CN116502479B - Collision detection method and device of three-dimensional object in simulation environment - Google Patents
Collision detection method and device of three-dimensional object in simulation environment Download PDFInfo
- Publication number
- CN116502479B CN116502479B CN202310781219.9A CN202310781219A CN116502479B CN 116502479 B CN116502479 B CN 116502479B CN 202310781219 A CN202310781219 A CN 202310781219A CN 116502479 B CN116502479 B CN 116502479B
- Authority
- CN
- China
- Prior art keywords
- road
- dimensional object
- collision detection
- dimensional
- dimensional objects
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 124
- 238000004088 simulation Methods 0.000 title claims abstract description 61
- 238000004891 communication Methods 0.000 claims abstract description 36
- 238000010586 diagram Methods 0.000 claims abstract description 17
- 230000015654 memory Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 13
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a collision detection method and device of a three-dimensional object in a simulation environment, comprising the following steps: acquiring road data in a high-precision map; constructing an inter-road communication graph based on the road data; in each round of automatic driving simulation period, collision detection is carried out when the detection pair consisting of two three-dimensional objects is judged to be at the same intersection or the same road based on road data, and collision detection is carried out when the detection pair is judged to be at an adjacent road based on an inter-road communication diagram under the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road. Therefore, most three-dimensional objects which cannot possibly collide are filtered out through the road data in the high-precision map, and then collision detection is carried out on the rest three-dimensional objects, so that the efficiency of collision detection is improved, and the consumption of calculation resources is reduced.
Description
Technical Field
The invention belongs to the technical field of automatic driving virtual simulation, and particularly relates to a collision detection method and device for a three-dimensional object in a simulation environment.
Background
In order to prevent collision of the automatic driving automobile in actual driving, damage to traffic participants such as vehicles and pedestrians is caused, and the driving track of the automatic driving automobile needs to be verified in a virtual simulation environment in advance so as to facilitate correction and improvement of an automatic driving algorithm, thereby ensuring the safety of the automatic driving automobile.
Because the position and the gesture of the automatic driving vehicle dynamically change in the virtual simulation environment, the real-time requirement on collision detection is high, and the traditional collision detection algorithm does not consider high-precision map information, all traffic participants in the virtual simulation environment or traffic participants in a certain range can be subjected to bounding box collision detection with the automatic driving vehicle, and a large amount of invalid calculation exists in the mode that the automatic driving vehicle cannot collide with other traffic participants not on a connected channel.
Patent application publication No. CN108628184A discloses a collision detection method for a robot simulation system, which is based on the construction of a detection data structure of each object, calculates the minimum distance between geometric models by the detection data structure, and judges whether the models collide according to whether the minimum distance is 0. The detection method is high in calculation consumption and has a large number of invalid calculations because the minimum distance between every two geometric models is calculated.
The patent application with publication number of CN111177888A discloses a simulation scene collision detection method and system, comprising the following steps: respectively obtaining the most salient points corresponding to the two objects to be detected, and calculating a first distance between the two most salient points; if the first distance is not zero, respectively splitting the two objects to be detected to obtain respectively corresponding sub-objects, and calculating second distances of two salient points on the two sub-objects with the same height; if the first distance is zero or the second distance is zero, judging that two objects to be detected collide at the moment. When the detection method is applied to a large number of detection objects, the distance between every two objects to be detected needs to be calculated, the calculation consumption is large, and a large number of invalid calculations exist.
Based on the above existing detection means, the efficient collision detection can improve the detection efficiency of virtual simulation and save the calculation power consumption of the server, so in order to improve the efficiency and instantaneity of automatic driving simulation, a collision detection method suitable for use in an automatic driving simulation environment needs to be provided.
Disclosure of Invention
In view of the foregoing, an object of the present invention is to provide a method and an apparatus for detecting a collision of a three-dimensional object in a simulation environment, so as to improve efficiency and instantaneity of automatic driving simulation, and reduce calculation consumption.
In order to achieve the above object, a method for detecting a collision of a three-dimensional object in a simulation environment according to an embodiment of the present invention includes the following steps:
acquiring road data in a high-precision map;
constructing an inter-road communication graph based on the road data;
in each round of automatic driving simulation period, collision detection is carried out when the detection pair consisting of two three-dimensional objects is judged to be at the same intersection or the same road based on road data, and collision detection is carried out when the detection pair is judged to be at an adjacent road based on an inter-road communication diagram under the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road.
