CN110320531B - Obstacle identification method based on laser radar, map creation method and device - Google Patents
Obstacle identification method based on laser radar, map creation method and device Download PDFInfo
- Publication number
- CN110320531B CN110320531B CN201810277257.XA CN201810277257A CN110320531B CN 110320531 B CN110320531 B CN 110320531B CN 201810277257 A CN201810277257 A CN 201810277257A CN 110320531 B CN110320531 B CN 110320531B
- Authority
- CN
- China
- Prior art keywords
- distance
- vehicle
- information
- obstacle
- laser radar
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to the technical field of environment perception of intelligent vehicles, in particular to a method for identifying obstacles based on a laser radar, a method and a device for creating a map. Obtaining a first distance on the left side of the vehicle and a second distance on the right side of the vehicle according to the obtained lane information of the current vehicle; analyzing obstacle information detected by the laser radar to obtain the transverse distance between the point cloud data and the vehicle; removing information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle, clustering the residual obstacle information, extracting contour points, and updating the grid map by using the obstacle contour point information; the method has the advantages that data processing amount and resource occupation are reduced, processing efficiency is improved, points except contour points are eliminated, the data processing amount is reduced, the problems that processing resources are occupied greatly and processing efficiency is low due to the fact that laser radar data volume is large are solved, and the problem that driving is affected due to the fact that the range of a rectangular frame of the obstacle after low-arc-shaped obstacle clustering is larger than the influence range of an actual obstacle is solved.
Description
Technical Field
The invention relates to the technical field of environment perception of intelligent vehicles, in particular to a method for identifying obstacles based on a laser radar, a method and a device for creating a map.
Background
The automatic driving automobile depends on the cooperation of artificial intelligence, visual calculation, radar, monitoring device and global positioning system, so that the computer can operate the motor vehicle automatically and safely without any active operation of human. The automatic driving system mainly comprises environment perception, decision planning, motion control and the like. Wherein the environmental perception is a part of the emphasis and difficulty of the automatic driving system. The automatic driving automobile senses environmental information through sensors equipped on the automobile, and the sensors mainly comprise a camera, a laser radar, a millimeter wave radar, an infrared camera and the like. The laser radar has the advantages of long detection distance, high detection precision, strong anti-interference capability, no limitation of day and night and the like, and becomes the key research content of automatic driving environment perception.
A patent document with a chinese patent publication No. CN106997049A discloses a method and a device for detecting an obstacle based on laser point cloud data, which obtains the three-dimensional coordinates of each sampling point in a moving carrier coordinate system according to the laser point cloud data of an object detected by a laser radar, establishes a grid map, and projects the sampling points onto the grids corresponding to the grid map according to the three-dimensional coordinates of each sampling point; and determining an obstacle grid according to the grid map to obtain an obstacle grid map, and further determining the position and the shape of the obstacle.
However, because the amount of data of the laser radar is large, in practical application, if all obstacle information detected by the laser radar is analyzed, unnecessary obstacle information, such as an obstacle which has no influence on a vehicle and is far away, can be obtained, and the processing method of projecting all information into the grid map can seriously occupy the resources of a processing device, influence the processing efficiency of data, and bring adverse effects to the practical application of the laser radar.
Disclosure of Invention
The invention aims to provide a method for identifying obstacles based on a laser radar, a method and a device for creating a map, which are used for solving the problems of large occupation of processing resources and low processing efficiency caused by large data volume of the laser radar.
In order to reduce the data processing amount of the laser radar, reduce the resource occupation, improve the processing efficiency and increase the practicability of the laser radar by eliminating the careless obstacle information, the invention provides a obstacle identification method based on the laser radar, which comprises the following steps:
1) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
2) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
3) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
4) and clustering the residual obstacle information and extracting contour point information of the obstacle target after clustering.
In order to eliminate more careless obstacle information, reduce the data processing amount of the laser radar more, reduce resource occupation better, improve the processing efficiency and increase the practicability of the laser radar, the longitudinal distance from the point cloud data to the vehicle is extracted in the step 2), and the obstacle information of which the longitudinal distance at the front side is greater than the third distance is also eliminated in the step 3).
In order to obtain an accurate and real-time forward rejection distance, the third distance is calculated according to the running speed, the braking performance and the acceleration performance of the vehicle.
