Method and device for generating reference line in automatic driving process

Abstract

The invention provides a reference line generation method and device in an automatic driving process, and the method comprises the steps: obtaining the number of lane lines at two sides of a current driving vehicle and the types of the lane lines, and determining the current lane of the vehicle according to the number of the lane lines and the types of the lane lines; determining a lane change trend according to a width difference between a first lane width of a lane where the vehicle is currently located and a second lane width after the vehicle travels along the current lane for a first preset duration; selecting one lane line from the currently identified lane lines as a reference line based on the lane where the vehicle is located and the lane change trend; and updating the width of the current driving lane based on the lane change trend, and generating a reference line based on the updated lane width and the reference line. According to the invention, the problem that the reference line is generated only for the conventional road scene in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and device for generating a reference line during an autonomous driving process. Background Art

[0002] The realization of intelligent driving functions requires the cooperation of multiple modules such as positioning, perception, prediction, decision-making, planning, and control. Among them, the generation of the reference path required for vehicle driving is a very critical part of the entire intelligent driving system. A reasonable path is a prerequisite for the vehicle to achieve safe and efficient intelligent driving functions. As the basic reference line for vehicle driving, the reference line of the intelligent driving vehicle is an important reference for the vehicle's autonomous driving process, and has an important impact on ensuring the safety and efficiency of vehicle traffic. However, the existing method for generating reference lines for autonomous driving is only for conventional road scenes, resulting in low effectiveness in generating reference lines in complex road scenes.

[0003] There is currently no effective solution to the above problems in the prior art. Summary of the invention

[0004] The present invention provides a method and device for generating a reference line during an autonomous driving process, so as to solve the problem in the prior art of only generating reference lines for conventional road scenes.

[0005] In a first aspect, the present application provides a method for generating a reference line during an autonomous driving process, comprising: obtaining the number of lane lines and the type of lane lines on both sides of a currently traveling vehicle, and determining the lane in which the vehicle is currently located based on the number of lane lines and the type of lane lines; determining a lane change trend based on a width difference between a first lane width of the lane in which the vehicle is currently located and a second lane width after the vehicle has traveled along the current lane for a first preset period of time; selecting a lane line from the currently identified lane lines as a baseline based on the lane in which the vehicle is located and the lane change trend; updating the width of the current driving lane based on the lane change trend, and generating the reference line based on the updated lane width and the baseline.

[0006] In a second aspect, the present application provides a device for generating a reference line during an automatic driving process, including: a first processing module, used to obtain the number of lane lines and the type of lane lines on both sides of a currently traveling vehicle, and determine the lane in which the vehicle is currently located based on the number of lane lines and the type of lane lines; a determination module, used to determine the lane change trend based on the width difference between the first lane width of the lane in which the vehicle is currently located and the second lane width after the vehicle has traveled along the current lane for a first preset period of time; a selection module, used to select a lane line from the currently identified lane lines as a baseline based on the lane in which the vehicle is located and the lane change trend; a second processing module, used to update the width of the current driving lane based on the lane change trend, and generate the reference line based on the updated lane width and the baseline.

[0007] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute the in-vehicle voice testing method described in the first aspect of the present application.

[0008] In a fourth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the vehicle-mounted voice testing method described in the first aspect of the present application.

[0009] In an embodiment of the present application, after determining the lane where the current vehicle is located by the number of lane lines and the type of lane lines currently obtained, the change trend of the lane where the current vehicle is located is then determined. Then, based on the change trend of the lane, a lane line is selected from the currently identified lane lines as the baseline. In addition, the width of the current driving lane is updated based on the lane change trend, and a reference line is generated based on the updated lane width and the baseline. It can be seen that in the embodiment of the present application, after determining the current lane of the vehicle, the corresponding reference line can be determined based on the change trend of the road and the lane width updated in real time, that is, in the embodiment of the present application, the generation of the reference line is not only for conventional road scenes, but can generate corresponding reference lines according to different road scenes, which not only enriches the scenes of autonomous driving, but also improves the safety of autonomous driving, thereby solving the problem of generating reference lines only for conventional road scenes in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a method for generating a reference line during an autonomous driving process provided by an embodiment of the present application;

[0011] Figure 2A flowchart of a method for generating an autonomous driving reference line based on multi-scenario recognition provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of the structure of a device for generating a reference line during an autonomous driving process provided by an embodiment of the present application;

