Local path planning method, device, equipment and medium based on environmental perception

Abstract

The present application provides a method, device, equipment and medium for local path planning based on environmental perception, wherein the method includes: perceiving the environmental information of the vehicle, determining the front radar drivable area, corner radar drivable area, forward-view drivable area, forward-view lane lines, circumferential drivable area and circumferential lane lines; fusing each drivable area multiple times to obtain a multi-source drivable area, fusing each lane line to obtain a fused lane line; positioning the vehicle according to a high-precision map and fused lane lines; judging the positioning results and road conditions, and based on the positioning results, planning a local path for the vehicle according to the radar drivable area, multi-source drivable area, high-precision map and fused lane lines. Based on the needs of collision avoidance and obstacle avoidance, the vehicle uses multiple sensors to perceive environmental information in real time, and combines with high-precision maps to complete local path planning based on environmental perception, accurately identify environmental risks, reduce collision accident rates, and improve driving safety.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent driving technology, and specifically to a local path planning method, device, equipment and medium based on environmental perception. Background Art

[0002] With the development of intelligent driving technology, enhancing the reliability and safety of intelligent driving based on environmental perception is a very important part of the path planning process. Currently, intelligent driving vehicles on the market basically plan their paths based on obstacle information and map information obtained by the vehicle's sensors and navigation. In the field of intelligent driving, perception is divided into target perception and environmental perception. The objects of target perception are objects that can move or be moved autonomously, such as various vehicles, pedestrians, and movable obstacles (cones, water barriers). Its purpose is to perform functions such as following vehicles, changing lanes, avoiding obstacles, and braking according to the target. The objects of environmental perception are inherent elements or facilities in the environment that cannot be moved, such as lane lines, guardrails, walls, curbs, ground markings, traffic signs, traffic lights, etc. Its purpose is to determine the collision risk of the environment based on lane lines, drivable areas, high-precision maps, etc., and plan the vehicle's driving path.

[0003] Traditional intelligent driving vehicles' path planning is mostly based on the vehicle's sensors and high-precision map information. During the path planning process, the combined effects of multi-source environmental information, lane lines, and high-precision maps are not taken into account. The differences in path planning are not clearly defined to design corresponding detailed path planning strategies. At the same time, the limitations of different environmental information perception sources are not considered. There is no detailed path planning strategy designed for scene differentiation. As a result, it is impossible to respond in a timely manner to inaccurate local path planning caused by dynamic changes in the on-site environment, thereby affecting driving safety. Summary of the Invention

[0004] In view of the shortcomings of the existing technology mentioned above, the present application provides a local path planning method, device, equipment and medium based on environmental perception to solve the technical problem that local path planning is inaccurate due to the failure to consider the combined effects of multi-source environmental information, lane lines, high-precision maps, and the limitations of different environmental information perception sources, thereby affecting driving safety.

[0005] In a first aspect, the present application provides a local path planning method based on environment perception, the method comprising:

[0006] Perceive the environmental information around the vehicle and determine the front radar drivable area, corner radar drivable area, forward vision drivable area, forward vision lane markings, peripheral vision drivable area, and peripheral vision lane markings;

[0007] The front radar drivable area and the corner radar drivable area are fused once to obtain a radar drivable area, the forward view drivable area and the peripheral view drivable area are fused twice to obtain a visual drivable area, the radar drivable area and the visual drivable area are fused three times to obtain a multi-source drivable area, and the forward view lane line and the peripheral view lane line are fused to obtain a fused lane line.

[0008] Positioning the vehicle according to the high-precision map and the fused lane line to obtain a positioning result;

[0009] The positioning result, road slope, road curvature radius and effective length of the lane line are judged, and based on the judgment result, local path planning is performed for the vehicle in a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map and the fused lane line to obtain a local path planning result.

[0010] In one embodiment of the present invention, obtaining the multi-source drivable area includes:

[0011] Obtaining a first area envelope point of the front radar drivable area, a second area envelope point of the corner radar drivable area, a third area envelope point of the forward vision drivable area, and a fourth area envelope point of the peripheral vision drivable area;

[0012] Establishing a coordinate system with the center of the rear axle of the vehicle as the origin, projecting the first area envelope points and the second area envelope points onto the coordinate system, performing the first fusion, and obtaining a first envelope point set;

[0013] Projecting the third region envelope points and the fourth region envelope points onto the coordinate system, performing the second fusion, and obtaining a second envelope point set;

[0014] The first envelope point set and the second envelope point set are fused to obtain the multi-source drivable area. In one embodiment of the present invention, based on the judgment result, local path planning for the vehicle in a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map, and the fused lane lines includes:

[0015] Detecting the actual position of the vehicle and obtaining the positioning result, and judging the positioning result based on the actual position;

[0016] If the positioning result is successful, the first effective length of the radar drivable area is compared with the effective length threshold to obtain a first result; if the first result is that the first effective length is less than or equal to the effective length threshold, the second effective length of the multi-source drivable area is compared with the effective length threshold to obtain a second result; if the first result is that the first effective length is greater than the effective length threshold, the local path planning is performed based on the high-precision map and the radar drivable area;

[0017] If the positioning result is positioning failure, the current road slope is compared with the road slope threshold to perform the local path planning according to the comparison result.

[0018] In one embodiment of the present invention, after obtaining the second result, the method further includes:

[0019] If the second effective length is less than or equal to the effective length threshold, performing the local path planning according to the high-precision map;

[0020] If the second effective length is greater than the effective length threshold, the local path planning is performed according to the high-precision map and the multi-source drivable area.

[0021] In one embodiment of the present invention, comparing the current road slope with a road slope threshold to perform the local path planning based on the comparison result includes:

[0022] If the current road slope is greater than or equal to the road slope threshold, comparing the first effective length with the effective length threshold to obtain a third result; if the third result is that the first effective length is less than or equal to the effective length threshold, issuing a first deceleration signal and performing the local path planning based on the effective length of the radar drivable area; if the third result is that the first effective length is greater than the effective length threshold, performing the local path planning based on the radar drivable area;

[0023] If the current road slope is less than the road slope threshold, the current road curvature radius is compared with the curvature radius threshold; if the current road curvature radius is greater than or equal to the curvature radius threshold, the first effective length is compared with the effective length threshold to obtain a fourth result; if the current road curvature radius is less than the curvature radius threshold, the lane line effective length of the fused lane line is compared with the lane line length threshold to perform the local path planning based on the comparison result.

