Simulation method and device for driving assistance system, driving assistance system and vehicle

Abstract

The present disclosure provides a simulation method, simulation device, driving assistance system and vehicle for a driving assistance system. The simulation method is used to simulate the driving control function in the driving assistance system, and the simulation method includes: obtaining actual test data of the target vehicle, the actual test data including the driving parameters of the target vehicle; feeding the actual test data back into the simulation model of the driving control function for simulation; wherein the simulation model processes the driving parameters so that, starting from a first moment, the simulated vehicle in the simulation model continues to travel forward at the speed and direction of the target vehicle at the first moment, the first moment being the moment when the target vehicle triggers the driving control function as recorded in the actual test data. The present disclosure solves the problem of a relatively low triggering rate of the driving control function of the simulated vehicle when using actual test data for feeding back simulation.

Description

Technical Field

[0001] The present disclosure relates to the field of driving assistance technology, and in particular to a simulation method and device for a driving assistance system, a driving assistance system, and a vehicle. Background Art

[0002] Performance testing of vehicle driving control functions is typically accomplished using a re-injection simulation method. This method involves injecting collected actual vehicle driving data into a simulation system to simulate and drive the simulated vehicle within the simulation system, thereby enabling it to make driving decisions such as deceleration and cornering.

[0003] However, the aforementioned recharge simulation method suffers from a relatively low trigger rate in actual testing of driving control functions. In other words, the simulated vehicle is unable to make driving decisions such as slowing down or turning while driving. Summary of the Invention

[0004] In view of this, the embodiments of the present disclosure are directed to providing a simulation method, a simulation device, a driving assistance system, and a vehicle for a driving assistance system. The following describes in detail various aspects of the embodiments of the present disclosure.

[0005] In a first aspect, an embodiment of the present disclosure provides a simulation method for a driving assistance system, wherein the simulation method is used to simulate a driving control function in the driving assistance system, and the simulation method includes: obtaining actual test data of a target vehicle, wherein the actual test data includes driving parameters of the target vehicle; and feeding the actual test data back into a simulation model of the driving control function for simulation; wherein the simulation model processes the driving parameters so that, starting from a first moment, the simulated vehicle in the simulation model continues to travel forward at the speed and direction of the target vehicle at the first moment, wherein the first moment is the moment when the target vehicle triggers the driving control function recorded in the actual test data.

[0006] As a possible implementation method, the driving parameters include one or more of the following: longitudinal speed parameters, lateral angle parameters, and the simulation model processes the driving parameters including: changing the longitudinal speed parameters of the simulated vehicle so that the simulated vehicle continues to move forward from the first moment according to the speed of the target vehicle at the first moment; and / or changing the lateral angle parameters of the simulated vehicle so that the simulated vehicle continues to move forward from the first moment according to the direction of the target vehicle at the first moment.

[0007] As a possible implementation manner, the longitudinal velocity parameter includes a longitudinal acceleration, and the changing of the longitudinal velocity parameter of the simulated vehicle includes: removing the longitudinal acceleration of the simulated vehicle at the first moment.

[0008] As a possible implementation manner, the lateral angle parameter includes a steering wheel angle, and the changing of the lateral angle parameter of the simulated vehicle includes: removing the steering wheel angle of the simulated vehicle at the first moment.

[0009] As a possible implementation, removing the steering wheel angle of the simulated vehicle at the first moment includes: if the steering wheel angle of the target vehicle at the first moment is greater than a first threshold, removing the steering wheel angle of the simulated vehicle at the first moment.

[0010] As a possible implementation manner, the first threshold is greater than or equal to 10 degrees.

[0011] In a second aspect, an embodiment of the present disclosure provides a simulation device for a driving assistance system, wherein the simulation device is used to simulate a driving control function in the driving assistance system, and the simulation device includes: an acquisition module for acquiring actual test data of a target vehicle, wherein the actual test data includes driving parameters of the target vehicle; a simulation module for feeding the actual test data back into a simulation model of the driving control function for simulation; wherein the simulation model processes the driving parameters so that, starting from a first moment, the simulated vehicle in the simulation model continues to travel forward at the speed and direction of the target vehicle at the first moment, and the first moment is the moment when the target vehicle triggers the driving control function recorded in the actual test data.

[0012] In a third aspect, an embodiment of the present disclosure provides a simulation device for a driving assistance system, wherein the simulation device is used to simulate the driving control function in the driving assistance system, and the simulation device includes: a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the computer program is executed by the processor, the steps of any simulation method in the first aspect are implemented.

[0013] In a fourth aspect, an embodiment of the present disclosure provides a driving assistance system, wherein a driving control function in the driving assistance system is implemented by any simulation method in the first aspect.

[0014] In a fifth aspect, an embodiment of the present disclosure provides a vehicle, which includes a driving assistance system, and the driving control function in the driving assistance system is implemented by any simulation method in the first aspect.

[0015] The disclosed embodiment processes the driving parameters in the actual test data so that the simulated vehicle continues to travel forward at the speed and direction at the triggering moment of the driving control function of the target vehicle, thereby avoiding the influence of the driving parameters of the target vehicle on the triggering of the driving control function of the simulated vehicle, thereby improving the trigger rate when the driving control function in the driving assistance system is re-injected simulated using actual test data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is a flow chart of the simulation method of the driving assistance system provided by the embodiment of the present disclosure.

