to obtain at least one projection image, the processor is specifically configured to:
and projecting the second point cloud to a horizontal plane to obtain at least one projection image.
Further, when determining the obstacle information of the environment around which the movable platform is located according to the projection image, the processor 702 is specifically configured to:
dividing the projected image into a plurality of grid regions;
and determining whether each grid region is an obstacle region according to the point cloud in each grid region.
Further, when the processor 702 divides the projection image into a plurality of grid regions, it is specifically configured to:
acquiring the type of the movable platform;
determining the location of the plurality of grid regions based on the type of the movable platform.
Further, the types of movable platforms include omnidirectional motion robots; the processor 702, when determining the positions of the plurality of grid regions according to the type of the movable platform, is specifically configured to:
acquiring the current position of the omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the omnidirectional moving robot as a geometric center.
Further, the types of movable platforms include non-omnidirectional mobile robots; the processor 702, when determining the positions of the plurality of grid regions according to the type of the movable platform, is specifically configured to:
acquiring the current position of the non-omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the non-omnidirectional moving robot as a boundary point.
Further, when the processor 702 divides the projection image into a plurality of grid regions, it is specifically configured to:
acquiring the size of the movable platform;
determining a size of each of the plurality of grid regions based on the size of the movable platform.
Further, when determining whether each grid region is an obstacle region according to the point cloud in each grid region, the processor 702 is specifically configured to:
acquiring the number of point clouds in each grid area;
and when the number of the point clouds is larger than a preset number threshold, determining that the grid area is an obstacle area.
Further, when determining whether each grid region is an obstacle region according to the point cloud in each grid region, the processor 702 is specifically configured to:
acquiring the number and depth information of the point clouds in each grid area;
and determining whether the grid area is an obstacle area or not according to the number and the depth information of the point clouds.
Further, when the processor 702 determines whether the grid region is an obstacle region according to the number and depth information of the point clouds, it is specifically configured to:
determining voting information of each point cloud in each grid area according to the depth information of the point clouds;
determining an evaluation parameter of each grid area according to the number of the point clouds and the voting information;
and comparing the evaluation parameter with a preset parameter, and determining the grid area with the evaluation parameter larger than the preset parameter as the obstacle area.
Further, the grid area includes any one or more of an obstacle area, a free area, and an unknown area.
Further, when the processor 702 obtains the first point cloud corresponding to the surrounding environment where the movable platform is located, the processor is specifically configured to:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a laser radar.
Further, when the processor 702 obtains the first point cloud corresponding to the surrounding environment where the movable platform is located, the processor is specifically configured to:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a camera.
Further, when the processor 702 obtains the first point cloud corresponding to the surrounding environment where the movable platform is located through the camera, the processor is specifically configured to:
converting the point cloud obtained by the camera into a world coordinate system based on a preset conversion matrix to obtain a first point cloud corresponding to the surrounding environment where the movable platform is located;
the preset conversion matrix comprises an internal reference matrix and an external reference matrix, and the external reference matrix comprises a rotation matrix and/or a translation vector.
In the embodiment of the invention, the obstacle detection equipment filters the first point cloud to obtain the second point cloud by acquiring the first point cloud corresponding to the surrounding environment where the movable platform is located according to the size information of the movable platform, so that the calculation complexity is reduced; and projecting the second point cloud to a two-dimensional plane to obtain at least one projection image, and determining obstacle information of the surrounding environment where the movable platform is located according to the at least one projection image, so that the obstacle detection efficiency and accuracy are improved.
An embodiment of the present invention further provides a movable platform, where the movable platform includes: a body; the power system is arranged on the machine body and used for providing moving power for the movable platform; and the above obstacle detecting device. In the embodiment of the invention, the movable platform obtains the first point cloud corresponding to the surrounding environment where the movable platform is located, the first point cloud is filtered according to the size information of the movable platform to obtain the second point cloud, and the second point cloud is projected to the two-dimensional plane to obtain at least one projection image, so that the obstacle information of the surrounding environment where the movable platform is located is determined according to the at least one projection image, the calculation complexity is reduced, and the obstacle detection efficiency and accuracy are improved.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method described in the embodiment corresponding to fig. 6 of the present invention is implemented, and the apparatus according to the embodiment corresponding to the present invention described in fig. 7 may also be implemented, which is not described herein again.
The computer readable storage medium may be an internal storage unit of the device according to any of the foregoing embodiments, for example, a hard disk or a memory of the device. The computer readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the apparatus. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
The above disclosure is intended to be illustrative of only some embodiments of the invention, and is not intended to limit the scope of the invention.
