Decision making method for intelligent drive, device, recording medium, and electronic device

Abstract

To disclose a decision making method for intelligent drive, a device, a recording medium, and an electronic device.SOLUTION: A decision making method for intelligent drive includes steps of: determining a first motion parameter of a vehicle on the basis of travel data detected by the vehicle, a second motion parameter of a target having a collision risk with the vehicle, and a safety tolerance; determining, on the basis of the first motion parameter and the second motion parameter, a collision allowance time of a collision between the vehicle and the target and a relationship of crossing of the vehicle and the target in an image domain within a collision period; determining an emergency brake decision making result on the basis of the first motion parameter, the second motion parameter, the safety tolerance, and the collision allowance time in response to the collision allowance time being equal to or less than a preset time threshold and the relationship of crossing being crossing; and performing intelligent drive on the vehicle on the basis of the emergency brake decision making result.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a decision-making method, device, storage medium and electronic device for intelligent driving. [Background technology]

[0002] The Autonomous Emergency Braking (AEB) system is an active safety technology for automobiles that automatically detects obstacles ahead, assesses collision risks, issues warnings when necessary, and even automatically applies emergency braking to ensure safe driving. The AEB system in the related technology determines whether to trigger the AEB function based on a single decision-making model, which may result in decision-making errors due to misrecognition in complex or special situations, causing the AEB system to falsely trigger in non-emergency situations, potentially threatening the safe driving of the vehicle and impacting the driving and riding experience of the driver and passengers. Summary of the Invention [Problem to be solved by the invention]

[0003] In order to solve the technical problem that AEB systems in the prior art falsely trigger in non-emergency situations, the present disclosure provides an intelligent driving decision-making method, device, storage medium and electronic device, which reduce the occurrence of false triggering situations of AEB systems and achieve the effect of improving vehicle driving safety and driving and riding comfort. [Means for solving the problem]

[0004] A decision-making method for an intelligent drive according to an embodiment of the first aspect of the present disclosure includes: determining a first motion parameter of the vehicle, a second motion parameter of a target object that is at risk of collision with the vehicle, and a safety margin based on driving data detected by the vehicle; determining a collision time to collision between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain within a collision period based on the first motion parameter and the second motion parameter; determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision in response to the time to collision being equal to or less than a predetermined time threshold and the crossing relationship being a crossing; and performing intelligent driving for the vehicle based on the emergency braking decision-making result.

[0005] An intelligent drive decision-making device according to an embodiment of the second aspect of the present disclosure, a first determination module for determining a first motion parameter of the vehicle, a second motion parameter of a target object that has a collision risk with the vehicle, and a safety margin based on driving data detected by the vehicle; a second determination module for determining a collision time between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain during a collision period based on the first motion parameter and the second motion parameter; a third determination module for determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision in response to the time to collision being equal to or less than a predetermined time threshold and the crossing relationship being a crossing; and a driving module for performing intelligent driving for the vehicle based on the emergency braking decision-making result.

[0006] A computer-readable storage medium according to an embodiment of the third aspect of the present disclosure stores a computer program for executing the intelligent driving decision-making method according to the embodiment of the first aspect of the present disclosure.

[0007] An electronic device according to an embodiment of the fourth aspect of the present disclosure includes: a processor; a memory for storing instructions executable by the processor; The processor is used to read and execute the instructions from the memory to implement the intelligent driving decision-making method according to the embodiment of the first aspect of the present disclosure.

[0008] An embodiment of a fifth aspect of the present disclosure provides a computer program product, the computer program product comprising instructions that, when executed by a processor, perform the intelligent driving decision-making method according to the embodiment of the first aspect of the present disclosure. [Effects of the Invention]

[0009] An intelligent driving decision-making method provided by an embodiment of the present disclosure is applied to a vehicle equipped with an AEB system, and detects driving data in real time while the vehicle is driving. Based on the driving data, the method determines a first motion parameter of the vehicle, a second motion parameter of a target object around the vehicle that is at risk of collision with the vehicle, and a safety margin. Based on the first and second motion parameters, the method determines a collision time between the vehicle and the target object, and determines whether the vehicle and the target object will intersect in the image domain within the collision time period from the current time to the collision time. If the collision time period is less than a predetermined time threshold and the vehicle and the target object intersect in the image domain within the collision time period, the method determines an emergency braking decision-making result, i.e., whether to trigger the AEB system, based on the first and second motion parameters, and finally performs intelligent driving for the vehicle based on the emergency braking decision-making result. This method increases the factors to be considered when determining whether to trigger the emergency braking function based on the intersection relationship between the vehicle and the target object in the image domain, improves the accuracy of decision-making, reduces the occurrence of false triggering of the AEB system in non-emergency situations due to measurement errors or calculation errors, ensures that the AEB system can trigger the emergency braking function in emergency situations to reduce collision losses, and achieves the effects of improving vehicle driving safety and driving and riding comfort. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic diagram of an application scenario of an intelligent driving decision-making method provided by an exemplary embodiment of the present disclosure; FIG. [Figure 2] FIG. 1 is a block diagram of an intelligent driving decision-making system provided by an exemplary embodiment of the present disclosure. [Figure 3] 1 is a schematic flowchart of an intelligent drive decision-making method provided by an exemplary embodiment of the present disclosure. [Figure 4] 4 is a schematic flowchart of an intelligent drive decision-making method provided by another exemplary embodiment of the present disclosure. [Figure 5] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 6] 1 is a schematic diagram of a multi-frame historical environment image and a historical position frame of a target object therein provided by an exemplary embodiment of the present disclosure; [Figure 7] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 8] 2 is a schematic diagram of an image of a vehicle safety area in a vehicle coordinate system and a camera coordinate system provided by an exemplary embodiment of the present disclosure; FIG. [Figure 9] 1 is a schematic diagram of a safety area image and predicted position frame corresponding to a safety area provided by an exemplary embodiment of the present disclosure; [Figure 10] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 11] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 12]10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 13] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 14] 10 is a schematic flowchart of an intelligent drive decision-making method provided by yet another exemplary embodiment of the present disclosure. [Figure 15] 1 is a schematic structural diagram of an intelligent driving decision-making device provided by an exemplary embodiment of the present disclosure; FIG. [Figure 16] FIG. 2 is a schematic structural diagram of a decision-making device for intelligent driving provided by another exemplary embodiment of the present disclosure. [Figure 17] 1 is a schematic structural diagram of an electronic device provided according to an exemplary embodiment of the present disclosure; DETAILED DESCRIPTION OF THE INVENTION

[0011] In order to explain the present disclosure, exemplary embodiments of the present disclosure will be described in detail below with reference to the drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, not all embodiments, and the present disclosure is not limited to the exemplary embodiments.

[0012] The relative arrangement of components and steps, formulas and numerical values ​​set forth in these examples do not limit the scope of the present disclosure unless specifically stated otherwise.

