Lateral control method and apparatus, and vehicle

Abstract

A lateral control method and apparatus, and a vehicle, which are applicable to the field of intelligent driving. The method comprises: acquiring real-time lateral information; on the basis of the real-time lateral information and a plurality of lateral parameters, determining a plurality of predicted trajectories; and on the basis of the plurality of predicted trajectories, determining whether or not to trigger a lateral active safety function. The method can be applied to intelligent vehicles or electric vehicles and helps improve the accuracy of the triggering timing of lateral active safety functions, thereby contributing to an enhanced driving experience for users.

Description

Lateral control method, device and vehicle

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on March 19, 2024, with application number 202410318412.3 and application name “Lateral Control Method, Device and Vehicle”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving, and more specifically, to a lateral control method, device and vehicle. Background Art

[0003] In recent years, active safety features have been applied in more and more vehicles. Active safety features are designed to take proactive judgments and safety measures in emergency situations before the driver's subjective reaction, thereby significantly reducing road traffic accidents and related casualties. Such features are of great significance in active driving safety. For example, the lateral active safety function can help correct the driving route when the vehicle gradually deviates from the lane or there is a risk of a side collision. Compared with longitudinal deceleration and parking, the driver's overall driving experience will be more comfortable and safe. If the lateral active safety function is triggered too early, it may go against the driver's driving intention; if the lateral active safety function is triggered too late, it may cause the vehicle to cause an accident. Therefore, how to improve the accuracy of the triggering timing of the lateral active safety function has become an urgent problem to be solved. Summary of the Invention

[0004] The present application provides a lateral control method, device, and vehicle, which help improve the accuracy of the triggering timing of the lateral active safety function, thereby helping to improve the user's driving experience.

[0005] In a first aspect, the present application provides a lateral control method, which includes: obtaining real-time lateral information; determining multiple predicted trajectories based on the real-time lateral information and multiple lateral parameters; and determining whether to trigger a lateral active safety function based on the multiple predicted trajectories.

[0006] Based on the above technical solution, the vehicle can generate multiple predicted trajectories for the driver over the next period of time based on real-time lateral information and multiple lateral parameters. Based on these multiple predicted trajectories, the vehicle can then determine whether to trigger the lateral active safety function. This decision based on multiple predicted trajectories can improve the vehicle's accuracy in determining whether to trigger the lateral active safety function, thereby enhancing the user's driving experience.

[0007] In some possible implementations, determining a plurality of predicted trajectories may also be understood as determining the trajectory of the driver when driving the vehicle within a period of time in the future.

[0008] In some possible implementations, before determining multiple predicted trajectories based on the real-time lateral information and multiple lateral parameters, the method also includes: determining that the vehicle is in one of the following scenarios: a sharp turn, an emergency lane change, accidental accelerator pedal depression, or sudden steering wheel movement.

[0009] Current lateral active safety features primarily rely on vehicle model prediction lines or safe reachable set predictions, which have limited scalability scenarios. The vehicle's performance tends to be conservative in scenarios such as sharp turns, emergency lane changes, accidental accelerator pedal activation, and sudden steering. This means that as long as the vehicle is in these scenarios, the lateral active safety feature is easily triggered. Frequent triggering of the lateral active safety feature can result in a poor user experience. Furthermore, the current solution cannot protect against aggressive and abnormal driver operations, and lacks interpretability, making it impossible to adjust for differences in whether the lateral active safety feature is engaged or not.

[0010] Based on the above technical solution, in some special scenarios, multiple predicted trajectories of the driver driving the vehicle in the future can be obtained through the vehicle's real-time lateral information and multiple lateral parameters. This allows the vehicle to judge whether to trigger the lateral active safety function based on multiple predicted trajectories in these special scenarios, which helps to improve the vehicle's accuracy in triggering the lateral active safety function in these special scenarios, effectively avoids false triggering of the lateral active safety function resulting in a poor user experience, and can also avoid safety risks caused by late triggering of the lateral active safety function, helping to improve the user's driving experience.

[0011] In the embodiment of the present application, by considering and integrating the multimodal prediction and decision-making process of the driver's real-time lateral actions, it is not only possible to ensure the regulatory test scenarios based on active safety, but also to adapt to different scenarios and directions during the generalization process of the actual vehicle.

[0012] In some possible implementations, the multiple lateral parameters may be information pre-stored in the vehicle, or may be obtained by the vehicle from a cloud server via over-the-air technology, or may be determined by the vehicle based on the user's historical driving information.

[0013] In some possible implementations, the method further includes: acquiring first configuration information from the plurality of configuration information, where the first configuration information includes the plurality of horizontal parameters.

[0014] Based on the above technical solution, different driving styles and lateral action levels can be embedded into the overall decision-making solution, which can enable more differentiated interpretations in the evaluation and make the decision-making process more flexible.

[0015] Exemplary lateral active safety features include lateral obstacle collision prevention (LOCP). For example, when the vehicle deviates from its current lane and is at risk of colliding with obstacles such as lateral barriers, fences, or rubbing against obstacles in front of it, the system can assist the driver by turning the steering wheel to avoid or mitigate the collision risk.

[0016] For example, the lateral active safety function can also be an autonomous emergency steering (AES) function. For example, if the driver engages in dangerous driving behavior and the active braking function cannot stop the vehicle to avoid an obstacle, the vehicle can achieve emergency obstacle avoidance through front wheel steering, or through front wheel steering and direct yaw torque.

[0017] For example, the lateral active safety function may be an emergency lane keeping assist (ELKA) function. For example, when the vehicle deviates from its current lane and is at risk of colliding with another vehicle or running off the road boundary, the emergency driver-assistant steering wheel turns to avoid and mitigate the collision risk.

[0018] In combination with the first aspect, in certain implementations of the first aspect, the real-time lateral information includes a first steering wheel angle, and the multiple lateral parameters include multiple angle change rates, wherein the multiple predicted trajectories are determined based on the real-time lateral information and the multiple lateral parameters, including: determining multiple curvatures based on the first steering wheel angle and the multiple angle change rates; and determining the multiple predicted trajectories based on the multiple curvatures.

[0019] Based on the above technical solution, the vehicle can determine multiple curvatures based on the real-time steering wheel angle and multiple steering angle change rates. Based on these multiple curvatures, the vehicle can then determine multiple predicted trajectories for the driver's driving over a period of time. This allows the vehicle to determine whether to trigger the lateral active safety function based on multiple predicted trajectories, improving the vehicle's accuracy in determining whether to trigger the function and thus enhancing the user's driving experience.

[0020] In some possible implementations, multiple curvatures are determined based on the first turning angle and the multiple turning angle change rates; and the multiple predicted trajectories are determined based on the multiple curvatures, including: determining the multiple curvatures based on the first turning angle, a first reaction time (TTR) and the multiple turning angle change rates.

[0021] In some possible implementations, the first TTR may be determined by a time to collision (TTC) between the vehicle and the obstacle.

[0022] Exemplarily, the first TTR is the product of the TTC and a first value, where the first value is greater than 0 and less than 1.

