CN117677976A - Method for generating travelable region, mobile platform, and storage medium - Google Patents
Method for generating travelable region, mobile platform, and storage medium Download PDFInfo
- Publication number
- CN117677976A CN117677976A CN202180100392.7A CN202180100392A CN117677976A CN 117677976 A CN117677976 A CN 117677976A CN 202180100392 A CN202180100392 A CN 202180100392A CN 117677976 A CN117677976 A CN 117677976A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- target
- determining
- candidate
- 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 51
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000009432 framing Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- UDHXJZHVNHGCEC-UHFFFAOYSA-N Chlorophacinone Chemical compound C1=CC(Cl)=CC=C1C(C=1C=CC=CC=1)C(=O)C1C(=O)C2=CC=CC=C2C1=O UDHXJZHVNHGCEC-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
A travelable region generation method comprising: acquiring point cloud data, and generating an initial travelable region according to the point cloud data (S101); convolving the grid in the initial travelable region to obtain a convolution result (S102); filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions (S103); a plurality of target waypoints in the point cloud data are determined, and a target travelable region is generated from the plurality of target waypoints and the candidate travelable region (S104). The accuracy of the drivable area is improved.
Description
The present disclosure relates to the field of environmental awareness, and in particular, to a method for generating a drivable region, a mobile platform, and a storage medium.
The Free Space (Free Space) refers to an area in the environment where the mobile platform is located, where the mobile platform can safely explore and reach. Especially when facing unstructured scenes or local unstructured scenes, the movable platform can effectively guide actions of the movable platform at subsequent moments, safety accidents are avoided, and safe operation of the movable platform is guaranteed. However, the existing method for generating the drivable region has poor filtering effect on boundary noise of the drivable region, so that the generated drivable region has low accuracy, and can influence the safe operation of the movable platform, even cause safety accidents.
Disclosure of Invention
Based on this, the embodiment of the application provides a method for generating a drivable region, a movable platform and a storage medium, which aim to improve the accuracy of the drivable region.
In a first aspect, an embodiment of the present application provides a method for generating a drivable region, including:
acquiring point cloud data, and generating an initial travelable area according to the point cloud data;
convolving the grids in the initial travelable region to obtain a convolution result;
filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions;
and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the target route edge points and the candidate travelable region.
In a second aspect, embodiments of the present application also provide a mobile platform including a radar device, a memory, and a processor;
the radar device is used for collecting point cloud data;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and when executing the computer program, implement the following steps:
acquiring point cloud data, and generating an initial travelable area according to the point cloud data;
Convolving the grids in the initial travelable region to obtain a convolution result;
filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions;
and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the target route edge points and the candidate travelable region.
In a third aspect, embodiments of the present application also provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement the steps of the travelable region generation method as described above.
The embodiment of the application provides a method for generating a drivable region, a movable platform and a storage medium, wherein the method is used for obtaining a convolution result by convolving grids in an initial drivable region, filtering the grids in the initial drivable region based on the convolution result, eliminating unreasonable regions in the initial drivable region, obtaining accurate candidate drivable regions, determining a plurality of target route edge points in point cloud data, and generating the target drivable region based on the plurality of target route edge points and the candidate drivable region, so that unreasonable regions do not exist in the target drivable region, and the accuracy of the drivable region is greatly improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of a scenario for implementing a method for generating a driving area according to an embodiment of the present application;
FIG. 2 is a schematic flowchart of steps of a method for generating a travelable region according to an embodiment of the present application;
FIG. 3 is a schematic illustration of an initial travelable region in an embodiment of the present application;
FIG. 4 is a schematic illustration of candidate travelable regions in an embodiment of the present application;
FIG. 5 is a schematic view of a point cloud segment according to an embodiment of the present application;
FIG. 6 is another schematic diagram of a point cloud segment in an embodiment of the present application;
FIG. 7 is another schematic view of a point cloud segment in an embodiment of the present application;
FIG. 8 is a schematic illustration of a target travelable region in an embodiment of the present application;
Fig. 9 is a schematic block diagram of a movable platform according to an embodiment of the present application.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
The Free Space (Free Space) refers to an area in the environment where the mobile platform is located, where the mobile platform can safely explore and reach. Especially when facing unstructured scenes or local unstructured scenes, the movable platform can effectively guide actions of the movable platform at subsequent moments, safety accidents are avoided, and safe operation of the movable platform is guaranteed. However, the existing method for generating the drivable region has poor filtering effect on boundary noise of the drivable region, so that the generated drivable region has low accuracy, and can influence the safe operation of the movable platform, even cause safety accidents.
In order to solve the above problems, the embodiments of the present application provide a method for generating a drivable region, a movable platform, and a storage medium, where the method includes convolving a grid in an initial drivable region to obtain a convolution result, filtering the grid in the initial drivable region based on the convolution result, so as to eliminate an unreasonable region in the initial drivable region, obtain an accurate candidate drivable region, and finally determining a plurality of target routing points in point cloud data, and generating a target drivable region based on the plurality of target routing points and the candidate drivable region, so that an unreasonable region does not exist in the target drivable region, and accuracy of the drivable region is greatly improved.
The method for generating the drivable region can be applied to a movable platform, a control terminal, a server and the like, wherein the movable platform can comprise, but is not limited to, an unmanned aerial vehicle, a movable robot and an automatic driving vehicle, and the movable robot can comprise a floor sweeping machine, a meal delivery robot, an unmanned aerial vehicle and the like. Referring to fig. 1, fig. 1 is a schematic diagram of a scenario for implementing a method for generating a travelable region according to an embodiment of the present application. As shown in fig. 1, the autonomous vehicle 100 includes a vehicle body 110, a power system 120 and a radar device 130, the power system 120 and the radar device 130 are disposed on the vehicle body 110, the power system 120 is used for providing moving power for the autonomous vehicle 100, and the radar device 130 is used for collecting point cloud data of the environment where the autonomous vehicle 100 is located.
