CN113432616A - Map making and/or processing method, map storage device and path planning method - Google Patents
Map making and/or processing method, map storage device and path planning method Download PDFInfo
- Publication number
- CN113432616A CN113432616A CN202110710631.2A CN202110710631A CN113432616A CN 113432616 A CN113432616 A CN 113432616A CN 202110710631 A CN202110710631 A CN 202110710631A CN 113432616 A CN113432616 A CN 113432616A
- Authority
- CN
- China
- Prior art keywords
- planning
- elements
- road
- vehicle
- traffic
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003672 processing method Methods 0.000 title description 10
- 230000003068 static effect Effects 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 32
- 238000012360 testing method Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- 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
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
提出一种用于车辆的地图的制作和/或加工方法，包括：提供并存储静态道路元素；选取规划辅助元素，并存储规划辅助元素或用于指向规划辅助元素的信息，规划辅助元素表示从静态道路元素或其子元素中选取的与车辆的通行安全性相关联的元素；提供数据接口，经由其能够直接读取规划辅助元素。提出一种地图存储装置，包括：静态道路元素存储单元(1)、存储规划辅助元素或用于指向规划辅助元素的信息的规划辅助元素存储单元(2)及用于经由数据接口读取数据的接口单元(3)。还提出一种地图的使用方法及一种为自动驾驶车辆进行路径规划的路径规划方法。通过直接读取标记有相关的通行安全性的规划辅助元素，可提升自动驾驶安全性，减少规划的计算量。
A method for making and/or processing a map for a vehicle is proposed, including: providing and storing static road elements; selecting a planning aid element, and storing the planning aid element or information for pointing to the planning aid element, wherein the planning aid element represents a An element selected from the static road element or its sub-elements that is associated with the safety of the vehicle's passage; provides a data interface via which the planning aid element can be directly read. A map storage device is proposed, comprising: a static road element storage unit (1), a planning assistance element storage unit (2) for storing planning assistance elements or information for pointing to the planning assistance elements, and a storage unit (2) for reading data via a data interface Interface unit (3). A method for using a map and a path planning method for path planning for an autonomous vehicle are also proposed. By directly reading planning aids that are marked with the relevant traffic safety, the safety of autonomous driving can be improved and the computational load of planning can be reduced.
Description
Technical Field
The invention relates to the field of high-precision maps and the field of automatic driving, in particular to a method for manufacturing and/or processing a vehicle map, a method for using the map, a map storage device and a path planning method for planning paths of automatic driving vehicles. "automatic driving" as referred to herein includes automatic driving and/or driving assistance at a level of L1 or higher.
Background
With the high-precision map, the automatic vehicle can realize high-precision positioning, judgment of a travelable area, lane to be traveled and acquisition of road properties (such as gradient, curvature and the like) ahead. The high-precision map can provide full link assistance of perception, positioning, decision, path planning and control for the automatic driving system, and the robustness of the system is improved.
In recent years, the automatic driving technology has been rapidly developed along with high-precision maps. The function module of automatic driving comprises: positioning, sensing, fusing, predicting, decision planning and the like. The typical decision planning module can be divided into three levels: global path planning, behavioral decision making, and motion planning. Global path planning refers to the search and selection of a road-level path given the current position and destination of a vehicle, and vehicles can easily realize global path planning thanks to the topological structure of a (high-precision) map.
High-precision maps serving autonomous or high-level driving assistance systems have lane-level information stored therein, including, but not limited to, lane characteristics, types of vehicles permitted to pass, transit time limits, and the like. The automatic driving in the future can be automatically driven to land on the ground based on a high-precision map, a path rapid planning algorithm, rapid map display and storage are adopted, and vehicle-mounted intelligent driving equipment is combined, so that safe and reliable driving experience is finally brought.
However, the current automatic driving technology and high-precision maps still need to be further developed.
For example, the real-time matching between the actual lane state and the map labeling state, the uncertainty of whether the response to the dangerous scene in the complex urban road scene can ensure the safety of vehicles and pedestrians, and the contradiction processing and decision of the lane change requirement and the safe lane change condition under the short-distance condition.