[0013] Summary of the application Intelligent driving systems include automated driving systems and driver assistance systems. Driver assistance systems, also known as driver assistance systems, utilize devices such as sensors, communication devices, decision-making devices, and execution devices installed in a vehicle to monitor the driver, the vehicle, and its driving environment in real time and assist the driver in driving through information control, motion control, and other methods. Driver assistance systems for braking assistance, i.e., autonomous emergency braking (AEB) systems, are becoming increasingly important in vehicle driving assistance technologies. While a vehicle is traveling, a detection device detects information such as the speed of surrounding obstacles and the distance between the obstacles and the vehicle in real time, and calculates the collision risk between the vehicle and the surrounding obstacles. If a collision risk exists and the driver does not take effective avoidance measures, the AEB system triggers emergency braking intervention to reduce damage caused by the collision. An AEB system can be divided into three parts: sensing, decision-making, and execution. This specification describes the driver assistance system as an intelligent driving system, and unless otherwise specified, the vehicle is the vehicle that makes the driving assistance decision.

[0014] While the driver is driving the vehicle, the vehicle uses sensors such as millimeter-wave radar, lidar, and camera as detection devices to process the driving environment around the vehicle to obtain environmental sensing information, and determines motion parameters such as the relative position between the vehicle and other obstacles in the driving environment, and the speed and acceleration of the obstacles, based on the environmental sensing information.

[0015] Then, an electronic control unit (ECU) in the vehicle performs decision-making analysis based on the speed and acceleration of the host vehicle, the speed and acceleration of the obstacle, and the distance between the host vehicle and the obstacle to determine whether there is a collision risk between the host vehicle and the obstacle. If it determines that there is a collision risk, the AEB system will trigger an emergency braking function and take corresponding measures according to the emergency level.

[0016] When a vehicle is traveling normally and encounters a situation where a preceding vehicle (obstacle) applies emergency braking, another vehicle changes lanes, or a pedestrian crosses the road, and the distance between the vehicle and the obstacle is close, the AEB system determines that a safety hazard exists and first issues a warning to the driver by means of an audio warning, a display on the instrument panel, or steering wheel vibration, etc., to alert the driver to take evasive action. If the driver does not take braking action after the warning is issued, or the applied braking force is insufficient, the AEB system determines that the situation is dangerous, and in this case, the AEB system issues a partial braking command, applies partial braking force to perform auxiliary braking, and alerts the driver to take evasive action. If the driver still does not take braking action, the AEB system will actively intervene when the distance between the vehicle and the obstacle ahead is smaller than the safe distance, issue a full braking command, and have the execution device perform automatic emergency braking on the vehicle to the maximum extent possible based on the full braking command to slow down the vehicle, reduce the probability of collision between the vehicle and the obstacle ahead, reduce losses due to collision, and thereby improve driving safety.

[0017] When a vehicle is traveling in a normal driving environment with normal lighting and no external interference, the AEB system can accurately sense the surrounding driving environment and make correct decisions. Therefore, issuing a full braking command reliably indicates the occurrence of an emergency situation. For example, when a vehicle needs to slow down or even come to a complete stop in the shortest possible time to avoid a collision or respond to an unexpected situation, the AEB system activates the vehicle's full braking capability and performs braking (full braking). However, in prior art, the decision-making method used to determine whether to trigger the emergency braking function relies on a single decision-making model, which can be affected by factors such as ambient light and external interference, or in complex special scenes, resulting in sensing errors or decision-making errors due to interference, causing the AEB system to falsely trigger in non-emergency situations. Meanwhile, false triggering of the AEB system in non-emergency situations can cause a rear-end collision with a following vehicle, posing a significant threat to vehicle safety and affecting the driving and riding experience of the driver and passengers. Furthermore, full braking rapidly decelerates the vehicle, which can have a certain impact on the vehicle's braking system, tires, and vehicle structure. As can be seen from the above, the accuracy of decision-making by the AEB system is important for vehicle active safety function technology and has important implications for the safe and stable driving of the vehicle.

[0018] To solve the technical problem that the prior art relies on a single decision-making model to make decisions, which makes the AEB system prone to falsely triggering the emergency braking function, increasing driving risks and reducing driving comfort, an embodiment of the present disclosure provides a decision-making method for intelligent driving, which uses the decision-making model of the conventional AEB system to determine whether a vehicle and a target will intersect in the image domain, and if the time to collision in the AEB system decision-making model is below a preset time threshold and the vehicle and the target intersect in the image domain, determines to trigger emergency braking if the lateral distance between the vehicle and the target at the time of collision is less than a safety margin. Making the decision to trigger emergency braking using both the numerical domain and the image domain improves the accuracy of decision-making and reduces the occurrence of false triggering of the AEB system in non-emergency situations due to measurement or calculation errors, ensuring that the AEB system can trigger the emergency braking function in emergency situations to reduce collision losses, thereby achieving the effects of improving vehicle driving safety and driving comfort.

[0019] Exemplary System FIG. 1 is a schematic diagram of an application scenario of an intelligent driving decision-making method provided by an exemplary embodiment of the present disclosure. As shown in FIG. 1, the scenario includes a vehicle 100 and other vehicles 200 traveling around the vehicle 100. There may be multiple other vehicles 200, and FIG. 1 illustrates other vehicles 200-1, 200-2, 200-3, and 200-4. Here, the other vehicle 200-1 is a vehicle traveling in front of the lane in which the vehicle 100 is located, the other vehicle 200-2 is a vehicle traveling in another lane in front of the vehicle 100, the other vehicle 200-3 is a vehicle traveling behind the lane in which the vehicle 100 is located, and the other vehicle 200-4 is a vehicle traveling in the oncoming lane. When driving the vehicle 100, the driver mainly takes into consideration the driving conditions of the other vehicles 200-1 and 200-2.

[0020] Typically, when another vehicle 200-1 slows down or another vehicle 200-2 traveling in another lane changes lanes into the lane in which the vehicle 100 is located, the distance between the vehicle 100 and the other vehicle 200-1 or 200-2 traveling in front becomes closer, and the driver should actively brake to avoid a collision, or when the driver observes that there are no vehicles traveling in the other lane, the driver can steer to change lanes into the other lane to avoid a collision. However, in reality, various unexpected situations may occur, such as, for example, the vehicle 100 traveling too fast, the preceding vehicle suddenly brakes, the other vehicle suddenly changes lanes into the lane in which the vehicle (i.e., the vehicle 100) is located, other obstacles suddenly appearing, the driver driving due to fatigue, or the driver's physical condition suddenly changing, and effective avoidance measures cannot be taken in a timely manner, which may result in a collision between the vehicle 100 and the other vehicle.

[0021] In order to reduce the probability of collision between the vehicle 100 and other vehicles and reduce losses caused by the collision, in an embodiment of the present disclosure, the vehicle 100 is equipped with an intelligent driving decision-making system as shown in FIG. 2, which may include a detection device 101, a decision-making device 102, and an execution device 103.