[0013] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0015] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0016] The present application embodiment proposes a method for generating a reference line during an autonomous driving process, such as Figure 1 As shown, the steps of the method include:

[0017] Step 101, obtaining the number of lane lines and the type of lane lines on both sides of the current driving vehicle, and determining the lane the vehicle is currently in according to the number of lane lines and the type of lane lines;

[0018] In a specific example, take the example of a vehicle driving on eight lanes in both directions, and four lanes in one direction. The vehicle is driving in the leftmost lane. At this time, the vehicle can obtain the image in the foreground direction through the front camera, so as to extract the number of lane lines from the image, for example, four lane lines are extracted, including one solid line and three wide dashed lines. The above is just an example. The number of lane lines is different in different driving environments, and the types of lane lines are also different, such as lane lines of different colors, or lane lines for other purposes such as guide lines, special lane lines, etc.

[0019] Step 102, determining a lane change trend according to a width difference between a first lane width of a lane where the vehicle is currently located and a second lane width after the vehicle has traveled along the current lane for a first preset time period;

[0020] In the specific example, the first preset time can be set to 2s to 3s. It should be noted that the first preset time cannot be too long or too short, because the first preset time is too long or too short for automatic driving. By comparing the lane width of the current lane with the lane that may be passed after the first preset time, the lane change trend can be determined, that is, whether the lane change trend is from wide to narrow, from narrow to wide, or unchanged. Then, a suitable baseline can be selected according to the lane change trend to determine the accurate reference line, that is, the accurate reference line can be determined under different road environments. The reference line in the automatic driving scenario is a guide line used to guide the vehicle to drive safely and accurately, that is, the vehicle can drive automatically according to the reference line without the user operating the vehicle.

[0021] Step 103, based on the lane where the vehicle is located and the lane change trend, select a lane line from the currently identified lane lines as a reference line;

[0022] It can be seen that in the embodiment of the present application, a suitable baseline can be selected according to different lane change trends, and the baseline is used to generate a reference line. Since the reference line is different in different road scenes, the baseline is also different in different road environments. Through the above method, different baselines can be reasonably selected according to different road environments, so as to prepare for the subsequent accurate determination of the reference line.

[0023] Step 104 , updating the width of the current driving lane based on the lane change trend, and generating a reference line based on the updated lane width and the baseline.

[0024] After determining the baseline, the lane width needs to be updated according to the lane change trend. Because the lane width is also changing in real time when the road environment is complex, the lane width needs to be updated in real time so that an accurate reference line can be generated based on the determined baseline and real-time lane width.

[0025] Through the above steps 101 to 104, in the embodiment of the present application, after determining the lane where the current vehicle is located by the currently acquired number of lane lines and lane line types, the change trend of the lane where the current vehicle is located is further determined. Then, according to the change trend of the lane, a lane line is selected from the currently identified lane lines as the baseline. In addition, the width of the current driving lane is updated based on the lane change trend, and a reference line is generated based on the updated lane width and the baseline. It can be seen that in the embodiment of the present application, after determining the current lane of the vehicle, the corresponding reference line can be determined according to the change trend of the road and the lane width updated in real time, that is, the generation of the reference line in the embodiment of the present application is not only for conventional road scenes, but can generate corresponding reference lines according to different road scenes, which not only enriches the scenes of autonomous driving, but also improves the safety of autonomous driving, thereby solving the problem of only generating reference lines for conventional road scenes in the prior art.

[0026] In the embodiment of the present application, the lane where the current vehicle is located can be determined by the number of lane lines and the type of lane lines. Based on this, the method involved in the above step 101 of obtaining the number of lane lines on both sides of the current moving vehicle and the type of lane lines, and determining the lane where the vehicle is currently located according to the number of lane lines and the type of lane lines, can further include:

[0027] Step 11, determining a left lane line and a right lane line from the acquired lane lines, wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle;

[0028] It can be seen that the left and right lane lines in the embodiment of the present application refer to the lane lines on the left and right sides of the lane where the vehicle is currently located.