In particular, any system development is based on the definition of requirements and functions, and its validation is mostly based on scenario testing. It is difficult for the defined scene to fully cover the complex combination of variables that may occur in reality. Therefore, even if the vehicle has the capability of identifying the lane state in real time, if the lane has complexity due to its own attributes, such as a variable guide lane, a tidal lane, etc., the vehicle may have unusual scenes such as temporary traffic control, congestion, and adverse road user retrograde movement during its driving, and it is difficult to ensure that the system makes safe and timely decisions.
For example, in the case of road environments such as a three-dimensional intersection, since the high-precision map for autonomous driving in china does not allow the expression of height information, the influence on the driving plan and decision of the vehicle is yet to be verified.
Therefore, in the face of customer's desire for vehicle safety, the fitting manner relying only on the conventional high-precision map is still insufficient.
Disclosure of Invention
The invention aims to provide an improved map making and/or processing method for a vehicle, a map using method, a map storage device and a route planning method.
According to a first aspect of the present invention, a method for producing and/or processing a map for a vehicle is provided, wherein the production and/or processing method comprises the following steps: providing and storing static road elements; selecting a planning auxiliary element and storing the planning auxiliary element or information for pointing to the planning auxiliary element, wherein the planning auxiliary element represents an element selected from a static road element or a sub-element of the static road element and associated with the traffic safety of the vehicle; and providing a data interface via which the planning assistance elements can be read directly.
Optionally, the particular driving assistance function of the planning assistance element for a particular vehicle is selected and marked in dependence on the vehicle passage safety.
Optionally, the planning assistance element comprises the following road segments: aiming at the traffic light identification function of a front camera of a vehicle, a road section which does not meet the safety condition of the traffic light identification function of the front camera is screened out based on stop line information and/or road orientation information and/or a traffic light installation position provided by static road elements, wherein a planning auxiliary element corresponding to the road section is marked as insecurity aiming at the traffic light identification function of the front camera.
Optionally, the planning assistance element comprises a limitation required to turn on the associated driving assistance function.
Optionally, the planning assistance element comprises at least one of the following road information: tidal lanes, variable-guidance lanes, autodrive lanes, left-turn waiting areas, bus lanes, non-hybrid lanes, level crossings, other lanes not suitable for a particular driving assistance function of a vehicle.
Optionally, the planning assistance element is classified according to the availability of a specific driving assistance function for the vehicle as: "no pass element", "dangerous pass element", "cautious pass element".
Optionally, the data interface is arranged such that the planning assistance element can be directly overwritten via said data interface.
Optionally, the mapping and/or processing method further comprises providing and storing at least one of the following information: dynamic road environment elements, dynamic surrounding vehicle information, dynamic weather and road condition information and real-time communication information.
Optionally, the static road element comprises a static road environment element and/or a road connection relation.
According to a second aspect of the present invention, there is provided a method of using a map produced and/or processed by the method of producing and/or processing a map of the present invention, wherein the method of using comprises: the planning assistance elements are read directly via a data interface.
According to a third aspect of the present invention, there is provided a map storage device for storing a map produced and/or processed by the map producing and/or processing method according to the present invention, wherein the map storage device comprises: a static road element storage unit for storing static road elements, a planning assistance element storage unit for storing planning assistance elements or information for pointing to planning assistance elements, and an interface unit for reading data via a data interface.
According to a fourth aspect of the present invention, there is provided a path planning method for planning a path for an autonomous vehicle using a map storage device according to the present invention, wherein the path planning method comprises:
step S1, acquiring destination information;
step S2, reading planning assistance elements directly from the map via a data interface; and
and step S3, carrying out global path planning based on the planning auxiliary elements.
Optionally, step S3 includes:
a substep S31 of performing global path planning while avoiding a link including a "no-pass element" according to the destination information;
a substep S32, if the global path planning in the substep S31 fails, prompting the path generation failure and temporarily not starting the automatic driving; and
in sub-step S33, if the global path planning in sub-step S31 is successful, it is verified whether the generated global path passes through a road segment containing a "dangerous traffic element" and a "cautious traffic element".
