CN114003026A - Improved lane change mechanism based on Apollo framework - Google Patents
Improved lane change mechanism based on Apollo framework Download PDFInfo
- Publication number
- CN114003026A CN114003026A CN202110691404.XA CN202110691404A CN114003026A CN 114003026 A CN114003026 A CN 114003026A CN 202110691404 A CN202110691404 A CN 202110691404A CN 114003026 A CN114003026 A CN 114003026A
- Authority
- CN
- China
- Prior art keywords
- lane
- apollo
- framework
- planning
- module
- 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
- 230000008859 change Effects 0.000 title claims abstract description 43
- 230000007246 mechanism Effects 0.000 title claims abstract description 25
- 230000008447 perception Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 2
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003068 static effect Effects 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Abstract
The invention discloses an Apollo framework-based improved lane change mechanism, which comprises the following components in percentage by weight: planning a global path by combining high-precision map information; 2: expanding redundant lane change information in a road to a global path of a routing module; 3: determining whether lane changing is needed and the lane changing direction by combining high-precision map information, perception obstacle information and decision information; 4: and generating a reference line on the road in the corresponding lane changing direction and planning a lane changing track. According to the invention, the routing module and the planning module in the Apollo frame are expanded and optimized, so that the Apollo frame is added with an active lane changing function, and the Apollo frame can be suitable for more variable lane changing scenes.
Description
Technical Field
The invention relates to an improved lane change mechanism based on an Apollo framework.
Background
With the rise of new energy vehicles, ADAS and the related technology of automatic driving have been developed rapidly. Centuries 2017, one of the leaders of automated driving technology, released Apollo, a software development platform that could be integrated with vehicles and hardware systems.
The lane change behavior is one of the main behaviors of the automatic driving vehicle, and is applied to various scenes (such as lane change, road merging, overtaking and the like) based on road network driving. The lane change mechanism in Apollo is mainly completed by matching routing and planning modules. Namely, the routing specifies the position of the road needing lane change in the global planning, and the planning module considers the position of the road needing lane change when generating the local planning path after receiving the global path planned by the routing, so as to plan the lane change track. However, the routing and planning system of the Apollo framework only supports the behavior of passive lane change, and cannot plan the track (such as overtaking, merging, etc.) which can be applied to the scene of active lane change. In a hundred-degree Apollo framework, only a passive lane-changing scene is supported at present, namely lane-changing behavior is limited as a result of routing, and planning can only change lanes according to a lane-changing position and a lane-changing direction specified by routing. While routing does not consider road condition or dynamic information (such as obstacle information and vehicle position information) when planning lane change information. The design and logic of routing and planning modules in the current Apollo framework are not able to support the flexible lane change requirement.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects of the prior art, the invention provides a method for expanding and optimizing the logics of a routing module and a planning module in an Apollo framework, so that the Apollo framework can meet the requirements of different lane-changing scenes.
The technical scheme is as follows: the invention provides an improved lane change mechanism based on an Apollo framework, which comprises the following steps: an improved lane change mechanism based on Apollo framework comprises the following steps
Step 1: planning a global path by combining high-precision map information;
step 2: expanding redundant lane change information in a road to a global path of a routing module;
and step 3: determining whether lane changing is needed and the lane changing direction by combining high-precision map information, perception obstacle information and decision information;
and 4, step 4: and generating a reference line on the road in the corresponding lane changing direction and planning a lane changing track.
The planning of the global path in the step 1 specifically comprises: the method for searching the global optimal path by using the A-star algorithm comprises the following steps: 1) initializing an open list (open _ set) and a close list (close _ set) and putting a starting point into the open list;
2) when each iteration starts, the nodes in the open list are sorted (the distance to the end point is optimal) and the optimal node n in the current open list is popped up;
3) whether the detector of the adjacent node m of the n is in the open list or not is judged, if not, the detector is added into the open list, and if yes, whether the overhead from the current node n to the m is minimum or not is checked, and the optimal father node of the m is updated;
4) and continuously iterating the steps 2 and 3 until the track reaching the terminal point is searched.
In the A-algorithm, an open list open _ set and a closed list close _ set are containers applied by the A-algorithm; n is the node currently being searched in the searching process, and m is the adjacent node of the current node n.
