Method and apparatus for detecting drivable region, and vehicle

Abstract

Provided in the present application are a method and apparatus for detecting a drivable region, and a vehicle, which can be applied to the field of intelligent driving. The method comprises: acquiring data collected by means of a sensor; and on the basis of the data, determining information of a drivable region of a vehicle, wherein the information of a drivable region includes a road attribute and / or a boundary attribute of the drivable region. The present application can be applied to intelligent vehicles or electric vehicles, helping to improve the accuracy of planning and decision-making which are performed by vehicles, and also helping to reduce the cost of intelligent driving.

Description

Methods, devices and vehicles for detecting drivable areas

[0001] This application claims priority to Chinese Patent Application No. 202411049392.0, filed with the China National Intellectual Property Administration on July 31, 2024, entitled "Drivable Area Detection Method, Apparatus and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to a method, apparatus, and vehicle for detecting drivable areas. Background Technology

[0003] Vehicles in autonomous driving mode rely on the detection results of their drivable area when making planning and decisions. Currently, the detection of the drivable domain depends on high-definition (HD) maps. On the one hand, HD maps have poor real-time performance. In scenarios involving changes in road topology, such as road construction and detours, the drivable area obtained by the vehicle in autonomous driving mode through the HD map may be incorrect, leading to inaccurate planning and decisions. On the other hand, relying on HD maps also results in higher costs for autonomous driving. Summary of the Invention

[0004] This application provides a drivable area detection method, device, and vehicle, which determines the drivable area of ​​a vehicle by collecting data from sensors, which helps improve the accuracy of vehicle planning and decision-making, and also helps reduce the cost of intelligent driving.

[0005] In a first aspect, this application provides a method for detecting a drivable area, the method comprising: acquiring data collected by a sensor; determining environmental information around a vehicle based on the data, the environmental information including information about a drivable area and first information, wherein the drivable area is determined by other targets around the vehicle besides dynamic targets and static road structure elements, and the first information includes the dynamic target and / or the static road structure elements.

[0006] Based on the above technical solution, the generation of drivable areas does not rely on high-precision maps but on data collected by sensors. This helps improve the accuracy of vehicle planning and decision-making, and also helps reduce the cost of intelligent driving. Simultaneously, the generation of drivable area information does not depend on dynamic targets or static road structure elements; that is, the generation of drivable areas is independent of road topology. This avoids the inability to detect drivable areas due to lost road topology, and also avoids unstable detection results due to unstable road topology, which could lead to unexpected steering and degradation issues. Thus, when vehicles are driving on roads without road topology (e.g., unstructured roads), or when the road topology is lost or unstable during vehicle operation, they can rely on this drivable area as a fallback, avoiding unexpected steering and degradation issues caused by unstable drivable area detection results, thereby helping to ensure user driving safety.

[0007] Furthermore, the current representation of drivable areas includes information such as dynamic obstacles, static obstacles, and road boundaries. Areas occupied by dynamic obstacles at the current moment, such as vehicles, pedestrians, and non-motorized vehicles, may be considered drivable areas. This representation is detrimental to the planning and control module's ability to generate strategies and plan trajectories for future moments. Based on the above technical solution, determining the drivable area using targets other than dynamic targets and static road structure elements can maximize the description of the vehicle's drivable area, enabling vehicles to bypass lane line semantic boundaries without exceeding physical boundaries. For example, vehicles can use the oncoming lane to avoid obstacles based on the drivable area.

[0008] In some possible implementations, the dynamic target includes dynamic vehicles, pedestrians, non-motorized vehicles, etc.

[0009] In some possible implementations, the static elements of the road structure include lane lines, lane turning arrows, etc.

[0010] In some possible implementations, the other target includes one or more of the following: negative obstacles (e.g., ditches, cliffs, etc.), road boundaries (e.g., curbs), immovable static obstacles (e.g., guardrails, fences), and static obstacles spaced at intervals less than or equal to a preset interval (e.g., continuously arranged water-filled barriers or traffic cones).

[0011] For example, the environmental information includes multiple levels of information, such as the drivable area as the first level (e.g., the bottom level), static road structure elements as the second level (e.g., the middle level), and dynamic targets as the third level (e.g., the high level). In this way, the environmental information around the vehicle can be completely expressed through different levels.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, determining the environmental information around the vehicle based on the data includes: inputting the data into a prediction model to obtain the features of multiple grids, the features of which include whether each grid is a grid corresponding to a drivable area and the visibility of each grid; and determining the information of the drivable area based on the features of the multiple grids in different time domains.

[0013] In some possible implementations, the characteristics of each grid also include the occupancy of each grid.

[0014] The drivable area attribute of each grid can be used to indicate whether each grid corresponds to a drivable area or a non-drivable area.

[0015] The visibility of each grid cell output by the above prediction model can be represented by a visibility value. For example, the visibility value of each grid cell can be represented by a value between 0 and 1.

[0016] Optionally, based on the data, the environmental information surrounding the vehicle is determined, including: inputting the data into a drivable area prediction model to obtain the features of multiple grids, each grid's features including its drivable area attributes and visibility; determining the state of each grid based on the drivable area attributes and visibility of the multiple grids corresponding to a single frame of data; generating scalarized data of the drivable area based on the states of the visible grids in multiple frames and the states of the grids in multiple frames; and vectorizing the scalarized data to obtain the environmental information.

[0017] The visible grid state above can be the confidence level of the visible grids among multiple grids that are drivable areas. The multi-frame imaginary grid state can be the confidence level of the invisible grids among multiple grids that are drivable areas.

[0018] For example, data from the previous frame collected by sensors can determine that a certain area is visible and drivable. In the next frame, if this area is occluded (or becomes invisible), and the supplementary information output by the prediction model indicates that the area is still drivable, then it can be determined that the area remains drivable. Alternatively, if the supplementary information output by the prediction model indicates that the area is not drivable, and the cumulative output results for multiple frames are all non-drivable, then the confidence that the area is drivable will continuously decrease. For example, when this confidence drops below a certain threshold, the area can be determined to be non-drivable.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the environmental information surrounding the vehicle is determined based on the data, including: inputting the data into a prediction model to obtain information on the drivable area grid, the visibility and occupancy of the grid; and determining the information of the drivable area based on the information on the drivable area grid, the visibility and occupancy of the grid in different time domains.

[0020] In some possible implementations, the environmental information surrounding the vehicle is determined based on this data, including: inputting the data into a drivable area prediction model to obtain information on drivable area grids, grid visibility, and whether grids are occupied; determining whether drivable area grids are visible based on the drivable area grids corresponding to single-frame data and the visibility of grids corresponding to single-frame data; generating scalar data of the drivable area based on updating the state of visible grids in multiple frames, updating the state of supplementary grids in multiple frames, and the occupancy of grids; and vectorizing the scalar data to obtain the environmental information.

[0021] For example, the confidence level is higher for visible graticles and lower for imaginary graticles.

[0022] For example, the data from the previous frame collected by the sensor can determine that the area is a visible drivable area. If the area is occluded in the next frame, and the prediction model outputs supplementary information indicating that the area is still a drivable area, then the area remains a drivable area. However, if the prediction model outputs supplementary information indicating that the area is a non-drivable area, and the output results for multiple frames are all non-drivable areas, it will affect the attribute of the drivable area.

[0023] Based on the above technical solution, by attenuating the data in the time domain, the memory cycle of the drivable area can be enhanced. This attenuation can be understood as having higher confidence in visible information and lower confidence in information that is merely imagined.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, determining environmental information around the vehicle based on the data includes: determining the environmental information based on the data and second information, wherein the second information includes at least one of a standard definition (SD) map, crowdsourced data, or real-time traffic flow information.

[0025] Based on the above technical solutions, combining at least one of SD maps, crowdsourced data, and real-time traffic flow information can help achieve beyond-line-of-sight detection of drivable areas. This helps to increase the range of detected drivable areas, providing more options for the planning and decision-making of the traffic control module.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the other objective includes one or more of the following: immovable stationary obstacles, static obstacles with an interval less than or equal to a preset interval, or negative obstacles.

[0027] Based on the above technical solution, the vehicle can determine the drivable area by combining the first static obstacle and the negative obstacle. In this way, by detecting the negative obstacle, the vehicle can avoid driving into the negative obstacle, thereby helping to avoid the vehicle falling off the road and improving the safety of the user.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, the drivable area includes a first area, the information of the drivable area includes boundary attributes of the first area, the boundary attributes include soft boundaries and / or hard boundaries, wherein the soft boundary includes the boundary where the first area and the second area intersect, the road attributes of the first area indicate a first road surface type, the road attributes of the second area indicate a second road surface type, the traffic priority of the first road surface type is higher than the traffic priority of the second road surface type; the hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge and cliff edge.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the information of the drivable area includes the road attributes of the drivable area, which include the road type of one or more polygonal regions where the drivable area is located, and the road type is used to indicate that the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy road surface.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: sending the environmental information to the planning and control module.

