Vehicle control system, method and intelligent vehicle

Abstract

The application provides a vehicle control system, a method and an intelligent vehicle, relates to the technical field of intelligent vehicle safety, and aims to solve the technical problem that an intelligent vehicle cannot autonomously avoid in the prior art when encountering an emergent dangerous situation; after a dangerous source monitoring device detects current dangerous source data in a surrounding environment region, a dangerous source avoidance triggering instruction is sent, a path planning device can be triggered to send a dangerous source avoidance execution instruction after determining a current dangerous source avoidance path of the intelligent vehicle, so that a whole vehicle control device can be further triggered to control the intelligent vehicle to perform a dangerous source avoidance action according to the current dangerous source avoidance path, the dangerous source monitoring device, the path planning device and the whole vehicle control device are mutually coordinated, the whole link is penetrated from the detection of an emergent dangerous source to autonomous avoidance of the dangerous source, the bottleneck of the broken chain of the "perception-decision-execution" chain in the prior art is broken, and the safety of the intelligent vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicle safety, in particular to a vehicle control system, method and intelligent vehicle. BACKGROUND

[0002] In the intelligent vehicle technology, when the intelligent vehicle encounters an unexpected dangerous situation, it often triggers local video recording and simple alarm for danger prompt, lacks the ability to autonomously respond to the dangerous situation, and relies on manual intervention to perform risk avoidance actions, so that safety problems are prone to occur due to human operation delay or negligence. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a vehicle control system, method and intelligent vehicle to realize autonomous avoidance of the intelligent vehicle when encountering an unexpected dangerous situation and improve the safety of the intelligent vehicle.

[0004] In a first aspect, the present application provides a vehicle control system, comprising a danger source monitoring device, a path planning device and a whole vehicle control device;

[0005] The danger source monitoring device is configured to acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle, extract M frames of environment images with the same size and continuity from an environment video stream contained in the current environment data, detect danger source data in each frame of environment image by using a danger source detection model, determine current danger source data based on the danger source data in each frame of environment image when the overlap rate of danger source regions in N consecutive frames of environment images is greater than or equal to a first threshold value and / or the confidence fluctuation degree is less than or equal to a second threshold value, and send a danger source avoidance trigger instruction based on the current danger source data, wherein M is a positive integer greater than 1, and N is less than or equal to M.

[0006] The path planning device is configured to determine a current danger source avoidance path corresponding to the intelligent vehicle based on the current danger source data in the danger source avoidance trigger instruction when the danger source avoidance trigger instruction is received, and send a danger source avoidance execution instruction based on the current danger source avoidance path.

[0007] The whole vehicle control device is configured to control the intelligent vehicle to perform a danger source avoidance action according to the current danger source avoidance path in the danger source avoidance execution instruction when the danger source avoidance execution instruction is received.

[0008] Optionally, the vehicle control system provided by the present application further comprises a vehicle-mounted communication device.

[0009] The vehicle-mounted communication device is configured to forward the danger source avoidance trigger instruction to a user client when receiving the danger source avoidance trigger instruction, so that the user client performs a danger source avoidance prompt based on current danger source data in the danger source avoidance trigger instruction; and forward the danger source avoidance trigger instruction to a vehicle control device when receiving a confirmation avoidance instruction returned by the user client.

[0010] The vehicle control device is further configured to acquire current vehicle state data of the intelligent vehicle when receiving the danger source avoidance trigger instruction, and send the danger source avoidance trigger instruction to a path planning device when determining that the intelligent vehicle meets intelligent driving conditions based on the current vehicle state data.

[0011] Optionally, the vehicle-mounted communication device is further configured to send a first wake-up instruction to the vehicle control device when receiving a sentinel mode start instruction sent by the user client, wherein the sentinel mode start instruction is initiated by the user client when the intelligent vehicle is in a stationary state.

[0012] The vehicle control device is further configured to wake up an in-vehicle network and send a second wake-up instruction to the danger source monitoring device when receiving the first wake-up instruction.

[0013] The danger source monitoring device is further configured to acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle when receiving the second wake-up instruction.

[0014] Optionally, the path planning device is configured to determine a current danger level based on the current danger source data, and determine a current danger source avoidance action based on the current danger level; and determine a current danger source avoidance path based on the current danger source avoidance action.

[0015] Optionally, the path planning device is configured to determine a current danger level corresponding to a trigger condition reached by the current danger source data based on a corresponding relationship between danger levels and trigger conditions, and determine a current danger source avoidance action corresponding to the current danger level based on a corresponding relationship between danger levels and danger source avoidance actions.

[0016] Optionally, the vehicle control device is further configured to determine a detected abnormal situation as a to-be-handled abnormal situation when detecting an abnormal situation in a vehicle control process according to an abnormality detection mode corresponding to each abnormal situation, determine a target handling strategy corresponding to the to-be-handled abnormal situation based on a corresponding relationship between abnormal situations and handling strategies, and handle the to-be-handled abnormal situation based on the target handling strategy.

[0017] In a second aspect, the present application provides a vehicle control method applied to a danger source monitoring device in the vehicle control system.

[0018] acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle;

[0019] extract M frames of environment images with same size and continuity from an environment video stream contained in the current environment data; detect hazard source data in each frame of environment image by using a hazard source detection model; when an overlap rate of hazard source regions in continuous N frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value, determine current hazard source data based on the hazard source data in each frame of environment image; wherein M is a positive integer greater than 1, and N is less than or equal to M;

[0020] based on the current hazard source data, send a hazard source avoidance triggering instruction to trigger the path planning device to determine a current hazard source avoidance strategy corresponding to the intelligent vehicle based on the current hazard source data in the hazard source avoidance triggering instruction, and then trigger the vehicle control device to control the intelligent vehicle to perform a hazard source avoidance action based on the current hazard source avoidance strategy in the hazard source avoidance execution instruction.