The step 2 of adding the redundant information of the variable lanes to the global path specifically includes: the unexpanded routing module adds the road information which is lane-changeable and is not added to the global path.
The step 1 and the step 2 are specifically as follows:
1) searching by using an A-algorithm to obtain a global path;
2) finding all road sections which can change roads and are not added with the global path by combining the high-precision map information;
3) adding the road section in the step 2) into a global path, and adding a correct lane changing direction to guide vehicles entering redundant roads to change lanes to the original global path.
And step 3, after the planning module obtains the expanded global path, determining the final lane changing direction according to the input instruction of the decision module and the input of the sensing module. If the vehicle can safely change the lane to the road of the decision instruction according to the information provided by perception, the lane is changed, otherwise, the vehicle continuously runs on the current road, and the lane is changed again when no other obstacles around the vehicle in the straight road influence the lane change.
The input instruction includes whether to change lane or change lane direction.
The sensing module inputs sensing information including front obstacles.
The step 4 specifically comprises the following steps: and generating a reference line on the road in the corresponding direction according to the lane changing direction finally determined by planning, and guiding the vehicle to perform lane changing action towards the corresponding direction by using the traction of the reference line on the vehicle.
An Apollo framework-based improved lane-change mechanism, comprising:
the Routing module is used for global path planning;
the Planning module is used for local path Planning;
the high-precision map module is used as a road changing mechanism entrance module;
the decision module is used as a parameter entering module of a lane changing mechanism.
Has the advantages that: the improved lane change mechanism based on the Apollo framework has the following advantages:
1) according to the invention, the routing module and the planning module in the Apollo frame are expanded and optimized, so that the Apollo frame is added with the function of active lane change, and the method is suitable for more variable lane change scenes;
2) the lane change track is comprehensively generated by combining decision instructions (namely lane change instructions and lane change directions) issued by a decision module, the global path of a routing module and redundant lane change information; the lane changing direction can follow the lane changing direction in the global path, and can also change lanes in any direction according to an instruction issued by the decision module; the practicability and the expandability of the existing framework are improved.
Drawings
FIG. 1 is a flow chart of a lane change mechanism based on Apollo framework improvement;
fig. 2 is a schematic diagram of lane change redundancy information.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
Example 1
An Apollo framework based improved lane-changing mechanism, comprising the steps of:
step 1: and (5) completing the search of the global optimal path by using an A-x algorithm. The a-Star algorithm is the most effective direct search method for solving the shortest path in the static road network, and is also an effective algorithm for solving a plurality of search problems. The closer the distance estimate is to the actual value in the algorithm, the faster the final search speed.
Main idea of A ×: starting from the starting point, its neighboring tiles are examined and then expanded around until the target is found. The open list (open _ set) and the closed list (close _ set) are containers used by the a-x algorithm. Wherein n is the node currently being searched in the searching process, and m is the adjacent node of the current node n. Main logic of a ×:
1) initializing an open list (open _ set) and a close list (close _ set) and putting a starting point into the open list;
2) when each iteration starts, the nodes in the open list are sorted (the distance to the end point is optimal) and the optimal node n in the current open list is popped up;
3) whether the detector of the adjacent node m of the n is in the open list or not is judged, if not, the detector is added into the open list, and if yes, whether the overhead from the current node n to the m is minimum or not is checked, and the optimal father node of the m is updated;
4) and continuously iterating the steps 2 and 3 until the track reaching the terminal point is searched.
And searching through A to obtain a global optimal path.
Step 2: redundant information of the variable lanes is added to the global path. As shown in fig. 2, for example, a circle point is a start point and a pentagram point is an end point. And the route module which is not expanded outputs lane _ 3-lane _8 as travelable areas. But lane0 ~ 2 is not added to the global path.
And the routing module after the improvement continuously adds the roads (such as lane _ 0-lane _2 in the figure) which are not added into the global path and are variable roads into the global path. The specific idea is as follows: 1) firstly, searching by using A to obtain a global path; 2) finding all road sections which can change roads and are not added with the global path by combining the high-precision map information; 3) these expandable road segments are added to the global route and the correct lane-change directions are added to direct vehicles entering the redundant roads to change the global route from which they came.