In one embodiment, the road data includes a road ID, a road length, a road orientation, an intersection to which the road belongs.
In one embodiment, the constructing the inter-road communication map based on the road data includes:
and taking each road as a connecting edge, and adding a vertex between the two connected roads to form an inter-road communication diagram.
In one embodiment, the collision detection method further comprises: before simulation, initializing a road, frenet coordinates and a moving direction of each three-dimensional object in an automatic driving simulation environment in a high-precision map;
updating Frenet coordinates and moving directions of each three-dimensional object before each round of judgment is carried out;
the Frenet coordinates comprise the distance of the three-dimensional object along the direction of the road reference line and the distance of the three-dimensional object along the direction of the normal vector of the road reference line.
In one embodiment, the collision detection when the road data is determined to be at the same intersection or the same road comprises:
comparing the road where the two three-dimensional objects in the detection pair are positioned with the road ID in the road data to judge whether the two three-dimensional objects are positioned on the same road, and performing collision detection when the two three-dimensional objects are positioned on the same road;
and comparing the road where the two three-dimensional objects in the detection pair are located, the current Frenet coordinates and bounding box information with the intersection where the road in the road data belongs to so as to judge whether the two three-dimensional objects are located at the same intersection, and performing collision detection when the two three-dimensional objects are located at the same intersection.
In one embodiment, the determining that the road is adjacent based on the inter-road communication map includes:
searching two continuous edges corresponding to the road where the two three-dimensional objects are located in the inter-road communication graph, and judging that the two continuous edges are separated by a vertex, wherein the two three-dimensional objects are located in adjacent roads.
In one embodiment, the remaining road length of the three-dimensional object in the direction of movement is calculated by:
if the difference between the moving direction of the three-dimensional object and the road direction of the road where the three-dimensional object is located is [ -pi/2, pi/2 ], the remaining road length is the road length of the road where the three-dimensional object is located minus the distance of the three-dimensional object along the road reference line direction, otherwise the remaining road length is the distance of the three-dimensional object along the road reference line direction.
In a second aspect, to achieve the above object, the present invention further provides a collision detection apparatus for a three-dimensional object in a simulation environment, including:
the acquisition module is used for acquiring road data in the high-precision map;
the map construction module is used for constructing an inter-road communication map based on road data;
and the judging and detecting module is used for carrying out collision detection on the detection pair consisting of two three-dimensional objects in each automatic driving simulation period, judging whether the two three-dimensional objects are positioned at the same intersection or on the same road based on road data, and carrying out collision detection on the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road of any three-dimensional object when the two three-dimensional objects are positioned on the adjacent road based on the inter-road communication diagram.
In a third aspect, to achieve the above object, the present invention further provides a computing device, including a memory and one or more processors, where the memory stores executable codes, and the one or more processors are configured to implement a method for detecting a collision of the three-dimensional object in a simulation environment when the one or more processors execute the executable codes.
In a fourth aspect, to achieve the above object, the present invention further provides a computer-readable storage medium having stored thereon a computer program which, when processed and executed, implements the above collision detection method of a three-dimensional object in a simulation environment.
Compared with the prior art, the invention has the beneficial effects that at least the following steps are included:
according to the collision detection method and device provided by the invention, road data in the high-precision map are acquired, and the inter-road communication map is constructed according to the road data, wherein the inter-road communication map records the connection relation between roads, so that collision detection is carried out when the detection pair consisting of two three-dimensional objects is judged to be at the same intersection or the same road based on the road data in each round of automatic driving simulation period, and collision detection is carried out when the detection is judged to be at the adjacent road based on the inter-road communication map under the condition that the length of the rest of the road of any three-dimensional object in the moving direction is smaller than the length of the rest of the road. Therefore, most three-dimensional objects which cannot possibly collide are filtered out through the road data in the high-precision map, and then collision detection is carried out on the rest three-dimensional objects, so that the efficiency of collision detection is improved, and the consumption of calculation resources is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for collision detection of a three-dimensional object in a simulated environment provided by an embodiment of the present invention;
FIG. 2 is an exemplary diagram of an inter-road communication map provided by an embodiment of the present invention;
FIG. 3 is another flow chart of a method for collision detection of a three-dimensional object in a simulated environment provided by an embodiment of the present invention;
FIG. 4 is a flow chart of a collision detection apparatus for a three-dimensional object in a simulated environment provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description is presented by way of example only and is not intended to limit the scope of the invention.