[0021] In a third aspect, the present application provides another vehicle control method applied to the path planning device in the vehicle control system, comprising:

[0022] receive a hazard source avoidance triggering instruction sent by the hazard source monitoring device; wherein the hazard source avoidance triggering instruction is that the hazard source monitoring device extracts M frames of environment images with same size and continuity from an environment video stream contained in current environment data in a surrounding environment region corresponding to the intelligent vehicle; detects hazard source data in each frame of environment image by using a hazard source detection model; when an overlap rate of hazard source regions in continuous N frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value, determines current hazard source data based on the hazard source data in each frame of environment image; wherein M is a positive integer greater than 1, and N is less than or equal to M; and sends the hazard source avoidance triggering instruction based on the current hazard source data;

[0023] determine a current hazard source avoidance strategy corresponding to the intelligent vehicle based on the current hazard source data in the hazard source avoidance triggering instruction;

[0024] based on the current hazard source avoidance strategy, send a hazard source avoidance execution instruction to trigger the vehicle control device to control the intelligent vehicle to perform a hazard source avoidance action based on the current hazard source avoidance strategy in the hazard source avoidance instruction.

[0025] In a fourth aspect, the present application provides an intelligent vehicle comprising the vehicle control system.

[0026] The present application has the following advantages:

[0027] The vehicle control system, method and intelligent vehicle provided by the application can detect the current danger source data in the surrounding environment area through the danger source monitoring device, send a danger source avoidance triggering instruction, determine the current danger source avoidance path of the intelligent vehicle through the path planning device after the danger source avoidance triggering instruction is sent, send a danger source avoidance execution instruction, control the intelligent vehicle to perform the danger source avoidance action according to the current danger source avoidance path through the vehicle control device after the danger source avoidance execution instruction is sent, and realize the mutual cooperation of the danger source monitoring device, the path planning device and the vehicle control device, complete the full-link connection from the sudden danger source detection to the danger source autonomous avoidance, break through the bottleneck of the broken chain of the "perception-decision-execution" in the prior art, and improve the safety of the intelligent vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0029] Figure 1 The composition framework schematic diagram of the vehicle control system provided by the embodiment of the application is shown;

[0030] Figure 2 The interaction flow schematic diagram of the vehicle control method provided by the embodiment of the application is shown;

[0031] Figure 3 The overview flow schematic diagram of the danger source detection model training method provided by the embodiment of the application is shown;

[0032] Figure 4 The functional structure schematic diagram of a vehicle control device provided by the embodiment of the application is shown;

[0033] Figure 5 The functional structure schematic diagram of another vehicle control device provided by the embodiment of the application is shown;

[0034] Figure 6 The hardware structure schematic diagram of an electronic device provided by the embodiment of the application is shown. DETAILED DESCRIPTION

[0035] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part but not all of the embodiments of the present application. The components of the embodiments of the present application generally described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0036] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part but not all of the embodiments of the present application. The components of the embodiments of the present application generally described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0037] The danger source monitoring device is a device for monitoring whether there is a danger in the surrounding environment of the intelligent vehicle. In the present application, the danger source monitoring device can be, but is not limited to, a sentinel mode controller.

[0038] The path planning device is a device for determining the driving path of the intelligent vehicle. In the present application, the path planning device can be, but is not limited to, intelligent driving control. The danger source monitoring device and the path planning device can be two independent controllers, or the danger source monitoring device and the path planning device can be integrated into a single domain controller.

[0039] The vehicle control device is a device for controlling the intelligent vehicle. In the present application, the vehicle control device can be, but is not limited to, a vehicle controller, an electronic control unit (ECU), a drive system, etc.

[0040] It should be noted that "and / or" mentioned in the present application describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. The character " / " generally represents an "or" relationship between the front and rear associated objects.

[0041] The embodiments of the present application provide a vehicle control system, as shown in Figure 1 The vehicle control system provided by the embodiments of the present application includes a danger source monitoring device 110, a path planning device 120, and a vehicle control device 130.

[0042] The danger source monitoring device 110 is configured to acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle, extract M frames of environment images with the same size and in succession from an environment video stream contained in the current environment data, detect danger source data in each frame of environment image by using a danger source detection model, and determine current danger source data based on the danger source data in each frame of environment image when an overlap rate of danger source regions in N consecutive frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value, wherein M is a positive integer greater than 1, and N is less than or equal to M. The danger source monitoring device 110 is further configured to send a danger source avoidance triggering instruction based on the current danger source data, wherein the current danger source data at least includes any one of a fire, a flood, smoke, and an abnormal vehicle. The danger source monitoring device 110 includes any one of a temperature sensor, a smoke sensor, and a surround-view camera.

[0043] The path planning device 120 is configured to, when the danger source avoidance triggering instruction is received, determine a current danger source avoidance path corresponding to the intelligent vehicle based on the current danger source data in the danger source avoidance triggering instruction, and send a danger source avoidance execution instruction based on the current danger source avoidance path.

[0044] The whole vehicle control device 130 is configured to, when the danger source avoidance execution instruction is received, control the intelligent vehicle to perform a danger source avoidance action according to the current danger source avoidance path in the danger source avoidance execution instruction.

[0045] In a specific implementation, the danger source monitoring device 110 can call an environment detection sensor to acquire the current environment data in the surrounding environment region corresponding to the intelligent vehicle. For example, the environment detection sensor includes but is not limited to a temperature sensor, a smoke sensor, a surround-view camera, and the like. Correspondingly, the danger source monitoring device 110 can call the temperature sensor to collect temperature data, call the smoke sensor to collect smoke concentration data, and call the surround-view camera sensor to collect environment video stream data. Further, the danger source monitoring device 110 can input the current environment data into the danger source detection model to obtain pedestrian, obstacle, and other conventional danger source data in the surrounding environment region corresponding to the intelligent vehicle as the current danger source data, so as to realize detection and autonomous avoidance of different conventional danger sources. In addition, after the danger source monitoring device 110 inputs the current environment data into the danger source detection model, it can also obtain a fire, a flood, smoke, an abnormal vehicle, and the like as the current danger source data, so as to realize detection and autonomous avoidance of various types of sudden danger sources while realizing detection and autonomous avoidance of various types of conventional danger sources, thereby improving the performance of the vehicle control system and the safety of the intelligent vehicle.

[0046] In specific implementation, the hazard source monitoring device is configured to extract M frames of environment images with the same size and continuity from an environment video stream contained in current environment data through an input layer of the hazard source detection model; detect hazard source data in each frame of environment image through a detection layer of the hazard source detection model; and determine current hazard source data based on the hazard source data in each frame of environment image when an overlap rate of hazard source regions in N consecutive frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value through an output layer of the hazard source detection model; wherein M is a positive integer greater than 1, and N is less than or equal to M.

