Identification method, control method and system based on vehicle driving blind area

Abstract

The invention belongs to the technical field of automobile intelligent driving, and particularly relates to an identification method based on a vehicle driving blind area, a control method and a system thereof, and the identification method based on the vehicle driving blind area comprises the steps: obtaining the sizes of a vehicle center point, a stop line and a pedestrian crossing; determining a region of interest and a blind area direction; generating a maximum angle line passing through a surrounding vehicle bounding box corner point in the region of interest based on the vehicle center point; calculating the proportion of the pedestrian crosswalk segmented by the maximum angle line through the pedestrian crosswalk in the blind area direction; according to the method, the problem that in a complex urban road environment, an existing automatic driving system is difficult to effectively recognize and deal with a blind area is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile intelligent driving, and specifically relates to an identification method and a control method and a system thereof based on a vehicle driving blind spot. Background Art

[0002] With the continuous development of autonomous driving technology, vehicles are equipped with more and more sensors and intelligent systems. Modern vehicles are usually equipped with sensors such as cameras and radars, which can sense the vehicle's position, posture, speed and other states in real time. At the same time, the application of high-precision maps and navigation systems enables vehicles to obtain more detailed road information, such as lane lines, traffic signs, etc. These technological advances have laid the foundation for improving the safety and intelligence level of vehicles.

[0003] However, vehicles still face many challenges in complex urban road environments. Especially on multi-lane urban roads, when a vehicle is about to pass through a short intersection without a traffic light or a black light in the direction of travel, if a large vehicle in the side lane slows down or stops, it may cause a blind spot, increasing the risk of collision with crossing pedestrians or vehicles. Existing autonomous driving systems often find it difficult to effectively identify and respond to such potentially dangerous situations, which can easily lead to emergency braking or collision accidents.

[0004] In addition, existing autonomous driving systems often rely on high-performance sensors to assist in identifying blind spots when dealing with such scenarios. However, this approach not only increases the cost of the vehicle, but may also cause unnecessary braking due to oversensitivity, affecting the smoothness and comfort of driving. At the same time, methods that rely solely on sensors are also difficult to fully utilize the driver's experience and judgment, and cannot predict potential dangerous situations based on experience like human drivers. Summary of the invention

[0005] In view of the shortcomings of the prior art described above, an object of the present invention is to provide a method for identifying and controlling a vehicle driving blind spot and a system thereof, which solves the problem that the existing automatic driving system is difficult to effectively identify and deal with blind spots in complex urban road environments.

[0006] To achieve the above purpose, the present invention adopts the following technical solution.

[0007] A first aspect of the present invention provides a method for identifying a vehicle driving blind spot, comprising: Get the center point of the vehicle and the size of the crosswalk; Determine the areas of interest and blind spots; Generate a maximum angle line passing through the corner points of the bounding box of the surrounding vehicles in the focus area based on the center point of the vehicle; Calculate the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot; and Blind spot areas are identified based on the ratio and the size of the crosswalk.

[0008] As an optional implementation, determining the area of ​​interest includes: Define the lateral extent to include up to two lanes on either side of the vehicle; and Define the longitudinal range to exclude vehicles whose front end has not passed the center point of the vehicle and vehicles whose front end has passed the far edge of the upcoming intersection crosswalk; The area of ​​interest is determined based on the horizontal and vertical extents.

[0009] As an optional implementation, generating a maximum angle line passing through corner points of a bounding box of surrounding vehicles in the focus area based on the center point of the vehicle includes: Based on the center point of the vehicle, the first maximum angle line and the second maximum angle line are generated towards the front and rear respectively, where: The first maximum angle line connects the center point of the vehicle and the corner point of the outermost edge of the bounding box of the front vehicle in the focus area; The second maximum angle line connects the center point of the vehicle and the corner point of the outermost edge of the bounding box of the rear vehicle in the focus area; Calculating the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot includes calculating the proportion of the crosswalk divided by the first maximum angle line through the crosswalk in the direction of the blind spot.

[0010] As an optional implementation manner, the crosswalk size includes the crosswalk length and the crosswalk width; and the identifying the blind spot area based on the ratio and the crosswalk size includes: Obtaining a preset width of the longitudinal far end of the blind spot area based on the width of the crosswalk; The blind spot area is identified based on the ratio, the length of the crosswalk, and a preset width of the longitudinal distal end of the blind spot area.

[0011] A second aspect of the present invention provides a control method based on a vehicle driving blind spot, comprising: Identifying a blind spot area of ​​the vehicle, wherein the blind spot area is obtained based on the method for identifying a vehicle driving blind spot according to the first aspect of the present invention; Determine whether to enable pre-braking decision based on the proportion of the blind spot area occupying the crosswalk; When the pre-braking decision is enabled, generating a trajectory including a series of trajectory points within a predetermined time period; Adjust the speed limit at each trajectory point based on the distance from the ego vehicle to the upcoming intersection; and Control the ego vehicle speed according to the adjusted speed limit at the trajectory point to achieve the desired deceleration.