The invention is characterized in that: aiming at the technical problems that a large amount of invalid calculation exists and the calculation consumption is large, the simulation efficiency is low and the real-time performance is poor when all objects are detected and collided in the existing automatic driving scene, the embodiment of the invention provides the collision detection method and device for the three-dimensional objects in the simulation environment, and the road data in a high-precision map is used as a data basis to filter out most of the three-dimensional objects which cannot possibly collide, and then the collision detection is carried out on the rest three-dimensional objects, so that the collision detection efficiency and the real-time performance are improved, and the calculation resource consumption is reduced.
Fig. 1 is a flowchart of a method for detecting a collision of a three-dimensional object in a simulation environment, as shown in fig. 1, where the method for detecting a collision of a three-dimensional object in a simulation environment includes the following steps:
s110, acquiring road data in the high-precision map.
In an embodiment, a high-precision map, which is a high-precision map for automatic driving, is obtained in real time, and the map precision can be up to the centimeter level. The road data in the high-definition map includes a road ID, a road length L, a road orientation H, and an intersection J to which the road belongs.
S120, constructing an inter-road communication map based on the road data.
In an embodiment, constructing an inter-road connectivity graph based on road data includes: and taking each road as a connecting edge, and adding a vertex between the two connected roads to form an inter-road communication diagram.
Specifically, each road R in the road set R in the high-precision map 1 ,r 2 ,…,r n Each connecting edge e as a road-to-road communication graph 1 ,e 2 ,…,e n If two continuous edges r in high-precision map i And r j Directly connected, then at e i And e j Adding a vertex v between ij An inter-road communication map G is formed as shown in fig. 2.
And S130, in each automatic driving simulation period, collision detection is carried out on detection pairs consisting of two three-dimensional objects when the road data are judged to be at the same intersection or the same road, and collision detection is carried out on the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road when the road is judged to be at the adjacent road based on the inter-road communication diagram.
In the embodiment, the three-dimensional object refers to an entity with a three-dimensional shape, including pedestrians, automobiles, signboards and other entities on roads, and the entity is denoted by o.
In an embodiment, before simulation, the road, frenet coordinates and moving direction of each three-dimensional object in the autopilot simulation environment in the high-precision map are initialized. In the field of autopilot, the Frenet coordinate system, which describes the position of an object relative to the road, is more suitable because most roads are not straight, but arc with a degree of curvature. In an embodiment, frenet coordinates include a distance s along the road reference line direction, a distance l along the road reference line normal vector direction, of the three-dimensional object. The value of the moving direction d is 0< d <2 pi.
In the embodiment, the simulation collision detection is carried out according to a simulation period, wherein the simulation period is set by itself, and in each round of automatic driving simulation period, firstly, the Frenet coordinate and the moving direction of each three-dimensional object in the automatic driving simulation environment in a high-precision map are updated; then, three-dimensional objects in the automatic driving simulation environment are arranged and combined pairwise to form a detection pair set D [ (o) 1 ,o 2 ), (o 1 ,o 3 ), ..., (o m , o n )]Traversing the set of detection pairs D, for each detection pair (o i , o j ) The method for judging the position and detecting the collision of the three-dimensional object comprises the following steps: for a detection pair consisting of two three-dimensional objects, collision detection is performed when the two three-dimensional objects are judged to be at the same intersection or the same road based on road data, and collision detection is performed when the two three-dimensional objects are judged to be at adjacent roads based on an inter-road communication map under the condition that the length of the remaining road of any three-dimensional object in the moving direction is smaller than the length of the remaining road.
In an embodiment, the detecting a collision when the road data is determined to be at the same intersection or the same road includes: according to the detection of two three-dimensional objects (o i , o j ) Comparing the road with the road ID in the road data to judge whether the road is on the same road, and performing collision detection when the road is on the same road; according to the detection of two three-dimensional objects (o i , o j ) The road, the current Frenet coordinates and bounding box information are compared with the intersection of the road in the road data to judge whether the road is at the same intersection, and collision detection is carried out when the road is at the same intersection.
