CN115092136B

CN115092136B - Vehicle speed planning method and device, vehicle and storage medium

Info

Publication number: CN115092136B
Application number: CN202210896038.6A
Authority: CN
Inventors: 黄熠文; 赵永正; 张惠康; 李力耘
Original assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Current assignee: Guangzhou Xiaopeng Motors Technology Co Ltd
Priority date: 2022-07-27
Filing date: 2022-07-27
Publication date: 2023-09-12
Anticipated expiration: 2042-07-27
Also published as: CN115092136A

Abstract

The embodiment of the application provides a vehicle speed planning method, a vehicle speed planning device, a vehicle and a storage medium, and relates to the technical field of automatic driving. According to the method, a target rectangular frame representing an obstacle is determined according to a vehicle track and an obstacle track; performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the own vehicle to obtain a target speed limit value; based on the target speed limit value, the speed of the own vehicle is planned, the speed response can be performed in advance, and the collision with obstacles with relatively close distance from the own vehicle is avoided, so that the safety of automatic driving can be improved.

Description

Vehicle speed planning method and device, vehicle and storage medium

Technical Field

The embodiment of the application relates to the technical field of automatic driving, in particular to a vehicle speed planning method, a vehicle speed planning device, a vehicle and a storage medium.

Background

The speed planning method in the automatic driving technology at least comprises two processes of collision detection and speed planning. If the predicted obstacle track and the vehicle track have collision conditions, the vehicle is subjected to speed planning according to the obstacle track.

The existing collision detection method only considers the collision condition, and does not carry out related treatment on the obstacle which does not collide with the track of the vehicle. However, there may be an obstacle closer to the track of the vehicle among the obstacles not colliding with the track of the vehicle, and in the case that sudden acceleration occurs to the obstacle closer to the track of the vehicle or sudden uncontrolled steering occurs due to a fault, there is a risk of collision between the vehicle and the obstacle, resulting in potential safety hazard for automatic driving.

Disclosure of Invention

The embodiment of the application provides a vehicle speed planning method, a vehicle speed planning device, a vehicle and a storage medium, so as to solve the problems.

In a first aspect, an embodiment of the present application provides a vehicle speed planning method. The method comprises the following steps: determining a target rectangular frame representing an obstacle according to a vehicle track and an obstacle track, wherein the transverse distance between the target rectangular frame and the vehicle is positioned between a preset collision distance and a preset passing distance, the preset passing distance is larger than the preset collision distance, and the obstacle track comprises a plurality of rectangular frames representing the obstacle; performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a target speed limit value; and planning the speed of the own vehicle based on the target speed limit value.

In a second aspect, an embodiment of the present application provides a vehicle speed planning apparatus. The device comprises: the object determining module is used for determining an object rectangular frame representing an obstacle according to a vehicle track and an obstacle track, wherein the transverse distance between the object rectangular frame and the vehicle is positioned between a preset collision distance and a preset passing distance, the preset passing distance is larger than the preset collision distance, and the obstacle track comprises a plurality of rectangular frames representing the obstacle; the table look-up processing module is used for performing table look-up processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a target speed limit value; and the vehicle speed planning module is used for planning the vehicle speed of the own vehicle based on the target speed limit value.

In a third aspect, an embodiment of the present application provides a vehicle. The vehicle includes a memory, one or more processors, and one or more applications. Wherein one or more application programs are stored in the memory and configured to perform the methods provided by the embodiments of the present application when invoked by one or more processors.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium. The computer readable storage medium has stored therein program code configured to perform the method provided by the embodiments of the present application when invoked by a processor.

The embodiment of the application provides a vehicle speed planning method, a vehicle speed planning device, a vehicle and a storage medium, wherein a target rectangular frame representing an obstacle which is not collided with a vehicle but is transversely close to the vehicle is determined, a target speed limit value is determined according to the minimum transverse distance between the target rectangular frame and the vehicle, the vehicle speed planning is carried out according to the target speed limit value, the vehicle can be reasonably limited according to the minimum transverse distance between the obstacle and the vehicle, the speed response is carried out in advance, and the collision between the obstacle and the vehicle with the obstacle with the relatively close distance is avoided, so that the safety of automatic driving can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of an application scenario of a vehicle speed planning method according to an exemplary embodiment of the present application;

FIG. 2 is a flow chart of a vehicle speed planning method according to an embodiment of the present application;

FIG. 3 is a schematic illustration of a vehicle track provided by an exemplary embodiment of the present application;

FIG. 4 is a flow chart of a vehicle speed planning method according to another embodiment of the present application;

FIG. 5 is a flow chart of a vehicle speed planning method according to another embodiment of the present application;

FIG. 6 is a block diagram of a vehicle speed planning apparatus according to an embodiment of the present application;

FIG. 7 is a block diagram of a vehicle according to an embodiment of the present application;

fig. 8 is a block diagram of a computer readable storage medium according to an embodiment of the present application.

Detailed Description

In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic diagram of an application scenario of a vehicle speed planning method according to an exemplary embodiment of the present application. The vehicle speed planning system 10 includes a host vehicle 11 and an obstacle 12. The own vehicle 11 and the obstacle 12 can communicate with each other to realize data exchange.

