Method and device for determining reference line in path planning, vehicle and storage medium

Abstract

The invention relates to a reference line determination method and device in path planning, a vehicle and a storage medium, and relates to the technical field of path planning. The method comprises the following steps: acquiring driving data of a vehicle in the driving process of the vehicle; the driving data comprises at least one of the following items: intelligent driving mode information, road information, positioning information and reference line information; according to the driving data, determining a target type from a sensing type of a reference line and a map type, and performing path planning on the vehicle based on a target reference line of the target type; the reference line of the map type is generated based on map data of a road where the vehicle is located, and the reference line of the perception type is generated based on environment perception data of the road where the vehicle is located. Therefore, the accuracy of vehicle path planning can be improved, and path planning errors caused by dependence on a single reference line are avoided.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, in particular to the field of path planning technology, and specifically to a method, device, vehicle and storage medium for determining a reference line in path planning. Background Art

[0002] The reference line in path planning refers to the basic line used to generate the path. It can be a straight line or a curve. It is one of the important concepts in the path planning algorithm and is the basis and guiding direction of the path planning algorithm.

[0003] At present, there are two main ways to plan a path. One is to plan a path based on a reference line generated by the environmental perception data of the road where the vehicle is located. This method is highly dependent on the vehicle's sensors. In cases where there are many vehicles around, the ground lane lines are unclear or worn, etc., the path planning effect may be affected. The other is to plan a path based on a reference line generated by the map data of the road where the vehicle is located. This method strongly relies on positioning accuracy. In closed scenes (such as tunnels), the positioning accuracy is low, resulting in inaccurate path planning.

[0004] Therefore, how to determine the reference line in path planning to make path planning more accurate has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method, device, vehicle and storage medium for determining a reference line in path planning, so as to at least solve the technical problem of how to determine a reference line in path planning in the related art so as to make path planning more accurate. The technical solution of the present application is as follows:

[0006] According to a first aspect of the present application, a method for determining a reference line in path planning is provided, the method comprising: obtaining driving data of the vehicle during driving of the vehicle; the driving data comprising at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information; determining a target type from a perception type and a map type of the reference line according to the driving data, so as to plan a path for the vehicle based on a target reference line of the target type; the reference line of the map type is generated based on the map data of the road on which the vehicle is located, and the reference line of the perception type is generated based on the environmental perception data of the road on which the vehicle is located.

[0007] According to the above technical means, it is possible to dynamically and comprehensively judge whether the reference line used for path planning is of the perception type or the map type based on the intelligent driving mode information, road information, positioning information, reference line information and other information in the vehicle's driving data. This method comprehensively considers multiple information and can more comprehensively evaluate the current driving environment and conditions, so as to select the most appropriate reference line for path planning, reduce misjudgment and planning errors caused by relying on a single reference line, and improve the accuracy of path planning.

[0008] In a possible implementation, when the driving data satisfies a first preset condition, the target type is a map type; the first preset condition includes any one of the following: road information is used to indicate that there are no lane lines on the road where the vehicle is located; road information is used to indicate that the wear degree of the lane lines on the road where the vehicle is located exceeds a preset wear degree range; intelligent driving mode information is used to indicate that the vehicle is in navigation mode.

[0009] According to the above technical means, a reference line of a map type can be selected when the driving data meets the first preset condition. Since the driving data meets the above first preset condition, it can be explained that the environmental perception data of the road currently located by the vehicle is limited. Therefore, when the driving data meets the first preset condition, selecting a reference line of a map type can improve the accuracy of the vehicle's path planning.

[0010] In another possible implementation, when the driving data satisfies a second preset condition, the target type is a perception type; the second preset condition includes any one of the following: positioning information is used to indicate that an abnormality has occurred in the positioning of the vehicle; positioning information is used to indicate that the vehicle has not performed positioning initialization processing; positioning information is used to indicate that the positioning error of the vehicle is higher than a preset error range; reference line information is used to indicate that the number of reference lines of the map type is lower than a preset number; road information is used to indicate that the exploration distance ahead of the road where the vehicle is located is lower than a preset distance; the exploration distance is determined based on the maximum distance of the road information ahead of the vehicle that can be obtained based on the map information.

[0011] According to the above technical means, a reference line of the perception type can be selected when the driving data meets the second preset condition. Since the driving data meets the above second preset condition, it can be explained that the map data of the road where the vehicle is currently located is limited. Therefore, when the driving data meets the second preset condition, a reference line of the perception type can be selected to improve the accuracy of the vehicle's path planning.

[0012] In another possible implementation, determining the target type from the perception type and the map type of the reference line according to the driving data includes: selecting the type with the highest priority from the perception type and the map type of the reference line as the target type according to the driving data.

[0013] According to the above technical means, the type with the highest priority is selected as the target type according to the driving data, that is, the vehicle can plan the path based on the reference line of the most suitable type, thereby improving the accuracy of the vehicle's path planning.

[0014] In another possible implementation, when the driving data satisfies a third preset condition, the priority of the map type is higher than the priority of the perception type; the third preset condition includes any one of the following: the reference line information is used to indicate that the confidence of the reference line of the perception type is lower than a preset confidence; the road information is used to indicate that the road on which the vehicle is located is an unstructured road; the road information is used to indicate that there is a divergence and merging area within a preset distance range in front of the road on which the vehicle is located.

[0015] According to the above technical means, when the driving data meets the third preset condition, it can be explained that the reference line of the perception type is unreliable, or the vehicle is in a complex road scene, resulting in unreliable environmental perception data. Therefore, when the driving data meets the third preset condition, the priority of the map type can be set to be higher than the priority of the perception type, so that path planning can be performed based on the reference line of the map type, thereby improving the accuracy of path planning.

[0016] In another possible implementation, when the driving data satisfies a fourth preset condition, the priority of the perception type is higher than the priority of the map type; the fourth preset condition includes any one of the following: the reference line information is used to indicate that the matching relationship between the reference line of the perception type and the reference line of the map type is mismatched; the matching relationship is used to indicate whether the environmental perception data used to generate the reference line of the perception type matches the map data used to generate the reference line of the map type.

[0017] According to the above technical means, when the driving data meets the fourth preset condition, it can be explained that there is a difference between the map data and the environmental perception data. This may be that the actual road data of the road where the vehicle is located has changed, and the road data included in the map data has not been adjusted accordingly, that is, the map data is inaccurate. Therefore, when the driving data meets the fourth preset condition, the priority of the perception type can be set higher than the priority of the map type, so that the path planning is performed based on the reference line of the perception type, thereby improving the accuracy of the path planning.

[0018] In another possible implementation, the target type is determined from the perception type and map type of the reference line according to the driving data, including: when the driving data satisfies the fifth preset condition, the type of the reference line used for path planning for the vehicle at the previous moment is determined as the target type; the fifth preset condition includes any one of the following: when the vehicle is in the process of changing lanes, the road information is used to indicate that the lane line of the road where the vehicle is located is pressed by the vehicle; when the vehicle is in the process of changing lanes, the positioning information is used to indicate that the vehicle is in a positioning fuzzy state; the positioning fuzzy state is used to indicate that the positioning accuracy of the vehicle is lower than the preset accuracy.