[0031] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the vehicle's movement based on the environmental information.

[0032] Secondly, a method for detecting drivable areas is provided, the method comprising: acquiring data collected by sensors; and determining information about the drivable area of ​​the vehicle based on the data, the information about the drivable area including road attributes and / or boundary attributes of the drivable area.

[0033] Based on the above technical solution, data collected by sensors can determine the vehicle's drivable area, eliminating the need for high-precision maps and helping to reduce the costs associated with intelligent driving. Furthermore, this drivable area information, including road attributes and / or boundary attributes, can improve the accuracy of vehicle planning and decision-making, thereby enhancing user safety.

[0034] In some possible implementations, the method further includes: determining that the vehicle is in an intelligent driving state.

[0035] In some possible implementations, the road attributes of the drivable area include the road type of one or more polygonal regions where the drivable area is located, which indicates whether the polygonal region is a dry road, a flooded road, a slippery road, a snow-covered road, a gravel road, an oil-stained road, or a grassy area.

[0036] In some possible implementations, the boundary attribute may include soft boundaries and / or hard boundaries, where there is a risk of accident or collision if the vehicle crosses the hard boundary.

[0037] In some possible implementations, the drivable area includes a first area, the boundary attributes of which include information on soft boundaries and / or hard boundaries, wherein the soft boundary includes the boundary where the first area and the second area intersect, the road attributes of the first area indicate a first road surface type, the road attributes of the second area indicate a second road surface type, and the traffic priority of the first road surface type is higher than that of the second road surface type; the hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, determining the information of the drivable area of ​​the vehicle based on the data includes: determining information of a first static obstacle based on the data, the first static obstacle including other targets around the vehicle besides dynamic targets and static elements of the road structure; and determining information of the drivable area based on the information of the first static obstacle.

[0039] Based on the above technical solution, the determination of the drivable area does not depend on dynamic targets or static road structure elements, that is, it does not depend on dynamic targets or road topology. This avoids the accuracy of drivable area detection results being affected by a lack of road topology or by road topology instability, thereby helping to improve user driving safety.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, determining the information of the first static obstacle based on the data includes: inputting the data into a prediction model to obtain the information of the first static obstacle.

[0041] Based on the above technical solution, by inputting the data collected by the sensors into the prediction model, the information of the first static obstacle can be predicted. In this way, the trained prediction model can directly output information about static obstacles related to the detected drivable area, which helps improve the efficiency of drivable area detection.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, determining the information of the first static obstacle based on the data includes: determining multiple targets based on the data, the multiple targets including the first target and the information of the first static obstacle, the first target including dynamic targets and / or static elements of road structures; and selecting the first static obstacle from the multiple targets.

[0043] Based on the above technical solution, when there are first static obstacles, dynamic targets and static road structure elements among the multiple targets detected by the data collected by the sensor, the first static obstacle can be selected from the multiple targets, and then the drivable area of ​​the vehicle can be determined based on the first static obstacle.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, determining the information of the drivable area based on the information of the first static obstacle includes: determining the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located; and determining the drivable area based on a preset detection area and the non-drivable area, wherein the drivable area is the area in the preset detection area excluding the non-drivable area.

[0045] Based on the above technical solution, the non-drivable area can be determined by the area where the first static obstacle is located, rather than by simply drawing lines (e.g., distinguishing drivable and non-drivable areas by the inside / outside of lines). This helps to increase the range of detected drivable areas while ensuring user safety, providing more options for the planning and decision-making of the traffic control module.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, determining the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located includes: determining the non-drivable area based on the polygonal outline of the first static obstacle.

[0047] Based on the above technical solution, non-drivable areas are determined by combining the polygonal outlines of static obstacles, rather than by simply drawing lines or using rectangular boxes. This helps to increase the range of detected drivable areas while ensuring user safety, providing more options for the planning and decision-making of the traffic control module.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, determining the non-drivable area based on the polygonal outline of the first static obstacle includes: determining a first polygonal outline of the first static obstacle based on the data; predicting a second polygonal outline of the first static obstacle based on the type of the first static obstacle and the first polygonal outline; and determining the non-drivable area based on the first polygonal outline and the second polygonal outline.

[0049] Based on the above technical solution, the non-drivable area can be determined by the first polygonal contour line detected by the sensor and the second polygonal contour line predicted, which helps to increase the range of the detected drivable area and provide more options for the planning and decision-making of the planning and control module.

[0050] In conjunction with the second aspect, in some implementations of the second aspect, determining the information of the first static obstacle based on the data includes: determining the information of the first static obstacle and the information of the negative obstacle based on the data; wherein, determining the information of the drivable area based on the information of the first static obstacle includes: determining the information of the drivable area based on the information of the first static obstacle and the information of the negative obstacle.

[0051] Based on the above technical solution, the vehicle can determine the drivable area by combining the first static obstacle and the negative obstacle. In this way, by detecting the negative obstacle, the vehicle can avoid driving into the negative obstacle, thereby helping to avoid the vehicle falling off the road and improving the safety of the user.

[0052] In conjunction with the second aspect, in some implementations of the second aspect, determining the information on the vehicle's drivable area based on the data includes: determining the information on the vehicle's drivable area based on the data and first information, wherein the first information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0053] Based on the above technical solutions, combining at least one of SD maps, crowdsourced data, and real-time traffic flow information can help achieve beyond-line-of-sight detection of drivable areas. This helps to increase the range of detected drivable areas, providing more options for the planning and decision-making of the traffic control module.

[0054] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending information about the drivable area to the planning and control module.

[0055] Based on the above technical solution, after the perception module obtains information about the drivable area, it can send the information about the drivable area to the planning and control module so that the planning and control module can make plans and decisions based on the drivable area.

[0056] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: when it is determined from the data that the area around the vehicle includes a second target, sending information about the second target to the control module, the second target including dynamic targets and / or static elements of the road structure.

[0057] Based on the above technical solution, if the data collected by the sensors determines that there is a second target around the vehicle, the perception module can send information about the drivable area to the planning and control module, as well as information about the second target, so that the planning and control module can make plans and decisions based on the information about the drivable area and the second target.

[0058] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: controlling the vehicle's movement based on the boundary attributes and / or road attributes of the drivable area.

[0059] In some possible implementations, controlling the vehicle's movement based on the boundary attributes and / or road attributes of the drivable area includes: controlling the distance between the vehicle and the soft boundary to be greater than or equal to a first preset distance; or, controlling the distance between the vehicle and the hard boundary to be greater than or equal to a second preset distance; wherein the second preset distance is greater than the first preset distance.

[0060] Based on the above technical solutions, for hard boundaries, the distance between the vehicle and the boundary can be increased, which can reduce the risk of vehicle accidents.

[0061] In some possible implementations, the vehicle's movement is controlled based on the boundary attributes and / or road attributes of the drivable area, including: when it is detected that the collision risk between the vehicle and an obstacle meets preset conditions and the collision risk can be avoided after the vehicle crosses the soft boundary, the vehicle is controlled to cross the soft boundary.

[0062] Based on the above technical solution, if a vehicle can avoid collision risk when it breaks through a soft boundary, then the vehicle can break through the soft boundary in an emergency, thereby helping to improve the driving safety of users. Thirdly, this application provides a drivable area detection device, which includes: an acquisition unit for acquiring data collected by sensors; and a determination unit for determining environmental information around the vehicle based on the data. The environmental information includes information about the drivable area and first information. The drivable area is determined by targets around the vehicle other than dynamic targets and static road structure elements. The first information includes dynamic targets and / or static road structure elements.

[0063] In conjunction with the third aspect, in some implementations of the third aspect, the determining unit is specifically used to: input the data into a prediction model to obtain features of multiple grids, the features of the multiple grids including whether each grid is a drivable area and the visibility of each grid; and determine the information of the drivable area based on the features of the multiple grids in different time domains.

[0064] In conjunction with the third aspect, in some implementations of the third aspect, the determining unit is specifically used to: determine the environmental information based on the data and the second information, wherein the second information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0065] In conjunction with the third aspect, in some implementations of the third aspect, the other objective includes one or more of the following: immovable stationary obstacles, static obstacles with an interval less than or equal to a preset interval, or negative obstacles.

[0066] In conjunction with the third aspect, in some implementations of the third aspect, the drivable area includes a first area, the information of which includes boundary attributes of the first area, the boundary attributes including soft boundaries and / or hard boundaries, wherein the soft boundary includes the boundary where the first area and the second area intersect, the road attributes of the first area indicate a first road surface type, the road attributes of the second area indicate a second road surface type, and the traffic priority of the first road surface type is higher than the traffic priority of the second road surface type; the hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0067] In conjunction with the third aspect, in some implementations of the third aspect, the information of the drivable area includes the road attributes of the drivable area, which include the road type of one or more polygonal regions where the drivable area is located, and the road type is used to indicate whether the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy road surface.