The radar device 130 may include a laser radar and a millimeter wave radar. Alternatively, autonomous vehicle 100 may include one or more radar devices 130. Taking a laser radar as an example, the laser radar can detect information such as the position, the speed and the like of an object in a certain environment by emitting a laser beam, so as to obtain a laser point cloud. The lidar may transmit a detection signal to an environment including a target object, and then receive a reflected signal reflected from the target object, and obtain a laser point cloud based on the reflected detection signal, the received reflected signal, and based on data parameters such as a time interval between transmission and reception. The laser point cloud may include N points, each of which may include parameter values such as x, y, z coordinates and intensity (reflectivity).
In one embodiment, the autonomous vehicle 100 further includes a drive control system (not shown in fig. 1) that may include one or more processors and a sensing system, the sensing system for measuring pose information, motion information, and ambient information of the autonomous vehicle 100, the one or more processors for acquiring point cloud data and generating an initial travelable region from the point cloud data; convolving the grids in the initial travelable area to obtain a convolution result; filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions; and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the plurality of target route edge points and the candidate travelable region.
Hereinafter, a method for generating a travelable region provided in an embodiment of the present application will be described in detail with reference to the scenario in fig. 1. It should be noted that, the scenario in fig. 1 is only used to explain the method for generating a drivable region provided in the embodiment of the present application, but does not constitute limitation of the application scenario of the method for generating a drivable region provided in the embodiment of the present application.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating steps of a method for generating a travelable region according to an embodiment of the present application. The travelable region generation method may apply a movable platform for generating the travelable region.
As shown in fig. 2, the travelable region generation method may include steps S101 to S104.
Step S101, acquiring point cloud data, and generating an initial travelable area according to the point cloud data.
And acquiring point cloud data acquired by a radar device in the movable platform. The radar device may include a lidar, a millimeter wave radar, and the movable platform may include one or more radar devices.
In an embodiment, obstacle point cloud data is extracted from the point cloud data; determining angles and distances between each obstacle point in the obstacle point cloud data and the movable platform; an initial travelable region is generated based on the angle and distance between each obstacle point and the movable platform.
The angles and distances between each obstacle point in the obstacle point cloud data and the movable platform can be determined based on a ray method, namely, the current position point of the movable platform in the obstacle point cloud data is determined, the current position point of the movable platform is taken as an origin, rays are shot according to a preset angle resolution, the rays are cut off at any obstacle point cloud on a path, and a set of a ray angle theta and a cut-off distance d can be obtained, wherein the set is FS= { theta i ,d i I=1, 2, …, n, then the set of ray angles θ and cut-off distances d is projected as a raster pattern, and the grids within the cut-off distances in each direction are marked as True, resulting in an initial travelable region. Taking a horizontal ray as an example, an initial travelable region generated with an angular resolution of 1 ° may be as shown in fig. 3, where each vertex of the polygon in fig. 3 represents a cut-off point of each ray.
For example, the manner of extracting the obstacle point cloud data from the point cloud data may be: performing rasterization processing on the point cloud data to obtain a raster map, and determining the height of the lowest point in the raster map as a target height; determining points with the height smaller than or equal to the target height in the grid map as candidate ground points; performing plane fitting based on a plurality of candidate ground points to obtain a fitting plane, and determining the distance between each candidate ground point and the fitting plane; and extracting obstacle point cloud data from the point cloud data according to the distance between each candidate ground point and the fitting plane. The plane fitting algorithm can be based on a plane fitting algorithm, and a fitting plane is obtained through a plurality of candidate ground points, wherein the plane fitting algorithm can comprise a Ranac algorithm and a least square method.
For example, according to the distance between each candidate ground point and the fitting plane, the manner of extracting the obstacle point cloud data from the point cloud data may be: and marking target ground points in the point cloud data according to the distance between each candidate ground point and the fitting plane, and removing each target ground point from the point cloud data, so that obstacle point cloud data can be obtained. The marked target ground points include candidate ground points with a distance from the fitting plane being smaller than or equal to a preset distance threshold, and the preset distance threshold can be set based on actual situations, which is not particularly limited in this embodiment.
It can be understood that, in addition to the method based on plane fitting, the method of dividing the ground point cloud and the obstacle point cloud may also use the height difference of the point cloud to divide the ground point cloud and the obstacle point cloud, and may also use the semantic division model based on deep learning to divide the ground point cloud and the obstacle point cloud, and of course, may also use other methods to divide the ground point cloud and the obstacle point cloud, which is not limited in particular in the embodiment of the present application.
Step S102, convolving the grids in the initial travelable area to obtain a convolution result.
Illustratively, a target convolution operator is obtained, wherein the target convolution operator is determined from a first dimension of the movable platform and a second dimension of the grid in the initial travelable region; and convolving the grids in the initial travelable area according to the target convolution operator to obtain a convolution result. For example, where the length and width of the movable platform are L and W and the size of the grid in the initial travelable region is x, the length and width of the target convolution operator can be expressed as: l=l/x, w=w/x. In order to reduce the amount of calculation, the element at each edge position of the target convolution operator may be set to 1, and the elements at the remaining positions excluding the edge position may be set to 0.
And step S103, filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions.
