CN112113575B - Automatic driving system, high-precision map switching method thereof and storage medium - Google Patents
Automatic driving system, high-precision map switching method thereof and storage medium Download PDFInfo
- Publication number
- CN112113575B CN112113575B CN202010562148.XA CN202010562148A CN112113575B CN 112113575 B CN112113575 B CN 112113575B CN 202010562148 A CN202010562148 A CN 202010562148A CN 112113575 B CN112113575 B CN 112113575B
- Authority
- CN
- China
- Prior art keywords
- precision
- map
- layer
- switching
- automatic driving
- 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
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims description 10
- 238000011161 development Methods 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 13
- 238000004904 shortening Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
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
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3667—Display of a road map
- G01C21/367—Details, e.g. road map scale, orientation, zooming, illumination, level of detail, scrolling of road map or positioning of current position marker
Abstract
The invention discloses an automatic driving system, a high-precision map switching method and a computer-readable storage medium thereof, wherein the method comprises the following steps: positioning by using a map presented by a first precision layer when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. The invention reduces the use of map layers with higher precision under the condition of ensuring the automatic driving positioning requirement, thereby achieving the effect of shortening the development period of the automatic driving high-precision map.
Description
Technical Field
The present disclosure relates to the field of autopilot technologies, and in particular, to an autopilot system, a high-precision map switching method thereof, and a computer readable storage medium.
Background
The high-precision map provides higher map precision, and more abundant road information at a lane level, than the conventional map. The higher map accuracy is realized in that the map accuracy is accurate to the centimeter level, and the richer road information is realized in that the map accuracy comprises the information of the number, the width, the gradient, the curvature information, the actual style of other traffic participants and the like. Therefore, the high-precision map can provide more accurate positioning and auxiliary environment perception for automatic driving, realize decision planning, improve the safety of automatic driving and is an indispensable condition for realizing L3 level and above automatic driving. The high-precision map is composed of multiple layers of layers with different precision levels, such as a 10-meter-level layer, a 5-meter-level layer, a centimeter-level layer and the like, and road information displayed by the layer with higher precision level is finer.
The automatic driving technology is continuously developed, and accordingly, higher demands for automatic driving positioning, namely, higher-precision maps with higher precision levels are required. To meet the above requirements, it is necessary to construct a global high-precision map with a higher precision level using a long development period.
Disclosure of Invention
According to the automatic driving system, the high-precision map switching method and the computer readable storage medium, the problem that a long development period is required for map development in order to meet the automatic driving positioning requirement is solved, the use of map layers with higher precision is reduced under the condition that the automatic driving positioning requirement is guaranteed, and therefore the effect of shortening the development period of an automatic driving high-precision map is achieved.
The embodiment of the application provides a high-precision map switching method of an automatic driving system, which comprises the following steps:
positioning by using a map presented by a first precision layer when automatic driving starts;
in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements;
and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information.
In an embodiment, before the step of locating using the map presented in the first precision layer at the beginning of the automatic driving, the method further comprises the steps of:
respectively setting anchor points at corresponding positions of the first precision layer and the second precision layer;
and fusing the first precision layer and the second precision layer into a global map by taking the anchor point as a reference anchor point for layer fusion.
In an embodiment, the precision level of the first precision layer is in the centimeter level, and the precision level of the second precision layer is in the sub-meter level.
In an embodiment, before the step of locating using the map presented in the first precision layer at the beginning of the automatic driving, the method further comprises the steps of:
corresponding semantic information is set for the map switching mark, and observation constraint corresponding to the semantic information is set.
In one embodiment, the map switch is identified as a road facility having a characteristic pattern, the characteristic pattern having a uniqueness when the road facility having the characteristic pattern is identified.
In an embodiment, the semantic information is switching the first precision layer to the second precision layer or switching the second precision layer to the first precision layer.
In an embodiment, the different places are located at a starting point section of the automatic driving route, a complex section meeting a preset condition, a common section not meeting the preset condition, and a stop point section.
In an embodiment, the length of the starting point section is a first preset length, and the length of the stop point section is a second preset length.