The own vehicle 11 may acquire the obstacle track of the obstacle 12 in real time or at intervals of a preset period, where the preset period may be set according to actual requirements, for example, 0.5 seconds, which is not particularly limited herein. The own vehicle 11 can realize different functions according to the own vehicle track and the obstacle track. For example, the own vehicle 11 may establish an ST map from the travel tracks of the own vehicle 11 and the obstacle 12 to clarify the relative positions of the own vehicle 11 and the obstacle 12. The ST diagram is used here to describe the longitudinal movement of the obstacle 12 in the lane in which the vehicle 11 is located, i.e. the longitudinal speed. S refers to a distance forward along a travel track of the own vehicle with the own vehicle as an origin, and T refers to time. For another example, the own vehicle 11 may calculate the lateral distance between the obstacle 12 and the own vehicle 11 from the own vehicle trajectory and the obstacle trajectory.

The obstacle 12 may be one obstacle or include a plurality of obstacles. The obstacle may be a vehicle or other device capable of communication connection with the own vehicle 11. When the obstacle 12 includes a plurality of vehicles, the plurality of vehicles may be the same or different. For example, the plurality of vehicles may be vehicles from the same manufacturer or may be vehicles from different manufacturers. For another example, the plurality of vehicles may be vehicles of the same type or vehicles of different types. The vehicle may be a gasoline vehicle, an electric vehicle, or the like, wherein the electric vehicle may be a pure electric vehicle, a hybrid vehicle, or a fuel cell vehicle, or the like, and is not particularly limited herein.

Referring to fig. 2, fig. 2 is a flow chart of a vehicle speed planning method according to an embodiment of the application. The vehicle speed planning method may be applied to the own vehicle 11 shown in fig. 1, or the vehicle speed planning apparatus 400 shown in fig. 6 to be mentioned below, or the vehicle 500 shown in fig. 7 to be mentioned below. The vehicle speed planning method may include the following steps S110 to S130.

Step S110, determining a target rectangular frame representing the obstacle according to the vehicle track and the obstacle track.

The vehicle track in the embodiment of the application comprises a plurality of rectangular frames for representing the vehicle. The own vehicle trajectory refers to a travel trajectory of the own vehicle planned according to the destination of the own vehicle and the current travel environment of the own vehicle, instead of an actual own vehicle travel trajectory. The current driving environment includes obstacle vehicles around the own vehicle, a front lane congestion situation, lane lines, and the like. The length of the rectangular frame representing the own vehicle may be greater than or equal to the length of the own vehicle, and the width of the rectangular frame may be greater than or equal to the width of the own vehicle.

The obstacle trajectory in the embodiment of the application comprises a plurality of rectangular boxes for representing the obstacle. The obstacle trajectory refers to a travel trajectory planned by an obstacle according to the destination of the obstacle and the current travel environment of the obstacle, rather than an actual obstacle travel trajectory. The current driving environment includes obstacle vehicles around the obstacle, a front lane congestion situation, lane lines, and the like. The length of the rectangular frame characterizing the obstacle may be greater than or equal to the obstacle length, and the width of the rectangular frame may be greater than or equal to the obstacle width.

The target rectangular frame in the embodiment of the application meets the following conditions: the transverse distance between the target rectangular frame and the own vehicle is positioned between a preset collision distance and a preset passing distance.

The lateral distance between the target rectangular frame and the vehicle may refer to a distance between a corner point closest to the vehicle track on the target rectangular frame and the vehicle track. An obstacle characterized by a target rectangular frame refers to an obstacle that does not collide with the own vehicle but is laterally close to the own vehicle, the obstacle can pass closely by the own vehicle, and the collision of the own vehicle with the obstacle can be caused once the obstacle suddenly accelerates at a position close to the own vehicle.

The preset collision distance in the embodiment of the application is a distance measurement index of collision detection. If the distance between the vehicle and the obstacle exceeds the preset collision distance, the vehicle collides with the obstacle. The preset collision distance may be set according to the actual demand for the safety of the automatic driving, and is not particularly limited herein.

In some embodiments, the preset collision distance may be set according to the vehicle width. For example, the preset collision distance may be greater than or equal to half the width of the vehicle. As an example, the preset collision distance may be a vehicle width. As another example, the preset collision distance may be 1.5 times the width of the vehicle.

In other embodiments, the preset collision distance may be set according to the vehicle width and the virtual width. The virtual width refers to a distance index of collision detection, and the virtual width may be added to the left and right of the vehicle track in the conventional collision detection method. For example, the preset collision distance may be half the width of the vehicle plus the virtual width.

In still other embodiments, the preset collision distance may be set according to the width of the lane in which the own vehicle is currently located. For example, the preset collision distance may be greater than or equal to the width of the lane in which the own vehicle is currently located. As an example, the preset collision distance may be a width of a lane in which the own vehicle is currently located.

The preset passing distance in the embodiment of the application refers to a distance which can not collide with the vehicle and can pass through the vehicle at a short distance. The preset passing distance is larger than the preset collision distance. The preset passing distance may be set according to the actual requirement for the safety of the automatic driving, and is not particularly limited herein.

In some embodiments, the preset pass distance may be set according to a preset collision distance. As an example, the preset collision distance may be half the width of the vehicle plus the virtual width, and the preset passing distance may be half the width of the vehicle plus the virtual width plus 0.5 meter. As another example, the preset collision distance may be the vehicle width, and the preset passing distance may be 1.5 times the vehicle width.