[0023] In some possible implementations, the multiple lateral parameters include a first turning angle change rate range, and multiple predicted trajectories are determined based on the real-time lateral information and the multiple lateral parameters, including: determining multiple curvatures based on the first turning angle and the first turning angle change rate range.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the real-time lateral information includes a first steering wheel angle and a first steering wheel angle change rate, and the multiple lateral parameters include multiple time lengths, wherein the multiple predicted trajectories are determined based on the real-time lateral information and the multiple lateral parameters, including: determining the first heading angle of the vehicle based on the first TTR and the first steering wheel angle change rate, the first TTR being determined by the collision time TTC between the vehicle and the obstacle; determining the multiple steering wheel angle change rates based on the first steering wheel angle and the multiple time lengths; determining the multiple curvatures based on the first steering wheel angle and the multiple steering wheel angle change rates; and determining the multiple predicted trajectories based on the multiple curvatures.

[0025] Based on the above technical solution, multiple curvatures can be determined based on the real-time steering wheel angle, angle change rate, and multiple time periods, thereby generating multiple predicted trajectories. By using multiple predicted trajectories to determine whether to trigger the lateral active safety function, the vehicle's accuracy in determining whether to trigger the function can be improved, thereby enhancing the user's driving experience.

[0026] In some possible implementations, the multiple time periods may be determined based on user settings, or may also be determined based on the user's historical driving information.

[0027] In combination with the first aspect, in certain implementations of the first aspect, determining the multiple predicted trajectories based on the multiple curvatures includes: determining the lateral offset distance corresponding to each of the multiple curvatures based on the multiple curvatures; determining the multiple predicted trajectories based on the multiple curvatures and the lateral offset distance corresponding to each curvature.

[0028] Based on the above technical solution, after obtaining multiple curvatures, the vehicle can predict the vehicle's trajectory within the driver's reaction time within a period of time. The trajectory within the driver's reaction time is then smoothed to obtain a smoothed trajectory. In this way, the trajectory within the driver's reaction time and the smoothed trajectory can form the predicted trajectory.

[0029] In some possible implementations, the method further includes: determining a trajectory corresponding to static road perception and a trajectory corresponding to regression compensation based on road structure information; and determining a predicted trajectory based on the trajectory within the driver's reaction time, the smooth trajectory, the trajectory corresponding to static road perception, and the trajectory corresponding to regression compensation.

[0030] In combination with the first aspect, in certain implementations of the first aspect, before determining multiple predicted trajectories based on the real-time lateral information and the multiple lateral parameters, the method also includes: controlling the display device to display a first interface, the first interface including multiple gear information, the multiple gear information corresponding to multiple configuration information respectively, and the lateral parameters included in each of the multiple configuration information are different; according to the user's input for the first gear, obtaining first configuration information from the multiple configuration information, the first gear is associated with the first configuration information, and the first configuration information includes the multiple lateral parameters.

[0031] Exemplarily, the multiple configuration information includes first configuration information and second configuration information, the angle change rate included in the first configuration information is in the range of [1.0rad / s, 1.5rad / s], and the angle change rate included in the second configuration information is (1.5rad / s, 2.0rad / s].

[0032] Based on the above technical solution, users can set their preferred driving style or gear position (e.g., conservative, moderate, or aggressive) through the vehicle's display. Different style preferences or gear positions can correspond to different lateral parameters. This allows the vehicle to determine multiple predicted trajectories based on the user's settings and real-time lateral information while the driver is controlling the vehicle. By integrating different drivers' driving styles and lateral parameters into the overall decision-making solution, the evaluation can be explained by more differences, making the vehicle's decision-making process more flexible and accurate.

[0033] In combination with the first aspect, in certain implementations of the first aspect, before determining multiple predicted trajectories based on the real-time lateral information and the multiple lateral parameters, the method also includes: obtaining the user's historical driving information; and determining the multiple lateral parameters based on the historical driving information.

[0034] Based on the above technical solution, the vehicle can determine multiple lateral parameters based on the user's historical driving information. This can make the multiple lateral parameters stored in the vehicle more consistent with the user's driving style preferences, helping to improve the vehicle's accuracy in determining whether to trigger lateral active safety functions.

[0035] In combination with the first aspect, in certain implementations of the first aspect, the lateral active safety function includes a lateral collision avoidance function, and determining whether to trigger the lateral active safety function based on the multiple predicted trajectories includes: when the collision risk between the first predicted trajectory among the multiple predicted trajectories and the obstacle does not meet the preset collision condition, determining not to trigger the lateral collision avoidance function; or, when, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not meet the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle meets the preset collision condition, determining not to trigger the lateral collision avoidance function.

[0036] Based on the above technical solution, when there is no collision risk or the collision risk is low between a predicted trajectory among multiple predicted trajectories and an obstacle, the lateral collision avoidance function may not be triggered; alternatively, when the collision risk between most of the predicted trajectories among multiple predicted trajectories and an obstacle is low, the lateral collision avoidance function may not be triggered.

[0037] In combination with the first aspect, in certain implementations of the first aspect, the lateral active safety function includes a lateral collision avoidance function, and determines whether to trigger the lateral active safety function based on the multiple predicted trajectories, including: when the collision risk between each predicted trajectory in the multiple predicted trajectories and the obstacle meets a preset collision condition, determining to trigger the lateral collision avoidance function and controlling the prompt device to prompt the user that there is a risk in the current lateral action.

[0038] Based on the above technical solution, when the vehicle triggers the side collision avoidance function, the prompt device can remind the user that the current lateral action is risky, which can enhance the driver's attention.

[0039] In combination with the first aspect, in certain implementations of the first aspect, determining whether to trigger the lateral active safety function based on the multiple predicted trajectories includes: determining the vehicle's driving space in a future period of time based on the multiple predicted trajectories; and determining whether to trigger the lateral active safety function based on the collision risk between the driving space and the obstacle.

[0040] In a second aspect, the present application provides a lateral control device, which includes: an acquisition unit for acquiring real-time lateral information; a determination unit for determining multiple predicted trajectories based on the real-time lateral information and multiple lateral parameters; the determination unit is also used to determine whether to trigger the lateral active safety function based on the multiple predicted trajectories.

[0041] In combination with the second aspect, in certain implementations of the second aspect, the real-time lateral information includes a first steering wheel angle, the multiple lateral parameters include multiple angle change rates, and the determination unit is specifically used to: determine multiple curvatures based on the first angle and the multiple angle change rates; and determine the multiple predicted trajectories based on the multiple curvatures.

[0042] In combination with the second aspect, in certain implementations of the second aspect, the real-time lateral information includes a first steering wheel angle and a first steering wheel angle change rate, the multiple lateral parameters include multiple time lengths, and the determination unit is specifically used to: determine the first heading angle of the vehicle based on the first TTR and the first steering wheel angle change rate, the first TTR being determined by the collision time TTC between the vehicle and the obstacle; determine multiple steering wheel angle change rates based on the first steering wheel angle and the multiple time lengths; determine multiple curvatures based on the first steering wheel angle and the multiple steering wheel angle change rates; and determine the multiple predicted trajectories based on the multiple curvatures.

[0043] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is specifically used to: determine, based on the multiple curvatures, a lateral offset distance corresponding to each of the multiple curvatures; and determine the multiple predicted trajectories based on the multiple curvatures and the lateral offset distance corresponding to each curvature.

[0044] In combination with the second aspect, in certain implementations of the second aspect, the device further includes a control unit, which is used to control the display device to display a first interface, wherein the first interface includes multiple gear information, and the multiple gear information respectively corresponds to multiple configuration information, and the lateral parameter range included in each configuration information in the multiple configuration information is different; the acquisition unit is also used to obtain first configuration information from the multiple configuration information based on the user's input for the first gear, and the first gear is associated with the first configuration information, and the first configuration information includes the multiple lateral parameters.