[0024] In one embodiment of the present invention, after obtaining the fourth result, the method further includes:

[0025] If the first effective length is less than or equal to the effective length threshold, sending a second deceleration signal and performing the local path planning according to the effective length of the radar drivable area;

[0026] If the first effective length is greater than the effective length threshold, the local path planning is performed according to the radar drivable area.

[0027] In one embodiment of the present invention, comparing the effective lane length of the fused lane line with a lane length threshold to perform the local path planning based on the comparison result includes:

[0028] If the lane line effective length is greater than or equal to the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a fifth result; if the fifth result is that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain a sixth result; if the fifth result is that the first effective length is greater than the effective length threshold, the local path planning is performed based on the fused lane line and the radar drivable area;

[0029] If the effective length of the lane line is less than the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a seventh result; if the seventh result is that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain an eighth result; if the seventh result is that the first effective length is greater than the effective length threshold, the local path planning is performed according to the radar drivable area.

[0030] In one embodiment of the present invention, after obtaining the sixth result, the method further includes:

[0031] If the second effective length is less than or equal to the effective length threshold, performing the local path planning according to the fused lane line;

[0032] If the second effective length is greater than the effective length threshold, the local path planning is performed according to the fused lane line and the multi-source drivable area.

[0033] In one embodiment of the present invention, after obtaining the eighth result, the method further includes:

[0034] If the second effective length is less than or equal to the effective length threshold, issuing a third deceleration signal and performing the local path planning according to the effective length of the multi-source drivable area;

[0035] If the second effective length is greater than the effective length threshold, the local path planning is performed according to the effective length of the multi-source drivable area.

[0036] In one embodiment of the present invention, if the first effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is less than or equal to the effective length threshold, the collision warning function is locked.

[0037] In one embodiment of the present invention, after locking the collision warning function, the method further includes:

[0038] monitoring a length of a drivable area in the local path planning result, and comparing the length of the drivable area with a drivable area length threshold;

[0039] If the length of the drivable area is less than the drivable area length threshold, the emergency brake function is activated.

[0040] In one embodiment of the present invention, after monitoring the length of the drivable area in the local path planning result, the method further includes:

[0041] Calculating the vehicle's warning speed based on a preset warning time interval and the length of the drivable area;

[0042] The actual speed of the vehicle is determined based on the warning speed and the local path planning result.

[0043] In one embodiment of the present invention, the expression corresponding to the trajectory obtained by the local path planning is determined as:

[0044] y=a0+a1x+a2x 2 +a3x 3

[0045] Among them, y is the horizontal coordinate of the trajectory; x is the vertical coordinate of the trajectory; a0, a1, a2, and a3 are the lateral deviation, heading angle, road curvature, and road curvature change rate respectively.

[0046] In a second aspect, an embodiment of the present application provides a local path planning device based on environment perception, the device comprising:

[0047] The perception module is used to perceive the environmental information around the vehicle and determine the front radar drivable area, corner radar drivable area, forward vision drivable area, forward vision lane markings, peripheral vision drivable area and peripheral vision lane markings;

[0048] a fusion module for fusing the front radar drivable area and the corner radar drivable area once to obtain a radar drivable area, fusing the forward-view drivable area and the peripheral-view drivable area twice to obtain a visual drivable area, fusing the radar drivable area and the visual drivable area three times to obtain a multi-source drivable area, and fusing the forward-view lane lines and the peripheral-view lane lines to obtain fused lane lines;

[0049] A positioning module locates the vehicle based on the high-precision map and the fused lane lines to obtain a positioning result;

[0050] The local path planning module is used to judge the positioning result, road slope, road curvature radius and effective length of the lane line, and based on the judgment result, perform local path planning for the vehicle in a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map and the fused lane line to obtain the local path planning result.

[0051] In a third aspect, the present application provides an electronic device, comprising:

[0052] one or more processors;

[0053] A storage device is used to store one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the local path planning method based on environmental perception described in the first aspect.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the local path planning method based on environmental perception described in the first aspect.

[0055] As described above, the embodiments of the present invention provide a method, apparatus, device, and medium for local path planning based on environment perception, which have the following beneficial effects:

[0056] The vehicle's existing perception sensors perceive the surrounding environment in real time, obtaining the front radar drivable area, corner radar drivable area, forward-view drivable area, forward-view lane lines, surround-view drivable area, and surround-view lane lines. The drivable area envelope points are then fused three times for the front radar drivable area, corner radar drivable area, forward-view drivable area, and surround-view drivable area to obtain a multi-source drivable area. The forward-view lane lines and surround-view lane lines are then fused to obtain fused lane lines. The vehicle is then positioned using a high-precision map and the fused lane lines. Local path planning is then performed for the vehicle based on the positioning results, road slope, road curvature radius, and lane line effective length. This effectively combines multi-source environmental information, lane lines, and high-precision maps for local path planning, avoiding local path planning failures or inaccuracies due to perception anomalies in individual information sources. This accurately identifies environmental risks, reduces collision accident rates, and effectively improves driving safety.

[0057] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0059] Figure 1 is a schematic diagram of dual-lane environment information based on environment perception, shown in an exemplary embodiment of the present application;

[0060] Figure 2 is a schematic diagram of single-lane environmental information based on environmental perception, shown in an exemplary embodiment of the present application;

[0061] Figure 3 is a flowchart of a local path planning method based on environment perception shown in an exemplary embodiment of the present application;

[0062] Figure 4 This is a flowchart of a specific local path planning method based on environment perception shown in an exemplary embodiment of the present application;

[0063] Figure 5 is a logic diagram of an intelligent driving system based on environment perception shown in an exemplary embodiment of the present application;

[0064] Figure 6is a block diagram of a local path planning device based on environment perception, shown in an exemplary embodiment of the present application;

[0065] Figure 7 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0066] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application 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 application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0067] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0068] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0069] In intelligent vehicle driving technology, environmental perception involves sensing obstacles, lane markings, and traffic signs such as traffic lights around the vehicle, including road surfaces and static objects. This information is collected through cameras, lidar, millimeter-wave radar, and other technologies. With the advancement of intelligent vehicle driving technology, enhancing the reliability and safety of intelligent driving based on environmental perception is a crucial component of the path planning process. Traditional intelligent vehicles plan local paths based on their own sensors and high-precision maps. This local path planning process lacks integration of multiple sources of environmental information, lane markings, and high-precision maps, and fails to consider the limitations of different environmental information perception sources. Detailed local path planning strategies for different scenarios are not designed, resulting in inaccurate local path planning and impacting driving safety.