In an embodiment, determining that the road is adjacent based on the inter-road communication map includes: searching two continuous edges corresponding to the road where the two three-dimensional objects are located in the inter-road communication graph, judging that the two continuous edges are separated by a vertex, if the two continuous edges are positioned on adjacent roads, and continuously judging any three-dimensional object o if the two continuous edges are positioned on the adjacent roads i Or o j Whether the remaining road length in the moving direction is smaller than itselfAnd the length is smaller than the self length, and collision detection is carried out.
Illustratively, for detecting a position of two three-dimensional objects (o i , o j ) Find O in graph G i The road r where i Corresponding edge e i And o j The road r where j Corresponding edge e j Judging e in the inter-road communication graph G i And e j Whether or not to be separated by a vertex, if so, two three-dimensional objects (o i , o j ) On the adjacent lane, otherwise not on the adjacent lane.
In an embodiment, the remaining road length of the three-dimensional object in the moving direction is calculated by: if the difference between the moving direction of the three-dimensional object and the road direction of the road where the three-dimensional object is located is [ -pi/2, pi/2 ], the remaining road length is the road length of the road where the three-dimensional object is located minus the distance of the three-dimensional object along the road reference line direction, otherwise the remaining road length is the distance of the three-dimensional object along the road reference line direction.
Illustratively, for three-dimensional objects o i The remaining road length calculation process in the moving direction is as follows: read o i Road r i If o i Is in the direction d of movement of (2) i And r i Is directed toward h i The difference between [ -pi/2, pi/2]Remaining road length b i For the road length l i Subtracting o i Along the road reference line direction distance s i Otherwise the remaining road length is s i。
In an embodiment, according to the three-dimensional object o i And o j Collision detection is performed with the bounding box information and Frenet coordinates.
Based on step S130 of the above collision detection method, the embodiment further provides specific steps of the simulation flow, as shown in fig. 3, including the following steps:
s310, initializing the position of each three-dimensional object in a high-precision map and starting simulation;
s320, judging whether the simulation is finished, if so, directly finishing the simulation, and if not, executing S330;
s330, forming detection pairs for every two three-dimensional objects, and constructing a detection pair set;
s340, judging whether all detection pairs are detected completely, if yes, jumping to execute S320, and if not, executing S350;
s350, acquiring a next pair of detection pairs to be detected;
s360, judging whether two three-dimensional objects in the detection pair are at the same intersection, if so, executing S390, and if not, executing S370;
s370, judging whether two three-dimensional objects in the detection pair are in the same lane, if so, executing S390, and if not, executing S380;
s380, judging whether two three-dimensional objects in the detection pair are positioned in adjacent lanes, wherein the length of the remaining road of a single three-dimensional object in the moving direction is less than the length of the single three-dimensional object, if so, executing S390, otherwise, judging that the two objects are unlikely to collide, ending the detection and jumping to execute S350;
s390; and performing collision detection on the two three-dimensional objects in the detection pair.
According to the collision detection method for the three-dimensional object in the simulation environment, most three-dimensional objects which cannot possibly collide are filtered out through the road data in the high-precision map, and then collision detection is carried out on the rest three-dimensional objects, so that the collision detection efficiency is improved, and the consumption of computing resources is reduced.
Based on the same inventive concept, an embodiment further provides a collision detection device of a three-dimensional object in a simulation environment, as shown in fig. 4, including an acquisition module 410, a graph construction module 420, and a judgment and detection module 430.
The acquiring module 410 is configured to acquire road data in the high-precision map; the diagram construction module 420 is configured to construct an inter-road connectivity diagram based on the road data; the judging and detecting module 430 is configured to perform collision detection on a detection pair consisting of two three-dimensional objects in each automatic driving simulation period, when the two three-dimensional objects are judged to be at the same intersection or the same road based on road data, and when the two three-dimensional objects are judged to be at adjacent roads based on an inter-road communication map, the collision detection is performed under a condition that the length of the remaining road of any three-dimensional object in the moving direction is smaller than the length of the other three-dimensional object.