[0017] Figure 2 FIG2 is a schematic diagram of a simulation process of a driving assistance system provided by an embodiment of the present disclosure.

[0018] Figure 3 FIG2 is a schematic diagram of a simulation process of a driving assistance system provided by another embodiment of the present disclosure.

[0019] Figure 4 FIG2 is a schematic structural diagram of a simulation device for a driving assistance system provided by an embodiment of the present disclosure.

[0020] Figure 5 Shown is a structural schematic diagram of a simulation device for a driving assistance system provided by another embodiment of the present disclosure.

[0021] Figure 6 Shown is a schematic structural diagram of a driving assistance system provided by an embodiment of the present disclosure.

[0022] Figure 7 Shown is a schematic structural diagram of a vehicle provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments.

[0024] Driver assistance systems are a significant advancement in modern transportation. They utilize intelligent sensors and advanced algorithms to monitor the vehicle's driving status and surroundings in real time, providing immediate assistance and support to the driver. These systems typically integrate multiple functions, such as emergency braking, lane keeping, and cruise control, helping drivers avoid potential dangers at critical moments and enhancing driving safety.

[0025] For example, Advanced Driver Assistance Systems (ADAS) can acquire environmental data through sensors like cameras and radar. Software and hardware systems then process and analyze this data to identify and assess traffic conditions, such as road, sea, and weather conditions, providing information and driving assistance to the driver. When potential danger is detected, ADAS alerts the driver and can even take proactive intervention measures, such as emergency braking.

[0026] Driver assistance system functions can generally be divided into two categories: driving control functions and non-driving control functions. Non-driving control functions focus on providing information and warnings to the driver to enhance safety and convenience. For example, the Forward Collision Warning (FCW) function detects traffic conditions ahead and warns the driver of potential collision risks in advance, allowing the driver to take timely action. Another example is the Blind Spot Detection (BSD) function, which warns the driver when it detects other vehicles in the blind spot, thereby reducing the risk of lane change accidents.

[0027] The driving control function of a driving assistance system can control the movement of a vehicle, for example, controlling the speed and direction of the vehicle. In other words, the driving control function of a driving assistance system can help the driver better control the vehicle. It should be noted that in addition to controlling the movement of the vehicle, the driving control function of a driving assistance system may also have other auxiliary functions (such as a warning function), which are not limited in the embodiments of the present disclosure.

[0028] The embodiments of the present application do not limit the driving control functions of the driving assistance system. For example, the driving control functions may include the Autonomous Emergency Braking (AEB) function, the Lane Keeping Assist (LKA) function, the Adaptive Cruise Control (ACC) function, and the Automatic Parking Assist (APA) function. It should be noted that in addition to the driving control functions listed above, other driving control functions that can control the driving of a vehicle introduced in future driving assistance systems (such as ADAS) also fall within the scope of protection of this disclosure.

[0029] The AEB function uses sensors such as radar and cameras to detect traffic ahead. If it determines a vehicle is about to approach an obstacle, posing a collision risk, it will alert the driver with an alarm. If the driver fails to react in time, AEB will automatically apply braking, such as deceleration or lateral maneuvering, to help mitigate the severity of the collision or even avoid the accident entirely.

[0030] The LKA function can identify lane markings through a camera and warn the driver or perform driving control when the vehicle unintentionally deviates from the lane. The LKA function usually includes sub-functions such as Lane Departure Warning (LDW), Lane Departure Prevention (LDP) and Lane Centering Control (LCC). These functions can remind the driver through sound, visual or steering wheel vibration, or automatically make slight steering adjustments, such as automatically adjusting the steering wheel, to help the driver keep the vehicle in the center of the lane (or correct its course when a ship is detected to have deviated from its course, or correct its course when an aircraft is detected to have deviated from its flight path).

[0031] The ACC function monitors traffic conditions ahead through radar or cameras, automatically controls the accelerator and brakes to adjust driving speed and maintain a safe distance, thereby reducing the driver's operating burden and improving safety.

[0032] In addition, the APA function can identify suitable parking spaces through ultrasonic sensors or cameras installed around the vehicle body, and automatically control the vehicle's steering, acceleration and braking to achieve precise and safe parking.

[0033] During the development and testing process of the driving assistance system, commonly used testing methods include the re-injection simulation method. The re-injection simulation method involves injecting the actual driving data of a vehicle (such as a vehicle) into a simulation environment to verify and optimize the performance of the driving assistance system. Specifically, the actual collected driving data (sensor data, camera images, GPS information, environmental data, etc.) is input into the simulation system, so that the simulated vehicle equipped with the driving assistance system function to be tested in the simulation system can simulate the driving process of the real vehicle and trigger the corresponding driving assistance function under the drive of the driving data, thereby completing the performance verification and optimization of the driving assistance system. This process simulates the real-world driving scene, allowing engineers and other relevant personnel to conduct detailed analysis and verification of the performance of the driving assistance system in a controlled environment.

[0034] More specifically, in driver assistance system testing, re-injection simulation can be used to detect the triggering of driving control functions under specific conditions, such as emergency braking, lane keeping, adaptive cruise control, and automatic parking, allowing necessary adjustments and optimization of these functions. This approach not only improves test safety but also significantly reduces the time and cost of real-vehicle testing, enabling development and testing teams to quickly iterate and improve the driving control functions of driver assistance systems.