[0070] First of all, it should be explained that local path planning refers to planning the path of the vehicle within a short period of time based on the current local environment information, such as planning the path of the vehicle within 3s, 4s or 5s based on the current local environment information.

[0071] See Figure 1 , Figure 1 FIG is a schematic diagram of dual-lane environment information based on environment perception, shown in an exemplary embodiment of the present application. Figure 1 As shown, the area formed by the dashed lines on both sides (i.e., the drivable area boundaries) is the drivable area, and the solid lines on both sides and the middle dashed line are the lane lines. The drivable area boundaries are the boundaries formed by the static obstacles surrounding the vehicle. When there are no static obstacles in the lane, the drivable area boundaries are generally formed by the guardrails, walls, curbs, bushes, etc. on both sides of the lane. Therefore, when there are no static obstacles in the lane, the drivable area boundaries are located outside the lane lines. When the vehicle is driving according to its local driving path, this local driving path is planned centered under the lane lines on both sides of the lane (i.e., the part of the lane bounded by the right solid line and the middle dashed line) and is the driving route for a preset time period in the future.

[0072] See Figure 2 , Figure 2 FIG is a schematic diagram of single lane environment information based on environment perception, shown in an exemplary embodiment of the present application. Figure 2 As shown, the area formed by the dotted lines on both sides (i.e., the boundaries of the drivable area) is the drivable area, and the solid lines on both sides are lane lines. Since a wider soft shoulder is set on the right side of the single lane (i.e., the area formed by the rightmost dotted line and the solid line on the right), the vehicle takes the lane lines into consideration when planning the local path. Based on the boundary of the drivable area of ​​the vehicle, the vehicle drives along the right lane line in the lane. Therefore, in the case of a single lane, the local driving path is planned in the center under the boundary of the drivable area, and is the driving route within the preset time period in the future, which can effectively avoid the risk of collision with obstacles on both sides and improve driving safety.

[0073] In addition, it should be noted that the lane environment applicable to the local path planning method based on environmental perception provided in this application is not limited to single-lane and two-lane roads, but also includes other multi-lane roads as well as branches, ramps, small roads, etc., which are not restricted here.

[0074] See Figure 3 , Figure 3 This is a flow chart of a method for local path planning based on environment perception, illustrating an exemplary embodiment of the present application. It should be understood that this method may also be applicable to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment used for this method.

[0075] like Figure 3 As shown, in an exemplary embodiment, the local path planning method based on environment perception includes at least steps S301 to S304, which are described in detail as follows:

[0076] Step S301 , sensing the environmental information around the vehicle, and determining the front radar drivable area, corner radar drivable area, forward vision drivable area, forward vision lane markings, peripheral vision drivable area, and peripheral vision lane markings.

[0077] The vehicle includes, but is not limited to, tricycles, fuel vehicles, and new energy vehicles (i.e., plug-in hybrid vehicles, extended-range electric vehicles, hybrid vehicles, pure electric vehicles, hydrogen vehicles, ethanol vehicles, etc.). Since the environmental information involved in intelligent driving comes from sensor perception and high-precision maps, the environmental information surrounding the vehicle includes radar data and image information collected by the vehicle's perception sensors, namely radar and cameras, respectively. Of course, the perception information here can also include ultrasonic echo information, which is not further limited here.

[0078] The vehicle perception sensors include a front millimeter-wave radar, a corner millimeter-wave radar, a front-view camera, and a surround-view camera. The front millimeter-wave radar perceives the front radar drivable area, the corner millimeter-wave radar perceives the corner radar drivable area, the front-view camera perceives the front drivable area and the front lane line, and the surround-view camera perceives the surround-view drivable area and the surround-view lane line. It should be noted that in order to accurately cover the detection area, the front millimeter-wave radar is arranged on the front side of the vehicle, and the corner millimeter-wave radar is arranged at the top center of the vehicle; in order to form a panoramic image acquisition around the vehicle, the front-view camera is arranged on the front side of the vehicle, and the surround-view camera is arranged at the top center of the vehicle. The above arrangement position is only an optimal method, and there is no restriction on the arrangement position of each radar and camera here.

[0079] Step S302: fuse the front radar drivable area and the corner radar drivable area once to obtain the radar drivable area; fuse the forward drivable area and the peripheral drivable area twice to obtain the visual drivable area; fuse the radar drivable area and the visual drivable area three times to obtain the multi-source drivable area; fuse the forward lane line and the peripheral lane line to obtain the fused lane line.

[0080] It should be noted that the methods of obtaining drivable areas based on radar perception and cameras are mature existing technologies and will not be described in detail here. As for the obtained front radar drivable area, corner radar drivable area, forward-view drivable area and surround-view drivable area, it is necessary to further fuse the drivable areas, that is, fuse the envelope points of the drivable areas according to the radar and camera respectively. Specifically, the front radar drivable area and the corner radar drivable area are fused into the radar drivable area, the forward-view drivable area and the surround-view drivable area are fused into the visual drivable area, and then the radar drivable area and the visual drivable area are fused to obtain a multi-source drivable area. Lane lines need to be fused for the forward lane lines and the surround-view lane lines to obtain fused lane lines.