It should be noted that, in the collision detection device of the three-dimensional object in the simulation environment provided in the foregoing embodiment, the division of the functional modules should be used for illustration, and the foregoing functional allocation may be performed by different functional modules according to the need, that is, the internal structure of the terminal or the server is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the collision detection device of the three-dimensional object in the simulation environment provided in the above embodiment belongs to the same concept as the collision detection method embodiment of the three-dimensional object in the simulation environment, and the specific implementation process of the collision detection device is detailed in the collision detection method embodiment of the three-dimensional object in the simulation environment, which is not described herein.
According to the collision detection device for the three-dimensional object in the simulation environment, most of three-dimensional objects which cannot possibly collide are filtered through the road data in the high-precision map, and then collision detection is carried out on the rest three-dimensional objects, so that the collision detection efficiency is improved, and the consumption of computing resources is reduced.
Based on the same inventive concept, an embodiment further provides a computing device including a memory and one or more processors, wherein the memory stores executable code, and the one or more processors execute the executable code to implement a collision detection method of a three-dimensional object in a simulation environment, including the steps of:
s110, acquiring road data in a high-precision map;
s120, constructing an inter-road communication diagram based on road data;
and S130, in each automatic driving simulation period, collision detection is carried out on detection pairs consisting of two three-dimensional objects when the road data are judged to be at the same intersection or the same road, and collision detection is carried out on the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road when the road is judged to be at the adjacent road based on the inter-road communication diagram.
As shown in fig. 5, the computing device provided by the embodiment includes, at a hardware level, hardware required by other services such as internal buses, network interfaces, and memories, in addition to the processor and the memory. The memory is a nonvolatile memory, and the processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to realize the collision detection method of the three-dimensional object in the simulation environment, which is described in the above steps S110-S130. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present invention, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
Based on the same inventive concept, an embodiment further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-mentioned collision detection method of a three-dimensional object in a simulation environment, specifically comprising the steps of:
s110, acquiring road data in a high-precision map;
s120, constructing an inter-road communication diagram based on road data;
and S130, in each automatic driving simulation period, collision detection is carried out on detection pairs consisting of two three-dimensional objects when the road data are judged to be at the same intersection or the same road, and collision detection is carried out on the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road when the road is judged to be at the adjacent road based on the inter-road communication diagram.
In embodiments, computer-readable media, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, read only optical disk read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
The foregoing detailed description of the preferred embodiments and advantages of the invention will be appreciated that the foregoing description is merely illustrative of the presently preferred embodiments of the invention, and that no changes, additions, substitutions and equivalents of those embodiments are intended to be included within the scope of the invention.
Claims (8)
1. A method for collision detection of a three-dimensional object in a simulated environment, comprising the steps of:
acquiring road data in a high-precision map;
constructing an inter-road communication graph based on the road data; in each round of automatic driving simulation period, aiming at a detection pair consisting of two three-dimensional objects, collision detection is carried out when the road data is judged to be at the same intersection or the same road, and collision detection is carried out when the road-to-road communication diagram is judged to be at an adjacent road under the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road;
before simulation, initializing a road, frenet coordinates and a moving direction of each three-dimensional object in an automatic driving simulation environment in a high-precision map, wherein the Frenet coordinates comprise a distance of the three-dimensional object along a road reference line direction and a distance of the three-dimensional object along a road reference line normal vector direction;
updating Frenet coordinates and moving directions of each three-dimensional object before each round of judgment is carried out;
wherein, judge and be in the same intersection or carry out collision detection when same road based on the road data, include: comparing the road where the two three-dimensional objects in the detection pair are positioned with the road ID in the road data to judge whether the two three-dimensional objects are positioned on the same road, and performing collision detection when the two three-dimensional objects are positioned on the same road; and comparing the road where the two three-dimensional objects in the detection pair are located, the current Frenet coordinates and bounding box information with the intersection where the road in the road data belongs to so as to judge whether the two three-dimensional objects are located at the same intersection, and performing collision detection when the two three-dimensional objects are located at the same intersection.
2. The method for detecting the collision of the three-dimensional object in the simulation environment according to claim 1, wherein the road data includes a road ID, a road length, a road orientation, an intersection to which the road belongs.