Illustratively, deleting the grids of the initial travelable region, wherein the convolution result does not meet the preset condition, and reserving the grids of the convolution result meeting the preset condition to obtain candidate travelable regions. Wherein the preset condition is determined according to the number of edge positions in the target convolution operator. For example, the target convolution operator includes K edge positions, where the elements at each edge position are all 1, and the elements at the remaining positions are all 0, and the preset condition includes that the difference between the convolution result and K is less than or equal to the preset difference threshold.
It should be noted that, by convolving the grids in the initial travelable region to obtain a convolution result, and filtering the grids in the initial travelable region according to the convolution result, the unreasonable grids in the initial travelable region can be eliminated. After the initial travelable region obtained based on the ray diagram shown in fig. 3 is convolved and filtered, the candidate travelable region 10 shown in fig. 4 can be obtained.
Step S104, a plurality of target route edge points in the point cloud data are determined, and a target travelable region is generated according to the plurality of target route edge points and the candidate travelable region.
In an embodiment, a plurality of continuous point cloud segments are framed in the point cloud data along a scanning path of a radar device in a movable platform; determining a point cloud distance proportion, a point cloud height difference and a point cloud included angle of a point cloud segment, wherein the point cloud included angle comprises an included angle between a first side line segment and a second side line segment passing through the center point of the point cloud segment; and determining a plurality of target road edge points from the plurality of point cloud segments according to the point cloud distance proportion, the point cloud height difference and the point cloud included angle.
For example, the manner of framing a plurality of consecutive point cloud segments in the point cloud data along the scan path of the radar apparatus in the movable platform may be: setting a plurality of sliding windows with different widths; for each sliding window, moving the sliding window in the point cloud data along a scanning path of the radar device in the movable platform, and selecting a point cloud segment by the sliding window frame, so that a plurality of continuous point cloud segments can be obtained. For example, the width of the sliding window a is 7 points, the width of the sliding window B is 9 points, a plurality of continuous point cloud segments containing 7 points can be framed by the sliding window a, and a plurality of continuous point cloud segments containing 9 points can be framed by the sliding window B.
Because the radar device scanning path of the irregular scanning path has the condition of turning or turning back and the condition that the depth difference of the point cloud data collected by the radar device is quite large at the target edge, if the target road edge point is determined by only using the point cloud height difference and the point cloud included angle of the point cloud section, more wrong road edge points can occur, the accuracy of the road edge point cannot be ensured, and the target road edge point is determined by comprehensively considering the point cloud distance proportion, the point cloud height difference and the point cloud included angle of the point cloud section, the problem can be solved, so that the accuracy of the road edge point is improved, and a drivable area can be accurately generated later.
The point cloud height difference includes a maximum height difference between a center point of the point cloud segment and other points in the point cloud segment, a first side line segment passes through the center point and a side point in the point cloud segment that is located in a first direction of the center point, and a second side line segment passes through the center point and a side point in the point cloud segment that is located in a second direction of the center point. As shown in fig. 5, the point cloud segment framed by the sliding window 20 includes 7 points, the maximum height difference between the center point 21 and the rest points in the point cloud segment is h, and the point cloud included angle is an included angle β between the first side line segment 22 and the second side line segment 23.
Illustratively, determining a first side point adjacent to a center point of the point cloud segment and a second side point adjacent to the center point, and determining a first distance between the first side point and the second side point; determining a first boundary point of the point cloud segment and a second boundary point of the point cloud segment, and determining a second distance between the first boundary point and the second boundary point; and determining the point cloud distance proportion of the point cloud segment according to the first distance and the second distance.Wherein, let the first distance be d 1 The second distance is d 2 The point cloud distance ratio of the point cloud segment is:
for example, when the point cloud is at the edge of the object, the point cloud distance ratio r will be increased due to abrupt change of the depth of the point cloud, and as shown in fig. 6, the sliding window 30 frames a point cloud segment including 7 points, and the distance d between the first side point 32 and the second side point 33 adjacent to the center point 31 1 Distance d between the first boundary point 34 and the second boundary point 35 is the first distance 2 A second distance, thus, the point cloud distance ratio r is d 2 /d 1 。
Illustratively, at the scan path turn-around or curve, the point cloud distance ratio r will be close to 1 and the numerator and denominator will be small, as shown in FIG. 7, the sliding window 40 frames a point cloud segment comprising 7 points, the distance d between the adjacent first side point 42 and second side point 43 from the center point 41 1 Distance d between first boundary point 44 and second boundary point 45 is the first distance 2 A second distance, thus, the point cloud distance ratio r is d 2 /d 1 。
In an embodiment, selecting a point cloud segment, wherein the point cloud distance proportion, the point cloud height difference and the point cloud included angle meet the preset route point conditions, from a plurality of point cloud segments as a target point cloud segment; and determining a plurality of target route edge points according to the plurality of target point cloud segments. The preset road edge point conditions include that the point cloud distance proportion is located in a preset proportion range, the point cloud height difference is located in a preset height difference range, the point cloud included angle is located in a preset included angle range, and the preset proportion range, the preset height difference range and the preset included angle range can be set based on actual conditions, and the embodiment is not limited in specific.
For example, the manner of determining the plurality of target waypoints according to the plurality of target waypoint cloud segments may be: determining a central point in each target point cloud segment as a first candidate route edge point, and determining an angle between each first candidate route edge point and the movable platform; dividing the first candidate route edge points into route edge point groups corresponding to each angle interval in a plurality of preset angle intervals according to the angle between each first candidate route edge point and the movable platform; and determining the candidate route edge point closest to the movable platform in the route edge point group as a target route edge point, so that a plurality of target route edge points can be obtained.