In some embodiments, the preset collision distance and the preset passing distance may also be adjusted according to the track of the vehicle. For example, when a lane change of the own vehicle is detected according to the track of the own vehicle, the preset collision distance and the preset passing distance may be increased, and after the lane change of the own vehicle, the preset collision distance and the preset passing distance may be reduced. The scale of the increase and decrease may be preset, and the scale of the increase and decrease of the preset collision distance and the preset passing distance may be the same or may be different, without specific limitation.

In some embodiments, the implementation of step S110 may include the steps of: determining two collision boundaries and two passing boundaries relative to the vehicle track; a rectangular frame which is located outside the two collision boundaries but has corner points located inside the two passing boundaries in the rectangular frames on the obstacle track is determined as a target rectangular frame for representing the obstacle. The two traffic boundaries are located outside the two collision boundaries with respect to the vehicle trajectory.

The distance between the two collision boundaries may be twice the above-mentioned preset collision distance. The two collision boundaries are symmetrically arranged relative to the track of the vehicle. The collision boundary may be a straight line or a curved line. How the two collision boundaries are specifically set can be determined according to actual requirements, and no specific limitation is made here.

As an example, referring to fig. 3, fig. 3 is a schematic diagram of a vehicle track according to an exemplary embodiment of the present application. The two collision boundaries may be two straight lines symmetrically arranged with respect to the vehicle trajectory, a solid rectangular box C in fig. 3 representing (the position of) the vehicle, dashed rectangular boxes a and B representing (the position of) the vehicle predicted from the vehicle trajectory, dashed rectangular boxes D and E representing (the position of) the obstacle predicted from the obstacle trajectory, and a thickened arrow representing the traveling direction of the vehicle.

The distance between the two traffic boundaries may be twice the above-mentioned preset traffic distance. The two passing boundaries are symmetrically arranged relative to the track of the vehicle. The traffic boundary may be a straight line or a curved line. As an example, as shown in fig. 3, the two passing boundaries may be two straight lines symmetrically disposed with respect to the own vehicle trajectory. How the two passing boundaries are specifically set can be determined according to actual requirements, and no specific limitation is made here.

In some embodiments, the shape of the traffic boundary may coincide with the collision boundary, e.g., both the traffic boundary and the collision boundary may be straight or curved.

In other embodiments, the shape of the traffic boundary may not coincide with the collision boundary, e.g., the traffic boundary may be a curve, but the collision boundary may be a straight line.

In still other embodiments, the shape of the traffic and collision boundaries may be adjusted according to the vehicle trajectory. For example, the shapes of the passing boundary and the collision boundary may be changed from a straight line to a curved line when the lane change of the own vehicle is detected from the trajectory of the own vehicle, and the shapes of the passing boundary and the collision boundary may be changed from a curved line back to a straight line after the lane change of the own vehicle. The timing of adjusting the passing boundary and the collision boundary shape may be the same as or different from the timing of adjusting the preset collision distance and the preset passing distance, and is not particularly limited herein.

In some embodiments, when the vehicle track is acquired, two collision boundaries and two traffic boundaries set relative to the vehicle track may be determined according to the preset collision distance and the preset traffic distance. When the vehicle track is acquired, two collision boundaries and two passing boundaries are determined, so that the two collision boundaries and the two passing boundaries have real-time performance, and the real-time performance and the accuracy of a vehicle speed planning result can be improved.

In other embodiments, two collision boundaries and two passing boundaries set relative to the preset vehicle track may be further constructed based on the preset vehicle track, and when the current vehicle track is obtained, the preset vehicle track and the vehicle track are overlapped to obtain the two collision boundaries and the two passing boundaries set relative to the vehicle track. The preset vehicle track may be a line set randomly, or may be a historical vehicle track, which is not limited herein.

In some embodiments, a method of determining rectangular boxes each located outside two collision boundaries but having corner points located inside two traffic boundaries from among the rectangular boxes on the obstacle trajectory may include the steps of: acquiring the transverse distance between each corner of a rectangular frame on an obstacle track and a vehicle track to obtain four transverse distances; determining a minimum lateral distance from the four lateral distances; if the minimum transverse distance is between the preset collision distance and the preset passing distance, determining the rectangular frame with the corner point corresponding to the minimum transverse distance as the rectangular frame which is positioned outside the two collision boundaries and has the corner point positioned inside the two passing boundaries, wherein the minimum transverse distance is the minimum transverse distance between the target rectangular frame and the own vehicle.

In some embodiments, the obstacle track, the vehicle track, and the rectangular frame on the obstacle track may be converted into ST graphs, where S represents a distance (also referred to as a longitudinal distance) between the current vehicle and the vehicle along the driving direction, and T represents a time.

As an example, the lateral distance between the corner point of each rectangular frame and the track of the vehicle may be calculated in real time according to the ST graph, so as to obtain four lateral distances corresponding to each rectangular frame. Comparing the four lateral distances results in a minimum lateral distance.