[0081] In one embodiment, obtaining a multi-source drivable area includes:

[0082] Obtaining a first area envelope point of the front radar drivable area, a second area envelope point of the corner radar drivable area, a third area envelope point of the forward vision drivable area, and a fourth area envelope point of the peripheral vision drivable area;

[0083] Establishing a coordinate system with the center of the rear axle of the vehicle as the origin, projecting the first area envelope points and the second area envelope points onto the coordinate system, performing the first fusion, and obtaining a first envelope point set;

[0084] Projecting the third region envelope points and the fourth region envelope points onto the coordinate system, performing the second fusion, and obtaining a second envelope point set;

[0085] The first envelope point set and the second envelope point set are fused to obtain the multi-source drivable area. Considering that the drivable areas reflected in the front radar drivable area, the corner radar drivable area, the forward-view drivable area and the circumferential-view drivable area are different, it is necessary to fuse each drivable area. Each drivable area can be considered to be composed of the envelope of local boundary points. When fusion is performed, the drivable area envelope points of the front radar drivable area and the corner radar drivable area are first projected into the vehicle coordinate system. Then, in the vehicle coordinate system, an envelope point is taken for each degree of 360° of the vehicle body. If there are several envelope points in this degree, the average position of the multiple envelope points is taken according to the weight. Finally, the radar drivable area composed of the envelope points of the front radar drivable area and the corner radar drivable area for 360° of the vehicle is obtained. The acquisition of the visual drivable area and the multi-source drivable area is similar and will not be repeated here. By fusing environmental information from different sources multiple times, the accuracy of the obtained multi-source drivable area is guaranteed, making the environmental information more accurate and reliable.

[0086] Step S303: Position the vehicle based on the high-precision map and the fused lane lines to obtain a positioning result.

[0087] Among them, the high-precision map includes map elements such as road shape, road markings, traffic signs and obstacles. The fused lane lines can be considered as the vehicle's real-time perception of the front lane lines and the surrounding lane lines, and the fusion of the two lane lines.

[0088] In step S304, the positioning result, road slope, road curvature radius, and effective lane line length are judged. Based on the judgment result, a local path planning is performed for the vehicle in a preset time period according to the radar drivable area, multi-source drivable area, high-precision map, and fused lane lines to obtain a local path planning result.

[0089] The road slope is the slope along the road's forward direction, specifically the effective road slope within the visually drivable area. The road curvature radius is the distance from the centerline of a curve to the center of the circle, specifically the effective road curvature radius within the visually drivable area. The lane effective length is the effective length of the fused lane lines. Local path planning for a preset time period can be considered as path planning for a shorter period of time, such as 3s, 4s, or 5s. After the vehicle's current position is determined based on the high-precision map and fused lane lines, the positioning result, road slope, road curvature radius, and effective lane line length are determined. Based on this determination, local path planning is performed for the vehicle. Different determinations lead to different local path planning strategies. Specifically, local path planning is performed for different situations based on the radar drivable area, multi-source drivable area, high-precision map, and fused lane lines.

[0090] In one embodiment, based on the judgment result, local path planning for the vehicle within a preset time period is performed according to the radar drivable area, the multi-source drivable area, the high-precision map, and the fused lane lines, including:

[0091] Detect the actual position of the vehicle and obtain the positioning result, and judge the positioning result based on the actual position;

[0092] If the positioning result is successful, the first effective length of the radar drivable area is compared with the effective length threshold to obtain a first result; if the first result shows that the first effective length is less than or equal to the effective length threshold, the second effective length of the multi-source drivable area is compared with the effective length threshold to obtain a second result; if the first result shows that the first effective length is greater than the effective length threshold, local path planning is performed based on the high-precision map and the radar drivable area;

[0093] If the positioning result is positioning failure, the current road slope is compared with the road slope threshold to perform local path planning based on the comparison result.

[0094] Specifically, after obtaining the second result, the method further includes:

[0095] If the second effective length is less than or equal to the effective length threshold, local path planning is performed according to the high-precision map;

[0096] If the second effective length is greater than the effective length threshold, local path planning is performed based on the high-precision map and the multi-source drivable area.

[0097] The accuracy of the positioning result of the vehicle is determined by detecting the actual position of the vehicle. The detection of the actual position can be obtained based on the navigation positioning of the vehicle. There is no restriction on the method of obtaining the actual position.

[0098] The effective length is the longer of the left and right boundaries of the drivable area. The first effective length for a radar drivable area is the longer of the left and right boundaries of the radar drivable area. The second effective length for a multi-source drivable area is the longer of the left and right boundaries of the multi-source drivable area.

[0099] Local path planning based on HD maps and radar drivable areas refers to using HD maps as the primary method, supplemented by radar drivable areas. This involves using the radar drivable areas to correct the local path planned by the HD map. Local path planning based on HD maps refers to using only HD maps for local path planning. Local path planning based on HD maps and multi-source drivable areas refers to using HD maps as the primary method, supplemented by multi-source drivable areas. This involves using multi-source drivable areas to correct the local path planned by the HD map. It should be noted that the specific local path can be calculated based on a pre-trained algorithm model, which will not be discussed in detail here.

[0100] In one embodiment, the current road slope is compared with a road slope threshold, and local path planning is performed based on the comparison result, including:

[0101] If the current road slope is greater than or equal to the road slope threshold, the first effective length is compared with the effective length threshold to obtain a third result; if the third result shows that the first effective length is less than or equal to the effective length threshold, a first deceleration signal is issued and local path planning is performed based on the effective length of the radar drivable area; if the third result shows that the first effective length is greater than the effective length threshold, local path planning is performed based on the radar drivable area;

[0102] If the current road slope is less than the road slope threshold, the current road curvature radius is compared with the curvature radius threshold; if the current road curvature radius is greater than or equal to the curvature radius threshold, the first effective length is compared with the effective length threshold to obtain a fourth result; if the current road curvature radius is less than the curvature radius threshold, the effective length of the fused lane line is compared with the lane line length threshold to perform local path planning based on the comparison result.

[0103] Specifically, after obtaining the fourth result, the method further includes:

[0104] If the first effective length is less than or equal to the effective length threshold, a second speed reduction signal is issued and local path planning is performed according to the effective length of the radar drivable area;

[0105] If the first effective length is greater than the effective length threshold, local path planning is performed according to the radar drivable area.