The embodiment of the application also provides an automatic driving system, which comprises a processor, a memory and a high-precision map switching program stored on the memory and capable of running on the processor, wherein the high-precision map switching program realizes the steps of the high-precision map switching method of the automatic driving system when being executed by the processor.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a high-precision map switching program, and the high-precision map switching program realizes the steps of the high-precision map switching method of the automatic driving system when being executed by a processor.
The technical scheme of the automatic driving system, the high-precision map switching method and the computer readable storage medium provided by the embodiment of the application has at least the following technical effects:
positioning by using a map presented by a first precision layer at the beginning of automatic driving; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is effectively solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
Drawings
Fig. 1 is a schematic structural diagram of an autopilot system according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a first embodiment of a high-precision map switching method of the autopilot system of the present application;
fig. 3 is a schematic diagram of a map switching identifier according to an embodiment of the present application;
FIG. 4 is a flow chart of a second embodiment of a high-precision map switching method for an autopilot system of the present application;
FIG. 5 is a schematic diagram of layer fusion according to an embodiment of the present application;
FIG. 6 is a flow chart of a third embodiment of a high-precision map switching method for an autopilot system of the present application;
fig. 7 is a flowchart of a fourth embodiment of a high-precision map switching method of the autopilot system of the present application.
Detailed Description
In order to solve the problem that a very long development period is required to develop a map in order to meet the requirement of automatic driving positioning, the method adopts a map presented by a first precision map layer to perform positioning when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Under the condition of ensuring the automatic driving positioning requirement, the use of map layers with higher precision level is reduced, and therefore the effect of shortening the development period of the automatic driving high-precision map is achieved.
In order to better understand the above technical solution, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, which is a schematic hardware structure of an autopilot system according to various embodiments of the present application, the system may include: a processor 101, a memory 102, an image pickup apparatus 103, a display apparatus 104, and the like. Those skilled in the art will appreciate that the hardware configuration of the autopilot system shown in fig. 1 is not limiting of the autopilot system and that the autopilot system may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
The various components of the autopilot system are described in detail below in conjunction with fig. 1:
the processor 101 is a control center of the automated driving system, connects various parts of the entire automated driving system, and performs various functions and processes data of the automated driving system by running or executing programs stored in the memory 102 and calling the data stored in the memory 102, thereby performing overall monitoring of the automated driving system.
The memory 102 may be used to store various programs for the autopilot system as well as various data. The memory 102 mainly includes a stored program area and a stored data area, wherein the stored program area stores at least a program required for performing high-precision map switching; the storage data area may store various data of the automated driving system, such as high-precision map data. In addition, the memory 102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
The image capturing apparatus 103 may be used to acquire image information of a road surface facility during automatic driving, and transmit the image information to the processor 101 for image recognition or road information data acquisition.
The display device 104 may be used to display a high-precision map.
In the embodiment of the present application, the processor 101 may be configured to invoke the high-precision map switching program stored in the memory 102, and perform the following operations:
positioning by using a map presented by a first precision layer when automatic driving starts;
in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements;
and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information.
In one embodiment, the processor 101 may be configured to invoke the high precision map switching program stored in the memory 102 and perform the following operations:
respectively setting anchor points at corresponding positions of the first precision layer and the second precision layer;
and fusing the first precision layer and the second precision layer into a global map by taking the anchor point as a reference anchor point for layer fusion.
In an embodiment, the precision level of the first precision layer is in the centimeter level, and the precision level of the second precision layer is in the sub-meter level.
In one embodiment, the processor 101 may be configured to invoke the high precision map switching program stored in the memory 102 and perform the following operations:
corresponding semantic information is set for the map switching mark, and observation constraint corresponding to the semantic information is set.
In one embodiment, the map switch is identified as a road facility having a characteristic pattern, the characteristic pattern having a uniqueness when the road facility having the characteristic pattern is identified.
In an embodiment, the semantic information is switching the first precision layer to the second precision layer or switching the second precision layer to the first precision layer.
In an embodiment, the different places are located at a starting point section of the automatic driving route, a complex section meeting a preset condition, a common section not meeting the preset condition, and a stop point section.
In an embodiment, the length of the starting point section is a first preset length, and the length of the stop point section is a second preset length.