As another example, the position of the corner point of each rectangular frame in the ST view, which is denoted by S and T, may also be acquired. The obtained positions of the corner points and the vehicle track can be input into a preset minimum transverse distance calculation model, and the minimum transverse distance is obtained. The preset minimum lateral distance calculation model may be trained in advance and stored in a vehicle or a device (e.g., a server) in communication with the vehicle for calculating the above-described minimum lateral distance from the positions of the corner points of each rectangular frame and the vehicle trajectory. The processing speed can be improved by adopting the model to calculate the minimum transverse distance.

In other embodiments, a method of determining rectangular boxes each located outside two collision boundaries but having corner points located inside two traffic boundaries from rectangular boxes on an obstacle trajectory may include the steps of: generating a virtual track graph according to the obstacle track, the vehicle track, the rectangular frames on the obstacle track, the two collision boundaries and the two passing boundaries (as shown in fig. 3, the rectangular frames on the vehicle track can be deleted or reserved according to the selection of computing resources); the virtual track diagram is identified by adopting an image identification technology to obtain a target point between two collision boundaries and two passing boundaries, and a rectangular frame corresponding to the target point is determined as a rectangular frame which is positioned outside the two collision boundaries but has corner points positioned inside the two passing boundaries; if the target point is not identified, continuing to identify the virtual track graph. The image recognition technique may be selected from the prior art, and is not particularly limited herein. The image recognition technology can be adopted to carry out large-scale recognition, so that the comprehensiveness of the speed planning method can be improved.

In still other embodiments, a method of determining rectangular boxes each located outside two collision boundaries but having corner points located inside two traffic boundaries from among the rectangular boxes on the obstacle trajectory may include the steps of: and inputting the obstacle track, the vehicle track, the rectangular frame on the obstacle track, the two collision boundaries and the two passing boundaries into a preset target determination model to obtain the rectangular frame which is positioned outside the two collision boundaries and has the corner points positioned inside the two passing boundaries. The preset target determination model may be pre-trained and stored in the vehicle or in a device in communication with the vehicle for determining a rectangular box located outside the two collision boundaries but having corner points located inside the two traffic boundaries from the obstacle trajectory, the vehicle trajectory, the rectangular box on the obstacle trajectory, the two collision boundaries, and the two traffic boundaries. The processing speed can be improved by adopting the model to determine the target rectangular frame.

And step S120, performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a target speed limit value.

The minimum lateral distance and the speed limit value in the embodiment of the present application have a mapping relationship, and may be one-to-one mapping, many-to-one mapping, or one-to-many mapping, which is not particularly limited herein. The mapping relation between the minimum lateral distance and the speed limit value can be preset and form a speed limit mapping table (shown in table 1), and the speed limit mapping table is stored in a vehicle or a device or a database communicated with the vehicle, so that the speed limit value corresponding to the minimum lateral distance is searched in the speed limit mapping table according to the minimum lateral distance, and the processing speed is improved. In practical application, the user with authority can modify the data in the speed limit mapping table according to the practical requirement to dynamically update the speed limit mapping table, so that the speed limit mapping table is more in line with the practical application of the user, and the robustness and accuracy of the vehicle speed planning method are improved.

TABLE 1

Minimum lateral distance	Speed limit value
		A	A'
B(B>A)	B'(B'>A')
		C(C>B)	C'(C'>B')

As an embodiment, as shown in table 1, the mapping relationship between the minimum lateral distance and the speed limit value may be sorted from small to large according to the size of the minimum lateral distance or the speed limit value. In other embodiments, the mapping relationship between the minimum lateral distance and the speed limit value may be sorted from large to small according to the minimum lateral distance or the speed limit value. The specific arrangement order of the mapping relationship between the minimum transverse distance and the speed limit value can be determined according to actual requirements, and is not particularly limited herein.

In some embodiments, when determining the minimum lateral distance between the target rectangular frame and the own vehicle, the speed limit mapping table may be queried according to the minimum lateral distance between the target rectangular frame and the own vehicle, to obtain a speed limit value corresponding to the minimum lateral distance, and use the speed limit value as the target speed limit value.

Step S130, planning the speed of the own vehicle based on the target speed limit value.

In other embodiments, the speed limit value has a mapping relationship with the deceleration, and may be a one-to-one mapping, a many-to-one mapping, or a one-to-many mapping, which is not particularly limited herein. The mapping relation between the speed limit value and the deceleration may be preset and form a deceleration mapping table (as shown in table 2), and the deceleration mapping table is stored in the own vehicle or a device or a database in communication with the own vehicle, so as to search the deceleration corresponding to the speed limit value in the mapping table according to the speed limit value, thereby improving the processing speed. In practical application, the user with authority can modify the data in the deceleration mapping table according to the actual demand so as to dynamically update the deceleration mapping table, so that the deceleration mapping table is more in line with the practical application of the user, and the robustness and accuracy of the vehicle speed planning method are improved.

TABLE 2

Speed limit value	Deceleration rate
		A'	A”
B'(B'>A')	B”(B”>A”)
		C'(C'>B')	C'(C”>B”)

As an embodiment, as shown in table 2, the map of the speed limit value and the deceleration may be sorted from small to large according to the magnitude of the speed limit value or the deceleration. In other embodiments, the map of the speed limit value and the deceleration may be sorted from large to small according to the speed limit value or the deceleration. The specific arrangement order of the mapping relation between the speed limit value and the deceleration can be determined according to the actual requirement, and the specific limitation is not made here.