And step 3: after the extended global path is obtained by the planning module, the final lane changing direction is determined according to the input instruction (for example, whether lane changing and lane changing direction) of the decision module and the input (for example, whether an obstacle exists in front) of the sensing module.
And 4, step 4: and generating a reference line (a reference track of the vehicle) on the road in the corresponding direction according to the lane changing direction finally determined by planning, and using the traction of the vehicle by the reference line to guide the vehicle to perform lane changing action in the corresponding direction.
The main technical effect of the application is that corresponding modules are expanded in the existing Apollo framework, so that the routing and planning modules can support the active lane changing function, and the expanded framework can meet the more flexible lane changing requirement.
The principle and the implementation of the present invention are explained herein by using specific examples, and the above description of the implementation examples is only used to help understand the method and the core idea of the present invention; meanwhile, for those skilled in the art, the specific embodiments and the application range may be changed according to the idea of the present invention. In summary, this summary should not be construed to limit the present invention.
Claims (10)
1. An Apollo framework-based improved lane change mechanism, which is characterized in that: comprises the following steps
Step 1: planning a global path by combining high-precision map information;
step 2: expanding redundant lane change information in a road to a global path of a routing module;
and step 3: determining whether lane changing is needed and the lane changing direction by combining high-precision map information, perception obstacle information and decision information;
and 4, step 4: and generating a reference line on the road in the corresponding lane changing direction and planning a lane changing track.
2. The improved lane-change mechanism based on the Apollo framework of claim 1, wherein: the planning of the global path in the step 1 specifically comprises: the method for searching the global optimal path by using the A-star algorithm comprises the following steps:
1) initializing an open list (open _ set) and a close list (close _ set) and putting a starting point into the open list;
2) when each iteration starts, the nodes in the open list are sorted (the distance to the end point is optimal) and the optimal node n in the current open list is popped up;
3) whether the detector of the adjacent node m of the n is in the open list or not is judged, if not, the detector is added into the open list, and if yes, whether the overhead from the current node n to the m is minimum or not is checked, and the optimal father node of the m is updated;
4) and continuously iterating the steps 2 and 3 until the track reaching the terminal point is searched.
3. The improved lane-change mechanism based on the Apollo framework of claim 2, wherein: in the A-algorithm, an open list open _ set and a closed list close _ set are containers applied by the A-algorithm; n is the node currently being searched in the searching process, and m is the adjacent node of the current node n.
4. The improved lane-change mechanism based on the Apollo framework of claim 1, wherein: the step 2 of adding the redundant information of the variable lanes to the global path specifically includes: the unexpanded routing module adds the road information which is lane-changeable and is not added to the global path.
5. The Apollo framework based improved lane-change mechanism of claim 1 or 4, wherein: the step 1 and the step 2 are specifically as follows:
1) searching by using an A-algorithm to obtain a global path;
2) finding all road sections which can change roads and are not added with the global path by combining the high-precision map information;
3) adding the road section obtained in the step 2) into a global path, and adding a lane changing direction capable of returning to an original lane to guide vehicles entering a redundant road to change lanes to the original global path.
6. An improved lane-change mechanism based on the Apollo framework according to claim 1, characterized in that: and 3, after the planning module obtains the expanded global path, determining the final lane changing direction according to the input instruction of the decision module and the input of the sensing module.
7. The improved lane-change mechanism based on Apollo framework according to claim 6, characterized in that: the input instruction includes whether to change lane or change lane direction.
8. The improved lane-change mechanism based on Apollo framework according to claim 6, characterized in that: the sensing module inputs sensing information including front obstacles.
9. The improved lane-change mechanism based on the Apollo framework of claim 1, wherein: the step 4 specifically comprises the following steps: and generating a reference line on the road in the corresponding direction according to the lane changing direction finally determined by planning, and guiding the vehicle to perform lane changing action towards the corresponding direction by using the traction of the reference line on the vehicle.