Since the road edges are generally symmetrically distributed on two sides of the road, that is, under the condition that the road surface has no obstacle, the road edges are the nearest 'protrusions' of the radar device (movable platform) connected with the ground plane, most false detection road edge points outside the road surface can be removed through the scheme of the embodiment, the accuracy of the road edge points is ensured, and the following accurate generation of the travelable area is facilitated.
The preset plurality of angle intervals may be set based on practical situations, which is not specifically limited in this embodiment. For example, the first candidate route edge points are a route edge point a, a route edge point B, a route edge point C, a route edge point D, a route edge point E, and a route edge point F, and the preset angle interval includes an angle interval a:0 ° -120 °, angle interval b:121 ° -240 ° and angle interval C241 ° -360 °, curtaining point a, curtaining point B, curtaining point C, curtaining point D, curtaining point E, curtaining point F and the movable platform are respectively 33 °, 129 °, 50 °, 220 °, 300 °, 270 °, thus dividing curtaining point a and curtaining point C into angle interval a: dividing a road edge point B and a road edge point D into an angle interval B according to a first road edge point group corresponding to 0-120 degrees: and dividing the road edge point E and the road edge point F into a third road edge point group corresponding to an angle interval c of 241-360 degrees by the second road edge point group corresponding to 121-240 degrees.
In one embodiment, a candidate route edge point closest to the movable platform in the route edge point group is determined as a second candidate route edge point; updating a preset probability occupation grid map according to a plurality of second candidate route edge points, wherein the probability occupation grid map is used for representing the probability that the corresponding point is a route edge point; and determining a point corresponding to the updated probability occupying grid map, wherein the grid occupying probability is larger than a preset probability threshold, as a target road edge point. The preset probability threshold may be set based on actual situations, which is not specifically limited in this embodiment. The probability occupation grid map is updated through the second candidate road edge points with high accuracy, and then the points corresponding to the updated probability occupation grid map with the probability larger than the preset probability threshold value are determined as target road edge points, so that the accuracy of the road edge points can be further improved.
For example, according to the plurality of second candidate route edge points, the method for updating the preset probability occupation grid map may be: determining that the probability occupies a first position in the grid map where the second candidate waypoint exists and a second position in the grid map where the second candidate waypoint does not exist; for a point at a first location, the grid occupancy probability of the point is increased, and for a point at a second location, the grid occupancy probability of the point is decreased.
In one embodiment, a target curbside trajectory is generated from a plurality of target curbside points; and generating a target travelable region according to the target road edge track and the candidate travelable region. As shown in fig. 8, the target road-edge trajectories generated from the plurality of target road-edge points are a road-edge trajectory 52 and a road-edge trajectory 53, and the target travelable region 51 is located between the Lu Yangui trajectory 52 and the road-edge trajectory 53.
Illustratively, curve fitting is performed on a plurality of target cursors to obtain candidate cursors, and a first parameter of a curve equation of the candidate cursors is determined; acquiring a second parameter of a curve equation of a historical road edge track, wherein the historical road edge track is determined based on road edge points in the point cloud data of the previous frame; and determining a parameter adjustment value according to the second parameter and the first parameter, and adjusting the candidate route track according to the parameter adjustment value to obtain the target route track. The fitting algorithm of the path-edge track can comprise a RANSAC algorithm, a least square method, a Hough transform algorithm and the like. The parameters of the curve equation of the historical road edge track and the parameters of the curve equation of the candidate road edge track are combined to adjust the candidate road edge track, so that the stability and the continuity of the road edge track can be ensured, and the accuracy of the road edge track can be improved.
According to the method for generating the drivable region, the convolution result is obtained by convolving the grids in the initial drivable region, then the filtering is carried out on the grids in the initial drivable region based on the convolution result, so that an unreasonable region in the initial drivable region can be eliminated, an accurate candidate drivable region is obtained, a plurality of target route edge points in point cloud data are finally determined, and the target drivable region is generated based on the plurality of target route edge points and the candidate drivable region, so that an unreasonable region does not exist in the target drivable region, and the accuracy of the drivable region is greatly improved.
Referring to fig. 9, fig. 9 is a schematic block diagram of a movable platform according to an embodiment of the present application.
As shown in fig. 9, the mobile platform 300 includes a radar apparatus 310, a processor 320, and a memory 330, and the radar apparatus 310, the processor 320, and the memory 330 are connected by a bus 340, such as an I2C (Inter-integrated Circuit) bus.
Specifically, the radar device 310 may be a laser radar, a millimeter wave radar, or the like, and the radar device 310 is configured to collect point cloud data.
Specifically, the processor 320 may be a Micro-controller Unit (MCU), a central processing Unit (Central Processing Unit, CPU), a digital signal processor (Digital Signal Processor, DSP), or the like.
Specifically, the Memory 330 may be a Flash chip, a Read-Only Memory (ROM) disk, an optical disk, a U-disk, a removable hard disk, or the like.
Wherein the processor 320 is configured to run a computer program stored in the memory 330 and to implement the following steps when the computer program is executed:
acquiring point cloud data, and generating an initial travelable area according to the point cloud data;
convolving the grids in the initial travelable region to obtain a convolution result;
filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions;
and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the target route edge points and the candidate travelable region.
Optionally, when the processor performs convolution on the grid in the initial travelable region to obtain a convolution result, the processor is configured to perform:
obtaining a target convolution operator, wherein the target convolution operator is determined according to a first size of a movable platform and a second size of the grid;
and convolving the grids in the initial travelable region according to the target convolution operator to obtain a convolution result.
Optionally, when the processor filters the grids in the initial travelable region according to the convolution result to obtain a candidate travelable region, the processor is configured to implement:
and deleting the grids of the initial travelable region, wherein the convolution result of the grids does not meet the preset condition, and reserving the grids of the convolution result meeting the preset condition to obtain candidate travelable regions.