[0012] As an optional implementation manner, the determining whether to enable the pre-braking decision based on the proportion of the blind spot area occupying the crosswalk includes: Activating pre-braking decision when the ratio exceeds a preset ratio of the length of the crosswalk; and When the ratio is less than or equal to a preset ratio of the length of the crosswalk, the pre-braking decision is not enabled.

[0013] As an optional implementation, when the pre-braking decision is enabled, a trajectory including a series of trajectory points within a predetermined time period is generated, wherein each trajectory point represents a position of the vehicle at a specific moment within the predetermined time period.

[0014] As an optional implementation, adjusting the speed limit of each trajectory point includes: The speed reduction value X is calculated based on a preset calculation formula, where P is the proportion of the blind spot area occupying the crosswalk, and V_ego is the current speed of the vehicle.

[0015] As an optional implementation manner, the control method based on the vehicle driving blind spot also includes: Sending a voice reminder to the driver after a predetermined time delay after the pre-braking decision is enabled, the voice reminder is used to instruct the driver to pay attention to the road conditions ahead; Get the stop line; When the center of the vehicle is within a predetermined distance from the stop line of the intersection, the vehicle lights are activated if the pre-braking decision is enabled.

[0016] A third aspect of the present invention provides a vehicle driving blind spot recognition system, comprising: an acquisition unit, at least for acquiring information about the vehicle and road conditions through one or more information sources; A determination unit, at least for determining a region of interest; The generating unit is at least used to generate a maximum angle line passing through the corner points of the bounding box of the surrounding vehicles in the focus area based on the center point of the vehicle; the calculating unit is at least used to calculate the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the blind spot direction; the identifying unit is used to identify the blind spot area based on the determined proportion and the preset width of the longitudinal far end.

[0017] A fourth aspect of the present invention provides a control system based on a vehicle driving blind spot, comprising: An identification unit, at least used to identify a blind spot area of ​​a vehicle, wherein the blind spot area is obtained based on the identification method based on a vehicle driving blind spot according to the first aspect of the present invention; A decision unit, at least for determining whether to enable a pre-braking decision based on a proportion of the blind spot area occupying the crosswalk; A trajectory generating unit, at least for generating a trajectory including a series of trajectory points within a predetermined time period when a pre-braking decision is enabled; an adjusting unit, at least for adjusting a speed limit at each trajectory point based on a distance to an upcoming intersection; and a control unit, at least for controlling a vehicle speed according to the adjusted speed limit at the trajectory point to achieve an expected deceleration.

[0018] A fifth aspect of the present invention provides an electronic device, comprising: At least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the steps of the identification method described in the first aspect of the present invention or the control method described in the second aspect of the present invention.

[0019] The sixth aspect of the present invention provides a readable storage medium storing a computer program, characterized in that the computer program is executed by a processor to perform the steps of the identification method described in the first aspect of the present invention or the control method described in the second aspect of the present invention.

[0020] In summary, compared with the prior art, the present invention includes at least one of the following beneficial technical effects: 1. Improve safety: Reduce the risk of collision by actively identifying special blind spots and intelligent pre-braking. 2. Enhanced intelligence: Combine vehicle status, road conditions and driving experience to achieve smarter decision-making. 3. Improve comfort: avoid unnecessary emergency braking and ensure smooth driving. 4. Reduce costs: Reduce dependence on high-performance sensors and optimize costs. 5. Strong adaptability: It can be applied to complex urban road environments, especially multi-lane intersections. 6. Human-machine collaboration: Through voice reminders and other means, effective cooperation between the vehicle computer and the driver is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a schematic diagram of an architecture based on a vehicle driving blind spot in a specific embodiment of the present invention.

[0023] Figure 2It is a flow chart of a method for identifying a vehicle driving blind spot in a specific embodiment of the present invention.

[0024] Figure 3 It is a schematic diagram of obtaining vehicle and road condition information in a specific embodiment of the present invention.

[0025] Figure 4 It is a flow chart of a control method based on a vehicle driving blind spot in a specific embodiment of the present invention.

[0026] Figure 5 A block diagram of a vehicle driving blind spot recognition system according to a specific embodiment of the present invention

[0027] Figure 6 A block diagram of a control system based on a vehicle driving blind spot in a specific embodiment of the present invention

[0028] Figure 7 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention. In addition, it should be understood that the specific embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0030] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments of the present invention. In addition, in the following embodiments, the description of each embodiment has its own emphasis, and for parts not described in detail in one embodiment, reference can be made to the relevant description of other embodiments.

[0031] There is a special driving environment on urban roads, namely, intersections without traffic lights. In this environment, both vehicles and pedestrians have the right of way, which poses unique challenges and safety hazards to drivers. This special road section requires drivers to remain highly vigilant and adopt special driving skills. In this special road environment, when drivers encounter obstructed vision, safety accidents are likely to occur.

[0032] The inherent uncertainty of this particular stretch of road can make it difficult for drivers to assess surrounding traffic conditions and make informed decisions about when to slow down, stop, or pass, a challenge that is often exacerbated at night or in poor weather conditions, which are common in urban environments.