Claims (33)
1. An obstacle detection method, applied to a movable platform, the method comprising:
acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located;
filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud;
projecting the second point cloud to a two-dimensional plane to obtain at least one projection image;
determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
2. The method of claim 1, wherein the dimensional information comprises a height and/or a safe ride height of the movable platform, and wherein filtering the first point cloud to obtain a second point cloud based on the dimensional information of the movable platform comprises:
and filtering the first point cloud according to the height and/or the safe crossing height of the movable platform to obtain a second point cloud.
3. The method of claim 1, wherein the two-dimensional plane comprises a horizontal plane, and wherein projecting the second point cloud onto the two-dimensional plane results in at least one projection image comprising:
and projecting the second point cloud to a horizontal plane to obtain at least one projection image.
4. The method of claim 1, wherein determining from the projected image obstacle information for the environment around which the movable platform is located comprises:
dividing the projected image into a plurality of grid regions;
and determining whether each grid region is an obstacle region according to the point cloud in each grid region.
5. The method of claim 4, wherein the dividing the projected image into a plurality of grid regions comprises:
acquiring the type of the movable platform;
determining the location of the plurality of grid regions based on the type of the movable platform.
6. The method of claim 5, wherein the type of movable platform comprises an omnidirectional motion robot; the determining the locations of the plurality of grid regions based on the type of the movable platform comprises:
acquiring the current position of the omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the omnidirectional moving robot as a geometric center.
7. The method of claim 5, wherein the type of movable platform comprises a non-omnidirectional motion robot; the determining the locations of the plurality of grid regions based on the type of the movable platform comprises:
acquiring the current position of the non-omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the non-omnidirectional moving robot as a boundary point.
8. The method of claim 4, wherein the dividing the projected image into a plurality of grid regions comprises:
acquiring the size of the movable platform;
determining a size of each of the plurality of grid regions based on the size of the movable platform.
9. The method of claim 4, wherein determining whether each grid region is an obstacle region from the point cloud in each grid region comprises:
acquiring the number of point clouds in each grid area;
and when the number of the point clouds is larger than a preset number threshold, determining that the grid area is an obstacle area.
10. The method of claim 4, wherein determining whether each grid region is an obstacle region from the point cloud in each grid region comprises:
acquiring the number and depth information of the point clouds in each grid area;
and determining whether the grid area is an obstacle area or not according to the number and the depth information of the point clouds.
11. The method of claim 10, wherein determining whether the grid region is an obstacle region based on the number and depth information of the point clouds comprises:
determining voting information of each point cloud in each grid area according to the depth information of the point clouds;
determining an evaluation parameter of each grid area according to the number of the point clouds and the voting information;
and comparing the evaluation parameter with a preset parameter, and determining the grid area with the evaluation parameter larger than the preset parameter as the obstacle area.
12. The method of claim 4, wherein the grid region comprises any one or more of an obstacle region, a free region, and an unknown region.
13. The method of claim 1, wherein the obtaining a first point cloud corresponding to an environment surrounding the movable platform comprises:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a laser radar.
14. The method of claim 1, wherein the obtaining a first point cloud corresponding to an environment surrounding the movable platform comprises:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a camera.
15. The method of claim 14, wherein the acquiring, by a camera, a first point cloud corresponding to an environment around which the movable platform is located comprises:
converting the point cloud obtained by the camera into a world coordinate system based on a preset conversion matrix to obtain a first point cloud corresponding to the surrounding environment where the movable platform is located;
the preset conversion matrix comprises an internal reference matrix and an external reference matrix, and the external reference matrix comprises a rotation matrix and/or a translation vector.
16. An obstacle detection apparatus, comprising a memory and a processor;
the memory to store program instructions;
the processor, configured to invoke the program instructions, and when the program instructions are executed, configured to:
acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located;
filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud;
projecting the second point cloud to a two-dimensional plane to obtain at least one projection image;
determining obstacle information of the environment around which the movable platform is located according to the at least one projection image.
17. The apparatus of claim 16, wherein the dimension information comprises a height of the movable platform and/or a safe ride-through height, and wherein the processor is configured to, when filtering the first point cloud to obtain the second point cloud according to the dimension information of the movable platform, specifically:
and filtering the first point cloud according to the height and/or the safe crossing height of the movable platform to obtain a second point cloud.