[0029] Step 12, when the first preset condition is met and the second preset condition is not met, determining that the vehicle is in the leftmost lane;

[0030] Step 13, when the second preset condition is met and the first preset condition is not met, determining that the vehicle is in the rightmost lane;

[0031] Step 14, when both the first preset condition and the second preset condition are satisfied, determining that the current driving environment of the vehicle is a single lane;

[0032] The first preset condition refers to that there is no lane line on the left side of the left lane line and the left lane line is a solid line, or the first preset condition refers to that there is no lane line on the left side of the left lane line and the lateral distance of the left roadside line is less than the first preset distance. The second preset condition refers to that there is no lane line on the right side of the right lane line and the right lane line is a solid line, or the second preset condition refers to that there is no lane line on the right side of the right lane line and the lateral distance of the right roadside line is less than the first preset distance.

[0033] Through the first preset condition and the second preset condition in the above-mentioned embodiment of the present application, it can be determined whether the current vehicle is in the leftmost lane, the rightmost lane or a single lane. After determining the lane where the current vehicle is located, a reasonable baseline can be determined based on the road change trend. For example, if the current vehicle is in the leftmost lane, and the current road change trend is that the lane is narrowing and the current lane is merging into the main road lane, the leftmost lane line can be used as the baseline, and a reference line can be generated based on the baseline, so that the autonomous driving vehicle can accurately merge into the main road. In a specific example, the first preset distance can be 3m, or it can be set accordingly according to actual needs.

[0034] In the embodiment of the present application, generally, when a lane changes, its lane width will also change accordingly. Therefore, in the embodiment of the present application, the lane change trend can be determined according to the change in lane width. Based on this, the method of determining the lane change trend according to the width difference between the first lane width of the lane where the vehicle is currently located and the second lane width after the vehicle has traveled along the current lane for a first preset time involved in the above step 102 can further include:

[0035] Step 21, determining the difference between the second lane width and the first lane width;

[0036] Step 22, when the difference is positive and the ratio of the difference to the first lane width is greater than a second preset threshold, determining that the lane change trend is from the current lane to the widened lane;

[0037] Step 23, when the difference is negative and the ratio of the absolute value of the difference to the first lane width is greater than a second preset threshold, determining that the lane change trend is from the current lane to the narrowed lane;

[0038] Step 24, when the lane change trend is from the current lane to the narrowed lane, and the width of the second lane is less than a third preset threshold, determining that the lane change trend is that the lane narrows and becomes a disappearing lane;

[0039] Step 25: When the difference is less than the fourth preset threshold, determine that the current driving lane has not changed.

[0040] It can be seen from the above steps 21 to 25 that if the lane width in front of the vehicle's current lane is greater than the lane width of the current vehicle, it can be determined that the lane change trend is from narrow to wide; if the lane width in front of the vehicle's current lane is less than the lane width of the current vehicle, it can be determined that the lane change trend is from wide to narrow. Furthermore, in the scenario where the lane change trend is from wide to narrow, there is also a special side road scenario, that is, in the process of the vehicle's road slowly narrowing, the lane may disappear. In addition, if the lane width in front of the vehicle's current lane is equal to the lane width of the current vehicle, it indicates that the current lane has not changed. It can be seen that in the embodiment of the present application, various road change trends encountered in the actual driving process are taken into account, that is, corresponding baselines can be generated according to various road change trends, thereby generating corresponding reference lines, so that the automatic driving scenario can adapt to various road scenarios.

[0041] In the embodiment of the present application, different reference lines are selected for different road change trends. Therefore, the method of selecting a lane line from the currently identified lane lines as the reference line based on the lane where the vehicle is located and the lane change trend involved in the above step 103 may further include:

[0042] Step 31, determining the road driving scene where the current vehicle is located according to the lane change trend;

[0043] Step 32, when the road driving scene remains unchanged, select the lane line with the highest confidence from all current lane lines as the baseline;

[0044] Step 33, when the road driving scene indicates that the vehicle is merging into the main road, the lane line on the side other than the wide dashed line is used as the reference line;

[0045] Step 34: When the road driving scene is characterized as a lane disappearing scene, the lane line on the lane disappearing side is used as a reference line.