[0033] It is very difficult to maneuver a vehicle at an intersection without traffic lights. The driver often needs to perform precise deceleration or parking operations to avoid collisions with pedestrians or vehicles that suddenly appear. Considering that vehicles or pedestrians may appear from all directions, it is a great challenge for the driver.

[0034] With the advancement of vehicle technology, there is a growing demand for smart cars that can help drivers cope with the challenges of this special driving environment. At this time, smart cars with driving assistance functions, if they also have blind spot recognition capabilities and can adopt pre-braking strategies, can enhance users' driving safety at intersections without signal lights, improve traffic flow, reduce driver stress, and enhance driver experience.

[0035] like Figure 1 As shown, the self-driving car is equipped with cameras and radar sensors, which can sense the vehicle's position, posture, speed and other states in real time, whether there are traffic lights at the intersection and the specific light color and shape, as well as specific lane line information, such as solid or dotted lines, lane width, lane line position, etc. Combined with navigation information broadcast by the map, it can obtain information on the same-direction lane and the opposite lane, reference information on the trajectory of the vehicle in the current lane, etc. By using high-precision map information, it can obtain information on short intersections and crosswalks in real time, so that the vehicle can reach its destination safely, risk-free, efficiently and intelligently.

[0036] The core part of the present invention lies in the planning module. The recognition method, control method and system based on the vehicle driving blind spot provided by the present invention can actively identify the blind spot range of the crosswalk based on the planning module, obtain the crosswalk information of the short intersection ahead and the no-traffic light information output by the perception from the high-precision map, and then plan the blind spot range blocked by the vehicle's box frame by simulating the ray perspective starting from the center point of the vehicle; then output the pre-braking decision of this scene; in the horizontal and vertical trajectory planning parts, according to the pre-braking decision, output a trajectory point with a preset time such as 4s in real time, and then adjust the speed limit value of each trajectory point in combination with the distance value to the intersection, and consider the jerk of deceleration comfort, and finally give each trajectory point speed information to achieve the expected deceleration and avoid the risk of collision with crossing obstacles such as pedestrians and animals.

[0037] The technical solution to be protected by the present invention is explained in detail below in combination with various aspects and specific embodiments of the present invention.

[0038] like Figure 2 and Figure 3 As shown, the first aspect of the present invention provides a method for identifying a vehicle driving blind spot, the method comprising the following steps:

[0039] Step S1: Obtain information about vehicles and road conditions through one or more information sources.

[0040] Specifically, the information source includes but is not limited to sensors such as cameras and laser radars equipped on the vehicle, which can sense the vehicle center point, vehicle position, posture, speed and other states in real time. In addition, the information source can also be navigation information broadcast by the map or V2X information, etc., to obtain information on the same lane and the opposite lane, the trajectory reference information of the vehicle in the current lane, and the vehicle center point, stop line and crosswalk size, the crosswalk size includes the crosswalk length L and the crosswalk width A, etc.

[0041] In one embodiment of the present invention, the acquisition of information on vehicles and road conditions includes at least: acquiring the actual position and status of the vehicle and surrounding vehicles, the position and status of traffic lights at intersections, the distance between the stop line and the crosswalk and the vehicle, etc.

[0042] Step S2: determining a focus area, in which there are surrounding vehicles close to the vehicle.

[0043] Specifically, the focus area includes a specific area around the vehicle, such as the left and right lanes of the vehicle and the area within a certain distance range in front and behind the vehicle, wherein the certain distance range in front and behind the vehicle may be the distance range between the two nearest intersections in front and behind the vehicle. Determining the focus area can help narrow the scope that needs to be analyzed and improve recognition efficiency. After determining the focus area, by paying attention to vehicles, pedestrians and other potential obstacles in the area, the vehicle can be assisted to more accurately identify possible blind spots, providing a basis for subsequent pre-braking strategies, thereby better predicting potential dangerous situations, taking appropriate deceleration operations in advance, and improving vehicle driving safety.

[0044] Specifically, the blind spot direction may be the direction of the blind spot area of ​​interest, or the blind spot direction may be obtained according to the left and right directions of the vehicle. Figure 3 The blind spot direction shown in is the direction corresponding to the left side of the vehicle.

[0045] Step S3: generating a maximum angle line passing through the corner points of the bounding box of surrounding vehicles in the focus area based on the center point of the vehicle;

[0046] Specifically, the vehicle center point (ego) is defined as the geometric center of the vehicle. A bounding box can be generated for each identified surrounding vehicle. The bounding box can be a rectangle whose four corner points completely surround the vehicle. The size of the bounding box can be determined based on the actual size of the detected vehicle or using a preset standard size.

[0047] Step S4: Calculate the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot; specifically, the present invention can identify the stop line through a vehicle-mounted camera or obtain the position of the stop line from high-precision map data. The stop line is usually located in front of the crosswalk, which is the position where the vehicle needs to stop at the intersection.