[0045] In combination with the second aspect, in some implementations of the second aspect, the acquisition unit is further used to acquire historical driving information of the user; and the determination unit is further used to determine the multiple lateral parameters based on the historical driving information.

[0046] In combination with the second aspect, in certain implementations of the second aspect, the lateral active safety function includes a lateral collision avoidance function, and the determination unit is specifically used to: determine not to trigger the lateral collision avoidance function when the collision risk between the first predicted trajectory among the multiple predicted trajectories and the obstacle does not meet the preset collision condition; or, when, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not meet the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle meets the preset collision condition, determine not to trigger the lateral collision avoidance function.

[0047] In combination with the second aspect, in certain implementations of the second aspect, the lateral active safety function includes a lateral collision avoidance function, and the determination unit is specifically used to: when the collision risk between each predicted trajectory in the multiple predicted trajectories and the obstacle meets the preset collision condition, determine to trigger the lateral collision avoidance function and control the prompt device to prompt the user that there is a risk in the current lateral action.

[0048] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is specifically used to: determine the vehicle's driving space in the future period based on the multiple predicted trajectories; and determine whether to trigger the lateral active safety function based on the collision risk between the driving space and the obstacle.

[0049] In a third aspect, the present application provides a lateral control device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor executes the instructions stored in the memory to enable the device to perform any possible method in the first aspect.

[0050] In a fourth aspect, the present application provides a vehicle comprising any possible device in the second aspect or the third aspect.

[0051] In a fifth aspect, the present application provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any possible method in the first aspect.

[0052] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or separately packaged with the processor, and the embodiments of the present application do not specifically limit this.

[0053] In a sixth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program code. When the computer program code runs on a computer, the computer executes any possible method in the first aspect above.

[0054] In a seventh aspect, the present application provides a chip system comprising a processor for calling a computer program or computer instructions stored in a memory so that the processor executes any possible method in the above-mentioned first aspect.

[0055] In combination with the seventh aspect, in a possible implementation, the processor is coupled to the memory through an interface.

[0056] In combination with the seventh aspect, in a possible implementation, the chip system also includes a memory, in which a computer program or computer instructions are stored.

[0057] In an eighth aspect, the present application provides a chip system including a circuit for executing any possible method in the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] FIG1 is a functional block diagram of a vehicle provided in an embodiment of the present application.

[0059] FIG2 is a schematic block diagram of an advanced driver assistance system ADAS provided in an embodiment of the present application.

[0060] FIG3 is a schematic flow chart of a lateral control method provided in an embodiment of the present application.

[0061] FIG4 is a set of human-machine interfaces HMI provided in an embodiment of the present application.

[0062] FIG5 is a schematic diagram of the driver's intention configuration and lateral action configuration under different gear positions provided by an embodiment of the present application.

[0063] FIG6 is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0064] FIG7 is a schematic diagram of another application scenario provided by an embodiment of the present application.

[0065] FIG8 is a schematic diagram of another application scenario provided by an embodiment of the present application.

[0066] FIG9 is another HMI provided by an embodiment of the present application.

[0067] FIG10 is another schematic flow chart of the lateral control method provided in an embodiment of the present application.

[0068] FIG11 is a schematic block diagram of a lateral control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a way to describe the association relationship of associated objects, indicating that there can be three kinds of relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. "At least one" means one or more. For example, "at least one of A and B" is similar to "A and / or B", describing the association relationship of associated objects, indicating that there can be three kinds of relationships, for example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0070] In the embodiments of the present application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present application does not constitute a restriction on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary restriction. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0071] FIG1 is a functional block diagram of a vehicle 100 provided in an embodiment of the present application. The vehicle 100 may include a perception system 110, a computing platform 120, and a display device 130, wherein the perception system 110 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the perception system 110 may include a positioning system, which may be a global positioning system (GPS), a BeiDou system, or other positioning systems. For another example, the perception system 110 may include one or more of an inertial measurement unit (IMU), an accelerometer, a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0072] Some or all functions of the vehicle 100 may be controlled by a computing platform 120. The computing platform 120 may include one or more processors, such as processors 121 to 12n (n is a positive integer). A processor is a circuit capable of processing signals. In one implementation, the processor may be a circuit capable of reading and executing instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement certain functions through the logical relationships of a hardware circuit. The logical relationships of the hardware circuit may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 120 may also include a memory for storing instructions, and some or all of the processors 121 to 12n may call the instructions in the memory to implement corresponding functions.

[0073] The display devices 130 in the cockpit are mainly divided into two categories: the first is the vehicle-mounted display screen; the second is a projection display screen, such as a head-up display (HUD). The vehicle-mounted display screen is a physical display screen and a key component of the in-vehicle infotainment system. The cockpit can be equipped with multiple displays, such as the digital instrument panel, the central control screen, the display in front of the front passenger (also known as the front passenger), the display in front of the left rear passenger, and the display in front of the right rear passenger. Even the vehicle windows can serve as display screens. A head-up display, also known as a head-up display system, is primarily used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's gaze shift time, avoids pupil changes caused by the driver's gaze shift, and improves driving safety and comfort. HUDs include, for example, combiner-HUD (C-HUD), windshield-HUD (W-HUD), and augmented reality HUD (AR-HUD). It should be understood that other types of HUD systems may appear as technology evolves, and this application is not limited to this.

[0074] The above display device 130 is described by taking a vehicle-mounted display screen and a projection display screen as examples, and the embodiments of the present application are not limited thereto. For example, the display device 130 can also be a light display screen or a projection screen.

[0075] The vehicle 100 in this application may include: road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the vehicle 100 may be a vehicle (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a lawn mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. The embodiments of this application do not specifically limit the type of vehicle.

[0076] Vehicle 100 may include an advanced driving assistant system (ADAS). ADAS utilizes a variety of sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, camera, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the vehicle's surroundings, and analyzes and processes the obtained information to implement functions such as obstacle perception, target recognition, vehicle positioning, path planning, driver monitoring / reminders, etc., thereby improving the safety, automation and comfort of vehicle driving.

[0077] For example, FIG2 shows a schematic block diagram of an ADAS provided by an embodiment of the present application. From a logical functional perspective, the ADAS may include three main functional modules: a perception module 210, a decision module 220, and an execution module 230. The perception module 210 senses the vehicle's surroundings through sensors and inputs corresponding real-time data into the decision module 220. The decision module 220 makes corresponding decisions based on the information obtained by the perception module 210. After receiving the decision signal from the decision module 220, the execution module 230 takes corresponding actions, such as driving, changing lanes, steering, braking, and warnings.

[0078] The above perception module 210 may be the above perception system 110 , and the decision module 220 may be located in the above computing platform 120 .

[0079] At different levels of automated driving (L0-L5), ADAS can provide varying degrees of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. These levels are based on the Society of Automotive Engineers (SAE) grading standards. L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At L1-L3, monitoring and responding to road conditions are performed jointly by the driver and the system, with the driver taking over dynamic driving tasks. At L4 and L5, the driver transitions completely to the role of passenger. For example, automated parking can include automatic parking assistance (APA), automated parking assistance (RPA), and automated parking assistance (AVP). With APA, the driver doesn't need to control the steering wheel, but still needs to operate the accelerator and brakes from within the vehicle. With RPA, the driver can remotely park the vehicle from outside using a terminal (such as a mobile phone). With AVP, the vehicle can park itself without a driver. In terms of the corresponding levels of autonomous driving, APA is approximately at the L1 level, RPA is approximately at the L2-L3 level, and AVP is approximately at the L4 level.