[0068] In conjunction with the third aspect, in some implementations of the third aspect, the device further includes: a sending unit for sending the environmental information to the control module.

[0069] In conjunction with the third aspect, in some implementations of the third aspect, the device further includes a control unit for controlling the vehicle's movement based on the environmental information.

[0070] Fourthly, a drivable area detection device is provided, the device comprising: an acquisition unit for acquiring data collected by sensors; and a determination unit for determining information about the drivable area of ​​the vehicle based on the data, the information about the drivable area including road attributes and / or boundary attributes of the drivable area.

[0071] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine information about a first static obstacle based on the data, the first static obstacle including other targets around the vehicle besides dynamic targets and static elements of the road structure; and determine information about the drivable area based on the information about the first static obstacle.

[0072] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: input the data into the prediction model to obtain information about the first static obstacle.

[0073] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine multiple targets based on the data, the multiple targets including information on a first target and a first static obstacle, the first target including dynamic targets around the vehicle and / or static elements of the road structure; and select the first static obstacle from the multiple targets.

[0074] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located; and determine the drivable area based on a preset detection area and the non-drivable area, wherein the drivable area is the area in the preset detection area excluding the non-drivable area.

[0075] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine the non-drivable area based on the polygonal outline of the first static obstacle.

[0076] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used for: determining a first polygonal outline of the first static obstacle based on the data; predicting a second polygonal outline of the first static obstacle based on the type of the first static obstacle and the first polygonal outline; and determining the non-drivable area based on the first polygonal outline and the second polygonal outline.

[0077] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine information about a first static obstacle and information about a negative obstacle based on the data; and determine information about the drivable area based on the information about the first static obstacle and the information about the negative obstacle.

[0078] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the determining unit is specifically used to: determine information about the drivable area of ​​the vehicle based on the data and the first information, wherein the first information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0079] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the drivable area includes a first area, the boundary attributes of which include information on soft boundaries and / or hard boundaries, wherein the soft boundary includes the boundary where the first area and the second area intersect, the road attributes of the first area indicate a first road surface type, the road attributes of the second area indicate a second road surface type, and the traffic priority of the first road surface type is higher than the traffic priority of the second road surface type; the hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0080] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the road attributes of the drivable area include the road type of one or more polygonal regions where the drivable area is located, which is used to indicate whether the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy area.

[0081] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the device further includes: a transmitting unit for transmitting information about the drivable area to the control module.

[0082] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the sending unit is further configured to send information about the second target to the control module when the determining unit determines, based on the data, that the vehicle is surrounded by a second target. The second target includes dynamic targets and / or static elements of the road structure around the vehicle.

[0083] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the device further includes: a control unit for controlling the movement of the vehicle based on the boundary attributes and / or road attributes of the drivable area.

[0084] Fifthly, this application provides a drivable area detection device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program in the memory, enabling the intelligent driving device to implement the methods described in the first aspect and any possible implementation thereof.

[0085] Sixthly, this application provides a drivable area detection system, which includes a sensing system and the apparatus described in the second or third aspect above.

[0086] In a seventh aspect, this application provides a vehicle that includes the device described in the second or third aspect above, or the system described in the fourth aspect above.

[0087] The term "vehicle" in this application is used in a broad sense and can refer to means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle.

[0088] Eighthly, this application provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method in any possible implementation of the first aspect.

[0089] Ninthly, this application provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method in any possible implementation of the first aspect.

[0090] In a tenth aspect, this application provides a chip including circuitry for performing the method in any possible implementation of the first aspect described above. Attached Figure Description

[0091] Figure 1 is a functional block diagram of the vehicle provided in an embodiment of this application.

[0092] Figure 2 is a schematic block diagram of the intelligent driving system provided in an embodiment of this application.

[0093] Figure 3 is a schematic flowchart of the drivable area detection method provided in the embodiments of this application.

[0094] Figure 4 is a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0095] Figure 5 is another schematic diagram of the intelligent driving scenario provided in the embodiments of this application.

[0096] Figure 6 is another schematic diagram of the intelligent driving scenario provided in the embodiments of this application.

[0097] Figure 7 is another schematic diagram of the intelligent driving scenario provided in the embodiments of this application.

[0098] Figure 8 is another schematic diagram of the intelligent driving scenario provided in the embodiments of this application.

[0099] Figure 9 is another schematic diagram of the intelligent driving scenario provided in the embodiments of this application.

[0100] Figure 10 is a schematic flowchart of the drivable area detection method provided in the embodiments of this application.

[0101] Figure 11 is another schematic block diagram of the intelligent driving system provided in an embodiment of this application.

[0102] Figure 12 is a schematic block diagram of the drivable area detection device provided in an embodiment of this application. Detailed Implementation

[0103] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; "and / or" in this document is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. "At least one" refers to one or more. For example, "at least one of A and B," similar to "A and / or B," describes the association relationship between related objects, indicating that three relationships can exist. For example, at least one of A and B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0104] The prefixes such as "first" and "second" used in this application embodiment are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not constitute unnecessary restrictions due to the use of such prefixes. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0105] Figure 1 is a functional block diagram of a vehicle 100 provided in an embodiment of this application. The vehicle 100 may include a sensing system 110, a computing platform 120, and a display device 130. The sensing system 110 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the sensing system 110 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou Navigation Satellite System, or another positioning system. As another example, the sensing system 110 may include one or more of the following: an inertial measurement unit (IMU), an accelerometer, a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0106] Some or all of the functions of vehicle 100 can be controlled by computing platform 120. Computing platform 120 may include one or more processors, such as processors 121 to 12n (n being a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 120 may also include a memory for storing instructions. Some or all of the processors 121 to 12n can call the instructions in the memory to implement the corresponding functions.

[0107] The in-cabin display devices 130 are mainly divided into two categories: the first is the in-vehicle display screen; the second is the projection display screen, such as the head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. Multiple displays can be installed in the cabin, such as the digital instrument cluster display, the central control screen, the display screen in front of the front passenger (also known as the front-seat passenger), the display screen in front of the left rear passenger, the display screen in front of the right rear passenger, and even the car window can be used as a display screen. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's eye-shift time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. Examples of HUDs include combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems. It should be understood that HUDs can also evolve into other types of systems as technology progresses, and this application does not limit them.

[0108] The above description of the display device 130 uses an in-vehicle display screen and a projection display screen as examples, but the embodiments of this application are not limited thereto. For example, the display device 130 can also be a light display screen or a projection screen.

[0109] Optionally, the structure of the vehicle 100 described above is merely illustrative. In actual applications, various components of the vehicle 100 may be added or removed as needed.

[0110] Vehicle 100 may include an intelligent driving system, which may include an advanced driving assistant system (ADAS) and an autonomous driving system (ADS). The intelligent driving system uses various sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, camera devices, ultrasonic sensors, global positioning system, inertial measurement unit) to acquire information from the vehicle's surroundings, and analyzes and processes the acquired information to achieve functions such as obstacle perception, target recognition, vehicle positioning, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving the vehicle.

[0111] For example, Figure 2 shows a schematic block diagram of an intelligent driving system provided in an embodiment of this application. The intelligent driving system may include three functional modules: a perception module 210, a planning module 220, and a control module 230. The perception module 210 perceives the environment surrounding the vehicle through sensors and outputs corresponding perception data to the planning module 220. The planning module 220 obtains road element information based on the information acquired by the perception module 210. Based on the vehicle's current location and the road element information, the planning module 220 determines the physical connectivity of the vehicle from its current location to a sampling point, and plans the vehicle's trajectory to that sampling point when the vehicle is physically connected from its current location to that sampling point. The planning module 220 determines the vehicle's strategy space based on this trajectory. The planning module 220 can send this strategy space to the control module 230. The control module 230 can evaluate the strategy space in Euclidean space to make behavioral or interactive decisions for the vehicle.

[0112] The above-mentioned sensing module 210, planning module 220 and control module 230 can be located in the above-mentioned computing platform 120.

[0113] Vehicle-based driving automation systems are classified into five levels (or L0-L5) based on the degree to which they can perform dynamic driving tasks, according to the role allocation in performing these tasks and the presence or absence of an operational design domain (ODD), such as the external conditions (road, traffic, weather, lighting, etc.) defined during the system's design. Levels 0-2 represent driver assistance, where the system assists humans in performing dynamic driving tasks, but the driver remains the primary driver. Levels 3-5 represent autonomous driving, where the system performs dynamic driving tasks in place of the human under the designed operating conditions; when activated, the system becomes the primary driver. The names and definitions of each level are as follows:

[0114] Level 0 driving automation (also known as emergency assistance) systems cannot continuously perform lateral or longitudinal motion control of the vehicle during dynamic driving tasks, but they possess the ability to continuously perform partial target and event detection and response during dynamic driving tasks. Level 1 driving automation (also known as partial driver assistance) systems continuously perform lateral or longitudinal motion control of the vehicle during dynamic driving tasks under their design operating conditions, and possess the ability to perform partial target and event detection and response adapted to the performed lateral or longitudinal motion control. Level 2 driving automation (also known as combined driver assistance) systems continuously perform lateral and longitudinal motion control of the vehicle during dynamic driving tasks under their design operating conditions, and possess the ability to perform partial target and event detection and response adapted to the performed lateral and longitudinal motion control. Level 3 driving automation (also known as conditionally automated driving) systems continuously perform all dynamic driving tasks under their design operating conditions. Level 4 driving automation (also known as highly automated driving) systems continuously perform all dynamic driving tasks under their design operating conditions and automatically execute minimum risk strategies. Level 5 driving automation (also known as fully automated driving) systems continuously perform all dynamic driving tasks and automatically execute minimum-risk strategies under any drivable conditions. Typically, intelligent driving systems fall between Level 2 and Level 5; for example, ADAS is Level 2, and ADS is Level 3-Level 5.

[0115] Figure 3 shows a schematic flowchart of the drivable area detection method 300 provided in an embodiment of this application. This method 300 can be executed by the vehicle 100, or by the computing platform 120; or by a processor, chip, or circuit in the computing platform 120; or by the intelligent driving system; or by the perception module 210. The method 300 includes:

[0116] S310 acquires data collected by the sensor.

[0117] For example, the sensor may include, but is not limited to, one or more of the following: a camera device, a lidar, a millimeter-wave radar, and an ultrasonic radar.

[0118] S320, based on this data, determine information about the vehicle's drivable area, including the road attributes and / or boundary attributes of the drivable area.

[0119] Optionally, the method 300 further includes: determining that the vehicle is in an intelligent driving state.

[0120] For example, when a user instructs the vehicle to activate the intelligent driving function, it can be determined that the vehicle is in intelligent driving mode.

[0121] For example, the intelligent driving function includes: intelligent driving navigation assist (NCA) function, adaptive cruise control (ACC) function, automatic lane keeping (ALK) function, L3 level highway and expressway autonomous driving, L3 level urban trunk and branch road autonomous driving, automatic parking assist (APA) function, remote parking assist (RPA) function, or automatic valet parking (AVP) function, etc.

[0122] Optionally, the road attributes of the drivable area include the road type of one or more polygonal regions where the drivable area is located. The road type is used to indicate whether the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, an oil-stained road surface, or a grassy area.

[0123] The areas containing dry, flooded, slippery, snow-covered, gravel, oil-stained, or grassy surfaces can be considered drivable areas; alternatively, dry and slippery surfaces can be considered drivable areas, while flooded, snow-covered, gravel, oil-stained, or grassy surfaces can be considered low-traction areas. Low-traction areas may be neither drivable nor non-drivable. Alternatively, a low-traction area may also be considered a drivable area. When a drivable area includes both high-traction areas (e.g., dry surfaces) and low-traction areas (e.g., snow-covered surfaces), priority should be given to ensuring the vehicle travels in the high-traction area.

[0124] Optionally, the boundary attribute may include a soft boundary and / or a hard boundary, wherein there is a risk of accident or collision if the vehicle crosses the hard boundary.

[0125] Optionally, the drivable area includes a first area, the boundary attributes of which include information on soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first area and the second area intersect. The road attributes of the first area indicate a first road surface type, and the road attributes of the second area indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0126] The traffic priority of the first road surface type is higher than that of the second road surface type, which can also be understood as the adhesion of the first road surface type being higher than that of the second road surface type.

[0127] Optionally, based on the data, determining information about the drivable area of ​​the vehicle includes: determining information about a first static obstacle based on the data, the first static obstacle including other targets around the vehicle besides dynamic targets and static road structure elements, and determining information about the drivable area.

[0128] For example, the first static obstacle includes immovable static obstacles, and / or static obstacles spaced at intervals less than or equal to a preset interval.

[0129] For example, immovable static obstacles include, but are not limited to, flower beds, guardrails, barriers, pillars, or trees.

[0130] For example, static obstacles with intervals less than or equal to a preset interval include movable static obstacles with intervals less than or equal to the preset interval. Examples include continuously placed traffic cones, water-filled barriers, or fences.

[0131] The above fences can be used as immovable static obstacles, or they can be used as movable static obstacles with intervals less than or equal to a preset interval. This application does not specifically limit this.

[0132] For example, the area occupied by the discrete, movable, static obstacle that does not constitute a road boundary, the area occupied by the dynamic target, and the area occupied by stationary vehicles on the road can be considered a drivable area. When the perception module 210 acquires this drivable area, it can send the information of the drivable area, the information of the discrete, movable, static obstacle that does not constitute a road boundary, and the information of the dynamic target to the planning module 220. Thus, the planning module 220 can perform planning and decision-making based on the information sent by the perception module 210.

[0133] For example, the discrete, movable, and non-road boundary static obstacle can be a discretely arranged cone, or cones spaced at intervals greater than or equal to a preset interval.

[0134] For example, the preset interval is 50cm.

[0135] For example, Figure 4 shows a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0136] As shown in Figure 4, during vehicle 100's operation, data collected by sensors can identify multiple targets, such as guardrails, lane lines (dashed or solid lines), traffic cones, and water-filled barriers. When the interval between water-filled barriers is less than or equal to a preset interval, and the interval between traffic cones is greater than a preset interval, the area occupied by the water-filled barriers can be designated as a non-drivable area. Thus, continuously arranged water-filled barriers form a boundary, and the area occupied by the barriers is considered a non-drivable area. The roads on both sides of the water-filled barriers are drivable areas.

[0137] Optionally, determining information about the first static obstacle based on the data includes: inputting the data into a prediction model to obtain information about the first static obstacle.

[0138] For example, the prediction model can be trained using a training dataset. This training dataset could include data collected by sensors and information about labeled obstacles (such as static obstacles with intervals less than or equal to a preset interval, static obstacles with intervals greater than a preset interval, immovable static obstacles, and dynamic obstacles). The prediction model can then be trained using this training dataset.

[0139] The prediction models mentioned above can be neural networks (NN), such as transformers, multi-layer perceptrons (MLPs), residual neural networks (ResNets), and recurrent neural networks (RNNs); or they can be other machine learning algorithms, such as support vector machines (SVMs) or decision trees.

[0140] Optionally, determining the information of the first static obstacle based on the data includes: determining multiple targets based on the data, the multiple targets including the first target and the information of the first static obstacle, the first target including at least one of movable static obstacles, static obstacles with an interval greater than or equal to a first preset interval, dynamic targets, or lane lines; and selecting the first static obstacle from the multiple targets.

[0141] For example, as shown in Figure 4, through data collected by sensors, vehicle 100 can acquire multiple surrounding targets, including guardrails, dashed lines, solid lines, water-filled barriers spaced at intervals less than or equal to a preset interval, and traffic cones spaced at intervals greater than a preset interval. Vehicle 100 can filter out the water-filled barriers spaced at intervals less than or equal to the preset interval from the multiple targets. Thus, vehicle 100 can determine its drivable area based on the area occupied by the water-filled barriers.

[0142] Optionally, determining the information of the drivable area based on the information of the first static obstacle includes: determining the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located; and determining the drivable area based on a preset detection area and the non-drivable area, wherein the drivable area is the area in the preset detection area excluding the non-drivable area.

[0143] For example, the preset detection area can be an area determined by data collected by the vehicle's sensors.

[0144] For example, as shown in Figure 4, when the interval between the water-filled barriers is determined to be less than or equal to a preset interval, the area occupied by the water-filled barriers can be identified as a non-drivable area. By removing this non-drivable area from the entire area detected by the sensor, the drivable area of ​​the vehicle 100 can be obtained.

[0145] The entire area detected by the above sensors can include the area consisting of the outermost physical boundary detected by the sensors and the unknown boundary.

[0146] Optionally, determining the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located includes: determining the non-drivable area based on the polygonal outline of the first static obstacle.

[0147] For example, Figure 5 shows a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0148] As shown in Figure 5, the vehicle 100 can determine the polygonal outline of the surrounding fence by using data collected by sensors. The area enclosed by the polygonal outline of the fence can be a non-drivable area.

[0149] Optionally, determining the non-drivable area based on the polygonal outline of the first static obstacle includes: determining a first polygonal outline of the first static obstacle based on the data; predicting a second polygonal outline of the first static obstacle based on the type of the first static obstacle and the first polygonal outline; and determining the non-drivable area based on the first polygonal outline and the second polygonal outline.

[0150] For example, as shown in Figure 6, for a series of water-filled barriers, vehicle 100 can determine polygonal outline 1 using data collected by a camera. Vehicle 100 can also predict polygonal outline 2 based on polygonal outline 1 and the shape of the water-filled barriers. Thus, polygonal outline 1 and polygonal outline 2 constitute the area occupied by the water-filled barriers, which is a non-drivable area for vehicle 100.

[0151] For the fence, vehicle 100 can determine the polygonal outline 3 using data collected by the camera. Vehicle 100 can also predict the polygonal outline 4 based on the polygonal outline 3 and the shape of the fence. Thus, polygonal outline 3 and polygonal outline 4 constitute the area occupied by the fence, which is a non-drivable area for vehicle 100.

[0152] The polygonal contours detected and predicted by the sensors can be used to determine non-drivable areas. This improves the accuracy of non-drivable area detection, thereby helping to expand the range of drivable areas and providing more scope for planning and decision-making by the planning module 220. It avoids simply drawing lines to define drivable areas behind water-filled barriers or fences as non-drivable areas.

[0153] Optionally, determining information about the first static obstacle based on the data includes: determining information about the first static obstacle and information about the negative obstacle based on the data; wherein determining information about the drivable area based on the information about the first static obstacle includes: determining information about the drivable area based on the information about the first static obstacle and the information about the negative obstacle.

[0154] For example, Figure 7 shows a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0155] As shown in Figure 7, when a road collapse occurs in front of vehicle 100, the collapsed area can be identified as a non-drivable area. Therefore, the drivable area for the vehicle can be determined based on this non-drivable area. When the planning module 220 obtains information about the drivable area, it can control the vehicle to perform emergency braking based on the distance between vehicle 100 and the polygonal outline 5 of the drivable area.

[0156] For example, if a number of vehicles greater than or equal to a certain threshold fall within a preset time period within a range of a first preset distance from the direction of travel of vehicle 100, it can be determined that a road collapse has occurred in front of the road.

[0157] For example, if a number of vehicles greater than or equal to a certain threshold fall within a preset time period along a first direction and at a first preset distance from the vehicle, this includes: if the rate of change of the visible portion of a number of vehicles greater than or equal to the certain threshold is less than or equal to a threshold of 1, it can be determined that a road collapse has occurred ahead.

[0158] For example, the visible portion can be the visible portion of the rear of the vehicle. For instance, when vehicle 100 and vehicle 200 are calibrated to be on the same horizontal plane, the visible portion of the rear of vehicle 200 is 100%. If the horizontal plane of vehicle 100 is higher than that of vehicle 200, the visible portion of the rear of the vehicle may be less than 100%.

[0159] As shown in Figure 7, the road surface in front of vehicle 100 collapses, causing vehicle 200 to fall into the collapsed area. At this time, vehicle 100 can still detect the position information of vehicle 200, but the visible portion of vehicle 200 is less than 100%. More specifically, when the visible portion of vehicle 200 is less than 100%, the entire rear portion of vehicle 200 can be recovered based on the existing visible portion. Then, the specific value (percentage) of the visible portion of vehicle 200 can be determined based on the proportion of the existing visible portion to the entire rear portion. For example, threshold 1 can be -5% / frame (i.e., the visible portion of the current frame image is reduced by 5% compared to the previous frame image), or it can be -10% / frame, or it can be other values. It can be understood that the smaller the rate of change of the visible portion, the larger the absolute value of the rate of change, that is, the greater the change in the visible portion of vehicle 200.

[0160] Figure 7 above uses road collapse as an example for illustration. Negative obstacles can also be of other types, such as ditches and cliffs.

[0161] Optionally, determining the drivable area information of the vehicle based on the data includes: determining the drivable area information of the vehicle based on the data and first information, wherein the first information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0162] For example, the road where vehicle 100 is currently located is road 1, and the crowdsourced data can be data collected by sensors when vehicle 100 or other vehicles pass through road 1 in the past.

[0163] For example, real-time traffic flow information may include the travel trajectories of one or more vehicles located in front of vehicle 100.

[0164] For example, Figure 8 shows a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0165] As shown in Figure 8(a), vehicle 100 is on a highway. Vehicle 100 can determine the drivable area using data collected by sensors.

[0166] As shown in Figure 8(b), if vehicle 100 determines its drivable area based on data collected by sensors, this drivable area is determined by information from the guardrails on both sides of the road. In this case, due to the limited detection range of the sensors and the vehicle's inability to detect information about ramp exits, the vehicle can determine that the ramp exits within this drivable area are closed.

[0167] As shown in Figure 8(c), if vehicle 100 uses data collected by sensors and a standard map (e.g., a standard map indicating that a ramp exit is open and connects to a toll station), then the ramp exit in the drivable area determined by vehicle 100 is not closed. Thus, by combining information from the standard map, beyond-line-of-sight detection of the drivable area can be performed. Without improving the detection capabilities of the sensors, combining map information or crowdsourced data helps to expand the range of the detected drivable area, thereby providing more data for planning and decision-making.

[0168] Figure 8 above illustrates this using a ramp exit as an example. Beyond-line-of-sight detection can also be applied to other intelligent driving scenarios. For example, during driving, vehicle 100 detects a portion of the polygonal outline of a guardrail using sensors, while another portion of the polygonal outline is obscured by other targets (e.g., other vehicles). Vehicle 100 can perform beyond-line-of-sight detection on the guardrail based on data collected by sensors and crowdsourced data (e.g., data collected by sensors from other vehicles passing through the road segment). This avoids situations where only a portion of the polygonal outline of a static obstacle is detected, or where the static obstacle is not detected at all, due to obstruction by other targets. This helps improve the accuracy of drivable area detection results, thereby enhancing user driving safety.

[0169] Optionally, the drivable area includes a first area, the boundary attributes of which include information on soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first area and the second area intersect. The road attributes of the first area indicate a first road surface type, and the road attributes of the second area indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0170] For example, Figure 9 shows a schematic diagram of an intelligent driving scenario provided in an embodiment of this application.

[0171] As shown in Figure 9, the vehicle 100 can use data collected by sensors to determine the road surface, including guardrails and the dry and snow-covered surfaces between the guardrails. The vehicle 100 can define the area containing the dry surface as a drivable area and the area containing the snow-covered surface as a low-traction area. The boundary where the drivable area and the low-traction area meet can be a soft boundary.

[0172] Alternatively, vehicle 100 can define both the dry road surface and the snow-covered road surface between the guardrails on both sides as a drivable area. This drivable area can be further divided into high-traction areas and low-traction areas, where the area containing the dry road surface is the high-traction area and the area containing the snow-covered road surface is the low-traction area. The boundary where the high-traction area and the low-traction area meet is a soft boundary.

[0173] Optionally, the vehicle can control its movement based on the boundary attributes of the drivable area. For example, if a collision risk between the vehicle and an obstacle is detected to meet preset conditions and the vehicle can avoid the collision risk by crossing the soft boundary, the vehicle can be controlled to cross the soft boundary. In this way, if the vehicle can avoid the collision risk by crossing the soft boundary, the vehicle can cross the soft boundary in an emergency, thereby helping to improve the safety of the user.

[0174] Optionally, taking the method 300 being executed by the perception module 210 as an example, the method 300 further includes: sending information about the drivable area to the planning module 220.

[0175] For example, taking the perception module 210 as the execution subject of method 300, after obtaining the information of the drivable area, the perception module 210 can send the information of the drivable area to the planning module 220.

[0176] Optionally, the method 300 further includes: when it is determined from the data that a second target exists around the vehicle, sending information about the second target to the control module, the second target including dynamic targets and / or static road structure elements. For example, the perception module 210 can generate environmental information around the vehicle, such as drivable areas as a first level (e.g., bottom level), static road structure elements as a second level (e.g., intermediate level), and dynamic targets as a third level (e.g., high level). In this way, the environmental information around the vehicle can be comprehensively expressed through different levels.

[0177] For example, as shown in Figure 4, when the sensor detects cones with an interval greater than or equal to a preset interval, the sensing module 210, in addition to sending information about the drivable area (determined by the area where the water-filled barriers are located) to the planning module 220, can also send information about the cones (e.g., the position and size of the cones) to the control module. In this way, the planning module 220 can perform planning and control based on the information about the drivable area and the cones.

[0178] Optionally, the method 300 further includes controlling the vehicle's movement based on the boundary attributes and / or road attributes of the drivable area.

[0179] Optionally, controlling the vehicle's movement based on the boundary attributes and / or road attributes of the drivable area includes: controlling the distance between the vehicle and the soft boundary to be greater than or equal to a first preset distance; or controlling the distance between the vehicle and the hard boundary to be greater than or equal to a second preset distance; wherein the second preset distance is greater than the first preset distance.

[0180] Figure 10 shows a schematic flowchart of a drivable area detection method 1000 provided in an embodiment of this application. This method 1000 can be executed by the vehicle 100, or by the computing platform 120; or by a processor, chip, or circuit in the computing platform 120; or by the intelligent driving system; or by the perception module 210. The method 1000 includes:

[0181] S1010: Acquire data collected by the sensor.

[0182] The above S1010 process can be referred to as the process of S310 above, and will not be repeated here.

[0183] S1020, Based on the data, determine the environmental information around the vehicle. The environmental information includes information on the drivable area and first information. The drivable area is determined by other targets around the vehicle besides dynamic targets and static road structure elements. The first information includes dynamic targets and / or static road structure elements.

[0184] In this embodiment, the generation of drivable area information does not rely on high-precision maps but is based on data collected by sensors. This helps improve the accuracy of vehicle planning and decision-making, and also helps reduce the cost of intelligent driving. Simultaneously, the generation of drivable area information does not rely on dynamic targets or static road structure elements; that is, the generation of drivable areas is independent of road topology. This avoids the inability to detect drivable areas due to road topology loss, and also avoids unstable detection results due to unstable road topology, which could lead to unexpected steering and degradation problems. Thus, when the vehicle is driving on roads without road topology (e.g., unstructured roads), or when the road topology is lost or unstable during vehicle operation, it can rely on this drivable area as a fallback, avoiding unexpected steering and degradation problems caused by unstable drivable area detection results, thereby helping to ensure user driving safety.

[0185] Furthermore, the current representation of drivable areas includes information such as dynamic obstacles, static obstacles, and road boundaries. Areas occupied by dynamic obstacles such as vehicles, pedestrians, and non-motorized vehicles at the current moment may be considered drivable areas. This representation method is not conducive to the planning and control module's generation of strategies and trajectory planning for future moments.

[0186] Based on the above technical solution, by determining the drivable area using static targets other than dynamic targets and static road structure elements, the drivable area of ​​the vehicle can be described to the maximum extent, enabling the vehicle to break through the semantic boundaries of lane lines without breaking through physical boundaries. For example, the vehicle can use the oncoming lane to avoid obstacles based on the drivable area.

[0187] For example, the information of the first target includes one or more of the following: the coordinates, type, polygon outline, and height of the first target.

[0188] For example, the information about the drivable area includes the coordinates of multiple points on the polygonal outline in which the drivable area is located.

[0189] For example, the dynamic target includes dynamic vehicles, pedestrians, non-motorized vehicles, etc.

[0190] For example, the static elements of the road structure include lane lines, lane turning arrows, etc.

[0191] For example, the other targets include one or more of the following: negative obstacles (e.g., ditches, cliffs, etc.), road boundaries (e.g., curbs), immovable static obstacles (e.g., guardrails, fences), and static obstacles spaced at intervals less than or equal to a preset interval (e.g., continuously arranged water-filled barriers or traffic cones).

[0192] For example, the environmental information includes multiple levels of information, such as the drivable area as the first level (e.g., the bottom level), static road structure elements as the second level (e.g., the middle level), and dynamic targets as the third level (e.g., the high level). In this way, the environmental information around the vehicle can be completely expressed through different levels.

[0193] Optionally, the drivable area is determined by other targets around the vehicle besides dynamic targets, static road structure elements, discretely arranged stationary obstacles, and stationary vehicles.

[0194] For example, the environmental information includes multiple levels of information, such as drivable areas as the first level (e.g., bottom level), static elements of road structure, discretely arranged stationary obstacles, stationary vehicles as the second level (e.g., intermediate level), and dynamic targets as the third level (e.g., high level).

[0195] Optionally, based on the data, determine the environmental information around the vehicle, including: inputting the data into a prediction model to obtain the features of multiple grids, the features of each grid including the drivable area attributes and visibility of each grid; and determining the information of the drivable area based on the drivable area attributes and visibility in different time domains.

[0196] Optionally, the characteristics of each grid also include the occupancy of each grid.

[0197] The drivable area attribute of each grid can be used to indicate whether each grid corresponds to a drivable area or a non-drivable area.

[0198] The visibility of each grid cell output by the above prediction model can be represented by a visibility value. For example, the visibility value of each grid cell can be represented by a value between 0 and 1. The higher the visibility value, the higher the visibility of the grid cell.

[0199] Optionally, based on the data, determining the environmental information surrounding the vehicle includes: inputting the data into a drivable area prediction model to obtain the features of multiple grids, each grid's features including its drivable area attributes and visibility; determining the state of each grid based on the drivable area attributes and visibility of the multiple grids corresponding to a single frame of data; updating the states of the visible grids across multiple frames and the states of the implied grids across multiple frames to determine scalarized data of the drivable area; and vectorizing the scalarized data to obtain the environmental information.

[0200] The visible grid state above can be the confidence level of the visible grids among multiple grids that are drivable areas. The multi-frame imaginary grid state can be the confidence level of the invisible grids among multiple grids that are drivable areas.

[0201] For example, data from the previous frame collected by sensors can determine that a certain area is visible and drivable. In the next frame, if this area is occluded (or becomes invisible), and the supplementary information output by the prediction model indicates that the area is still drivable, then it can be determined that the area remains drivable. Alternatively, if the supplementary information output by the prediction model indicates that the area is not drivable, and the cumulative output results for multiple frames are all non-drivable, then the confidence that the area is drivable will continuously decrease. For example, when this confidence drops below a certain threshold, the area can be determined to be non-drivable.

[0202] Optionally, as shown in Figure 11, the drivable area post-processing module 1120 can generate first scalarized data of the drivable area based on the drivable area attributes and visibility of multiple grids corresponding to multiple frames of data; and verify the scalarized data of the drivable area according to the occupancy of multiple grids to obtain second scalarized data of the drivable area. The drivable area post-processing module 1120 can vectorize the second scalarized data to obtain environmental information around the vehicle. In this embodiment, verifying the first scalarized data by the occupancy of each grid can improve the accuracy of the final drivable area, thereby helping to improve the accuracy of the planning and decision-making of the control module.

[0203] Figure 11 shows a schematic block diagram of an intelligent driving system 1100 provided in an embodiment of this application. The intelligent driving system 1100 includes a drivable area prediction model 1110, a drivable area post-processing module 1120, an environmental information integration and output module 1130, and a planning and control module 1140. The drivable area prediction model 1110, the drivable area post-processing module 1120, and the environmental information integration and output module 1130 may be located in the aforementioned perception module 210, and the planning and control module 1140 may be the aforementioned planning module 220.

[0204] For example, the drivable area prediction model 1110 can be trained using a training dataset that includes sample sensor data and the drivable area attributes, visibility, and occupancy of labeled grids. The drivable area prediction model 1110 can be trained using the training dataset.

[0205] By inputting the data collected by the sensors into the drivable area prediction model 1110, features of multiple grids can be obtained. These features include the drivable area attributes, visibility, and occupancy of each grid. The drivable area post-processing module 1120 can acquire the output of the drivable area prediction model 1110 and determine the state of each grid based on the drivable area attributes and visibility of each grid corresponding to a single frame of data. The drivable area post-processing module 1120 can update the states of visible grids and the states of imputed grids across multiple frames to determine scalarized data of the drivable area. The drivable area post-processing module 1120 can vectorize the scalarized data of the drivable area to obtain vectorized data of the drivable area, which is then output to the environmental information integration and output module 1130.

[0206] The environmental information integration and output module 1130 can use the vectorized data of the drivable area as layer 0, the static elements of the road structure as layer 1, and the dynamic targets as layer 2. Layer 0, layer 1, and layer 2 can constitute the environmental information. The environmental information integration and output module 1130 can send the environmental information to the planning and control module 1140.

[0207] In this embodiment of the application, the method of obtaining the static elements and dynamic targets of the road structure in layer 1 and layer 2 is not specifically limited.

[0208] Layer 1 and Layer 2 can also be located in the same layer.

[0209] The planning and control module 1140 can make decisions and plans based on this environmental information.

[0210] Optionally, based on the data, determining environmental information around the vehicle includes: determining the environmental information based on the data and second information, wherein the second information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0211] In this embodiment, combining at least one of SD maps, crowdsourced data, and real-time traffic flow information helps to achieve beyond-line-of-sight detection of drivable areas. This helps to increase the range of detected drivable areas, providing more options for the planning and decision-making of the traffic control module.

[0212] Optionally, the other targets include one or more of the following: immovable stationary obstacles, static obstacles spaced at intervals less than or equal to a preset interval, or negative obstacles.

[0213] In this embodiment, the vehicle can determine the drivable area by combining a first static obstacle and negative obstacles. Thus, by detecting negative obstacles, the vehicle can avoid entering them, thereby helping to prevent vehicle falls and improving user safety.

[0214] Optionally, the drivable area includes a first area, and the information of the drivable area includes the boundary attributes of the first area, which include soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first area and the second area intersect. The road attributes of the first area indicate a first road surface type, and the road attributes of the second area indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0215] Optionally, the information of the drivable area includes the road attributes of the drivable area, which include the road type of one or more polygonal areas where the drivable area is located. The road type is used to indicate whether the polygonal area is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy area.

[0216] Optionally, taking the method 1000 being executed by the perception module 210 as an example, the method 1000 further includes: sending the environmental information to the planning module 220.

[0217] Optionally, taking the method 1000 being executed by an intelligent driving system as an example, the method 1000 further includes: controlling the vehicle's driving based on the environmental information.

[0218] Methods 300 and 1000 can be combined with each other. For example, in method 1000, the environmental information determined based on the data collected by the sensors may include the information on the drivable area, such as the boundary attributes and / or road attributes of the drivable area.

[0219] Figure 12 shows a schematic block diagram of a drivable area detection device 1200 provided in an embodiment of this application. The device 1200 includes: an acquisition unit 1210 for acquiring data collected by sensors; and a determination unit 1220 for determining information about the drivable area of ​​the vehicle based on the data, wherein the information about the drivable area includes road attributes and / or boundary attributes of the drivable area.

[0220] Optionally, the determining unit 1210 is specifically used to: determine information about a first static obstacle based on the data, the first static obstacle including other targets around the vehicle besides dynamic targets and static elements of the road structure; and determine information about the drivable area based on the information about the first static obstacle.

[0221] Optionally, the determining unit 1210 is specifically used to: input the data into the prediction model to obtain information about the first static obstacle.

[0222] Optionally, the determining unit 1210 is specifically used to: determine multiple targets based on the data, the multiple targets including information on a first target and a first static obstacle, the first target including dynamic targets and / or static elements of the road structure around the vehicle; and filter out the first static obstacle from the multiple targets.

[0223] Optionally, the determining unit 1210 is specifically used to: determine the non-drivable area of ​​the vehicle based on the area where the first static obstacle is located; and determine the drivable area based on a preset detection area and the non-drivable area, wherein the drivable area is the area in the preset detection area other than the non-drivable area.

[0224] Optionally, the determining unit 1210 is specifically used to: determine the non-drivable area based on the polygonal outline of the first static obstacle.

[0225] Optionally, the determining unit 1210 is specifically used to: determine a first polygonal outline of the first static obstacle based on the data; predict a second polygonal outline of the first static obstacle based on the type of the first static obstacle and the first polygonal outline; and determine the non-drivable area based on the first polygonal outline and the second polygonal outline.

[0226] Optionally, the determining unit 1210 is specifically used to: determine information about a first static obstacle and information about a negative obstacle based on the data; and determine information about the drivable area based on the information about the first static obstacle and the information about the negative obstacle.

[0227] Optionally, the determining unit 1210 is specifically used to: determine information about the drivable area of ​​the vehicle based on the data and the first information, wherein the first information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0228] Optionally, the drivable area includes a first area, the boundary attributes of which include information on soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first area and the second area intersect. The road attributes of the first area indicate a first road surface type, and the road attributes of the second area indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0229] Optionally, the road attributes of the drivable area include the road type of one or more polygonal regions where the drivable area is located. The road type is used to indicate whether the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy area.

[0230] Optionally, the device 1200 further includes a transmitting unit for transmitting information about the drivable area to the control module.

[0231] Optionally, the sending unit is further configured to send information about the second target to the control module when the determining unit determines, based on the data, that the vehicle is surrounded by a second target. The second target includes dynamic targets and / or static elements of the road structure around the vehicle.

[0232] Optionally, the device 1200 further includes a control unit for controlling the vehicle's movement based on the boundary attributes and / or road attributes of the drivable area.

[0233] In one embodiment, the acquisition unit 1210 is used to acquire data collected by the sensor; the determination unit 1220 is used to determine environmental information around the vehicle based on the data, the environmental information including information on the drivable area and first information, the drivable area being determined by other targets around the vehicle other than dynamic targets and static road structure elements, and the first information including dynamic targets and / or static road structure elements.

[0234] Optionally, the determining unit 1220 is specifically used to: input the data into the prediction model to obtain the features of multiple grids, the features of the multiple grids including whether each grid is a drivable area and the visibility of each grid; and determine the information of the drivable area based on the features of the multiple grids in different time domains.

[0235] Optionally, the determining unit 1220 is specifically used to: determine the environmental information based on the data and the second information, wherein the second information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

[0236] Optionally, the other targets include one or more of the following: immovable stationary obstacles, static obstacles spaced at intervals less than or equal to a preset interval, or negative obstacles.

[0237] Optionally, the drivable area includes a first area, and the information of the drivable area includes the boundary attributes of the first area, which include soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first area and the second area intersect. The road attributes of the first area indicate a first road surface type, and the road attributes of the second area indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first area intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

[0238] Optionally, the information of the drivable area includes the road attributes of the drivable area, which include the road type of one or more polygonal areas where the drivable area is located. The road type is used to indicate whether the polygonal area is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy area.

[0239] Optionally, the device 1200 further includes a transmitting unit for transmitting the environmental information to the control module.

[0240] Optionally, the device 1200 further includes a control unit for controlling the vehicle's movement based on the environmental information.

[0241] It should be understood that the division of units in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the device can be implemented by a processor calling software; for example, the device includes a processor connected to memory, which stores instructions. The processor calls the instructions stored in memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be, for example, a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. The functions of some or all units can be implemented through the design of the hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all units are implemented through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby implementing the functions of some or all units. All units of the above devices can be implemented entirely through processor calling software, or entirely through hardware circuits, or partially through processor calling software with the remaining parts implemented through hardware circuits.

[0242] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0243] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0244] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together as a System-on-a-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and AI processor, CPU and GPU, etc.

[0245] This application also provides a drivable area detection device, which includes a processing unit and a storage unit. The storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to cause the device to perform the methods or steps described in the above embodiments.

[0246] Optionally, if the intelligent driving device is located in a vehicle, the aforementioned processing unit may be one or more of the processors 121-12n shown in FIG1.

[0247] This application also provides an intelligent driving system, which includes a perception system and a computing platform, the computing platform including the aforementioned drivable area detection device.

[0248] This application also provides a vehicle that may include the aforementioned drivable area detection device or the aforementioned intelligent driving system.

[0249] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0250] This application also provides a computer-readable medium storing program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0251] This application also provides a chip, which includes a circuit for performing the methods described in the above embodiments.

[0252] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, power-on erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0253] It should be understood that in the embodiments of this application, the memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0254] It should also be understood that, in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0255] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0256] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0257] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0258] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0259] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0260] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0261] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be covered. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A travelable area detection method characterized by comprising: The method comprises: obtaining data collected by a sensor; determining, according to the data, environment information around a vehicle, the environment information comprising information of a drivable area and first information, the drivable area being determined by one or more of a static obstacle around the vehicle, a static obstacle with a distance less than or equal to a preset distance, or a negative obstacle, and the first information comprising a dynamic target and / or a static element of a road structure.

2. The method of claim 1, wherein, The determining, according to the data, of the environment information around the vehicle comprises: inputting the data into a prediction model to obtain features of a plurality of grids, the features of the plurality of grids comprising whether each grid of the plurality of grids is a drivable area and visibility of the each grid; determining, according to the features of the plurality of grids in different time domains, the information of the drivable area.

3. The method according to claim 1 or 2, characterized in that, The determining, according to the data, of the environment information around the vehicle comprises: determining, according to the data and second information, the environment information, the second information comprising at least one of standard map (SD) information, crowd-sourcing data, or real-time traffic flow information.

4. The method according to any one of claims 1 to 3, characterized in that, The drivable area comprises a first area, and the information of the drivable area comprises a boundary attribute of the first area, the boundary attribute comprising a soft boundary and / or a hard boundary, wherein the soft boundary comprises a boundary where the first area and a second area meet, a road attribute of the first area indicating a first road type, and a road attribute of the second area indicating a second road type, a passing priority of the first road type being higher than a passing priority of the second road type; the hard boundary comprises a boundary where the first area meets at least one of a road curb, a flower bed, a fence, a ditch edge, and a cliff edge.

5. The method according to any one of claims 1 to 4, characterized in that, The information of the drivable area comprises a road attribute of the drivable area, the road attribute comprising a road type of one or more polygon areas where the drivable area is located, the road type being used to indicate that the polygon area is a dry road, a water-logged road, a slippery road, a snow-covered road, a gravel road, or a grassland.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: sending the environment information to a regulation and control module.

7. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: controlling the vehicle to travel according to the environment information.

8. A travelable area detection method characterized by comprising: The method comprises: obtaining data collected by a sensor; determining, according to the data, information of a drivable area of a vehicle, the information of the drivable area comprising a road attribute and / or a boundary attribute of the drivable area.

9. The method of claim 8, wherein, The determining, according to the data, of the information of the drivable area of the vehicle comprises: determining, according to the data, information of a first static obstacle, the first static obstacle comprising one or more of a static obstacle around the vehicle, a static obstacle with a distance less than or equal to a preset distance, or a negative obstacle; determining, according to the information of the first static obstacle, the information of the drivable area.

10. The method of claim 9, wherein, The determining, according to the data, of the information of the first static obstacle comprises: inputting the data into a prediction model to obtain the information of the first static obstacle.

11. The method according to claim 9 or 10, characterized in that, The determining, according to the information of the first static obstacle, of the information of the drivable area comprises: determine an untravelable area of the vehicle according to a region where the first static obstacle is located; determine the travelable area according to a preset detection region and the untravelable area, the travelable area being a region in the preset detection region except the untravelable area.

12. The method of claim 11, wherein, The method further includes: determine a first polygon contour line of the first static obstacle according to the data; predict a second polygon contour line of the first static obstacle according to a type of the first static obstacle and the first polygon contour line; determine the untravelable area according to the first polygon contour line and the second polygon contour line.

13. The method according to any one of claims 9 to 12, characterized in that, The method further includes: determine information of the first static obstacle and information of a negative obstacle according to the data; wherein the determining the information of the travelable area according to the information of the first static obstacle includes: determine the information of the travelable area according to the information of the first static obstacle and the information of the negative obstacle.

14. The method according to any one of claims 8 to 13, characterized in that, The method further includes: determine the information of the travelable area of the vehicle according to the data and first information, the first information including at least one of information of a standard map (SD), crowd-sourcing data or real-time traffic flow.

15. The method according to any one of claims 8 to 14, characterized in that, The travelable area includes a first region, a boundary attribute of the first region including information of a soft boundary and / or a hard boundary, wherein the soft boundary includes a boundary where the first region and a second region meet, a road attribute of the first region indicating a first road surface type, a road attribute of the second region indicating a second road surface type, a passing priority of the first road surface type being higher than a passing priority of the second road surface type; the hard boundary including a boundary where the first region meets at least one of a road curb, a flower bed, a fence, a ditch edge and a cliff edge.

16. The method according to any one of claims 8 to 15, characterized in that, The road attribute of the travelable area includes a road type of one or more polygon regions where the travelable area is located, the road type being used to indicate that the polygon region is a dry road surface, a water-accumulated road surface, a wet road surface, a snow-covered road surface, a sand-stone road surface or a grassland.

17. The method according to any one of claims 8 to 16, characterized in that, The method further includes: send the information of the travelable area to a regulation and control module.

18. The method of claim 17, wherein, The method further includes: when a second target around the vehicle is determined according to the data, send information of the second target to the regulation and control module, the second target including a dynamic target around the vehicle and / or a road structure static element.

19. The method according to any one of claims 8 to 18, characterized in that, The method further includes: control the vehicle to travel according to the boundary attribute and / or the road attribute of the travelable area.

20. A travelable area detection device characterized by comprising: The method further includes: an acquisition unit, configured to acquire data collected by a sensor; The determining unit is configured to determine, according to the data, environment information around the vehicle, the environment information comprising information of a drivable area and first information, the drivable area being determined by one or more of a static obstacle around the vehicle, a static obstacle with a distance less than or equal to a preset distance, or a negative obstacle, and the first information comprising a dynamic target and / or a road structure static element.

21. The apparatus of claim 20, wherein, The determining unit is specifically configured to: input the data into a prediction model to obtain features of a plurality of grids, the features of the plurality of grids comprising whether each grid in the plurality of grids is a drivable area and visibility of each grid in the plurality of grids; determine the information of the drivable area according to the features of the plurality of grids in different time domains.

22. The apparatus of claim 20 or 21, wherein, The determining unit is specifically configured to: determine the environment information according to the data and second information, the second information comprising at least one of information of a standard map (SD), crowd-sourced data, or real-time traffic flow.

23. The apparatus of any one of claims 20-22, wherein, The drivable area comprises a first area, and the information of the drivable area comprises a boundary attribute of the first area, the boundary attribute comprising a soft boundary and / or a hard boundary, wherein the soft boundary comprises a boundary where the first area and a second area meet, a road attribute of the first area indicating a first road surface type, and a road attribute of the second area indicating a second road surface type, a passing priority of the first road surface type being higher than a passing priority of the second road surface type; the hard boundary comprises a boundary where the first area meets at least one of a road curb, a flower bed, a fence, a ditch edge, and a cliff edge.

24. The apparatus of any one of claims 20-23, wherein, The information of the drivable area comprises a road attribute of the drivable area, the road attribute comprising a road type of one or more polygon areas where the drivable area is located, the road type being used to indicate that the polygon area is a dry road surface, a water-logged road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassland.

25. The apparatus of any one of claims 20-24, wherein, The apparatus further comprises: a sending unit configured to send the environment information to a regulation and control module.

26. The apparatus of any one of claims 20-25, wherein, The apparatus further comprises: a control unit configured to control driving of the vehicle according to the environment information.

27. A travelable area detection device characterized by comprising: The apparatus comprises: an acquisition unit configured to acquire data collected by a sensor; a determining unit configured to determine, according to the data, information of a drivable area of the vehicle, the information of the drivable area comprising a road attribute and / or a boundary attribute of the drivable area.

28. The apparatus of claim 27, wherein, The determining unit is specifically configured to: determine, according to the data, information of a first static obstacle, the first static obstacle comprising one or more of a static obstacle around the vehicle, a static obstacle with a distance less than or equal to a preset distance, or a negative obstacle; determine the information of the drivable area according to the information of the first static obstacle.

29. The apparatus of claim 28, wherein, The determining unit is specifically configured to: input the data into a prediction model to obtain the information of the first static obstacle.

30. The apparatus of claim 28 or 29, wherein, The determining unit is specifically configured to: determine, according to an area where the first static obstacle is located, an un-drivable area of the vehicle; Based on the preset detection area and the non-drivable area, the drivable area is determined, wherein the drivable area is the area in the preset detection area other than the non-drivable area.

31. The apparatus of claim 30, wherein, The determining unit is specifically used for: Based on the data, the first polygonal outline of the first static obstacle is determined; Based on the type of the first static obstacle and the first polygonal outline, predict the second polygonal outline of the first static obstacle; The non-drivable area is determined based on the first polygonal outline and the second polygonal outline.

32. The apparatus of any one of claims 28-31, wherein, The determining unit is specifically used for: Based on the data, determine the information of the first static obstacle and the information of the negative obstacle; The information of the drivable area is determined based on the information of the first static obstacle and the information of the negative obstacle.

33. The apparatus of any one of claims 27-32, wherein, The determining unit is specifically used for: Based on the data and the first information, information on the drivable area of ​​the vehicle is determined, wherein the first information includes at least one of standard map SD, crowdsourced data, or real-time traffic flow information.

34. The apparatus of any one of claims 27-33, wherein, The drivable area includes a first area, the boundary attributes of which include information about soft boundaries and / or hard boundaries. The soft boundary includes the boundary where the first region and the second region intersect. The road attributes of the first region indicate a first road surface type, and the road attributes of the second region indicate a second road surface type. The traffic priority of the first road surface type is higher than that of the second road surface type. The hard boundary includes the boundary where the first region intersects with at least one of the following: curb, flower bed, fence, ditch edge, and cliff edge.

35. The apparatus of any one of claims 27-34, wherein, The road attributes of the drivable area include the road type of one or more polygonal regions where the drivable area is located. The road type is used to indicate whether the polygonal region is a dry road surface, a flooded road surface, a slippery road surface, a snow-covered road surface, a gravel road surface, or a grassy area.

36. The apparatus of any one of claims 27-35, wherein, The device further includes: The sending unit is used to send information about the drivable area to the planning and control module.

37. The apparatus according to claim 36, characterized in that, The sending unit is further configured to send information about the second target to the planning and control module when the determining unit determines, based on the data, that the vehicle is surrounded by a second target. The second target includes dynamic targets and / or static elements of the road structure around the vehicle.

38. The apparatus of any one of claims 27-35, wherein, The device further includes: A control unit is configured to control the movement of the vehicle based on the boundary attributes and / or road attributes of the drivable area.

39. A travelable area detection device characterized by comprising: include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 19.

40. The device of claim 39, wherein, The device also includes the memory.

41. A travelable area detection system characterized by comprising: The drivable area detection system includes a sensing system and a computing platform, wherein the computing platform includes the apparatus as described in any one of claims 20 to 40.

42. A vehicle characterized by Includes the apparatus as described in any one of claims 20 to 40, or includes the system as described in claim 41.

43. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, cause the processor to implement the method as described in any one of claims 1 to 19.

44. A computer program product, characterised in that, The computer program product includes computer program code that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 19.

45. A chip, comprising: The chip includes circuitry for performing the method as described in any one of claims 1 to 19.

Images