[0106] Considering that a slope affects the effective length of environmental perception and that the road beyond the top of the slope is not perceptible, especially when the current slope is greater than or equal to the road slope threshold, the vehicle will issue a first deceleration signal to reduce its speed to ensure driving safety. Furthermore, considering that the road curvature radius directly affects the speed and angle of a vehicle's turns and also affects the effective length of environmental perception, when the current road curvature radius is greater than or equal to the curvature radius threshold and the first effective length of the radar drivable area is less than or equal to the effective length threshold, the vehicle will issue a second deceleration signal to reduce its speed to ensure driving safety.

[0107] Local path planning is performed based on the radar drivable area, that is, only the radar drivable area is used for local path planning; local path planning is performed based on the effective length of the radar drivable area, that is, only the effective length of the radar drivable area is used for local path planning.

[0108] In one embodiment, the effective lane length of the fused lane line is compared with a lane length threshold, and local path planning is performed based on the comparison result, including:

[0109] If the lane line effective length is greater than or equal to the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a fifth result. If the fifth result shows that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain a sixth result. If the fifth result shows that the first effective length is greater than the effective length threshold, local path planning is performed based on the fused lane line and the radar drivable area.

[0110] If the effective length of the lane line is less than the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a seventh result; if the seventh result is that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain an eighth result; if the seventh result is that the first effective length is greater than the effective length threshold, local path planning is performed based on the radar drivable area.

[0111] Specifically, after obtaining the sixth result, the method further includes:

[0112] If the second effective length is less than or equal to the effective length threshold, local path planning is performed based on the fused lane line;

[0113] If the second effective length is greater than the effective length threshold, local path planning is performed based on the fused lane lines and multi-source drivable areas.

[0114] Specifically, after obtaining the eighth result, the method further includes:

[0115] If the second effective length is less than or equal to the effective length threshold, a third deceleration signal is issued and local path planning is performed according to the effective length of the multi-source drivable area;

[0116] If the second effective length is greater than the effective length threshold, local path planning is performed according to the effective length of the multi-source drivable area.

[0117] Local path planning based on fused lane lines and radar drivable areas means taking the fused lane lines as the main method and the radar drivable areas as the auxiliary method, that is, using the radar drivable areas to correct the local driving path planned based on the fused lane lines; local path planning based on fused lane lines means performing local path planning based only on the fused lane lines; local path planning based on fused lane lines and multi-source drivable areas means taking the fused lane lines as the main method and the multi-source drivable areas as the auxiliary method, that is, using the multi-source drivable areas to correct the local driving path planned based on the fused lane lines; local path planning based on the effective length of the multi-source drivable areas means performing local path planning based only on the effective length of the multi-source drivable areas.

[0118] It should be noted that if the effective lane line of the fused lane line is smaller than the lane line length threshold, it indicates that the detected fused lane line range is shorter. The area outside the effective length of the lane line is an area where lane line perception cannot be performed. The road conditions are unclear and there is a risk of collision. Therefore, when the first effective length and the second effective length are both smaller than or equal to the effective length threshold, in order to ensure driving safety, the vehicle will send a third deceleration signal to reduce the speed.

[0119] See Figure 4 , Figure 4This is a flowchart of a specific local path planning method based on environment perception, as shown in an exemplary embodiment of the present application. Figure 4 As shown, the specific local path planning method based on environment perception includes at least steps S401 to S412, which are described in detail as follows:

[0120] Step S401: Position the vehicle based on the high-precision map and the fused lane lines.

[0121] Step S402: Determine whether the positioning is successful.

[0122] Specifically, if the positioning is successful, proceed to step S403; if the positioning is unsuccessful, proceed to step S405.

[0123] Step S403: determine whether the effective length of the radar drivable area is ≤ 25 meters.

[0124] 25 meters is a preferred effective length threshold, which can be determined according to specific circumstances and is not limited here. The same applies below.

[0125] Specifically, if the effective length of the radar drivable area is ≤25 meters, proceed to step S404; if the effective length of the radar drivable area is greater than 25 meters, local path planning of the vehicle is performed based on the high-precision map and supplemented by the radar drivable area.

[0126] Step S404: determine whether the effective length of the multi-source drivable area is ≤ 25 meters.

[0127] Specifically, if the effective length of the multi-source drivable area is ≤25 meters, the local path planning of the vehicle will be carried out entirely based on the high-precision map; if the effective length of the multi-source drivable area is greater than 25 meters, the local path planning of the vehicle will be carried out mainly based on the high-precision map, with the multi-source drivable area as an auxiliary.

[0128] Step S405 , determining whether the current road slope is ≥ K_slope.

[0129] Specifically, if the current road slope is ≥K_slope, the process proceeds to step S406 ; if the current road slope is <K_slope, the process proceeds to step S407 .

[0130] Step S406: Determine whether the effective length of the radar drivable area is ≤ 25 meters.

[0131] Specifically, if the effective length of the radar drivable area is ≤25 meters, the speed is reduced and local path planning is performed based on the effective length of the radar drivable area; if the effective length of the radar drivable area is greater than 25 meters, local path planning is performed based on the radar drivable area.

[0132] Step S407: determine whether the current road curvature radius is greater than or equal to K_curvature.

[0133] Specifically, if the current road curvature radius is ≥K_curvature, the process proceeds to step S406 ; if the current road curvature radius is <K_curvature, the process proceeds to step S408 .

[0134] Step S408: Determine whether the lane line effective length is ≥ K_length.

[0135] Specifically, if the effective length of the lane line is ≥ K_length, then proceed to step S411; if the effective length of the lane line is < K_length, then proceed to step S409.

[0136] Step S409: determine whether the effective length of the radar drivable area is ≤ 25 meters.

[0137] Specifically, if the effective length of the radar drivable area is ≤25 meters, proceed to step S410; if the effective length of the radar drivable area is greater than 25 meters, perform local path planning based on the radar drivable area.

[0138] Step S410: Determine whether the effective length of the multi-source drivable area is ≤ 25 meters.

[0139] Specifically, if the effective length of the multi-source drivable area is ≤25 meters, the speed is reduced and local path planning is performed based on the effective length of the multi-source drivable area; if the effective length of the multi-source drivable area is greater than 25 meters, local path planning is performed based on the effective length of the multi-source drivable area.

[0140] Step S411: determine whether the effective length of the radar drivable area is ≤ 25 meters.