Optionally, the sub-step S33 further includes:
substep S331: if the generated global path contains the road sections of the dangerous traffic elements, the road sections containing the dangerous traffic elements are avoided and the global path planning is carried out again, wherein,
S331A: if the complete path is successfully generated under the condition of avoiding the 'no-pass element' and the 'dangerous pass element', path planning is finished, and the vehicle starts normal automatic driving; and
S331B: if the complete path is failed to be generated under the condition of avoiding the traffic prohibition elements and the dangerous traffic elements, displaying road sections containing the traffic prohibition elements or the dangerous traffic elements, and starting prudent automatic driving of the vehicle, wherein the road sections containing the traffic prohibition elements or the dangerous traffic elements optionally indicate that the requirement of manual takeover exists;
substep S332: if the generated global path does not contain the road section of the dangerous traffic element but contains the cautious traffic element, path planning is completed, and the vehicle starts cautious automatic driving on the road section containing the cautious traffic element; and
substep S333: and if the generated global path does not contain the road sections of the dangerous traffic elements and does not contain the road sections of the cautious traffic elements, finishing path planning and starting normal automatic driving of the vehicle.
The invention has the positive effects that: by directly reading the planning auxiliary element layer in the map, which is associated with the traffic safety of the vehicle, the automatic driving safety can be improved, and the calculation amount of path planning is reduced.
Drawings
The principles, features and advantages of the present invention may be better understood by describing the invention in more detail below with reference to the accompanying drawings. The drawings comprise:
FIG. 1 schematically illustrates a map storage device according to an exemplary embodiment of the present invention;
fig. 2 schematically shows a hierarchical structure of a map stored by a map storage apparatus according to an exemplary embodiment of the present invention;
FIG. 3 schematically illustrates a process of screening planning assistance elements according to an exemplary embodiment of the present invention;
FIG. 4 schematically illustrates a traffic light identification function screening planning assistance element for a front camera of a vehicle;
FIG. 5 schematically illustrates a process of screening planning assistance elements in conjunction with actual tests according to an exemplary embodiment of the present invention;
FIG. 6 schematically illustrates a method of path planning for an autonomous vehicle in accordance with an exemplary embodiment of the invention; and
fig. 7 schematically shows another path planning method.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and exemplary embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
Fig. 1 schematically shows a map storage apparatus according to an exemplary embodiment of the present invention. The map storage device is used for storing the map which is manufactured and/or processed by the manufacturing and/or processing method of the map for the vehicle. The map according to the embodiment of the present invention may be, for example, a high-precision map. The map making and/or processing method comprises the following steps: providing and storing static road elements; selecting a planning auxiliary element and storing the planning auxiliary element or information for pointing to the planning auxiliary element, wherein the planning auxiliary element represents an element selected from a static road element or a sub-element of the static road element and associated with the traffic safety of the vehicle; and providing a data interface via which the planning assistance elements can be read directly. It is to be understood that "directly reading the planning assistance element" especially means that the planning assistance element is read without retrieving the static road element. The static road elements may include, for example, static road environment elements and road connection relationships. The sub-elements of the static road element may for example represent lanes within the static road.
As shown in fig. 1, the map storage device accordingly includes: a static road element storage unit 1 for storing static road elements, a planning assistance element storage unit 2 for storing information for pointing to planning assistance elements, and an interface unit 3 for reading data via a data interface. The planning assistance element storage unit 2 may also be arranged for storing planning assistance elements, in which case the planning assistance elements stored in the planning assistance element storage unit 2 are associated with corresponding static road elements. As a result, the static road elements and the planning aid elements can be read directly in a suitable manner via the interface unit 3. For example, associating static road elements with planning assistance elements may be achieved by pairing the identification numbers of the static road elements with the identification numbers of the planning assistance elements.
According to the invention, the driving safety can be improved through the planning auxiliary element associated with the traffic safety of the vehicle. According to the invention, the static road elements and the planning auxiliary elements can be directly and synchronously read in a matching manner through the data interface, and the planning auxiliary elements do not need to be read by searching the road elements layer by layer, so that the calculation amount can be reduced. For example, when planning a route based on a map, the amount of calculation can be reduced and the planning speed can be increased.
In addition, different car factories have different requirements on the specification of the high-precision map, and the specification and calling mode of the map planning auxiliary elements described by the invention can assist the car factories or operation units to selectively screen and avoid unsafe elements.