According to the technical scheme, the map presented by the first precision layer is used for positioning when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is effectively solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
As shown in fig. 2, in a first embodiment of the present application, the high-precision map switching method of the autopilot system of the present application specifically includes the following steps:
step S110, at the start of automatic driving, positioning is performed using the map presented in the first precision layer.
In this embodiment, the first precision layer is a centimeter-level precision layer, that is, a high-precision layer with a centimeter-level precision, which is the highest precision layer in this embodiment. In the existing automatic driving high-precision map technology, the centimeter-level high-precision map is the high-precision map with the highest precision level, so that the centimeter-level precision map layer is selected as the first precision map layer, and if the high-precision map with the higher precision level appears in future, the centimeter-level high-precision map layer can also be selected as the first precision map layer.
The map presented by the first precision layer is used for positioning, so that the high precision layer with the highest precision level is used for positioning as much as possible during automatic driving, and the aim of obtaining more accurate positioning is fulfilled. Positioning using a map presented in centimeter-level precision layers is the most accurate solution currently available to provide positioning. When the map presented by the centimeter-level precision map layer is used for positioning, the centimeter-level precision map layer can provide more detailed road information for the automatically driven vehicle, and besides a basic road network, the road side facilities such as the number of lanes, lane lines, road side facility edge lines, street lamps and the like, and relevant information of attributes and types of the road side facilities can be provided, so that the automatically driven vehicle can be positioned more accurately through the information.
When automatic driving starts, the vehicle is at the starting point, and needs to gradually drive into the main traffic road at a higher speed after starting from the starting point, and the road condition in the process is often complex, so that in order to ensure the safety of the process, the map presented by the first precision layer is required to be used for positioning, namely the centimeter-level precision layer is required to be used for positioning. The road section which is undergone by the process of gradually accelerating from the starting point to drive into the main traffic road is called as the starting point road section of the automatic driving route, and the accurate positioning is required to be carried out in the road section, so that a centimeter-level high-precision map is required to be constructed in the range of the starting point road section. The length of the start point road section may be different in different actual automatic driving routes, but in order to uniformly determine the range of the high-precision map, a length needs to be preset for this road section. The actual length is generally within 20 meters, so the preset length can be set to be 20 meters, and other values can be set according to different actual conditions.
Step S120, when a map switching identifier is identified in the automatic driving process, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements.
In this embodiment, the map switching identifier is an entity identifier that is set in different places according to the positioning requirement change, and may specifically be a road facility with a feature pattern, where the feature of the feature pattern is unique when the road facility with the feature pattern is identified.
The positioning requirement change includes a change to a higher positioning requirement and a change to a lower positioning requirement. Such positioning demand change often occurs when the road situation becomes complex or the road situation becomes simple, and according to such characteristics, we can divide the automatic driving route into a start point section, one or more complex sections, one or more common sections, and a stop point section. The starting point section and the stop point section need to be preset to be 20 meters, and can be set to other values according to actual conditions; the division of the complex road section and the common road section also needs to preset a division condition, the preset condition can be the complexity of the road, the density of vehicles or personnel, other conditions capable of judging whether the vehicles need more accurate positioning or not, or a combination of the conditions, the road sections meeting the preset condition can be divided into the complex road sections, and the road sections not meeting the preset condition are divided into the common road sections. Also, the segments other than the start point segment and the stop point segment may be divided into more kinds of segments according to actual needs.
After the road sections are divided, the user can clearly know which road sections need more accurate positioning, namely a starting point road section, a complex road section and a stop point road section, and which road sections have lower positioning requirements, namely a common road section. Therefore, a high-precision map with higher precision level can be built only for road sections with higher positioning requirements, and the setting position of the map switching mark for map switching can be determined, namely, the map switching mark is arranged between the road sections according to the positioning requirements. For example, a map switching identifier for switching a higher-precision layer to a lower-precision layer is set at a location where a start-point road section with higher positioning requirements enters a common road section with lower positioning requirements, and a map switching identifier for switching a lower-precision layer to a higher-precision layer is set at a location where a common road section with lower positioning requirements enters a complex road section with higher positioning requirements.
The map switching mark is a road facility similar to a traffic sign on a road and provided with a entity, and the characteristic graph can be shown as L1 and L2 in fig. 3, or can be designed into other graphs capable of obviously representing map switching with high precision. It should be noted that the feature pattern of the map switch identifier needs to be unique when identified by the autopilot system, i.e. the feature pattern of the map switch identifier cannot be identical or too similar to the pattern visible on other road surfaces, resulting in erroneous judgment of the autopilot system.
The semantic information of the map switching identification is information capable of determining how to switch the map by switching the first precision layer to the second precision layer or switching the second precision layer to the first precision layer. According to the different number and types of layers in practical application, the semantic information can also be other map switching information. Because the semantic information corresponds to the map switch identification, when the map switch identification is identified, the corresponding semantic information can be obtained, so that how to switch the map is determined. The semantic information corresponding to the map switching identifier shown by L1 in fig. 3 is to switch the sub-meter precision layer into the centimeter precision layer, and the semantic information corresponding to the map switching identifier shown by L2 is to switch the centimeter precision layer into the sub-meter precision layer.
Step S130, if the semantic information meets the observation constraint, performing high-precision map switching according to the semantic information after matching the anchor points arranged on the first precision layer and the second precision layer.
In this embodiment, the observation constraint corresponds to semantic information, which is a condition for judging whether map switching is possible, and if the semantic information satisfies the observation constraint, this means that map switching is possible. The anchor points are matched to ensure that the map to be switched is the map of the same area, so that the situation of map switching errors is avoided. Besides anchor point matching, other technical means which can achieve the same effect can be adopted to perform switching preparation work of the high-precision map. After the high-precision map is matched, the high-precision map can be switched according to the semantic information, namely, when the semantic information is that the sub-meter precision map layer is switched to the centimeter precision map layer, the sub-meter precision map layer is switched to the centimeter precision map layer; and when the semantic information is that the centimeter-level precision image layer is switched to the sub-meter-level precision image layer, the centimeter-level precision image layer is switched to the sub-meter-level precision image layer.
In this embodiment, the first precision layer and the second precision layer represent map layers that can be switched from each other, and do not represent map layers that include only two layers. In practical applications, the high-precision map may include multiple precision layers, e.g., more than 3 layers of different precision. When there are multiple precision layers, the switching identification, anchor matching and the like correspond to the layers of each other. I.e. the first precision layer and the second precision layer may correspond to any two of the plurality of layers of different precision, respectively. For example, when the number of layers is 3, the switching identifier includes 6 types, and each layer is provided with a corresponding anchor point.
The method has the beneficial effects that when automatic driving starts, a map presented by a first precision layer is used for positioning; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is effectively solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
As shown in fig. 4, in a second embodiment of the present application, the high-precision map switching method of the autopilot system of the present application specifically includes the following steps:
step S210, anchor points are respectively set at corresponding positions of the first precision layer and the second precision layer.
In this embodiment, the first precision layer is a centimeter-level precision layer, the second precision layer is a sub-meter-level precision layer, and the precision layers of other precision levels may be set to be the first precision layer and the second precision layer according to practical situations. In actual situations, there may be cases where more than two precision layers are used, in which case the precision layers may be named as third precision layer and fourth precision layer … … in order according to the rule of decreasing precision level
The anchor points are respectively arranged at the corresponding positions of the first precision layer and the second precision layer to ensure the corresponding relation between the two layers, so that the two layers can be accurately corresponding, and different errors of the displayed areas can not occur when the two layers are required to be switched. The implementation of the method can be shown in fig. 5, an anchor point set on the first precision layer M2 is D1, an anchor point set on the second precision layer M3 is D2, and the anchor points D1 and D2 are respectively set at corresponding positions of the first precision layer and the second precision layer.
And step S220, the anchor point is used as a reference anchor point for layer fusion, and the first precision layer and the second precision layer are fused into an overall map.
In this embodiment, the global map includes a first precision layer and a second precision layer, and in actual situations, the global map may also include more layers. After the anchor points are used as reference anchor points for layer fusion to fuse the first precision layer and the second precision layer into the global map, the content presented by the two precision layers can be displayed on the global map, and the switching between the two precision layers can be realized.