18. The apparatus of claim 16, wherein the two-dimensional plane comprises a horizontal plane, and wherein the processor is configured to project the second point cloud onto the two-dimensional plane to obtain at least one projection image, and is further configured to:
and projecting the second point cloud to a horizontal plane to obtain at least one projection image.
19. The apparatus of claim 16, wherein the processor is configured to determine, from the projected image, obstacle information of an environment surrounding the movable platform, and in particular to:
dividing the projected image into a plurality of grid regions;
and determining whether each grid region is an obstacle region according to the point cloud in each grid region.
20. The device of claim 19, wherein the processor, when dividing the projected image into a plurality of grid regions, is specifically configured to:
acquiring the type of the movable platform;
determining the location of the plurality of grid regions based on the type of the movable platform.
21. The apparatus of claim 20, wherein the type of movable platform comprises an omnidirectional exercise robot; the processor, when determining the positions of the plurality of grid regions according to the type of the movable platform, is specifically configured to:
acquiring the current position of the omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the omnidirectional moving robot as a geometric center.
22. The apparatus of claim 20, wherein the type of movable platform comprises a non-omnidirectional motion robot; the processor, when determining the positions of the plurality of grid regions according to the type of the movable platform, is specifically configured to:
acquiring the current position of the non-omnidirectional moving robot;
and determining the positions of the grid areas by taking the current position of the non-omnidirectional moving robot as a boundary point.
23. The device of claim 19, wherein the processor, when dividing the projected image into a plurality of grid regions, is specifically configured to:
acquiring the size of the movable platform;
determining a size of each of the plurality of grid regions based on the size of the movable platform.
24. The apparatus according to claim 19, wherein the processor, when determining from the point cloud in each grid region whether said each grid region is an obstacle region, is configured to:
acquiring the number of point clouds in each grid area;
and when the number of the point clouds is larger than a preset number threshold, determining that the grid area is an obstacle area.
25. The apparatus according to claim 19, wherein the processor, when determining from the point cloud in each grid region whether said each grid region is an obstacle region, is configured to:
acquiring the number and depth information of the point clouds in each grid area;
and determining whether the grid area is an obstacle area or not according to the number and the depth information of the point clouds.
26. The apparatus of claim 25, wherein the processor is configured to determine whether the grid region is an obstacle region based on the number and depth information of the point clouds, and is further configured to:
determining voting information of each point cloud in each grid area according to the depth information of the point clouds;
determining an evaluation parameter of each grid area according to the number of the point clouds and the voting information;
and comparing the evaluation parameter with a preset parameter, and determining the grid area with the evaluation parameter larger than the preset parameter as the obstacle area.
27. The apparatus of claim 19, wherein the grid region comprises any one or more of an obstacle region, a free region, an unknown region.
28. The apparatus of claim 16, wherein the processor, when obtaining the first point cloud corresponding to the environment around which the movable platform is located, is specifically configured to:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a laser radar.
29. The apparatus of claim 16, wherein the processor, when obtaining the first point cloud corresponding to the environment around which the movable platform is located, is specifically configured to:
and acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located through a camera.
30. The apparatus of claim 29, wherein the processor, when acquiring the first point cloud corresponding to the environment around which the movable platform is located through the camera, is specifically configured to:
converting the point cloud obtained by the camera into a world coordinate system based on a preset conversion matrix to obtain a first point cloud corresponding to the surrounding environment where the movable platform is located;
the preset conversion matrix comprises an internal reference matrix and an external reference matrix, and the external reference matrix comprises a rotation matrix and/or a translation vector.
31. A movable platform, comprising:
a body;
the power system is arranged on the machine body and used for providing moving power for the movable platform;
and an obstacle detecting device as claimed in any one of claims 16-30.
32. An obstacle detection system, comprising: an obstacle detection device and a movable platform;
the obstacle detection device is used for acquiring a first point cloud corresponding to the surrounding environment where the movable platform is located; filtering the first point cloud according to the size information of the movable platform to obtain a second point cloud; projecting the second point cloud to a two-dimensional plane to obtain at least one projection image; determining obstacle information of the environment around which the movable platform is located according to the at least one projection image; and sending the obstacle information to a movable platform;
and the movable platform is used for moving by bypassing the obstacle according to the received obstacle information.
33. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 15.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/083566 WO2020215172A1 (en) | 2019-04-20 | 2019-04-20 | Obstacle detection method and device, mobile platform, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110799989A true CN110799989A (en) | 2020-02-14 |
Family
ID=69448681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980002940.5A Pending CN110799989A (en) | 2019-04-20 | 2019-04-20 | Obstacle detection method, equipment, movable platform and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110799989A (en) |
| WO (1) | WO2020215172A1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402308A (en) * | 2020-03-17 | 2020-07-10 | 北京百度网讯科技有限公司 | Method, apparatus, device and medium for determining speed of obstacle |
| CN111476830A (en) * | 2020-03-13 | 2020-07-31 | 上海高仙自动化科技发展有限公司 | Point cloud data processing method, robot, electronic device and readable storage medium |
| CN111474930A (en) * | 2020-04-13 | 2020-07-31 | 北京欣奕华科技有限公司 | Tracking control method, device, equipment and medium based on visual positioning |
| CN111652060A (en) * | 2020-04-27 | 2020-09-11 | 宁波吉利汽车研究开发有限公司 | Laser radar-based height-limiting early warning method and device, electronic equipment and storage medium |
| CN112699734A (en) * | 2020-12-11 | 2021-04-23 | 深圳市银星智能科技股份有限公司 | Threshold detection method, mobile robot and storage medium |
| CN113219446A (en) * | 2021-04-30 | 2021-08-06 | 森思泰克河北科技有限公司 | In-vehicle radar occupancy identification method and device and vehicle-mounted radar |
| CN113610883A (en) * | 2021-04-30 | 2021-11-05 | 新驱动重庆智能汽车有限公司 | Point cloud processing system and method, computer device, and storage medium |
| CN114445701A (en) * | 2021-12-15 | 2022-05-06 | 深圳市速腾聚创科技有限公司 | Early warning method and device for platform barrier, medium and electronic equipment |
| CN114521836A (en) * | 2020-08-26 | 2022-05-24 | 北京石头创新科技有限公司 | Automatic cleaning equipment |
| CN115951621A (en) * | 2023-03-15 | 2023-04-11 | 临工重机股份有限公司 | Obstacle avoidance control method and device for aerial work platform, electronic equipment and storage medium |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112558599B (en) * | 2020-11-06 | 2024-04-02 | 深圳拓邦股份有限公司 | Robot work control method and device and robot |
| CN112882058B (en) * | 2021-01-08 | 2022-09-20 | 中国石油大学(华东) | Shipborne laser radar obstacle detection method based on variable-size grid map |
| CN116416291A (en) * | 2021-12-31 | 2023-07-11 | 华为技术有限公司 | Electronic fence automatic generation method, real-time detection method and device |
| CN115082731B (en) * | 2022-06-15 | 2024-03-29 | 苏州轻棹科技有限公司 | Target classification method and device based on voting mechanism |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160004923A1 (en) * | 2014-07-01 | 2016-01-07 | Brain Corporation | Optical detection apparatus and methods |
| CN109645897A (en) * | 2019-01-10 | 2019-04-19 | 轻客小觅智能科技（北京）有限公司 | A kind of obstacle detection method and system of sweeper |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107928566A (en) * | 2017-12-01 | 2018-04-20 | 深圳市沃特沃德股份有限公司 | Vision sweeping robot and obstacle detection method |
| CN109190704A (en) * | 2018-09-06 | 2019-01-11 | 中国科学院深圳先进技术研究院 | The method and robot of detection of obstacles |
| CN109446886B (en) * | 2018-09-07 | 2020-08-25 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device, equipment and storage medium based on unmanned vehicle |
-
2019
- 2019-04-20 CN CN201980002940.5A patent/CN110799989A/en active Pending
- 2019-04-20 WO PCT/CN2019/083566 patent/WO2020215172A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160004923A1 (en) * | 2014-07-01 | 2016-01-07 | Brain Corporation | Optical detection apparatus and methods |
| CN109645897A (en) * | 2019-01-10 | 2019-04-19 | 轻客小觅智能科技（北京）有限公司 | A kind of obstacle detection method and system of sweeper |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476830A (en) * | 2020-03-13 | 2020-07-31 | 上海高仙自动化科技发展有限公司 | Point cloud data processing method, robot, electronic device and readable storage medium |
| CN111402308A (en) * | 2020-03-17 | 2020-07-10 | 北京百度网讯科技有限公司 | Method, apparatus, device and medium for determining speed of obstacle |
| CN111402308B (en) * | 2020-03-17 | 2023-08-04 | 阿波罗智能技术(北京)有限公司 | Method, device, equipment and medium for determining obstacle speed |
| CN111474930A (en) * | 2020-04-13 | 2020-07-31 | 北京欣奕华科技有限公司 | Tracking control method, device, equipment and medium based on visual positioning |