[0035] However, in the above process, the actual driving data injected into the simulation system may include driving behavior data such as vehicle speed, steering wheel angle, ship speed, heading, and airspeed and heading of aircraft, so that the simulated vehicle does not trigger its driving control function under certain conditions, but instead performs corresponding driving controls including emergency braking, lane keeping, adaptive cruise control and automatic parking according to the existing driving behavior (data), resulting in a low triggering rate of the driving control function of the simulated vehicle and poor development and testing performance of the driving assistance system.

[0036] For example, a pure re-injection simulation method is used in the vehicle's AEB function test, that is, the re-injection simulation is performed directly based on actual road test data (i.e., driving data, such as sensor data containing environmental monitoring, as well as road test data such as vehicle speed or steering wheel angle). In this case, the speed of the simulated vehicle's AEB function is consistent with that of the shadow vehicle (the actual vehicle) when it is triggered. Therefore, the simulated vehicle may slow down longitudinally after the AEB function is triggered, resulting in the failure to trigger the simulated vehicle's own AEB function; or, because the shadow vehicle's own triggering time is short, the simulated vehicle may have already performed lateral avoidance with the shadow vehicle within a short period of time after the AEB function is triggered, resulting in the failure to trigger the simulated vehicle's AEB function.

[0037] For example, during a ship's LKA function test, ship navigation data collected during actual navigation (such as speed, heading angle, and environmental data such as ocean currents and wind speeds) is injected into the simulation system. This means that when the simulated ship's LKA function is triggered, the heading angle of the shadow ship (the actual ship) is consistent. Therefore, after triggering the LKA function, the simulated ship may adjust its lateral course to match the shadow ship's, causing the simulated ship's LKA function to fail to trigger.

[0038] For example, during an aircraft's ACC function test, data collected during actual flight (such as position, climate, speed, and attitude) is fed back into the simulation. Because the simulated aircraft's ACC function is triggered at the same speed as the actual aircraft, the simulated aircraft may then follow the actual aircraft's longitudinal deceleration after triggering the ACC adaptive deceleration, resulting in the ACC function failing to trigger.

[0039] For another example, during a vehicle's APA function test, actual parking data (e.g., sensor data, vehicle speed, and steering wheel angle) from a real-world road test is injected into the simulation system. Because the simulated vehicle's operating state is identical to that of the shadow vehicle when the APA function is triggered, the simulated vehicle may park itself after the APA function is triggered (including longitudinal acceleration or deceleration, and / or lateral steering wheel angle), preventing the APA function from being triggered on the simulated vehicle.

[0040] It should be understood that the above examples are merely illustrative and do not limit the application scenarios of driving control functions. For example, AEB can be applied not only to vehicles but also to other vehicles such as ships and aircraft. The same applies to ACC, LKA, and APA, and will not be detailed here.

[0041] To address the problem of a relatively low trigger rate when using actual test data to perform re-injection simulation of the driving control function, the present disclosure proposes a simulation method. This method processes the driving parameters in the actual test data during the re-injection simulation process, so that the simulated vehicle starts from the triggering moment of the driving control function of the target vehicle and continues to move forward at the speed and direction at the triggering moment, thereby avoiding the influence of the driving parameters of the target vehicle on the triggering of the driving control function of the simulated vehicle, thereby improving the trigger rate when using actual test data to perform re-injection simulation of the driving control function in the driving assistance system. The simulation method proposed in the present disclosure can be applied to the re-injection simulation of the driving assistance system, including but not limited to any of the driving control functions mentioned above.

[0042] Figure 1 The following is a flow chart of the simulation method provided by the embodiment of the present disclosure. It should be understood that Figure 1 This is for illustration only, any Figure 1 Simple improvements to the simulation method based on this method fall within the scope of protection of this disclosure. Figure 1 As shown, in step S110 , actual test data of the target vehicle is acquired.

[0043] The target vehicle refers to a physical vehicle. The actual test data collected by the target vehicle can be used by the simulated vehicle in the simulation model. That is, the simulated vehicle can use the actual test data collected by the target vehicle to perform simulations (i.e., re-injection simulations) to test and / or optimize the performance of the driving control function. Therefore, in some embodiments, the target vehicle can also be referred to or understood as a physical vehicle, an actual vehicle, a shadow vehicle of a simulated vehicle, etc.

[0044] In the simulation method provided in the embodiment of the present disclosure, the target vehicle can be equipped with high-quality sensors and data recording equipment to ensure that its driving parameters such as speed, position and driving direction, as well as environmental parameters such as traffic conditions, can be accurately collected, thereby providing real simulation test data and providing accurate environmental input for the simulation model to ensure the authenticity and complexity of the simulation environment, so that the simulation test of the driving control function is closer to the actual driving scenario.

[0045] The embodiments of this disclosure do not limit the implementation of the target vehicle's driving control function. In some embodiments, the target vehicle's driving control function can be manually triggered by the driver. For example, when a driver detects an obstacle ahead while driving on the road, they can manually apply the brakes to implement emergency braking. For another example, the driver can also apply the brakes in time to avoid the obstacle when the AEB function issues a roadblock warning.