[0141] Specifically, if the effective length of the radar drivable area is ≤ 25 meters, proceed to step S412; if the effective length of the radar drivable area is greater than 25 meters, local path planning is performed based on the fused lane lines and supplemented by the radar drivable area.

[0142] Step S412: Determine whether the effective length of the multi-source drivable area is ≤ 25 meters.

[0143] Specifically, if the effective length of the multi-source drivable area is ≤25 meters, local path planning is performed entirely based on the fused lane lines; if the effective length of the multi-source drivable area is greater than 25 meters, local path planning is performed mainly based on the fused lane lines, with the multi-source drivable area as an auxiliary.

[0144] The above-mentioned local path planning method effectively solves the problem that the local path planning strategy is relatively one-sided when facing multi-source environmental information by constructing local path planning strategies in different scenarios and different conditions. It avoids the failure of the local path planning strategy when an abnormality or failure occurs in a certain information source, and avoids the frequent system exits and frequent requests for user takeover due to local path planning failures. In addition, the traditional method has low scenario adaptability when performing local path planning based on environmental perception.

[0145] Table 1: Parameters

[0146]

[0147]

[0148] In addition, the specific information corresponding to the parameters mentioned above can be referred to Table 1 above, where the initial values ​​in Table 1 are preferred values. Of course, the initial values ​​of each parameter can be determined according to the specific situation, and there is no limit on the value of the initial value here.

[0149] In one embodiment, if the first effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is less than or equal to the effective length threshold, the collision warning function is locked.

[0150] It should be noted that there are two possibilities for the short detection range of the drivable area: one is that there are fewer target obstacles on both sides of the road and fewer boundary points of the drivable area are detected, so the detection range of the drivable area is shorter, and the possibility of collision is smaller in this case; the other is that the sensor detection capability in the current scene is limited, and the detection range is smaller. For example, in scenes such as curves and pure concrete guardrails, the detection capabilities of visual cameras and millimeter-wave radars are poor, and the detection range of the drivable area is short. This situation is more dangerous and the possibility of collision is greater.

[0151] The collision warning function prevents the vehicle from colliding with obstacles. It determines the current collision risk based on environmental information and provides early warning to prevent serious collisions. The collision warning function is subject to certain activation conditions: It is activated when the first effective length of the radar-enabled drivable area is greater than the effective length threshold. If the first effective length of the radar-enabled drivable area is less than or equal to the effective length threshold, the second effective length of the multi-source drivable area is further compared with the effective length threshold. If the second effective length is greater than the effective length threshold, the collision warning function is activated. If the second effective length is less than or equal to the effective length threshold, the collision warning function is locked. It should be noted that the collision warning function can be considered to be initially off. When the activation conditions are met, the collision warning function is activated. If the activation conditions are not met, the collision warning function remains off.

[0152] Furthermore, after locking the collision warning function, the method further includes:

[0153] Monitor the length of the drivable area in the local path planning result and compare the drivable area length with the drivable area length threshold;

[0154] If the length of the drivable area is less than the drivable area length threshold, the emergency brake function is activated.

[0155] Among them, the length of the drivable area is the length of the drivable area of ​​the vehicle obtained after local path planning. Because local path planning is a real-time process, the local path planning results change in real time, and the length of the drivable area will also change in real time. The vehicle will monitor its drivable area length in real time, and then compare the drivable area length with the drivable area length threshold. When the drivable area length is less than the drivable area length threshold, the emergency brake function will be activated to prevent the vehicle from colliding with the target obstacle.

[0156] In one embodiment, after monitoring the length of the drivable area in the local path planning result, the method further includes:

[0157] Calculate the vehicle's warning speed based on the preset warning time interval and the length of the drivable area;

[0158] The actual speed of the vehicle is determined based on the warning speed and the local path planning results.

[0159] For example, the collision warning function requires a minimum effective length of 25m for the drivable area. When the drivable area length in the local path planning result monitored by this vehicle is 25m, if the collision warning interval is set to 2s, then the calculated warning speed is 12.5m / s. This warning speed can be understood as the maximum speed that the current drivable area can support. Then, the current actual speed is planned in combination with other requirements such as the scenario.

[0160] See Figure 5 , Figure 5 This is a logic diagram of an intelligent driving system based on environmental perception, shown in an exemplary embodiment of the present application. Figure 5 As shown, the intelligent driving system includes a perception module, a fusion module, a collision warning function module, a positioning module and a local path planning module, wherein the perception module is used to perceive the environmental information around the vehicle, determine the front radar drivable area, the corner radar drivable area, the forward drivable area, the forward lane line, the peripheral drivable area and the peripheral lane line; the fusion module is used to fuse the front radar drivable area and the corner radar drivable area once to obtain the radar drivable area, fuse the forward drivable area and the peripheral drivable area twice to obtain the visual drivable area, fuse the forward lane line and the peripheral lane line into a fused lane line, and fuse the radar drivable area and the visual drivable area Perform three fusions to obtain a multi-source drivable area; the positioning module is used to locate the vehicle based on the high-precision map and the fused lane line to obtain a positioning result; the local path planning module is used to judge the positioning result, road slope, road curvature radius and effective length of the lane line, and based on the judgment result, plan the local path of the vehicle according to the radar drivable area, the multi-source drivable area, the high-precision map and the fused lane line to obtain a local path planning result; the collision warning function module is used to judge whether the vehicle currently has a collision risk based on the first effective length of the radar drivable area or the second effective length of the multi-source drivable area, and give an early warning to avoid more serious collision accidents.

[0161] In one embodiment, it is characterized in that the expression corresponding to the trajectory obtained by local path planning is determined as:

[0162] y=a0+a1x+a2x 2 +a3x 3

[0163] Among them, y is the horizontal coordinate of the trajectory; x is the vertical coordinate of the trajectory; a0, a1, a2, and a3 are the lateral deviation, heading angle, road curvature, and road curvature change rate respectively.