[0048] The present invention uses a geometric calculation method, such as a line segment intersection algorithm, to calculate the coordinates of the intersection of the maximum angle line and the stop line, which represents the intersection of the blind spot boundary and the stop line, and calculates the proportion of the crosswalk segmented by the maximum angle line through the crosswalk in the direction of the blind spot; Figure 3 As shown, when the first maximum angle line crosses the crosswalk, it will divide the crosswalk into two, and the ratio of the area of ​​the left side crosswalk divided by it to the total area of ​​the crosswalk is the ratio of the crosswalk divided by the maximum angle line through the crosswalk.

[0049] Step S5: identifying a blind spot area based on the ratio and the size of the crosswalk;

[0050] In one embodiment of the present invention, the crosswalk size includes the crosswalk length and the crosswalk width; and the identifying the blind spot area based on the ratio and the crosswalk size includes: Obtaining a preset width of the longitudinal far end of the blind spot area based on the width of the crosswalk; The blind spot area is identified based on the ratio, the length of the crosswalk, and a preset width of the longitudinal distal end of the blind spot area.

[0051] Specifically, the starting point of the longitudinal far end is defined as the far edge of the upcoming crosswalk at the intersection. This position can be identified by the vehicle camera or obtained from the high-precision map data. The preset width of the far edge can be a multiple of the width of the crosswalk, that is, the crosswalk can also be understood as a virtual crosswalk, which can keep the length of the crosswalk unchanged and increase the width of the crosswalk, so that the proportion of the area of ​​the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot also changes. Please continue to refer to Figure 3 , with the stop line as the horizontal line, the preset width of the far edge can be A, or 2A, and correspondingly, the blind area range can be Figure 3 In the B area, or the B+D area, that is, in a possible blind spot range, the ratio P=B area / (B area+C area), the B area represents the blind spot range; or in a possible blind spot range, the ratio P=(B area+D area) / 2(B area+C area), the B area+D area represents the blind spot range.

[0052] In this way, the blind area range can be expanded and the predictability of the blind area range can be improved.

[0053] In one embodiment of the present invention, the present invention also needs to obtain information about the vehicle and road conditions, including determining the actual position and status of the vehicle, which involves using the vehicle's sensors and navigation system to determine the vehicle's precise position, as well as the vehicle's motion status, such as speed and direction. In addition, it is also necessary to determine the position and status of the intersection, which involves using map data and the vehicle's sensor data to determine the position of the intersection, as well as the traffic conditions at the intersection, such as whether there are other vehicles or pedestrians.

[0054] Obtaining information about vehicles and road conditions also includes determining the location and status of traffic lights, which involves using the vehicle's cameras or other sensors to detect the presence and location of traffic lights, and using image recognition technology to determine the status of traffic lights, such as no light or a black light.

[0055] In addition, obtaining information about vehicle and road conditions also includes determining road marking information, which involves using the vehicle's camera or other sensors to detect markings on the road, such as lane lines, stop lines, and crosswalks. Image recognition technology can then be used to parse the specific information of these markings, such as solid or dotted lines, lane width, and the location of lane lines. This information helps the vehicle determine its position on the road more accurately, as well as more accurately predict and plan its own driving trajectory.

[0056] In one embodiment of the present invention, determining the region of interest includes defining a horizontal range and a vertical range.

[0057] Specifically, when defining the lateral range, a maximum of two lanes on each side of the vehicle may be included. For example, if the vehicle is traveling in the middle lane of a multi-lane road, the vehicle's lane, as well as the lane to its left and the lane to its right will be considered. If the vehicle is traveling in the outermost lane of the road, the vehicle's lane and the two lanes inside it will be considered. Figure 3 Focus on the left two lanes as shown.

[0058] This ensures that sufficient attention is paid to the most directly relevant traffic environment around the vehicle, while at the same time not processing too much distant information that may not be relevant to the vehicle's driving safety.

[0059] Specifically, when defining the longitudinal range, the present invention excludes two types of vehicles: one is a vehicle whose front end has not exceeded the center point of the vehicle, and the other is a vehicle whose front end has exceeded the far edge of the upcoming intersection crosswalk.

[0060] Specifically, for vehicles whose fronts have not exceeded the center point of the vehicle, since they are behind or parallel to the vehicle, they usually do not block the view in front of the vehicle, so they can be excluded from the scope of attention. For vehicles whose fronts have exceeded the far edge of the upcoming intersection crosswalk, these vehicles have passed the critical intersection area and are unlikely to have a direct impact on the vehicle's field of vision through the intersection, so they can also be excluded from the scope of attention.

[0061] Here, by defining the area of ​​interest in this way, the most relevant and important surrounding traffic information can be processed centrally, improving computing efficiency and reducing unnecessary interference, helping the vehicle to better identify potential obstacles or risk factors that may affect its safe passage through intersections.

[0062] In one embodiment of the present invention, generating a maximum angle line passing through corner points of a bounding box of surrounding vehicles in a focus area based on a vehicle center point includes: With the center point of the vehicle as a reference, a first maximum angle line F and a second maximum angle line S are generated toward the front and rear, respectively.

[0063] Specifically, Figure 3 As shown, the first maximum angle line F and the second maximum angle line S, the generation process of the first maximum angle line F is as follows: first, identify the bounding box of all front vehicles in the focus area, the bounding box is a virtual rectangular box, used to represent the space occupied by the vehicle on the two-dimensional plane; then, determine the corner point of the outermost edge of the bounding box, that is, the corner point closest to the edge of the lane; finally, connect the center point of the vehicle and the corner point of the outermost edge to form the first maximum angle line F.

[0064] The generation process of the second maximum angle line S is similar: first, identify the bounding boxes of all rear vehicles in the focus area; then, determine the corner points of the outermost edges of these bounding boxes; finally, connect the center point of the vehicle and the corner points of the outermost edges to form the second maximum angle line S.

[0065] Calculating the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot includes calculating the proportion of the crosswalk divided by the first maximum angle line through the crosswalk in the direction of the blind spot.

[0066] Here, the boundary of the vehicle's field of view can be effectively defined in this way. The first maximum angle line represents the boundary of the vehicle's front field of view, and the second maximum angle line represents the boundary of the vehicle's rear field of view. The area between the two lines is the vehicle's potential blind spot, that is, the area that may be difficult for the driver or vehicle sensor to directly observe. The present invention focuses on the problem of the first maximum angle line in the scenario of an unlimited intersection blind spot range.

[0067] The maximum angle line generated in this way can more accurately evaluate the impact of surrounding vehicles on the vehicle's field of view, thereby providing an important basis for subsequent blind spot identification and safety decision-making. It is of great significance to improve the safety of vehicles in complex traffic environments, especially when approaching potentially dangerous areas such as intersections.

[0068] In one embodiment of the present invention, the preset width of the longitudinal distal end can be adjusted according to the width of the crosswalk to adapt to different road conditions and traffic conditions. Specifically, the preset width of the longitudinal distal end can be set to twice the width of the crosswalk, that is, 2A, where A represents the width of the crosswalk.

[0069] This setting method takes into account the changes in the width of pedestrian crossings in different road environments. On urban main roads, pedestrian crossings are usually wider, while on secondary roads or branch roads, pedestrian crossings may be relatively narrow. By associating the preset width with the actual pedestrian crossing width, the range of blind spot recognition can be adaptively adjusted.

[0070] In an application scenario of the present invention, on a busy urban main road, if the width of the crosswalk is 3 meters, the preset width of the longitudinal far end will be 6 meters. This setting can ensure that when the vehicle identifies the blind spot, it fully considers the larger range that may affect the safety of the vehicle. In contrast, on a narrower branch road, if the width of the crosswalk is 2 meters, the preset width of the longitudinal far end will be 4 meters.

[0071] In one embodiment of the present invention, the enabling logic conditions of the vehicle driving blind spot recognition method include: a) & b) & c) & d) & e), wherein: a) The distance between the vehicle and the next intersection stop line dis_to_stopline is less than the first preset length, such as the first preset length = 55m; b) The perception output is that the traffic light status of the next intersection is unknown (corresponding to the direction of the vehicle's intersection), that is, tfl_status == UNKNOWN; c) There is a zebra crossing or pedestrian crossing after the stop line of the next intersection output by the map, that is, is_crosswalk == true; d) There is a lane next to the lane, that is, (llane_n||rlane_n)! = 0; e) In the area of ​​the concerned vehicle, the vehicle farthest from the vehicle in the longitudinal direction has a lower speed, that is, V_smax<preset speed, such as preset speed = 6m / s.

[0072] Here, through this dynamic adjustment mechanism, the present invention can maintain an appropriate blind spot recognition range in different road environments. This approach takes into account both safety and ensures a sufficiently large recognition range on wider roads, while also taking into account efficiency and avoiding unnecessary computing burden on narrower roads. This flexible adjustment strategy helps to improve the adaptability and reliability of the vehicle under various road conditions.

[0073] like Figure 4 As shown, the second aspect of the present invention provides a control method based on a vehicle driving blind spot, comprising the following steps.

[0074] Step S6: Identify the blind spot area of ​​the vehicle.

[0075] Specifically, the present invention utilizes the aforementioned recognition method based on vehicle driving blind spots to obtain blind spot area information. This method takes into account factors such as the traffic environment around the vehicle, road conditions, and the position of other vehicles, and can obtain a more accurate and reasonable blind spot range.

[0076] Step S7: Determine whether to enable the pre-braking decision based on the proportion of the blind spot area occupying the crosswalk.

[0077] Specifically, by calculating the projected area of ​​the blind spot area on the crosswalk or pedestrian crossing and comparing it with the total area of ​​the crosswalk, an occupancy ratio P is obtained, and the ratio can be used to determine whether it is necessary to initiate a pre-braking decision.

[0078] Step S8: When the pre-braking decision is enabled, a trajectory is generated that includes a series of trajectory points within a predetermined time period, such as 4 seconds.

[0079] Specifically, the generated series of trajectory points within a predetermined time period represents the expected position of the vehicle within a future period of time.

[0080] Step S9: Adjust the speed of each trajectory point based on the distance from the vehicle to the upcoming intersection.

[0081] Specifically, as the vehicle approaches an intersection, the present invention gradually reduces the speed of each trajectory point to ensure that the vehicle can safely pass through an area where a blind spot may exist.

[0082] Step S10: Control the vehicle speed according to the adjusted speed limit of the trajectory point to achieve the expected deceleration.

[0083] Specifically, the speed limit is a range of speed values. By precisely adjusting the vehicle's power output and braking force, the speed is ensured to be reduced smoothly, allowing the vehicle to safely pass through potential danger areas while maintaining driving stability and comfort. The best deceleration effect is achieved by continuously monitoring vehicle speed changes and fine-tuning control parameters according to actual conditions.

[0084] In one embodiment of the present invention, the process of determining whether to enable the pre-braking decision based on the proportion of the blind spot area occupying the crosswalk is as follows:

[0085] The present invention calculates the projection length of the blind spot area on the crosswalk and compares it with the total length of the crosswalk to obtain an occupancy ratio, which reflects the coverage degree of the blind spot area on the crosswalk, and compares the calculated occupancy ratio with a preset threshold.

[0086] When the occupancy ratio exceeds a preset ratio of the length of the crosswalk, the present invention determines that the blind spot area poses a greater threat to pedestrian safety, and thus activates the pre-braking decision. For example, if the preset ratio is 50%, it means that when the blind spot area occupies more than 50% of the length of the crosswalk, the pre-braking mechanism will be activated.

[0087] On the contrary, when the occupancy ratio is less than or equal to the preset ratio of the length of the crosswalk, the present invention considers that the blind spot area has relatively little impact on pedestrian safety, so the pre-braking decision is not activated. In this case, the vehicle will continue to operate according to the normal driving strategy and will continue to monitor the changes in the blind spot area.

[0088] The ratio-based decision-making mechanism adopted by the present invention avoids unnecessary deceleration operations while ensuring safety, thereby improving the efficiency and comfort of vehicle driving. At the same time, the present invention takes into account the differences in different road environments and traffic conditions, making the vehicle's response more flexible and intelligent.

[0089] In one embodiment of the present invention, when the pre-braking decision is enabled, a trajectory is generated that includes a series of trajectory points within a predetermined time period. Specifically, the present invention uses the vehicle's sensors and navigation system to obtain information such as the vehicle's real-time position, speed, and direction. Based on these data, the vehicle's movement trajectory within a future period of time is predicted. The predetermined time period is usually set to 3-5 seconds, which is sufficient to cover the vehicle deceleration process, but not too long to cause inaccurate predictions.

[0090] A series of trajectory points are generated within this predetermined time period. For example, if the predetermined time period is 4 seconds, then a trajectory point is generated every 1 second, and a total of 4 trajectory points are generated. Each trajectory point contains not only the position information, but also the predicted speed and acceleration at that moment.

[0091] The present invention takes into account multiple factors when generating trajectories, including the vehicle's current motion state, road geometry, traffic rules, and possible behaviors of other road users, and uses high-precision map data to improve the accuracy of trajectory prediction, especially in scenarios such as complex intersections or curves.

[0092] By generating such a series of detailed trajectory points, the present invention provides an accurate reference for subsequent speed control and path planning, allowing the vehicle to perform pre-braking operations more smoothly and safely while maintaining driver comfort and efficiency.

[0093] In one embodiment of the present invention, when adjusting the speed limit of each trajectory point, the present invention uses a preset calculation formula to determine the speed reduction value.

[0094] Specifically, first determine the proportion P of the blind spot area occupying the crosswalk, and at the same time, obtain the current speed V_ego of the vehicle in real time through the vehicle navigation or high-precision map; use the preset calculation formula X=J+θPV_ego to calculate the speed reduction value X. In this specific calculation formula, J is the basic deceleration value, such as J=0.3, to ensure that there is a certain deceleration even when the blind spot occupies a small proportion; θ is the proportional coefficient, such as θ=0.1, which is used to adjust the sensitivity of deceleration according to the blind spot occupancy proportion P; P is the proportion of the blind spot occupying the crosswalk; V_ego is the current speed of the vehicle.

[0095] Here, in this way, the speed reduction value X can be dynamically adjusted to adapt to different traffic environments and vehicle conditions. For example, if the blind spot occupancy ratio is high or the vehicle speed is high, the calculated value of X will be larger, thereby guiding the vehicle to decelerate more significantly to ensure safety. Conversely, if the blind spot occupancy ratio is low or the vehicle speed is slow, the value of X will be small, and the deceleration will be relatively gentle.

[0096] The present invention applies the calculated speed reduction value X to the speed limit adjustment of the trajectory point, ensuring that the speed limit of each trajectory point can reflect the necessary safety deceleration requirements, thereby optimizing the vehicle's driving trajectory and speed and ensuring driving safety.

[0097] In one embodiment of the present invention, a voice reminder is sent to the driver after a predetermined time delay after the pre-braking decision is enabled, and the voice reminder is used to instruct the driver to pay attention to the road conditions ahead;

[0098] Specifically, when the vehicle triggers the active blind spot pre-braking action, a 0.3s delay is set. This short delay can prevent the sudden reminder from disturbing the driver. After 0.3s, a voice reminder is sent to the driver through the vehicle audio system, and the reminder content can be: "Be careful of the road conditions ahead, drive carefully." This concise and clear reminder is designed to draw the driver's attention to potential dangers ahead without excessively distracting the driver.

[0099] In one embodiment of the present invention, when the center of the vehicle is located within a predetermined distance from a stop line at an intersection, the vehicle lights are activated if the pre-braking decision is enabled.

[0100] Specifically, after the active blind spot pre-braking is triggered, the vehicle's position is continuously monitored, and the vehicle's positioning system and high-precision map data can be used to accurately calculate the distance between the vehicle's center point and the intersection stop line. When both conditions (a) and (b) are met, the vehicle's headlights are turned on: (a) Active blind spot pre-braking has been triggered; (b) The distance between the center of the vehicle and the stop line of the intersection is less than a preset distance, such as 20m.

[0101] Specifically, when both conditions (a) and (b) are met at the same time, the vehicle's headlights will flash once. The purpose of this light reminder is to warn potential pedestrians who may be crossing the crosswalk, as well as vehicles that may be unaware of the situation in the other lane. In this way, the present invention not only reminds other road users that the vehicle is approaching the intersection, but also indirectly illuminates possible blind spots, thereby increasing the driver's field of vision.

[0102] These interactive reminder strategies are combined with the vehicle's automatic control system to form a comprehensive safety warning mechanism. Through this multi-level safety measure, the present invention fully utilizes the vehicle's automatic control, the driver's judgment and the attention of other road users, thereby comprehensively improving driving safety, especially in complex intersection environments.

[0103] like Figure 5 As shown, the third aspect of the present invention provides a recognition system based on a vehicle driving blind spot, comprising: An acquisition unit 11 is used to acquire at least the center point of the vehicle, the stop line and the size of the crosswalk; A determination unit 12, at least used to determine the direction of the concerned area and the blind area; A generating unit 13 is at least used to generate a maximum angle line passing through corner points of a bounding box of surrounding vehicles in a focus area based on a center point of the vehicle; The calculation unit 14 is at least used to calculate the proportion of the crosswalks divided by the maximum angle line through the crosswalk in the direction of the blind spot; The identification unit 15 is used to identify the blind spot area based on the ratio and the size of the crosswalk.

[0104] Based on the same idea as the method in the above-mentioned embodiment, the vehicle driving blind spot recognition system provided by the present invention can implement the method of the above-mentioned first aspect embodiment. For the convenience of explanation, the structural diagram of the system embodiment only shows the parts related to the embodiment of the present invention. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the system, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0105] like Figure 6As shown, the fourth aspect of the present invention provides a control system based on a vehicle driving blind spot, comprising: A blind spot recognition unit 16, at least used to recognize a blind spot area of ​​the vehicle, wherein the blind spot area is obtained based on the recognition method based on the vehicle driving blind spot described in any one of the above embodiments; A pre-braking decision unit 17, at least for determining whether to enable a pre-braking decision based on a proportion of the blind spot area occupying the crosswalk; a trajectory generating unit 18, at least for generating a trajectory including a series of trajectory points within a predetermined time period when the pre-braking decision is enabled; a speed limiting unit 19, configured to adjust a speed limit at each trajectory point based at least on a distance from the ego vehicle to an upcoming intersection; The deceleration control unit 20 is at least used to control the vehicle speed according to the adjusted speed limit of the trajectory point to achieve the expected deceleration.

[0106] Based on the same idea as the method in the above-mentioned embodiment, the control system based on the vehicle driving blind spot provided by the present invention can implement the method of the above-mentioned second aspect embodiment. For the convenience of explanation, the structural diagram of the system embodiment only shows the parts related to the embodiment of the present invention. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the system, and may include more or fewer components than shown in the diagram, or a combination of certain components, or a different arrangement of components.

[0107] like Figure 7 As shown, the fifth aspect of the present invention provides an electronic device, including: At least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the steps of the method described in any one of the above embodiments.

[0108] A sixth aspect of the present invention discloses a readable storage medium storing a computer program, wherein the computer program is executed by a processor to perform the steps of the method described in any one of the above embodiments.

[0109] Computer-readable storage media may include: any entity or device capable of carrying a computer program, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc. A computer program includes a computer program code. The computer program code may be in source code form, object code form, an executable file, or some intermediate form, etc. A computer-readable storage medium may include: any entity or device capable of carrying a computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0112] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying a vehicle driving blind spot, characterized in that: include: Get the center point of the vehicle and the size of the crosswalk; Determine the areas of interest and blind spots; Generate a maximum angle line passing through the corner points of the bounding box of the surrounding vehicles in the focus area based on the center point of the vehicle; Calculate the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot; as well as Blind spot areas are identified based on the ratio and the size of the crosswalk.

2. The method for identifying a vehicle driving blind spot according to claim 1, characterized in that: Areas of concern identified include: Define the lateral extent to include up to two lanes on either side of the vehicle; and Define the longitudinal range to exclude vehicles whose front end has not passed the center point of the vehicle and vehicles whose front end has passed the far edge of the upcoming intersection crosswalk; The area of ​​interest is determined based on the horizontal and vertical extents.

3. The method for identifying a vehicle driving blind spot according to claim 2, characterized in that: The method of generating a maximum angle line passing through corner points of a bounding box of surrounding vehicles in the focus area based on the center point of the vehicle comprises: Based on the center point of the vehicle, the first maximum angle line and the second maximum angle line are generated towards the front and rear respectively, where: The first maximum angle line connects the center point of the vehicle and the corner point of the outermost edge of the bounding box of the front vehicle in the focus area; The second maximum angle line connects the center point of the vehicle and the corner point of the outermost edge of the bounding box of the rear vehicle in the focus area; Calculating the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot includes calculating the proportion of the crosswalk divided by the first maximum angle line through the crosswalk in the direction of the blind spot.

4. The method for identifying a vehicle driving blind spot according to claim 1, characterized in that: The crosswalk dimensions include the crosswalk length and the crosswalk width; The identifying of the blind spot area based on the ratio and the size of the crosswalk includes: Obtaining a preset width of the longitudinal far end of the blind spot area based on the width of the crosswalk; The blind spot area is identified based on the ratio, the length of the crosswalk, and a preset width of the longitudinal distal end of the blind spot area.

5. A control method based on vehicle driving blind spots, characterized in that: include: Identify a blind spot area of ​​a vehicle, wherein the blind spot area is obtained based on the vehicle driving blind spot identification method according to any one of claims 1 to 4; Determine whether to enable pre-braking decision based on the proportion of the blind spot area occupying the crosswalk; When the pre-braking decision is enabled, generating a trajectory including a series of trajectory points within a predetermined time period; Adjust the speed limit at each trajectory point based on the distance from the ego vehicle to the upcoming intersection; and Control the ego vehicle speed according to the adjusted speed limit at the trajectory point to achieve the desired deceleration.

6. The control method based on the vehicle driving blind spot according to claim 5, wherein the determining whether to enable the pre-braking decision based on the proportion of the blind spot area occupying the crosswalk comprises: When the ratio exceeds a preset ratio of the length of the crosswalk, a pre-braking decision is activated; as well as When the ratio is less than or equal to a preset ratio of the length of the crosswalk, the pre-braking decision is not enabled.

7. The control method based on vehicle driving blind spot according to claim 5, characterized in that: When the pre-braking decision is enabled, a trajectory is generated comprising a series of trajectory points within a predetermined time period, wherein each trajectory point represents a position of the vehicle at a specific moment within the predetermined time period.

8. The method according to claim 5, wherein adjusting the speed limit of each track point comprises: The speed reduction value X is calculated based on a preset calculation method, where P is the proportion of the blind spot area occupying the crosswalk, and V_ego is the current speed of the vehicle.

9. The control method based on vehicle driving blind spot according to claim 6, characterized in that: Also includes: Sending a voice reminder to the driver after a predetermined time delay after the pre-braking decision is enabled, the voice reminder is used to instruct the driver to pay attention to the road conditions ahead; Get the stop line; When the center of the vehicle is within a predetermined distance from the stop line of the intersection, the vehicle lights are activated if the pre-braking decision is enabled.

10. A vehicle driving blind spot recognition system, characterized in that: include: An acquisition unit, used to acquire at least a vehicle center point and a crosswalk size; A determination unit, at least used to determine the direction of the concerned area and the blind area; A generating unit, at least used to generate a maximum angle line passing through corner points of a bounding box of surrounding vehicles in a focus area based on a center point of the vehicle; A calculation unit, at least used to calculate the proportion of the crosswalk divided by the maximum angle line through the crosswalk in the direction of the blind spot; A recognition unit is used to identify a blind spot area based on the ratio and the size of the crosswalk.

11. A control system based on vehicle driving blind spots, characterized in that: include: A blind spot recognition unit, at least used to recognize a blind spot area of ​​a vehicle, wherein the blind spot area is obtained based on the vehicle driving blind spot recognition method according to any one of claims 1 to 4; A pre-braking decision unit, at least for determining whether to enable a pre-braking decision based on a proportion of the blind spot area occupying the pedestrian crossing; a trajectory generating unit, at least for generating a trajectory including a series of trajectory points within a predetermined time period when the pre-braking decision is enabled; a speed limit unit for adjusting a speed limit at each trajectory point based on at least a distance from the ego vehicle to an upcoming intersection; and The deceleration control unit is at least used to control the vehicle speed according to the adjusted speed limit of the trajectory point to achieve the expected deceleration.

12. An electronic device, characterized in that: include: at least one processor; And at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the identification method described in any one of claims 1-4 or the control method described in any one of claims 5-9.

13. A readable storage medium storing a computer program, characterized in that: The computer program is used by a processor to execute the steps of the identification method according to any one of claims 1 to 4 or the control method according to any one of claims 5 to 9.

Images