[0046] In other embodiments, the target vehicle's travel control module can be proactively triggered to control the vehicle's movement under specific conditions, without the need for manual driver activation. For example, a delivery drone flying over a city could proactively sense buildings and wind speed, adjusting its flight speed in real time to avoid obstacles and maintain efficient and safe flight by optimizing its flight path. Another example is a helicopter equipped with ACC flying at low altitude. If the driver fails to brake in time and suddenly detects an obstacle ahead, the ACC system will immediately sound an alarm and automatically decelerate to avoid a collision and ensure flight safety.

[0047] The embodiments of the present disclosure do not limit the type of target vehicle. In some embodiments, the target vehicle may be a smart driving vehicle specifically used for test data collection. Smart driving vehicles are equipped with various sensors (such as lidar, cameras, ultrasonic sensors, and GPS) to obtain real-time information about the surrounding environment, and they can record large amounts of data (such as motion status, surrounding environment, and traffic conditions) at a high frequency.

[0048] For example, using an intelligent driving data collection vehicle as the target vehicle can obtain information about the surrounding environment in real time during driving, and can also record a large amount of data including speed, steering wheel angle, road conditions, etc. at a high frequency.

[0049] In other embodiments, the target vehicle may have already passed the design and testing phase and entered mass production. For example, production vehicles can collect real, diverse data in real-world driving environments, including driving behavior, vehicle dynamics, and environmental conditions. This data provides rich input for the re-injection simulation, making the simulation results more realistic.

[0050] The disclosed embodiments do not limit the type of target vehicle. In some embodiments, a vehicle can be used as the target vehicle. For example, data from a vehicle traveling on an actual road (including sensor data, driving behavior data, etc.) can provide actual test data for the simulated vehicle in the simulation model.

[0051] Since the navigation data of the ship under different sea conditions (including data such as the ship's position, speed, heading, and surrounding environment) can be used to test the driving control function of the ship's driving assistance system in the recharge simulation, in other embodiments, the ship can also be used as a target vehicle.

[0052] In some other embodiments, an aircraft may be used as a target vehicle. For example, data from the aircraft during actual flight, such as speed, attitude, and external environment data such as wind speed or direction, may be collected to evaluate the performance of its flight (or driving) control system based on re-injection simulation.

[0053] It should be understood that the types of target vehicles listed above are merely illustrative and do not constitute a limitation on the types of target vehicles. Any vehicle that can provide actual test data and be applied to the recharge simulation to test its driving control function can be used as a target vehicle.

[0054] Actual test data refers to detailed information about the vehicle's performance, status, and surrounding environment collected by various sensors, data recording devices, and monitoring systems during the actual operation of the target vehicle. In the disclosed embodiment, the actual test data includes driving parameters and environmental parameters.

[0055] Driving parameters are a series of dynamic data generated by the target vehicle during its travel, reflecting its motion state and performance. In the disclosed embodiments, to more fully describe the driving control performance of the target and simulated vehicles, the driving parameters may further include longitudinal velocity parameters and lateral angle parameters based on the target vehicle's trajectory on a two-dimensional plane.

[0056] The longitudinal velocity parameter refers to the dynamic data generated when the target vehicle is traveling along its main direction of travel, such as the speed and acceleration generated when the vehicle is traveling forward.

[0057] The lateral angle parameter refers to the dynamic data generated when the target vehicle has a rotation angle on a plane relative to its main direction of travel, and can be used to indicate the lateral (i.e., sideways) deflection of the target vehicle. For example, the angle between the projection of the vehicle's forward direction on the ground and the north direction (or other reference direction, such as the center angle of the road) is the heading angle (Heading Angle); for another example, the lateral offset or slippage of a ship relative to its longitudinal axis (centerline of the hull) during navigation is the sideslip angle (Sideslip Angle); for another example, the yaw angle (Yaw Angle), which is the rotation angle of the vehicle around its vertical axis (Z axis), that is, the deflection of the vehicle's head relative to its initial or desired direction. Among them, compared with the heading angle, the yaw angle focuses more on the dynamic rotation of the vehicle body.

[0058] In addition to driving parameters, in the embodiments of the present disclosure, the actual test data also includes environmental parameters. Environmental parameters refer to external environmental information related to the actual operation of the target vehicle in a specific scenario. In some embodiments, environmental parameters may include road conditions, such as road surface type, roughness, and friction coefficient. In other embodiments, environmental parameters may also include traffic conditions, such as traffic density, flow, etc. In some other embodiments, environmental parameters may also include meteorological parameters, such as temperature, humidity, wind speed, and precipitation. The embodiments of the present disclosure do not limit the specific content of the environmental parameters. As long as it is external environmental information that affects the driving control function of the target vehicle, it is within the scope of the present disclosure.

[0059] The disclosed embodiments do not limit the source of actual test data. In some embodiments, the actual test data may come from a variety of sensors of the target vehicle. For example, real-time position data may be obtained based on GPS, and speed and acceleration components in two or three dimensions may be obtained using an inertial measurement unit (IMU), as well as environmental parameters recorded by cameras and radars. In other embodiments, the actual test data may also come from external data sources. For example, road and traffic data may also be obtained through road sensors and traffic detection systems.

[0060] Based on the unlimited source of actual test data, the embodiments of the present disclosure do not limit the method for obtaining actual test data. In some embodiments, actual test data can be collected by various sensors on the target vehicle and stored or transmitted through a related (e.g., on-board) computing platform. In other embodiments, real-time and historical data can also be obtained through cooperation with meteorological services and traffic management departments.

[0061] The actual test data obtained based on one or more of the above acquisition methods can be used directly in the embodiments of the present disclosure, or can be processed and analyzed using data analysis tools to improve the reliability and accuracy of the data.

[0062] After obtaining the actual test data of the target vehicle, such as Figure 1 As shown, in step S120, the actual test data is fed back into the simulation model of the driving control function for simulation.

[0063] By simulating actual driving scenarios and target vehicle behaviors, simulation models allow engineers and other relevant personnel to reproduce and analyze data from actual driving in a virtual environment to evaluate and optimize the performance and safety of driver assistance systems while reducing the risks and costs of actual testing.

[0064] In the disclosed embodiments, the simulation model includes at least a dynamics model for simulating the physical motion of the target vehicle, such as speed, acceleration, and steering response, as well as a control and decision-making model that reflects the core logic of the driver assistance system and performs driving control functions. Furthermore, the disclosed embodiments may also include a sensor model for simulating the behavior of sensors such as cameras, lidar, and millimeter radar waves to generate perception data similar to the real world; an environmental model that provides realistic background information, including road (or route), traffic, and weather; and a traffic flow model that simulates the dynamic behavior of surrounding vehicles and pedestrians to reproduce complex traffic scenes.

[0065] In step S120, after the actual test data is fed back into the simulation model, the simulated vehicle's performance in the virtual environment is observed, and the relevant data and test results are recorded. These test results are used to evaluate the performance of the driving assistance system's ride control function, including responsiveness, response time, stability, and safety. If the test results do not meet expectations, the ride control function may require further adjustment and optimization.

[0066] In the disclosed embodiment, the simulation model can process the driving parameters in the actual test data so that starting from the first moment, the simulated vehicle in the simulation model continues to move forward at the speed and direction of the target vehicle at the first moment.

[0067] The first moment refers to the moment when the target vehicle triggers the driving control function as recorded in the actual test data, i.e., the triggering moment. For example, in an AEB function test of a simulated vehicle, the first moment refers to the moment when the emergency braking function of the target vehicle is triggered.

[0068] It should be understood that, starting from the first moment, the simulated vehicle will continue to move forward at the speed and direction of the target vehicle (or itself) at the first moment. For example, during an AEB functional test, starting from the first moment, the simulated vehicle does not substantially decelerate according to the driving parameters of the target vehicle and continues to move forward according to the motion state of the target vehicle (or itself) at the first moment. For another example, during an AEB functional test, starting from the first moment, the simulated vehicle does not turn according to the driving parameters of the target vehicle and continues to move forward in the direction of the target vehicle (or itself) at the first moment.

[0069] In some embodiments, starting from the first moment, the simulated vehicle continues to travel forward at the speed and direction of the target vehicle at the first moment. This can also be understood as starting from the first moment, the simulated target vehicle no longer continues to travel according to the driving parameters of the target vehicle, but instead travels according to the driving parameters of the target vehicle at the first moment. In this way, the simulated vehicle and the target vehicle may separate after the first moment. For example, the target vehicle decelerates but does not turn after the first moment, while the simulated vehicle does not decelerate after the first moment, or does not decelerate but turns, or the deceleration of the two vehicles is inconsistent, etc.

[0070] It should be noted that the phrase "starting from the first moment" mentioned in the embodiments of the present disclosure is not intended to emphasize the length of a period of time after the first moment, but rather to emphasize that starting from the first moment, the simulated vehicle no longer maintains the same driving parameters as the target vehicle. For example, a short period of time after the first moment, the simulated vehicle continues to move forward at the speed and direction of the target vehicle at the first moment, but after this short period of time, the simulated vehicle triggers a driving control function. In this case, the simulated vehicle will take measures such as deceleration and / or steering to control its driving. That is, after a short period of time, the simulated vehicle will no longer continue to move forward at the speed and direction of the first moment, but will make its own driving decisions.

[0071] The determination of the first moment usually involves a series of conditions based on driving parameters and environmental parameters, and the first moment refers to the specific time point when the condition is met. The embodiments of the present disclosure do not limit the specific conditions. In some embodiments, the condition may be that the speed reaches a certain value and the distance between the simulated vehicle and the obstacle is shortened to below a safety threshold. For example, the relevant department has set up an overspeed AEB function system for autonomous driving vehicles traveling on highways. When the actual speed of the vehicle exceeds the set maximum speed limit, such as 120 kilometers per hour, the moment is the first moment. In the recharge simulation, once the speed of the simulated vehicle reaches or exceeds the threshold, the system will take emergency braking.

[0072] In other embodiments, the determination condition may also be a change in any other parameter related to driving behavior and safety. For example, in urban traffic, if a vehicle's sensors detect that the distance to a preceding obstacle is less than a safe distance (e.g., 3 meters at a speed of 30 km / h), the moment the actual distance falls below this threshold is the trigger moment, also known as the first moment. In simulation testing, when the distance between the simulated vehicle and the preceding obstacle reaches or falls below 3 meters, the AEB system is triggered, applying emergency braking to avoid or mitigate a collision.

[0073] In an embodiment of the present disclosure, the processing of driving parameters by the simulation model may include changing the driving parameters of the simulated vehicle, for example, changing the driving parameters of the simulated vehicle after the first moment. In some embodiments, changing the driving parameters of the simulated vehicle includes changing the longitudinal speed parameters of the simulated vehicle so that the simulated vehicle continues to move forward at the speed of the target vehicle at the first moment starting from the first moment. As an example, after the ACC function of the aircraft is triggered, the flight speed of the simulated aircraft is changed so that the simulated aircraft flies forward at the speed at the moment when the ACC function is triggered. As another example, if Figure 2 As shown in Figure 2, before the AEB function of the vehicle is triggered (at time T0), the speed of the simulated vehicle (V0_n) is the same as the speed of the actual vehicle (V0_s), that is, V0_n=V0_s, and the motion states of the two are exactly the same, as shown in Figure 2. Figure 2 As shown in the figure, at time T0, the simulated vehicle and the actual vehicle completely overlap. Starting from the moment the AEB function is triggered (i.e., time T1), the actual vehicle decelerates and its speed is V1_s; while the simulated vehicle still maintains its (or the actual vehicle's) speed at time T1 (V1_n) and continues to move forward. In other words, starting from time T1, the speed of the simulated vehicle is greater than the speed of the actual vehicle (V1_n>V1_s), that is, Figure 2 As shown, starting from time T1, the simulated vehicle and the actual vehicle body begin to separate.

[0074] In other embodiments, changing the driving parameters of the simulated vehicle may include changing the lateral angle parameters of the simulated vehicle so that the simulated vehicle continues to move forward in the direction of the target vehicle at the first moment. As an example, after the LKA function of a ship is triggered, the course angle of the simulated ship is changed so that the simulated ship continues to sail forward according to the course angle at the time of LKA triggering. As another example, Figure 3 As shown in Figure 2, before the AEB function of the vehicle is triggered (at time T0), the steering wheel angle (SW0_n) of the simulated vehicle is the same as the steering wheel angle (SW0_s) of the actual vehicle, that is, SW0_n=SW0_s, and the driving directions of the two are exactly the same, as shown in Figure 2. Figure 3As shown in the figure, at time T0, the simulated vehicle and the actual vehicle completely overlap. Starting from the moment the AEB function is triggered (i.e., time T1), the actual vehicle performs a turning (obstacle avoidance) operation, and its steering wheel angle is SW1_s; while the simulated vehicle does not perform a turning operation, and maintains its (or the actual vehicle's) driving direction at time T1 (SW1_n) and continues to move forward. In other words, starting from time T1, the steering wheel angle of the simulated vehicle is not equal to the steering wheel angle of the actual vehicle (SW1_n≠SW1_s), that is, Figure 3 As shown, starting from time T1, the simulated vehicle and the actual vehicle body begin to separate.

[0075] In some other embodiments, changing the driving parameters of the simulated vehicle may include changing the longitudinal speed parameters of the simulated vehicle so that the simulated vehicle continues to travel forward at the speed of the target vehicle at the first moment, and may also include changing the lateral angle parameters of the simulated vehicle so that the simulated vehicle continues to travel forward at the direction of the target vehicle at the first moment. For example, when the APA function of the vehicle is triggered, the speed and direction of the simulated vehicle are changed so that the simulated vehicle continues to travel forward at the speed and direction at the time the APA function is triggered. For another example, when the AEB function of the vehicle is triggered, the speed and direction of the simulated vehicle are changed so that the simulated vehicle continues to travel forward at the speed and direction at the time the AEB function is triggered.

[0076] In some embodiments, modifying the longitudinal velocity parameter of the simulated vehicle may involve removing the longitudinal acceleration of the simulated vehicle at the first moment, causing the simulated vehicle to continue traveling forward at the speed at the first moment. This prevents the longitudinal velocity parameter from influencing the triggering of the simulated vehicle's travel control functions, thereby improving the triggering rate of the travel control functions in the driver assistance system when using actual test data for re-injection simulation. As an example, the longitudinal acceleration of the simulated vehicle at the first moment may be removed, causing the simulated vehicle to continue traveling forward at a constant speed at the speed at the first moment.

[0077] As another example, after removing the longitudinal acceleration of the simulated vehicle at the first moment, the simulated vehicle's speed is allowed to fluctuate around the baseline speed at the first moment or at a certain historical moment (during normal driving) to simulate real-world factors such as uneven roads, changes in wind resistance, and slight adjustments to driving maneuvers. As a further example, after the first moment, the vehicle maintains a baseline speed of 60 km / h while allowing a speed variation of ±5 km / h to reflect slight acceleration or deceleration that may be encountered in actual driving.

[0078] In other embodiments, changing the longitudinal speed parameter of the simulated vehicle at the first moment may be changing the speed of the simulated vehicle at the first moment. For example, the speed of the simulated vehicle at the first moment may be changed to the average speed before the first moment (which may include or exclude the first moment), or to the average speed of a certain historical driving time period, or to the instantaneous speed at the first moment. In this way, the speed of the simulated vehicle and the target vehicle after the first moment is different, and the simulated vehicle can maintain its own speed, which is conducive to the simulation model triggering the driving control function.

[0079] Correspondingly, in the disclosed embodiment, changing the lateral angle parameter of the simulated vehicle at the first moment may be changing the steering wheel angle of the simulated vehicle at the first moment, so that the simulated vehicle continues to travel forward in the direction of travel at the first moment from the first moment, thereby avoiding the influence of the lateral angle parameter on the triggering of the driving control function of the simulated vehicle, thereby improving the triggering rate when the driving control function in the driving assistance system is re-injected using actual test data. In some embodiments, the steering wheel angle after the first moment can be modified to 0, that is, the steering wheel angle of the simulated vehicle after the first moment can be removed.

[0080] It should be understood that the embodiment of the present disclosure is intended to change the driving parameters of the simulated vehicle after the first moment to avoid the influence of the driving parameters on the triggering of the driving control function in the re-injection simulation test. Therefore, the present disclosure does not limit its specific changing method. As long as it meets the above purpose, it is within the scope of the present disclosure.

[0081] In the disclosed embodiment, the driving parameters at the first moment can be modified based on a relevant algorithm. For example, when the AEB function of the simulated vehicle is triggered, if the longitudinal acceleration of the simulated vehicle is not zero, the longitudinal acceleration is changed to zero. As another example, when the AEB function of the simulated vehicle is triggered, if the steering wheel angle of the simulated vehicle is greater than or equal to a first threshold (for details on the setting of the first threshold, see below), the steering wheel angle is changed to zero.

[0082] In actual driving, the steering wheel angle may change due to a variety of factors. For example, the driver (or a driving assistance system) may change the vehicle's direction of travel or perform obstacle avoidance maneuvers by turning the steering wheel. To address this situation where the target vehicle's steering wheel angle changes after the first moment, the disclosed embodiment changes the simulated vehicle's steering wheel angle at the first moment so that the simulated vehicle continues to travel in the direction of the first moment.

[0083] However, based on responses to external conditions, such as lane keeping, crosswind, or uneven road surface, the driver (or driving assistance system) may need to correct the driving direction of the target vehicle by adjusting the steering wheel.

[0084] Typically, when a driver (or a driver assistance system) needs to change the vehicle's direction, such as to turn or avoid an obstacle, they will make a large steering wheel movement, resulting in a large steering wheel angle. This angle is often larger than the angle used by the driver (or driver assistance system) to make fine adjustments to the vehicle.

[0085] As an example, when performing an obstacle avoidance maneuver, the driver may need to turn the steering wheel quickly and significantly to steer around a sudden obstacle. In contrast, the LKA or LCC functions may make smaller steering wheel adjustments to help the vehicle stay in or center its lane, and these adjustments are typically smaller, resulting in smaller steering wheel angles.

[0086] Based on this, in the simulation method proposed in the embodiment of the present disclosure, when the steering wheel angle of the target vehicle at the first moment is greater than or equal to the first threshold, the steering wheel angle of the simulated vehicle at the first moment is removed, thereby avoiding erroneous removal of the necessary steering wheel angle at the first moment.

[0087] According to relevant research and statistics, the distribution of steering wheel angles exhibits certain regularities. For example, one study indicates that when a vehicle is driving in a straight line, the driver constantly makes minor adjustments to maintain the vehicle's direction, and most of these minor adjustments correspond to steering wheel angles within 10 degrees. This means that if the steering wheel angle exceeds this value, especially reaching 10 degrees, it may indicate that the driver is making more significant directional adjustments, such as obstacle avoidance maneuvers.

[0088] Based on this, in the disclosed embodiment, the first threshold can be set to 10 degrees. When the target vehicle's steering wheel angle at the first moment is less than this threshold, it can be assumed that the target vehicle is performing normal route keeping or slight directional adjustments, and its steering wheel angle does not need to be removed. However, when the target vehicle's steering wheel angle at the first moment reaches or exceeds 10 degrees, it may be assumed that the driver is performing an emergency obstacle avoidance maneuver, in which case the steering wheel angle needs to be removed.

[0089] For ease of understanding, the following takes the AEB function of a vehicle as an example to describe in detail the simulation method for improving the triggering rate of the emergency braking function in the driving assistance function proposed in the embodiment of the present disclosure.

[0090] The high-quality sensors and data recording equipment equipped on the intelligent driving data collection vehicle collect driving parameters such as speed (including speed changes) and direction (including direction changes), as well as environmental parameters such as traffic conditions. Furthermore, data analysis tools are used to process and analyze the collected driving parameters. These analyzed parameters are then fed back into the simulation model.

[0091] In Test 1, the intelligent driving vehicle decelerated in its driving direction at time T1, using AEB. However, the simulation vehicle, having eliminated its deceleration parameters at T1, did not decelerate. At T1, the vehicle's body completely overlapped with the intelligent driving vehicle's. After T1, the two vehicles gradually separated. Specifically, the two vehicles continued to travel in the same direction, but the intelligent driving vehicle was in front, and the simulation vehicle was behind.

[0092] In Test 2, the intelligent driving vehicle automatically turned the steering wheel at T2 based on AEB, generating a steering wheel angle, and the vehicle's driving direction changed accordingly (turning right after T2). However, the simulation vehicle detected that the steering wheel angle was greater than 10 degrees at T2, so the simulation vehicle erased the steering wheel angle parameter and its driving direction did not change. At T2, the simulation vehicle completely overlapped with the intelligent driving vehicle's body, and after T2, the two bodies gradually separated. Specifically, the two remained basically consistent in the longitudinal direction, but in the transverse direction, the simulation vehicle was on the left and the intelligent driving vehicle was on the right.