[0047] The input layer of the hazard source detection model continuously receives the environment video stream, and extracts M frames of environment images with the same size and continuity at a fixed frequency, to ensure time continuity and spatial consistency. The detection layer of the hazard source detection model detects the hazard source category (fire, flood, smoke, abnormal vehicle, etc.), the position coordinates of the hazard source bounding box (i.e. the hazard source region), and the confidence (in the interval of 0-1) representing the confidence degree of the hazard source in the hazard source bounding box in each frame of environment image, to obtain the hazard source data in each frame of environment image. The output layer of the hazard source detection model calculates the intersection over union (IoU) of the hazard source regions in N consecutive frames of environment images as the overlap rate. When the overlap rate is greater than or equal to a first threshold value (for example, 70%), it is determined that the same hazard source continuously exists in the N consecutive frames of environment images, and the spatial consistency verification is confirmed to pass. The difference between the maximum value and the minimum value of the confidence of the hazard source in the hazard source region in the N consecutive frames of environment images is calculated as the confidence fluctuation degree. When the confidence fluctuation degree is less than or equal to a second threshold value (for example, 0.15), it is confirmed that the detection result reliability verification passes. The hazard source data that passes the spatial consistency verification and / or the detection result reliability verification is determined as the current hazard source data.

[0048] In the embodiment of the present application, the dangerous source detection model can be a deep learning model such as YOLOv8, Faster R-CNN, Transformer (such as DETR) or lightweight MobileNet, and the dangerous source detection model is loaded into the dangerous source monitoring device after being trained by the cloud server for dangerous source detection. The dangerous source detection model includes an input layer, a detection layer and an output layer. In the embodiment of the present application, an adaptive scaling layer (Adaptive Scaling Layer) is introduced in the input layer to uniformly scale environment images of different resolutions to a reference size (such as 640x640), and edge padding is performed on environment images with large aspect ratio differences to preserve the original dangerous source morphological features. In the detection layer, FPN (Feature Pyramid Network) is integrated to enhance the sensitivity of small-size dangerous source (such as 10x10 pixels) detection through multi-scale feature fusion, so that the dangerous source detection model can capture the details of both close-range large-size dangerous sources and long-range small-size dangerous sources, and improve the accuracy of dangerous source detection. In the output layer, spatial consistency verification and / or detection result reliability verification are performed to screen the dangerous sources detected by the detection layer, and the dangerous source data that passes the spatial consistency verification and / or detection result reliability verification is determined as the current dangerous source data, thereby further improving the accuracy of dangerous source detection. In addition, in the detection layer, on the one hand, the dangerous sources in M frames of environment images can be dynamically tracked, and the motion trajectory of the dangerous source can be predicted through an LSTM network or a Kalman filter to exclude instantaneous false detection of dangerous sources (such as false detection of dangerous sources caused by reflection, moving light source interference, etc.). On the other hand, a sliding window algorithm can be used to calculate the dynamic IOU change rate of the dangerous source bounding box (i.e. the specific position and range of the dangerous source in the image is delimited by a rectangular box), and when the dynamic IOU change rate is lower than a threshold value, the dangerous source bounding box is filtered as an invalid bounding box. In this way, through dynamic tracking of the dangerous source and / or IOU change rate filtering, invalid dangerous sources can be filtered out, thereby improving the accuracy of dangerous source detection.

[0049] In a specific implementation, the vehicle control system provided by the embodiment of the present application further includes a vehicle-mounted communication device 140.

[0050] The vehicle-mounted communication device is configured to, when receiving the dangerous source avoidance triggering instruction, forward the dangerous source avoidance triggering instruction to the user client to prompt the user client to avoid the dangerous source based on the current dangerous source data in the dangerous source avoidance triggering instruction; and when receiving the confirmation avoidance instruction returned by the user client, forward the dangerous source avoidance triggering instruction to the vehicle control device.

[0051] The whole vehicle control device is further used to receive the danger source avoidance trigger instruction, acquire current vehicle state data of the intelligent vehicle, and send the danger source avoidance trigger instruction to the path planning device when it is determined that the intelligent vehicle meets the intelligent driving condition based on the current vehicle state data.

[0052] Further, the vehicle-mounted communication device is further used to upload the current environment data and the danger source data in the surrounding environment region corresponding to the intelligent vehicle acquired by the danger source monitoring device to the cloud.

[0053] The vehicle-mounted communication device and the whole vehicle control device provided by the embodiment of the application have the following advantages: the danger source avoidance trigger instruction is received by the vehicle-mounted communication device, and the danger source avoidance trigger instruction is forwarded to the user client for processing, so that the user can be prompted to avoid the danger source based on the received data; and when the confirmation avoidance instruction returned by the user client is received, the danger source avoidance trigger instruction is forwarded to the whole vehicle control device; the whole vehicle control device acquires current vehicle state data of the intelligent vehicle, and when it is determined that the vehicle meets the automatic driving condition, the danger source avoidance trigger instruction received is forwarded to the path planning device, so that the path planning device plans an optimal avoidance path according to the received danger source avoidance trigger instruction and the vehicle state data, thereby realizing active avoidance of the intelligent vehicle when the danger source is encountered, and improving the driving safety and convenience.

[0054] In the specific implementation, the vehicle-mounted communication device is further used to send a first wake-up instruction to the whole vehicle control device when the sentinel mode opening instruction sent by the user client is received; the sentinel mode opening instruction is initiated by the user client when the intelligent vehicle is in a stationary state.

[0055] The whole vehicle control device is further used to wake up the in-vehicle network and send a second wake-up instruction to the danger source monitoring device when the first wake-up instruction is received.

[0056] The danger source monitoring device is further used to acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle when the second wake-up instruction is received.

[0057] In the vehicle-mounted communication device provided in the embodiments of the present application, after the vehicle-mounted communication device receives the sentinel mode starting instruction initiated by the user through the client when the intelligent vehicle is stationary, the first wake-up instruction (i.e., starting the sentinel mode) is sent to the vehicle control device, so as to wake up the network system inside the vehicle; after the vehicle control device receives the first wake-up instruction, the danger source monitoring device in the intelligent vehicle is woken up and activated; after the danger source monitoring device receives the second wake-up instruction, the current environmental data in the surrounding environment area of the intelligent vehicle, such as temperature, humidity, light intensity, etc., can be obtained, which provides real-time information for the safety protection of the vehicle and prevents potential safety hazards. By starting the sentinel mode by the user, the vehicle-mounted communication device delivers the instruction to the vehicle control device, and the vehicle control device wakes up the danger source monitoring device to perform environmental monitoring, so as to realize the safety monitoring function of the intelligent vehicle in the stationary state.

