CN114910088B - Method, system and storage medium for planning mixed road path - Google Patents
Method, system and storage medium for planning mixed road path Download PDFInfo
- Publication number
- CN114910088B CN114910088B CN202110175473.5A CN202110175473A CN114910088B CN 114910088 B CN114910088 B CN 114910088B CN 202110175473 A CN202110175473 A CN 202110175473A CN 114910088 B CN114910088 B CN 114910088B
- Authority
- CN
- China
- Prior art keywords
- road
- virtual
- path
- planning
- unstructured
- 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
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
Abstract
The invention discloses a method, a system and a storage medium for planning a mixed road path. The method for planning the mixed road path comprises the steps of carrying out global path planning in a preformed structured virtual road network to form a global planning path, and then carrying out local path planning on an unstructured area in the virtual road network to obtain a local planning path so as to realize the planning of the mixed road path. The invention realizes the whole path planning in the scene of the structured and unstructured mixed map by utilizing the virtual road network, so that the automatic driving vehicle can carry out the path planning according to the optimal route. By utilizing the virtual road network, the map switching process is avoided, and the global no-stop in the vehicle driving process is realized.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to a method, a system and a storage medium for planning a mixed road path.
Background
In the field of automatic driving, the road structure is divided into two types of structured roads and unstructured roads according to the difference of the road structures. The structured road refers to a highway, an urban arterial road and other roads with better structuring, and the environment has clear road mark lines and needs to follow traffic rules when running on the road. Unstructured roads refer to environments such as parks, parks and the like without obvious road structures, and the environments have no clear road sign lines and do not need to follow traffic rules when driving. In the prior art, hybrid road path planning on a structured environment and a non-structured environment is realized, and the switching is mainly based on a map. Firstly, two maps are stored in a structured and unstructured mode according to a scene. When a vehicle enters an unstructured road from a structured road, the map scene is switched by using positioning information. For a structured map scene, path planning is realized by analyzing a road topological structure; for unstructured maps, path planning is mainly implemented through graph search techniques. Both of these implementation ideas are completely not feasible, and therefore, it is necessary to switch to the corresponding path planning module according to the map type.
In the prior art, the map is cut according to the scene, so that the intersection point of the two maps can be planned firstly during planning, and the next path planning is performed after the map is switched. In addition, in the switching process, the path planning is needed again, so that the vehicle must be stopped during switching, and the whole flow is not consistent.
Disclosure of Invention
The invention aims at solving the technical defects in the prior art and provides a method, a system and a storage medium for planning a mixed road path.
The technical scheme adopted for realizing the purpose of the invention is as follows:
a method for planning a mixed road path comprises the steps of carrying out global path planning in a preformed structured virtual road network to form a global planning path, and then carrying out local path planning on an unstructured area in the virtual road network to obtain a local planning path so as to realize the planning of the mixed road path.
The structured virtual road network is formed by converting and mapping unstructured areas into virtual roads and then establishing a road network topology together with the structured roads.
The virtual road comprises at least one virtual connection road and a virtual center road, wherein the at least one virtual connection road and the virtual center road are respectively provided with a virtual road network weight, the virtual connection road corresponds to one outlet or one inlet of the unstructured area, and the virtual center road corresponds to the unstructured area.
When global path planning is performed, if the end point or the starting point of the path is in the unstructured area, a virtual center road of the unstructured area is used as the starting point or the end point.
In the unstructured region, a corresponding coordinate point is found according to the virtual connection road found in the global search, the coordinate point is used as a starting point, the end point selected by a user is used as the end point of the secondary search, and the secondary search is performed.
And for a scene passing through the unstructured region, performing secondary path searching by using a coordinate point corresponding to the virtual connection road at the entrance as a starting point and a coordinate point corresponding to the virtual connection road at the exit as an ending point.
The invention also aims at providing a system for planning the mixed road path, which is provided with a task information analysis module, wherein the task information analysis module is used for carrying out global path planning in a preformed structured virtual road network according to the starting point and the end point of an input path to form a global planning path, and then carrying out local path planning on an unstructured area in the virtual road network to obtain a local planning path so as to realize the planning of the mixed road path;
the structured virtual road network is formed by converting and mapping an unstructured area into a virtual road and then establishing a road network topology together with the structured road;
the virtual road comprises at least one virtual connection road and a virtual center road, wherein the at least one virtual connection road and the virtual center road are respectively provided with a virtual road network weight, the virtual connection road corresponds to an outlet or an inlet of the unstructured region, and the virtual center road corresponds to the unstructured region.