[0019] According to the above-mentioned technical means, when the vehicle is in the process of changing lanes, if the driving data meets the fifth preset condition, it can be said that the vehicle is currently in an unstable state. By determining the type of reference line used for path planning of the vehicle at the previous moment as the target type, the switching of the reference line type can be suppressed, thereby reducing the shaking of the vehicle and improving the stability of the vehicle's driving.

[0020] In another possible implementation, before determining the target type from the perception type and the map type of the reference line based on the driving data, the method further includes: matching the reference line of the perception type and the reference line of the map type so that the attributes included in the reference line of the perception type match the attributes included in the reference line of the map type.

[0021] According to the above technical means, by matching the perception type reference lines and the map type reference lines so that the attributes included in the perception type reference lines match the attributes included in the map type reference lines, the output form of the reference lines can be unified, so that the vehicle can switch between different types of reference lines more smoothly.

[0022] According to the second aspect provided by the present application, a device for determining a reference line in path planning is provided, the device comprising an acquisition unit and a determination unit. The acquisition unit is used to acquire driving data of the vehicle during the driving of the vehicle; the driving data comprises at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information; the determination unit is used to determine the target type from the perception type and map type of the reference line according to the driving data, so as to plan the path of the vehicle based on the target reference line of the target type; the reference line of the map type is generated based on the map data of the road where the vehicle is located, and the reference line of the perception type is generated based on the environmental perception data of the road where the vehicle is located.

[0023] According to the third aspect provided by the present application, a vehicle is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0024] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of the vehicle, the vehicle is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on a vehicle, the vehicle executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0026] Therefore, the above technical features of the present application have the following beneficial effects:

[0027] (1) Based on the intelligent driving mode information, road information, positioning information, reference line information and other information in the vehicle's driving data, it can dynamically and comprehensively determine whether the reference line used in path planning is of the perception type or the map type. This method comprehensively considers multiple information and can more comprehensively evaluate the current driving environment and conditions, thereby selecting the most appropriate reference line for path planning, reducing misjudgment and planning errors caused by relying on a single reference line, and improving the accuracy of path planning.

[0028] (2) When the driving data meets the first preset condition, a reference line of a map type may be selected. Since the driving data meets the first preset condition, it can be indicated that the environmental perception data of the road currently located by the vehicle is limited. Therefore, when the driving data meets the first preset condition, selecting a reference line of a map type can improve the accuracy of the vehicle's path planning.

[0029] (3) When the driving data meets the second preset condition, a reference line of the perception type may be selected. Since the driving data meets the second preset condition, it can be indicated that the map data of the road the vehicle is currently on is limited. Therefore, when the driving data meets the second preset condition, a reference line of the perception type may be selected to improve the accuracy of the vehicle's path planning.

[0030] (4) Based on the driving data, the type with the highest priority is selected as the target type. That is, the vehicle can plan the path based on the reference line of the most appropriate type, thereby improving the accuracy of the vehicle's path planning.

[0031] (5) When the driving data meets the third preset condition, it can be explained that the reference line of the perception type is unreliable, or the vehicle is in a complex road scene, resulting in unreliable environmental perception data. Therefore, when the driving data meets the third preset condition, the priority of the map type can be set higher than the priority of the perception type, so that path planning can be performed based on the reference line of the map type, thereby improving the accuracy of path planning.

[0032] (6) When the driving data meets the fourth preset condition, it can be explained that there is a difference between the map data and the environmental perception data. This may be because the actual road data of the road where the vehicle is located has changed, while the road data included in the map data has not been adjusted accordingly, that is, the map data is inaccurate. Therefore, when the driving data meets the fourth preset condition, the priority of the perception type can be set higher than the priority of the map type, so that the path planning is performed based on the reference line of the perception type, thereby improving the accuracy of the path planning.

[0033] (7) When the vehicle is in the process of changing lanes, if the driving data satisfies the fifth preset condition, it can be said that the vehicle is currently in an unstable state. By determining the type of reference line used for path planning of the vehicle at the previous moment as the target type, the switching of the reference line type can be suppressed, thereby reducing the shaking of the vehicle and improving the driving stability of the vehicle.

[0034] (8) By matching the perception-type reference line with the map-type reference line so that the attributes included in the perception-type reference line match the attributes included in the map-type reference line, the output form of the reference line can be unified, so that the vehicle can switch between different types of reference lines more smoothly.

[0035] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0036] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0038] Figure 1 is a flow chart showing a method for determining a reference line in path planning according to an exemplary embodiment;

[0039] Figure 2 is a flow chart showing another method for determining a reference line in path planning according to an exemplary embodiment;

[0040] Figure 3 is a schematic diagram of a travel direction of a reference line according to an exemplary embodiment;

[0041] Figure 4is a schematic diagram of another reference line's passing direction according to an exemplary embodiment;

[0042] Figure 5 is a schematic diagram of a passing direction of another reference line according to an exemplary embodiment;

[0043] Figure 6 is a flowchart of a method for determining a matching relationship between a perception-type reference line and a map-type reference line according to an exemplary embodiment;

[0044] Figure 7 is a schematic diagram showing a center line of a map and an area where a vehicle can pass safely according to an exemplary embodiment;

[0045] Figure 8 is a schematic diagram showing a map center line and a reference line of a perception type according to an exemplary embodiment;

[0046] Fig. 9 is a schematic diagram showing a perception-type reference line and a map-type reference line according to an exemplary embodiment;

[0047] Fig.10 is a schematic diagram showing a reference line of a target type and a reference line used for path planning of a vehicle at a previous moment according to an exemplary embodiment;

[0048] Fig.11 is a block diagram of a device for determining a reference line in path planning according to an exemplary embodiment;

[0049] Fig.12 is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0052] In response to the above problems, this application proposes a method for determining reference lines in path planning, which can comprehensively judge whether the reference line used in path planning is of perception type or map type based on the intelligent driving mode information, road information, positioning information, reference line information and other information in the vehicle's driving data. This method comprehensively considers multiple information and can more comprehensively evaluate the current driving environment and conditions, thereby selecting the most appropriate reference line for path planning, reducing misjudgments and planning errors caused by relying on a single reference line, and improving the accuracy of path planning.

[0053] For ease of understanding, the method for determining the reference line in the path planning provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0054] Figure 1 is a flow chart showing a method for determining a reference line in path planning according to an exemplary embodiment. Figure 1 As shown, the method for determining the reference line in the path planning includes the following steps:

[0055] S101. Acquire driving data of a vehicle during driving of the vehicle.

[0056] Among them, the driving data includes at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information.

[0057] Exemplarily, the intelligent driving mode information includes information for indicating the driving mode the vehicle is in. The road information includes information for indicating whether the road the vehicle is on is an unstructured road, and information for indicating whether the lane line of the road the vehicle is on is crossed by the vehicle.