As shown in fig. 5, the anchor point on the first precision layer M2 is D1, the anchor point on the second precision layer M3 is D2, and the anchor points D1 and D2 are used as the fusion reference anchor points of the first precision layer M2 and the second precision layer M3 to fuse the layers, so that the global map M1 can be obtained finally.
Step S230, at the start of automatic driving, positioning is performed using the map presented in the first precision layer.
Step S240, when a map switching identifier is identified in the automatic driving process, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements.
Step S250, if the semantic information meets the observation constraint, performing high-precision map switching according to the semantic information after matching the anchor points set on the first precision layer and the second precision layer.
The method has the beneficial effects that the step of fusing the precision layers into the global map is added on the basis of the first embodiment, and anchor points are respectively arranged at the corresponding positions of the first precision layer and the second precision layer; the anchor point is used as a reference anchor point for layer fusion to fuse the first precision layer and the second precision layer into an overall map; positioning by using a map presented by a first precision layer when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is further effectively solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
As shown in fig. 6, in a third embodiment of the present application, the high-precision map switching method of the autopilot system of the present application specifically includes the following steps:
step S310, corresponding semantic information is set for the map switching identification, and observation constraints corresponding to the semantic information are set.
In this embodiment, the corresponding semantic information is set for the map switching identifier to ensure that the autopilot system can determine what operation needs to be performed when identifying the map switching identifier, specifically, the semantic information of the map switching identifier shown as L1 in fig. 3 is set to switch the sub-meter precision layer into the centimeter precision layer; the semantic information of the map switching mark shown as L2 in fig. 3 is set to switch the centimeter level precision layer to the sub-meter level precision layer. In different practical applications, corresponding semantic information can be set for the map switching mark according to specific situations. The setting of the observation constraint corresponding to the semantic information is to determine whether the autopilot system should perform the operation, and the corresponding operation cannot be performed unless the semantic information corresponding to the observation constraint is obtained, but the semantic information which cannot correspond to the observation constraint is obtained.
Step S320, at the start of automatic driving, positioning is performed using the map presented in the first precision layer.
Step S330, when a map switching identifier is identified in the automatic driving process, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements.
Step S340, if the semantic information satisfies the observation constraint, performing high-precision map switching according to the semantic information after matching the anchor points set on the first precision layer and the second precision layer.
The method has the beneficial effects that the steps of defining the semantic information and setting the observation constraint are added on the basis of the first embodiment, the corresponding semantic information is set for the map switching mark, and the observation constraint corresponding to the semantic information is set; positioning by using a map presented by a first precision layer when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is further effectively solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
As shown in fig. 7, in a fourth embodiment of the present application, the high-precision map switching method of the autopilot system of the present application specifically includes the following steps:
in step S410, anchor points are set at corresponding positions of the first precision layer and the second precision layer respectively.
And step S420, the anchor point is used as a reference anchor point for layer fusion, and the first precision layer and the second precision layer are fused into an overall map.
Step S430, setting corresponding semantic information for the map switching mark, and setting observation constraint corresponding to the semantic information.
Step S440, at the start of automatic driving, positioning is performed using the map presented in the first precision layer.
Step S450, acquiring semantic information of a map switching identifier when the map switching identifier is identified in an automatic driving process; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements.
Step S460, if the semantic information meets the observation constraint, performing high-precision map switching according to the semantic information after matching the anchor points arranged on the first precision layer and the second precision layer.
In the present embodiment, the automatic driving route is divided into five sections in order: a starting point road section, a first common road section, a complex road section, a second common road section, and a stop point road section. The starting point road section, the complex road section and the stop point road section have higher positioning requirements, and centimeter-level precision image layers are built on the three road sections; the positioning requirements of two common road sections are low, and sub-meter-level precision image layers are built on the two road sections.