It is also an object of the present invention to provide a computer readable storage medium storing a computer program configured to implement the steps of the method of hybrid road path planning when called by a processor.
The invention realizes the whole path planning in the scene of the structured and unstructured mixed map by utilizing the virtual road network, so that the automatic driving vehicle can carry out the path planning according to the optimal route. By utilizing the virtual road network, the map switching process is avoided, and the global no-stop in the vehicle driving process is realized.
Drawings
FIG. 1 is a flow chart of a method of hybrid road path planning of the present invention;
FIG. 2 is a schematic diagram of an unstructured region virtualized into a virtual road network node;
FIG. 3 is a schematic diagram of an unstructured region mapped to a virtual road;
FIG. 4 is a schematic illustration of structured zone to unstructured zone or unstructured zone to structured zone path planning;
FIG. 5 is a schematic diagram of a path plan through an unstructured region with both a start point and an end point in the structured region;
FIG. 6 is a schematic diagram of a path layout with start and end points in unstructured regions.
Detailed Description
The invention is described in further detail below with reference to the drawings and the specific examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Global path planning refers to the step of receiving a task instruction to plan a global path from a current position to an end point based on a high-precision map.
As shown in fig. 1-3, the method for planning a hybrid road path of the present invention performs global search in a preformed structured virtual road network, performs global path planning to form a global planned path, and then performs local path planning on an unstructured area in the virtual road network to obtain a local planned path, so as to realize the planning of the hybrid road path:
wherein the structured virtual road network is formed by the following steps:
converting the unstructured region into a plurality of virtual roads, setting corresponding virtual road network weights, and establishing road network topology together with the structured roads, so that the structured virtual road network is formed; after the structured virtual road network is formed, when the road planning is carried out, after the global path planning of the structured virtual map or the road network is carried out, the local path planning of the unstructured map is sequentially carried out aiming at the unstructured area, so that the decoupling and the matching of the two algorithms are realized.
Preferably, the optimal path is searched in the unstructured area by using a graph searching mode, so that local path planning or quadratic programming is realized.
In the general structured road network structure, an unstructured region is virtualized into a virtual road network node. The road network weight matrix stores the shortest distance between any two roads in the road network, and inspires a subsequent search algorithm. The length, type and topology information of all roads in the road network are needed for establishing the weight matrix. The global path searching process also includes two steps, the first step is to find the optimal path in the virtual road network, and the second step is to find the local optimal path in the corresponding unstructured region. The two are combined to form a global path. For such road network mapping, however, as shown in fig. 2, the unstructured regions typically have more than one entrance and exit with the structured regions. In order to obtain an optimal path, each gateway must establish a virtual connection road. For an unstructured area with N entrances, M exits, (NxM) virtual roads need to be created. This causes the road network to be very loaded, and the optimal path search speed is slow. When the virtual road actually enters the unstructured area, the virtual road is replaced by the secondary path planning of the unstructured area.
In order to solve the problem of the very load of the road network, the invention introduces a concept of a central road, and maps an unstructured area into two virtual roads, namely a connecting road and a central road. Each connecting channel corresponds to an outlet or inlet, and the central channel corresponds to an unstructured region. Thus, the road connection relationship is optimized to (m+n).
Because the unstructured region is mapped into two types of connecting roads (roads) and central roads (roads), the virtual road network weight can be set for each road. The weight of the connecting channel (road) represents the weight of each entry, and the weight of the central channel (road) represents the weight of the entire unstructured region.
The following functions can be realized through the virtual road network weight:
firstly, avoid unstructured area as much as possible: if the central road weight is reduced, the unstructured region can be avoided when the global path is searched, and the traffic can be realized by means of the unstructured region when no other selection exists.
Secondly, selecting an optimal entrance and exit route: because each gateway has a corresponding road weight, for example, by adjusting the road weight, a more appropriate entrance route can be selected as much as possible during global path planning.
In order that the global path planning algorithm can find the path topological relation from the structured area to the unstructured area, the connection relation between the unstructured area and the structured area is perfected, and a virtual lane is arranged between the structured area and the unstructured area, as shown in fig. 3.
Generally, the following three typical application scenarios in the hybrid path planning are:
one structured region to unstructured region or unstructured region to structured region, referring to fig. 4, and the other one with start point and end point both in structured region but penetrating unstructured region, referring to fig. 5, and the other with start point and end point both in unstructured region but penetrating structured region, referring to fig. 6.
It is not concerned about the distinction of these three scenes for the user, and only the positions of the start point and the end point are input. The task information analysis module of the path planning is responsible for decomposing a path planning task into tasks of the path planning task which can be executed practically.