[0058] The reference line information includes information indicating the confidence of the perceptual type reference line, information indicating the matching relationship between the perceptual type reference line and the map type reference line, and the like.

[0059] In addition, the specific process of obtaining the vehicle's driving data can be referred to the specific description in the following example, and this application will not go into details here.

[0060] S102: Determine a target type from the perception type and the map type of the reference line according to the driving data, and plan a path for the vehicle based on the target reference line of the target type.

[0061] The map-type reference line is generated based on the map data of the road where the vehicle is located, and the perception-type reference line is generated based on the environmental perception data of the road where the vehicle is located. Usually, the reference line refers to the lane lines on both sides of the vehicle's position.

[0062] In some embodiments, the target type applicable to the reference line can be judged and selected directly based on the driving data and the first preset condition and the second preset condition.

[0063] In one example, when the driving data meets the first preset condition, the target type is a map type.

[0064] The first preset condition includes any one of the following:

[0065] (1) Road information is used to indicate that the road on which the vehicle is located has no lane markings.

[0066] It is understandable that the road where the vehicle is located has no lane lines, including the situation where there are no designed lane lines on the road, the lane lines are blocked by obstacles (such as snow, mud and water), resulting in the vehicle's sensors being unable to detect the lane lines, etc. The map data of the road where the vehicle is located includes high-precision road information, including lane lines, traffic signs, road geometry, etc. Even if there are no clearly designed lane lines on the road, the map data may still include lane lines or assumed lane lines, or even if the lane lines are blocked by obstacles (such as snow, mud and water), the map data also includes clear and accurate lane lines. Therefore, when there are no lane lines on the road where the vehicle is located, you can select a map-type reference line for path planning.

[0067] (2) The road information is used to indicate that the wear degree of the lane line of the road on which the vehicle is located exceeds a preset wear degree range.

[0068] It is understandable that if the wear degree of the lane line of the road where the vehicle is located exceeds the preset wear degree range, it means that the lane line is unclear and the vehicle's sensor cannot effectively identify the lane line, while the map data includes clear and accurate lane lines. Therefore, when the wear degree of the lane line of the road where the vehicle is located exceeds the preset wear degree range, the reference line of the map type can be selected for path planning.

[0069] (3) Intelligent driving mode information is used to indicate that the vehicle is in pilot mode.

[0070] It is understandable that if the vehicle is in pilot mode, it means that the vehicle is driving in a more complex road environment, such as highways, urban roads, etc. The map data includes high-precision road information, including lane lines, traffic signs, road geometry, etc. These high-precision road information can provide a more stable and reliable data basis. Therefore, when the vehicle is in pilot mode, you can select a map-type reference line for path planning.

[0071] In another example, when the driving data meets the second preset condition, the target type is a perception type.

[0072] The second preset condition includes any one of the following:

[0073] (1) Positioning information is used to indicate that there is an abnormality in the positioning of the vehicle.

[0074] It is understandable that if the positioning of the vehicle is abnormal, it means that the map data may not be able to provide the positioning information of the vehicle, that is, it is impossible to determine the current location of the vehicle, and thus it is impossible to obtain the road information around the vehicle. If in this case, continuing to plan the path based on the reference line of the map data may lead to inaccurate path planning, thus affecting driving safety. In this case, the perception-type reference line can directly rely on the environmental perception data collected by the vehicle's sensors for path planning, thereby avoiding driving deviations or dangers caused by positioning abnormalities. Therefore, in the event of an abnormality in the positioning of the vehicle, a perception-type reference line can be selected for path planning.

[0075] (2) Positioning information is used to indicate that the vehicle has not yet completed positioning initialization processing.

[0076] It is understandable that if the vehicle has not been initialized for positioning, the vehicle's positioning information may be unstable or unreliable. If you continue to rely on inaccurate positioning information to determine the reference line for path planning, it may cause driving deviations and affect driving safety. Through the perception type reference line, the vehicle can plan the path based on the actual environmental perception data, thereby effectively avoiding the potential risks caused by inaccurate positioning information. Therefore, if the vehicle has not been initialized for positioning, the perception type reference line can be selected for path planning.

[0077] (3) Positioning information is used to indicate that the positioning error of the vehicle is higher than a preset error range.

[0078] It is understandable that if the positioning error of the vehicle is higher than the preset error range, it means that the vehicle cannot provide accurate positioning information. Determining reference lines for path planning based on inaccurate location information may result in inaccurate path planning, thereby affecting driving safety. In this case, through the perception type reference line, the vehicle can directly rely on the environmental perception data collected by the vehicle's sensors for path planning, thereby avoiding driving deviations or dangers caused by positioning abnormalities. Therefore, when the positioning error of the vehicle is higher than the preset error range, the perception type reference line can be selected for path planning.

[0079] (4) The reference line information is used to indicate that the number of reference lines of a map type is lower than a preset number.

[0080] It is understandable that if the number of map-type reference lines is lower than the preset number, it means that the number of map-type reference lines is insufficient. When the number of map reference lines is insufficient, it may cause gaps or deviations in path planning, affecting driving safety. Through perception-type reference lines, the vehicle can accurately identify road features in the surrounding environment based on environmental perception data, thereby supplementing the deficiencies of map reference lines and improving the accuracy and reliability of path planning. Therefore, when the number of map-type reference lines is lower than the preset number, perception-type reference lines can be selected for path planning.

[0081] (5) Road information is used to indicate that the exploration distance ahead of the vehicle is less than a preset distance.

[0082] The exploration distance is determined by the maximum distance of the road information ahead of the vehicle that can be obtained based on the map information.

[0083] It is understandable that if the exploration distance ahead of the vehicle is lower than the preset distance, it means that the map data cannot provide enough information about the road ahead to reflect the real-time changes in the environment. Through the perception type reference line, the vehicle can obtain the road ahead information in real time based on the environmental perception data, making up for the lack of map data, thereby ensuring that the path planning is more accurate and safe. Therefore, when the exploration distance ahead of the vehicle is lower than the preset distance, the perception type reference line can be selected for path planning.

[0084] It should be noted that the positioning information in the second preset condition is used to indicate that there is an abnormality in the positioning of the vehicle, the positioning information is used to indicate that the vehicle has not performed positioning initialization processing, and the positioning information is used to indicate that the positioning error of the vehicle is higher than the preset error range, all of which can indicate that the positioning of the vehicle is unavailable.

[0085] In other embodiments, the type with the highest priority may be selected as the target type from the perception type and the map type of the reference line according to the driving data.

[0086] For example, when the driving data satisfies both the first preset condition and the second preset condition, the type with the highest priority can be selected as the target type from the perception type and the map type of the reference line according to the driving data. Alternatively, when the intelligent driving mode information is used to indicate that the vehicle is in cruise mode, the type with the highest priority can be selected as the target type from the perception type and the map type of the reference line according to the driving data.

[0087] In one example, when the driving data meets the third preset condition, the priority of the map type is higher than the priority of the perception type.