[0046] In the embodiment of the present application, the confidence of the lane line is determined based on multiple attributes of the lane line, such as the clarity of the lane line obtained from the front camera, the degree of damage of the lane line, the length of the lane line, the distance from the vehicle, and other factors. Therefore, the higher the confidence, the higher the integrity of the lane line, which means that the clarity of the lane line in the acquired image is higher, the degree of damage of the lane line is lower, and the lane line is longer and closer to the vehicle. The confidence can be determined by the score. In a specific example, a weight can be set for each attribute, and then the score of each attribute is obtained based on the lane line in the image. The score is multiplied by the weight and then summed up. The highest score indicates the highest confidence. It can be seen that if the current lane does not change, such as a long straight lane, the lane line with a higher confidence can be used as the baseline of the current vehicle. For example, the lane line on the left side of the vehicle is more complete than the lane line on the right side of the vehicle, and it is also displayed more clearly in the image, so the lane line on the left side of the vehicle can be used as the baseline. For the scenario where the vehicle merges into the main road, the lane lines are usually solid on the left lane and dotted on the right lane. Therefore, the left lane is set as the baseline in this scenario. Because in this case, the dotted line will disappear when merging into the main road, while the solid line will always exist along the main road. Therefore, the solid line of the left lane is set as the baseline. When the reference line is generated based on the baseline later, the reference line will still exist.

[0047] In the embodiment of the present application, the method of determining the road driving scene of the current vehicle according to the lane change trend involved in the above step 31 may further include:

[0048] Step 41, when the vehicle is in the rightmost lane, the left lane line is a wide dashed line and the lane is narrowing, it is determined that the road driving scene is a scene of merging into the main road from the right;

[0049] Step 42, when the vehicle is in the leftmost lane, the right lane line is a wide dashed line and the lane is narrowing, determine that the road driving scene is a scene of merging into the main road from the left; wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle;

[0050] Step 43: After the lane is narrowed, the width of the second lane is less than a third preset threshold, and the road driving scene is determined to be a disappearing lane scene.

[0051] It can be seen that in the embodiments of the present application, the road driving scene can be determined according to the lane in which the current vehicle is located and the lane change trend. Specifically, several special scenes such as merging into the main road from the right, merging into the main road from the left, and disappearing lane can be determined. Then, the corresponding baseline is determined according to the road driving scene, so that the autonomous driving can adapt to different road scenes.

[0052] In the embodiment of the present application, the method of updating the width of the current driving lane based on the lane change trend involved in the above step 104, and generating a reference line based on the updated lane width and the baseline, may further include:

[0053] Step 51, when the lane change trend indicates that the road driving scene is unchanged, determining that the current lane width does not need to be updated;

[0054] Step 52, when the lane change trend indicates that the road driving scene is a scene of merging into the main road or a scene of disappearing lanes, the lane width is updated according to the comparison result between the current lane width and the preset threshold value, wherein, when the current lane width is greater than the fifth preset threshold value, the current lane width is updated to the fifth preset threshold value; when the current lane width is less than the sixth preset threshold value, the current lane width is updated to the sixth preset threshold value; when the current lane width is greater than the sixth preset threshold value and less than the fifth preset threshold value, there is no need to update the lane width; the sixth preset threshold value is less than the fifth preset threshold value;

[0055] Step 53, based on the reference line being translated to the middle of the lane by half the updated lane width, discrete points of the reference line are obtained, and the reference line is obtained by fitting based on the discrete points.

[0056] In a specific example, the value of the fifth preset threshold may be 4m, and the value of the sixth preset threshold may be 2.5m. Since the reference line is half the width of the lane shifted from the baseline to the middle of the lane, it is set to a certain value for lanes that are too wide (set to 4m if the lane width is greater than 4m) so that the vehicle can get as close to the baseline as possible to ensure the safety of autonomous driving; it is also set to a certain value for lanes that are too narrow (set to 2.5m if the lane width is less than 2.5m) to avoid driving accidents caused by the reference line being too close to the roadside.

[0057] The present application is explained below in conjunction with the specific implementation manner of an embodiment of the present application. The specific implementation manner provides a method for generating an autonomous driving reference line based on multi-scene recognition, which includes: a vehicle lane position judgment module, a lane width change trend judgment module, a scene recognition module, a line selection module, and a reference line generation module.

[0058] Among them, the lane position judgment module of the vehicle is used to calculate the number of lane lines to the left and right based on the left and right side lines of the vehicle, and at the same time combine the lane line types such as dotted lines, solid lines, wide dotted lines, etc. to judge the number of lanes in the current driving environment and determine whether the vehicle is in the outermost lane or in the middle lane.