[0058] In specific implementation, the path planning device is configured to determine a current danger level based on the current danger source data, and determine a current danger source avoidance action based on the current danger level; and determine a current danger source avoidance path based on the current danger source avoidance action.

[0059] In the embodiments of the present application, the path planning device can determine the danger level corresponding to the trigger condition reached by the current danger source data as the current danger level based on the corresponding relationship between the danger level and the trigger condition; and determine the danger source avoidance action corresponding to the current danger level as the current danger source avoidance action based on the corresponding relationship between the danger level and the danger source avoidance action.

[0060] Specifically, for example, if the current danger source data is that the distance between the intelligent vehicle and the flame is less than or equal to 1 m, the danger level is Level 1, if the current danger source data is that the smoke concentration is greater than 20%, the danger level is Level 2, and if the current danger source data is that the abnormal vehicle approaches the intelligent vehicle, the danger level is Level 3.

[0061] When the danger level is Level 1, the danger avoidance action is forced emergency reversing (which can be moving at a speed of 8 km / h at most); when the danger level is Level 2, the danger avoidance action is low-speed driving away (which can be moving at a speed of 5 km / h at most); and when the danger level is Level 3, the danger avoidance action is side translation (i.e., the intelligent vehicle performs lateral avoidance, and the avoidance distance is 0.5 m).

[0062] Further, when the danger level is Level 2 or Level 3, the vehicle-mounted communication device forwards the danger source avoidance trigger instruction to the user client for processing, so that the user can be prompted to avoid the danger source based on the received data, and when the user client returns a confirmation avoidance instruction, the danger source avoidance trigger instruction is forwarded to the vehicle control device, and the vehicle control device controls the intelligent vehicle to perform danger avoidance action.

[0063] Further, when the vehicle is in the sentry mode in the parking lot, the path planning device determines a current danger source avoidance path based on the preset planning algorithm and the current danger source avoidance action, specifically including the following steps:

[0064] a. Safety area search: search for each drivable area; wherein the drivable area includes an open position area, an exit position, an open corner area, etc.

[0065] The search method of the open position area includes: discretizing the parking lot map into a grid map or a topological map, each grid is marked as "passable" or "non-passable"; using A* algorithm or SPFA algorithm to calculate the shortest path from the current position of the vehicle to each passable grid, and screening out the areas with reachable path and no obstacles as candidate open areas; after removing the isolated candidate open areas that are not connected to the main channel, the candidate open areas with an area greater than the square of the minimum turning radius of the vehicle are selected as the open position area.

[0066] The search method of the exit position includes: obtaining a candidate exit set containing all exits in the parking lot map; based on the path length, the number of turns, and the congestion probability (such as historical data or real-time sensor feedback) of the vehicle from the current position to each candidate exit, using Dijkstra or A* algorithm to evaluate the path cost, and obtaining the path cost of the vehicle from the current position to each candidate exit; the candidate exit with the minimum path cost in each candidate exit is determined as the exit position; the candidate exit with the minimum path cost is the exit with the shortest path, the least turns, and the least obstacles.

[0067] The search method of the open corner area includes: identifying all corner areas (such as the four vertices of a rectangular area, an L-shaped wall surrounding area) in the parking lot map; performing fan scanning on each corner area to detect whether there are obstacles or obstructions in the fan area; after removing the corner areas with obstacles and obstructions from each corner area, using geometric dilation method to expand the vehicle contour by a certain distance (for example, 0.5-1 meters) as a safety accommodation area, and determining the corner area with an area not less than the safety accommodation area as a corner area that can accommodate vehicle parking, i.e., an open corner area.

[0068] In the embodiments of the present application, each drivable area can also be searched in a sector area or a circular area with a set distance (for example, 50 m) as a radius. At this time, the drivable grids, candidate exits, and corner areas in the sector area or the circular area are first screened according to the parking lot map, and then the above-mentioned manner is used to search the open position area, the exit position, and the open corner area from the drivable grids, candidate exits, and corner areas in the sector area or the circular area, and details are not repeated here.

[0069] The target position is determined according to the priority order of each drivable area. In the embodiments of the present application, the drivable area with the highest priority can be determined as the target position. For example, the priority order from high to low is exit position-open position area-open corner area. When the open position area, the exit position, and the open corner area are searched, the exit position can be determined as the target position. When the open position area and the open corner area are searched, the open position area can be determined as the target position. The target position is determined through the priority order to ensure that the intelligent vehicle is preferentially parked in a position easy to drive away, and the influence on other vehicles and pedestrians is reduced.

[0070] b, path feasibility verification: the minimum turning radius is greater than or equal to 2.2 m, and obstacles with a height less than 1.5 m are avoided.

[0071] The feasibility of the driving path of the intelligent vehicle is verified to ensure that the path has enough space when turning and avoids obstacles such as fire hydrants or low-hanging objects on the driving path.

[0072] c, trajectory generation: B-spline curve smoothing processing, and the speed curve is limited to 0 to 5 km / h.

[0073] In the embodiments of the present application, a smooth and continuous driving path can be obtained based on the B-spline curve, which helps to improve the comfort and safety of driving, and the vehicle speed is in a moderate range, avoiding instability and safety hazards caused by fast driving.

[0074] Further, when the whole vehicle control device controls the intelligent vehicle to perform a danger source avoidance action, the environment detection sensor acquires current environment data in the surrounding environment area corresponding to the intelligent vehicle every 200 milliseconds to ensure that there is no sudden danger on the driving path, such as pedestrians suddenly entering the driving path. When the path planning fails, a local risk avoidance strategy is triggered, that is, the danger warning light of the intelligent vehicle is started to remind surrounding vehicles and pedestrians to avoid or emit a short and continuous beep to remind surrounding factors that may cause safety hazards. Through the above-mentioned manner, it is ensured that the vehicle can take risk avoidance measures in time when encountering an emergency, and the driving safety is ensured.

[0075] Further, the determination of the current danger source avoidance action can be determined by a data table (i.e., the corresponding relationship is pre-stored in the data table) or by a deep learning model (i.e., the corresponding relationship is learned by the deep learning model in the model training process).