[0088] The third precondition includes any one of the following:

[0089] (1) The reference line information is used to indicate that the confidence level of the reference line of the perception type is lower than a first preset confidence level.

[0090] It is understandable that if the confidence of the reference line of the perception type is lower than the first preset confidence, it means that the environmental perception data is affected by factors such as environmental noise, sensor performance, weather conditions, etc., resulting in a low confidence of the reference line of the perception type. If path planning is performed based on the reference line of the perception type with low confidence, misidentification, information loss, or misinterpretation of the local environment may occur, making the path planning inaccurate. Therefore, when the confidence of the reference line of the perception type is lower than the first preset confidence, the priority of the map type can be set to be higher than the priority of the perception type, and the reference line of the map type with the highest priority can be selected for path planning.

[0091] In other embodiments, in addition to the need for the reference line information to indicate that the confidence of the reference line of the perception type is lower than the first preset confidence, it is also necessary to indicate that the confidence of the reference line used for path planning for the vehicle at the last moment is higher than the second preset confidence. The second preset confidence is higher than the first preset confidence. For example, the first preset confidence is 0.3 and the second preset confidence is 0.7.

[0092] It can be understood that by setting two preset confidences, and the second preset confidence is higher than the first preset confidence, the reference line of the map type will be switched only when the confidence of the reference line of the perception type at the previous moment is higher than the second preset confidence, and the confidence of the reference line of the perception type at the current moment is lower than the first preset confidence. This method avoids switching to the reference line of the map type immediately when the confidence of the reference line of the perception type rises slightly, and maintains the stability of the vehicle.

[0093] (2) Road information is used to indicate that the road the vehicle is on is an unstructured road.

[0094] Among them, unstructured roads, also known as heavy-map areas, refer to the complex road conditions encountered by vehicles in cities or highways when driving with the navigation assistance function (navigate on autopilot, NOV). Complex road conditions include a large number of diverging and merging, on- and off-ramps, etc. These scenes have the characteristics of non-parallel lane lines, non-unique driving directions, and variable lane widths. In addition, unstructured roads can also refer to sections that lack clear and stable road features and signs.

[0095] It is understandable that when a vehicle is on an unstructured road, the environmental perception data is prone to misjudgment due to the ambiguity or dynamic changes of the road. Map data can provide stable and reliable road information, which helps the vehicle to accurately plan its path in a complex or unknown road environment. Therefore, when the road the vehicle is on is an unstructured road, the priority of the map type can be set higher than the priority of the perception type, and the reference line of the map type with the highest priority can be selected for path planning.

[0096] (3) Road information is used to indicate that there is a divergence and merging area within a preset distance range ahead of the vehicle on the road.

[0097] The preset distance range may be 0-100 meters or other ranges, and the present application does not specifically limit the preset distance range.

[0098] Understandably, in the divergent merging area, the vehicle needs to make more complex driving decisions, such as choosing the correct lane, adjusting the driving route, etc. Based on map data, the vehicle can analyze the road information within a preset distance range ahead in advance, so that the vehicle can complete the path planning before entering the divergent merging area, and have enough time to make corresponding adjustments. The environmental perception data is collected in real time and relies on the sensor's immediate perception of the vehicle's surroundings. It cannot provide comprehensive environmental information before driving to the divergent merging area to plan the path in advance. Therefore, in the case that there is a divergent merging area within a preset distance range ahead of the vehicle, the priority of the map type can be set to be higher than the priority of the perception type, and the reference line of the map type with the highest priority can be selected for path planning.

[0099] In another example, when the driving data meets the fourth preset condition, the priority of the perception type is higher than the priority of the map type.

[0100] The fourth precondition includes any one of the following:

[0101] (1) The reference line information is used to indicate that the matching relationship between the perception type reference line and the map type reference line is mismatched.

[0102] The matching relationship is used to indicate whether the environmental perception data used to generate the reference line of the perception type matches the map data used to generate the reference line of the map type.

[0103] It is understandable that if the matching relationship between the reference line of the perception type and the reference line of the map type is not matched, it means that there is a difference between the environmental perception data used to generate the reference line of the perception type and the map data used to generate the reference line of the map type. This indicates that the actual road data of the road where the vehicle is located has changed, and the road data included in the map data has not been adjusted accordingly, that is, the map data is inaccurate. Therefore, in the case where the matching relationship between the reference line of the perception type and the reference line of the map type is not matched, the priority of the perception type can be set to be higher than the priority of the map type, and the reference line of the perception type with the highest priority can be selected for path planning.

[0104] In other embodiments, when the driving data satisfies the fifth preset condition, the type of the reference line used for path planning of the vehicle at the last moment is determined as the target type.

[0105] The fifth precondition includes any one of the following:

[0106] (1) When a vehicle is in the process of changing lanes, the road information is used to indicate that the lane line of the road where the vehicle is located is crossed by the vehicle.

[0107] It is understandable that when a vehicle changes lanes through a lane change assist function (such as the UDLC function or the ALC function) or avoids an obstacle, the vehicle may run over the lane line of the road where the vehicle is located within a certain period of time. In order to reduce the shaking of the vehicle, the switching of the reference line type can be suppressed during this process, that is, the type of reference line used for path planning for the vehicle at the last moment continues to be used.

[0108] (2) When the vehicle is in the process of changing lanes, the positioning information is used to indicate that the vehicle is in a positioning ambiguity state.

[0109] The positioning fuzzy state is used to indicate that the positioning accuracy of the vehicle is lower than the preset accuracy.

[0110] It is understandable that if the positioning accuracy of the vehicle is lower than the preset accuracy, it means that the current position of the vehicle is relatively vague. When the vehicle is in the process of changing lanes, if the positioning accuracy is low, the type of reference line selected at the current moment is inconsistent with the type of reference line at the previous moment, which may not produce the expected effect. Instead, it may cause inaccurate control of the vehicle in terms of steering, speed adjustment, etc., and even cause vehicle instability. Therefore, when the vehicle is in the process of changing lanes, the positioning information is used to indicate that the vehicle is in a state of ambiguous positioning, and the switching of the reference line type is suppressed, that is, the type of reference line used for path planning for the vehicle at the previous moment continues to be used.

[0111] As a possible implementation method, whether the vehicle is in the process of changing lanes can be determined based on the following mathematical expression (1).

[0112]

[0113] Among them, S lc =1 means the vehicle is in the process of changing lanes, S lc =0 may indicate that the vehicle is not in the process of changing lanes; S lcs Indicates the lane-changing status of the vehicle.

[0114] The lane change status flag of the vehicle may include a standby flag, a lane change activation flag, a lane change execution flag, a lane change rollback flag, a lane change completion flag, a system takeover flag, a waiting state flag, a shutdown flag, a fault flag, a lane change cancellation flag, a lane change inhibition flag, a driver-triggered rollback flag, and a system-triggered rollback flag. The standby flag may be represented by 0, the lane change activation flag may be represented by 1, the lane change execution flag may be represented by 2, the lane change rollback flag may be represented by 3, the lane change completion flag may be represented by 4, the system takeover flag may be represented by 5, the waiting state flag may be represented by 6, the shutdown flag may be represented by 7, the fault flag may be represented by 8, the lane change cancellation flag may be represented by 9, the lane change inhibition flag may be represented by 10, the driver-triggered rollback flag may be represented by 11, and the system-triggered rollback flag may be represented by 12.