[0059] The lane width change trend judgment module is used to calculate the current lane width based on the cubic polynomial coefficients of the left and right lane lines of the lane where the vehicle is located and preview the lane width change trend ahead. The current lane width can mainly be divided into a regular lane, an extra-wide lane or an overly narrow lane. By previewing the lane width change forward, the lane can be divided into a widening, narrowing or cut-off road.

[0060] The scene recognition module is used to combine the output results of the vehicle lane position judgment module and the lane width change trend judgment module to determine whether the vehicle is currently traveling in the outermost lane or an unconventional lane. At the same time, it can identify lane merging scenarios by combining the typical line features of the left and right lanes, such as wide dashed lines.

[0061] The line selection module is used to select the most reasonable lane line as the baseline among all lane lines based on the scene ID identified by the scene recognition module and the current output lane line situation, and maintain stable line selection when there is no significant difference in the scene ID.

[0062] The reference line generation module is used to generate discrete points by sampling according to the baseline selected by the line selection module, push the reference line discrete points to one side according to the updated road width, perform Kalman filtering, and finally obtain the fitted reference line cubic polynomial coefficients.

[0063] Based on the above modules, the method for generating an autonomous driving reference line based on multi-scene recognition in this specific implementation is as follows: Figure 2 As shown, the following steps are included:

[0064] In step 201, the lane position determination module of the vehicle sorts out all lane lines. The two lane lines closest to the vehicle in the lateral direction are the left and right lines, and the left and right lines are the left-left line and the right-right line respectively.

[0065] Condition 1: If the left-left line does not exist, the left line exists and is a solid line or the lateral distance to the left side of the road is less than 3m, then the left lane of the vehicle does not exist.

[0066] Condition 2: If the right line does not exist, the right line exists and is a solid line or the lateral distance from the right side of the road is less than 3m, it means that the right lane of the vehicle does not exist.

[0067] When condition one is met but condition two is not met, the vehicle is in the leftmost lane; when condition two is met but condition one is not met, the vehicle is in the rightmost lane; when condition one and condition two are met at the same time, the vehicle is in a single lane driving environment.

[0068] In step 202, the lane width change trend judgment module determines the current lane width level through the lateral position distance of the lane line and calculates the lateral position change amount based on the longitudinal distance when looking forward for 3 seconds to determine the lane change trend.

[0069] Condition 1: The current lane width is greater than 4m and is an extra-wide lane.

[0070] Condition 2: The current lane width is less than 2.8m, which is too narrow.

[0071] Condition three: If the difference between the forward preview lane width and the current lane width exceeds one fifth of the current lane width, the lane is significantly widened.

[0072] Condition 4: If the difference between the forward preview lane width and the current lane width is positive and greater than one-fifth of the current lane width, the lane is significantly widened.

[0073] Condition 5: If the difference between the current lane width and the forward preview lane width is negative and greater than one-fifth of the current lane width, the lane is significantly narrowed.

[0074] Step 203: The scene recognition module further processes and determines scenes with typical features based on the lane position information and lane width change trend.

[0075] Condition 1: The rightmost lane has a wide dashed line on the left and the lane is obviously narrowed, which indicates that the vehicle is merging into the main road from the right.

[0076] Condition 2: When the leftmost lane has a wide dashed line on the right and the lane is obviously narrowed, it is judged as merging into the main road from the left.

[0077] Condition 3: If the lane is obviously narrowed and the width of the lane is less than 1.4m, the lane is judged to be terminated and the lane scene disappears.

[0078] In step 204, the line selection module completes the selection of corresponding baselines for different scenarios. When no special scenario is determined, the line selection is performed normally according to the lane line confidence of the forward-looking output from high to low. In the merging scenario, the lane line on the side of the non-wide dotted line is selected as the baseline. In the lane disappearance scenario, the line is selected according to left and right. If the leftmost lane disappears, the left line is selected, and if the rightmost lane disappears, the right line is selected.

[0079] Step 205: The reference line generation module updates the lane width in combination with the scene and translates the reference line discrete points to the other side by half the lane width, and outputs the reference line coefficients after filtering and fitting. Based on the selected baseline discrete sampling, the obtained discrete points are translated to the other side by half the lane width to obtain the reference line discrete points, and then fitted after Kalman filtering to obtain the reference line cubic coefficients.