3. The method for detecting collision of three-dimensional objects in a simulation environment according to claim 1, wherein constructing the inter-road communication map based on road data comprises:
and taking each road as a connecting edge, and adding a vertex between the two connected roads to form an inter-road communication diagram.
4. The method for detecting the collision of the three-dimensional object in the simulation environment according to claim 1, wherein the judging of the adjacent road based on the inter-road communication map includes:
searching two continuous edges corresponding to the road where the two three-dimensional objects are located in the inter-road communication graph, and judging that the two continuous edges are separated by a vertex, wherein the two three-dimensional objects are located in adjacent roads.
5. The method for detecting the collision of the three-dimensional object in the simulation environment according to claim 1, wherein the remaining road length of the three-dimensional object in the moving direction is calculated by:
if the difference between the moving direction of the three-dimensional object and the road direction of the road where the three-dimensional object is located is [ -pi/2, pi/2 ], the remaining road length is the road length of the road where the three-dimensional object is located minus the distance of the three-dimensional object along the road reference line direction, otherwise the remaining road length is the distance of the three-dimensional object along the road reference line direction.
6. A collision detection apparatus for a three-dimensional object in a simulated environment, comprising:
the acquisition module is used for acquiring road data in the high-precision map;
the map construction module is used for constructing an inter-road communication map based on road data;
the judging and detecting module is used for carrying out collision detection on the detection pair consisting of two three-dimensional objects in each automatic driving simulation period, judging whether the two three-dimensional objects are positioned at the same intersection or on the same road based on road data, and carrying out collision detection on the condition that the length of the rest road of any three-dimensional object in the moving direction is smaller than the length of the rest road of any three-dimensional object when the two three-dimensional objects are positioned on the adjacent road based on the inter-road communication diagram;
before simulation, initializing a road, frenet coordinates and a moving direction of each three-dimensional object in an automatic driving simulation environment in a high-precision map, wherein the Frenet coordinates comprise a distance of the three-dimensional object along a road reference line direction and a distance of the three-dimensional object along a road reference line normal vector direction;
updating Frenet coordinates and moving directions of each three-dimensional object before each round of judgment is carried out;
wherein, judge and be in the same intersection or carry out collision detection when same road based on the road data, include: comparing the road where the two three-dimensional objects in the detection pair are positioned with the road ID in the road data to judge whether the two three-dimensional objects are positioned on the same road, and performing collision detection when the two three-dimensional objects are positioned on the same road; and comparing the road where the two three-dimensional objects in the detection pair are located, the current Frenet coordinates and bounding box information with the intersection where the road in the road data belongs to so as to judge whether the two three-dimensional objects are located at the same intersection, and performing collision detection when the two three-dimensional objects are located at the same intersection.
7. A computing device comprising a memory and one or more processors, the memory having executable code stored therein, wherein the one or more processors, when executing the executable code, are configured to implement the method of collision detection of a three-dimensional object in a simulated environment of any of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being processed and executed, implements a collision detection method of a three-dimensional object in a simulation environment according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310781219.9A CN116502479B (en) | 2023-06-29 | 2023-06-29 | Collision detection method and device of three-dimensional object in simulation environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310781219.9A CN116502479B (en) | 2023-06-29 | 2023-06-29 | Collision detection method and device of three-dimensional object in simulation environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116502479A CN116502479A (en) | 2023-07-28 |
| CN116502479B true CN116502479B (en) | 2023-09-01 |
Family