[0115] Based on the above S101-S102, the present application provides a method for determining reference lines in path planning, which can comprehensively judge whether the reference lines used in path planning are of perception type or map type based on the intelligent driving mode information, road information, positioning information, reference line information and other information in the vehicle's driving data. This method comprehensively considers multiple information and can more comprehensively evaluate the current driving environment and conditions, thereby selecting the most appropriate reference line for path planning, reducing misjudgments and planning errors caused by relying on a single reference line, and improving the accuracy of path planning.

[0116] In some embodiments, before determining the target type from the perception type and map type of the reference line according to the driving data, the perception type reference line and the map type reference line may be preprocessed to unify the output form of the reference line, so that the vehicle can switch between different types of reference lines more smoothly. Figure 2 As shown, the method for determining a reference line in path planning provided by the embodiment of the present application further includes the following steps:

[0117] S201: Matching processing is performed on a reference line of the perception type and a reference line of the map type, so that the attributes included in the reference line of the perception type match the attributes included in the reference line of the map type.

[0118] As a possible implementation method, matching processing of the perception type reference line and the map type reference line includes: matching processing of the perceived travel direction in the attributes included in the perception type reference line with the map travel direction in the attributes included in the map type reference line, and transferring attributes of the attributes included in the perception type reference line and the attributes included in the map type reference line.

[0119] In one example, the perceived travel direction in the attributes included in the reference line of the perception type and the map travel direction in the attributes included in the reference line of the map type may be matched based on the correspondence between the perceived travel direction and the map travel direction.

[0120] Among them, the perceived traffic direction includes three directions, namely, straight, left lane change, and right lane change. The map traffic direction includes ten directions, namely, straight, straight left divergence, straight right divergence, left lane change, left-left divergence, left-right divergence, right lane change, right-left divergence, right-right divergence, left advance, and right advance. The corresponding relationship between the perceived traffic direction and the map traffic direction includes: the corresponding relationship between the perceived traffic direction of straight and the map-perceived direction of straight, straight left divergence, and straight right divergence, the corresponding relationship between the perceived traffic direction of left lane change and the map-perceived direction of left lane change, left-left divergence, and left-right divergence, and the corresponding relationship between the perceived traffic direction of right lane change and the map-perceived direction of right lane change, right-left divergence, and right-right divergence.

[0121] It should be noted that since the positions of the left advance and the right advance are usually far away from the current position of the vehicle, these long-distance advance information usually do not affect the current lane change decision, so the left advance and the right advance do not need to be matched.

[0122] like Figure 3 As shown, the vehicle is traveling in the lane where reference line 0 is located. The perceived direction of reference line 0 is straight ahead, the perceived direction of reference line 3 is left lane change, and the perceived direction of reference line 6 is right lane change. Figure 4 As shown, the vehicle is in the lane where reference line 0 is located. The sensed traffic direction of reference line 0 is straight ahead, the sensed traffic direction of reference line 2 is straight ahead right divergence, and the sensed traffic direction of reference line 6 is right lane change. Figure 5 As shown, the vehicle is in the lane where reference line 0 is located, the perceived travel direction of reference line 0 is straight ahead, the perceived travel direction of reference line 3 is left lane change, and the perceived travel direction of reference line 10 is right ahead.

[0123] In another example, the attributes required for transferring the attributes included in the perception-type reference line and the attributes included in the map-type reference line include: the exploration distance ahead of the road where the vehicle is located, the distance between the lane and the divergence and confluence area ahead of the road where the vehicle is located, the position and direction of the divergence and confluence area ahead of the road where the vehicle is located, and the priority of the reference line. In this way, the vehicle can identify the divergence and confluence area ahead of the road where the vehicle is located, whether based on the perception-type reference line or the map-type reference line, so as to complete the lane change in advance.

[0124] Based on the above S201, the perception type reference line and the map type reference line can be matched to make the attributes included in the perception type reference line match the attributes included in the map type reference line, and the output form of the reference line can be unified, so that the vehicle can switch between different types of reference lines more smoothly.

[0125] In some embodiments, in order to obtain the driving data of the vehicle, the above S101 can be specifically implemented as the steps in the following examples. The following is an exemplary description of the process of obtaining the driving data of each vehicle.

[0126] (1) Intelligent driving mode information

[0127] ①The vehicle is in cruise mode

[0128] As a possible implementation, the vehicle may be determined to be in cruise mode when the number of perceived center lines and the number of map center lines are both zero. The perceived center line is generated based on environmental perception data of the road on which the vehicle is located; and the map center line is generated based on map data of the road on which the vehicle is located.

[0129] Exemplarily, it can be determined that the vehicle is in cruise mode based on the following mathematical expression (2).

[0130] S mpf =0 ((C m =0)∧(C p =0)) (2)

[0131] Among them, S mpf =0 means the vehicle is in cruise mode, C m =0 can indicate that the number of perceived center lines is zero; C p =0 may indicate that the number of map center lines is zero.

[0132] ②The vehicle is in pilot mode

[0133] As a possible implementation, the vehicle may be determined to be in the pilot mode when the number of perceived center lines is zero and the top-level state machine for controlling and managing the entire vehicle behavior determines that the vehicle may be in the pilot mode.

[0134] Exemplarily, it can be determined that the vehicle is in the pilot mode based on the following mathematical expression (3).

[0135]

[0136] Among them, S mpf =2 means the vehicle is in cruise mode; S s =2 may indicate that the top-level state machine determines that the vehicle may be in pilot mode.

[0137] In addition, the top-level state machine can determine whether the vehicle can be in the pilot mode based on the distance between the vehicle's current location and the navigation target (destination).

[0138] Exemplarily, the top-level state machine may determine whether the vehicle can be in pilot mode based on the following mathematical expression (4).

[0139]

[0140] Among them, S N =0 means the vehicle cannot be in pilot mode; S N =1 can indicate that the vehicle can be in pilot mode;

[0141] D me D is the distance between the vehicle's current location and the navigation target (destination); meL It is the distance limit between the vehicle's current position and the navigation target (destination).

[0142] For example, based on the above mathematical expression (4), S N =0, the vehicle can issue a warning and enter cruise mode.

[0143] Exemplarily, the top-level state machine determines that the vehicle can be in the pilot mode only when the jump of the signal that the vehicle can be in the pilot mode is maintained for a preset time, and then it can be determined that the vehicle can be in the pilot mode. For example, the preset time can be 500 milliseconds.

[0144] (2) Road information

[0145] ①Whether the road the vehicle is on is an unstructured road

[0146] Exemplarily, whether the road where the vehicle is located is an unstructured road can be determined based on the following mathematical expression (5).