In some embodiments, the speed limit map may be generated according to a mapping relationship between the minimum lateral distance and the speed limit value (table 1), and the deceleration map may be generated according to a mapping relationship between the speed limit value and the deceleration (table 2).

In other embodiments, the speed limiting mapping table and the deceleration mapping table may be fused into a comprehensive mapping table (as shown in table 3) according to the mapping relation among the minimum lateral distance, the speed limiting value and the deceleration, and by searching data in one comprehensive mapping table, resources may be saved and the processing speed may be improved.

TABLE 3 Table 3

Minimum lateral distance	Speed limit value	Deceleration rate
			A	A'	A”
B(B>A)	B'(B'>A')	B”(B”>A”)
			C(C>B)	C'(C'>B')	C'(C”>B”)

As an embodiment, as shown in table 3, the mapping relationship between the minimum lateral distance, the speed limit value, and the deceleration may be sorted from small to large according to the minimum lateral distance, the speed limit value, or the magnitude of the deceleration. In other embodiments, the mapping relationship between the minimum lateral distance, the speed limit value, and the deceleration may be sorted from large to small according to the minimum lateral distance, the speed limit value, and the deceleration. The specific arrangement sequence of the mapping relation between the minimum transverse distance, the speed limit value and the deceleration can be determined according to actual requirements, and the specific limitation is not carried out here.

In some embodiments, the implementation of step S130 may include the steps of: and acquiring deceleration corresponding to the target speed limit value, and planning the speed of the own vehicle based on the deceleration. Specifically, table look-up processing can be performed according to the target speed limit value, so as to obtain the deceleration corresponding to the target speed limit value. By planning the speed of the own vehicle according to the deceleration corresponding to the target speed limit value, the speed of the own vehicle when reaching the position corresponding to the target rectangular frame can be ensured to be the target speed limit value, so that the collision with an obstacle close to the own vehicle is avoided by responding in advance, and the safety of automatic driving is improved.

According to the vehicle speed planning method provided by the embodiment of the application, the target rectangular frame representing the obstacle which is not collided with the vehicle but transversely approaches the vehicle is determined, the target speed limit value is determined according to the minimum transverse distance between the target rectangular frame and the vehicle, the vehicle speed is planned according to the target speed limit value, the vehicle can be reasonably limited according to the minimum transverse distance between the obstacle and the vehicle, the speed response is carried out in advance, and the collision between the obstacle and the obstacle with a relatively close distance between the obstacle and the vehicle is avoided, so that the safety of automatic driving can be improved.

Referring to fig. 4, fig. 4 is a flow chart of a vehicle speed planning method according to another embodiment of the application. The vehicle speed planning method may be applied to the own vehicle 11 shown in fig. 1, or the vehicle speed planning apparatus 400 shown in fig. 6 to be mentioned below, or the vehicle 500 shown in fig. 7 to be mentioned below. The vehicle speed planning method may include the following steps S210 to S250.

Step S210, determining a target rectangular frame representing the obstacle according to the vehicle track and the obstacle track.

Step S210 is referred to the aforementioned step S110, and is not described herein.

And step S220, performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a preliminary speed limit value.

As described above, the speed limit value corresponding to the minimum lateral distance can be obtained by performing the table look-up process based on the minimum lateral distance between the target rectangular frame and the host vehicle, and the speed limit value can be determined as the preliminary speed limit value.

And step S230, if the preliminary speed limit value meets the preset condition, determining the preliminary speed limit value as a target speed limit value.

In some embodiments, the preset condition may be: and the vehicle reaches the preliminary speed limit value when the vehicle runs at a speed reduction by a preset deceleration from the current position to the position corresponding to the target rectangular frame.

The preset deceleration may be a fixed value that is set in advance and stored in the own vehicle. The preset deceleration may be a deceleration that is comfortable for the user, for example, 3 meters per second. The preset deceleration may be determined based on experimental or test data. Wherein the experimental data refers to the determined user comfort information or the threshold value of user's discomfort by simulating different decelerations of the vehicle. The test data may be user comfort information or thresholds for user discomfort determined by measuring different decelerations of the vehicle. The preset deceleration may take any one of the above threshold values. By setting the preset deceleration, the vehicle can run at a reduced speed at the preset deceleration, and the comfort of the vehicle is improved.

If the preset condition is that the vehicle reaches the preliminary speed limit value when the vehicle runs at a speed reduction from the current position to the position corresponding to the target rectangular frame by using a preset deceleration, the mapping relationship between the speed limit value and the deceleration is a many-to-one mapping, that is, all the speed limit values correspond to the same preset deceleration.

In other embodiments, the preset conditions may be: and (3) decelerating and driving to a position corresponding to the target rectangular frame by using the deceleration corresponding to the preliminary speed limit value to reach the preliminary speed limit value, wherein different preliminary speed limit values correspond to different decelerations.

And step S240, if the preliminary speed limit value does not meet the preset condition, continuing to perform table look-up processing in a preset mode until a preset minimum speed limit value is found, and determining the preset minimum speed limit value as a target speed limit value.