[0022] Here, the detection device 101 is used to detect driving data in real time, and may include a motion detection module 1011 and an environment detection module 1012. The motion detection module 1011 may include a plurality of sensors installed in the vehicle 100, such as a vehicle speed sensor, an accelerator pedal position sensor, an acceleration sensor, a distance sensor, and a gyroscope, and is used to collect driving data of the vehicle 100 itself and obtain vehicle driving data. The environment detection module 1012 may include a plurality of sensors installed in the vehicle 100, such as an on-board camera, a lidar, and a millimeter-wave radar, and is used to collect data on the surrounding environment in which the vehicle 100 is driving and obtain driving environment data.

[0023] The decision-making device 102 may include a numerical domain calculation module 1021, an image domain reasoning module 1022, a check module 1023, and an emergency braking decision-making module 1024. Here, the numerical domain calculation module 1021 is used to determine a first motion parameter of the vehicle 100 based on vehicle driving data in the numerical domain according to the principle of kinematics, and to determine a second motion parameter of a target object at risk of collision with the vehicle 100 based on driving environment data, and to calculate a time to collision (TTC) between the vehicle 100 and the target object in the numerical domain. The image domain reasoning module 1022 is used to determine a historical position frame sequence of the target object in a first-person view (FPV) image from the front viewpoint of the vehicle 100 within a certain past period based on the driving environment data, and to estimate a predicted position frame sequence of the target object in the FPV image within a collision period from the current time to the collision time. The check module 1023 is used to determine whether the numerical domain and the image domain satisfy the check condition, i.e., in the numerical domain, determine whether the TTC meets a preset time threshold corresponding to the AEB system (for example, determine whether the TTC is equal to or less than the preset time threshold), and in the image domain, determine whether the vehicle 100 and the target object intersect. If the check module 1023 determines that both the numerical domain and the image domain satisfy the check condition (i.e., the collision time is equal to or less than the preset time threshold and the intersection relationship is intersection), the emergency braking decision-making module 1024 is used to determine the lateral distance between the vehicle 100 and the target object at the collision time based on the first motion parameter and the second motion parameter, and to determine an emergency braking decision-making result, i.e., whether to trigger emergency braking, based on the lateral distance and the safety margin corresponding to the target object.

[0024] The execution unit 103 is used to perform intelligent driving for the vehicle 100 based on the emergency braking decision-making result. Specifically, when the emergency braking decision-making result indicates that the AEB function needs to be triggered, the execution unit 103 determines a braking urgency based on the AEB system, a first motion parameter of the vehicle 100, and a second motion parameter of the target object, generates a control command, and provides driving assistance to the vehicle 100 based on the control command, thereby achieving the effects of reducing collision losses and improving vehicle driving safety. When the emergency braking decision-making result indicates that the AEB function does not need to be triggered, the execution unit 103 determines that the AEB system does not need to be triggered to perform automatic emergency braking, thereby avoiding false triggering of the emergency braking function in non-emergency situations, improving the accuracy of decision-making, reducing the occurrence of false triggering of the AEB system in non-emergency situations due to misrecognition, and achieving the effects of improving vehicle driving safety and driving and riding comfort.

[0025] The intelligent driving decision-making system provided in the embodiments of the present disclosure refers to the numerical domain and the image domain to determine whether an emergency braking function needs to be triggered, thereby improving the accuracy of decision-making and avoiding false triggering of the emergency braking function in non-emergency situations, reducing the occurrence of false triggering of the AEB system in non-emergency situations due to misrecognition, ensuring that the AEB system triggers the emergency braking function in emergency situations to reduce collision losses, and achieving the effects of improving vehicle driving safety and driving and riding comfort.

[0026] Exemplary Methods 3 is a schematic flowchart of an intelligent driving decision-making method provided by an exemplary embodiment of the present disclosure. The method provided by the embodiment of the present disclosure can be applied to the vehicle 100 shown in FIG. 3, and as shown in FIG. 3, the intelligent driving decision-making method can include steps 301 to 304.

[0027] In step S301, a first motion parameter of the vehicle, a second motion parameter of a target object that has a collision risk with the vehicle, and a safety margin are determined based on driving data detected by the vehicle.

[0028] An embodiment of the present disclosure can be implemented by a vehicle 100 (hereinafter also referred to as the host vehicle) shown in FIG. 1, and specifically, can be implemented by an intelligent drive decision-making system in the vehicle 100, such as that shown in FIG. 2.

[0029] During the process of driving a vehicle, various sensors in the vehicle detect data of the vehicle itself and the driving environment around the vehicle in real time to obtain driving data. Then, based on the driving data, the motion parameters of the own vehicle, the motion parameters of target objects among all objects in the surrounding environment that are at risk of collision with the vehicle, and the safety margin of the target objects are determined. In the embodiments of the present disclosure, for ease of distinction, the motion parameters of the own vehicle are referred to as first motion parameters, and the motion parameters of the target objects are referred to as second motion parameters.

[0030] The safety margin is the tolerance for the overall uncertainty during measurement, and mainly consists of two parts: the tolerance for the uncertainty of the measuring instrument and the tolerance for the measurement uncertainty due to the measurement conditions. In the embodiment of the present disclosure, the safety margin is a preset value, which is preset based on the type of target object and is the tolerance value that indicates the vehicle's ability to avoid the target object. The safety margins corresponding to different types of target objects are generally different.

[0031] In step S302, a collision time between the vehicle and the target object and an intersection relationship between the vehicle and the target object in the image domain during the collision time are determined based on the first motion parameter and the second motion parameter.

[0032] Common decision-making models for AEB systems include a Time To Collision (TTC) model, a safety distance model, and a minimum deceleration model for collision avoidance. In the embodiment of the present disclosure, the decision-making model is described as a TTC model. Based on a first motion parameter of the vehicle and a second motion parameter of the target object, the time required for the vehicle and the target object to continue traveling until a collision occurs based on the current state is calculated in the numerical domain, i.e., TTC. Based on the first motion parameter of the vehicle and the second motion parameter of the target object, the intersection relationship between the vehicle and the target object in the image domain within the collision period is predicted.

[0033] Here, the collision period is the period from the current time to the collision time. The intersection relationship includes intersection and non-intersection. If the positions of the vehicle and the target object in the predicted image overlap within the collision period, it is determined that the vehicle and the target object intersect in the image domain. If the positions of the vehicle and the target object in the predicted image do not overlap within the collision period, it is determined that the vehicle and the target object do not intersect in the image domain.

[0034] In step S303, in response to the collision time being equal to or less than a predetermined time threshold and the intersection relationship being an intersection, an emergency braking decision-making result is determined based on the first motion parameter, the second motion parameter, the safety margin, and the collision time being.

[0035] Determine whether the TTC is equal to or less than a preset time threshold, and determine whether the intersection relationship between the vehicle and the target object in the collision period in the image domain is an intersection. If the TTC is equal to or less than the preset time threshold and the vehicle and the target object in the collision period intersect in the image domain, it is considered that the check conditions are met in both the numerical domain and the image domain. At this time, determine whether to trigger emergency braking based on the first motion parameter, the second motion parameter, the time to collision, and the safety margin, and obtain an emergency braking decision-making result. The emergency braking decision-making result includes triggering emergency braking and not triggering emergency braking.

[0036] In step S304, intelligent driving is performed for the vehicle based on the emergency braking decision-making result.

[0037] When the emergency braking decision-making result is to trigger emergency braking, it indicates that the AEB system needs to be triggered to perform automatic emergency braking. At this time, the AEB system is triggered to assist the driver and provide driving assistance to the vehicle, thereby minimizing losses caused by collisions and improving vehicle driving safety.

[0038] When the emergency braking decision-making result is not to trigger emergency braking, it means that there is no need to trigger the AEB system to perform automatic emergency braking. In this case, it is considered that no emergency situation occurs, and the vehicle does not need to trigger the AEB system, which avoids false triggering of the emergency braking function in non-emergency situations, reduces the occurrence of situations in which the AEB system is falsely triggered in non-emergency situations due to misrecognition, and achieves the effects of improving vehicle driving safety and driving / riding comfort.

[0039] The intelligent driving decision-making method provided in the embodiment of the present disclosure first determines a first motion parameter of the vehicle, a second motion parameter of a target object at risk of collision with the vehicle, and a safety margin based on driving data detected by the vehicle, then determines a collision time between the vehicle and the target object and an intersection relationship between the vehicle and the target object in the image domain during the collision period based on the first motion parameter and the second motion parameter, and if the collision time is less than a predetermined time threshold and the intersection relationship is intersection, determines an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the collision time, and finally performs intelligent driving for the vehicle based on the emergency braking decision-making result. This method increases the consideration factors for whether to trigger the emergency braking function based on the intersection relationship between the vehicle and the target object in the image domain, improves the decision-making accuracy, reduces the occurrence of false triggering of the AEB system in non-emergency situations due to measurement errors or calculation errors, ensures that the AEB system triggers the emergency braking function in emergency situations to reduce collision losses, and achieves the effects of improving vehicle driving safety and driving comfort.

[0040] In some embodiments, step S301 in the above embodiment, "determining a first motion parameter of the vehicle, a second motion parameter of a target object at risk of collision with the vehicle, and a safety margin based on driving data detected by the vehicle," can be implemented by steps S3011 to S3013 shown in FIG. 4.

[0041] In step S3011, a first motion parameter of the vehicle is determined based on the vehicle driving data detected in real time by the vehicle motion detection module in the driving data.

[0042] While a driver is driving a vehicle, a motion detection module in the vehicle detects driving data of the vehicle itself in real time to obtain vehicle driving data. Here, the motion detection module may include multiple sensors installed in the vehicle, such as a vehicle speed sensor, an accelerator pedal position sensor, an acceleration sensor, a distance sensor, a gyroscope, etc. The corresponding vehicle driving data may include driving data such as the vehicle speed collected by the vehicle speed sensor, the pedal position collected by the accelerator pedal position sensor, the acceleration collected by the acceleration sensor, the distance collected by the distance sensor, and the yaw angle collected by the gyroscope.

[0043] The vehicle driving data detected in real time by the motion detection module is processed to obtain a first motion parameter of the vehicle. In some embodiments of the present disclosure, the first motion parameter may include a real-time speed and a real-time acceleration of the vehicle. In some embodiments, the first motion parameter may further include other data, such as a yaw angle of the vehicle, a real-time position, and the like, and is not limited to these in the embodiments of the present disclosure.

[0044] In step S3012, the vehicle environment detection module in the driving data determines the target object that has a collision risk with the vehicle and the second motion parameters of the target object based on the driving environment data detected within a preset time period.

[0045] While the driver is driving the vehicle, the environment detection module in the vehicle detects data of the surrounding environment in real time and stores it in an on-board memory. The latest driving environment data stored within a preset time period is read from the on-board memory. Here, the environment detection module may include various sensors installed in the vehicle, such as an on-board camera, a lidar, and a millimeter-wave radar. The corresponding driving environment data may include collected driving data such as environmental images, laser signals, and millimeter-wave signals.

[0046] The environment detection module processes the driving environment data detected in real time, selects a target object that may collide with the vehicle from all recognized objects, and determines a second motion parameter of the target object based on the read driving environment data within a preset time period. In an embodiment of the present disclosure, the second motion parameter can include a real-time speed and real-time acceleration of the target object, and a relative position between the target object and the vehicle.

[0047] In step S3013, a safety margin is determined based on the type of target object.

[0048] In an embodiment of the present disclosure, the safety margin is a preset value, which is a preset tolerance indicating the vehicle's ability to avoid the target object based on the type of the target object. A correspondence table between safety margins and different types of obstacles is pre-stored in the on-board memory. After the target object is determined, the correspondence table stored in the on-board memory is searched based on the type of the target object to obtain the safety margin corresponding to the target object. Here, the obstacle type may include non-stationary or stationary objects such as passenger cars, trucks, buses, trailers, unfinished vehicles (chassis), motorcycles, pedestrians, cyclists, water-filled temporary protective fences, bollards, tunnel walls, bridge piers, etc. Different types of targets generally have different safety margins set.

[0049] The method provided by the embodiments of the present disclosure detects driving data in real time using a detection device in a vehicle, determines motion parameters and safety margins between the vehicle and a target object based on the driving data, and provides data for subsequent decision-making.

[0050] In some embodiments, in the above embodiments, step S3012 in the above embodiments, "determining a target object that has a collision risk with the vehicle and a second motion parameter of the target object based on driving environment data detected by the vehicle environment detection module in the driving data within a predetermined time period" can be realized by steps S30121 to S30123 shown in FIG. 5.

[0051] In step S30121, based on the driving environment data detected in real time by the vehicle environment detection module in the driving data, the target object that is at risk of collision with the vehicle, as well as the real-time speed, real-time acceleration, and relative position of the target object to the vehicle are determined.

[0052] In some embodiments, the target object that is at risk of collision with the vehicle can be determined by the following steps a to c.

[0053] In step a, the environment detection module preprocesses the driving environment data detected in real time to obtain environment sensing information, where the preprocessing can include processing steps such as data cleaning, type conversion, data noise reduction, data augmentation, and data standardization.

[0054] In step b, the pre-trained target detection model performs feature extraction, classification, recognition, etc. on the environmental sensing information to recognize multiple obstacles that may affect the normal driving of the vehicle in the current driving environment. These obstacles may include movable objects such as vehicles moving or parked on the roadside, pedestrians, etc., as well as stationary objects such as water-filled temporary protective fences, bollards, tunnel walls, bridge piers, etc.

[0055] In step c, a collision risk assessment is performed for each obstacle to obtain a collision risk assessment result for each obstacle, and a target object is selected from each obstacle based on the collision risk assessment result for each obstacle.

[0056] In some embodiments, the TTC of a collision between the vehicle and each obstacle can be calculated based on the TTC model. The smaller the TTC corresponding to an obstacle, the higher the risk of a collision between the vehicle and this obstacle. The magnitude of the TTC corresponding to each obstacle is compared, and the obstacle with the smallest TTC is selected as the target object.