[0147]

[0148] Among them, S mp =1 means that the road the vehicle is on is an unstructured road; S mp=0 can indicate that the road where the vehicle is located is not an unstructured road; S on It can indicate that the vehicle is in navigation state; D re It can represent the distance between the vehicle and the ramp in front of the road where the vehicle is located; K re is the set distance threshold; S ir =1 can indicate that the vehicle is on the ramp; S er =1 may indicate that the vehicle is at the ramp exit.

[0149] It should be noted that the above-mentioned ramps may include service areas, toll stations and other scenes.

[0150] ②Whether the lane line of the road where the vehicle is located is crossed by other vehicles

[0151] As a possible implementation method, it can be determined whether the lane line of the road where the vehicle is located is pressed by the vehicle when the vehicle is in the process of changing lanes based on the a0 coefficient of the left lane line of the road where the vehicle is located and the a0 coefficient of the right lane line of the road where the vehicle is located.

[0152] Exemplarily, whether the lane line of the road where the vehicle is located is crossed by the vehicle can be determined based on the following mathematical expression (6).

[0153]

[0154] Among them, S rol =1 may indicate that the lane line of the road where the vehicle is located is pressed by the vehicle; S rol =0 can indicate that the lane line of the road where the vehicle is located is not pressed by the vehicle; ll a0 The a0 coefficient of the left lane line of the road where the vehicle is located; rl a0 It can represent the a0 coefficient of the right lane line of the road where the vehicle is located; l1 is the first line pressure threshold, which can be determined according to the width of the vehicle, for example, l1 can be 1.0; l1 is the second line pressure threshold, which can be determined according to the width of the vehicle, for example, r1 can be 1.0.

[0155] (3) Positioning information

[0156] The positioning information may be fused positioning information. Fusion positioning can provide the positioning information of the vehicle for map data, and the positioning information of the vehicle includes the location of the vehicle, so as to determine the map data around the vehicle according to the location of the vehicle. In addition, fusion positioning usually adjusts the positioning information of the vehicle according to the reference line of the perception type and the area (freespace) where the vehicle can pass safely provided by sensors such as laser radar.

[0157] As a possible implementation, it is possible to determine whether the vehicle's positioning is abnormal, whether the vehicle is performing positioning initialization processing, and whether the vehicle's positioning error is higher than a preset error range based on the status identifier of the positioning information. In other words, it is possible to determine whether the vehicle's positioning is available based on the status identifier of the positioning information.

[0158] Among them, the status identifier of the positioning information may include an invalid identifier, an uninitialized identifier, a positioning abnormality identifier, a global navigation satellite system (GNSS) filter positioning identifier, a first fused positioning identifier, and a second fused positioning identifier. When the status identifier of the positioning information is the first fused positioning identifier, the positioning of the vehicle's lateral position (i.e., the position of the vehicle in the left and right directions) is valid. When the status identifier of the positioning information is the second fused positioning identifier, the positioning of the vehicle's lateral position and longitudinal position are both valid. For example, the invalid identifier is represented by 0, the uninitialized identifier is represented by 1, the positioning abnormality identifier is represented by 2, the GNSS filter positioning identifier is represented by 3, the first fused positioning identifier is represented by 4, and the second fused positioning identifier is represented by 5.

[0159] Exemplarily, based on the status identification of the above positioning information, it can be determined whether the positioning of the vehicle is available based on the following mathematical expression (7).

[0160]

[0161] Among them, S loc_good =0 means the vehicle positioning is unavailable; S loc_good =1 means the vehicle positioning is available; S loc It is the status mark of the positioning information; d lat is the deviation between the current position of the vehicle and the predicted position in the positioning information; a0 It is the a0 coefficient of the left lane line of the current position of the vehicle and the a0 coefficient of the right lane line of the road the vehicle is currently on. The a0 coefficient is usually a parameter that reflects the geometry of the lane line and represents the initial position or offset of the lane line.

[0162] (4) Reference line information

[0163] ①Confidence of the reference line of the perception type

[0164] As a possible implementation method, the perception type reference line is generated in real time and is easily affected by factors such as vehicle posture, weather, and lighting. Therefore, the confidence of the perception type reference line can be determined based on parameters related to the perception type reference line, such as the length of the perception type reference line, the far end lateral yaw distance, and the short-term heading change rate.

[0165] Among them, the far-end lateral runout distance refers to the lateral offset of the far-end position of the reference line of the perception type relative to the current position of the vehicle during the vehicle's driving process. The far-end lateral runout distance can be used to reflect the degree of deviation of the reference line of the perception type relative to the vehicle. The short-term heading change rate refers to the rate at which the vehicle's heading angle (i.e., the vehicle's forward direction) changes in a short period of time. The short-term heading change rate can be used to reflect the speed at which the vehicle's direction changes.

[0166] ②Matching relationship between perception type reference lines and map type reference lines

[0167] As a possible implementation, it may be determined whether the reference line of the perception type matches the reference line of the map type based on the freespace, the map centerline, the reference line of the perception type, and the reference line of the map type, wherein the map centerline is generated based on the map data of the road where the vehicle is located.

[0168] For example, Figure 6 As shown, first, collision detection can be performed on freespace and the center line of the map. If there is a collision risk between freespace and the center line of the map, it can be determined that the matching relationship between the reference line of the perception type and the reference line of the map type is mismatched. If there is no collision risk between freespace and the center line of the map, then the map center line and the reference line of the perception type are subjected to line pressure detection. If there is no line pressure risk between the map center line and the reference line of the perception type, it can be determined that the matching relationship between the reference line of the perception type and the reference line of the map type is matched. If there is a line pressure risk between the map center line and the reference line of the perception type, then the lateral deviation calculation is performed on the reference line of the map type and the reference line of the perception type. If the lateral deviation between the reference line of the map type and the reference line of the perception type is within the preset deviation range, it can be determined that the matching relationship between the reference line of the perception type and the reference line of the map type is matched. If the lateral deviation between the reference line of the map type and the reference line of the perception type is not within the preset deviation range, it can be determined that the matching relationship between the reference line of the perception type and the reference line of the map type is mismatched.

[0169] The following is an exemplary description of the collision detection between the freespace and the center line of the map.

[0170] like Figure 7 As shown, curve C m is the center line of the map, (x fi ,y fi ) is the freespace coordinate point, L mfcL is the lateral collision limit.

[0171] For example, it is possible to determine whether there is a collision risk between the freespace and the centerline of the map based on the number of coordinates where the freespace collides with the centerline of the map. Specifically, it is possible to determine whether there is a collision risk between the freespace and the centerline of the map based on the following mathematical expressions (8) to (11).