[0080] As mentioned earlier, active safety features are being used in more and more vehicles. Active safety features are designed to take proactive judgments and preventive safety measures in emergency situations before the driver's subjective reaction, thereby significantly reducing road traffic accidents and related casualties. Such features are of great significance in active driving safety. For example, the lateral active safety function can help correct the driving route when the vehicle gradually deviates from the lane or there is a risk of a side collision. Compared with longitudinal deceleration and parking, the driver's overall driving experience will be more comfortable and safer. If the lateral active safety function is triggered too early, it may go against the driver's driving intention; if the lateral active safety function is triggered too late, it may cause the vehicle to cause an accident. Therefore, how to improve the accuracy of the triggering timing of the lateral active safety function has become an urgent problem to be solved.

[0081] A core component of active safety features lies in risk assessment and safety decision-making, which determine whether the feature should be activated and when to intervene. Driver control plays a crucial role in this process. While driving, the vehicle's yaw rate, steering wheel angle, steering wheel speed, steering torque, and longitudinal acceleration and deceleration information are all subject to significant uncertainty and exhibit nonlinear variations. Existing active safety feature decision-making solutions primarily fall into the following categories:

[0082] (1) Traditional solutions such as 5R1V use the sector range of the sensor to perform overall target screening and risk decision-making, considering whether there are obstacles invading the sector range. At the same time, lane line information is used as input to limit the scene to the lane, and false triggering of functions is also difficult to handle.

[0083] (2) Advanced multi-sensor solutions, such as those based on vehicle prediction lines and refined collision detection, consider lane shape as a long-term trend. However, the entire model does not consider driver operation and places excessively high demands on accuracy. Furthermore, they perform poorly in situations such as sharp bends, ramps, and emergency driver maneuvers. Consequently, excessive restrictions are added to the scenario, resulting in poor safety coverage.

[0084] (3) Considering the entire environment being built into a potential field, the more prominent advantage in terms of safety lies in passability. Most of the consideration is still on the driver's longitudinal acceleration and deceleration information, and the lateral information is used less.

[0085] Among them, lateral active safety functions are also favored by users compared to traditional automatic emergency braking systems (autonomous emergency braking, AEB) and other longitudinal active safety functions. The embodiment of this application aims to design a multimodal active safety prediction and decision-making solution, focusing on the multimodal prediction and decision-making process that integrates the driver's lateral movements. It can not only ensure the regulatory test scenarios of the active safety foundation, but also adapt to different scenarios and directions during the generalization process of actual vehicles. At the same time, different driving styles and lateral action levels are embedded in the overall decision-making solution, which has more differentiated explanations in the evaluation and makes the decision-making process more flexible.

[0086] FIG3 shows a schematic flow chart of a lateral control method 300 provided in an embodiment of the present application. The method 300 includes:

[0087] S310, obtaining real-time horizontal information.

[0088] Exemplarily, the real-time lateral information may include one or more of a steering wheel angle change rate (steerAngleRate), a steering wheel angle (steerAngle), a vehicle heading angle (θ), a lateral angular velocity, and a lateral acceleration.

[0089] For example, the vehicle can construct a state space based on the real-time lateral information obtained above. For example, the state space can be as follows:

[0090] in, represents the state space of the vehicle, x represents the lateral coordinate of the vehicle, y represents the longitudinal coordinate of the vehicle, θ represents the heading angle of the vehicle, v represents the longitudinal velocity of the vehicle, a represents the longitudinal acceleration of the vehicle, w represents the yaw angular velocity of the vehicle, and a c Indicates the lateral acceleration of the vehicle.

[0091] The above state space may include the real-time lateral information and longitudinal information of the vehicle.

[0092] The above state space may include more or less horizontal information and vertical information, which is not limited in the embodiments of the present application.

[0093] S320: Determine a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters.

[0094] Optionally, before determining multiple predicted trajectories based on the real-time lateral information and multiple lateral parameters, the method 300 also includes: obtaining first configuration information from multiple configuration information, the lateral parameter range in each configuration information in the multiple configuration information is different, and the first configuration information includes the multiple lateral parameters.

[0095] Optionally, obtaining the first pre-configuration information from multiple configuration information includes: controlling the display device to display a first interface, the first interface including multiple gear information, and the multiple gear information respectively corresponding to the multiple configuration information; obtaining the first configuration information according to the user's input for the first gear, and the first gear corresponds to the first configuration information.

[0096] Exemplarily, FIG4 shows a set of human machine interfaces (HMIs) provided in an embodiment of the present application.

[0097] As shown in (a) of Figure 4, the HMI is the setting interface of the assisted driving function 401. The setting interface of the assisted driving function 401 includes the settings of active safety functions, such as the anti-collision braking function and the lateral collision avoidance function. Among them, the description of the anti-collision braking function is "automatically applying brakes when about to collide with the front or the front crossing target when moving forward, or when about to collide with the rear or the rear crossing target when reversing", and the description of the lateral collision avoidance function is "when the vehicle deviates from the current lane and there is a risk of collision with obstacles such as water barriers, fences, etc. in the side formation, or there is a risk of scratching the side and front obstacles, the emergency auxiliary driver turns the steering wheel to avoid and reduce the collision risk". When the user clicks the control 402, the vehicle can start the lateral collision avoidance function and display the HMI shown in (b) of Figure 4 on the display screen.

[0098] The above-mentioned activation of the side collision avoidance function can be understood as the vehicle automatically activating the side collision avoidance function when it detects a risk of collision with a side obstacle.

[0099] As shown in Figure 4(b), this HMI is another setup interface for the assisted driving function 401. Upon detecting a user click on control 402, the vehicle may display a gear selection box 403, which includes different gears, such as conservative, moderate, and aggressive. The description of the gear information reads, "You can select different gears, each with different lateral parameters." This setup interface also includes an icon 404, which describes the side collision avoidance function. Upon detecting a user click on icon 404, the vehicle may display the HMI shown in Figure 4(c) on the display screen.

[0100] As shown in Figure 4 (c), the HMI is an introduction to the side collision avoidance function. This description includes the following: "When the vehicle deviates from its current lane and is at risk of colliding with obstacles such as lateral barriers or fences, or snagging obstacles in front of or to the side, the driver is assisted in steering to avoid and mitigate the collision risk. Conservative gear: The driver is predicted to turn the steering wheel early, resulting in a lower steering angular velocity; Moderate gear: The driver is predicted to turn the steering wheel at a moderate time in advance, resulting in a moderate steering angular velocity; Aggressive gear: The driver is predicted to turn the steering wheel late, resulting in a higher steering angular velocity." Users can select different gears based on their driving style. This allows the vehicle to predict its trajectory while driving, combining real-time lateral information with a specific gear, and then determine whether to trigger the side collision avoidance function.

[0101] The HMI shown in FIG. 4 is described above by taking the driver's reaction time and the steering wheel angular velocity in different gears as examples, but the embodiments of the present application are not limited thereto.

[0102] For example, Figure 5 shows a schematic diagram of driver intention configuration and lateral action configuration under different gears provided by an embodiment of the present application. The driver intention configuration includes, but is not limited to, posture information, steering information, and attention and orientation monitoring. The lateral action configuration information includes, but is not limited to, lane change aggressiveness, vehicle lateral offset distance, steering wheel direction changes, and longitudinal acceleration changes.

[0103] The above attention and direction monitoring can be understood as the direction of the driver's gaze. For example, the position of the user's eyeballs can be obtained through data collected by a camera in the vehicle cabin, and thus the direction of the driver's gaze can be obtained.

[0104] Optionally, before determining a plurality of predicted trajectories based on the real-time lateral information and the plurality of lateral parameters, the method 300 further includes: acquiring historical driving information of the user; and determining the plurality of lateral parameters based on the historical driving information.

[0105] For example, the vehicle can collect statistics on the driver's lateral information (e.g., the steering wheel angle change rate) in scenarios where the lateral active safety function is triggered or when the active safety function is about to be triggered over a period of time in the past (e.g., one month or six months), so as to obtain the lateral parameter range.

[0106] Optionally, the multiple lateral parameters are determined based on the historical driving information, including: determining the multiple lateral parameters based on the historical driving information and the scenario in which the vehicle is located, the scenario in which the vehicle is located includes but is not limited to a scenario in which the user drives the vehicle through a sharp bend, a scenario in which the user drives the vehicle to change lanes urgently, or a scenario in which the user drives the vehicle to turn the steering wheel suddenly.

[0107] Optionally, the vehicle can record historical driving information when the lateral active safety function is triggered in different scenarios. For example, the vehicle can record the range of steering wheel angle change rates when the user is driving the vehicle through a sharp bend. For another example, the vehicle can record the range of steering wheel angle change rates when the user is driving the vehicle in an emergency lane change. For another example, the vehicle can record the range of steering wheel angle conversion rates when the user is driving the vehicle in an abrupt steering turn.

[0108] Optionally, determining the multiple lateral parameters according to the historical driving information includes: determining the multiple lateral parameters according to the historical driving information and user identification information.

[0109] Exemplarily, the method further includes: determining identification information of the user based on images captured by a camera in the cabin.

[0110] Optionally, the vehicle can record historical driving information for different users. For example, the vehicle can collect statistics on the driver's lateral information (e.g., steering wheel angle change rate) when user A drives the vehicle over a period of time (e.g., one month or six months) in scenarios where the vehicle's lateral active safety function is triggered or about to be triggered.

[0111] For another example, the vehicle may collect statistics on the driver's lateral information (e.g., the steering wheel angle change rate) when user B is driving the vehicle over the past period of time (e.g., one month or six months) in scenarios where the vehicle triggers the lateral active safety function or is about to trigger the active safety function.

[0112] Optionally, the real-time lateral information includes a first steering wheel angle and a first steering wheel angle change rate, and the multiple lateral parameters include multiple time lengths. Based on the real-time lateral information and the multiple lateral parameters, the multiple predicted trajectories are determined, including: determining the first heading angle of the vehicle based on the first TTR and the first steering wheel angle change rate, the first TTR being determined by the collision time TTC between the vehicle and the obstacle; determining multiple steering wheel angle change rates based on the first steering wheel angle and the multiple time lengths; determining multiple curvatures based on the first steering wheel angle and the multiple steering wheel angle change rates; and determining the multiple predicted trajectories based on the multiple curvatures.

[0113] For example, FIG6 shows a schematic diagram of an application scenario provided by an embodiment of the present application.

[0114] As shown in FIG6 (a), the user drives the vehicle in lane 1, with the front of the vehicle facing lane 2. The vehicle can determine the collision time TTC between the vehicle 100 and the cone based on the vehicle state (e.g., speed) and the distance between the vehicle 100 and the cone. The vehicle 100 can determine the first reaction time TTR based on the following formula (1): TTR = k * TTC (1)

[0115] Here, k is a preset value, and k is greater than 0 and less than 1.

[0116] For example, the vehicle 100 may determine the first heading angle Δθ of the vehicle based on the first reaction time TTR and formula (2): Δθ=TTR*steerAngleRate (2)

[0117] Here, steerAngleRate is the steering wheel angle change rate obtained in step S310.

[0118] For example, taking the case where the multiple lateral parameters include multiple time durations (multiple featureTimes), the vehicle can determine the angular rates of multiple steering wheels based on the first heading angle Δθ and the following formula (3):

[0119] Among them, featureRate is the steering wheel angle change rate.

[0120] For example, Table 1 shows the duration featureTime ranges under different gears.

[0121] Table 1

[0122] For example, if the vehicle detects that the user has selected a conservative gear, the duration range corresponding to the conservative gear is [2s, 2.4s]. It can be seen that for the conservative gear, the steering wheel angle change rate obtained by formula (3) is smaller; for the aggressive gear, the steering wheel angle change rate obtained by formula (3) is larger.

[0123] For example, in the above formula (3), featureTime can be 2s, 2.1s, 2.2s, 2.3s, and 2.4s respectively. The vehicle 100 can calculate the curvature corresponding to each featureTime using the following formula (4):

[0124] Here, kappa is the curvature of the predicted trajectory, steerAngle is the steering wheel angle obtained in S310 , and wheelbase is the wheelbase of the vehicle.

[0125] In formula (3), five different featureTimes can be used to obtain five different steering wheel angle change rates, featureRate. Formula (4) can be used to calculate five different curvatures. Five predicted trajectories can be obtained based on these five different curvatures. As shown in FIG6(b), vehicle 100 can obtain the trajectories within the reaction time of predicted trajectories 1-5 based on these five different curvatures.

[0126] The above embodiments are based on formulas (1)-(4) and Table 1, and multiple curvature radii are obtained as examples for illustration. The embodiments of the present application are not limited thereto. For example, the multiple lateral parameters may also include multiple rates of change of the turning angle. For example, Table 2 shows the range of the rate of change of the turning angle under different gears provided in the embodiments of the present application.

[0127] Table 2

[0128] For example, if the vehicle detects that the user has selected a conservative gear, the steering angle change rate corresponding to the conservative gear is in the range of [1.0 rad / s, 1.5 rad / s]. In this way, the TTR can be obtained by formula (1). Based on the different steering angle change rates under the conservative gear and formula (5), different curvatures can be obtained.

[0129] Each of the predicted trajectories 1-5 further includes a smooth trajectory, a trajectory corresponding to static road perception, and a trajectory corresponding to regression compensation. The smooth trajectory can be determined by the lateral constraint of the vehicle.

[0130] For example, the smooth trajectory in each predicted trajectory may be determined based on the curvature of the trajectory within the reaction time and the speed of the vehicle.

[0131] For example, the first configuration information may include a mapping relationship between the curvature, the vehicle speed, and the lateral offset distance. After the curvature is obtained by formula (4), the lateral offset distance corresponding to the smooth trajectory can be obtained based on the curvature, the vehicle speed, and the mapping relationship.

[0132] S330 : Determine whether to trigger a lateral active safety function based on the multiple predicted trajectories.

[0133] Optionally, the lateral active safety function includes a lateral collision avoidance function, which determines whether to trigger the lateral active safety function based on the multiple predicted trajectories, including: when the collision risk between the first predicted trajectory among the multiple predicted trajectories and the obstacle does not meet the preset collision condition, determining not to trigger the emergency steering function.