[0080] Among them, in conventional scenarios, the lane width is calculated based on the difference in the lateral distance between the left and right lines. In merging scenarios and lane disappearance scenarios, if the lateral distance between the left and right lines is greater than 4m, it is calculated as 4m, and if it is less than 2.5m, it is calculated as 2.5m. The road width is normally updated within the range of 2.5m to 4m.

[0081] It can be seen that in this specific implementation, the scene is identified and a reasonable baseline is preliminarily selected by relying on forward-looking lane line recognition. At the same time, corresponding road width update logic is formulated according to different scenarios, thereby realizing the applicability of the reference line in different scenarios during autonomous driving.

[0082] For the above Figure 1 , the embodiment of the present application also provides a device for generating a reference line during an automatic driving process, such as Figure 3 As shown, the device comprises:

[0083] The first processing module 302 is used to obtain the number of lane lines and the type of lane lines on both sides of the current driving vehicle, and determine the current lane of the vehicle according to the number of lane lines and the type of lane lines;

[0084] A determination module 304, configured to determine a lane change trend according to a width difference between a first lane width of a lane currently located by the vehicle and a second lane width after the vehicle has traveled along the current lane for a first preset time period;

[0085] A selection module 306, configured to select a lane line from currently identified lane lines as a reference line based on the lane where the vehicle is located and the lane change trend;

[0086] The second processing module 308 is used to update the width of the current driving lane based on the lane change trend, and generate a reference line based on the updated lane width and the baseline.

[0087] In an optional implementation manner of the embodiment of the present application, the first processing module in the embodiment of the present application may further include: a first determination unit, used to determine the left lane line and the right lane line from the acquired lane lines, wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle; a second determination unit, used to determine that the vehicle is in the leftmost lane when the first preset condition is met and the second preset condition is not met; a third determination unit, used to determine that the vehicle is in the rightmost lane when the second preset condition is met and the first preset condition is not met; a fourth determination unit, used to determine that the current driving environment of the vehicle is a single lane when the first preset condition and the second preset condition are met at the same time; wherein the first preset condition refers to that there is no lane line on the left side of the left lane line and the left lane line is a solid line, or the first preset condition refers to that there is no lane line on the left side of the left lane line and the lateral distance of the left side roadside line is less than the first preset distance; the second preset condition refers to that there is no lane line on the right side of the right lane line and the right lane line is a solid line, or the second preset condition refers to that there is no lane line on the right side of the right lane line and the lateral distance of the right side roadside line is less than the first preset distance.

[0088] In an optional implementation manner of the embodiment of the present application, the determination module in the embodiment of the present application may further include: a fifth determination unit, used to determine the difference between the second lane width and the first lane width; a sixth determination unit, used to determine that the lane change trend is from the current lane to the widened lane when the difference is positive and the ratio of the difference to the first lane width is greater than the second preset threshold; a seventh determination unit, used to determine that the lane change trend is from the current lane to the narrowed lane when the difference is negative and the ratio of the absolute value of the difference to the first lane width is greater than the second preset threshold; an eighth determination unit, used to determine that the lane change trend is that the lane narrows and becomes a disappearing lane when the lane change trend is from the current lane to the narrowed lane and the second lane width is less than the third preset threshold; a ninth determination unit, used to determine that the current driving lane has not changed when the difference is less than the fourth preset threshold.

[0089] In an optional implementation manner of an embodiment of the present application, the selection module in the embodiment of the present application may further include: a tenth determination unit, used to determine the road driving scene in which the current vehicle is located according to the lane change trend; a first selection unit, used to select the lane line with the highest confidence from all current lane lines as the baseline when the road driving scene is unchanged; a second selection unit, used to use the lane line on the side of the non-wide dotted line as the baseline when the road driving scene characterizes that the vehicle is merging into the main road; and a third selection unit, used to use the lane line on the lane disappearing side as the baseline when the road driving scene characterizes that the current lane disappears.

[0090] In an optional implementation manner of the embodiment of the present application, the tenth determination unit in the embodiment of the present application may further include: a first determination subunit, used to determine that the road driving scene is a scene of merging into the main road from the right when the vehicle is in the rightmost lane, the left lane line is a wide dashed line and the lane is narrowing; a second determination subunit, used to determine that the road driving scene is a scene of merging into the main road from the left when the vehicle is in the leftmost lane, the right lane line is a wide dashed line and the lane is narrowing; wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle; a third determination subunit, used to determine that the road driving scene is a disappearing lane scene when the width of the second lane is less than a third preset threshold after the lane is narrowed.