A map switching identifier shown as L2 in fig. 3 is set at a place where a starting point road section with higher positioning requirement enters a first common road section with lower positioning requirement and is recorded as a first map switching identifier; setting a map switching identifier shown as L1 in FIG. 3 at a place where a first common road section with lower positioning requirements enters a complex road section with higher positioning requirements, and marking the map switching identifier as a second map switching identifier; setting a map switching identifier shown as L2 in fig. 3 at a place where a complex road section with higher positioning requirement enters a second common road section with lower positioning requirement, and marking the map switching identifier as a third map switching identifier; and setting a map switching identifier shown as L1 in fig. 3 at a place where a second common road section with lower positioning requirements enters a stop road section with higher positioning requirements, and marking the map switching identifier as a fourth map switching identifier.
Fusing the centimeter-level precision image layer and the sub-meter-level precision image layer into a global map; setting semantic information of a map switching mark shown as L1 in FIG. 3 to switch a sub-meter-level precision layer into a centimeter-level precision layer; setting semantic information of a map switching mark shown as L2 in FIG. 3 to switch a centimeter-level precision layer into a sub-meter-level precision layer; an observation constraint corresponding to the two semantic information is set.
Starting automatic driving, and positioning by using a map presented by a centimeter-level precision layer at a starting point road section; when the first map switching mark is identified, switching the centimeter-level precision image layer into a sub-meter-level precision image layer according to semantic information; when the second map switching mark is identified, switching the sub-meter precision layer into a centimeter precision layer according to semantic information; when the third map switching mark is identified, switching the centimeter-level precision image layer into a sub-meter-level precision image layer according to semantic information; when the fourth map switching mark is identified, switching the sub-meter-level precision image layer into a centimeter-level precision image layer according to semantic information, stopping the vehicle, and ending the automatic driving.
The method has the beneficial effects that the step of fusing the precision layers into the global map is added on the basis of the third embodiment, and anchor points are respectively arranged at the corresponding positions of the first precision layer and the second precision layer; the anchor point is used as a reference anchor point for layer fusion to fuse the first precision layer and the second precision layer into an overall map; setting corresponding semantic information for the map switching mark, and setting observation constraint corresponding to the semantic information; positioning by using a map presented by a first precision layer when automatic driving starts; in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements; and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information. Therefore, the problem that the map development needs to be carried out in order to meet the automatic driving positioning requirement is further solved, the use of map layers with higher precision is reduced under the condition of ensuring the automatic driving positioning requirement, and the effect of shortening the development period of the automatic driving high-precision map is achieved.
Based on the same inventive concept, the embodiment of the present application further provides an autopilot system, where the autopilot system includes a processor, a memory, and a high-precision map switching program stored in the memory and capable of running on the processor, where the high-precision map switching program, when executed by the processor, implements each process of the high-precision map switching method embodiment of the autopilot system as described above, and can achieve the same technical effects, so that repetition is avoided and no further description is given here.
Since the autopilot system provided in the embodiments of the present application is an autopilot system used for implementing the method in the embodiments of the present application, based on the method described in the embodiments of the present application, a person skilled in the art can understand the specific structure and the modification of the autopilot system, and therefore, the disclosure is not repeated here. All automatic driving systems adopted by the method of the embodiment of the application belong to the scope of protection required by the application.
Based on the same inventive concept, the embodiments of the present application further provide a computer readable storage medium, where a high-precision map switching program is stored on the computer readable storage medium, where each process of the high-precision map switching method embodiment of the autopilot system described above is implemented when the high-precision map switching program is executed by a processor, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.
Since the computer readable storage medium provided in the embodiments of the present application is a computer readable storage medium used for implementing the method in the embodiments of the present application, based on the method described in the embodiments of the present application, a person skilled in the art can understand the specific structure and the modification of the computer readable storage medium, and therefore, the detailed description thereof is omitted herein. All computer readable storage media used in the methods of the embodiments of the present application are within the scope of the present application.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A high-precision map switching method of an automatic driving system, the high-precision map at least comprising a first precision layer and a second precision layer, and the precision level of the first precision layer is higher than that of the second precision layer, the method comprising the steps of:
positioning by using a map presented by a first precision layer when automatic driving starts;
in the automatic driving process, when a map switching identifier is identified, semantic information of the map switching identifier is acquired; the map switching mark is an entity mark which is arranged at different places according to the change of positioning requirements;
and if the semantic information meets the observation constraint, matching the anchor points arranged on the first precision layer and the second precision layer, and then switching the high-precision map according to the semantic information.
2. The method for high-precision map switching of an autopilot system of claim 1 further comprising, prior to the step of locating using a map presented in a first precision map layer at the beginning of autopilot, the steps of:
respectively setting anchor points at corresponding positions of the first precision layer and the second precision layer;
and fusing the first precision layer and the second precision layer into a global map by taking the anchor point as a reference anchor point for layer fusion.
3. The high-precision map switching method of an automatic driving system according to claim 1 or 2, wherein the precision level of the first precision map layer is in the order of centimeters and the precision level of the second precision map layer is in the order of sub-meters.
4. The method for high-precision map switching of an autopilot system of claim 1 further comprising, prior to the step of locating using a map presented in a first precision map layer at the beginning of autopilot, the steps of:
corresponding semantic information is set for the map switching mark, and observation constraint corresponding to the semantic information is set.
5. The high-precision map switching method of an automatic driving system according to claim 1 or 4, wherein the map switching identification is a road facility having a characteristic pattern, and the pattern feature when the road facility having the characteristic pattern is identified has uniqueness.
6. The high-precision map switching method of an automatic driving system according to claim 1 or 4, wherein the semantic information is switching a first precision map layer to a second precision map layer or switching the second precision map layer to the first precision map layer.
7. The high-precision map switching method of an automatic driving system according to claim 1, wherein the different places are located at a start point section of an automatic driving route, a complex section satisfying a preset condition, a normal section not satisfying the preset condition, a stop point section.
8. The method for switching a map with high accuracy of an automatic driving system according to claim 7, wherein the length of the start point section is a first preset length and the length of the stop point section is a second preset length.
9. An autopilot system comprising a processor, a memory and a high precision map switching program stored on the memory and executable on the processor, the high precision map switching program when executed by the processor implementing the steps of the high precision map switching method of an autopilot system of any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a high-precision map switching program which, when executed by a processor, implements the steps of the high-precision map switching method of the automated driving system according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010562148.XA CN112113575B (en) | 2020-06-18 | 2020-06-18 | Automatic driving system, high-precision map switching method thereof and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010562148.XA CN112113575B (en) | 2020-06-18 | 2020-06-18 | Automatic driving system, high-precision map switching method thereof and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112113575A CN112113575A (en) | 2020-12-22 |
| CN112113575B true CN112113575B (en) | 2024-02-06 |
Family
ID=73798952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010562148.XA Active CN112113575B (en) | 2020-06-18 | 2020-06-18 | Automatic driving system, high-precision map switching method thereof and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112113575B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002340589A (en) * | 2001-05-17 | 2002-11-27 | Jekku:Kk | Navigation system with location correcting function and recording medium |
| JP2015184155A (en) * | 2014-03-25 | 2015-10-22 | 株式会社日立製作所 | Map data structure, map data update method, vehicle position correction method, on-vehicle device, server, and vehicle position data correction system |
| JP2016048210A (en) * | 2014-08-28 | 2016-04-07 | 株式会社ゼンリン | Vehicle position specification device, drive support device and data structure |
| JP2016151931A (en) * | 2015-02-18 | 2016-08-22 | 株式会社トヨタマップマスター | Map data structure, map data storage medium, navigation device and navigation method |
| JP2018100867A (en) * | 2016-12-20 | 2018-06-28 | パイオニア株式会社 | Display device, control method, program, and storage medium |
| CN108253973A (en) * | 2016-12-28 | 2018-07-06 | 北京四维图新科技股份有限公司 | High-precision map and the associated method and apparatus of standard map and hybrid navigation method and apparatus |
| CN108931254A (en) * | 2017-05-26 | 2018-12-04 | 千寻位置网络有限公司 | The system and method for latter end high-precision navigation |
| JP2019045212A (en) * | 2017-08-30 | 2019-03-22 | 株式会社 ミックウェア | Information processing device, map switching method, and map switching program |
| CN110110021A (en) * | 2019-03-22 | 2019-08-09 | 纵目科技（上海）股份有限公司 | Coordinate transformation method, terminal and storage medium between a kind of high-precision local map |
| CN111157006A (en) * | 2020-01-08 | 2020-05-15 | 浙江光珀智能科技有限公司 | Path searching method and system supporting multiple maps |
-
2020
- 2020-06-18 CN CN202010562148.XA patent/CN112113575B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002340589A (en) * | 2001-05-17 | 2002-11-27 | Jekku:Kk | Navigation system with location correcting function and recording medium |
| JP2015184155A (en) * | 2014-03-25 | 2015-10-22 | 株式会社日立製作所 | Map data structure, map data update method, vehicle position correction method, on-vehicle device, server, and vehicle position data correction system |
| JP2016048210A (en) * | 2014-08-28 | 2016-04-07 | 株式会社ゼンリン | Vehicle position specification device, drive support device and data structure |
| JP2016151931A (en) * | 2015-02-18 | 2016-08-22 | 株式会社トヨタマップマスター | Map data structure, map data storage medium, navigation device and navigation method |
| JP2018100867A (en) * | 2016-12-20 | 2018-06-28 | パイオニア株式会社 | Display device, control method, program, and storage medium |
| CN108253973A (en) * | 2016-12-28 | 2018-07-06 | 北京四维图新科技股份有限公司 | High-precision map and the associated method and apparatus of standard map and hybrid navigation method and apparatus |
| CN108931254A (en) * | 2017-05-26 | 2018-12-04 | 千寻位置网络有限公司 | The system and method for latter end high-precision navigation |
| JP2019045212A (en) * | 2017-08-30 | 2019-03-22 | 株式会社 ミックウェア | Information processing device, map switching method, and map switching program |
| CN110110021A (en) * | 2019-03-22 | 2019-08-09 | 纵目科技（上海）股份有限公司 | Coordinate transformation method, terminal and storage medium between a kind of high-precision local map |
| CN111157006A (en) * | 2020-01-08 | 2020-05-15 | 浙江光珀智能科技有限公司 | Path searching method and system supporting multiple maps |
Non-Patent Citations (1)
| Title |
|---|
| 基于CORS的公众位置修正方法研究与实现;宋玉兵;彭树标;沈飞;王勇;;测绘通报(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112113575A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162050B (en) | Travel control method and travel control system | |
| CN108253973B (en) | Method and device for associating high-precision map with standard map | |
| CN111046709B (en) | Vehicle lane level positioning method and system, vehicle and storage medium | |
| JP7153777B2 (en) | Automatic driving reference route determination method, device, terminal, storage medium, and program | |
| CN109631916B (en) | Map generation method, map generation device, map generation equipment and storage medium | |
| CN110174110B (en) | Map corresponding method and device, electronic equipment and computer readable medium | |
| CN112614365B (en) | Electronic map processing method and device | |
| CN104949679A (en) | Navigation information determination method and navigation information determination device | |
| CN112113575B (en) | Automatic driving system, high-precision map switching method thereof and storage medium | |
| CN112732844B (en) | Method, apparatus, device and medium for automatically associating road object with road | |
| CN114863047A (en) | Intersection virtual line drawing method and device, electronic equipment and computer program product | |
| CN110473405B (en) | Driving state detection method and device, readable storage medium and electronic equipment | |
| CN113392170A (en) | High-precision map data generation method and device and server | |
| CN112683284A (en) | Method and device for updating high-precision map | |
| CN112418193A (en) | Lane line identification method and system | |
| CN116222603A (en) | Navigation route generation method and device, electronic equipment and storage medium | |
| CN115112125A (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114964210A (en) | Map drawing method, map drawing device, computer equipment and storage medium | |
| CN115683139A (en) | Vehicle-mounted map path planning method, system, electronic equipment and storage medium | |
| CN112101177A (en) | Map construction method and device and carrier | |
| CN113280824A (en) | High-precision map and standard map association method and equipment | |
| CN115993124B (en) | Virtual lane line generation method, device, equipment and computer readable storage medium | |
| CN112629546B (en) | Position adjustment parameter determining method and device, electronic equipment and storage medium | |
| CN112101369B (en) | Image segmentation method and device | |
| CN110440816B (en) | Lane maze creating and navigation route recommending method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |