Method, device and vehicle for determining obstacles in a road traveled by the vehicle

Abstract

The application discloses a kind of vehicle driving road obstacle determination method, device and vehicle.Therein, the method comprises: obtaining the original point cloud data collected by millimeter wave radar in vehicle;Determine the target information of vehicle based on original point cloud data, wherein the target information at least includes the driving area information allowed to drive vehicle and the obstacle information hindering vehicle driving;Based on target data, obtain the point cloud data to be supplemented of vehicle from road terminal equipment;Determine target obstacle information in obstacle information based on the point cloud data to be supplemented, wherein target obstacle information is used to represent the actual position of target obstacle in vehicle driving road.The application solves the technical problem of low accuracy of obstacle positioning.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a method, apparatus, and vehicle for determining obstacles in a vehicle's driving path. Background Technology

[0002] Currently, 360° coverage of the area around the vehicle is typically achieved by overlapping the camera field of view of multiple millimeter-wave radars, thus enabling all-around perception. A typical automotive millimeter-wave radar layout consists of one forward-facing radar and four corner radars. The forward-facing radar has both narrow and wide beam detection ranges. The wide beam has a large detection angle but a short detection distance, while the narrow beam has a long detection distance but a small detection angle. The corner radars have a similar wide beam detection range to the forward radar, with a large detection angle but a short detection distance. In some driving scenarios, obstacles may move between the narrow and wide beam ranges of the millimeter-wave radar, and obstacles may be obscured by other obstacles, resulting in low accuracy in obstacle localization.

[0003] There is currently no effective solution to the technical problem of low accuracy in obstacle localization in the aforementioned related technologies. Summary of the Invention

[0004] This invention provides a method, apparatus, and vehicle for determining obstacles on a road where a vehicle is traveling, in order to at least solve the technical problem of low accuracy in obstacle location.

[0005] According to one aspect of the present invention, a method for determining obstacles in a vehicle's driving path is provided. The method may include: acquiring raw point cloud data collected by a millimeter-wave radar in the vehicle; determining target information of the vehicle based on the raw point cloud data, wherein the target information includes at least driving area information allowing the vehicle to travel and obstacle information obstructing the vehicle's travel; acquiring supplementary point cloud data of the vehicle from roadside equipment based on the target information; and determining target obstacle information from the obstacle information based on the supplementary point cloud data, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving path.

[0006] Optionally, the detection range and detection angle of all millimeter-wave radars in the vehicle are determined separately; all detection ranges and detection angles are stitched together to obtain the detection range of the vehicle.

[0007] Optionally, based on the target information, the point cloud data of the vehicle to be supplemented is obtained from the roadside equipment, including: determining the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information, wherein the starting coordinates are the coordinates of the frame in which the target obstacle appears, and the disappearance coordinates are the coordinates of the target obstacle in the frame before it disappears; and obtaining the point cloud data to be supplemented from the roadside equipment based on the starting coordinates and disappearance coordinates.

[0008] Optionally, point cloud data to be supplemented is obtained from the roadside equipment based on the starting coordinates and the disappearance coordinates, including: determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates; and determining the point cloud data in the roadside equipment corresponding to the area to be supplemented as the point cloud data to be supplemented.

[0009] Optionally, determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates includes: in response to the starting coordinates being within the detection range and the disappearance coordinates being outside the detection range, or in response to both the starting coordinates and the disappearance coordinates being within the detection range, predicting the target coordinates of the target obstacle based on the starting coordinates and the disappearance coordinates, wherein the target coordinates can be the coordinates of the target obstacle in the frame where it disappears; and determining the area to be supplemented for the vehicle based on the target coordinates.

[0010] Optionally, determining the area to be supplemented for the vehicle based on the target coordinates includes: determining the angle to be supplemented based on the target coordinates and the preset length corresponding to the target obstacle; determining the detection distance corresponding to the angle to be supplemented; and determining the closed area formed by the angle to be supplemented and the detection distance corresponding to the angle to be supplemented as the area to be supplemented.

[0011] Optionally, determining target obstacle information based on the point cloud data to be supplemented includes: fusing the point cloud data to be supplemented and the original point cloud data to obtain fused data; and processing the fused data to obtain target obstacle information.

[0012] According to another aspect of the present invention, an apparatus for determining obstacles in a vehicle's driving path is also provided, comprising: a first acquisition unit for acquiring raw point cloud data collected by a millimeter-wave radar in the vehicle; a first determination unit for determining target information of the vehicle based on the raw point cloud data, wherein the target information includes at least driving area information that allows the vehicle to drive and obstacle information that obstructs the vehicle's driving; a second acquisition unit for acquiring supplementary point cloud data of the vehicle from a roadside device based on the target information; and a second determination unit for determining target obstacle information in the obstacle information based on the supplementary point cloud data, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving path.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method for determining obstacles in a vehicle's driving path according to the embodiments of the present invention.

[0014] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program, when running, executes the method for determining obstacles in a vehicle's driving path according to the embodiments of the present invention.

[0015] According to another aspect of the present invention, a vehicle is also provided. This vehicle is used to perform the method for determining obstacles in a vehicle's driving path according to the embodiments of the present invention.

[0016] In this embodiment of the invention, raw point cloud data collected by millimeter-wave radar in a vehicle is acquired; target information of the vehicle is determined based on the raw point cloud data, wherein the target information includes at least information on the driving area where the vehicle is allowed to travel and information on obstacles that obstruct the vehicle's travel; based on the target information, supplementary point cloud data of the vehicle is acquired from roadside equipment; target obstacle information is determined from the obstacle information based on the supplementary point cloud data, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving road. In other words, this embodiment of the invention acquires raw point cloud data from millimeter-wave radar in a vehicle, and can determine target information such as driving area information and obstacle information based on the raw point cloud data. By analyzing the target information, supplementary point cloud data in the vehicle can be determined, and the actual position of the target obstacle in the vehicle's driving road can be determined using the supplementary point cloud data. This ensures that the obstacle does not leave the detection range of the millimeter-wave radar in the vehicle, thereby solving the technical problem of low accuracy in obstacle positioning and achieving the technical effect of improving the accuracy of obstacle positioning. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of a method for determining obstacles in a vehicle driving road according to an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of a method for improving the perception capability of vehicle-end millimeter-wave radar based on roadside equipment according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of a target leaving the camera's field of view from the narrow beam range of a front radar, according to an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of a region to be supplemented when a target is occluded, according to an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of a device for determining obstacles in a vehicle driving road according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of the present invention, an embodiment of a method for determining obstacles in a vehicle driving road is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a method for determining obstacles in a vehicle driving road according to an embodiment of the present invention, such as... Figure 1 As shown, the method may include the following steps:

[0028] Step S102: Obtain the raw point cloud data collected by the millimeter-wave radar in the vehicle.

[0029] In the technical solution provided in step S102 of the present invention, raw point cloud data collected by millimeter-wave radar in a vehicle can be acquired. The detection range parameters of the millimeter-wave radar can be determined based on the raw point cloud data. The millimeter-wave radar in the vehicle can include forward-facing millimeter-wave radar and angular radar. The raw point cloud data can be point cloud parameters output by the millimeter-wave radar, including parameters such as the radial distance, radial velocity, and radar cross-section (RCS) of the points. The detection range parameters can be camera viewing angle parameters of the millimeter-wave radar, including the detection distance and detection angle. It should be noted that this is only an illustrative example and does not impose specific limitations on the content of the raw point cloud data and detection range parameters.

[0030] For example, the detection angle of a common millimeter-wave radar can be between -75° and 75°, and its maximum detection distance can occur at 0°, reaching a maximum of 300m. The detection distance gradually decreases at other angles. It should be noted that the detection range parameters of millimeter-wave radar are parameters of the radar itself and are related to its design. This is only an example and does not impose specific limitations on the detection angle and detection distance of millimeter-wave radar.

[0031] Optionally, the detection range of the millimeter-wave radar can be determined based on its detection distance and detection angle. For example, the detection distance can be the radius of the millimeter-wave radar's camera field of view. Based on the radius and detection angle, a fan-shaped area can be obtained, which can be the detection range of the millimeter-wave radar.

[0032] For example, forward-facing millimeter-wave radar and multiple corner radars can be deployed on a vehicle to provide all-around perception of the area within a 360° range around the vehicle. The camera viewing angle parameters of each millimeter-wave radar, such as detection distance and detection angle, can be determined and stitched together to obtain the raw point cloud data of the millimeter-wave radar in the vehicle. In other words, it can cover the raw point cloud data of the millimeter-wave radar within a 360° range around the vehicle.

[0033] Step S104: Determine the target information of the vehicle based on the original point cloud data, wherein the target information includes at least the driving area information that allows the vehicle to drive and the obstacle information that obstructs the vehicle's driving.

[0034] In the technical solution provided in step S104 of the present invention, after determining the original point cloud data of the millimeter-wave radar in the vehicle, the target information of the vehicle can be determined based on the original point cloud data. The target information can include at least the driving area information that allows the vehicle to travel and the obstacle information that obstructs the vehicle's travel. The driving area information can be the vehicle's drivable area (freespace). The obstacle information can include information about road traffic participants and road boundary targets. The information about road traffic participants can include the position, speed, bounding box, and trajectory of vehicles and pedestrians. The information about road boundary targets can include the position and bounding box of guardrails and curbs. It should be noted that this is only an example and does not impose specific limitations on the obstacle information, road traffic participant information, and road boundary target information.

[0035] Optionally, based on the detection range and detection angle of the millimeter-wave radar in the vehicle, the situation around the vehicle can be detected while the vehicle is in motion, and the detection results can be obtained. The detection results can include obstacle information of obstacles around the vehicle. Through the detection results of multiple consecutive frames, the trajectory of the obstacle can be determined. Based on the obstacle information in the detection results of the current frame, the drivable area information of the vehicle at the current moment can be determined.

[0036] For example, based on the detection results of the current frame, information on obstacles such as road traffic participants and road boundary targets can be obtained. On the road currently being driven, the range of the vehicle's driving area can be the range after removing the locations of road traffic participants and road boundary targets.

[0037] Step S106: Based on the target information, obtain the point cloud data of the vehicle to be supplemented from the roadside equipment.

[0038] In the technical solution provided in step S106 of the present invention, the target information of the vehicle can be determined based on the original point cloud data. Based on the target information, the supplementary point cloud data of the vehicle can be transmitted from the roadside equipment, wherein the roadside equipment can be a roadside millimeter-wave radar. The supplementary point cloud data can be parameters of the field of view of the supplementary millimeter-wave radar camera, which can be used to characterize the detection range of the vehicle, such as the angle and distance of the detection range. This is only an example and does not impose specific limitations on the supplementary point cloud data.

[0039] Optionally, the millimeter-wave radar in the vehicle can detect target information in real time during the vehicle's movement, determining whether obstacles around the vehicle are always within the detection area of ​​the millimeter-wave radar. If so, it means that the obstacle information is not missing, and it is not necessary to determine the point cloud data to be supplemented. If not, it means that the obstacle information is missing, and its trajectory can be determined through the obstacle information. The trajectory of the obstacle after it disappears from the detection area can be predicted, and the roadside equipment can be contacted to confirm whether the prediction is correct, thereby obtaining the point cloud data to be supplemented for the vehicle.

[0040] In this embodiment of the invention, if an obstacle disappears from the detection area of ​​the millimeter-wave radar in the vehicle, the trajectory of the obstacle can be predicted, and supplementary data of the vehicle can be obtained from the roadside equipment. The movement trajectory of the obstacle can be confirmed through the supplementary data, thereby solving the technical problem of the obstacle being lost from the detection range of the vehicle and achieving the technical effect of improving the accuracy of obstacle positioning.

[0041] Step S108: Determine the target obstacle information from the obstacle information based on the point cloud data to be supplemented.

[0042] In the technical solution provided by step S108 of the present invention, target obstacle information can be determined from obstacle information based on the point cloud data to be supplemented and / or the original point cloud data transmitted in the roadside equipment. The target obstacle information can be used to characterize the actual position of the target obstacle on the road where the vehicle is traveling.

[0043] Optionally, after a target obstacle disappears from the detection area of ​​the millimeter-wave radar in the vehicle, the vehicle can predict the trajectory of the disappeared target obstacle based on the obstacle information and send the obstacle information to the roadside equipment. The roadside equipment can confirm the trajectory information of the target obstacle and compare it with the obstacle information received from the vehicle. If the comparison is successful, it can be determined that the predicted trajectory of the vehicle is correct, and the actual position of the target obstacle can be determined based on the original point cloud data. If the comparison is unsuccessful, the corresponding supplementary point cloud data can be extracted from the roadside equipment and sent to the vehicle. The vehicle can determine the target obstacle information based on the original point cloud data and the received supplementary point cloud data.

[0044] For example, based on the forward-facing millimeter-wave radar and corner radar in the vehicle, the detection angle and detection distance of the camera view of all millimeter-wave radars can be determined. The detection area of ​​the vehicle can be determined based on the detection angle and detection distance. Within the detection area of ​​the vehicle, information on obstacles that hinder the vehicle's movement can be detected. Based on the obstacle information, the driving area information of the vehicle can be determined.

[0045] For another example, during the detection process, it is possible to detect in real time whether road traffic participants disappear from the detection area of ​​the vehicle's millimeter-wave radar. If they disappear, the vehicle can predict the trajectory of the road traffic participant after disappearing from the detection area and transmit the predicted trajectory and other information to the roadside equipment. The roadside equipment can confirm the accuracy of the predicted trajectory based on the millimeter-wave radar in the roadside equipment. If it is correct, it can determine the actual position of the road traffic participant based on the point cloud data to be supplemented and the original point cloud data of the obstacle. If it is incorrect, the millimeter-wave radar in the roadside equipment can determine the actual trajectory of the road traffic participant after disappearing from the detection area and obtain the point cloud data to be supplemented. The point cloud data to be supplemented is transmitted to the vehicle. The vehicle can fuse the received point cloud data to be supplemented and the original point cloud data, and thus determine the actual position of the road traffic participant through the fusion result.

[0046] In this embodiment of the invention, when an obstacle disappears from the detection range of the millimeter-wave radar in the vehicle, the road testing unit can provide the point cloud data to be supplemented for the area of ​​the obstacle, thereby solving the technical problem of the obstacle being lost from the millimeter-wave radar in the vehicle.

[0047] In this application, steps S102 to S108 involve acquiring raw point cloud data collected by a millimeter-wave radar in a vehicle; determining target information for the vehicle based on the raw point cloud data, wherein the target information includes at least information about the driving area where the vehicle is allowed to travel and information about obstacles that obstruct the vehicle's travel; acquiring supplementary point cloud data for the vehicle from roadside equipment based on the target information; and determining target obstacle information from the obstacle information based on the supplementary point cloud data, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving road. In other words, this embodiment of the invention acquires raw point cloud data from a millimeter-wave radar in a vehicle, and can determine target information such as driving area information and obstacle information based on the raw point cloud data. By analyzing the target information, supplementary point cloud data in the vehicle can be determined, and the actual position of the target obstacle in the vehicle's driving road can be determined using the supplementary point cloud data. This ensures that the obstacle does not leave the detection range of the millimeter-wave radar in the vehicle, thereby solving the technical problem of low accuracy in obstacle positioning and achieving the technical effect of improving the accuracy of obstacle positioning.

[0048] The method described in this embodiment will be further described below.

[0049] As an optional embodiment, in step S102, the detection distance of all millimeter-wave radars in the vehicle is determined; all detection distances are stitched together to obtain the detection range of the vehicle.

[0050] In this embodiment, the detection range of each millimeter-wave radar in the vehicle can be determined, and all detection ranges can be stitched together to obtain the detection range of the vehicle's millimeter-wave radar. The millimeter-wave radar may include one forward-facing millimeter-wave radar and multiple corner radars. The forward-facing millimeter-wave radar can be used to detect the area in front of the vehicle. The corner radars can be used to detect areas other than the area in front of the vehicle.

[0051] Optionally, each millimeter-wave radar in the vehicle, and each millimeter-wave radar camera, has a detection angle and a detection distance. The maximum detection distance of the millimeter-wave radar can be used as the radius to determine the fan-shaped area of ​​the detection angle. The fan-shaped areas of all millimeter-wave radars can be stitched together to obtain the detection range of the vehicle.

[0052] As an optional embodiment, step S106 involves obtaining the point cloud data of the vehicle to be supplemented from the roadside equipment based on the target information, including: determining the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information; and obtaining the point cloud data to be supplemented from the roadside equipment based on the starting coordinates and disappearance coordinates.

[0053] In this embodiment, the starting coordinates and disappearance coordinates of the target obstacle can be determined from the vehicle's target information. Then, the point cloud data to be supplemented can be extracted from the roadside equipment using the starting coordinates and disappearance coordinates. The target obstacle can be an obstacle that disappears from the detection range of the millimeter-wave radar in the vehicle. The starting coordinates can be the coordinates of the frame in which the target obstacle appears; the disappearance coordinates can be the coordinates of the target obstacle in the frame before it disappears.

[0054] Optionally, all obstacles around the vehicle can be detected by the millimeter-wave radar in the vehicle to obtain the vehicle's target information. Based on the target information in the multi-frame detection results, the position information of all obstacles can be confirmed. Based on the position information, it can be determined whether the obstacle has disappeared from the detection range of the millimeter-wave radar in the vehicle. If all obstacles have not disappeared from the detection range of the vehicle, there is no need to determine the point cloud data to be supplemented, and the detection of obstacles around the vehicle can continue in real time. If an obstacle disappears from the detection range of the vehicle, the obstacle can be identified as a target obstacle, and the coordinates of the target obstacle when it enters the detection range of the millimeter-wave radar in the vehicle can be determined. The coordinates of the target obstacle in the frame before it disappears from the detection range of the millimeter-wave radar in the vehicle can also be determined. Based on the starting coordinates and disappearance coordinates of the target obstacle, the trajectory of the target obstacle can be predicted, and the point cloud data to be supplemented in the area where the trajectory of the target obstacle after disappearing from the detection range is located can be obtained from the roadside equipment.

[0055] In this embodiment of the invention, the vehicle will only interact with the roadside equipment when the obstacle leaves the detection range of the millimeter-wave radar in the vehicle. Furthermore, the correct obstacle's trajectory can only be transmitted to the vehicle when the predicted trajectory of the obstacle is incorrect, and the point cloud data to be supplemented can be determined. In the prior art, the roadside equipment can transmit all the motion trajectory information of the detected obstacles to the vehicle, resulting in low transmission efficiency and large transmission volume. Based on the above steps, this embodiment of the invention achieves the technical effect of improving transmission efficiency and reducing transmission volume.

[0056] As an optional embodiment, step S106 involves obtaining the point cloud data to be supplemented from the roadside equipment based on the starting coordinates and the disappearance coordinates, including: determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates; and determining the point cloud data in the roadside equipment corresponding to the area to be supplemented as the point cloud data to be supplemented.

[0057] In this embodiment, the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information can be determined. Based on the starting coordinates and disappearance coordinates of the target obstacle, the area to be supplemented for the vehicle can be determined, and the point cloud data such as the angle and distance to be supplemented corresponding to the area to be supplemented in the roadside equipment can be determined as the point cloud data to be supplemented.

[0058] Optionally, based on the disappearance coordinates and starting coordinates of the target obstacle, the trajectory of the target obstacle after disappearing from the detection range of the millimeter-wave radar in the vehicle can be predicted. The area where the predicted trajectory is located can be determined as the area to be supplemented by the vehicle. The predicted trajectory and other information of the target obstacle can be transmitted to the roadside equipment. The roadside equipment can determine whether the actual trajectory of the target obstacle is consistent with the predicted trajectory of the vehicle based on the millimeter-wave radar in the roadside equipment. If they are consistent, the point cloud data such as the angle and distance to be supplemented in the area to be supplemented can be determined as the point cloud data to be supplemented. If they are inconsistent, the roadside equipment can determine the area where the actual trajectory of the target obstacle is located as the area to be supplemented. The roadside equipment can also determine the point cloud data such as the angle and distance to be supplemented corresponding to the area to be supplemented as the point cloud data to be supplemented.

[0059] Optionally, based on the angle to be supplemented and the distance to be supplemented, a supplemented area for the vehicle can be formed. For example, with the distance to be supplemented as the radius and the angle to be supplemented as the angle, a sector area can be determined, which can be the supplemented area for the vehicle.

[0060] In this embodiment of the invention, the millimeter-wave radar in the vehicle detects surrounding obstacles and determines whether any obstacles disappear from the vehicle's detection range. If not, no intervention from the roadside equipment is required in the obstacle detection process. If so, the obstacle is determined to be a target obstacle, and the vehicle can predict the trajectory of the target obstacle. By communicating with the roadside equipment, the accuracy of the predicted trajectory can be determined. If accurate, the area where the trajectory is located can be identified as a supplementary area. If inaccurate, the actual trajectory of the target obstacle can be detected by the roadside equipment to determine the corresponding supplementary area. Since the roadside equipment can supplement the actual location information of the obstacle after it disappears from the vehicle's detection range, the technical problem of low accuracy in obstacle positioning is solved, and the technical effect of improving the accuracy of obstacle positioning is achieved.

[0061] As an optional embodiment, step S106, determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates, includes: in response to the starting coordinates being within the detection range and the disappearance coordinates being outside the detection range, or in response to both the starting coordinates and the disappearance coordinates being within the detection range, predicting the target coordinates of the target obstacle based on the starting coordinates and the disappearance coordinates, wherein the target coordinates can be the coordinates of the target obstacle in the frame where it disappears; and determining the area to be supplemented for the vehicle based on the target coordinates.

[0062] In this embodiment, if the starting coordinates are within the detection range of the millimeter-wave radar in the vehicle, it can be determined whether the disappearance coordinates of the target obstacle are within the detection range. Whether the disappearance coordinates are within or outside the detection range, the target coordinates of the target obstacle can be predicted based on the starting and disappearance coordinates of the target obstacle. The roadside equipment can determine the area to be supplemented for the vehicle based on the target coordinates. The target coordinates can be the coordinates of the target obstacle in the frame in which it disappears.

[0063] Optionally, if the initial coordinates of the target obstacle are within the detection range of the millimeter-wave radar in the vehicle, and the disappearance coordinates are not within the detection range, the motion trajectory of the target obstacle can be predicted based on the initial and disappearance coordinates of the target obstacle, thereby predicting the target coordinates of the target obstacle in the disappearance frame. Based on the target coordinates and the predicted motion trajectory, the angle to be supplemented in the area to be supplemented can be determined. The detection distance of the corner radar in the vehicle at the corresponding angle can be determined as the minimum value of the detection distance to be supplemented, and the maximum detection distance of the forward millimeter-wave radar in the vehicle can be determined as the maximum value of the detection distance to be supplemented. The area to be supplemented in the vehicle can be determined based on the angle to be supplemented, the maximum value of the detection distance to be supplemented, and the minimum value of the detection distance to be supplemented.

[0064] For example, by obtaining the initial and disappearance coordinates of a target obstacle, it can be determined whether the disappearance coordinates are within the detection range of the millimeter-wave radar in the vehicle. If not, the movement trajectory and coordinates of the target obstacle can be predicted. Based on the movement trajectory and target coordinates, the angle to be supplemented in the area can be determined. The detection distance at the corresponding angle of the camera view of the corner radar in the vehicle can be used as the minimum value of the distance to be supplemented, and the maximum detection distance of the forward-facing millimeter-wave radar in the vehicle can be used as the maximum value of the distance to be supplemented. Based on the angle to be supplemented, the maximum value of the distance to be supplemented, and the minimum value of the distance to be supplemented, a region can be obtained, and this region can be identified as the area to be supplemented for the vehicle. It should be noted that this is only an example and does not limit the method for determining the area to be supplemented.

[0065] Optionally, if the starting coordinates of the target obstacle are within the detection range of the millimeter-wave radar in the vehicle, and the disappearance coordinates are also within the detection range, it can be concluded that the target obstacle is outside the vehicle's driving area. In this case, it can be determined whether the boundary of the driving area at the angle corresponding to the disappearance coordinates of the target obstacle is generated by the bounding box of the road traffic participant. If not, no processing is required. If so, it can be determined whether the target obstacle disappears due to being occluded by the road traffic participant. Based on the starting and disappearance coordinates of the target obstacle, the trajectory of the target obstacle can be estimated. The detection angle of the forward millimeter-wave radar corresponding to the trajectory can be used as the angle to be supplemented. The position of the road traffic participant (e.g., the vehicle) occluding the target obstacle at the corresponding angle can be used as the minimum value of the detection distance to be supplemented. The maximum detection distance of the forward millimeter-wave radar at the detection angle can be used as the maximum value of the detection distance to be supplemented. The area to be supplemented for the vehicle can be determined based on the angle to be supplemented, the maximum value of the detection distance to be supplemented, and the minimum value of the detection distance to be supplemented.

[0066] In this embodiment of the invention, since obstacles include road traffic participants and road boundary targets, and since road boundary lines restrict the driving area of ​​vehicles, vehicles will not cross road boundary targets. Therefore, if a target obstacle is obscured by a road boundary target, the target obstacle obscured by the road boundary target can be ignored, thereby achieving the technical effect of improving the efficiency of obstacle detection.

[0067] As an optional embodiment, step S106, determining the area to be supplemented for the vehicle based on the target coordinates, includes: determining the angle to be supplemented based on the target coordinates and the preset length corresponding to the target obstacle; determining the detection distance corresponding to the angle to be supplemented; and determining the closed area formed by the angle to be supplemented and the detection distance corresponding to the angle to be supplemented as the area to be supplemented.

[0068] In this embodiment, the angle to be supplemented can be determined by the target coordinates and the preset length of the target obstacle, the corresponding detection distance at the angle to be supplemented can be determined, and the closed area enclosed by the angle to be supplemented and the detection distance can be determined as the area to be supplemented for the vehicle.

[0069] Optionally, if the initial coordinates of the target obstacle are within the detection range of the millimeter-wave radar in the vehicle, and the disappearance coordinates are not within the detection range, a larger closed area can be formed by the maximum value of the angle to be supplemented and the detection distance to be supplemented, and a smaller closed area can be formed by the minimum value of the angle to be supplemented and the detection distance to be supplemented. The smaller closed area is removed from the larger closed area to obtain the area to be supplemented for the vehicle.

[0070] Optionally, if the starting coordinates of the target obstacle are within the detection range of the millimeter-wave radar in the vehicle, and the disappearance coordinates are also within the detection range, it can be concluded that the target obstacle is outside the vehicle's driving area. In this case, it can be determined whether the boundary of the driving area at the angle corresponding to the disappearance coordinates of the target obstacle is generated by the bounding box of the road traffic participants. If not, it is not necessary to supplement the vehicle's original point cloud data. If so, a larger closed area can be formed by the maximum value of the angle to be supplemented and the detection distance to be supplemented, and a smaller closed area can be formed by the minimum value of the angle to be supplemented and the detection distance to be supplemented. The vehicle's area to be supplemented can be obtained by removing the smaller closed area from the larger closed area.

[0071] As an optional embodiment, step S104, determining target obstacle information based on the point cloud data to be supplemented, includes: fusing the point cloud data to be supplemented and the original point cloud data to obtain fused data; and processing the fused data to obtain target obstacle information.

[0072] In this embodiment, the point cloud data to be supplemented and the original point cloud data can be fused to obtain fused data. The fused data can be processed to obtain target obstacle information, which may include the target obstacle's location, bounding box, movement trajectory, vehicle detection range, and area to be supplemented, etc.

[0073] Optionally, the vehicle can communicate with roadside equipment. For example, a connection can be established between the two through vehicle-to-everything (V2X) wireless communication technology. The vehicle can send information such as the predicted trajectory of the target obstacle that disappears from the detection area of ​​the millimeter-wave radar in the vehicle to the roadside equipment. The roadside equipment can compare the obtained predicted trajectory information with the target obstacle's motion trajectory information detected by itself to determine whether the corresponding target obstacle exists. If it exists, the roadside equipment can send the target obstacle information to the vehicle; if it does not exist, it can extract the supplementary point cloud data such as the supplementary angle and supplementary detection distance of the target obstacle's location in the supplementary area from the target obstacle information detected by the roadside equipment and send it to the vehicle.

[0074] Optionally, the vehicle can, based on the data received from the roadside equipment, replace the area to be supplemented detected by the millimeter-wave radar in the vehicle with information such as the actual movement trajectory of the target obstacle sent by the roadside equipment when the received data is actual information about the target obstacle; when the received data is point cloud data to be supplemented, the supplemented point cloud data and the original point cloud data can be fused to obtain fused data, which can then be processed. For example, images can be drawn from the fused data to obtain information about the target obstacle. It should be noted that this is only an example and does not impose specific limitations on the representation of the target obstacle or the processing method of the fused data.

[0075] In this embodiment of the invention, raw point cloud data collected by millimeter-wave radar in a vehicle is acquired; target information of the vehicle is determined based on the raw point cloud data, wherein the target information includes at least information on the driving area where the vehicle is allowed to travel and information on obstacles that obstruct the vehicle's travel; based on the target information, supplementary point cloud data of the vehicle is acquired from roadside equipment; target obstacle information is determined from the obstacle information based on the supplementary point cloud data, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving road. In other words, this embodiment of the invention acquires raw point cloud data from millimeter-wave radar in a vehicle, and can determine target information such as driving area information and obstacle information based on the raw point cloud data. By analyzing the target information, supplementary point cloud data in the vehicle can be determined, and the actual position of the target obstacle in the vehicle's driving road can be determined using the supplementary point cloud data. This ensures that the obstacle does not leave the detection range of the millimeter-wave radar in the vehicle, thereby solving the technical problem of low accuracy in obstacle positioning and achieving the technical effect of improving the accuracy of obstacle positioning.

[0076] Example 2

[0077] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0078] Currently, the millimeter-wave radars commonly used in autonomous driving mainly fall into two categories: forward-facing radars and corner radars. Forward-facing radars generally have a longer detection range but a smaller detection angle, while corner radars have a relatively shorter detection range but a larger detection angle. A typical vehicle is equipped with one forward-facing radar and four corner radars, using multiple millimeter-wave radar cameras to cover a 360° area around the vehicle, thereby achieving omnidirectional perception.

[0079] In related technologies, the movement from a narrow beam range to a wide beam range under certain driving conditions can cause the target to be temporarily lost, affecting the stability of the perception results and resulting in the technical problem of low accuracy in target positioning.

[0080] One related technology specifies a deep learning-based roadside-view beyond-line-of-sight full-domain fusion perception system. This system collects and fuses heterogeneous data from roadside cameras, LiDAR, and millimeter-wave radar. Deep learning is then used to process the fused image and LiDAR point cloud data separately, and finally, a decision-level fusion process is employed to achieve fused perception. By deploying a roadside perception system and combining the advantages of each data source—image, LiDAR point cloud, and millimeter-wave radar point cloud—the perception range can be improved, and scene understanding of the monitored area can be achieved at multiple levels. Ultimately, this provides sufficient and reliable perception information for connected autonomous vehicles.

[0081] In another related technology, a vehicle-road cooperative system and method are specified, belonging to the field of communication technology. The vehicle-road cooperative system includes: an edge cloud, roadside computing nodes, and roadside micro base stations. The roadside computing nodes are used to acquire raw traffic data collected by the roadside infrastructure and determine traffic information based on this raw traffic data. The roadside micro base stations include: a near-field broadcast communication module and a mobile network communication module. The near-field broadcast communication module is used to send the acquired traffic information to traffic participants within a first coverage area, and the mobile network communication module is used to send the acquired traffic information to the edge cloud. The first coverage area is the coverage area of ​​the roadside micro base stations. This method can reduce the latency and construction cost of the vehicle-road cooperative system and improve its processing efficiency.

[0082] However, the above methods still have the technical problem of low accuracy in target positioning.

[0083] To address the aforementioned issues, this invention proposes a method for enhancing the perception capabilities of vehicle-mounted millimeter-wave radar based on roadside equipment. This method includes: acquiring the camera view of the vehicle-mounted millimeter-wave radar and using this view as preset information; acquiring target information detected by the vehicle-mounted millimeter-wave radar across multiple consecutive frames; acquiring road traffic participant target information from the multi-frame monitoring results, determining the trajectory of the road traffic target, calculating the drivable area of ​​the vehicle under the current road conditions based on the detection results of the current frame, and calculating the missing portion of the drivable area; determining the area to be supplemented based on the way the target track disappears, and sending this information to the roadside equipment; and the roadside equipment determining the supplementary data based on the data transmitted from the vehicle and sending it to the vehicle. This method solves the technical problem of low accuracy in target localization and achieves the technical effect of improving the accuracy of target localization.

[0084] The method for determining obstacles in the driving road of the vehicle according to an embodiment of the present invention will be further described below.

[0085] Figure 2 This is a flowchart illustrating a method for enhancing the perception capability of vehicle-mounted millimeter-wave radar based on roadside equipment according to an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0086] Step S202: Obtain the camera view of the vehicle-mounted millimeter-wave radar and determine the preset information.

[0087] In the technical solution provided by step S202 of the present invention, the maximum detection distance of all vehicle-mounted millimeter-wave radars under their respective camera views can be tested and recorded, and all maximum detection distances can be stitched together to determine preset information. The preset information can be parameters of the overall detection area camera view of the vehicle-mounted millimeter-wave radar, which may include the detection angle of the vehicle-mounted millimeter-wave radar and the detection distance under each detection angle. It should be noted that this is only an example and no specific limitation is made to the preset information.

[0088] Optionally, the vehicle-mounted millimeter-wave radar may include a forward-facing millimeter-wave radar and four corner millimeter-wave radars. By overlapping the camera field of view of multiple millimeter-wave radars, an area around the vehicle can be covered, thus achieving all-around perception. To balance detection range and detection angle, the forward-facing millimeter-wave radar can be divided into two transmission modes: narrow beam and wide beam. Narrow beams have a longer detection range but a smaller angular range, while wide beams have a larger angular range but a shorter detection range.

[0089] For example, when a vehicle is turning on a curve, the target will move between a narrow beam range and a wide beam range, resulting in the temporary loss of the target.

[0090] Step S204: Obtain target information detected by vehicle-mounted millimeter-wave radar in multiple consecutive frames.

[0091] In the technical solution provided by step S204 of the present invention, the target information of the vehicle millimeter-wave radar can be obtained in the detection results of multiple consecutive frames. The target information can be the original point cloud data, which can include the position, speed, bounding box and other information of road traffic participants such as vehicles and pedestrians, and can also include the information of road boundary targets such as guardrails and curbs. It should be noted that this is only an example and is not a specific limitation.

[0092] Step S206: Obtain the target trajectory and calculate the missing part of the camera's view.

[0093] In the technical solution provided in step S206 of the present invention, the driving trajectory of the road traffic target can be determined based on the target information of road traffic participants in the obtained continuous multi-frame detection results. The drivable area of ​​the vehicle under the current road conditions can be calculated based on the detection results of the current frame. The drivable area can be compared with the camera view of the vehicle-mounted millimeter-wave radar obtained in step S202. If the camera view of the vehicle-mounted millimeter-wave radar is smaller than the drivable area, the corresponding missing part in the drivable area can be determined within the camera view of the vehicle-mounted millimeter-wave radar. If the camera view of the vehicle-mounted millimeter-wave radar is greater than or equal to the drivable area, the following steps are not required.

[0094] Step S208: Determine the area to be supplemented based on the way the target track disappears, and send it to the roadside equipment.

[0095] In the technical solution provided by step S208 of the present invention, the existence of the target track can be analyzed. When the target track disappears, the coordinates at the time of track disappearance can be determined, the area to be supplemented can be further determined, and the area to be supplemented can be sent to the roadside equipment.

[0096] Optionally, Figure 3 This is a schematic diagram illustrating how a target leaves the camera's field of view from the narrow beam range of a front radar, according to an embodiment of the present invention. Figure 3 As shown, the white fan-shaped area in front of the vehicle is the narrow beam detection range of the front radar. The black squares and dashed lines within this range represent the tracks of the disappearing target. The gray fan-shaped area on the left is the area to be supplemented. Based on the target's movement before disappearing, the target's trajectory can be predicted, and the angle of the predicted trajectory can be determined as the area to be supplemented. The detection distance at the corresponding angle within the radar's panoramic camera's time range can be used as the minimum distance to be supplemented, and the maximum detection distance of the narrow beam can be used as the maximum distance to be supplemented. The area to be supplemented can be formed based on the angle to be supplemented, the minimum distance to be supplemented, and the maximum distance to be supplemented.

[0097] Optionally, Figure 4This is a schematic diagram of a region to be supplemented when a target is occluded, according to an embodiment of the present invention. Figure 4 As shown, the white fan-shaped area in front of the vehicle is the narrow beam detection range of the front radar. Within this range, there is a target closest to the vehicle. The trajectory of the disappearing target enters behind the closest target. The gray area behind the closest target forms the area to be supplemented. If the coordinates of the target when it disappears are outside the radar's panoramic detection range but within the narrow beam detection range of the front radar, we can analyze whether the radar's panoramic detection range at the corresponding angle is generated by the monitoring frame of road traffic. If not, no processing is required. Otherwise, we can determine whether the disappearing target disappeared due to occlusion. If so, for the second-degree target at the corresponding angle before disappearing, we can estimate the target's trajectory based on the situation before the target disappeared. The radar detection angle corresponding to the estimated target coordinates can be used as the angle to be supplemented. The radial distance from the position of the first-degree target at the corresponding angle to the radar can be used as the minimum supplement distance. The maximum radar detection distance at the corresponding angle can be used as the maximum supplement distance. The area to be supplemented can be formed based on the angle to be supplemented, the minimum supplement distance, and the maximum supplement distance.

[0098] In step S210, the roadside equipment determines the supplementary data based on the data from the vehicle and sends it to the vehicle.

[0099] In the technical solution provided in step S210 of the present invention, the vehicle can communicate with the roadside equipment. For example, communication can be established through vehicle-to-everything (V2X) wireless communication technology. The predicted information of the determined area to be supplemented and the disappeared targets can be sent to the roadside equipment. The roadside equipment can compare the predicted information of the disappeared targets from the vehicle-mounted millimeter-wave radar with the target information detected by the roadside millimeter-wave radar to determine whether there is a corresponding target. If there is, the target information can be sent to the vehicle. If there is no target, the original point cloud data of the corresponding area to be supplemented can be extracted from the detection data of the roadside millimeter-wave radar and then sent to the vehicle.

[0100] Optionally, the vehicle can receive data from roadside equipment. When receiving data from roadside equipment, the vehicle can replace the target data predicted by the onboard millimeter-wave radar with the target information sent by the roadside equipment. When the onboard millimeter-wave radar receives point cloud data, it can fuse the point cloud data from the roadside equipment with the point cloud data from the onboard millimeter-wave radar. This allows for further processing, and the perception result after comprehensive processing by the onboard and roadside millimeter-wave radars is output as the final result.

[0101] This invention collects raw point cloud data from a millimeter-wave radar in a vehicle. Based on this raw point cloud data, target information such as the driving area and obstacles hindering the vehicle's movement can be determined. By analyzing the target information, supplementary point cloud data can be identified within the vehicle. This supplementary point cloud data is then used to determine the actual location of the target obstacles on the vehicle's driving path, thereby ensuring that the obstacles do not fall out of the detection range of the millimeter-wave radar in the vehicle. This solves the technical problem of low accuracy in obstacle localization and achieves the technical effect of improving the accuracy of obstacle localization.

[0102] Example 3

[0103] According to an embodiment of the present invention, a device for determining obstacles in a vehicle's driving path is also provided. It should be noted that this device for determining obstacles in a vehicle's driving path can be used to execute the method for determining obstacles in a vehicle's driving path described in Embodiment 1.

[0104] Figure 5 This is a schematic diagram of a device for determining obstacles in a vehicle's driving path according to an embodiment of the present invention. Figure 5 As shown, the obstacle determination device 500 in the vehicle driving road may include: a first acquisition unit 502, a first determination unit 504, a second acquisition unit 506, and a second determination unit 508.

[0105] The first acquisition unit 502 is used to acquire raw point cloud data collected by the millimeter-wave radar in the vehicle.

[0106] The first determining unit 504 is used to determine the target information of the vehicle based on the original point cloud data, wherein the target information includes at least the driving area information that allows the vehicle to drive and the obstacle information that obstructs the vehicle's driving.

[0107] The second acquisition unit 506 is used to acquire the point cloud data of the vehicle to be supplemented from the roadside equipment based on the target information.

[0108] The second determining unit 508 is used to determine target obstacle information in obstacle information based on the point cloud data to be supplemented, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the road where the vehicle is traveling.

[0109] Optionally, the first acquisition unit 502 may include: a first determining module, used to determine the detection distance of all millimeter-wave radars in the vehicle respectively; and a stitching module, used to stitch together all the detection distances to obtain the detection range of the vehicle.

[0110] Optionally, the second acquisition unit 506 may include: a second determining module, used to determine the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information, wherein the starting coordinates are the coordinates of the frame in which the target obstacle appears, and the disappearance coordinates are the coordinates of the target obstacle in the frame before it disappears; and a first acquisition module, used to acquire the point cloud data to be supplemented from the roadside device based on the starting coordinates and disappearance coordinates.