In addition, different requirements of the management organization on the running and operating areas of vehicles with different qualifications and/or capabilities can be met, and the specification of the map planning auxiliary element and the calling mode thereof described by the invention are beneficial to the supervision and control of the vehicles. Conversely, the processing capacity of the system can be gradually improved and the function can be started in the corresponding area by simplifying the system depth on the premise of not influencing the long-term system design.
Furthermore, the authorities may have special regulations for certain road segments during special periods, for example not allowing vehicles with automatic driving and/or driving assistance functions (vehicles with automatic driving and/or driving assistance functions often have sensors that can collect information) to enter, or for example not allowing high-level automatic driving and/or driving assistance functions to be turned on in certain areas.
Optionally, the data interface is arranged such that the planning assistance element can be directly overwritten via said data interface. This facilitates, in particular, the modification of the properties of the planning aid elements, in particular the modification can be carried out in a targeted manner or in batches for specific categories.
Optionally, the mapping and/or processing method further comprises providing and storing at least one of the following information: dynamic road environment elements, dynamic surrounding vehicle information, dynamic weather and road condition information and real-time communication information. Fig. 2 schematically shows a hierarchical structure of a map stored by a map storage apparatus according to an exemplary embodiment of the present invention. The map may in particular be a high-precision map.
As shown in fig. 2, the stored map has a plurality of data layers, including, for example, a road connection (topology) relationship layer, a planning assistance element layer, a static road environment element layer, a dynamic surrounding vehicle information layer, a dynamic weather and road condition information layer, and a real-time communication information layer.
Each data layer may be stored in a corresponding storage unit. Accordingly, the map storage comprises at least one, in particular all, of the following storage units: the system comprises a road connection relation storage unit for storing a road connection relation, a static road environment element storage unit for storing static road environment elements, a planning auxiliary element storage unit for storing planning auxiliary elements, a dynamic road environment element storage unit for storing dynamic road environment elements, a dynamic surrounding vehicle information storage unit for storing dynamic surrounding vehicle information, a dynamic weather information storage unit for storing dynamic weather information and a real-time communication information storage unit for storing real-time communication information. It should be understood that the storage unit in the present invention may be a separate storage device, and may also represent a storage space in which corresponding data is stored in the storage device.
According to the method and the device, elements which may affect the automatic driving passing safety are selected from map layers such as static road environment elements and marked as planning auxiliary elements, the planning auxiliary elements can be stored as independent planning auxiliary element layers, and information used for pointing to the planning auxiliary elements can also be stored in the planning auxiliary element layers. It should be understood that the planning assistance elements are selected from other map layers such as static road environment element layers, but do not affect the expression of elements or attributes of the original map layers.
After the vehicle obtains the initial position and the target position, the path planning (global path planning) is realized by reading the connection (topological) relation of the bottom layer road in the high-precision map. And then reading static and dynamic road environment elements on the road where the vehicle is located, sensing, recognizing and processing the track information of the surrounding vehicles and other dynamic information, and realizing obstacle avoidance planning.
Within a certain defined range of the vehicle travel section, it is not necessary to read all the information stored in the high-precision map. One reason for this is that a large amount of data loading and processing requires the consumption of significant memory and processing power, CPU resources and memory space. The second reason is that the immediate decision making of the vehicle is not greatly facilitated by the early loading of dynamic information.
The files of the high-precision map for supporting automatic driving are far larger than those of a navigation electronic map, and the vehicle stores static road environment elements and is loaded at one time, so that the storage capacity is easily wasted and the system is blocked. Compared with the off-line storage of all high-precision maps in the vehicle, the vehicle has a more promising prospect of storing the road topological relation and downloading other information in a certain range around the vehicle from the cloud.
Therefore, the map storage apparatus according to the present invention may be a single storage apparatus, or may be a system composed of a plurality of storage devices that implement distributed storage.
Optionally, the planning assistance element is selected and marked for a specific driving assistance function of the vehicle in dependence on the vehicle passage safety. For example, tests, data analysis and verification may be performed for specific driving assistance functions, and if the driving assistance functions do not perform satisfactorily on certain road segments, these road segments may be screened out as planning assistance elements. These road segments may be marked in particular as planning assistance elements associated with the driving assistance function.
Fig. 3 schematically shows a process of screening planning assistance elements according to an exemplary embodiment of the present invention.
Based on the information provided by maps, in particular high-precision maps, the function and field of view of on-board sensors, for example front-facing cameras, it is possible to theoretically derive infrastructure locations or scenes that do not meet the safety design.
In this embodiment, the planning assistance elements are filtered for the traffic light recognition function of the front camera of the vehicle. For example, a vehicle may be equipped with 2 front cameras with a field angle of 120 ° and 1 front camera with a field angle of 60 °, which take over the function of identifying traffic lights.
And simulating and/or comparing the information such as the stop line, the road direction, the traffic light installation position and the like in the map information with the detectable range of the front cameras. Generally, when the red and green lamps are close to the stop line, the requirement for the angle of detection is high, and when the red and green lamps are far from the stop line, the requirement for resolution is high. When the traffic light is far away from the stop line, so that the requirement on the resolution is too high, or the angle of the stop line is inclined or the road gradient changes greatly, so that the requirement on the viewing angle is too high, and the like, the requirement on the vehicle passing safety can not be met. By comparing the information, infrastructure positions or scenes which do not meet the safety design can be theoretically screened out and stored in the planning auxiliary element storage unit 2 as planning auxiliary elements. Preferably, these planning assistance elements are marked as insecure with a traffic light identification function for the front camera.
Fig. 4 schematically shows a traffic light recognition function screening planning assistance element for a front camera of a vehicle. Part (a) of fig. 4 shows that the vehicle is far from the traffic light, and the traffic light is within the detection range of the front camera of the vehicle. Part (b) in fig. 4 shows that the vehicle a is located at the stop line, and the traffic light is not completely located in the detection range of the front camera of the vehicle a, so that the scene does not meet the requirement of vehicle traffic safety for the traffic light identification function of the front camera of the vehicle a.
It should be appreciated that the screening results will not be the same for different vehicles. For example, the configuration of the SUV and the car, and the installation positions of the sensors are greatly different, and a road section which does not meet the requirement of vehicle passing safety for some driving assistance functions of some vehicles may be safe for other vehicle types with different configurations. Part (c) in fig. 4 shows that the vehicle B is located at the stop line, and the traffic light is completely located in the detection range of the front camera of the vehicle B, so that the scene meets the requirement of vehicle traffic safety for the traffic light identification function of the front camera of the vehicle B.
Additionally or alternatively, the screened infrastructure location or scene may be actually tested, and further the planning assistance elements may be screened according to the test result. Fig. 5 schematically shows a process of screening planning assistance elements in connection with actual tests according to an exemplary embodiment of the present invention.
Optionally, the planning assistance element comprises a limitation required to turn on the associated driving assistance function. For example, the restriction condition may be that the associated driving assistance function is allowed to be turned on in a clear weather, and is not allowed to be turned on in a rainy or snowy weather.
Optionally, the planning assistance element may comprise, for example, the following road information: tidal lanes, variable-guidance lanes, autodrive lanes, left-turn waiting areas, bus lanes, non-hybrid lanes, level crossings, other lanes not suitable for a particular driving assistance function of a vehicle.
Both the variable guide lane and the tidal lane belong to variable lane sections. The variable guide lane represents a lane in which the direction of the vehicle after entering the lane is determined according to the indication of the corresponding variable lane signal lamp. Variable guide lanes are generally provided on a road section where traffic conditions are relatively complicated.
Optionally, the planning assistance element is labeled as at least one of the following elements depending on the availability of a specific driving assistance function for the vehicle: "no pass element", "dangerous pass element", "cautious pass element". In particular, the planning assistance elements can be classified according to the specific driving assistance function for the vehicle as: "no pass element", "dangerous pass element", "cautious pass element".
It should be appreciated that the classification results for the planning assistance elements may vary based on different vehicle functional designs and maturity and based on environmental conditions in different regions. For example, for a first-line city main road, the "bus lane" belongs to a "cautious traffic element" due to the fact that the design and management of the main road are more standard, and for a second-line city main road, the "bus lane" belongs to a "dangerous traffic element".
The classification of the planning assistance elements can be performed according to legal requirements, system function definitions and test results. The classification of the planning assistance elements may also be based on the behavior characteristics of other traffic participants, for example, in some road segments, the road structure itself meets the turn-on condition of a certain driving assistance sub-function, but there is a high probability that other traffic participants have aggressive driving behavior and will affect the performance of the certain driving assistance sub-function of the own vehicle, for example, resulting in a tendency of false braking or late braking in case of turning on the driving assistance sub-function, so that the road segment will be marked as "the driving assistance sub-function turn-on condition is not met".
The invention also relates to a use method of the map manufactured and/or processed by the map manufacturing and/or processing method, wherein the use method comprises the following steps: the planning assistance elements are read directly via a data interface. It will be appreciated that the features and advantages described above with respect to the mapping and/or machining method apply equally to the method of use. The map is particularly useful for path planning of vehicles.
Fig. 6 schematically illustrates a path planning method for path planning for an autonomous vehicle using the map storage specification of the present invention, according to an exemplary embodiment of the present invention.
The path planning method comprises the following steps: acquiring destination information; reading planning assistance elements directly from the map via a data interface; and performing global path planning based on the planning assistance element. According to the invention, the calculation amount can be reduced when planning and verifying the path by selecting the planning auxiliary element which is taken out and stored as the planning auxiliary element layer.
Specifically, the path planning method may include:
1. and the vehicle acquires destination information, and avoids road sections containing 'no-pass elements' to carry out global path planning.
2. And if the path planning fails, prompting that the path generation fails and not starting the automatic driving.
3. If the path planning is successful, verifying whether the path contains other planning auxiliary elements, namely whether the road segments contain dangerous traffic elements and cautious traffic elements.
4. If the road section contains the dangerous traffic element, the road section is avoided and the global path planning is carried out again:
a. if the complete path is successfully generated under the condition of avoiding the 'no-pass element' and the 'dangerous-pass element', the manual preferred path selection is required, and the vehicle starts normal automatic driving, so that the driver has the possibility of making selection or confirmation based on personal preference by manually selecting the preferred path;
b. if the complete path is failed to be generated under the condition of avoiding the 'no-pass element' and the 'dangerous-pass element', the position of the road section containing the elements is warned to prompt a driver, and under the necessary condition, the possibility of manual take-over exists in the road section, the driver or a supervisor is reminded, and meanwhile, the vehicle starts to be driven cautiously and automatically in the corresponding road section.
5. If the road section does not contain the dangerous traffic element, whether the road section containing the cautious traffic element is detected further:
a. if the 'cautious passing element' is included, starting cautious automatic driving of the vehicle on the corresponding road section;
b. if the 'cautious passing element' is not included and no other judgment condition is set, the vehicle starts normal automatic driving.
It should be understood that the manual selection of the path may also be performed by the system with the various determination conditions set.
It should be understood that "cautious autopilot" is a distinctive (more cautious) autopilot mode relative to normal autopilot, and that "cautious autopilot" includes, but is not limited to, system slowdown, system degradation, and the like. If the vehicle is temporarily not set with strategies and parameters different from normal autonomous driving, cautious autonomous driving may be equivalent to normal autonomous driving.
Fig. 7 schematically shows another path planning method. Under the condition of having enough computing power and not having the map elements of the planning assistance layer, the positions of the three types of planning assistance elements in the map data structure can be defined, and path planning and verification can be carried out by directly retrieving and extracting corresponding keywords. The specific method comprises the following steps:
1. the vehicle acquires destination information, performs global path planning, extracts and searches necessary attribute information of all lanes or roads in the path, and determines whether a link containing a 'no-pass element' is included.
2. And if the road sections contain the traffic prohibition elements, the road sections of the traffic prohibition elements are avoided, and the global path planning is completed again. And circularly judging whether the newly generated path contains the 'no-pass element'.
a. If the complete path which does not contain the traffic prohibition element is successfully generated, whether the complete path contains the dangerous traffic element is judged.
b. And if the complete path which does not contain the traffic prohibition element fails to be generated, prompting that the path is failed to be generated, and temporarily not starting the automatic driving.
3. And if the road section does not contain the traffic prohibition element, continuously judging whether the road section contains the dangerous traffic element.
4. And if the road section contains the dangerous traffic element, the road section is avoided and the global path planning is carried out again.
a. If the complete path is successfully generated under the condition of avoiding the 'no-pass elements' and the 'dangerous-pass elements', the manual path selection is required to be preferred, and the vehicle starts normal automatic driving.
b. If the complete path is failed to be generated under the condition of avoiding the 'no-pass element' and the 'dangerous-pass element', the position of the road section containing the elements is warned to prompt a driver, and if necessary, the possibility of manual take-over exists in the road section, the driver or a supervisor is reminded to pay attention to the road section, and meanwhile, the vehicle starts to be driven cautiously and automatically.
5. If the road section of the 'dangerous traffic element' is not included, whether the road section of the 'cautious traffic element' is included or not is further detected.
a. If a "cautious traffic element" is included, the vehicle begins cautious autonomous driving at the corresponding road segment.
b. If the 'cautious passing element' is not included and no other judgment condition is set, the vehicle starts normal automatic driving.
Although specific embodiments of the invention have been described herein in detail, they have been presented for purposes of illustration only and are not to be construed as limiting the scope of the invention. Various substitutions, alterations, and modifications may be devised without departing from the spirit and scope of the present invention.
Claims (10)
1. A method of making and/or processing a map for a vehicle, wherein the method comprises the steps of:
providing and storing static road elements;
selecting a planning auxiliary element and storing the planning auxiliary element or information for pointing to the planning auxiliary element, wherein the planning auxiliary element represents an element selected from a static road element or a sub-element of the static road element and associated with the traffic safety of the vehicle; and
a data interface is provided via which planning assistance elements can be read directly.
2. The method according to claim 1, wherein the specific driving assistance function of the planning assistance element for a specific vehicle is selected and marked in dependence on the vehicle passage safety.
3. The method of claim 2, wherein,
the planning assistance elements include the following road segments: aiming at the traffic light identification function of a front camera of a vehicle, screening out road sections which do not meet the safety condition of the traffic light identification function of the front camera based on stop line information and/or road orientation information and/or traffic light installation positions provided by static road elements, wherein planning auxiliary elements corresponding to the road sections are marked as unsafety aiming at the traffic light identification function of the front camera; and/or
The planning assistance element contains the constraints required to turn on the associated driving assistance function.
4. The method of any one of claims 1-3,
the planning assistance element comprises at least one of the following road information: tidal lanes, variable guide lanes, autodrive lanes, left-turn waiting areas, bus lanes, non-hybrid lanes, grade crossings, other lanes not suitable for a particular driving assistance function of a vehicle; and/or
The planning assistance elements are classified according to the availability of a specific driving assistance function for the vehicle as: "no pass element", "dangerous pass element", "cautious pass element"; and/or
The data interface is arranged such that the planning assistance element can be directly overwritten via said data interface.
5. The method of any one of claims 1-4,
the method further comprises providing and storing at least one of the following information: dynamic road environment elements, dynamic surrounding vehicle information, dynamic weather and road condition information and real-time communication information; and/or
The static road elements comprise static road environment elements and/or road connection relations.
6. Use of a map made and/or processed by a method according to any of claims 1-5, wherein the use comprises: the planning assistance elements are read directly via a data interface.
7. A map storage device for storing a map produced and/or processed by the method of any one of claims 1-5, wherein the map storage device comprises: a static road element storage unit (1) for storing static road elements, a planning assistance element storage unit (2) for storing planning assistance elements or information for pointing to planning assistance elements, and an interface unit (3) for reading data via a data interface.
8. A path planning method for path planning for autonomous vehicles using maps made and/or processed by the method according to any of claims 1-5, wherein the path planning method comprises:
step S1, acquiring destination information;
step S2, reading planning assistance elements directly from the map via a data interface; and
and step S3, carrying out global path planning based on the planning auxiliary elements.
9. The path planning method according to claim 8, wherein step S3 includes:
a substep S31 of performing global path planning while avoiding a link including a "no-pass element" according to the destination information;
a substep S32, if the global path planning in the substep S32 fails, prompting the path generation failure and temporarily not starting the automatic driving; and
in sub-step S33, if the global path planning in sub-step S32 is successful, it is verified whether the generated global path passes through a road segment containing a "dangerous traffic element" and a "cautious traffic element".