The preset mode may be a binary search mode. The preset minimum speed limit value can be determined according to experimental data or test data or user experience or actual requirements, for example, the preset minimum speed limit value can be 2.5 meters per second. The experimental data refers to data obtained by simulating vehicle travel measurement. The test data refers to data measured by a real driving vehicle.

When the speed limit value does not meet the preset condition, the table look-up processing is continuously carried out according to the preset mode, the speed limit value can be gradually reduced for a plurality of times, and therefore the rationality of the determined target speed limit value can be improved.

Step S250, planning the speed of the own vehicle based on the target speed limit value.

Step S250 is referred to the aforementioned step S130, and is not described herein.

According to the vehicle speed planning method provided by the embodiment of the application, the target rectangular frame representing the obstacle which is not collided with the vehicle but transversely approaches the vehicle is determined, the target speed limit value is determined according to the minimum transverse distance between the target rectangular frame and the vehicle, the vehicle speed is planned according to the target speed limit value, the vehicle can be reasonably limited according to the minimum transverse distance between the obstacle and the vehicle, the speed response is carried out in advance, and the collision between the obstacle and the obstacle with a relatively close distance between the obstacle and the vehicle is avoided, so that the safety of automatic driving can be improved. By determining the speed limit value meeting the preset condition or the preset minimum speed limit value as the target speed limit value, the self-vehicle can be ensured to reach the target speed limit value when reaching the position corresponding to the target rectangular frame, and therefore the self-vehicle can be ensured to be limited effectively. By setting the preset deceleration, the vehicle can run at a reduced speed at the preset deceleration, and the comfort of the vehicle is improved. In addition, whether the speed limit value meets the preset condition or not is judged, when the speed limit value does not meet the preset condition, table lookup processing is continuously carried out according to a preset mode, and the rationality of the determined target speed limit value can be improved by gradually reducing the speed limit value for a plurality of times.

Referring to fig. 5, fig. 5 is a flow chart of a vehicle speed planning method according to another embodiment of the application. The vehicle speed planning method may be applied to the own vehicle 11 shown in fig. 1, or the vehicle speed planning apparatus 400 shown in fig. 6 to be mentioned below, or the vehicle 500 shown in fig. 7 to be mentioned below. The vehicle speed planning method may include the following step S310 and step S350.

Step S310, determining a target rectangular frame for representing the obstacle according to the vehicle track and the obstacle track.

Step S310 is referred to the aforementioned step S110, and is not described herein.

Step S320, performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the own vehicle to obtain a preliminary speed limit value.

And step S330, if the preliminary speed limit value meets the preset condition, determining the preliminary speed limit value as a target speed limit value.

Step S320 and step S330 refer to the aforementioned step S220 and step S230, and are not described herein.

And step S340, if the preliminary speed limit value does not meet the preset condition, directly determining the preset minimum speed limit value as a target speed limit value.

Please refer to the related description of the aforementioned step S240 for the preset minimum speed limit value, which is not described herein.

And step S350, planning the speed of the own vehicle based on the target speed limit value.

In step S350, please refer to the aforementioned step S130, and the description thereof is omitted herein.

According to the vehicle speed planning method provided by the embodiment of the application, the target rectangular frame representing the obstacle which is not collided with the vehicle but transversely approaches the vehicle is determined, the target speed limit value is determined according to the minimum transverse distance between the target rectangular frame and the vehicle, the vehicle speed is planned according to the target speed limit value, the vehicle can be reasonably limited according to the minimum transverse distance between the obstacle and the vehicle, the speed response is carried out in advance, and the collision between the obstacle and the obstacle with a relatively close distance between the obstacle and the vehicle is avoided, so that the safety of automatic driving can be improved. By determining the speed limit value meeting the preset condition or the preset minimum speed limit value as the target speed limit value, the self-vehicle can be ensured to reach the target speed limit value when reaching the position corresponding to the target rectangular frame, and therefore the self-vehicle can be ensured to be limited effectively. By setting the preset deceleration, the vehicle can run at a reduced speed at the preset deceleration, and the comfort of the vehicle is improved. In addition, by judging whether the speed limit value meets the preset condition or not, when the speed limit value does not meet the preset condition, the preset minimum speed limit value is directly used as the target speed limit value, and the efficiency of determining the target speed limit value can be improved, so that the efficiency of the vehicle speed planning method is improved.

Referring to fig. 6, fig. 6 is a block diagram illustrating a vehicle speed planning apparatus according to an embodiment of the application. The vehicle speed planning apparatus 400 may be applied to the own vehicle 11 shown in fig. 1 described above, or a vehicle 500 shown in fig. 7 to be mentioned later. The vehicle speed planning device 400 comprises a target determination module 410, a table look-up processing module 420 and a vehicle speed planning module 430.

The target determining module 410 is configured to determine a target rectangular frame representing an obstacle according to a vehicle track and an obstacle track, where a lateral distance between the target rectangular frame and the vehicle is located between a preset collision distance and a preset passing distance, the preset passing distance is greater than the preset collision distance, the vehicle track includes a plurality of rectangular frames representing the vehicle, and the obstacle track includes a plurality of rectangular frames representing the obstacle.

And the table lookup processing module 420 is configured to perform table lookup processing according to the minimum lateral distance between the target rectangular frame and the own vehicle, so as to obtain a target speed limit value.