In order to facilitate the use of the laser radar and reduce the data processing amount of the laser radar so as to obtain a clear laser radar grid map, the invention also provides a multi-attribute grid map creating method based on the laser radar, which comprises the following steps:
1) creating a multi-attribute grid map comprising position information, speed information, height information and occupation condition information according to the driving speed, lane width, braking distance and turning radius information of the vehicle;
2) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
3) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
4) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
5) and clustering the residual obstacle information, extracting contour point information of the obstacle target after clustering, and updating the grid map according to the contour point information.
In order to remove the forward non-concerned obstacle information, reduce the data processing amount of the laser radar more, reduce the resource occupation better and improve the processing efficiency, the longitudinal distance between the point cloud data and the vehicle is extracted in the step 3), and the obstacle information of which the longitudinal distance at the front side is greater than the third distance is removed in the step 4).
In order to obtain an accurate and real-time forward rejection distance, the third distance is calculated according to the running speed, the braking performance and the acceleration performance of the vehicle.
In order to facilitate the laser radar to be used in the form of software and hardware and reduce the data processing amount of the laser radar so as to obtain a clear laser radar grid map, the invention provides a laser radar-based multi-attribute grid map creation device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the following steps when executing the program:
1) creating a multi-attribute grid map comprising position information, speed information, height information and occupation condition information according to the driving speed, lane width, braking distance and turning radius information of the vehicle;
2) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
3) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
4) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
5) and clustering the residual obstacle information, extracting contour point information of the obstacle target after clustering, and updating the grid map according to the contour point information.
In order to remove the forward non-concerned obstacle information, reduce the data processing amount of the laser radar more, reduce the resource occupation better and improve the processing efficiency, the longitudinal distance between the point cloud data and the vehicle is extracted in the step 3), and the obstacle information of which the longitudinal distance at the front side is greater than the third distance is removed in the step 4).
In order to obtain an accurate and real-time forward rejection distance, the third distance is calculated according to the running speed, the braking performance and the acceleration performance of the vehicle.
Drawings
Fig. 1 is a flowchart of an obstacle identification method based on a lidar according to embodiment 1;
fig. 2 is a flowchart of an obstacle identification method based on a lidar according to embodiment 2;
fig. 3 is a flowchart of a laser radar-based multi-attribute grid map creation method of embodiment 3;
FIG. 4 is a schematic view of a multi-attribute grid map of embodiment 3;
fig. 5 is a flowchart of a method for creating a laser radar-based multi-attribute grid map according to embodiment 4.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1
The embodiment 1 provides an obstacle identification method based on a laser radar, as shown in fig. 1, including the following steps:
1) and obtaining the current driving lane information of the vehicle, and calculating to obtain a first distance between the vehicle and the double yellow lines of the lane and a second distance between the vehicle and the lane fence.
According to the actual situation, the vehicle is in a form of approaching to the right in China, therefore, double yellow lines or single yellow lines of a lane are arranged on the left side of the vehicle, a fence at the edge of the lane is arranged on the right side of the vehicle, when the vehicle body is taken as a coordinate system, a first distance between the double yellow lines of the lane and the left side of the vehicle is calculated according to the acquired lane information of the current vehicle, and a second distance between the fence of the lane or an electronic fence of the current lane obtained according to a map and the right side of the vehicle is calculated.
2) And acquiring and analyzing obstacle information detected by the laser radar, and extracting the transverse distance from the point cloud data to the vehicle.
If the vehicle body is used as a coordinate system, according to the analysis of the obstacle information, the extracted point cloud data has longitudinal coordinates and transverse coordinates, and the transverse coordinates represent the transverse distance from the left side or the right side of the vehicle.
3) And eliminating the obstacle information of which the transverse distance exceeds the first distance on the left side of the vehicle and the second distance on the right side of the vehicle to obtain the residual obstacle information.
When the transverse distance between the extracted point cloud data and the vehicle body is not between the first distance on the left side of the vehicle body and the second distance on the right side of the vehicle body, the point cloud data which are not concerned are judged, the corresponding obstacle information is the information needing to be eliminated, and finally the residual obstacle information is obtained.
4) And clustering the residual obstacle information and extracting contour point information of the obstacle target after clustering.
The residual obstacle information is clustered, the contour points of the clustered obstacles are extracted, if the clustered obstacle size information is directly utilized, the problem of certain inaccuracy exists, the contour points are extracted, the data processing amount of the laser radar can be reduced, and the processing efficiency is improved. And finally, the obstacle can be identified according to the obtained contour point information.
The step 1) and the step 2) do not have a sequence, and can be carried out simultaneously.