[0164] Considering that the local path planning will change in real time, in order to prevent the vehicle from losing stability, the local path planning of the vehicle should ensure that the vehicle's motion trajectory is a smooth transition process. Therefore, the expression corresponding to the trajectory obtained by the local path planning is determined as: y = a0 + a1x + a2x 2 +a3x 3 ,During the path planning process, the change constraints of the cubic curve equation coefficients of path planning are as follows:

[0165] 1. The change difference of a0 is ≤ k_0;

[0166] 2. The change difference of a1 is ≤ k_1;

[0167] 3. The change difference of a2 is ≤ k_2;

[0168] 4. The change difference of a3 is ≤ k_3;

[0169] The specific information corresponding to k_0, k_1, k_2, and k_3 can be found in Table 1. The maximum value of a2, k_2, is affected by the vehicle's speed and is negatively correlated with it. a3 has a small value and a narrow range of variation, so it has little impact on path planning.

[0170] The local path planning method based on environmental perception provided in the above embodiment perceives the environmental information around the vehicle in real time through the existing perception sensors of the vehicle, obtains the front radar drivable area, the corner radar drivable area, the forward drivable area, the forward lane line, the peripheral drivable area and the peripheral lane line, and then performs three fusion of the drivable area envelope points of the front radar drivable area, the corner radar drivable area, the forward drivable area and the peripheral drivable area to obtain the multi-source drivable area, performs lane line fusion on the forward lane line and the peripheral lane line to obtain the fused lane line, and then combines the fused lane line and the forward lane line to obtain the fused lane line. The vehicle is positioned by combining high-precision maps and fused lane lines, and local path planning is performed for the vehicle within a preset time period based on the positioning results, road slope, road curvature radius, and effective lane line length. This is done by effectively combining multi-source environmental information, lane lines, and high-precision maps for local path planning, avoiding problems such as failure or inaccurate local path planning due to perception anomalies of individual information sources, accurately identifying environmental risks, reducing collision accident rates, and effectively improving driving safety.

[0171] See Figure 6 , Figure 6 is a block diagram of a local path planning device based on environment perception, as shown in an exemplary embodiment of the present application. Figure 6 As shown, this embodiment provides a local path planning device 600 based on environment perception, which includes:

[0172] The perception module 601 is used to perceive the environmental information around the vehicle and determine the front radar drivable area, the corner radar drivable area, the forward vision drivable area, the forward vision lane markings, the circumferential vision drivable area and the circumferential vision lane markings;

[0173] Fusion module 602 is configured to perform a primary fusion of the front radar drivable area and the corner radar drivable area to obtain a radar drivable area, perform a secondary fusion of the forward drivable area and the peripheral drivable area to obtain a visual drivable area, perform a tertiary fusion of the radar drivable area and the visual drivable area to obtain a multi-source drivable area, and perform lane line fusion of the forward lane lines and the peripheral lane lines to obtain fused lane lines;

[0174] The positioning module 603 locates the vehicle based on the high-precision map and the integrated lane lines to obtain a positioning result;

[0175] The local path planning module 604 is used to judge the positioning results, road slope, road curvature radius and effective lane line length, and based on the judgment results, plan the local path of the vehicle for a preset time period according to the radar drivable area, multi-source drivable area, high-precision map and fused lane lines to obtain the local path planning results.

[0176] It should be noted that the local path planning device based on environmental perception provided in the above embodiment and the local path planning method based on environmental perception provided in the above embodiment belong to the same concept, and the specific method of executing the operation of each step has been described in detail in the system embodiment and will not be repeated here.

[0177] An embodiment of the present application further provides an electronic device, including:

[0178] one or more processors;

[0179] The storage device is used to store one or more programs. When the one or more programs are executed by one or more processors, the electronic device implements the local path planning method based on environment perception provided in the above embodiment.

[0180] See Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. Figure 7 The electronic device 700 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0181] like Figure 7As shown, electronic device 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in read-only memory (ROM) 702 or the program loaded from storage portion 708 into random access memory (RAM) 703, such as the method for executing the above embodiment. In RAM 703, various programs and data required for system operation are also stored. CPU 701, ROM 702 and RAM 703 are connected to each other via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0182] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output section 707 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. Removable media 711, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 710 as needed, so that computer programs read therefrom can be installed into the storage section 708 as needed.

[0183] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 709, and / or installed from a removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the various functions defined in the system of the present application are executed.

[0184] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0186] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0187] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the aforementioned method for local path planning based on environmental perception. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0188] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A local path planning method based on environment perception, characterized in that: The method comprises: Perceive the environmental information around the vehicle and determine the front radar drivable area, corner radar drivable area, forward vision drivable area, forward vision lane markings, peripheral vision drivable area, and peripheral vision lane markings; The front radar drivable area and the corner radar drivable area are fused once to obtain a radar drivable area, the forward view drivable area and the peripheral view drivable area are fused twice to obtain a visual drivable area, the radar drivable area and the visual drivable area are fused three times to obtain a multi-source drivable area, and the forward view lane line and the peripheral view lane line are fused to obtain a fused lane line. Positioning the vehicle according to the high-precision map and the fused lane line to obtain a positioning result; Determining the positioning result, the road slope, the road curvature radius, and the effective length of the lane line, and based on the determination result, performing local path planning for the vehicle within a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map, and the fused lane line, to obtain a local path planning result; The obtaining of the multi-source drivable area includes: obtaining a first area envelope point of the front radar drivable area, a second area envelope point of the corner radar drivable area, a third area envelope point of the forward-view drivable area, and a fourth area envelope point of the peripheral-view drivable area; establishing a coordinate system with the center of the rear axle of the vehicle as the origin, projecting the first area envelope point and the second area envelope point onto the coordinate system, performing the first fusion to obtain a first envelope point set; projecting the third area envelope point and the fourth area envelope point onto the coordinate system, performing the second fusion to obtain a second envelope point set; and performing the third fusion on the first envelope point set and the second envelope point set to obtain the multi-source drivable area.

2. The local path planning method based on environment perception according to claim 1, characterized in that: Based on the judgment result, local path planning is performed for the vehicle in a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map, and the fused lane line, including: Detecting the actual position of the vehicle and obtaining the positioning result, and judging the positioning result based on the actual position; If the positioning result is successful, the first effective length of the radar drivable area is compared with the effective length threshold to obtain a first result; if the first result is that the first effective length is less than or equal to the effective length threshold, the second effective length of the multi-source drivable area is compared with the effective length threshold to obtain a second result; if the first result is that the first effective length is greater than the effective length threshold, the local path planning is performed based on the high-precision map and the radar drivable area; If the positioning result is positioning failure, the current road slope is compared with the road slope threshold to perform the local path planning according to the comparison result.