[0091] In an optional implementation manner of the embodiment of the present application, the second processing module in the embodiment of the present application may further include: an eleventh determination unit, used to determine that the current lane width does not need to be updated when the lane change trend characterizes that the road driving scene is unchanged; an updating unit, used to update the lane width according to the comparison result between the current lane width and the preset threshold when the lane change trend characterizes that the road driving scene is merging into the main road scene or disappearing lane scene, wherein when the current lane width is greater than the fifth preset threshold, the current lane width is updated to the fifth preset threshold; when the current lane width is less than the sixth preset threshold, the current lane width is updated to the sixth preset threshold, and when the current lane width is greater than the sixth preset threshold and less than the fifth preset threshold, there is no need to update the lane width; the sixth preset threshold is less than the fifth preset threshold; a generation unit, used to obtain discrete points of the reference line based on the half position of the updated lane width after the baseline is translated to the middle of the lane, and to obtain the reference line by fitting based on the discrete points.

[0092] like Figure 4 As shown, an embodiment of the present application provides an electronic device, including a processor 411, a communication interface 412, a memory 413 and a communication bus 414, wherein the processor 411, the communication interface 412, and the memory 413 communicate with each other through the communication bus 414.

[0093] Memory 413, used for storing computer programs;

[0094] In one embodiment of the present application, the processor 411 is used to execute the program stored in the memory 413 to implement the method for generating a reference line during autonomous driving provided by any of the aforementioned method embodiments, and the role it plays is similar and will not be repeated here.

[0095] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for generating a reference line during an autonomous driving process as provided in any of the aforementioned method embodiments are implemented.

[0096] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0098] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0099] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for generating a reference line during an autonomous driving process, characterized in that: include: Obtaining the number of lane lines and the type of lane lines on both sides of the currently moving vehicle, and determining the lane in which the vehicle is currently located according to the number of lane lines and the type of lane lines; determining a lane change trend according to a difference between a first lane width of a lane where the vehicle is currently located and a second lane width after the vehicle has traveled along the current lane for a first preset time period; Based on the lane where the vehicle is located and the lane change trend, selecting a lane line from the currently identified lane lines as a reference line; The width of the current driving lane is updated based on the lane change trend, and the reference line is generated based on the updated lane width and the baseline.

2. The method according to claim 1, characterized in that Obtaining the number of lane lines on both sides of the currently moving vehicle and the type of lane lines, and determining the lane in which the vehicle is currently located according to the number of lane lines and the type of lane lines includes: Determine a left lane line and a right lane line from the acquired lane lines, wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle; When the first preset condition is met and the second preset condition is not met, determining that the vehicle is in the leftmost lane; When the second preset condition is met and the first preset condition is not met, determining that the vehicle is in the rightmost lane; When the first preset condition and the second preset condition are satisfied at the same time, determining that the current driving environment of the vehicle is a single lane; The first preset condition refers to that there is no lane line on the left side of the left lane line and the left lane line is a solid line, or the first preset condition refers to that there is no lane line on the left side of the left lane line and the lateral distance of the left roadside line is less than the first preset distance; The second preset condition means that there is no lane line on the right side of the right lane line and the right lane line is a solid line, or the second preset condition means that there is no lane line on the right side of the right lane line and the lateral distance of the right roadside line is less than the first preset distance.

3. The method according to claim 1, characterized in that Determining the lane change trend according to a width difference between a first lane width of a lane where the vehicle is currently located and a second lane width after the vehicle has traveled along the current lane for a first preset time period includes: determining a difference between the second lane width and the first lane width; When the difference is positive and the ratio of the difference to the first lane width is greater than a second preset threshold, determining that the lane change trend is from the current lane to the widened lane; When the difference is negative and the ratio of the absolute value of the difference to the first lane width is greater than the second preset threshold, determining that the lane change trend is from the current lane to a narrowed lane; When the lane change trend is from the current lane to the narrowed lane, and the width of the second lane is less than a third preset threshold, determining that the lane change trend is that the lane narrows and becomes a disappearing lane; When the difference is less than a fourth preset threshold, it is determined that the current driving lane has no change.