10. The path planning method according to claim 9, wherein the sub-step S33 further includes:
substep S331: if the generated global path contains the road sections of the dangerous traffic elements, the road sections containing the dangerous traffic elements are avoided and the global path planning is carried out again, wherein,
S331A: if the complete path is successfully generated under the condition of avoiding the 'no-pass element' and the 'dangerous pass element', path planning is finished, and the vehicle starts normal automatic driving; and
S331B: if the complete path is failed to be generated under the condition of avoiding the traffic prohibition elements and the dangerous traffic elements, displaying road sections containing the traffic prohibition elements or the dangerous traffic elements, and starting prudent automatic driving of the vehicle, wherein the road sections containing the traffic prohibition elements or the dangerous traffic elements optionally indicate that the requirement of manual takeover exists;
substep S332: if the generated global path does not contain the road section of the dangerous traffic element but contains the cautious traffic element, path planning is completed, and the vehicle starts cautious automatic driving on the road section containing the cautious traffic element; and
substep S333: and if the generated global path does not contain the road sections of the dangerous traffic elements and does not contain the road sections of the cautious traffic elements, finishing path planning and starting normal automatic driving of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110710631.2A CN113432616A (en) | 2021-06-25 | 2021-06-25 | Map making and/or processing method, map storage device and path planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110710631.2A CN113432616A (en) | 2021-06-25 | 2021-06-25 | Map making and/or processing method, map storage device and path planning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113432616A true CN113432616A (en) | 2021-09-24 |
Family
ID=77754389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110710631.2A Pending CN113432616A (en) | 2021-06-25 | 2021-06-25 | Map making and/or processing method, map storage device and path planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113432616A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115713866A (en) * | 2022-10-11 | 2023-02-24 | 悉地（苏州）勘察设计顾问有限公司 | Road static information active service method based on vehicle running characteristics |
-
2021
- 2021-06-25 CN CN202110710631.2A patent/CN113432616A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115713866A (en) * | 2022-10-11 | 2023-02-24 | 悉地（苏州）勘察设计顾问有限公司 | Road static information active service method based on vehicle running characteristics |
| CN115713866B (en) * | 2022-10-11 | 2023-08-22 | 悉地（苏州）勘察设计顾问有限公司 | Road static information active service method based on vehicle operation characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12112535B2 (en) | Systems and methods for effecting map layer updates based on collected sensor data | |
| CN113724520B (en) | Vehicle-road cooperative information processing method and device, electronic equipment and storage medium | |
| KR20210029242A (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
| CN107577231B (en) | Method and device for making control decision of vehicle and unmanned vehicle | |
| CN112106124A (en) | System and method for using V2X and sensor data | |
| CN109767637A (en) | The method and apparatus of the identification of countdown signal lamp and processing | |
| CN110606093A (en) | Vehicle performance evaluation method, device, equipment and storage medium | |
| CN107886750B (en) | Unmanned automobile control method and system based on beyond-visual-range cooperative cognition | |
| CN113935441B (en) | Selection method, equipment and storage medium for testing road for automatic driving function of automobile | |
| CN110422177A (en) | A kind of control method for vehicle, apparatus and system | |
| CN112991799A (en) | Vehicle autopilot system and method using V2X communication | |
| US11847385B2 (en) | Variable system for simulating operation of autonomous vehicles | |
| CN109903574B (en) | Method and device for acquiring traffic information at intersection | |
| CN115675520A (en) | Unmanned driving implementation method and device, computer equipment and storage medium | |
| CN114973644B (en) | Road information generating device | |
| CN116597690B (en) | Highway test scene generation method, equipment and medium for intelligent network-connected automobile | |
| CN116745831A (en) | Map generation device, map generation program, and in-vehicle device | |
| CN119043358A (en) | Path determination method and device, vehicle-mounted controller and vehicle | |
| US20210048819A1 (en) | Apparatus and method for determining junction | |
| CN113432616A (en) | Map making and/or processing method, map storage device and path planning method | |
| US20230073038A1 (en) | Hierarchical processing of traffic signal face states | |
| CN114722931A (en) | Vehicle data processing method, device, data acquisition device and storage medium | |
| US12073607B2 (en) | Recognition model distribution system and updating method of recognition model | |
| US20240192007A1 (en) | Method and system for controlling autonomous driving by search and train of autonomous driving software linked with route guidance | |
| CN114954242B (en) | Control device, mobile object, control method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210924 |