[0172]

[0173] L mfci =XYToSL{(x fi ,y fi ),C m} (11)

[0174] Among them, C mf =0 may indicate that there is a risk of collision between the freespace and the center line of the map; C mf =1 means there is no collision risk between freespace and map centerline; N mfcL N is the threshold value of the number of coordinates that collide with the center line of the map; mfc is the number of coordinates where the freespace collides with the center line of the map; k is the number of coordinate points in the freespace; S mfci Is the distance between the coordinate point of the i-th freespace and the center line of the map within the lateral collision limit? mfci = 0 means that the distance between the coordinate point of the i-th freespace and the center line of the map is within the lateral collision limit; S mfci =1 means that the distance between the coordinate point of the i-th freespace and the center line of the map is not within the lateral collision limit; L mfci is the horizontal coordinate value of the coordinate point of the i-th freespace with the center line of the map as the baseline in the Frenet coordinate system; XYToSL is a function for calculating the horizontal coordinate value of the coordinate point of the i-th freespace with the center line of the map as the baseline in the Frenet coordinate system.

[0175] It should be noted that N mfcL It can be determined based on the quality and density of the freespace.

[0176] The following is an illustrative description of the line pressure detection of the map center line and the reference line of the perception type.

[0177] like Figure 8 As shown, curve l pl The left reference line of the perception type; the curve l pr The right reference line of the perception type; L mppLIt is the horizontal pressure line limit.

[0178] For example, it is possible to determine whether the map centerline and the perception type reference line have a risk of overlapping according to the number of coordinates of the map centerline and the perception type reference line that have overlapping problems. Specifically, it is possible to determine whether the map centerline and the perception type reference line have a risk of overlapping based on the following mathematical expressions (12) to (15).

[0179]

[0180] L mppi =XYToSL{(x pli ,y pli ),C m} (15)

[0181] Among them, P mp =0 may indicate that there is a risk of overlapping between the map centerline and the reference line of the perception type; P mp =1 means that there is no risk of overlapping the map center line and the reference line of the perception type; N mppL N is the coordinate number threshold for the map centerline and the reference line of the perception type that have line overlap problems; mfc is the number of coordinates with overlapping problems between the map center line and the reference line of the perception type; k is the number of coordinate points of the reference line of the perception type; S mppi Whether the distance between the coordinate point of the reference line of the i-th perception type and the center line of the map is within the horizontal pressure line limit; S mppi = 0 may indicate that the distance between the coordinate point of the reference line of the i-th perception type and the center line of the map is within the horizontal pressure line limit; S mfci =1 can indicate that the distance between the coordinate point of the reference line of the i-th perception type and the center line of the map is not within the horizontal pressure line limit; L mppi is the horizontal coordinate value of the coordinate point of the reference line of the i-th perception type with the center line of the map as the baseline in the Frenet coordinate system; XYToSL is a function for calculating the horizontal coordinate value of the coordinate point of the reference line of the i-th perception type with the center line of the map as the baseline in the Frenet coordinate system.

[0182] It should be noted that the perception type reference line includes the left reference line of the perception type and the right reference line of the perception type. When performing line pressure detection on the map center line and the perception type reference line, it is necessary to perform line pressure detection on the map center line and the left reference line of the perception type, and on the map center line and the right reference line of the perception type. The above example only performs line pressure detection on the map center line, one of the reference lines on the side of the perception type.

[0183] The following is an exemplary description of the calculation of lateral deviations for map-type reference lines and perception-type reference lines.

[0184] like Fig. 9 As shown, curve l pl The left reference line of the perception type; the curve l pr The right reference line of the perception type; curve C m is the center line of the map; curve l ml It is the left reference line of the map type; curve l mr It is the right reference line of the map type.

[0185] For example, it can be based on the following mathematical expressions (16)-(18):

[0186]

[0187] L mpli =XYToSL{(x pli ,y pli ),l ml} (18)

[0188] Among them, S mplL is the lateral deviation between the reference line of the map type and the reference line of the perception type; S mplL =0 may indicate that the lateral deviation between the reference line of the map type and the reference line of the perception type is within the preset deviation range; S mplL =1 may indicate that the lateral deviation between the reference line of the map type and the reference line of the perception type is not within the preset deviation range; L mplL L is the lateral deviation limit between the reference line of the map type and the reference line of the perception type; mplm is the average lateral deviation between the reference line of the map type and the reference line of the perception type; N pe L is the number of coordinate points within the effective length of the reference line of the perception type; mpli is the horizontal coordinate value of the coordinate point of the reference line of the i-th perception type in the Frenet coordinate system with the reference line of the map type as the baseline;

[0189] XYToSL is a function for calculating the horizontal coordinate value of the coordinate point of the reference line of the i-th perception type with the reference line of the map type as the baseline in the Frenet coordinate system.

[0190] In some embodiments, if the target type is different from the type of reference line used for path planning for the vehicle at the previous moment, a large lateral position offset may occur when the vehicle path is planned based on the reference line of the target type. In order to avoid large lateral shaking of the vehicle, it is also necessary to perform lateral deviation detection on the reference line of the target type and the reference line used for path planning for the vehicle at the previous moment.

[0191] For example, Fig.10 As shown, C m (k) is the reference line of the target type, and the target type is the map type; C p (k-1) is the type of reference line used for vehicle path planning at the last moment. The type of reference line used for vehicle path planning at the last moment is the perception type; k v is the time distance coefficient; L mpcv It is the lateral deviation at the time distance between the reference line of the target type and the reference line used for path planning of the vehicle at the previous moment.

[0192] The lateral deviation at the time distance between the reference line of the target type and the reference line used for path planning of the vehicle at the previous moment can be determined based on the following mathematical expression (19).

[0193] L mpcv =XYToSL{(x pcv (k-1),y pcv (k-1)),C m (k)} (19)

[0194] Among them, (x pcv (k-1),y pcv (l-1)) is the coordinate of the reference line used for vehicle path planning at the previous moment at the time distance.

[0195] According to the lateral deviation of the reference line of the target type and the reference line used for path planning of the vehicle at the last moment at the time interval, it can be determined whether the reference line of the target type and the reference line used for path planning of the vehicle at the last moment will cause a large lateral shaking of the vehicle. Exemplarily, the lateral deviation state of the type of the target type and the type of the reference line used for path planning of the vehicle at the last moment can be shown as the following expression (20).

[0196]

[0197] Among them, S mpcL = 0 can indicate that the lateral deviation between the reference line of the target type and the reference line used for path planning of the vehicle at the last moment will not cause a large lateral shaking of the vehicle; S mpcL= 0 may indicate that the lateral deviation between the reference line of the target type and the reference line used for path planning of the vehicle at the last moment may cause a large lateral shaking of the vehicle; L mpcL It is the lateral deviation limit at the time distance between the reference line of the target type and the reference line used for path planning of the vehicle at the previous moment.

[0198] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the reference line determination device in the path planning (for the convenience of description, hereinafter referred to as the determination device) or the vehicle includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0199] The embodiment of the present application can exemplarily divide the functional modules of the determination device or vehicle according to the above method. For example, the determination device or vehicle may include various functional modules corresponding to the various functional divisions, or two or more functions may be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0200] Fig.11 is a block diagram of a device for determining a reference line in path planning according to an exemplary embodiment. Fig.11 The determining device 1100 includes: an acquiring unit 1101 and a determining unit 1102.