4. The method according to claim 1, characterized in that: Based on the lane where the vehicle is located and the lane change trend, selecting a lane line from the currently identified lane lines as a reference line includes: Determining the road driving scene where the vehicle is currently located according to the lane change trend; When the road driving scene does not change, select the lane line with the highest confidence from all current lane lines as the reference line; wherein the higher the confidence of the lane line is, the higher the integrity of the lane line is; When the road driving scene indicates that the vehicle is merging into the main road, the lane line on the side other than the wide dashed line is used as the reference line; When the road driving scene characterizes that the current lane disappears, the lane line on the lane disappearing side is used as the reference line.

5. The method according to claim 4, characterized in that Determining the road driving scene where the vehicle is currently located according to the lane change trend includes: When the vehicle is in the rightmost lane, the left lane line is a wide dashed line and the lane is narrowing, determining that the road driving scene is a scene of merging into the main road from the right; When the vehicle is in the leftmost lane, the right lane line is a wide dashed line and the lane is narrowing, the road driving scene is determined to be a scene of merging into the main road from the left; wherein the left lane line is the lane line closest to the vehicle on the left side of the vehicle, and the right lane line is the lane line closest to the vehicle on the right side of the vehicle; After the lane is narrowed, if the width of the second lane is less than a third preset threshold, it is determined that the road driving scene is a disappearing lane scene.

6. The method according to claim 1, characterized in that Updating the width of the current driving lane based on the lane change trend, and generating the reference line based on the updated lane width and the baseline includes: When the lane change trend indicates that the road driving scene is unchanged, it is determined that the current lane width does not need to be updated; When the lane change trend indicates that the road driving scene is a scene of merging into the main road or disappearing lane, the lane width is updated according to the comparison result between the current lane width and the preset threshold value, wherein, when the current lane width is greater than the fifth preset threshold value, the current lane width is updated to the fifth preset threshold value; when the current lane width is less than the sixth preset threshold value, the current lane width is updated to the sixth preset threshold value; when the current lane width is greater than the sixth preset threshold value and less than the fifth preset threshold value, there is no need to update the lane width; the sixth preset threshold value is less than the fifth preset threshold value; Based on the reference line being translated to the middle of the lane by half the updated lane width, discrete points of the reference line are obtained, and the reference line is obtained by fitting based on the discrete points.

7. A device for generating a reference line during an automatic driving process, characterized in that: include: A first processing module is used to obtain the number of lane lines and the type of lane lines on both sides of the current driving vehicle, and determine the lane where the vehicle is currently located according to the number of lane lines and the type of lane lines; A determination module, configured to determine a lane change trend according to a width difference between a first lane width of a lane where the vehicle is currently located and a second lane width after the vehicle has traveled along the current lane for a first preset time period; A selection module, configured to select a lane line from currently identified lane lines as a reference line based on the lane where the vehicle is located and the lane change trend; The second processing module is used to update the width of the current driving lane based on the lane change trend, and generate the reference line based on the updated lane width and the baseline.

8. The device according to claim 7, characterized in that The first processing module comprises: A first determining unit is used to determine a left lane line and a right lane line from the acquired lane lines, wherein the left lane line is a lane line on the left side of the vehicle closest to the vehicle, and the right lane line is a lane line on the right side of the vehicle closest to the vehicle; A second determining unit, configured to determine that the vehicle is in the leftmost lane when the first preset condition is met and the second preset condition is not met; a third determining unit, configured to determine that the vehicle is in the rightmost lane when the second preset condition is met and the first preset condition is not met; a fourth determining unit, configured to determine that the current driving environment of the vehicle is a single lane when the first preset condition and the second preset condition are satisfied at the same time; The first preset condition refers to that there is no lane line on the left side of the left lane line and the left lane line is a solid line, or the first preset condition refers to that there is no lane line on the left side of the left lane line and the lateral distance of the left roadside line is less than the first preset distance; The second preset condition means that there is no lane line on the right side of the right lane line and the right lane line is a solid line, or the second preset condition means that there is no lane line on the right side of the right lane line and the lateral distance of the right roadside line is less than the first preset distance.

9. An electronic device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to execute the method for generating a reference line during an autonomous driving process as described in any one of claims 1 to 6.

10. A computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the method for generating a reference line during an autonomous driving process as described in any one of claims 1 to 6.

Images