And the vehicle speed planning module 430 is configured to plan the vehicle speed of the own vehicle based on the target speed limit value.

In some embodiments, the lookup processing module 420 includes a lookup processing sub-module and a speed limit value determination sub-module.

And the table look-up processing sub-module is used for performing table look-up processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a preliminary speed limit value.

And the speed limit value determining submodule is used for determining the preliminary speed limit value as a target speed limit value if the preliminary speed limit value meets a preset condition.

In some embodiments, the speed limit value determining submodule is further configured to, if the preliminary speed limit value does not meet the preset condition, continue the table look-up processing in a preset manner until a preset minimum speed limit value is found, and determine the preset minimum speed limit value as the target speed limit value.

In other embodiments, the speed limit value determining submodule is further configured to directly determine the preset minimum speed limit value as the target speed limit value if the preliminary speed limit value does not meet the preset condition.

In other embodiments, the preset conditions may be: and the vehicle reaches the preliminary speed limiting value when the vehicle runs at a speed reduction corresponding to the preliminary speed limiting value from the current position to the position corresponding to the target rectangular frame, and different preliminary speed limiting values correspond to different decelerations.

In some implementations, the targeting module 410 includes a boundary determination sub-module and a targeting determination sub-module.

The boundary determination submodule is used for determining two collision boundaries and two passing boundaries relative to the track of the vehicle, the distance between the two collision boundaries is twice the preset collision distance, and the distance between the two passing boundaries is twice the preset passing distance.

And the target determination submodule is used for determining a rectangular frame which is positioned outside two collision boundaries and has corner points positioned inside two passing boundaries in the rectangular frames on the obstacle track as a target rectangular frame for representing the obstacle.

In some embodiments, the object determination submodule is further configured to determine, from rectangular boxes on the obstacle trajectory, rectangular boxes that are located outside two collision boundaries but have corner points located inside two traffic boundaries. Specifically, the target determining submodule is further used for obtaining the transverse distance between each corner point of the rectangular frame on the obstacle track and the vehicle track, and obtaining four transverse distances; determining a minimum lateral distance from the four lateral distances; if the minimum transverse distance is between the preset collision distance and the preset passing distance, determining a rectangular frame with the corner point corresponding to the minimum transverse distance as a rectangular frame which is positioned outside two collision boundaries and has the corner point positioned inside the two passing boundaries, wherein the minimum transverse distance is the minimum transverse distance between the target rectangular frame and the own vehicle.

In some embodiments, the vehicle speed planning module 430 includes a deceleration acquisition sub-module and a vehicle speed planning sub-module.

And the deceleration acquisition sub-module is used for acquiring the deceleration corresponding to the target speed limit value.

And the vehicle speed planning sub-module is used for planning the speed of the own vehicle based on the deceleration.

It can be clearly understood by those skilled in the art that the vehicle speed planning device 400 provided in the embodiment of the present application can implement the vehicle speed planning method provided in the embodiment of the present application. The specific working process of the device and the module can refer to the corresponding process of the vehicle speed planning method in the embodiment of the application, and is not repeated here.

In the embodiments of the present application, the modules shown or discussed are coupled or directly coupled or communicatively coupled to each other via some interfaces, devices or modules, which may be electrical, mechanical or otherwise.

In addition, each functional module in the embodiment of the present application may be integrated in one processing module, or each module may exist alone physically, or two or more modules may be integrated in one module. The integrated modules may be implemented in hardware or in software as functional modules, which are not limited in this embodiment of the present application.

Referring to fig. 7, fig. 7 is a block diagram of a vehicle according to an embodiment of the application. The vehicle 500 may include one or more of the following components: the vehicle speed planning method provided by the embodiment of the application comprises a memory 510, one or more processors 520 and one or more application programs, wherein the one or more application programs can be stored in the memory 510 and configured to cause the one or more processors 520 to execute the vehicle speed planning method provided by the embodiment of the application when the one or more processors 520 call. The vehicle 500 is the same as the vehicle 11 shown in fig. 1.

Processor 520 may include one or more processing cores. The processor 520 utilizes various interfaces and lines to connect various portions of the overall vehicle 500 for executing or executing instructions, programs, code sets, or instruction sets stored in the memory 510, and for invoking execution or data stored in the memory 510, performing various functions of the vehicle 500, and processing data. Alternatively, the processor 520 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and editable logic array (Programmable Logic Array, PLA). The processor 520 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU) and a modem. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 520 and may be implemented solely by a single communication chip.

The Memory 510 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (ROM). Memory 510 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 510 may include a stored program area and a stored data area. The storage program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, and the like. The storage data area may store data created by the vehicle 500 in use, etc.

Referring to fig. 8, fig. 8 is a block diagram illustrating a computer readable storage medium according to an embodiment of the application. The computer readable storage medium 600 stores therein a program code 610, the program code 610 being configured to, when called by a processor, cause the processor to execute the above vehicle speed planning method provided by the embodiment of the present application.

The computer readable storage medium 600 may be an electronic Memory such as a flash Memory, an Electrically erasable programmable read-Only Memory (EEPROM), an erasable programmable read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), a hard disk, or a ROM. Optionally, the computer readable storage medium 600 comprises a Non-volatile computer readable medium (Non-Transitory Computer-Readable Storage Medium, non-TCRSM). The computer readable storage medium 600 has storage space for program code 610 that performs any of the method steps described above. These program code 610 can be read from or written to one or more computer program products. Program code 610 may be compressed in a suitable form.