[0093] The method embodiment of the present disclosure is described in detail above, and the device embodiment of the present disclosure is described in detail below. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment, so that what is not described in detail can be referred to the previous method embodiment.

[0094] like Figure 4 As shown in FIG, it is a schematic diagram of a simulation device of a driving assistance system according to an embodiment of the present disclosure. Figure 4 As shown, the simulation device 400 includes an acquisition module 410 for acquiring actual test data of the target vehicle, the actual test data including driving parameters of the target vehicle; the simulation device 400 also includes a simulation module 420 for feeding the actual test data back into the simulation model of the driving control function for simulation; wherein, the simulation model processes the driving parameters so that starting from the first moment, the simulated vehicle in the simulation model continues to move forward at the speed and direction of the target vehicle at the first moment, and the first moment is the moment when the target vehicle triggers the driving control function recorded in the actual test data.

[0095] like Figure 5 As shown in FIG, it is a schematic diagram of a simulation device of a driving assistance system according to an embodiment of the present disclosure. Figure 5As shown, the simulation device 500 includes: a memory 510 and a processor 520. The memory 510 stores a computer program that can be run on the processor 520. When the computer program is executed by the processor 520, Figure 1 Steps of the simulation method.

[0096] like Figure 6 As shown in FIG, it is a schematic diagram of the driving assistance system of the embodiment of the present disclosure. Figure 6 As shown, the driving control function in the driving assistance system 600 is implemented by the simulation device 400 .

[0097] like Figure 7 As shown in FIG, it is a schematic diagram of a vehicle according to an embodiment of the present disclosure. Figure 7 As shown, vehicle 700 includes driver assistance system 600 .

[0098] It should be understood that in the embodiments of the present disclosure, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0099] It should be understood that the term "and / or" as used herein simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " as used herein generally indicates that the related objects are in an "or" relationship.

[0100] It should be understood that in the various embodiments of the present disclosure, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0101] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. On the other hand, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0102] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0103] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD), or a semiconductor medium (e.g., a solid state disk (SSD), etc.).

[0104] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be based on the scope of protection of the claims.

Claims

1. A simulation method for a driving assistance system, characterized in that: The simulation method is used to simulate the driving control function in the driving assistance system, and the simulation method includes: Acquiring actual test data of a target vehicle, wherein the actual test data includes driving parameters of the target vehicle; Feeding the actual test data back into the simulation model of the driving control function for simulation; In which, the simulation model processes the driving parameters so that starting from the first moment, the simulated vehicle in the simulation model continues to move forward according to the speed and direction of the target vehicle at the first moment, and the first moment is the moment when the target vehicle triggers the driving control function recorded in the actual test data.

2. The method according to claim 1, characterized in that The driving parameters include one or more of the following: longitudinal speed parameters, lateral angle parameters, and the simulation model processes the driving parameters including: Changing the longitudinal speed parameter of the simulated vehicle so that the simulated vehicle continues to move forward at the speed of the target vehicle at the first moment starting from the first moment; and / or The lateral angle parameter of the simulated vehicle is changed so that the simulated vehicle continues to move forward according to the direction of the target vehicle at the first moment starting from the first moment.

3. The method according to claim 2, characterized in that The longitudinal velocity parameter includes a longitudinal acceleration, and the changing of the longitudinal velocity parameter of the simulated vehicle includes: The longitudinal acceleration of the simulated vehicle at the first moment is removed.

4. The method according to claim 2, characterized in that The lateral angle parameter includes a steering wheel angle, and the changing of the lateral angle parameter of the simulated vehicle includes: The steering wheel angle of the simulated vehicle at the first moment is removed.

5. The method according to claim 4, characterized in that The removing of the steering wheel angle of the simulated vehicle at the first moment includes: If the steering wheel angle of the target vehicle at the first moment is greater than or equal to a first threshold, the steering wheel angle of the simulated vehicle at the first moment is removed.

6. The method according to claim 5, characterized in that The first threshold is greater than or equal to 10 degrees.

7. A simulation device for a driving assistance system, characterized in that: The simulation device is used to simulate the driving control function in the driving assistance system, and the simulation device includes: an acquisition module, configured to acquire actual test data of a target vehicle, wherein the actual test data includes driving parameters of the target vehicle; A simulation module, configured to feed the actual test data back into the simulation model of the driving control function for simulation; In which, the simulation model processes the driving parameters so that starting from the first moment, the simulated vehicle in the simulation model continues to move forward according to the speed and direction of the target vehicle at the first moment, and the first moment is the moment when the target vehicle triggers the driving control function recorded in the actual test data.

8. A simulation device for a driving assistance system, characterized in that: The simulation device is used to simulate the driving control function in the driving assistance system. The simulation device includes: a memory and a processor. The memory stores a computer program that can be run on the processor. When the computer program is executed by the processor, the steps of the simulation method as described in any one of claims 1 to 6 are implemented.

9. A driving assistance system, characterized in that: The driving control function in the driving assistance system is implemented by the simulation method according to any one of claims 1 to 6.

10. A means of transport, characterized in that: The vehicle includes a driving assistance system, and a driving control function in the driving assistance system is implemented by the simulation method according to any one of claims 1 to 6.

Images