[0076] In the path planning device provided by the embodiments of the present application, the current danger level is determined based on the current danger source data, and the current danger source avoidance action is determined based on the current danger level, thereby constructing a three-level danger avoidance strategy system. When the danger level is Level 1, forced avoidance is triggered, thereby breaking through the traditional artificial confirmation link. When the danger level is Level 2 or Level 3, a user confirmation mechanism is provided. The three-level danger avoidance strategy system ensures that automatic emergency avoidance can be performed when the safety level is high, and the user confirmation mechanism is provided when the risk is controllable but needs to be confirmed by the user, thereby improving the safety of the intelligent vehicle and the user experience.

[0077] In specific implementation, the vehicle control device is further configured to, when an abnormal situation occurs in the vehicle control process according to the abnormality detection mode corresponding to each abnormal situation, determine the detected abnormal situation as a to-be-handled abnormal situation, determine a handling strategy corresponding to the to-be-handled abnormal situation as a target handling strategy based on the corresponding relationship between the abnormal situation and the handling strategy, and handle the to-be-handled abnormal situation based on the target handling strategy.

[0078] Specifically, for example, when the vehicle-mounted communication device times out (e.g., the TBOX heartbeat packet timeout is greater than 5 seconds), the local decision needs to be switched (i.e., the forced emergency reverse avoidance action when the danger level is Level 1 is performed); when there are continuous A frames of invalid environment images in the environment video stream collected by the environment detection sensor (A is greater than or equal to 10), the redundant sensor needs to be activated; and when the response delay of the control device in the vehicle control system is greater than 500 milliseconds, the vehicle control device needs to be triggered to perform safe parking.

[0079] The vehicle control device provided by the embodiments of the present application can also handle abnormal situations such as switching the local decision when the network is interrupted, activating the redundant camera when the sensor fails, and starting safe parking when the control timeout is 500 ms, thereby improving the reliability of the vehicle control system.

[0080] Based on the above embodiments, the embodiments of the present application provide an intelligent vehicle including the vehicle control system described above.

[0081] The vehicle control system and the intelligent vehicle provided by the embodiment of the present application can detect the current danger source data in the surrounding environment region through the danger source monitoring device, send a danger source avoidance triggering instruction, trigger the path planning device to send a danger source avoidance execution instruction after determining the current danger source avoidance path of the intelligent vehicle, and further trigger the vehicle control device to control the intelligent vehicle to perform the danger source avoidance action according to the current danger source avoidance path, so as to realize the mutual cooperation of the danger source monitoring device, the path planning device and the vehicle control device, complete the full-link connection from the sudden danger source detection to the danger source autonomous avoidance, break through the bottleneck of the broken "perception-decision-execution" chain in the prior art, and improve the safety of the intelligent vehicle.

[0082] Based on the same inventive concept, the embodiment of the present application also provides a vehicle control method, as shown in Figure 2 The interaction process of the vehicle control method provided by the embodiment of the present application is as follows:

[0083] Step 201: When the vehicle-mounted communication device receives the sentinel mode opening instruction sent by the user client, the vehicle-mounted communication device sends a first wake-up instruction to the vehicle control device; wherein the sentinel mode opening instruction is initiated by the user client when the intelligent vehicle is in a stationary state.

[0084] Step 202: When the vehicle control device receives the first wake-up instruction, the vehicle control device wakes up the in-vehicle network and sends a second wake-up instruction to the danger source monitoring device.

[0085] Step 203: When the danger source monitoring device receives the second wake-up instruction, the danger source monitoring device acquires the current environment data in the surrounding environment region corresponding to the intelligent vehicle; detects the current danger source data in the surrounding environment region by using a danger source detection model; and sends a danger source avoidance triggering instruction to the vehicle-mounted communication device based on the current danger source data.

[0086] In the embodiment of the present application, in one embodiment, the danger source monitoring device extracts M frames of environment images with the same size and in succession from the environment video stream contained in the current environment data; detects the danger source data in each frame of environment image by using a danger source detection model; and when the overlap rate of the danger source regions in the continuous N frames of environment images is greater than or equal to a first threshold value and / or the confidence fluctuation degree is less than or equal to a second threshold value, determines the current danger source data based on the danger source data in each frame of environment image; wherein M is a positive integer greater than 1, and N is less than or equal to M.

[0087] Step 204: When the vehicle-mounted communication device receives the danger source avoidance trigger instruction, the vehicle-mounted communication device forwards the danger source avoidance trigger instruction to the user client, so that the user client performs a danger source avoidance prompt based on the current danger source data in the danger source avoidance trigger instruction; when the user client returns a confirmation avoidance instruction, the vehicle-mounted communication device forwards the danger source avoidance trigger instruction to the vehicle control device.

[0088] Step 205: When the vehicle control device receives the danger source avoidance trigger instruction, the vehicle control device forwards the danger source avoidance trigger instruction to the path planning device; when the path planning device receives the danger source avoidance trigger instruction, the path planning device determines a current danger source avoidance path corresponding to the intelligent vehicle based on the current danger source data in the danger source avoidance trigger instruction; and the path planning device sends a danger source avoidance execution instruction to the vehicle control device based on the current danger source avoidance path.

[0089] In an embodiment, the path planning device determines a current danger level based on the current danger source data, and determines a current danger source avoidance action based on the current danger level; and the path planning device determines a current danger source avoidance path based on the current danger source avoidance action.

[0090] In another embodiment, the path planning device determines a current danger level corresponding to a trigger condition reached by the current danger source data based on a correspondence between danger levels and trigger conditions; and the path planning device determines a current danger source avoidance action corresponding to the current danger level based on a correspondence between danger levels and danger source avoidance actions.

[0091] Step 206: When the vehicle control device receives the danger source avoidance execution instruction, the vehicle control device controls the intelligent vehicle to perform a danger source avoidance action according to the current danger source avoidance path in the danger source avoidance execution instruction.

[0092] In an embodiment, when the vehicle control device detects an abnormal situation in a vehicle control process according to an abnormality detection manner corresponding to various abnormal situations, the vehicle control device determines the detected abnormal situation as a to-be-handled abnormal situation; the vehicle control device determines a target handling strategy corresponding to the to-be-handled abnormal situation based on a correspondence between abnormal situations and handling strategies; and the vehicle control device handles the to-be-handled abnormal situation based on the target handling strategy.

[0093] Next, the training method of the danger source detection model mentioned in the embodiments of the present application is described in detail, and the training method of the danger source detection model is shown in FIG. 2. Figure 3 As shown in FIG. 2, the training method of the danger source detection model provided in the embodiments of the present application has the following general process:

[0094] Step 301: Obtain a training sample data set; wherein the training sample data set comprises a plurality of training sample data; each training sample data comprises an original video frame image and flame label data, smoke label data, flood label data and abnormal vehicle label data corresponding to the original video frame image.

[0095] In the embodiments of the present application, when obtaining the training sample data set, the following methods can be used, but are not limited to:

[0096] First, a plurality of original video frame images are obtained; wherein each original video frame image contains at least one of the following dangerous sources: fire, smoke, flood and abnormal vehicle.

[0097] Then, using Labelme software, the pixel position information of each original video frame image is labeled to generate a standard mask image. Taking a standard mask image as an example, the image size of which is consistent with that of the original video frame image, each pixel point in the position area of the target dangerous source in the original video frame image is marked as 1, and each pixel point in the position area of the remaining dangerous source is marked as 0, thereby generating a binary mask image of the target dangerous source, and adding a target dangerous source label to the binary mask image, for example, assuming that the target dangerous source is fire, then adding a GT-H label to the binary mask image, so as to identify the dangerous source. When a plurality of different dangerous sources are contained in one original video frame image, the original video frame image and the standard mask images of the plurality of dangerous sources and the dangerous source labels constitute one training sample data.

[0098] Finally, based on the plurality of original video frame images and the plurality of standard mask images of the original video frame images, a plurality of training sample data are obtained to obtain the training sample data set.

[0099] Step 302: Based on the training sample data set, perform an iterative training operation on the target detection model; wherein the iterative training operation comprises: selecting a target training sample data from the training sample data set; inputting the original video frame image in the target training sample data into the target detection model, so that the target detection model extracts features from the original video frame image to obtain fire hazard source data, flood hazard source data and abnormal hazard source data; updating each weight and each threshold of the target detection model based on the prediction error between the fire hazard source data and the flame label data, the prediction error between the smoke hazard source data and the smoke label data in the target training sample data, the prediction error between the abnormal hazard source data and the abnormal vehicle label data in the target training sample data.

[0100] Step 303: Determine whether the iterative training termination condition is met; if yes, execute step 304; if no, return to step 302.

[0101] Step 304: based on the weights and thresholds of the target detection model updated when the last iteration training operation is performed.

[0102] Step 305: obtaining a verification data set and a test data set; wherein the verification data set includes a plurality of verification sample data; each verification sample data includes an original video frame image and fire hazard source, flood hazard source and abnormal vehicle verification data corresponding to the original video frame image; the test data set includes a plurality of test sample data; each test sample data includes an original video frame image and fire hazard source, flood hazard source and abnormal vehicle test data corresponding to the original video frame image.

[0103] Step 306: selecting a target verification sample data from the verification data set, and inputting the original video frame image in the target verification sample data into the target detection model, so that the target detection model extracts features of the original video frame image to obtain fire hazard source data, flood hazard source data and abnormal hazard source data, and obtains a verification loss curve based on the prediction error between the fire hazard source data and the fire hazard source verification data in the verification sample data, the prediction error between the flood hazard source data and the flood verification data in the verification sample data, and the prediction error between the abnormal hazard source data and the abnormal vehicle verification data in the verification sample data.

[0104] Step 307: selecting a target test sample data from the test data set, and inputting the original video frame image in the target test sample data into the target detection model, so that the target detection model extracts features of the original video frame image to obtain fire hazard source data, flood hazard source data and abnormal hazard source data, and obtains a test loss curve based on the prediction error between the fire hazard source data and the fire hazard source verification data in the test sample data, the prediction error between the flood hazard source data and the flood verification data in the test sample data, and the prediction error between the abnormal hazard source data and the abnormal vehicle verification data in the test sample data.

[0105] Step 308: optimizing the target detection model based on the verification loss curve and the test loss curve.

[0106] In the above-mentioned hazard source detection model training method provided by the embodiments of the present application, the YOLOv8 model is combined with multi-frame verification and confidence degree fluctuation degree to filter false detection, so that the fire detection false alarm rate is more accurate, and by updating the detection state in real time, the dangerous state is updated every 200 ms, and the static vehicle actively responds to the dynamic threat.

[0107] The functions and structures of the hazard source monitoring device and the path planning device mentioned in the embodiments of the present application will be briefly described below.

[0108] Referring to Figure 4 As shown in the figure, the dangerous source monitoring device provided by the embodiment of the application at least comprises:

[0109] The data acquisition unit 401 is configured to acquire current environment data in a surrounding environment region corresponding to the intelligent vehicle.

[0110] The dangerous source detection unit 402 is configured to extract M frames of environment images with the same size and in succession from an environment video stream contained in the current environment data based on the current environment data; detect dangerous source data in each frame of environment image by using a dangerous source detection model; when an overlap rate of dangerous source regions in N consecutive frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value, determine current dangerous source data based on the dangerous source data in each frame of environment image; wherein M is a positive integer greater than 1, and N is less than or equal to M; and send a dangerous source avoidance triggering instruction based on the current dangerous source data; wherein the current dangerous source data at least includes any one of fire, flood, smoke and abnormal vehicle;

[0111] The avoidance triggering unit 403 is configured to send a dangerous source avoidance triggering instruction based on the current dangerous source data, so as to trigger the path planning device to determine a current dangerous source avoidance strategy of the intelligent vehicle based on the current dangerous source data in the dangerous source avoidance triggering instruction, and then trigger the vehicle control device to control the intelligent vehicle to perform a dangerous source avoidance action based on the current dangerous source avoidance strategy in the dangerous source avoidance execution instruction.

[0112] Referring to Figure 5 As shown in the figure, the path planning device provided by the embodiment of the application at least comprises:

[0113] The instruction receiving unit 501 is configured to receive a dangerous source avoidance triggering instruction sent by the dangerous source monitoring device; wherein the dangerous source avoidance triggering instruction is that the dangerous source monitoring device extracts M frames of environment images with the same size and in succession from an environment video stream contained in current environment data in a surrounding environment region corresponding to the intelligent vehicle based on the current environment data; detects dangerous source data in each frame of environment image by using a dangerous source detection model; when an overlap rate of dangerous source regions in N consecutive frames of environment images is greater than or equal to a first threshold value and / or a confidence fluctuation degree is less than or equal to a second threshold value, determines current dangerous source data based on the dangerous source data in each frame of environment image; wherein M is a positive integer greater than 1, and N is less than or equal to M; and sends a dangerous source avoidance triggering instruction based on the current dangerous source data; wherein the current dangerous source data at least includes any one of fire, flood, smoke and abnormal vehicle;

[0114] The strategy determination unit 502 is configured to determine a current danger source avoidance strategy of the intelligent vehicle based on the current danger source data in the danger source avoidance trigger instruction.