3. The local path planning method based on environment perception according to claim 2, characterized in that: After obtaining the second result, the method further includes: If the second effective length is less than or equal to the effective length threshold, performing the local path planning according to the high-precision map; If the second effective length is greater than the effective length threshold, the local path planning is performed according to the high-precision map and the multi-source drivable area.

4. The local path planning method based on environment perception according to claim 2, characterized in that: The current road slope is compared with the road slope threshold, and local path planning is performed according to the comparison result, including: If the current road slope is greater than or equal to the road slope threshold, comparing the first effective length with the effective length threshold to obtain a third result; if the third result is that the first effective length is less than or equal to the effective length threshold, issuing a first deceleration signal and performing the local path planning based on the effective length of the radar drivable area; if the third result is that the first effective length is greater than the effective length threshold, performing the local path planning based on the radar drivable area; If the current road slope is less than the road slope threshold, the current road curvature radius is compared with the curvature radius threshold; if the current road curvature radius is greater than or equal to the curvature radius threshold, the first effective length is compared with the effective length threshold to obtain a fourth result; if the current road curvature radius is less than the curvature radius threshold, the lane line effective length of the fused lane line is compared with the lane line length threshold to perform the local path planning based on the comparison result.

5. The local path planning method based on environment perception according to claim 4, characterized in that: After obtaining the fourth result, the method further includes: If the first effective length is less than or equal to the effective length threshold, sending a second deceleration signal and performing the local path planning according to the effective length of the radar drivable area; If the first effective length is greater than the effective length threshold, the local path planning is performed according to the radar drivable area.

6. The local path planning method based on environment perception according to claim 4, characterized in that: The method of comparing the effective lane length of the fused lane line with a lane length threshold to perform local path planning according to the comparison result includes: If the lane line effective length is greater than or equal to the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a fifth result; if the fifth result is that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain a sixth result; if the fifth result is that the first effective length is greater than the effective length threshold, the local path planning is performed based on the fused lane line and the radar drivable area; If the effective length of the lane line is less than the lane line length threshold, the first effective length is compared with the effective length threshold to obtain a seventh result; if the seventh result is that the first effective length is less than or equal to the effective length threshold, the second effective length is compared with the effective length threshold to obtain an eighth result; if the seventh result is that the first effective length is greater than the effective length threshold, the local path planning is performed according to the radar drivable area.

7. The local path planning method based on environment perception according to claim 6, characterized in that: After obtaining the sixth result, the method further includes: If the second effective length is less than or equal to the effective length threshold, performing the local path planning according to the fused lane line; If the second effective length is greater than the effective length threshold, the local path planning is performed according to the fused lane line and the multi-source drivable area.

8. The local path planning method based on environment perception according to claim 6, characterized in that: After obtaining the eighth result, the method further includes: If the second effective length is less than or equal to the effective length threshold, issuing a third deceleration signal and performing the local path planning according to the effective length of the multi-source drivable area; If the second effective length is greater than the effective length threshold, the local path planning is performed according to the effective length of the multi-source drivable area.

9. The local path planning method based on environment perception according to any one of claims 2 to 8, characterized in that: If the first effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is greater than the effective length threshold, the collision warning function is activated; if the second effective length is less than or equal to the effective length threshold, the collision warning function is locked.

10. The local path planning method based on environment perception according to claim 9, characterized in that: After locking the collision warning function, the method further includes: monitoring a length of a drivable area in the local path planning result, and comparing the length of the drivable area with a drivable area length threshold; If the length of the drivable area is less than the drivable area length threshold, the emergency brake function is activated.

11. The method for local path planning based on environment perception according to claim 10, characterized in that: After monitoring the length of the drivable area in the local path planning result, the method further includes: Calculating the vehicle's warning speed based on a preset warning time interval and the length of the drivable area; The actual speed of the vehicle is determined based on the warning speed and the local path planning result.

12. The local path planning method based on environment perception according to any one of claims 1 to 8, characterized in that: The expression corresponding to the trajectory obtained by the local path planning is determined as: in, is the horizontal coordinate of the trajectory; is the ordinate of the trajectory; a0, a1, a2, and a3 are the lateral deviation, heading angle, road curvature, and road curvature change rate, respectively.

13. A local path planning device based on environment perception, characterized in that: The device comprises: The perception module is used to perceive the environmental information around the vehicle and determine the front radar drivable area, corner radar drivable area, forward vision drivable area, forward vision lane markings, peripheral vision drivable area and peripheral vision lane markings; a fusion module for fusing the front radar drivable area and the corner radar drivable area once to obtain a radar drivable area, fusing the forward-view drivable area and the peripheral-view drivable area twice to obtain a visual drivable area, fusing the radar drivable area and the visual drivable area three times to obtain a multi-source drivable area, and fusing the forward-view lane lines and the peripheral-view lane lines to obtain fused lane lines; A positioning module locates the vehicle based on the high-precision map and the fused lane lines to obtain a positioning result; a local path planning module, configured to determine the positioning result, the road slope, the road curvature radius, and the effective length of the lane line, and based on the determination result, perform local path planning for the vehicle within a preset time period according to the radar drivable area, the multi-source drivable area, the high-precision map, and the fused lane line, to obtain a local path planning result; The fusion module is specifically used to obtain the first area envelope point of the front radar drivable area, the second area envelope point of the corner radar drivable area, the third area envelope point of the forward-view drivable area, and the fourth area envelope point of the surround-view drivable area; establish a coordinate system with the center of the rear axle of the vehicle as the origin, project the first area envelope point and the second area envelope point onto the coordinate system, perform the first fusion, and obtain a first envelope point set; project the third area envelope point and the fourth area envelope point onto the coordinate system, perform the second fusion, and obtain a second envelope point set; perform the third fusion on the first envelope point set and the second envelope point set to obtain the multi-source drivable area.

14. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the local path planning method based on environmental perception as described in any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the local path planning method based on environment perception according to any one of claims 1 to 12.

Images