In path planning, the invention finds the corresponding structured road network node according to the input starting point. For an end point or origin point in an unstructured region, then its corresponding virtual center road is used as the origin point or end point, as shown in fig. 6.
After the global path planning is completed, whether the nodes passing through the whole path have virtual roads or not is analyzed. If the virtual road exists, searching an optimal path in an unstructured area corresponding to the virtual road in a graph searching mode, and realizing local path planning or quadratic programming.
For the path planning of structured roads to unstructured roads shown in fig. 4. In the unstructured region, a corresponding coordinate point is found according to the virtual connecting channel (road) found in the global search and is used as a starting point, and the end point selected by a user in the unstructured region is used as the end point of the secondary search to conduct the secondary search.
For the scenario shown in fig. 5, in which the starting point and the ending point are both on the structured road and the unstructured road is traversed, the task information analysis module does not perform two searches of the virtual connection road from the entrance to the center road and the virtual connection road from the center road to the exit, but directly performs the secondary path search by using the coordinate point corresponding to the virtual connection road of the entrance as the starting point and the coordinate point corresponding to the virtual connection road of the exit as the ending point.
The invention realizes the whole path planning in the scene of the structured and unstructured mixed map by utilizing the virtual road network, so that the automatic driving vehicle can carry out the path planning according to the optimal route. The invention avoids the map switching process and realizes global no stop in the running process of the vehicle.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (8)
1. The method for planning the mixed road path is characterized in that global path planning is carried out in a preformed structured virtual road network to form a global planning path, and then local path planning is carried out on an unstructured area in the virtual road network to obtain a local planning path so as to realize the planning of the mixed road path;
the structured virtual road network is formed by converting and mapping an unstructured area into a virtual road and then establishing a road network topology together with the structured road;
the virtual road comprises at least one virtual connection road and a virtual center road, wherein the at least one virtual connection road and the virtual center road are respectively provided with a virtual road network weight, the virtual connection road corresponds to an outlet or an inlet of the unstructured region, and the virtual center road corresponds to the unstructured region.
2. The method of claim 1, wherein when global route planning is performed, if the end point or the start point of the route is in the unstructured region, a virtual center road of the unstructured region is used as the start point or the end point.
3. The method of hybrid road path planning according to claim 1, wherein in the unstructured region, a corresponding coordinate point is found according to the virtual link found in the global search, as a start point, and an end point selected by the user is used as an end point of the secondary search, and the secondary search is performed.
4. The method of claim 1, wherein the secondary route search is performed using a coordinate point corresponding to the virtual connection road of the entrance as a start point and a coordinate point corresponding to the virtual connection road of the exit as an end point for a scene passing through the unstructured region.
5. The system for planning the mixed road path is characterized by being provided with a task information analysis module, wherein the task information analysis module is used for carrying out global path planning in a preformed structured virtual road network according to the starting point and the end point of an input path to form a global planning path, and then carrying out local path planning on an unstructured area in the virtual road network to obtain a local planning path so as to realize the planning of the mixed road path;
the structured virtual road network is formed by converting and mapping an unstructured area into a virtual road and then establishing a road network topology together with the structured road;
the virtual road comprises at least one virtual connection road and a virtual center road, wherein the at least one virtual connection road and the virtual center road are respectively provided with a virtual road network weight, the virtual connection road corresponds to an outlet or an inlet of the unstructured region, and the virtual center road corresponds to the unstructured region.
6. The system of claim 5, wherein when performing global path planning, if the end point or start point of the path is in an unstructured region, a virtual center road of the unstructured region is used as the start point or end point.