[0134] Exemplarily, taking (b) in FIG. 6 as an example, the vehicle 100 may determine the collision risk between each predicted trajectory and the cone based on the predicted trajectories 1-5. For example, the vehicle 100 may determine the collision risk between the predicted trajectory and the obstacle based on the collision risk between the vehicle's outline (such as a three-dimensional rectangular box or cube (3D bounding box, 3D bbox) or polygonal outline (polygon)) at each trajectory point on the predicted trajectory and the cone. If there is a predicted trajectory among the predicted trajectories 1-5 that has no collision risk with the cone or the collision risk between the predicted trajectory and the cone does not meet the preset collision conditions, the vehicle 100 may not trigger the side collision avoidance function.

[0135] Optionally, the lateral active safety function includes a lateral collision avoidance function, and determines whether to trigger the lateral active safety function based on the multiple predicted trajectories, including: when, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not meet the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle meets the preset collision condition, determining not to trigger the lateral collision avoidance function.

[0136] For example, taking (b) in FIG. 6 as an example, if the vehicle 100 determines that the collision risk between 3 or more predicted trajectories in the predicted trajectories 1-5 and the obstacle does not meet the preset collision conditions, then the vehicle may not trigger the side collision avoidance function.

[0137] Optionally, the lateral active safety function includes a lateral collision avoidance function, and determines whether to trigger the lateral active safety function based on the multiple predicted trajectories, including: when the collision risk between each predicted trajectory in the multiple predicted trajectories and the obstacle meets a preset collision condition, determining to trigger the lateral collision avoidance function and controlling the prompt device to prompt the user that there is a risk in the current lateral action.

[0138] For example, taking (b) in FIG. 6 as an example, if the vehicle 100 determines that the collision risks between all predicted trajectories in predicted trajectories 1-5 and obstacles meet the preset collision conditions, then the vehicle 100 can trigger the emergency steering function and control the display screen to display that the user's current lateral action is risky.

[0139] In the above embodiment, the lateral active safety function is described as the LOCP function, but the embodiments of the present application are not limited thereto. For example, the lateral active safety function may also be AES, emergency steering assist (ESA) or ELKA function.

[0140] For example, the AES function can be understood as when the driver engages in dangerous driving behavior and the active braking function is unable to stop and avoid obstacles, the vehicle can achieve emergency obstacle avoidance through front wheel steering, or through front wheel steering and direct yaw torque.

[0141] For example, the ELKA function can be understood as an emergency assistance system in which the driver turns the steering wheel to avoid and reduce the risk of collision when the vehicle deviates from the current lane and there is a risk of collision with other vehicles or driving off the road boundary.

[0142] FIG7 shows a schematic diagram of another application scenario provided by an embodiment of the present application.

[0143] As shown in FIG7( a ), when the driver is driving the vehicle through a sharp curve, the vehicle can predict trajectory 6-10 based on the above method 300 and determine the risk of collision with a lateral obstacle (e.g., a guardrail) based on the predicted trajectory 6-10. The vehicle 100 can determine whether to activate the side collision avoidance function based on the risk of collision with the guardrail.

[0144] As shown in FIG7( b ), a plurality of water barriers are provided at the entrance to a highway ramp. When a driver enters the ramp, the driver can predict trajectories 11-15 based on the method 300 described above and determine the risk of collision between the vehicle and the water barriers based on the predicted trajectories 11-15. Vehicle 100 can determine whether to activate the side collision avoidance function based on the risk of collision with the water barriers.

[0145] As shown in FIG7(c), when the driver changes lanes to overtake, vehicle 100 detects that the user first turns the steering wheel left, then right to return the vehicle to center. During the detection of the driver turning the steering wheel right to return the vehicle to center, vehicle 100 can predict trajectories 16-20 based on method 300 and determine the risk of collision between the vehicle and the cone based on predicted trajectories 16-20. Vehicle 100 can then determine whether to activate the side collision avoidance function based on the risk of collision with the cone.

[0146] FIG8 shows a schematic diagram of another application scenario provided by an embodiment of the present application.

[0147] Vehicle 100 is currently in lane 1. When the driver changes lanes to overtake (for example, the driver first changes lanes to lane 2, and then changes lanes from lane 2 to lane 1), vehicle 100 detects three stages of the driver's steering wheel turning. In stage 1, the driver first turns the steering wheel left to enter lane 2. In stage 2, the driver turns the steering wheel right to enter lane 1. In stage 3, the driver turns the steering wheel left again to ensure that the vehicle is centered in lane 1. Based on the steering wheel angle changes and multiple steering angle change rates during the driver's left steering in stage 3, vehicle 100 can determine multiple predicted trajectories. These multiple predicted trajectories can form the driving space of vehicle 100 (as shown in the dashed boxes in (a) and (b) of Figure 8).

[0148] For example, as shown in (a) in Figure 8, in stage 3, when the vehicle 100 detects that the driver has turned the steering wheel at a large angle, there is no risk of collision between the obtained driving space and the vehicle 200 in lane 1. At this time, the vehicle 100 may not activate the side collision avoidance function.

[0149] For example, as shown in (b) in Figure 8, in stage 3, when the vehicle 100 detects that the driver's steering wheel angle is small, there is a risk of collision between the obtained driving space and the vehicle 200 in lane 1. At this time, the vehicle 100 can activate the side collision avoidance function.

[0150] FIG9 shows a schematic diagram of another HMI provided in an embodiment of the present application.

[0151] As shown in FIG9 , when vehicle 100 determines to activate the side collision avoidance function based on the steering wheel angle and multiple steering angle change rates, it can also control the display screen to display a prompt message stating, "Your current lateral movement is detected to be risky. The side collision avoidance function has been activated." Simultaneously, vehicle 100 can control the display screen to indicate a possible collision zone between vehicle 100 and vehicle 200.

[0152] Exemplarily, the collision area may be displayed by being filled in red.

[0153] For example, the vehicle 100 may further display a risk ring on the side of the vehicle 100 that is deviated from through a display screen. The vehicle 100 may mark a red gradient ring in the risk direction based on the collision risk between the vehicle 100 and the vehicle 200.

[0154] For example, when the side collision avoidance function is triggered, the vehicle 100 may also control one or more of the following: a sound generating device to emit a prompt sound, a steering wheel to vibrate, or a seat belt to be tightened.

[0155] FIG10 shows a schematic flow chart of a lateral control method 1000 provided in an embodiment of the present application. As shown in FIG10 , the method 1000 includes:

[0156] S1010, executing a pre-decision process based on the vehicle status, static perception results and obstacle information.

[0157] Exemplarily, the pre-decision making process includes determining whether the vehicle presents a lateral risk.

[0158] Exemplarily, the state of the vehicle may include lateral information and longitudinal information of the vehicle. For example, the state of the vehicle may be represented by the state space of the vehicle.

[0159] Exemplarily, the static perception results include lane line information, road boundary information, etc.

[0160] Illustratively, the obstacle information includes the location and type of the obstacle (eg, whether the obstacle is another vehicle or a vulnerable road user (VRU)).

[0161] Optionally, a pre-decision process is performed, including: inputting the vehicle's state, static perception results, and obstacle information into a prediction model to preliminarily obtain the vehicle's lateral risk level.

[0162] Exemplarily, the prediction model may be a residual neural network (ResNet), a recurrent neural network (RNN), or a multilayer perceptron (MLP).

[0163] Exemplarily, the prediction model may also be a machine learning model, such as a support vector machine (SVM).

[0164] Illustratively, when the lateral risk level of the vehicle is greater than or equal to a preset risk level, S1020 may be executed; otherwise, the vehicle may determine not to trigger the lateral active safety function.