10. The Apollo framework-based improved lane-change mechanism of claim 1, wherein: the device comprises:
the Routing module is used for global path planning;
the Planning module is used for local path Planning;
the high-precision map module is used as a road changing mechanism entrance module;
the decision module is used as a parameter entering module of a lane changing mechanism.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110691404.XA CN114003026A (en) | 2021-06-22 | 2021-06-22 | Improved lane change mechanism based on Apollo framework |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110691404.XA CN114003026A (en) | 2021-06-22 | 2021-06-22 | Improved lane change mechanism based on Apollo framework |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114003026A true CN114003026A (en) | 2022-02-01 |
Family
ID=79921031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110691404.XA Pending CN114003026A (en) | 2021-06-22 | 2021-06-22 | Improved lane change mechanism based on Apollo framework |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114003026A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111947678A (en) * | 2020-08-27 | 2020-11-17 | 重庆智行者信息科技有限公司 | Automatic driving navigation method and system for structured road |
| CN112416004A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Control method and device based on automatic driving, vehicle and related equipment |
| CN112462776A (en) * | 2020-11-30 | 2021-03-09 | 的卢技术有限公司 | Unmanned driving decision-making method based on unstructured road |
| CN112985445A (en) * | 2021-04-20 | 2021-06-18 | 速度时空信息科技股份有限公司 | Lane-level precision real-time motion planning method based on high-precision map |
-
2021
- 2021-06-22 CN CN202110691404.XA patent/CN114003026A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111947678A (en) * | 2020-08-27 | 2020-11-17 | 重庆智行者信息科技有限公司 | Automatic driving navigation method and system for structured road |
| CN112416004A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Control method and device based on automatic driving, vehicle and related equipment |
| CN112462776A (en) * | 2020-11-30 | 2021-03-09 | 的卢技术有限公司 | Unmanned driving decision-making method based on unstructured road |
| CN112985445A (en) * | 2021-04-20 | 2021-06-18 | 速度时空信息科技股份有限公司 | Lane-level precision real-time motion planning method based on high-precision map |
Non-Patent Citations (1)
| Title |
|---|
| 王方浩: "apollo介绍之Routing模块", Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/65533164> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6857371B2 (en) | Learning methods that support safe autonomous driving, and learning devices, test methods, and test devices that use them. | |
| CN111506058B (en) | Method and device for planning a short-term path for autopilot by means of information fusion | |
| CN112099496B (en) | Automatic driving training method, device, equipment and medium | |
| US11680821B2 (en) | Map information system | |
| JP2022516383A (en) | Autonomous vehicle planning | |
| CN111735639B (en) | Automatic driving scene minimum set generation method for intelligent networked automobile demonstration area | |
| CN112947406A (en) | FLOYD and Astar-based hybrid path planning method | |
| JPWO2020100408A1 (en) | Danger scene prediction device, danger scene prediction method and danger scene prediction program | |
| CN114281084A (en) | Intelligent vehicle global path planning method based on improved A-x algorithm | |
| CN116080687A (en) | Predicted track post-processing method, system, equipment and medium | |
| Boubakri et al. | High definition map update for autonomous and connected vehicles: A survey | |
| CN114003026A (en) | Improved lane change mechanism based on Apollo framework | |
| KR20170070488A (en) | Method and apparatus for automatically generating drive route | |
| US10776542B2 (en) | Method and device for calibrating physics engine of virtual world simulator to be used for learning of deep learning-based device, and a learning method and learning device for real state network used therefor | |
| CN117075613A (en) | Unmanned vehicle sensing and obstacle avoidance method, system, computer equipment and storage medium | |
| CN115014380A (en) | Parking path planning method and device, electronic device and storage medium | |
| CN113074747B (en) | Path planning method, device, equipment and storage medium | |
| CN115562356A (en) | Flight vehicle graph search path planning method, terminal device and medium | |
| US11262201B2 (en) | Location-based vehicle operation | |
| CN114281105A (en) | Unmanned aerial vehicle path planning method for substation inspection | |
| US10969231B2 (en) | Map data update system and non-transitory computer-readable storage medium | |
| US20230204368A1 (en) | System for generating autonomous driving path using harsh environment information of high definition map and method thereof | |
| Qiu | A Review of Motion Planning for Urban Autonomous Driving | |
| CN113778102B (en) | AVP global path planning system, method, vehicle and storage medium | |
| KR102128551B1 (en) | Apparatus for modeling of reconnaissance behavior and the method thereof |
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 |