[0115] The execution trigger unit 503 is configured to send a danger source avoidance execution instruction based on the current danger source avoidance strategy, so as to trigger the whole vehicle control device to control the intelligent vehicle to perform a danger source avoidance action based on the current danger source avoidance strategy in the danger source avoidance instruction.

[0116] Based on the above embodiments, the electronic device provided by the embodiments of the present application can be a danger source monitoring device, a path planning device or a whole vehicle control device. Referring to Figure 6 As shown in the figure, the electronic device 600 provided by the embodiments of the present application at least includes a controller 601, a memory 602 and a computer program stored in the memory 602 and executable on the controller 601, and the controller 601 executes the computer program to realize the vehicle control method performed by the above-mentioned danger source monitoring device, path planning device or whole vehicle control device provided by the embodiments of the present application.

[0117] The electronic device 600 provided by the embodiments of the present application can further include a bus 603 connected with different components (including the controller 601 and the memory 602). Wherein, the bus 603 represents one or more of several bus structures, including a memory bus, a peripheral bus, a local bus, etc.

[0118] The memory 602 can include a readable storage medium in the form of a volatile memory, such as a random access memory (RAM) 6021 and / or a cache memory 6022, and can further include a read-only memory (ROM) 6023. The memory 602 can also include a program tool 6025 having a set of (at least one) program modules 6024, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof can include the implementation of a network environment.

[0119] The controller 601 can be one processing element or a collective term for multiple processing elements. For example, the controller 601 can be a central processing unit (CPU), or one or more integrated circuits configured to implement the vehicle control method performed by the above-mentioned hazard source monitoring device, path planning device, or whole-vehicle control device provided by the embodiments of the present application. Specifically, the controller 601 can be a general-purpose controller, including but not limited to a CPU, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, and the like.

[0120] The electronic device 600 can communicate with one or more external devices 604 (such as a keyboard, a mouse, or a voice input device) and can also communicate with one or more devices that enable a user to interact with the electronic device 600 (such as a display device, a speaker, a printer, or a telephone). Additionally, the electronic device 600 can communicate with one or more devices that enable the electronic device 600 to perform a function (such as a phone, a computer, or another electronic device). In one embodiment, the electronic device 600 can include the functionality of a mobile device, a personal digital assistant (PDA), a smart phone, a tablet, a laptop computer, a desktop computer, or other electronic devices. Figure 6 As shown, the network adapter 606 communicates with the other components of the electronic device 600 via the bus 603. It should be understood that although the network adapter 606 is shown as a separate component of the electronic device 600, the network adapter 606 can be integrated with other components of the electronic device 600, such as the controller 601. Figure 6 It should be understood that, although not shown in the

[0121] It should be understood that, although not shown in the Figure 6 The electronic device 600 shown in the figure is merely an example, and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0122] The computer readable storage medium provided by the embodiment of the present application is described as follows. The computer readable storage medium provided by the embodiment of the present application stores computer instructions, and the computer instructions are executed by the controller to implement the vehicle control method executed by the above-mentioned dangerous source monitoring device, path planning device or whole vehicle control device provided by the embodiment of the present application. In a specific implementation, the computer instructions can be built-in or installed in the controller, so that the controller can implement the vehicle control method executed by the above-mentioned dangerous source monitoring device, path planning device or whole vehicle control device provided by the embodiment of the present application by executing the built-in or installed computer instructions.

[0123] In addition, the vehicle control method executed by the above-mentioned dangerous source monitoring device, path planning device or whole vehicle control device provided by the embodiment of the present application can also be implemented as a computer program product, which includes program codes, and the program codes are executed on the controller to implement the vehicle control method executed by the above-mentioned dangerous source monitoring device, path planning device or whole vehicle control device provided by the embodiment of the present application.

[0124] The computer program product provided by the embodiment of the present application can adopt one or more computer readable storage media, and the computer readable storage media can be, but are not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or component, or any appropriate combination of the above. Specifically, more specific examples (non-exhaustive list) of the computer readable storage media include an electrical connection with one or more wires, a portable disc, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination of the above.

[0125] The computer program product provided by the embodiment of the present application can adopt a CD-ROM and include program codes, and can also be executed on an electronic device such as a dangerous source monitoring device, a path planning device or a whole vehicle control device. However, the computer program product provided by the embodiment of the present application is not limited to this. In the embodiment of the present application, the computer readable storage medium can be any tangible medium containing or storing program codes, which can be used or combined with an instruction execution system, device or component.

[0126] It should be noted that, although several units or sub-units of the apparatus are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, according to an embodiment of the application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into several units.

[0127] Moreover, although the operations of the method(s) herein are described in a particular, sequential order, this order is not meant to be a limitation and is not intended to imply that

[0128] Although preferred embodiments of the application have been described herein, with reference to the accompanying drawings, various changes and modifications can be suggested to one skilled in the art, and it is intended that the present application encompass such changes and modifications as fall within the scope of the appended claims.

[0129] Obviously, numerous modifications and variations of the present embodiments are possible in light of the above teachings. It is therefore to be understood that within the scope of the claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A vehicle control system, characterized in that, This includes hazard monitoring devices, route planning devices, and vehicle control devices; The hazard source monitoring device is used to acquire current environmental data within the surrounding environment area corresponding to the intelligent vehicle; extract M consecutive environmental images of the same size from the environmental video stream contained in the current environmental data; detect hazard source data in each frame of the environmental image using a hazard source detection model; based on the hazard source data in each frame of the environmental image, determine that when the overlap rate of the hazard source area in N consecutive environmental images is greater than or equal to a first threshold, it is determined that the same hazard source continuously exists in the N consecutive environmental images, confirming that the spatial consistency verification is passed; calculate the difference between the maximum and minimum confidence values ​​of the hazard source in the hazard source area in the N consecutive environmental images as the confidence fluctuation degree; when the confidence fluctuation degree is less than or equal to a second threshold, confirm that the detection result reliability verification is passed; and determine the hazard source data that has passed the spatial consistency verification and / or the detection result reliability verification as the current hazard source data; wherein, M is a positive integer greater than 1, and N is less than or equal to M; and send a hazard source avoidance trigger command based on the current hazard source data. The path planning device is configured to, upon receiving the hazard avoidance trigger command, determine the current hazard avoidance path corresponding to the intelligent vehicle based on the current hazard data in the hazard avoidance trigger command; and send a hazard avoidance execution command based on the current hazard avoidance path. The vehicle control device is used to control the intelligent vehicle to perform hazard avoidance actions according to the current hazard avoidance path in the hazard avoidance execution command when it receives the hazard avoidance execution command.