Optionally, when implementing determining a plurality of target routing points in the point cloud data, the processor is configured to implement:
selecting a plurality of continuous point cloud segments in the point cloud data along a scanning path of the radar device;
determining a point cloud distance proportion, a point cloud height difference and a point cloud included angle of the point cloud segment, wherein the point cloud included angle comprises an included angle between a first side line segment and a second side line segment passing through the center point of the point cloud segment;
and determining a plurality of target route edge points from a plurality of point cloud segments according to the point cloud distance proportion, the point cloud height difference and the point cloud included angle.
Optionally, when determining the point cloud distance proportion of the point cloud segment, the processor is configured to implement:
determining a first side point adjacent to a center point of the point cloud segment and a second side point adjacent to the center point, and determining a first distance between the first side point and the second side point;
Determining a first boundary point of the point cloud segment and a second boundary point of the point cloud segment, and determining a second distance between the first boundary point and the second boundary point;
and determining the point cloud distance proportion of the point cloud segment according to the first distance and the second distance.
Optionally, the point cloud height difference includes a maximum height difference between a center point of the point cloud segment and the remaining points within the point cloud segment.
Optionally, the first side line segment passes through the center point and a side point in the point cloud segment, which is located in a first direction of the center point, and the second side line segment passes through the center point and a side point in the point cloud segment, which is located in a second direction of the center point.
Optionally, when the processor determines a plurality of target route edge points from a plurality of the point cloud segments according to the point cloud distance proportion, the point cloud height difference and the point cloud included angle, the processor is configured to implement:
selecting a point cloud segment, of which the point cloud distance proportion, the point cloud height difference and the point cloud included angle meet the preset road edge point condition, from a plurality of point cloud segments as a target point cloud segment;
and determining a plurality of target route edge points according to the plurality of target point cloud segments.
Optionally, the preset road edge point condition includes that the point cloud distance proportion is located in a preset proportion range, the point cloud height difference is located in a preset height difference range, and the point cloud included angle is located in a preset included angle range.
Optionally, when determining a plurality of target waypoints according to a plurality of the target waypoints cloud segments, the processor is configured to implement:
determining a central point in each target point cloud segment as a first candidate curbside, and determining an angle between each first candidate curbside and the movable platform;
dividing the plurality of first candidate route edge points into route edge point groups corresponding to each angle interval in a plurality of preset angle intervals according to the angles;
and determining the candidate route edge point closest to the movable platform in the route edge point group as a target route edge point.
Optionally, the processor is further configured to implement the following steps:
determining a candidate route edge point closest to the movable platform in the route edge point group as a second candidate route edge point;
updating a preset probability occupation grid map according to a plurality of second candidate route edge points, wherein the probability occupation grid map is used for representing the probability that the corresponding point is a route edge point;
And determining the point corresponding to the updated probability occupying grid map, wherein the grid occupying probability of the point is larger than a preset probability threshold value, as a target road edge point.
Optionally, the processor is configured to, when implementing generating the target travelable region according to the plurality of target waypoints and the candidate travelable region, implement:
generating a target route track according to a plurality of target route points;
and generating a target travelable region according to the target road edge track and the candidate travelable region.
Optionally, when implementing generating the target routing track according to the plurality of target routing points, the processor is configured to implement:
performing curve fitting on a plurality of target curtaining points to obtain candidate curtaining tracks, and determining first parameters of curve equations of the candidate curtaining tracks;
acquiring a second parameter of a curve equation of a historical road edge track, wherein the historical road edge track is determined based on road edge points in the point cloud data of the previous frame;
and determining a parameter adjustment value according to the second parameter and the first parameter, and adjusting the candidate route track according to the parameter adjustment value to obtain a target route track.
Optionally, when implementing the generation of the initial travelable region according to the point cloud data, the processor is configured to implement:
Extracting obstacle point cloud data from the point cloud data;
determining angles and distances between each obstacle point in the obstacle point cloud data and a movable platform;
and generating an initial travelable region according to the angle and the distance between each obstacle point and the movable platform.
Optionally, when implementing extracting obstacle point cloud data from the point cloud data, the processor is configured to implement:
performing rasterization processing on the point cloud data to obtain a raster map, and determining the height of the lowest point in the raster map as a target height;
determining points with the height smaller than or equal to the target height in the grid map as candidate ground points;
performing plane fitting based on a plurality of candidate ground points to obtain a fitting plane, and determining the distance between each candidate ground point and the fitting plane;
and extracting obstacle point cloud data from the point cloud data according to the distance between each candidate ground point and the fitting plane.
It should be noted that, for convenience and brevity of description, a person skilled in the art may clearly understand that, in the specific working process of the movable platform described above, reference may be made to a corresponding process in the foregoing embodiment of the method for generating a drivable area, which is not described herein again.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, the computer program comprises program instructions, and the processor executes the program instructions to implement the steps of the method for generating the drivable region provided by the embodiment.
The computer readable storage medium may be an internal storage unit of the mobile platform according to any one of the foregoing embodiments, for example, a hard disk or a memory of the mobile platform. The computer readable storage medium may also be an external storage device of the removable platform, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the removable platform.
It is to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (31)
- A travelable region generation method characterized by comprising:acquiring point cloud data, and generating an initial travelable area according to the point cloud data;convolving the grids in the initial travelable region to obtain a convolution result;filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions;and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the target route edge points and the candidate travelable region.
- The method for generating a travelable region according to claim 1, wherein the convolving the grid in the initial travelable region to obtain a convolution result comprises:obtaining a target convolution operator, wherein the target convolution operator is determined according to a first size of a movable platform and a second size of the grid;and convolving the grids in the initial travelable region according to the target convolution operator to obtain a convolution result.