[0165] S1020: Determine whether to trigger a lateral active safety function based on the vehicle's real-time lateral information and multiple lateral parameters.

[0166] For example, S1020 may refer to the above-mentioned S320 and S330, which will not be repeated here.

[0167] In this way, the predictive decision process can be executed before executing S1020, avoiding the process of determining multiple predicted trajectories based on real-time lateral information and multiple lateral parameters while the vehicle is driving. In other words, executing the post-decision process (S1020 can also be referred to as the post-decision process) after the vehicle has initially determined that there is a lateral risk helps reduce the vehicle's computational overhead.

[0168] The above method 300 or method 1000 can be executed by the above-mentioned vehicle 100, or the method 300 or method 1000 can be executed by the above-mentioned computing platform 120, or the method 300 or method 1000 can be executed by a system consisting of the computing platform 120 and the perception system 110, or the method 300 or method 1000 can be executed by the system-on-a-chip (SoC) in the above-mentioned computing platform 120, or the method 300 or method 1000 can be executed by the processor, chip or circuit in the computing platform 120, or the method 300 or method 1000 can be executed by the above-mentioned decision module 220.

[0169] Figure 11 shows a schematic block diagram of a lateral control device 1100 provided herein. Device 1100 includes an acquisition unit 1110 for acquiring real-time lateral information; a determination unit 1120 for determining multiple predicted trajectories based on the real-time lateral information and multiple lateral parameters; and a determination unit 1120 for determining whether to trigger a lateral active safety function based on the multiple predicted trajectories.

[0170] Optionally, the real-time lateral information includes a first steering wheel angle, the multiple lateral parameters include multiple steering angle change rates, and the determination unit 1120 is specifically used to: determine multiple curvatures based on the first steering wheel angle and the multiple steering angle change rates; and determine the multiple predicted trajectories based on the multiple curvatures.

[0171] Optionally, the real-time lateral information includes a first steering wheel angle and a first steering wheel angle change rate, and the multiple lateral parameters include multiple time lengths. The determination unit 1120 is specifically used to: determine the first heading angle of the vehicle based on the first TTR and the first steering wheel angle change rate, wherein the first TTR is determined by the collision time TTC between the vehicle and the obstacle; determine multiple steering wheel angle change rates based on the first steering wheel angle and the multiple time lengths; determine multiple curvatures based on the first steering wheel angle and the multiple steering wheel angle change rates; and determine the multiple predicted trajectories based on the multiple curvatures.

[0172] Optionally, the determination unit 1120 is specifically configured to: determine, based on the multiple curvatures, a lateral offset distance corresponding to each of the multiple curvatures; and determine, based on the multiple curvatures and the lateral offset distance corresponding to each of the curvatures, the multiple predicted trajectories.

[0173] Optionally, the device also includes a control unit, which is used to control the display device to display a first interface, where the first interface includes multiple gear information, and the multiple gear information corresponds to multiple configuration information respectively, and the lateral parameter range included in each configuration information in the multiple configuration information is different; the acquisition unit 1110 is also used to obtain first configuration information from the multiple configuration information based on the user's input for the first gear, and the first gear is associated with the first configuration information, and the first configuration information includes the multiple lateral parameters.

[0174] Optionally, the acquisition unit 1110 is further configured to acquire historical driving information of the user; and the determination unit is further configured to determine the plurality of lateral parameters based on the historical driving information.

[0175] Optionally, the lateral active safety function includes a lateral collision avoidance function, and the determination unit 1120 is specifically used to: determine not to trigger the lateral collision avoidance function when the collision risk between the first predicted trajectory among the multiple predicted trajectories and the obstacle does not meet the preset collision condition; or, when, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not meet the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle meets the preset collision condition, determine not to trigger the lateral collision avoidance function.

[0176] Optionally, the lateral active safety function includes a lateral collision avoidance function, and the determination unit 1120 is specifically used to: when the collision risk between each predicted trajectory in the multiple predicted trajectories and the obstacle meets the preset collision condition, determine to trigger the lateral collision avoidance function and control the prompt device to prompt the user that the current lateral action is risky.

[0177] Optionally, the determination unit 1120 is specifically used to: determine the driving space of the vehicle in a future period of time based on the multiple predicted trajectories; and determine whether to trigger the lateral active safety function based on the collision risk between the driving space and the obstacle.

[0178] For example, the acquisition unit 1110 may be the computing platform or a processing circuit, processor, or controller in the computing platform in Figure 1. For example, if the acquisition unit 1110 is the processor 121 in the computing platform, the processor 121 may acquire the real-time lateral parameters of the vehicle.

[0179] For another example, the determining unit 1020 may be the computing platform in FIG1 or a processing circuit, processor, or controller in the computing platform. For example, if the determining unit 1120 is the processor 122 in the computing platform, the processor 122 may plan multiple predicted trajectories based on the real-time lateral parameter and multiple lateral parameters acquired by the processor 121, and determine whether to activate the lateral active safety function based on the multiple predicted trajectories.

[0180] The functions implemented by the acquisition unit 1110 and the functions implemented by the determination unit 1120 may be implemented by different processors, or may be implemented by the same processor, which is not limited in this embodiment of the present application.

[0181] It should be understood that the division of the various units in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or they may be physically separated. Furthermore, the units in the device may be implemented in the form of a processor calling software; for example, the device includes a processor connected to a memory storing instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or the functions of the various units in the device, where the processor is, for example, a general-purpose processor such as a CPU or a microprocessor, and the memory is a memory within the device or a memory external to the device. Alternatively, the units in the device may be implemented in the form of hardware circuits, and the functions of some or all of the units may be implemented through the design of the hardware circuits. The hardware circuits may be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units may be implemented through the design of the logical relationships between the components within the circuits. In another implementation, the hardware circuit may be implemented using a PLD, such as an FPGA, which may include a large number of logic gate circuits, and the connections between the logic gate circuits may be configured using a configuration file to implement the functions of some or all of the above units. All units of the above apparatus may be implemented entirely in the form of software called by a processor, or entirely in the form of hardware circuits, or partially in the form of software called by a processor and the rest in the form of hardware circuits.

[0182] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0183] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0184] In addition, the various units in the above apparatus may be fully or partially integrated together, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the apparatus. The at least one processor may be of different types, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0185] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps performed by the above embodiment.

[0186] Optionally, if the device is located in a vehicle, the processing unit may be the processors 121 - 12n shown in FIG. 1 .

[0187] An embodiment of the present application also provides a lateral control system, which may include a computing platform and a perception system, and the computing platform may include the above-mentioned lateral control device.

[0188] An embodiment of the present application also provides a vehicle, which may include the above-mentioned lateral control device or lateral control system.

[0189] An embodiment of the present application further provides a computer program product, which includes: computer program code, which enables the computer to execute the method in the above embodiment when the computer program code is run on a computer.

[0190] An embodiment of the present application further provides a computer-readable medium, wherein the computer-readable medium stores a program code. When the computer program code runs on a computer, the computer executes the method in the above embodiment.

[0191] An embodiment of the present application further provides a chip, which includes a circuit, and the circuit is used to execute the method in the above embodiment.

[0192] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0193] It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[0194] It should also be understood that in the various embodiments of the present application, 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 application.

[0195] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0196] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0197] In the several embodiments provided in this application, 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. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that 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.

[0198] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0199] 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.

[0200] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0201] The above description is merely a specific embodiment of the present application, but the scope of protection of the present 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 the present application should be covered and fall within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A lateral control method, characterized in that: include: Get real-time horizontal information; determining a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters; Determine whether to trigger a lateral active safety function based on the multiple predicted trajectories.

2. The method according to claim 1, characterized in that The real-time lateral information includes a first steering angle of the steering wheel, and the multiple lateral parameters include multiple steering angle change rates. The step of determining a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters includes: determining a plurality of curvatures according to the first rotation angle and the plurality of rotation angle change rates; The plurality of predicted trajectories are determined based on the plurality of curvatures.

3. The method according to claim 1, characterized in that The real-time lateral information includes a first steering angle and a first steering angle change rate of the steering wheel, and the multiple lateral parameters include multiple time lengths. The determining of the plurality of predicted trajectories based on the real-time lateral information and the plurality of lateral parameters includes: determining a first heading angle of the vehicle according to a first TTR and the first turning angle change rate, wherein the first TTR is determined by a time to collision TTC between the vehicle and the obstacle; determining a plurality of steering wheel angle change rates according to the first heading angle and the plurality of time durations; determining a plurality of curvatures according to the first rotation angle and the plurality of rotation angle change rates; The plurality of predicted trajectories are determined based on the plurality of curvatures.

4. The method according to claim 2 or 3, characterized in that The determining the plurality of predicted trajectories according to the plurality of curvatures includes: Determining, based on the multiple curvatures, a lateral offset distance corresponding to each of the multiple curvatures; The multiple predicted trajectories are determined according to the multiple curvatures and the lateral offset distance corresponding to each curvature.

5. The method according to any one of claims 2 to 4, characterized in that Before determining a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters, the method further includes: Controlling the display device to display a first interface, the first interface including a plurality of gear information, the plurality of gear information corresponding to a plurality of configuration information, each of the plurality of configuration information including a different range of lateral parameters; According to the user's input for the first gear, first configuration information is obtained from the plurality of configuration information, the first gear is associated with the first configuration information, and the first configuration information includes the plurality of lateral parameters.

6. The method according to any one of claims 2 to 4, characterized in that Before determining a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters, the method further includes: Get the user's historical driving information; The plurality of lateral parameters are determined according to the historical driving information.

7. The method according to any one of claims 1 to 6, characterized in that The lateral active safety function includes a lateral collision avoidance function, and determining whether to trigger the lateral active safety function based on the multiple predicted trajectories includes: When the collision risk between a first predicted trajectory among the multiple predicted trajectories and an obstacle does not meet a preset collision condition, determining not to trigger the lateral collision avoidance function; or, When, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not satisfy the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle satisfies the preset collision condition, it is determined that the lateral collision avoidance function is not triggered.

8. The method according to any one of claims 1 to 6, characterized in that The lateral active safety function includes a lateral collision avoidance function, and determining whether to trigger the lateral active safety function based on the multiple predicted trajectories includes: When the collision risk between each predicted trajectory in the plurality of predicted trajectories and the obstacle meets a preset collision condition, it is determined to trigger the lateral collision avoidance function and the prompt device is controlled to prompt the user that the current lateral action has a risk.

9. The method according to any one of claims 1 to 6, characterized in that The determining, based on the plurality of predicted trajectories, whether to trigger a lateral active safety function includes: Determining a travel space of the vehicle within a future period of time based on the multiple predicted trajectories; Whether to trigger the lateral active safety function is determined according to the collision risk between the driving space and the obstacle.

10. A lateral control device, characterized in that: include: An acquisition unit, used for acquiring real-time horizontal information; a determination unit, configured to determine a plurality of predicted trajectories based on the real-time lateral information and a plurality of lateral parameters; The determining unit is further configured to determine whether to trigger a lateral active safety function based on the multiple predicted trajectories.

11. The device according to claim 10, characterized in that The real-time lateral information includes a first steering wheel angle, the multiple lateral parameters include multiple steering wheel angle change rates, and the determining unit is specifically configured to: determining a plurality of curvatures according to the first rotation angle and the plurality of rotation angle change rates; The plurality of predicted trajectories are determined based on the plurality of curvatures.

12. The device according to claim 10, characterized in that The real-time lateral information includes a first steering wheel angle and a first steering wheel angle change rate, the multiple lateral parameters include multiple time durations, and the determining unit is specifically configured to: determining a first heading angle of the vehicle according to a first TTR and the first turning angle change rate, wherein the first TTR is determined by a time to collision TTC between the vehicle and the obstacle; determining a plurality of steering wheel angle change rates according to the first heading angle and the plurality of time durations; determining a plurality of curvatures according to the first rotation angle and the plurality of rotation angle change rates; The plurality of predicted trajectories are determined based on the plurality of curvatures.

13. The device according to claim 11 or 12, characterized in that The determining unit is specifically configured to: Determining, based on the multiple curvatures, a lateral offset distance corresponding to each of the multiple curvatures; The multiple predicted trajectories are determined according to the multiple curvatures and the lateral offset distance corresponding to each curvature.

14. The device according to any one of claims 11 to 13, characterized in that The device further comprises a control unit, The control unit is configured to control the display device to display a first interface, wherein the first interface includes a plurality of gear information, the plurality of gear information respectively corresponding to a plurality of configuration information, and each of the plurality of configuration information includes a different range of lateral parameters; The acquisition unit is further configured to acquire first configuration information from the plurality of configuration information according to a user input for the first gear, the first gear being associated with the first configuration information, and the first configuration information including the plurality of lateral parameters.

15. The device according to any one of claims 11 to 13, characterized in that The acquisition unit is further configured to acquire the user's historical driving information; The determining unit is further configured to determine the plurality of lateral parameters based on the historical driving information.

16. The device according to any one of claims 10 to 15, characterized in that The lateral active safety function includes a lateral collision avoidance function, and the determining unit is specifically configured to: When the collision risk between a first predicted trajectory among the multiple predicted trajectories and an obstacle does not meet a preset collision condition, determining not to trigger the lateral collision avoidance function; or, When, among the multiple predicted trajectories, the number of predicted trajectories whose collision risk with the obstacle does not satisfy the preset collision condition is greater than the number of predicted trajectories whose collision risk with the obstacle satisfies the preset collision condition, it is determined that the lateral collision avoidance function is not triggered.

17. The device according to any one of claims 10 to 15, characterized in that The lateral active safety function includes a lateral collision avoidance function, and the determining unit is specifically configured to: When the collision risk between each predicted trajectory in the plurality of predicted trajectories and the obstacle meets a preset collision condition, it is determined to trigger the lateral collision avoidance function and the prompt device is controlled to prompt the user that the current lateral action has a risk.

18. The device according to any one of claims 10 to 15, characterized in that The determining unit is specifically configured to: Determining a travel space of the vehicle within a future period of time based on the multiple predicted trajectories; Whether to trigger the lateral active safety function is determined according to the collision risk between the driving space and the obstacle.

19. A lateral control device, characterized in that: include: memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 9.

20. A vehicle, characterized in that: Comprising the apparatus of any one of claims 10 to 19.

21. A computer-readable storage medium, characterized in that Instructions are stored thereon, and when the instructions are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 9.

22. A computer program product, characterized in that The computer program product comprises a computer program code, which, when run on a computer, causes the computer to implement the method according to any one of claims 1 to 9.

23. A chip, characterized in that: The chip comprises a circuit for executing the method according to any one of claims 1 to 9.

Images