2. The vehicle control system according to claim 1, characterized in that, It also includes vehicle-mounted communication devices; The vehicle-mounted communication device is configured to, upon receiving the hazard avoidance trigger instruction, forward the hazard avoidance trigger instruction to the user client, so that the user client can provide a hazard avoidance prompt based on the current hazard data in the hazard avoidance trigger instruction; and upon receiving a confirmation avoidance instruction returned by the user client, forward the hazard avoidance trigger instruction to the vehicle control device. The vehicle control device is further configured to, upon receiving the hazard avoidance trigger command, acquire the current vehicle status data of the intelligent vehicle, and, based on the current vehicle status data, determine that the intelligent vehicle meets the intelligent driving conditions, send the hazard avoidance trigger command to the path planning device.

3. The vehicle control system according to claim 2, characterized in that, The vehicle communication device is further configured to send a first wake-up command to the vehicle control device when it receives a sentinel mode activation command sent by the user client; wherein the sentinel mode activation command is initiated by the user client when the intelligent vehicle is stationary. The vehicle control device is also used to wake up the in-vehicle network and send a second wake-up command to the hazard source monitoring device when it receives the first wake-up command; The hazard source monitoring device is also used to obtain current environmental data in the surrounding area corresponding to the intelligent vehicle when receiving the second wake-up command.

4. The vehicle control system according to claim 1, characterized in that, The path planning device is used to determine the current hazard level based on the current hazard source data, and to determine the current hazard source avoidance action based on the current hazard level; and to determine the current hazard source avoidance path based on the current hazard source avoidance action.

5. The vehicle control system according to claim 4, characterized in that, The path planning device is used to determine the current hazard level as the hazard level corresponding to the triggering condition reached by the current hazard source data, based on the correspondence between hazard level and triggering condition. Based on the correspondence between hazard level and hazard avoidance action, the hazard avoidance action corresponding to the current hazard level is determined as the current hazard avoidance action.

6. The vehicle control system according to claim 1, characterized in that, The vehicle control device is further configured to, when detecting an abnormal situation during vehicle control according to the abnormal detection methods corresponding to various abnormal situations, identify the detected abnormal situation as an abnormal situation to be processed; based on the correspondence between the abnormal situation and the processing strategy, determine the processing strategy corresponding to the abnormal situation to be processed as the target processing strategy; and process the abnormal situation to be processed based on the target processing strategy.

7. A vehicle control method, characterized in that, The method, applied to a hazard monitoring device in a vehicle control system as described in any one of claims 1 to 6, comprises: Acquire current environmental data within the surrounding area corresponding to the intelligent vehicle; M consecutive environmental images of the same size are extracted from the environmental video stream contained in the current environmental data; a hazard source detection model is used to detect hazard source data in each frame of the environmental image; based on the hazard source data in each frame of the environmental image, if the overlap rate of the hazard source region in N consecutive environmental images is greater than or equal to a first threshold, it is determined that the same hazard source continuously exists in the N consecutive environmental images, and the spatial consistency verification is confirmed to be passed. The difference between the maximum and minimum confidence values ​​of the hazard source in the hazard source region in the N consecutive environmental images is used as the confidence fluctuation degree. When the confidence fluctuation degree is less than or equal to a second threshold, the reliability verification of the detection result is confirmed to be passed. Hazard source data that have passed the spatial consistency verification and / or the reliability verification of the detection result are determined as the current hazard source data; where M is a positive integer greater than 1, and N is less than or equal to M; Based on the current hazard source data, a hazard source avoidance trigger command is sent to trigger the path planning device to determine the current hazard source avoidance strategy corresponding to the intelligent vehicle based on the current hazard source data in the hazard source avoidance trigger command. Then, the vehicle control device is triggered to control the intelligent vehicle to perform hazard source avoidance actions based on the current hazard source avoidance strategy in the hazard source avoidance execution command.

8. A vehicle control method, characterized in that, The method, applied to a path planning device in a vehicle control system as described in any one of claims 1 to 6, comprises: The system receives a hazard avoidance trigger command from a hazard source monitoring device. The hazard avoidance trigger command is as follows: the hazard source monitoring device extracts M consecutive environmental images of the same size from the environmental video stream contained in the current environmental data within the surrounding area corresponding to the intelligent vehicle; it uses a hazard source detection model to detect hazard source data in each frame of the environmental image; based on the hazard source data in each frame of the environmental image, if the overlap rate of the hazard source area in N consecutive environmental images is greater than or equal to a first threshold, it is determined that the same hazard source continuously exists in the N consecutive environmental images, confirming that the spatial consistency verification is passed; the difference between the maximum and minimum confidence scores of the hazard source areas in the N consecutive environmental images is used as the confidence fluctuation level; when the confidence fluctuation level is less than or equal to a second threshold, the reliability verification of the detection result is confirmed to be passed; and the hazard source data that has passed both the spatial consistency verification and / or the reliability verification of the detection result is determined as the current hazard source data; where M is a positive integer greater than 1, and N is less than or equal to M; based on the current hazard source data, a hazard avoidance trigger command is sent. Based on the current hazard source data in the hazard source avoidance trigger command, the current hazard source avoidance strategy corresponding to the intelligent vehicle is determined; Based on the current hazard avoidance strategy, a hazard avoidance execution command is sent to trigger the vehicle control device to control the intelligent vehicle to perform a hazard avoidance action based on the current hazard avoidance strategy in the hazard avoidance command.

9. An intelligent vehicle, characterized in that, The vehicle control system includes any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed on a processor, implements the vehicle control method as described in claim 8.

11. A computer program product containing instructions, characterized in that, The computer program product includes program code that, when run on a processor, implements the vehicle control method as described in claim 8.

12. A chip, characterized in that, It includes at least one interface circuit and at least one processor; the interface circuit is used to receive signals from the memory of the intelligent vehicle and send the signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, it implements the vehicle control method as described in claim 8.

Images