In summary, the embodiments of the present application provide a vehicle speed planning method, apparatus, vehicle, and storage medium, which determine a target rectangular frame representing an obstacle that does not collide with a vehicle but is laterally close to the vehicle, determine a target speed limit value according to a minimum lateral distance between the target rectangular frame and the vehicle, and perform vehicle speed planning according to the target speed limit value, so that the vehicle can be reasonably speed-limited according to the minimum lateral distance between the obstacle and the vehicle, and speed response can be performed in advance, so that the collision with the obstacle having a relatively close distance between the vehicle is avoided, and thus the safety of automatic driving can be improved.

Finally, it should be noted that: the above embodiments are only for illustrating the technical scheme of the present application, and are not limited thereto. Although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle speed planning method, comprising:

Determining a target rectangular frame representing an obstacle according to a vehicle track and an obstacle track, wherein the minimum transverse distance between the target rectangular frame and the vehicle is positioned between a preset collision distance and a preset passing distance, the preset passing distance is larger than the preset collision distance, the obstacle track comprises a plurality of rectangular frames representing the obstacle, the vehicle track comprises a plurality of rectangular frames representing the vehicle, and the minimum transverse distance is the minimum transverse distance among the transverse distances between four corner points of the target rectangular frame and the vehicle track;

performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a target speed limit value;

and planning the speed of the own vehicle based on the target speed limit value.

2. The method of claim 1, wherein the performing a lookup process according to the minimum lateral distance between the target rectangular frame and the vehicle to obtain the target speed limit value comprises:

performing table lookup processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a preliminary speed limit value;

and if the preliminary speed limit value meets a preset condition, determining the preliminary speed limit value as a target speed limit value.

3. The method according to claim 2, wherein the method further comprises:

if the preliminary speed limit value does not meet the preset condition, continuing to perform table look-up processing in a preset mode until a preset minimum speed limit value is found, and determining the preset minimum speed limit value as the target speed limit value; or alternatively

If the preliminary speed limit value does not meet the preset condition, the preset minimum speed limit value is directly determined to be the target speed limit value.

4. A method according to claim 2 or 3, wherein the preset conditions comprise:

the vehicle reaches the preliminary speed limit value when the vehicle runs at a speed reduction by a preset deceleration from the current position to the position corresponding to the target rectangular frame; or alternatively

And the vehicle reaches the preliminary speed limiting value when the vehicle runs at a speed reduction corresponding to the preliminary speed limiting value from the current position to the position corresponding to the target rectangular frame, and different preliminary speed limiting values correspond to different decelerations.

5. The method of claim 1, wherein determining a target rectangular box characterizing an obstacle from the vehicle trajectory and the obstacle trajectory comprises:

determining two collision boundaries and two passing boundaries relative to the vehicle track, wherein the distance between the two collision boundaries is twice the preset collision distance, and the distance between the two passing boundaries is twice the preset passing distance;

A rectangular frame which is located outside the two collision boundaries but has corner points located inside the two passing boundaries in the rectangular frames on the obstacle track is determined as a target rectangular frame for representing the obstacle.

6. The method of claim 5, wherein the method of determining rectangular boxes each located outside two collision boundaries but having corner points located inside two traffic boundaries comprises:

acquiring the transverse distance between each corner of a rectangular frame on an obstacle track and a vehicle track to obtain four transverse distances;

determining a minimum lateral distance from the four lateral distances;

if the minimum transverse distance is between the preset collision distance and the preset passing distance, determining a rectangular frame with the corner point corresponding to the minimum transverse distance as a rectangular frame which is positioned outside two collision boundaries and has the corner point positioned inside the two passing boundaries, wherein the minimum transverse distance is the minimum transverse distance between the target rectangular frame and the own vehicle.

7. The method of claim 1, wherein planning the speed of the own vehicle based on the target speed limit value comprises:

acquiring deceleration corresponding to the target speed limit value;

And planning the speed of the own vehicle based on the deceleration.

8. A vehicle speed planning apparatus, comprising:

the device comprises a target determining module, a target detecting module and a target judging module, wherein the target determining module is used for determining a target rectangular frame for representing an obstacle according to a vehicle track and an obstacle track, the minimum transverse distance between the target rectangular frame and the vehicle is positioned between a preset collision distance and a preset passing distance, the preset passing distance is larger than the preset collision distance, the obstacle track comprises a plurality of rectangular frames for representing the obstacle, the vehicle track comprises a plurality of rectangular frames for representing the vehicle, and the minimum transverse distance is the minimum transverse distance among the transverse distances between four corner points of the target rectangular frame and the vehicle track;

the table look-up processing module is used for performing table look-up processing according to the minimum transverse distance between the target rectangular frame and the vehicle to obtain a target speed limit value;

and the vehicle speed planning module is used for planning the vehicle speed of the own vehicle based on the target speed limit value.

9. A vehicle, characterized by comprising:

a memory;

one or more processors;

one or more applications, wherein the one or more applications are stored in the memory and configured to, when invoked by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.

10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code configured to, when called by a processor, cause the processor to perform the method according to any of claims 1-7.