7. The system for hybrid road path planning according to claim 5, wherein in the unstructured region, a corresponding coordinate point is found according to the virtual connection road found in the global search, and the end point selected by the user is used as the end point of the secondary search, and the secondary search is performed;
and for a scene passing through the unstructured region, performing secondary path searching by using a coordinate point corresponding to the virtual connection road at the entrance as a starting point and a coordinate point corresponding to the virtual connection road at the exit as an ending point.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program configured to implement the steps of the method of hybrid road path planning of any one of claims 1-4 when called by a processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110175473.5A CN114910088B (en) | 2021-02-09 | 2021-02-09 | Method, system and storage medium for planning mixed road path |
| PCT/CN2022/075682 WO2022171130A1 (en) | 2021-02-09 | 2022-02-09 | Hybrid road path planning method and system, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110175473.5A CN114910088B (en) | 2021-02-09 | 2021-02-09 | Method, system and storage medium for planning mixed road path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114910088A CN114910088A (en) | 2022-08-16 |
| CN114910088B true CN114910088B (en) | 2023-06-16 |
Family
ID=82761137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110175473.5A Active CN114910088B (en) | 2021-02-09 | 2021-02-09 | Method, system and storage medium for planning mixed road path |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114910088B (en) |
| WO (1) | WO2022171130A1 (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110081894A (en) * | 2019-04-25 | 2019-08-02 | 同济大学 | A kind of real-time planing method of unmanned wheel paths based on the fusion of road structure weight |
| CN111426330A (en) * | 2020-03-24 | 2020-07-17 | 江苏徐工工程机械研究院有限公司 | Path generation method and device, unmanned transportation system and storage medium |
| CN112270306A (en) * | 2020-11-17 | 2021-01-26 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned vehicle track prediction and navigation method based on topological road network |
-
2021
- 2021-02-09 CN CN202110175473.5A patent/CN114910088B/en active Active
-
2022
- 2022-02-09 WO PCT/CN2022/075682 patent/WO2022171130A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110081894A (en) * | 2019-04-25 | 2019-08-02 | 同济大学 | A kind of real-time planing method of unmanned wheel paths based on the fusion of road structure weight |
| CN111426330A (en) * | 2020-03-24 | 2020-07-17 | 江苏徐工工程机械研究院有限公司 | Path generation method and device, unmanned transportation system and storage medium |
| CN112270306A (en) * | 2020-11-17 | 2021-01-26 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned vehicle track prediction and navigation method based on topological road network |
Non-Patent Citations (4)
| Title |
|---|
| Dynamic motion planning for autonomous vehicle in unknown environments;P. Zhao 等;《2011 IEEE Intelligent Vehicles Symposium (IV)》;20110609;第284-289页 * |
| 一种混合路径规划方法在装甲车辆CGF中的应用;邓青等;《兵器装备工程学报》;20180725;第39卷(第07期);第120-122页 * |
| 基于A算法和人工势场法的移动机器人路径规划;王洪斌 等;《中国机械工程》;20190909;第30卷(第20期);第2489-2495页 * |
| 基于路网的车辆路径规划融合算法研究;胡习之 等;《机床与液压》;20201215;第48卷(第23期);第13-18页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114910088A (en) | 2022-08-16 |
| WO2022171130A1 (en) | 2022-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111947678B (en) | Automatic driving navigation method and system for structured road | |
| Larson et al. | Coordinated route optimization for heavy-duty vehicle platoons | |
| US8000891B2 (en) | Data formats and usage for massive point to point route calculation | |
| CN110515380B (en) | Shortest path planning method based on turning weight constraint | |
| Armant et al. | Minimizing the driving distance in ride sharing systems | |
| CN103149576A (en) | Map matching method of floating car data | |
| CN115560771A (en) | Sampling-based path planning method and device and automatic driving equipment | |
| US11415984B2 (en) | Autonomous driving control device and method | |
| CN113295177B (en) | Dynamic path planning method and system based on real-time road condition information | |
| CN114910088B (en) | Method, system and storage medium for planning mixed road path | |
| CN105698796A (en) | Route search method of multi-robot scheduling system | |
| Falek et al. | Muse: Multimodal separators for efficient route planning in transportation networks | |
| CN114074695A (en) | Train route handling method, device, equipment and storage medium | |
| CN116226309A (en) | Map data processing method and device, electronic equipment and storage medium | |
| CN113670308B (en) | Method for guiding vehicle to run and related system and storage medium | |
| CN112699202B (en) | Forbidden road identification method and device, electronic equipment and storage medium | |
| JP2020026987A (en) | Traffic light acquisition system, correspondence generating system, and traffic light acquisition program | |
| CN114859931A (en) | Multi-vehicle path planning method, device, equipment, storage medium and system | |
| CN114964293A (en) | Vehicle path planning method and device, electronic equipment and storage medium | |
| CN112212877A (en) | Internet of things unmanned vehicle and navigation path calculation method and device | |
| CN113865591A (en) | Method, device, equipment and medium for navigation by combining with self-owned route data of factory | |
| Carroll et al. | Work In Progress: A Solution Based on Dynamic User Equilibrium Toward the Selfless Traffic Routing Model | |
| Kim et al. | Finding realistic shortest path in road networks with lane changing and turn restriction | |
| CN115493609B (en) | Lane-level path information generation method, device, equipment, medium and program product | |
| Malowidzki et al. | Traffic Routes for Emergency Services |
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 |