Example 2
In order to remove forward non-concerned obstacle information, further reduce data processing amount of the lidar, better reduce resource occupation, and improve processing efficiency, embodiment 2 provides a method for identifying obstacles based on the lidar on the basis of embodiment 1, as shown in fig. 2, wherein forward non-concerned obstacle information of the vehicle is not removed in embodiment 1, so that in embodiment 1, the longitudinal distance from the point cloud data to the vehicle is further extracted in step 2), and obstacle information whose front longitudinal distance is greater than the third distance is further removed in step 3).
And finally, restricting the obstacle information detected by the laser radar in a four-side area, wherein the left side line is a first distance on the left side of the vehicle, the right side line is a second distance on the right side of the vehicle, the front side line is a third distance on the front side of the vehicle, and the bottom line is the front end of the vehicle.
Example 3
This embodiment 3 provides a laser radar-based multi-attribute grid map creation apparatus, where the apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements a laser radar-based multi-attribute grid map creation method, and the creation method, as shown in fig. 3, includes the following steps:
(1) a multi-attribute grid map including position information, speed information, height information, and occupancy information is created according to the traveling speed, lane width, braking distance, and turning radius information of the vehicle.
The method comprises the steps of setting the number of grids according to the running requirements of a vehicle, and simultaneously creating a blank multi-attribute grid map according to the running speed, the lane width, the braking distance and the turning radius information of the vehicle, wherein the multi-attribute grid map comprises position information, speed information, height information and occupation condition information.
(2) And obtaining the current driving lane information of the vehicle, and calculating to obtain a first distance between the vehicle and the double yellow lines of the lane and a second distance between the vehicle and the lane fence.
(3) And acquiring and analyzing obstacle information detected by the laser radar, and extracting the transverse distance from the point cloud data to the vehicle.
(4) And eliminating the obstacle information of which the transverse distance exceeds the first distance on the left side of the vehicle and the second distance on the right side of the vehicle to obtain the residual obstacle information.
There is no sequence between the above steps (2) and (3), and the steps (2), (3) and (4) can be performed simultaneously, and the processing modes of the steps (2), (3) and (4) correspond to those of the steps 1), (2) and (3) in the embodiment 1, respectively.
(5) And clustering the residual obstacle information, extracting contour point information of the obstacle target after clustering, and updating the grid map according to the contour point information.
According to the setting, a lane line, such as lane double yellow line 1, is arranged at the first distance on the left side of the vehicle; and the right second distance of the vehicle is the electronic fence 2, and the multi-attribute grid map is limited between the first distance of the left lateral distance of the vehicle and the second distance of the right lateral distance of the vehicle through the constraint of the lane line and the constraint of the electronic fence, as shown in fig. 4, and finally the obstacle information remained in the interval is obtained.
After the residual obstacle information is obtained, clustering is carried out on the cloud data of the residual obstacle points, obstacle position size information is given after clustering, if the grid map is updated by directly using the position size information, the problem that the size of the obstacle is expanded easily occurs to the arc-shaped obstacle, therefore, the contour point 3 information of the obstacle target after clustering is extracted, the grid map is updated according to the final contour point 3 information, the problem that the size of the obstacle after clustering is reduced, namely the size of the obstacle 5 is expanded, namely the area 4 is expanded is solved, the accuracy of the obstacle size information is improved, and the data processing amount of the laser radar can be reduced.
The grid map is updated through the contour point information of the remaining obstacles, and the grid map which is restricted by the lane lines and the electronic fence can be created, so that the data processing capacity of the laser radar is reduced, the resource occupancy rate is reduced, and the processing efficiency is improved.
Example 4
In this embodiment 4, based on embodiment 3, more pieces of irrelevant obstacle information are removed, and corresponding restrictions are set in the forward direction, so as to reduce the data processing amount of the laser radar more, as shown in fig. 5.
As shown in fig. 4, on the basis of the lane line constraint and the electronic fence constraint, the information of the unconscious obstacles except the third distance in the forward direction of the vehicle is also eliminated, wherein the third distance is calculated according to the running speed, the braking performance and the acceleration performance of the vehicle, and can also be directly set manually according to the requirements.
In the embodiment 3, the longitudinal distance from the point cloud data to the vehicle is further extracted in the step (3), the obstacle information of which the longitudinal distance on the front side is larger than the third distance is also removed in the step (4), and finally obtained residual obstacle information is brought into the updated actual grid map.
The present invention has been described in relation to particular embodiments thereof, but the invention is not limited to the described embodiments. In the thought given by the present invention, the technical means in the above embodiments are changed, replaced, modified in a manner that is easily imaginable to those skilled in the art, and the functions are basically the same as the corresponding technical means in the present invention, and the purpose of the invention is basically the same, so that the technical scheme formed by fine tuning the above embodiments still falls into the protection scope of the present invention.
Claims (9)
1. An obstacle identification method based on a laser radar is characterized by comprising the following steps:
1) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
2) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
3) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
4) and clustering the residual obstacle information and extracting contour point information of the obstacle target after clustering.
2. The obstacle recognition method based on the lidar as recited in claim 1, wherein the longitudinal distance of the point cloud data from the vehicle is further extracted in step 2), and the obstacle information of which the longitudinal distance at the front side is greater than the third distance is further rejected in step 3).
3. The lidar-based obstacle recognition method of claim 2, wherein the third distance is calculated from a traveling speed, a braking performance, and an acceleration performance of the vehicle.
4. A multi-attribute grid map creation method based on laser radar is characterized by comprising the following steps:
1) creating a multi-attribute grid map comprising position information, speed information, height information and occupation condition information according to the driving speed, lane width, braking distance and turning radius information of the vehicle;
2) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
3) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
4) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
5) and clustering the residual obstacle information, extracting contour point information of the obstacle target after clustering, and updating the grid map according to the contour point information.
5. The lidar based multi-attribute grid map creation method according to claim 4, wherein a longitudinal distance from the point cloud data to the vehicle is further extracted in step 3), and obstacle information with a front longitudinal distance greater than a third distance is further rejected in step 4).
6. The lidar based multi-attribute grid map creation method of claim 5, wherein the third distance is calculated from a traveling speed, a braking performance, and an acceleration performance of the vehicle.
7. A lidar based multi-attribute grid map creation apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor when executing the program implements the steps of:
1) creating a multi-attribute grid map comprising position information, speed information, height information and occupation condition information according to the driving speed, lane width, braking distance and turning radius information of the vehicle;
2) acquiring current lane information of vehicle running, and calculating to obtain a first distance between the vehicle and two yellow lines of a lane and a second distance between the vehicle and a lane fence;
3) acquiring and analyzing obstacle information detected by a laser radar, and extracting the transverse distance from point cloud data to a vehicle;
4) removing the obstacle information of which the transverse distance exceeds a first distance on the left side of the vehicle and a second distance on the right side of the vehicle to obtain the residual obstacle information;
5) and clustering the residual obstacle information, extracting contour point information of the obstacle target after clustering, and updating the grid map according to the contour point information.
8. The lidar based multi-attribute grid map creation apparatus according to claim 7, wherein a longitudinal distance from the point cloud data to the vehicle is further extracted in step 3), and obstacle information having a front longitudinal distance greater than a third distance is further rejected in step 4).
9. The lidar based multi-attribute grid map creation apparatus of claim 8, wherein the third distance is calculated from a traveling speed, a braking performance, and an acceleration performance of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810277257.XA CN110320531B (en) | 2018-03-30 | 2018-03-30 | Obstacle identification method based on laser radar, map creation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810277257.XA CN110320531B (en) | 2018-03-30 | 2018-03-30 | Obstacle identification method based on laser radar, map creation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110320531A CN110320531A (en) | 2019-10-11 |
| CN110320531B true CN110320531B (en) | 2021-09-03 |
Family
ID=68111815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810277257.XA Active CN110320531B (en) | 2018-03-30 | 2018-03-30 | Obstacle identification method based on laser radar, map creation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110320531B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110907945A (en) * | 2019-10-28 | 2020-03-24 | 广西电网有限责任公司电力科学研究院 | Positioning method considering indoor and outdoor flight of unmanned aerial vehicle |
| CN111144228B (en) * | 2019-12-05 | 2023-09-12 | 超越科技股份有限公司 | Obstacle identification method based on 3D point cloud data and computer equipment |
| CN111160302B (en) * | 2019-12-31 | 2024-02-23 | 深圳一清创新科技有限公司 | Obstacle information identification method and device based on automatic driving environment |
| CN111338341B (en) * | 2020-02-24 | 2023-07-18 | 北京百度网讯科技有限公司 | Vehicle obstacle avoidance method and device, electronic device, vehicle and storage medium |
| CN111239706B (en) * | 2020-03-30 | 2021-10-01 | 许昌泛网信通科技有限公司 | Laser radar data processing method |
| CN111551957B (en) * | 2020-04-01 | 2023-02-03 | 上海富洁科技有限公司 | Park low-speed automatic cruise and emergency braking system based on laser radar sensing |
| CN113859228B (en) * | 2020-06-30 | 2023-07-25 | 上海商汤智能科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
| CN111735464B (en) * | 2020-08-03 | 2020-12-01 | 北京主线科技有限公司 | Method and device for laser global mapping in port |
| CN112630788A (en) * | 2020-12-08 | 2021-04-09 | 广州小鹏自动驾驶科技有限公司 | Environmental obstacle position information detection method and device |
| CN112598314B (en) * | 2020-12-29 | 2022-08-23 | 潍柴动力股份有限公司 | Method, device, equipment and medium for determining perception confidence of intelligent driving automobile |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636763A (en) * | 2014-12-01 | 2015-05-20 | 北京工业大学 | Road and obstacle detecting method based on remotely piloted vehicles |
| CN105866790A (en) * | 2016-04-07 | 2016-08-17 | 重庆大学 | Laser radar barrier identification method and system taking laser emission intensity into consideration |
| CN206306932U (en) * | 2016-12-20 | 2017-07-07 | 山东科技大学 | A kind of vehicle turn signal automatic control system |
| CN107064955A (en) * | 2017-04-19 | 2017-08-18 | 北京汽车集团有限公司 | barrier clustering method and device |
| CN107272680A (en) * | 2017-06-16 | 2017-10-20 | 华南理工大学 | A kind of automatic follower method of robot based on ROS robot operating systems |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101104609B1 (en) * | 2007-10-26 | 2012-01-12 | 주식회사 만도 | Method and System for Recognizing Target Parking Location |
-
2018
- 2018-03-30 CN CN201810277257.XA patent/CN110320531B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636763A (en) * | 2014-12-01 | 2015-05-20 | 北京工业大学 | Road and obstacle detecting method based on remotely piloted vehicles |
| CN105866790A (en) * | 2016-04-07 | 2016-08-17 | 重庆大学 | Laser radar barrier identification method and system taking laser emission intensity into consideration |
| CN206306932U (en) * | 2016-12-20 | 2017-07-07 | 山东科技大学 | A kind of vehicle turn signal automatic control system |
| CN107064955A (en) * | 2017-04-19 | 2017-08-18 | 北京汽车集团有限公司 | barrier clustering method and device |
| CN107272680A (en) * | 2017-06-16 | 2017-10-20 | 华南理工大学 | A kind of automatic follower method of robot based on ROS robot operating systems |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110320531A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110320531B (en) | Obstacle identification method based on laser radar, map creation method and device | |
| CN108345822B (en) | Point cloud data processing method and device | |
| CN111537994B (en) | Unmanned mine card obstacle detection method | |
| CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
| CN111487641B (en) | Method and device for detecting object by using laser radar, electronic equipment and storage medium | |
| CN113424121A (en) | Vehicle speed control method and device based on automatic driving and computer equipment | |
| CN111192311B (en) | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making | |
| CN112462381B (en) | Multi-laser radar fusion method based on vehicle-road cooperation | |
| CN110210384B (en) | Road global information real-time extraction and representation system | |
| CN105955275B (en) | Robot path planning method and system | |
| CN106683530A (en) | Computerized judging system and method based on three-dimensional laser vision and high-precision lane model | |
| CN110286389A (en) | A kind of grid management method for obstacle recognition | |
| CN108345823B (en) | Obstacle tracking method and device based on Kalman filtering | |
| CN105205805A (en) | Vision-based intelligent vehicle transverse control method | |
| WO2022078342A1 (en) | Dynamic occupancy grid estimation method and apparatus | |
| US20210213955A1 (en) | Method and apparatus for evaluating a vehicle travel surface | |
| WO2021199584A1 (en) | Detecting debris in a vehicle path | |
| CN114743181A (en) | Road vehicle target detection method and system, electronic device and storage medium | |
| CN115018879A (en) | Target detection method, computer-readable storage medium, and driving apparatus | |
| CN117677976A (en) | Method for generating travelable region, mobile platform, and storage medium | |
| CN113740874A (en) | Road edge detection method, electronic equipment and vehicle | |
| CN117576652A (en) | Road object identification method and device, storage medium and electronic equipment | |
| US20230143963A1 (en) | Trajectory design for image data acquisition for object detection/recognition | |
| CN113189610B (en) | Map-enhanced autopilot multi-target tracking method and related equipment | |
| CN114779276A (en) | Obstacle detection method and device |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 450061 Yudao Road, Guancheng District, Zhengzhou City, Henan Province Patentee after: Yutong Bus Co.,Ltd. Address before: 450016 Yutong Road, Guancheng District, Zhengzhou City, Henan Province Patentee before: ZHENGZHOU YUTONG BUS Co.,Ltd. |