[0201] In a possible implementation, the acquisition unit 1101 is used to acquire the driving data of the vehicle during the driving of the vehicle; the driving data includes at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information. The determination unit 1102 is used to determine the target type from the perception type and map type of the reference line according to the driving data, so as to plan the path of the vehicle based on the target reference line of the target type; the reference line of the map type is generated based on the map data of the road where the vehicle is located, and the reference line of the perception type is generated based on the environmental perception data of the road where the vehicle is located.

[0202] According to the above technical means, the present application provides a device for determining reference lines in path planning, which can comprehensively judge whether the reference line used in path planning is of perception type or map type based on various information such as intelligent driving mode information, road information, positioning information, reference line information, etc. in the vehicle's driving data. This method comprehensively considers various information and can more comprehensively evaluate the current driving environment and conditions, thereby selecting the most appropriate reference line for path planning, reducing misjudgments and planning errors caused by relying on a single reference line, and improving the accuracy of path planning.

[0203] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0204] Fig.12 FIG. 1 is a block diagram of a vehicle according to an exemplary embodiment. Fig.12 As shown, vehicle 1200 includes, but is not limited to, a processor 1201 and a memory 1202 .

[0205] The memory 1202 is used to store executable instructions of the processor 1201. It can be understood that the processor 1201 is configured to execute instructions to implement the method for determining the reference line in path planning in the above embodiment.

[0206] It should be noted that those skilled in the art can understand that Fig.12 The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and the vehicle may include Fig.12 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0207] The processor 1201 is the control center of the vehicle, which uses various interfaces and lines to connect various parts of the entire vehicle, and executes various functions of the vehicle and processes data by running or executing software programs and / or modules stored in the memory 1202, and calling data stored in the memory 1202, so as to monitor the vehicle as a whole. The processor 1201 may include one or more processing units. Optionally, the processor 1201 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1201.

[0208] The memory 1202 may be used to store software programs and various data. The memory 1202 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 1202 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0209] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1202 including instructions, and the above instructions can be executed by the processor 1201 of the vehicle 1200 to implement the method for determining the reference line in the path planning in the above embodiment.

[0210] In actual implementation, Fig.11 The functions of the acquisition unit 1101 and the determination unit 1102 in Fig.12 The processor 1201 in the embodiment calls the computer program stored in the memory 1202 to implement. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0211] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0212] In an exemplary embodiment, the embodiment of the present application also provides a computer program product including one or more instructions, which can be executed by the processor 1201 of the vehicle to complete the method for determining the reference line in the path planning in the above embodiment.

[0213] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the vehicle's processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0214] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0215] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0216] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0217] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0218] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0219] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining a reference line in path planning, characterized in that: The method comprises: During the driving of the vehicle, the driving data of the vehicle is obtained; the driving data includes at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information; According to the driving data, a target type is determined from a perception type and a map type of a reference line, so as to plan a path for the vehicle based on a target reference line of the target type; the reference line of the map type is generated based on map data of a road on which the vehicle is located, and the reference line of the perception type is generated based on environmental perception data of the road on which the vehicle is located.

2. The method according to claim 1, characterized in that When the driving data satisfies a first preset condition, the target type is the map type; The first preset condition includes any one of the following: The road information is used to indicate that the road where the vehicle is located has no lane line; The road information is used to indicate that the wear degree of the lane line of the road where the vehicle is located exceeds a preset wear degree range; The intelligent driving mode information is used to indicate that the vehicle is in a pilot mode.

3. The method according to claim 1, characterized in that When the driving data satisfies a second preset condition, the target type is the perception type; The second preset condition includes any one of the following: The positioning information is used to indicate that an abnormality has occurred in the positioning of the vehicle; The positioning information is used to indicate that the vehicle has not been subjected to positioning initialization processing; The positioning information is used to indicate that the positioning error of the vehicle is higher than a preset error range; The reference line information is used to indicate that the number of reference lines of the map type is lower than a preset number; The road information is used to indicate that the exploration distance ahead of the road where the vehicle is located is lower than a preset distance; the exploration distance is determined based on the maximum distance of the road information ahead of the vehicle that can be obtained based on map information.

4. The method according to claim 1, characterized in that: The determining the target type from the perception type and the map type of the reference line according to the driving data includes: According to the driving data, a type with the highest priority is selected from the perception type and the map type of the reference line as the target type.

5. The method according to claim 4, characterized in that When the driving data meets the third preset condition, the priority of the map type is higher than the priority of the perception type. The third preset condition includes any one of the following: The reference line information is used to indicate that the confidence level of the reference line of the perception type is lower than a preset confidence level; The road information is used to indicate that the road on which the vehicle is located is an unstructured road; The road information is used to indicate that there is a divergence and merging area within a preset distance range in front of the road where the vehicle is located.

6. The method according to claim 4, characterized in that When the driving data satisfies a fourth preset condition, the priority of the perception type is higher than the priority of the map type; The fourth preset condition includes any one of the following: The reference line information is used to indicate that the matching relationship between the reference line of the perception type and the reference line of the map type is mismatched; the matching relationship is used to indicate whether the environmental perception data used to generate the reference line of the perception type matches the map data used to generate the reference line of the map type.

7. The method according to claim 1, characterized in that The determining the target type from the perception type and the map type of the reference line according to the driving data includes: When the driving data satisfies a fifth preset condition, determining the type of the reference line used for path planning of the vehicle at a previous moment as the target type; The fifth preset condition includes any one of the following: When the vehicle is in the process of changing lanes, the road information is used to indicate that a lane line of the road where the vehicle is located is pressed by the vehicle; When the vehicle is in the process of changing lanes, the positioning information is used to indicate that the vehicle is in a positioning ambiguity state; the positioning ambiguity state is used to indicate that the positioning accuracy of the vehicle is lower than a preset accuracy.

8. The method according to any one of claims 1 to 7, characterized in that: Before determining the target type from the perception type and the map type of the reference line according to the driving data, the method further includes: A matching process is performed on the reference line of the perception type and the reference line of the map type, so that the attributes included in the reference line of the perception type match the attributes included in the reference line of the map type.

9. A device for determining a reference line in path planning, characterized in that: It includes an acquisition unit and a determination unit; The acquisition unit is used to acquire driving data of the vehicle during driving of the vehicle; the driving data includes at least one of the following: intelligent driving mode information, road information, positioning information, and reference line information; The determination unit is used to determine the target type from the perception type and the map type of the reference line according to the driving data, so as to plan the path of the vehicle based on the target reference line of the target type; the reference line of the map type is generated based on the map data of the road where the vehicle is located, and the reference line of the perception type is generated based on the environmental perception data of the road where the vehicle is located.

10. A vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a vehicle, the vehicle is capable of performing the method of any one of claims 1 to 8.

12. A computer program product, characterized in that The computer program product comprises computer instructions which, when executed on a vehicle, cause the vehicle to perform the method according to any one of claims 1 to 8.

Images