[0057] In some other embodiments, the distance between the vehicle and each obstacle can be calculated based on a safe distance model. For multiple obstacles in the same lane, the closer the distance between the vehicle and the obstacles, the higher the possibility of collision and the higher the collision risk. The distances corresponding to each obstacle are compared, and the obstacle closest to the vehicle is selected as the target object.

[0058] Furthermore, in some other embodiments, the target object that has a collision risk with the vehicle can be determined based on other methods, and the embodiments of the present disclosure are not limited thereto.

[0059] After determining the target object, the real-time speed, real-time acceleration, and relative position of the target object to the vehicle are determined based on the driving environment data detected in real time by the environment detection module. Note that in the embodiment of the present disclosure, the real-time speed and real-time acceleration of the vehicle, and the real-time speed, real-time acceleration, and relative position of the target object are all vectors.

[0060] In an embodiment of the present disclosure, a target object that is at risk of collision with the vehicle is determined based on driving environment data, and the real-time speed, real-time acceleration, and relative position of the target object and the vehicle are determined to provide data for subsequent decision-making.

[0061] In step S30122, the environment detection module in the traveling data determines a history position frame sequence of the target object based on a plurality of traveling environment data detected within a preset time period.

[0062] Based on the multiple driving environment data detected by the environment detection module within a history period (a preset time), each frame image collected by the front camera of the vehicle 100 within this preset time period is determined as a first-person view (FPV) image. Then, a historical position frame of the target object is determined from each frame image and sorted in chronological order to obtain a historical position frame sequence of the target object. In one implementation, the historical position frame sequence of the target object can be determined by the following steps d to f.

[0063] In step d, a plurality of historical environment images from a first-person perspective are determined based on a plurality of pieces of driving environment data detected by the environment detection module in the driving data within a preset time period.

[0064] The image data in the plurality of driving environment data is processed, and the plurality of frames of historical environment images collected by the front camera of the vehicle are determined, and the viewpoint corresponding to the plurality of frames of historical environment images is, namely, FPV.

[0065] A historical position frame sequence of a target object in an image in which a front viewpoint of the vehicle 100 is a first person view (FPV) within a certain period of time in the past is determined based on the driving environment data.

[0066] In step e, each historical environment image is recognized, and a historical position frame of the target object in each historical environment image is determined.

[0067] The location area where the target object is located in the historical environment image of each frame is recognized, and the historical location frame of the target object in each historical environment image is obtained, where the location frame of the target object may be the contour line of the target object, a circumscribed rectangular frame of the contour line of the target object, or other regular or irregular bounding box that can represent the position of the target object.

[0068] As an example, the position frame of the target object is represented by a circumscribing rectangular frame of the target object's contour line. Figure 6(a) shows three time-series consecutive frames of historical environment images. Each frame image is recognized, the position of the target object in each frame image is determined, and the historical position frame of the target object in each frame of the historical environment image is obtained, as shown in Figure 6(b).

[0069] In step f, the historical location frames of the target object in each historical environment image are sorted according to time to obtain a historical location frame sequence.

[0070] The location frames in each image are sorted according to time order to obtain a sequence of historical location frames of the target object in the image domain.

[0071] In step S30123, a second motion parameter is determined based on the real-time velocity, real-time acceleration, relative position and history position frame sequence of the target object.

[0072] The real-time velocity, real-time acceleration, relative position to the vehicle, and historical position frame sequence of the target object are determined as second motion parameters of the target object.

[0073] The method provided by the embodiments of the present disclosure first determines the target object that is most likely to collide with the host vehicle based on the driving environment data detected in real time by the vehicle's environment detection module, and determines the real-time speed, real-time acceleration, and relative position of the target object and the host vehicle. Then, based on the driving environment data detected within a predetermined time period, determines a historical position frame sequence of the target object in the image domain, thereby obtaining second motion parameters of the target object and providing data for subsequent decision-making in the numerical domain and the image domain.

[0074] In some embodiments, in the above embodiments, step S302 in the above embodiments, "determining the collision time between the vehicle and the target object and the intersection relationship in the image domain between the vehicle and the target object during the collision period based on the first motion parameter and the second motion parameter" can be realized by steps S3021 to S3024 shown in FIG. 7.

[0075] In step S3021, a collision margin time for a collision between the vehicle and the target object is determined based on the real-time speed and real-time acceleration of the vehicle included in the first motion parameters, and the real-time speed, real-time acceleration and relative position of the target object included in the second motion parameters.

[0076] JPEG2025181814000002.jpg64166

[0077] In some embodiments, the TTC can be calculated based on the component of the relative position between the host vehicle and the target object in the X-axis direction (i.e., the vertical direction) of the vehicle coordinate system, the vertical component of the vehicle's real-time speed, the vertical component of the vehicle's real-time acceleration, the vertical component of the target object's real-time speed, and the vertical component of the target object's real-time acceleration, and substituted into the above equation (1).

[0078] JPEG2025181814000003.jpg35166

[0079] In step S3022, a first-person perspective safe area image is determined based on the vehicle safe area.

[0080] In an embodiment of the present disclosure, the vehicle safety area is defined as a front safety area in the vehicle coordinate system, with a vertical length of safe-x and a horizontal length of safe-y, as shown in the gray area in Fig. 8(a). Based on the mapping relationship between the vehicle coordinate system and the camera coordinate system of the front camera, the vehicle safety area in the vehicle coordinate system as shown in Fig. 8(a) is transformed into the camera coordinate system to obtain a safety area image in a first-person perspective as shown in Fig. 8(b), and the safety area image corresponding to the safety area is the gray area in Fig. 8(b).

[0081] In step S3023, a predicted position frame sequence of the target object within the collision period is determined based on the time to collision and the historical position frame sequence of the target object included in the second motion parameter.

[0082] The second motion parameters further include a historical position sequence of the target object. Based on the TTC and the historical position sequence of the target object, a predicted position frame sequence of the target object within the collision period is determined, i.e., based on the position frame of the target object in each historical environment image from the first-person perspective detected within a predetermined time in the past, a predicted position frame of the target object in each predicted image from the first-person perspective within the collision period is predicted. Each predicted position frame is sorted in time order to obtain a predicted position frame sequence of the target object. Here, the collision period is the period from the current time to the collision time.

[0083] In step S3024, based on the safe area image and the predicted position frame sequence, the intersection relationship in the image domain between the vehicle and the target object within the collision period is determined.

[0084] Determining whether the safety area image intersects with each predicted position frame in the sequence of predicted position frames can be done by determining whether a specific target point (e.g., the midpoint of the bottom edge) in the predicted position frame is within the safety area image corresponding to the safety area. As shown in Figure 9(a), the target point of the first predicted position frame is within the safety area image (gray area) corresponding to the safety area, indicating that the vehicle and the target object intersect at a first time corresponding to the first predicted position frame. As shown in Figure 9(b), the target point of the second predicted position frame is outside the safety area image (gray area), indicating that the vehicle and the target object do not intersect at a second time corresponding to the second predicted position frame.

[0085] In one implementation, the intersection relationship in the image domain between the vehicle and the target object during the collision period can be determined by steps S30241 to S30244 shown in FIG.

[0086] In step S30241, a target point sequence is determined based on the predicted position window sequence.

[0087] A target point of each predicted position frame in the predicted position frame sequence is determined in sequence to obtain a target point sequence, and each target point in the target point sequence corresponds one-to-one with each predicted position frame in the predicted position frame sequence.

[0088] In step S30242, the positional relationship between each target point in the target point sequence and the safety area image corresponding to the safety area is determined.

[0089] Determine whether each target point in the target point sequence is located within a safety area image corresponding to the safe area, and obtain a positional relationship between each target point and the safety area image, including whether the target point is located within the safety area image and whether the target point is not located within the safety area image, where whether the target point is not located within the safety area image includes whether the target point is located outside the safety area image and whether the target point is located on the boundary of the safety area image.

[0090] In step S30243, in response to the presence of two chronologically consecutive target points in the target point sequence located within the safety area image, it is determined that the intersection relationship in the image domain between the vehicle and the target object within the collision period is an image intersection.

[0091] A vehicle and a target object in a collision period are considered to intersect in the image domain if there are two time-sequentially consecutive target points in the target point sequence that are both located within the safe area image.

[0092] Although the embodiment of the present disclosure has been described using two target points as an example, in actual application, if there is one target point located in the safety area image in the target point sequence, it can be considered that the vehicle and the target object in the collision period intersect in the image domain, and only if there are multiple (more than two) time-series consecutive target points located in the safety area image in the target point sequence, it can be considered that the vehicle and the target object in the collision period intersect in the image domain. In practice, an appropriate number of target points can be selected according to the actual driving scene to determine whether there is an intersection, and this is not limited to the embodiment of the present disclosure.

[0093] In step S30244, in response to the absence of two chronologically consecutive target points in the target point sequence located within the safety area image, it is determined that the intersection relationship in the image domain between the vehicle and the target object within the collision period is an image non-intersection.

[0094] If there are no two time-sequentially consecutive target points in the target point sequence that are both located within the safe area image, it is considered that the vehicle and the target object within the collision period do not intersect in the image domain.

[0095] In an embodiment of the present disclosure, a predicted position frame sequence within a collision period of a target object is predicted based on a historical position frame sequence of the target object within a history period, and an intersection relationship between the predicted position frame sequence and an FPV safety area image corresponding to the safety area is determined to determine an intersection relationship in the image domain between the vehicle and the target object, thereby providing data related to the image domain for decision-making.

[0096] In some embodiments, in the above embodiments, step S303 in the above embodiments, "in response to the time to collision being equal to or less than a predetermined time threshold and the intersection relationship being an intersection, determine an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision" can be realized by steps S3031 to S3034 shown in FIG. 11.

[0097] In step S3031, a predicted displacement of the vehicle is determined based on the real-time speed and real-time acceleration of the vehicle included in the first motion parameters, and the time to collision.

[0098] JPEG2025181814000004.jpg31166

[0099] In step S3032, a predicted displacement of the target object is determined based on the real-time velocity and real-time acceleration of the target object included in the second motion parameters and the time to collision.

[0100] JPEG2025181814000005.jpg35165

[0101] In step S3033, the lateral distance between the vehicle and the target object at the time of collision is determined based on the predicted displacement of the vehicle, the predicted displacement of the target object, and the relative position of the target object and the vehicle included in the second motion parameters.

[0102] JPEG2025181814000006.jpg41165

[0103] JPEG2025181814000007.jpg73165

[0104] In step S3034, an emergency braking decision result is determined based on the lateral distance and the safety margin.

[0105] In one implementation, the emergency braking decision-making result can be realized by steps S30341 to S30343 shown in FIG.

[0106] In step S30341, the difference between the lateral distance and the safety margin is determined.

[0107] In step S30342, in response to the difference value being equal to or less than the preset threshold, the emergency braking decision-making result is determined as triggering emergency braking.

[0108] In step S30343, in response to the difference value being greater than the preset threshold, the emergency braking decision-making result is determined as not to trigger emergency braking.

[0109] For example, in one embodiment, the preset threshold value may be 0. The magnitude of the lateral distance and the safety margin is compared, and if the difference between the lateral distance and the safety margin is less than or equal to the prediction threshold value, i.e., the lateral distance is less than or equal to the safety margin, it is considered that there is no error in the sensing recognition, and if no effective measures are taken, the vehicle and the target object will collide within the calculated time to collision, and automatic emergency braking needs to be triggered, and the emergency braking decision-making result is determined to be that emergency braking is triggered. If the difference between the lateral distance and the safety margin is greater than the prediction threshold value, i.e., the lateral distance is greater than the safety margin, it is considered that there is an error in the sensing recognition, and the vehicle and the target object will not collide within the calculated time to collision, and automatic emergency braking does not need to be triggered, and the emergency braking decision-making result is determined to be that emergency braking is not triggered.

[0110] In practical applications, the prediction threshold may be other preset values, and is not limited to the embodiments of the present disclosure.

[0111] The method provided by the embodiment of the present disclosure predicts the lateral distance between the vehicle and the target at the time of collision, and determines an emergency braking decision-making result according to the lateral distance and a safety margin. If it is determined based on the lateral distance and the safety margin that the emergency braking function needs to be triggered, the emergency braking decision-making result is determined to trigger emergency braking; if it is determined based on the lateral distance and the safety margin that the emergency braking function does not need to be triggered, the emergency braking decision-making result is determined to not trigger emergency braking, thus reducing false triggers of the AEB system, ensuring that the AEB system triggers the emergency braking function in an emergency situation, and improving the accuracy of decision-making.

[0112] In some embodiments, in the above embodiment, step S304 of "performing intelligent driving for the vehicle based on the emergency braking decision-making result" in the above embodiment can be realized by steps S3041 and S3042 shown in FIG.

[0113] In step S3041, in response to the emergency braking decision-making result indicating that automatic emergency braking needs to be triggered, generate a control command based on the automatic emergency braking system, the first motion parameter, and the second motion parameter.

[0114] When the emergency braking decision-making result indicates that automatic emergency braking needs to be triggered, a control command can be generated based on the TTC determined by the first motion parameter and the second motion parameter and the preset time threshold of the AEB system. Specifically, the TTC is compared with the magnitude of the preset time threshold, and a corresponding control command is generated based on the comparison result.

[0115] JPEG2025181814000008.jpg35165

[0116] JPEG2025181814000009.jpg21165

[0117] In step S3042, driving assistance is provided to the vehicle based on the control command.

[0118] In the above embodiment, this step can be realized by steps S30421 to S30423 shown in FIG.

[0119] In step S30421, in response to the control command being a warning command, presentation information is output based on the warning command to alert the driver of the vehicle to apply the brakes.

[0120] It is determined that emergency braking needs to be triggered based on the numerical domain, the image domain and the safety margin, and if the generated control command is an alarm command, it issues an alarm to the driver (i.e., the driver of the vehicle) by a voice, an icon or other warning to alert the driver to brake and avoid a collision between the vehicle and the target object.

[0121] In step S30422, in response to the control command being a partial braking command, supplemental braking is performed on the vehicle based on the partial braking command.

[0122] If the generated control command is a partial braking command, a partial braking force is applied to achieve the purpose of reducing the speed and alerting the driver to brake, thereby reducing the probability of a collision between the vehicle and the target object.

[0123] In step S30423, in response to the control command being a full braking command, emergency braking is performed on the vehicle based on the full braking command.

[0124] If the generated control command is a full braking command, all braking force is applied to achieve the purpose of rapidly reducing the speed and reducing the loss caused by the collision between the vehicle and the target object.

[0125] The method provided by the embodiments of the present disclosure generates different control commands depending on the degree of urgency when it is determined that emergency braking needs to be triggered to provide driving assistance to the vehicle, thereby providing driving assistance to the vehicle based on a warning command, a partial braking command, or a full braking command, thereby reducing the probability of a collision between the vehicle and an obstacle ahead, reducing losses due to the collision, and thereby improving driving safety.

[0126] Exemplary Apparatus FIG. 15 is a schematic structural diagram of an intelligent driving decision-making device provided in an exemplary embodiment of the present disclosure. As shown in FIG. 15, the intelligent driving decision-making device 1500 includes: a first determination module 1501 for determining a first motion parameter of the vehicle, a second motion parameter of a target object that has a collision risk with the vehicle, and a safety margin based on driving data detected by the vehicle; a second determination module 1502 for determining a collision time between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain during a collision period based on the first motion parameter and the second motion parameter; a third determination module 1503 for determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision in response to the time to collision being equal to or less than a predetermined time threshold and the crossing relationship being a crossing; and a driving module 1504 for performing intelligent driving on the vehicle based on the emergency braking decision-making result.

[0127] Referring to FIG. 16, in some embodiments, the first determination module 1501: a first determination unit 15011 for determining a first motion parameter of the vehicle according to the vehicle driving data detected in real time by the vehicle motion detection module in the driving data; a second determination unit 15012 for determining a target object that has a collision risk with the vehicle and a second motion parameter of the target object based on the driving environment data detected by the vehicle environment detection module within a predetermined time period in the driving data; and a third determining unit 15013 for determining the safety margin based on the type of the target object.

[0128] In some embodiments, the second determining unit 15012 is a first determination subunit for determining the target object that has a collision risk with the vehicle, and the real-time speed, real-time acceleration, and relative position of the target object to the vehicle based on driving environment data detected in real time by the vehicle environment detection module in the driving data; a second determination subunit for determining a historical position frame sequence of the target object based on a plurality of driving environment data detected by the environment detection module in the driving data within the preset time period; and a third determination subunit for determining the second motion parameter based on the real-time velocity, real-time acceleration, and relative position of the target object and the historical position frame sequence.

[0129] In some embodiments, the second determination subunit can be specifically used to determine a plurality of historical environment images from a first-person perspective based on a plurality of driving environment data detected by the environment detection module in the driving data within the predetermined time period, recognize each of the historical environment images, determine a historical position frame of the target object in each of the historical environment images, sort the historical position frames of the target object in each of the historical environment images according to time, and obtain the historical position frame sequence.

[0130] Referring to FIG. 16, in some embodiments, the second determination module 1502: a fourth determination unit 15021 for determining a collision time to collision between the vehicle and the target object according to the real-time speed and real-time acceleration of the vehicle included in the first motion parameters, and the real-time speed, real-time acceleration and relative position of the target object included in the second motion parameters; a fifth determining unit 15022 for determining a safe area image in a first-person perspective according to the safe area of ​​the vehicle; a sixth determining unit 15023 for determining a predicted position frame sequence of the target object within the collision period according to the time to collision and the historical position frame sequence of the target object included in the second motion parameter; and a seventh determination unit 15024 for determining an intersection relationship in the image domain between the vehicle and the target object within the collision period based on the safe area image and the predicted position frame sequence.

[0131] In some embodiments, the seventh determining unit 15024 is a fourth determination subunit for determining a sequence of target points based on the sequence of predicted position frames; a fifth determination subunit for determining a positional relationship between each target point in the target point sequence and a safety area image corresponding to the safety area; a sixth determination subunit for determining, in response to the presence of two time-series consecutive target points in the target point sequence that are located within the safety area image, that an intersection relationship in an image domain between the vehicle and the target object within the collision period is an image intersection; and a seventh determination subunit for determining, in response to the absence of two chronologically consecutive target points in the target point sequence that are located within the safety area image, that an intersection relationship in the image domain between the vehicle and the target object within the collision period is an image non-intersection.

[0132] Referring to FIG. 16, in some embodiments, the third determination module 1503: an eighth determination unit 15031 for determining a predicted displacement of the vehicle according to the real-time speed, real-time acceleration, and time to collision of the vehicle included in the first motion parameters; a ninth determination unit 15032 for determining a predicted displacement of the target object according to the real-time velocity, real-time acceleration, and the time to collision of the target object included in the second motion parameters; a tenth determination unit 15033 for determining a lateral distance between the vehicle and the target object at a collision time based on the predicted displacement of the vehicle, the predicted displacement of the target object, and the relative position of the target object and the vehicle included in the second motion parameters; and an eleventh determining unit 15034 for determining an emergency braking decision-making result based on the lateral distance and the safety margin.

[0133] In some embodiments, the eleventh determining unit 15034 is an eighth determination subunit for determining a difference value between the lateral distance and the safety margin; a ninth determination subunit for determining the emergency braking decision-making result as triggering emergency braking in response to the difference value being equal to or less than a predetermined threshold; and a tenth decision subunit for determining the emergency braking decision-making result as not to trigger emergency braking in response to the difference value being greater than the preset threshold.

[0134] The beneficial technical effects corresponding to the exemplary embodiments of the apparatus in the present disclosure can be referred to the beneficial technical effects corresponding to the exemplary method part above, and therefore will not be described here.

[0135] Exemplary Electronic Devices FIG. 17 is a schematic structural diagram of an electronic device provided according to an exemplary embodiment of the present disclosure. As shown in FIG. 17, the electronic device 1700 includes at least one processor 1701 and a memory 1702.

[0136] The processor 1701 may be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities, and may control other components of the electronic device 1700 to perform desired functions.

[0137] The memory 1702 may include one or more computer program products, which may include various types of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored in the computer-readable storage media, and the processor 1701 may execute the one or more computer program instructions to implement the intelligent drive decision-making method and / or other desired functions of each embodiment of the present disclosure.

[0138] In one example, electronic device 1700 may further include input devices 1703 and output devices 1704, these components being connected to each other via a bus system and / or other form of connection (not shown).

[0139] The input device 1703 may further include, for example, a keyboard, a mouse, and the like.

[0140] The output device 1704 can output various types of information to the outside, and can include, for example, a display, a speaker, a printer, a communication network, and remote output devices connected to these.

[0141] 17 shows only some of the components related to the present disclosure in the electronic device 1700, and omits components such as buses, input / output interfaces, etc. Besides, the electronic device 1700 may further include any other appropriate components depending on the specific application.

[0142] Exemplary Computer Program Products and Computer-Readable Storage Media In addition to the above methods and apparatus, embodiments of the present disclosure may further provide a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform steps in the intelligent drive decision-making methods of various embodiments of the present disclosure described in the "Example Methods" section above.

[0143] The computer program product may have program code for carrying out operations of embodiments of the present disclosure written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and traditional procedural programming languages ​​such as "C" or similar programming languages. The program code may execute entirely on a user's computing device, partially on a user's device, as separate software packages, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0144] Additionally, an embodiment of the present disclosure may further comprise a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in the intelligent drive decision-making methods of various embodiments of the present disclosure described in the "Example Methods" section above.

[0145] The computer-readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0146] Although the basic principles of the present disclosure have been described above with reference to specific embodiments, the benefits, advantages, effects, etc. mentioned in the present disclosure are not limited but merely illustrative, and these benefits, advantages, effects, etc. do not necessarily exist in each embodiment of the present disclosure. Furthermore, the specific details disclosed above are not limited but merely serve to serve as examples and to facilitate understanding, and the above details do not necessarily limit the present disclosure to be realized by the above specific details.

[0147] Those skilled in the art can make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure also intends to include these modifications and variations.

Claims

1. determining a first motion parameter of the vehicle, a second motion parameter of a target object that is at risk of collision with the vehicle, and a safety margin based on driving data detected by the vehicle; determining a collision time to collision between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain during a collision period based on the first motion parameter and the second motion parameter; determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision in response to the time to collision being equal to or less than a predetermined time threshold and the crossing relationship being a crossing; and performing intelligent driving on the vehicle based on the emergency braking decision-making result, the intelligent driving decision-making method being executed by the intelligent driving decision-making device.

2. The step of determining a first motion parameter of the vehicle, a second motion parameter of a target object that has a collision risk with the vehicle, and a safety margin based on driving data detected by the vehicle, includes: determining a first motion parameter of the vehicle based on the vehicle driving data detected in real time by the vehicle motion detection module in the driving data; determining a target object that has a collision risk with the vehicle and a second motion parameter of the target object based on driving environment data detected by an environment detection module of the vehicle within a predetermined time period in the driving data; and determining the safety margin based on the type of the target object.

3. The step of determining a target object that has a collision risk with the vehicle and a second motion parameter of the target object based on driving environment data detected by an environment detection module of the vehicle within a predetermined time period in the driving data, determining the target object that is at risk of collision with the vehicle, and the real-time speed, real-time acceleration, and relative position of the target object to the vehicle based on driving environment data detected in real time by the vehicle environment detection module in the driving data; determining a history position frame sequence of the target object based on a plurality of driving environment data detected by the environment detection module in the driving data within the preset time period; and determining the second motion parameter based on the real-time velocity, real-time acceleration, and relative position of the target object and the historical position frame sequence.

4. The step of determining a history position frame sequence of the target object based on a plurality of driving environment data detected by the environment detection module in the driving data within the preset time period includes: determining a plurality of historical environment images from a first-person perspective based on a plurality of driving environment data detected by the environment detection module within the predetermined time period in the driving data; recognizing each of the historical environment images and determining a historical location frame of the target object in each of the historical environment images; 4. The intelligent driving decision-making method of claim 3, further comprising the step of: sorting the historical location frames of the target object in each of the historical environment images according to time to obtain the historical location frame sequence.

5. determining a collision time to collision between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain during a collision period based on the first motion parameter and the second motion parameter, determining a time to collision of a collision between the vehicle and the target object based on the real-time speed and real-time acceleration of the vehicle included in the first motion parameters and the real-time speed, real-time acceleration and relative position of the target object included in the second motion parameters; determining a first-person perspective safe area image based on the vehicle safe area; determining a predicted position frame sequence of the target object within the collision period based on the time to collision and the historical position frame sequence of the target object included in the second motion parameter; 2. The intelligent driving decision-making method of claim 1, further comprising: determining an intersection relationship in the image domain between the vehicle and the target object within the collision period based on the safe area image and the predicted position frame sequence.

6. determining an intersection relationship in an image domain between the vehicle and the target object within the collision period based on the safe area image and the predicted position frame sequence, determining a sequence of target points based on the sequence of predicted position windows; determining a positional relationship between each target point in the target point sequence and the safety area image corresponding to the safety area; determining, in response to the presence of two time-sequentially consecutive target points in the target point sequence that are located within the safety area image, that an intersection relationship in an image domain between the vehicle and the target object within the collision period is an image intersection; 6. The intelligent driving decision-making method of claim 5, further comprising: in response to the absence of two time-series consecutive target points in the target point sequence that are located within the safety area image, determining that an intersection relationship in the image domain between the vehicle and the target object within the collision period is an image non-intersection.

7. determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision, determining a predicted displacement of the vehicle based on a real-time speed and a real-time acceleration of the vehicle included in the first motion parameters and the time to collision; determining a predicted displacement of the target object based on the real-time velocity and real-time acceleration of the target object included in the second motion parameters and the time to collision; determining a lateral distance between the vehicle and the target object at a time of collision based on the predicted displacement of the vehicle, the predicted displacement of the target object, and a relative position of the target object and the vehicle included in the second motion parameters; and determining an emergency braking decision-making result based on the lateral distance and the safety margin.

8. determining an emergency braking decision-making result based on the lateral distance and the safety margin, determining a difference between the lateral distance and the safety margin; determining the emergency braking decision result as triggering emergency braking in response to the difference value being equal to or less than a predetermined threshold; and determining the emergency braking decision-making result as not to trigger emergency braking in response to the difference value being greater than the preset threshold.

9. a first determination module for determining a first motion parameter of the vehicle, a second motion parameter of a target object that has a collision risk with the vehicle, and a safety margin based on driving data detected by the vehicle; a second determination module for determining a collision time between the vehicle and the target object and an intersection relationship between the vehicle and the target object in an image domain during a collision period based on the first motion parameter and the second motion parameter; a third determination module for determining an emergency braking decision-making result based on the first motion parameter, the second motion parameter, the safety margin, and the time to collision in response to the time to collision being equal to or less than a predetermined time threshold and the crossing relationship being a crossing; and a driving module for performing intelligent driving on the vehicle based on the emergency braking decision-making result.

10. A computer-readable storage medium storing a computer program for executing the decision-making method for an intelligent drive according to any one of claims 1 to 8.

11. a processor; a memory for storing instructions executable by the processor; The processor is used to read and execute the instructions from the memory to realize the intelligent drive decision-making method according to any one of claims 1 to 8.

Images