[0111] Optionally, the second determining module may include: a first determining submodule, used to determine the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates; and a second determining submodule, used to determine the point cloud data corresponding to the area to be supplemented in the roadside equipment as the point cloud data to be supplemented.

[0112] Optionally, the second determining unit 506 may further include: a first prediction module, used to predict the target coordinates of the target obstacle based on the starting coordinates and the disappearance coordinates in response to the starting coordinates being within the detection range and the disappearance coordinates being outside the detection range, or in response to the starting coordinates and the disappearance coordinates being both within the detection range, wherein the target coordinates may be the coordinates of the target obstacle in the frame in which it disappears; and a third determining module, used to determine the area to be supplemented for the vehicle based on the target coordinates.

[0113] Optionally, the third determining module may include: a third determining submodule, used to determine the angle to be supplemented based on the target coordinates and the preset length corresponding to the target obstacle; a fourth determining submodule, used to determine the detection distance corresponding to the angle to be supplemented; and a fifth determining submodule, used to determine the closed area composed of the angle to be supplemented and the detection distance corresponding to the angle to be supplemented as the area to be supplemented.

[0114] Optionally, the first determining unit 504 may include: a fusion module for fusing the point cloud data to be supplemented and the original point cloud data to obtain fused data; and a processing module for processing the fused data to obtain target obstacle information.

[0115] According to an embodiment of the present invention, a first acquisition unit acquires raw point cloud data collected by a millimeter-wave radar in a vehicle, and a first determination unit determines target information of the vehicle based on the raw point cloud data. The target information includes at least driving area information that allows the vehicle to travel and obstacle information that obstructs the vehicle's travel. A second acquisition unit acquires supplementary point cloud data of the vehicle from roadside equipment based on the target information, and a second determination unit determines target obstacle information from the obstacle information based on the supplementary point cloud data. The target obstacle information is used to characterize the actual position of the target obstacle in the road where the vehicle is traveling, thereby solving the technical problem of low accuracy in obstacle positioning and achieving the technical effect of improving the accuracy of obstacle positioning.

[0116] Example 4

[0117] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the method for determining obstacles in a vehicle driving road as described in Embodiment 1.

[0118] Example 5

[0119] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the method for determining obstacles in a vehicle driving road as described in Embodiment 1.

[0120] Example 6

[0121] According to an embodiment of the present invention, a vehicle is also provided, which is used to perform the method for determining obstacles in the vehicle driving road according to the embodiments of the present invention.

[0122] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0123] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0125] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0126] Furthermore, the functional units in the various embodiments of the present invention 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0127] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part 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 the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0128] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining obstacles in a vehicle's driving path, characterized in that, The method includes: Acquire raw point cloud data collected by millimeter-wave radar in the vehicle; The target information of the vehicle is determined based on the original point cloud data, wherein the target information includes at least the driving area information that allows the vehicle to drive and the obstacle information that hinders the vehicle from driving; Based on the target information, the point cloud data of the vehicle to be supplemented is obtained from the roadside equipment; Based on the point cloud data to be supplemented, target obstacle information is determined from the obstacle information, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving road; The process of acquiring the point cloud data of the vehicle to be supplemented from the roadside equipment based on the target information includes: determining the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information, wherein the disappearance coordinates are the coordinates of the target obstacle in the frame before it disappears; determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates; predicting the target coordinates of the target obstacle based on the starting coordinates and the disappearance coordinates, wherein the target coordinates can be the coordinates of the target obstacle in the frame where it disappears; determining the angle to be supplemented based on the target coordinates and the preset length corresponding to the target obstacle; determining the detection distance corresponding to the angle to be supplemented; determining the closed area formed by the angle to be supplemented and the detection distance corresponding to the angle to be supplemented as the area to be supplemented; and determining the point cloud data in the roadside equipment corresponding to the area to be supplemented as the point cloud data to be supplemented.

2. The method according to claim 1, characterized in that, The method further includes: The detection distance and detection angle of all millimeter-wave radars in the vehicle are determined respectively; The detection range of the vehicle is obtained by stitching together all the detection distances and detection angles.

3. The method according to claim 1, characterized in that, The starting coordinates are the coordinates of the frame in which the target obstacle appears.

4. The method according to claim 1, characterized in that, Determining the target obstacle information based on the point cloud data to be supplemented includes: The point cloud data to be supplemented and the original point cloud data are fused to obtain fused data; The fused data is processed to obtain the target obstacle information.

5. A device for determining obstacles in a vehicle's driving path, characterized in that, The device includes: The first acquisition unit is used to acquire raw point cloud data collected by the millimeter-wave radar in the vehicle; The first determining unit is configured to determine the target information of the vehicle based on the original point cloud data, wherein the target information includes at least driving area information that allows the vehicle to drive and obstacle information that obstructs the vehicle's driving. The second acquisition unit is used to acquire the point cloud data to be supplemented for the vehicle from the roadside equipment based on the target information; The second determining unit is used to determine target obstacle information from the obstacle information based on the point cloud data to be supplemented, wherein the target obstacle information is used to characterize the actual position of the target obstacle in the vehicle's driving road; The second acquisition unit is configured to acquire the point cloud data of the vehicle to be supplemented from the roadside equipment based on the target information through the following steps: determining the starting coordinates and disappearance coordinates of the target obstacle in the obstacle information, wherein the disappearance coordinates are the coordinates of the target obstacle in the frame before disappearance; determining the area to be supplemented for the vehicle based on the starting coordinates and the disappearance coordinates; predicting the target coordinates of the target obstacle based on the starting coordinates and the disappearance coordinates, wherein the target coordinates can be the coordinates of the target obstacle in the frame where it disappears; determining the angle to be supplemented based on the target coordinates and the preset length corresponding to the target obstacle; determining the detection distance corresponding to the angle to be supplemented; determining the closed area formed by the angle to be supplemented and the detection distance corresponding to the angle to be supplemented as the area to be supplemented; and determining the point cloud data in the roadside equipment corresponding to the area to be supplemented as the point cloud data to be supplemented.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 4.

7. A vehicle, characterized in that, Used to perform the method according to any one of claims 1 to 4.

Images