- The method for generating a travelable region according to claim 1, wherein the filtering the grids in the initial travelable region according to the convolution result to obtain candidate travelable regions comprises:and deleting the grids of the initial travelable region, wherein the convolution result of the grids does not meet the preset condition, and reserving the grids of the convolution result meeting the preset condition to obtain candidate travelable regions.
- The method of generating a travelable region as claimed in claim 1, wherein the determining a plurality of target waypoints in the point cloud data comprises:framing a plurality of continuous point cloud segments in the point cloud data along a scanning path of a radar device in a movable platform;Determining a point cloud distance proportion, a point cloud height difference and a point cloud included angle of the point cloud segment, wherein the point cloud included angle comprises an included angle between a first side line segment and a second side line segment passing through the center point of the point cloud segment;and determining a plurality of target route edge points from a plurality of point cloud segments according to the point cloud distance proportion, the point cloud height difference and the point cloud included angle.
- The method for generating a travelable region as claimed in claim 4, wherein said determining a point cloud distance ratio of the point cloud segment comprises:determining a first side point adjacent to a center point of the point cloud segment and a second side point adjacent to the center point, and determining a first distance between the first side point and the second side point;determining a first boundary point of the point cloud segment and a second boundary point of the point cloud segment, and determining a second distance between the first boundary point and the second boundary point;and determining the point cloud distance proportion of the point cloud segment according to the first distance and the second distance.
- The travelable region generating method as defined in claim 4, wherein the point cloud height difference includes a maximum height difference between a center point of the point cloud segment and remaining points within the point cloud segment.
- The method according to claim 4, wherein the first side line segment passes through the center point and a side point in the point cloud segment that is located in a first direction of the center point, and the second side line segment passes through the center point and a side point in the point cloud segment that is located in a second direction of the center point.
- The method for generating a travelable region according to any one of claims 4-7, wherein the determining a plurality of target road edge points from a plurality of the point cloud segments according to the point cloud distance ratio, the point cloud height difference, and the point cloud angle comprises:selecting a point cloud segment, of which the point cloud distance proportion, the point cloud height difference and the point cloud included angle meet the preset road edge point condition, from a plurality of point cloud segments as a target point cloud segment;and determining a plurality of target route edge points according to the plurality of target point cloud segments.
- The method for generating a travelable region according to claim 8, wherein the predetermined road edge point condition includes that the point cloud distance ratio is within a predetermined ratio range, the point cloud height difference is within a predetermined height difference range, and the point cloud angle is within a predetermined angle range.
- The method of generating a travelable region as claimed in claim 8, wherein said determining a plurality of target waypoints from a plurality of said target point cloud segments comprises:Determining a central point in each target point cloud segment as a first candidate curbside, and determining an angle between each first candidate curbside and the movable platform;dividing the plurality of first candidate route edge points into route edge point groups corresponding to each angle interval in a plurality of preset angle intervals according to the angles;and determining the candidate route edge point closest to the movable platform in the route edge point group as a target route edge point.
- The travelable region generating method as defined in claim 10, further comprising:determining a candidate route edge point closest to the movable platform in the route edge point group as a second candidate route edge point;updating a preset probability occupation grid map according to a plurality of second candidate route edge points, wherein the probability occupation grid map is used for representing the probability that the corresponding point is a route edge point;and determining the point corresponding to the updated probability occupying grid map, wherein the grid occupying probability of the updated probability occupying grid map is larger than a preset probability threshold, as a target road edge point.
- The travelable region generating method as claimed in any one of claims 1-11, wherein the generating a target travelable region from a plurality of the target waypoints and the candidate travelable region comprises:Generating a target route track according to a plurality of target route points;and generating a target travelable region according to the target road edge track and the candidate travelable region.
- The method of generating a travelable region as claimed in claim 12, wherein the generating a target route track from a plurality of the target route points comprises:performing curve fitting on a plurality of target curtaining points to obtain candidate curtaining tracks, and determining first parameters of curve equations of the candidate curtaining tracks;acquiring a second parameter of a curve equation of a historical road edge track, wherein the historical road edge track is determined based on road edge points in the point cloud data of the previous frame;and determining a parameter adjustment value according to the second parameter and the first parameter, and adjusting the candidate route track according to the parameter adjustment value to obtain a target route track.
- The travelable region generating method as claimed in any one of claims 1-11, characterized in that the generating an initial travelable region from the point cloud data comprises:extracting obstacle point cloud data from the point cloud data;determining angles and distances between each obstacle point in the obstacle point cloud data and a movable platform;And generating an initial travelable region according to the angle and the distance between each obstacle point and the movable platform.
- The travelable region generation method as set forth in claim 14, wherein the extracting obstacle point cloud data from the point cloud data includes:performing rasterization processing on the point cloud data to obtain a raster map, and determining the height of the lowest point in the raster map as a target height;determining points with the height smaller than or equal to the target height in the grid map as candidate ground points;performing plane fitting based on a plurality of candidate ground points to obtain a fitting plane, and determining the distance between each candidate ground point and the fitting plane;and extracting obstacle point cloud data from the point cloud data according to the distance between each candidate ground point and the fitting plane.
- A mobile platform comprising a radar device, a memory, and a processor;the radar device is used for collecting point cloud data;the memory is used for storing a computer program;the processor is configured to execute the computer program and when executing the computer program, implement the following steps:Acquiring point cloud data, and generating an initial travelable area according to the point cloud data;convolving the grids in the initial travelable region to obtain a convolution result;filtering grids in the initial travelable region according to the convolution result to obtain candidate travelable regions;and determining a plurality of target route edge points in the point cloud data, and generating a target travelable region according to the target route edge points and the candidate travelable region.
- The mobile platform of claim 16, wherein the processor, when implementing convolving the grid in the initial travelable region to obtain a convolution result, is configured to implement:obtaining a target convolution operator, wherein the target convolution operator is determined according to a first size of a movable platform and a second size of the grid;and convolving the grids in the initial travelable region according to the target convolution operator to obtain a convolution result.
- The mobile platform of claim 16, wherein the processor, when implementing filtering the grid in the initial travelable region according to the convolution result to obtain candidate travelable regions, is configured to implement:And deleting the grids of the initial travelable region, wherein the convolution result of the grids does not meet the preset condition, and reserving the grids of the convolution result meeting the preset condition to obtain candidate travelable regions.
- The mobile platform of claim 16, wherein the processor, when implementing determining a plurality of target waypoints in the point cloud data, is configured to implement:selecting a plurality of continuous point cloud segments in the point cloud data along a scanning path of the radar device;determining a point cloud distance proportion, a point cloud height difference and a point cloud included angle of the point cloud segment, wherein the point cloud included angle comprises an included angle between a first side line segment and a second side line segment passing through the center point of the point cloud segment;and determining a plurality of target route edge points from a plurality of point cloud segments according to the point cloud distance proportion, the point cloud height difference and the point cloud included angle.
- The mobile platform of claim 19, wherein the processor, when determining the point cloud distance ratio of the point cloud segment, is configured to implement:determining a first side point adjacent to a center point of the point cloud segment and a second side point adjacent to the center point, and determining a first distance between the first side point and the second side point;Determining a first boundary point of the point cloud segment and a second boundary point of the point cloud segment, and determining a second distance between the first boundary point and the second boundary point;and determining the point cloud distance proportion of the point cloud segment according to the first distance and the second distance.
- The movable platform of claim 19, wherein the point cloud height difference comprises a maximum height difference between a center point of the point cloud segment and remaining points within the point cloud segment.
- The mobile platform of claim 19, wherein the first side line segment passes through the center point and a side point in the point cloud segment that is located in a first direction of the center point, and the second side line segment passes through the center point and a side point in the point cloud segment that is located in a second direction of the center point.
- The mobile platform of any one of claims 16-22, wherein the processor, when implementing determining a plurality of target curbside points from a plurality of the point cloud segments according to the point cloud distance ratio, the point cloud altitude difference, and the point cloud angle, is configured to implement:selecting a point cloud segment, of which the point cloud distance proportion, the point cloud height difference and the point cloud included angle meet the preset road edge point condition, from a plurality of point cloud segments as a target point cloud segment;And determining a plurality of target route edge points according to the plurality of target point cloud segments.
- The mobile platform of claim 23, wherein the predetermined curbside point condition includes the point cloud distance scale being within a predetermined scale range, the point cloud height difference being within a predetermined height difference range, and the point cloud angle being within a predetermined angle range.
- The mobile platform of claim 23, wherein the processor, when implementing determining a plurality of target waypoints from a plurality of the target waypoint cloud segments, is configured to implement:determining a central point in each target point cloud segment as a first candidate curbside, and determining an angle between each first candidate curbside and the movable platform;dividing the plurality of first candidate route edge points into route edge point groups corresponding to each angle interval in a plurality of preset angle intervals according to the angles;and determining the candidate route edge point closest to the movable platform in the route edge point group as a target route edge point.
- The mobile platform of claim 25, wherein the processor is further configured to implement the steps of:determining a candidate route edge point closest to the movable platform in the route edge point group as a second candidate route edge point;Updating a preset probability occupation grid map according to a plurality of second candidate route edge points, wherein the probability occupation grid map is used for representing the probability that the corresponding point is a route edge point;and determining the point corresponding to the updated probability occupying grid map, wherein the grid occupying probability of the point is larger than a preset probability threshold value, as a target road edge point.
- The mobile platform of any one of claims 16-26, wherein the processor, when implementing generating a target travelable region from a plurality of the target waypoints and the candidate travelable regions, is configured to implement:generating a target route track according to a plurality of target route points;and generating a target travelable region according to the target road edge track and the candidate travelable region.
- The mobile platform of claim 27, wherein the processor, when implementing generating a target routing track from a plurality of the target routing points, is configured to implement:performing curve fitting on a plurality of target curtaining points to obtain candidate curtaining tracks, and determining first parameters of curve equations of the candidate curtaining tracks;acquiring a second parameter of a curve equation of a historical road edge track, wherein the historical road edge track is determined based on road edge points in the point cloud data of the previous frame;And determining a parameter adjustment value according to the second parameter and the first parameter, and adjusting the candidate route track according to the parameter adjustment value to obtain a target route track.
- The mobile platform of any one of claims 16-26, wherein the processor, when enabled to generate an initial travelable region from the point cloud data, is configured to:extracting obstacle point cloud data from the point cloud data;determining angles and distances between each obstacle point in the obstacle point cloud data and a movable platform;and generating an initial travelable region according to the angle and the distance between each obstacle point and the movable platform.
- The mobile platform of claim 29, wherein the processor, when implementing extracting obstacle point cloud data from the point cloud data, is configured to implement:performing rasterization processing on the point cloud data to obtain a raster map, and determining the height of the lowest point in the raster map as a target height;determining points with the height smaller than or equal to the target height in the grid map as candidate ground points;performing plane fitting based on a plurality of candidate ground points to obtain a fitting plane, and determining the distance between each candidate ground point and the fitting plane;And extracting obstacle point cloud data from the point cloud data according to the distance between each candidate ground point and the fitting plane.
- A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the travelable region generation method of any one of claims 1-15.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/107684 WO2023000221A1 (en) | 2021-07-21 | 2021-07-21 | Free space generation method, movable platform and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117677976A true CN117677976A (en) | 2024-03-08 |
Family
ID=84979839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202180100392.7A Pending CN117677976A (en) | 2021-07-21 | 2021-07-21 | Method for generating travelable region, mobile platform, and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117677976A (en) |
| WO (1) | WO2023000221A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115884479B (en) * | 2023-02-22 | 2023-05-09 | 广州易而达科技股份有限公司 | Steering method, device and equipment of lighting lamp and storage medium |
| CN116520353B (en) * | 2023-06-29 | 2023-09-26 | 广汽埃安新能源汽车股份有限公司 | Ground detection method, device, storage medium and equipment based on laser point cloud |
| CN116863432B (en) * | 2023-09-04 | 2023-12-22 | 之江实验室 | Weak supervision laser travelable region prediction method and system based on deep learning |
| CN118243105A (en) * | 2024-03-28 | 2024-06-25 | 北京小米机器人技术有限公司 | Path planning method, path planning device, electronic equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7995054B2 (en) * | 2005-11-21 | 2011-08-09 | Leica Geosystems Ag | Identification of edge regions from 3D point data |
| CN106650640B (en) * | 2016-12-05 | 2020-03-03 | 浙江大学 | Negative obstacle detection method based on laser radar point cloud local structure characteristics |
| US10460180B2 (en) * | 2017-04-20 | 2019-10-29 | GM Global Technology Operations LLC | Systems and methods for visual classification with region proposals |
| CN111353969B (en) * | 2018-12-20 | 2023-09-26 | 长沙智能驾驶研究院有限公司 | Method and device for determining road drivable area and computer equipment |
| CN110569749B (en) * | 2019-08-22 | 2021-11-30 | 江苏徐工工程机械研究院有限公司 | Detection method and system for boundary line and travelable area of mine road |
| US10816993B1 (en) * | 2019-11-23 | 2020-10-27 | Ha Q Tran | Smart vehicle |
| CN113009453B (en) * | 2020-03-20 | 2022-11-08 | 青岛慧拓智能机器有限公司 | Mine road edge detection and mapping method and device |
| CN111737395B (en) * | 2020-08-19 | 2020-12-22 | 浙江欣奕华智能科技有限公司 | Method and device for generating occupancy grid map and robot system |
| CN112149572A (en) * | 2020-09-24 | 2020-12-29 | 知行汽车科技（苏州）有限公司 | Road edge detection method, device and storage medium |
| CN113030997B (en) * | 2021-05-27 | 2021-08-20 | 北京踏歌智行科技有限公司 | Method for detecting travelable area of open-pit mine area based on laser radar |
-
2021
- 2021-07-21 CN CN202180100392.7A patent/CN117677976A/en active Pending
- 2021-07-21 WO PCT/CN2021/107684 patent/WO2023000221A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023000221A1 (en) | 2023-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117677976A (en) | Method for generating travelable region, mobile platform, and storage medium | |
| CN110045376B (en) | Drivable region acquisition method, computer-readable storage medium, and terminal device | |
| US7826666B2 (en) | Methods and apparatus for runway segmentation using sensor analysis | |
| CN108509820B (en) | Obstacle segmentation method and device, computer equipment and readable medium | |
| CN108470174B (en) | Obstacle segmentation method and device, computer equipment and readable medium | |
| JP2021534481A (en) | Obstacle or ground recognition and flight control methods, devices, equipment and storage media | |
| CN110320531B (en) | Obstacle identification method based on laser radar, map creation method and device | |
| US11762061B2 (en) | System and method for free space estimation | |
| CN109635816B (en) | Lane line generation method, apparatus, device, and storage medium | |
| CN115782867B (en) | Track collision risk assessment method, device, electronic equipment and storage medium | |
| CN109636842B (en) | Lane line correction method, device, equipment and storage medium | |
| CN113806464A (en) | Road tooth determining method, device, equipment and storage medium | |
| JP2022089828A (en) | Information processing apparatus | |
| CN113835102B (en) | Lane line generation method and device | |
| CN114842450A (en) | Driving region detection method, device and equipment | |
| CN116071729A (en) | Method and device for detecting drivable area and road edge and related equipment | |
| CN115139303A (en) | Grid well lid detection method, device, equipment and storage medium | |
| US20220171975A1 (en) | Method for Determining a Semantic Free Space | |
| CN116311127A (en) | Road boundary detection method, computer equipment, readable storage medium and motor vehicle | |
| CN112859893B (en) | Obstacle avoidance method and device for aircraft | |
| CN113640810A (en) | Space parking space detection method, device, storage medium and program product | |
| CN117372995A (en) | Vehicle drivable region detection method, related device and storage medium | |
| CN117423089A (en) | Method and equipment for fitting travelable area based on image segmentation and radar point cloud | |
| CN116434181A (en) | Ground point detection method, device, electronic equipment and medium | |
| CN116071730A (en) | Background object detection method, device and equipment and automatic driving 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240515 Address after: Building 3, Xunmei Science and Technology Plaza, No. 8 Keyuan Road, Science and Technology Park Community, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province, 518057, 1634 Applicant after: Shenzhen Zhuoyu Technology Co.,Ltd. Country or region after: China Address before: 518057 Shenzhen Nanshan District, Shenzhen, Guangdong Province, 6/F, Shenzhen Industry, Education and Research Building, Hong Kong University of Science and Technology, No. 9 Yuexingdao District, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SZ DJI TECHNOLOGY Co.,Ltd. Country or region before: China |