| CN111474930B (en) * | 2020-04-13 | 2023-07-18 | 北京欣奕华科技有限公司 | Tracking control method, device, equipment and medium based on visual positioning |
| CN111652060A (en) * | 2020-04-27 | 2020-09-11 | 宁波吉利汽车研究开发有限公司 | Laser radar-based height-limiting early warning method and device, electronic equipment and storage medium |
| CN111652060B (en) * | 2020-04-27 | 2024-04-19 | 宁波吉利汽车研究开发有限公司 | Laser radar-based height limiting early warning method and device, electronic equipment and storage medium |
| CN114521836A (en) * | 2020-08-26 | 2022-05-24 | 北京石头创新科技有限公司 | Automatic cleaning equipment |
| CN114521836B (en) * | 2020-08-26 | 2023-11-28 | 北京石头创新科技有限公司 | Automatic cleaning equipment |
| CN112699734A (en) * | 2020-12-11 | 2021-04-23 | 深圳市银星智能科技股份有限公司 | Threshold detection method, mobile robot and storage medium |
| CN112699734B (en) * | 2020-12-11 | 2024-04-16 | 深圳银星智能集团股份有限公司 | Threshold detection method, mobile robot and storage medium |
| CN113610883B (en) * | 2021-04-30 | 2022-04-08 | 新驱动重庆智能汽车有限公司 | Point cloud processing system and method, computer device, and storage medium |
| CN113610883A (en) * | 2021-04-30 | 2021-11-05 | 新驱动重庆智能汽车有限公司 | Point cloud processing system and method, computer device, and storage medium |
| CN113219446A (en) * | 2021-04-30 | 2021-08-06 | 森思泰克河北科技有限公司 | In-vehicle radar occupancy identification method and device and vehicle-mounted radar |
| CN114445701B (en) * | 2021-12-15 | 2023-07-04 | 深圳市速腾聚创科技有限公司 | Early warning method and device for platform obstacle, medium and electronic equipment |
| CN114445701A (en) * | 2021-12-15 | 2022-05-06 | 深圳市速腾聚创科技有限公司 | Early warning method and device for platform barrier, medium and electronic equipment |
| CN115951621A (en) * | 2023-03-15 | 2023-04-11 | 临工重机股份有限公司 | Obstacle avoidance control method and device for aerial work platform, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020215172A1 (en) | 2020-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110799989A (en) | Obstacle detection method, equipment, movable platform and storage medium | |
| CN110325818B (en) | Joint 3D object detection and orientation estimation via multimodal fusion | |
| CN110988912B (en) | Road target and distance detection method, system and device for automatic driving vehicle | |
| US10915793B2 (en) | Method and system for converting point cloud data for use with 2D convolutional neural networks | |
| CN108369743B (en) | Mapping a space using a multi-directional camera | |
| CN111753609B (en) | Target identification method and device and camera | |
| US11669972B2 (en) | Geometry-aware instance segmentation in stereo image capture processes | |
| CN111192295B (en) | Target detection and tracking method, apparatus, and computer-readable storage medium | |
| CN112106111A (en) | Calibration method, calibration equipment, movable platform and storage medium | |
| KR102167835B1 (en) | Apparatus and method of processing image | |
| CN111213153A (en) | Target object motion state detection method, device and storage medium | |
| CN113111513B (en) | Sensor configuration scheme determining method and device, computer equipment and storage medium | |
| CN111739099B (en) | Falling prevention method and device and electronic equipment | |
| CN112381026A (en) | Method, system and device for detecting channel shoreline and storage medium | |
| CN115359130A (en) | Radar and camera combined calibration method and device, electronic equipment and storage medium | |
| CN116692690A (en) | Crane anti-collision early warning method, device, equipment and medium | |
| CN115359332A (en) | Data fusion method and device based on vehicle-road cooperation, electronic equipment and system | |
| CN117274526A (en) | Neural network model training method and image generating method | |
| CN112651405B (en) | Target detection method and device | |
| CN117408935A (en) | Obstacle detection method, electronic device, and storage medium | |
| CN111890358B (en) | Binocular obstacle avoidance method and device, storage medium and electronic device | |
| CN115077563A (en) | Vehicle positioning accuracy evaluation method and device and electronic equipment | |
| CN113393423A (en) | Cliff detection method and device based on point cloud and mobile robot | |
| CN114384486A (en) | Data processing method and device | |
| CN113609985B (en) | Object pose detection method, detection device, robot and storable medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200214 |
|
| WD01 | Invention patent application deemed withdrawn after publication |