ID=87328883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310781219.9A Active CN116502479B (en) | 2023-06-29 | 2023-06-29 | Collision detection method and device of three-dimensional object in simulation environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116502479B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9628975B1 (en) * | 2014-08-06 | 2017-04-18 | Mobile Video Computing Solutions Llc | Crash event detection, response and reporting apparatus and method |
| CN108628184A (en) * | 2018-06-13 | 2018-10-09 | 华南理工大学 | A kind of collision checking method for robot emulation system |
| CN111177888A (en) * | 2019-12-09 | 2020-05-19 | 武汉光庭信息技术股份有限公司 | Simulation scene collision detection method and system |
| CN112632734A (en) * | 2020-12-29 | 2021-04-09 | 武汉中海庭数据技术有限公司 | High-precision map road connectivity test method and system |
| CN115048824A (en) * | 2022-08-15 | 2022-09-13 | 北京华航唯实机器人科技股份有限公司 | Collision detection method and device and computer readable medium |
| CN115230694A (en) * | 2022-09-20 | 2022-10-25 | 毫末智行科技有限公司 | Obstacle recognition method and device for automatic driving vehicle and vehicle |
| WO2023024542A1 (en) * | 2021-08-25 | 2023-03-02 | 驭势科技（北京）有限公司 | Vehicle decision-making planning method and apparatus, and device and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6069923B2 (en) * | 2012-07-20 | 2017-02-01 | セイコーエプソン株式会社 | Robot system, robot, robot controller |
-
2023
- 2023-06-29 CN CN202310781219.9A patent/CN116502479B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9628975B1 (en) * | 2014-08-06 | 2017-04-18 | Mobile Video Computing Solutions Llc | Crash event detection, response and reporting apparatus and method |
| CN108628184A (en) * | 2018-06-13 | 2018-10-09 | 华南理工大学 | A kind of collision checking method for robot emulation system |
| CN111177888A (en) * | 2019-12-09 | 2020-05-19 | 武汉光庭信息技术股份有限公司 | Simulation scene collision detection method and system |
| CN112632734A (en) * | 2020-12-29 | 2021-04-09 | 武汉中海庭数据技术有限公司 | High-precision map road connectivity test method and system |
| WO2023024542A1 (en) * | 2021-08-25 | 2023-03-02 | 驭势科技（北京）有限公司 | Vehicle decision-making planning method and apparatus, and device and medium |
| CN115048824A (en) * | 2022-08-15 | 2022-09-13 | 北京华航唯实机器人科技股份有限公司 | Collision detection method and device and computer readable medium |
| CN115230694A (en) * | 2022-09-20 | 2022-10-25 | 毫末智行科技有限公司 | Obstacle recognition method and device for automatic driving vehicle and vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 面向低速自动驾驶车辆的避障规划研究;肖宏宇;付志强;陈慧勇;;同济大学学报(自然科学版)(S1);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116502479A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709058B2 (en) | Path planning method and device and mobile device | |
| CN109509210B (en) | Obstacle tracking method and device | |
| CN108732556B (en) | Vehicle-mounted laser radar simulation method based on geometric intersection operation | |
| JP6561199B2 (en) | Urban road recognition method, apparatus, storage medium and equipment based on laser point cloud | |
| JP6595182B2 (en) | Systems and methods for mapping, locating, and attitude correction | |
| CN110045376A (en) | It can travel area obtaining method, computer readable storage medium and terminal device | |
| CN111582189B (en) | Traffic signal lamp identification method and device, vehicle-mounted control terminal and motor vehicle | |
| CN111338361A (en) | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle | |
| CN109849930B (en) | Method and device for calculating speed of adjacent vehicle of automatic driving automobile | |
| CN113325389A (en) | Unmanned vehicle laser radar positioning method, system and storage medium | |
| CN115617042A (en) | Collision detection method and device, terminal equipment and computer-readable storage medium | |
| CN112036274A (en) | Driving region detection method and device, electronic equipment and storage medium | |
| CN115326051A (en) | Positioning method and device based on dynamic scene, robot and medium | |
| WO2022078342A1 (en) | Dynamic occupancy grid estimation method and apparatus | |
| CN113793534B (en) | Method and device for determining driving risk field under cooperative vehicle and road environment | |
| CN113345093B (en) | Filtering method for laser radar point cloud trailing points | |
| CN110782774A (en) | Crowdsourcing road data distributed processing method and device | |
| CN116502479B (en) | Collision detection method and device of three-dimensional object in simulation environment | |
| CN115164919B (en) | Method and device for constructing spatial travelable area map based on binocular camera | |
| WO2020248118A1 (en) | Point cloud processing method, system and device, and storage medium | |
| CN116740680A (en) | Vehicle positioning method and device and electronic equipment | |
| CN111210297B (en) | Method and device for dividing boarding points | |
| CN113160398B (en) | Rapid three-dimensional grid construction system, method, medium, equipment and unmanned vehicle | |
| CN114137524A (en) | Driving obstacle state estimation method and system based on millimeter wave radar | |
| CN115649178A (en) | Road boundary detection method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |