CN115562281A - Dynamic path planning method for automatic parking system in complex environment - Google Patents
Dynamic path planning method for automatic parking system in complex environment Download PDFInfo
- Publication number
- CN115562281A CN115562281A CN202211248482.3A CN202211248482A CN115562281A CN 115562281 A CN115562281 A CN 115562281A CN 202211248482 A CN202211248482 A CN 202211248482A CN 115562281 A CN115562281 A CN 115562281A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- path
- dynamic
- automatic parking
- 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
- 230000003068 static effect Effects 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 4
- 239000007787 solid Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent driving, in particular to a dynamic path planning method of an automatic parking system in a complex environment. The specific process of the invention comprises: s1, establishing an automatic vehicle parking path under a static environment map; s2, combining the automatic parking path with the vehicle kinematics model to define a safe driving area range in the vehicle parking process; s3, in the process that the vehicle follows the parking path, local dynamic environment monitoring is established under a static environment map; s4, in the running process of the vehicle, when dynamic obstacles appear in the range of a safe running area, re-planning by establishing an automatic parking path; the obstacle avoidance and parking adjustment device is used for avoiding obstacles and adjusting parking in the parking process. The invention improves the environmental adaptability of the automatic parking control system, simultaneously improves the safety performance of the driver in the auxiliary driving process, and can be used in association under various scenes of vertical, parallel and lateral parking.
Description
Technical Field
The invention relates to the technical field of intelligent driving, wherein IPC classification numbers are as follows: B60W30/06, in particular to a dynamic path planning method of an automatic parking system in a complex environment.
Background
At present, with the development of social economy and the annual increase of the vehicle utilization rate, vehicles become a necessary tool for people to go out daily, but with the increase of the vehicle utilization rate, the problems of traffic jam and difficulty in parking are increasingly prominent, the difficulty in parking gradually becomes one of the problems which owners have to face in the driving process, and in the face of the problem, an automatic parking system arises, and the automatic parking system helps drivers to rapidly plan parking paths and perform parking early warning through an auxiliary driving mode, so that the parking efficiency of the drivers is effectively improved. However, the automatic parking system is generally only suitable for an open and static scene in an actual use process, and when a parking scene is interfered by external factors and is shielded by an obstacle, the automatic parking effect is seriously influenced, even the automatic parking system collides with the obstacle, and finally the safety of vehicle driving and backing and warehousing is influenced.
CN202010214349 provides an automatic parking path planning method and system, and a parking control device, in which a multi-level tree-based search manner is established to dynamically plan a parking path, and the planned path is tangent to a median line of a vehicle, so as to implement following of the vehicle based on the planned path. However, the periodic path information manner described in this patent cannot quickly respond to a sudden obstacle, and only can identify the sudden obstacle after waiting for periodic update, and cannot better ensure the safety of backing up and entering a garage in the vehicle driving process.
The patent CN201780000872 provides a method and a device for controlling vehicle driving, in the patent, environment information in an external environment is acquired and transmitted to a vehicle-mounted controller, so as to control the vehicle driving through controlling the vehicle-mounted controller, but dynamic environment information cannot be obtained and generated without reason, and must be obtained and acquired in real time through a sensor.
Therefore, the invention provides a dynamic path planning method of an automatic parking system in a complex environment, aiming at the problems existing in the existing automatic parking dynamic path tracking.
Disclosure of Invention
Aiming at the existing problems, the invention provides a dynamic path planning method of an automatic parking system in a complex environment, which comprises the following specific processes: s1, establishing an automatic parking path of a vehicle under a static environment map; s2, combining the automatic parking path with the vehicle kinematics model to define a safe driving area range in the vehicle parking process; s3, in the process that the vehicle follows the parking path, local dynamic environment monitoring is established under a static environment map; s4, in the vehicle driving process, when dynamic obstacles appear in the safe driving area range, re-planning by establishing an automatic parking path; the obstacle avoidance and parking adjustment device is used for avoiding obstacles and adjusting parking in the parking process.
Specifically, the complex environments described in the present invention include parking environments in which obstacles are placed in a complex manner in a static environment, and parking environments in which dynamic obstacles exist.
Preferably, the static environment map is used for data acquisition and environment construction in a multi-sensor fusion-based mode; the multi-sensor comprises a solid laser radar and a vehicle-mounted combined inertial navigation system.
Preferably, the solid-state laser radar establishes a laser point cloud map based on parking spaces, real-time position calibration of the vehicle body is carried out on the laser point cloud map based on the laser point cloud map by collecting control information in the vehicle controller, and the real-time position calibration is combined with vehicle-mounted combined inertial navigation to correct calibration errors.
Preferably, a rasterized environment map is established in the static environment map, and an automatic parking path point is established on the rasterized environment map.
Preferably, the safe driving area range is firstly constructed by taking the edge size of the vehicle constructed by the vehicle dynamics model as a reference and taking the automatic parking path of the vehicle as a direction.
Preferably, an expansion boundary based on a safe driving area is established on the initial driving area.
Specifically, the expansion boundary is adaptively adjusted according to the pose information of the vehicle body in the three-dimensional grid map, so that the problem that the ground two-dimensional information is not collided and scratched but the three-dimensional pose information of the vehicle body is collided and scratched is solved.
Preferably, in the automatic parking path re-planning, when a dynamic obstacle is detected in the safe driving area range in the driving process of the vehicle, a local path planning algorithm based on a polynomial is established, and a parking early warning signal is provided at the same time.
Specifically, in the polynomial-based local path planning algorithm, a circular track is drawn according to position points of a dynamic obstacle, an intersection point of the circular track and an automatic parking track of a vehicle is calculated, a moving direction of the dynamic obstacle is determined through a solid laser radar, an obstacle avoidance curve angle is adjusted according to the intersection point and the moving direction, a parking path is regenerated in a three-dimensional grid map by combining position and posture information of a vehicle terminal point, and a shortest path calculation principle is adopted through the generated re-planned path to further shorten parking time.
Preferably, the polynomial local path planning algorithm establishes an obstacle avoidance curve which takes the dynamic obstacle as a circle center in the grid environment map based on the dynamic obstacle constraint parameter, and establishes a re-planned path from the current point to the ending point of the vehicle.
Preferably, in the dynamic path planning method, a vehicle parking specification constraint is established, and in the parking specification constraint, the vehicle warehousing specification degree is automatically evaluated by judging whether the edge size of the vehicle is overlapped with the parking space calibration point.
Specifically, the parking space calibration points automatically identify and position and pose by a solid laser radar,
Preferably, in the vehicle parking regulation constraint, when the vehicle warehousing regulation degree exceeds the specified score, the vehicle body deviation correction path is re-planned according to the deviation angle between the vehicle edge size and the parking space calibration point, so that the automatic deviation correction of the vehicle body position is performed.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a dynamic path planning method of an automatic parking system in a complex environment, which carries out fusion control by using a solid laser radar and vehicle-mounted combined inertial navigation, monitors and identifies dynamic obstacles in a parking space environment on the basis of calling a static environment map in the parking space environment, thereby carrying out real-time parking path adjustment and early warning according to the motion state of the dynamic obstacles, sending related planning data to a vehicle-mounted controller for vehicle auxiliary deviation correction, improving the environmental adaptability of the automatic parking control system, simultaneously improving the safety performance of a driver in the auxiliary driving process, and being used in association under various scenes of vertical, parallel and lateral parking.
Drawings
Fig. 1 is a flow chart of a dynamic path planning method of an automatic parking system in a complex environment.
Detailed Description
Example 1:
in the embodiment, as shown in fig. 1, the method for planning the dynamic path of the automatic parking system in the complex environment specifically includes the following steps: s1, establishing an automatic vehicle parking path under a static environment map; s2, combining the automatic parking path with the vehicle kinematics model to define a safe driving area range in the vehicle parking process; s3, in the process that the vehicle follows the parking path, local dynamic environment monitoring is established under a static environment map;
s4, in the vehicle driving process, when dynamic obstacles appear in the safe driving area range, re-planning by establishing an automatic parking path; the method is used for avoiding obstacles and adjusting parking in the parking process.
The static environment map is used for data acquisition and environment construction in a multi-sensor fusion-based mode; the multi-sensor comprises a solid laser radar and a vehicle-mounted combined inertial navigation system.
Specifically, the data acquisition and environment construction are carried out in a multi-sensor fusion-based mode, point cloud data of a solid-state laser radar are preprocessed, a parking environment-based three-dimensional environment point cloud map is built through the data preprocessing, point cloud distortion removal and point cloud registration calculation are carried out on the three-dimensional environment point cloud map, on the basis of the point cloud data preprocessing, feature extraction of the point cloud data based on static obstacles is carried out, edge information in the parking environment is identified, meanwhile, deep sliding window optimization is built on the basis, the point cloud information at the designated moment and vehicle-mounted combined inertial navigation are subjected to registration calculation, and therefore error correction is carried out on the acquired point cloud data through the vehicle-mounted combined inertial navigation data.
And establishing a grid environment map in the static environment map, and establishing automatic parking path points on the grid environment map.
Specifically, in the rasterized environment map provided by the invention, in order to further register with a three-dimensional environment point cloud map established based on a solid-state laser radar, a three-dimensional grid map based on a three-dimensional structure is established, and height information is blended into the three-dimensional grid map and is used for positioning and extracting edge pose data of an obstacle in a static environment. In the three-dimensional grid map based on the three-dimensional structure, the conversion from the point cloud map to the three-dimensional grid map is further realized by adopting a mode of mutually combining the cluster analysis based on adjacent points and the interpolation fitting.
The safe driving area range is characterized in that an initial driving area is constructed by taking the edge size of a vehicle constructed by a vehicle dynamic model as a reference and taking an automatic parking path of the vehicle as a direction.
Specifically, the safe driving area range is constructed to avoid scraping and damaging of the edges of the vehicle and static obstacles due to edge errors generated in the construction process of the environment map in a complex environment, but the safe driving area range constructed by combining the vehicle dynamics model and the automatic parking path is the minimum range of vehicle driving, and the problem that the planned safe driving area range is limited in the actual automatic parking planning may be caused, so that the safe driving area range expansion range calculation method based on the expansion boundary needs to be constructed on the basis of the safe driving area range.
The automatic correction of the vehicle body position is realized by calculating the deviation angle of the vehicle edge size and the parking space calibration point and converting the deviation angle into a front wheel steering angle, the controller automatically controls the steering angle of a steering wheel by acquiring the front wheel steering angle, and simultaneously, the vehicle body deviation correction path is re-planned, and the initial position point and the final position point of the vehicle are reset according to the acquired steering angle data of the steering wheel, so that the regulation of the vehicle parking standard is realized.
Claims (10)
1. A dynamic path planning method of an automatic parking system in a complex environment is characterized by comprising the following specific processes: s1, establishing an automatic vehicle parking path under a static environment map; s2, combining the automatic parking path with the vehicle kinematics model to define a safe driving area range in the vehicle parking process; s3, in the process of following the parking path of the vehicle, establishing local dynamic environment monitoring under a static environment map; s4, in the running process of the vehicle, when dynamic obstacles appear in the range of a safe running area, re-planning by establishing an automatic parking path; the obstacle avoidance and parking adjustment device is used for avoiding obstacles and adjusting parking in the parking process.
2. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 1, wherein the static environment map is used for data acquisition and environment construction in a multi-sensor fusion-based mode; the multi-sensor comprises a solid laser radar and a vehicle-mounted combined inertial navigation system.
3. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 2, wherein the solid-state laser radar establishes a laser point cloud map based on a parking space, real-time position calibration of a vehicle body is performed on the laser point cloud map based on the laser point cloud map by collecting control information in a vehicle controller, and the correction of calibration errors is performed by the real-time position calibration in combination with vehicle-mounted combined inertial navigation.
4. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 2, wherein a rasterized environment map is created in the static environment map, and automatic parking path points are created on the rasterized environment map.
5. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 1, wherein the range of the safe driving area is firstly based on a vehicle edge size constructed by a vehicle dynamic model, and an initial driving area is constructed by taking an automatic parking path of a vehicle as a direction.
6. The method for planning the dynamic path of the automatic parking system under the complex environment according to claim 5, wherein an expansion boundary based on a safe driving area is established on the initial driving area.
7. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 1, wherein the automatic parking path is re-planned, and when a dynamic obstacle is detected in the safe driving area range in the driving process of the vehicle, a polynomial-based local path planning algorithm is established, and a parking early warning signal is provided.
8. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 7, wherein the polynomial local path planning algorithm is used for establishing a constraint parameter based on a dynamic obstacle, generating an obstacle avoidance curve taking the dynamic obstacle as a circle center in a grid environment map, and establishing a re-planned path from a current point to a termination point of a vehicle.
9. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 1, wherein a vehicle parking specification constraint is established in the dynamic path planning method, and the degree of vehicle warehousing specification is automatically evaluated by judging whether the edge size of the vehicle coincides with the parking space calibration point or not in the parking specification constraint.
10. The method for planning the dynamic path of the automatic parking system in the complex environment according to claim 9, wherein in the vehicle parking regulation constraint, when the vehicle entering regulation degree exceeds a specified value, the vehicle body deviation correction path is re-planned according to the deviation angle between the edge size of the vehicle and the parking space calibration point, so as to automatically correct the position of the vehicle body.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211248482.3A CN115562281A (en) | 2022-10-12 | 2022-10-12 | Dynamic path planning method for automatic parking system in complex environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211248482.3A CN115562281A (en) | 2022-10-12 | 2022-10-12 | Dynamic path planning method for automatic parking system in complex environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115562281A true CN115562281A (en) | 2023-01-03 |
Family
ID=84744966
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211248482.3A Pending CN115562281A (en) | 2022-10-12 | 2022-10-12 | Dynamic path planning method for automatic parking system in complex environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115562281A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115973196A (en) * | 2023-03-16 | 2023-04-18 | 中国科学院大学 | Special-shaped ring anti-collision method, device and system for unmanned vehicle |
CN116533993A (en) * | 2023-07-07 | 2023-08-04 | 广汽埃安新能源汽车股份有限公司 | Parking control method and device |
-
2022
- 2022-10-12 CN CN202211248482.3A patent/CN115562281A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115973196A (en) * | 2023-03-16 | 2023-04-18 | 中国科学院大学 | Special-shaped ring anti-collision method, device and system for unmanned vehicle |
CN116533993A (en) * | 2023-07-07 | 2023-08-04 | 广汽埃安新能源汽车股份有限公司 | Parking control method and device |
CN116533993B (en) * | 2023-07-07 | 2023-09-22 | 广汽埃安新能源汽车股份有限公司 | Parking control method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109649384B (en) | Parking assisting method | |
US11809194B2 (en) | Target abnormality determination device | |
US11625038B2 (en) | Autonomous driving device | |
US10444346B2 (en) | Method for migrating radar sensor limitations with video camera input for active braking for pedestrians | |
CN115562281A (en) | Dynamic path planning method for automatic parking system in complex environment | |
US9359009B2 (en) | Object detection during vehicle parking | |
CN109002041B (en) | Vehicle obstacle avoidance method | |
CN113950703B (en) | Method, device and data processing system for determining whether external parameter matrix is accurate | |
CN111806433B (en) | Obstacle avoidance method, device and equipment for automatically driven vehicle | |
CN108032859A (en) | It is automatic to become channel control method, device and automobile | |
US11685406B2 (en) | Vehicle control device, vehicle control method, and storage medium | |
US20240043034A1 (en) | Method and system for conditional operation of an autonomous agent | |
CN110320531A (en) | Obstacle recognition method, map creating method and device based on laser radar | |
CN111775934A (en) | Intelligent driving obstacle avoidance system of automobile | |
US11836993B2 (en) | Method for controlling vehicle, vehicle control device, and storage medium | |
US11628862B2 (en) | Vehicle control device, vehicle control method, and storage medium | |
CN114384919B (en) | Vehicle obstacle avoidance path planning method and system based on large obstacle form information | |
CN112590777A (en) | Intelligent parking system based on computer control | |
CN116279458A (en) | System and method for adjusting LKAS system based on psychological characteristics during night overtaking | |
CN115991209A (en) | Unmanned control system of new energy automobile | |
CN116461553A (en) | Track control method, automatic driving vehicle, related device and medium | |
CN118302804A (en) | Parking assistance method and parking assistance device | |
CN115701400A (en) | Unmanned frame vehicle system | |
CN118394082A (en) | Automatic driving method based on laser point cloud technology | |
CN116176580A (en) | Automatic car following method and system with image and laser radar integrated |
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 |