A vehicle control method and device based on cooperation of each security function

Abstract

This invention discloses a vehicle control method and device based on the coordination of various safety functions, relating to the field of vehicle technology. The specific implementation of this invention includes: receiving first state data of multiple risk objects collected by sensors corresponding to various vehicle safety functions and second state data of the vehicle itself; determining risk labels corresponding to the multiple risk objects based on the first and second state data; generating control commands for the vehicle based on the risk labels for the multiple risk objects; and controlling the vehicle's actions based on the control commands to provide warnings or avoid the risk objects. This implementation, by constructing a unified risk perception and collaborative control architecture, fundamentally solves the command conflicts and vehicle instability caused by the independent operation of multiple safety functions in traditional systems. It not only achieves globally optimal control under multiple risk sources but also improves the vehicle's safety performance, ride comfort, and system robustness in complex driving scenarios.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a vehicle control method and apparatus based on the coordination of various safety functions. Background Technology

[0002] Traditional safety features include automatic emergency braking, forward collision warning, lane departure warning, lane keeping assist, and adaptive cruise control. In existing vehicle control schemes, a single safety function typically responds to a single risk factor; each safety function has its own independent identification logic, trigger threshold, and control execution channel, thus participating in vehicle control independently. However, when multiple risk factors exist simultaneously, conflicting control commands (such as braking and steering) triggered by two or more safety functions may arise. This can lead to vehicle instability and, in severe cases, vehicle accidents. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a vehicle control method and device based on the coordination of various safety functions. By constructing a unified risk perception and collaborative control architecture, it fundamentally solves the command conflicts and vehicle instability caused by the independent operation of multiple safety functions in the traditional way. It not only achieves global optimal control under multiple risk sources, but also improves the vehicle's safety performance, ride comfort and system robustness in complex driving scenarios.

[0004] To achieve the above objectives, according to one aspect of the present invention, a vehicle control method based on the coordination of various safety functions is provided, comprising: Receive first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and second state data of the vehicle itself; Based on the first state data and the second state data, risk labels corresponding to multiple risk objects are determined; For multiple risk objects, control commands are generated for the vehicle based on the risk tags; The vehicle's actions are controlled based on the control commands to provide warnings or avoid the risky object.

[0005] Optionally, if a moving object exists among the plurality of risk objects, determining the risk labels corresponding to the plurality of risk objects based on the first state data and the second state data includes: Based on each risk object and its corresponding first state data, predict the movement trajectory of each risk object within a preset time period and its corresponding probability. Based on the type of the risk object, the movement trajectory of the risk object and its corresponding probability, and the second state data, a risk score is given for each risk object; Based on the risk scoring results, a risk label is determined for each of the risk objects.

[0006] Optionally, the step of scoring each risk object based on its type, movement trajectory and corresponding probability, and the second state data includes: Based on the second state data, predict the vehicle's trajectory; For each of the aforementioned risk objects: Based on the vehicle's trajectory, the type of the risk object, the movement trajectory of the risk object and its corresponding probability, the collision probability, collision time distribution, collision energy and potential hazard between the vehicle and the risk object are calculated, and the risk score / level of the risk object is determined.

[0007] Optionally, generating control commands for the vehicle based on the risk tags for multiple risk objects includes: Based on the risk scores / levels corresponding to the multiple risk objects, a priority is assigned to each of the risk objects; Based on the priorities, road environment constraints, and passenger comfort / safety constraints, a control strategy and its corresponding control commands are generated for the vehicle.

[0008] Optionally, the method further includes: Based on the first state data and the second state data, if it is determined that the probability of one or more of the multiple risk objects colliding with the vehicle exceeds a preset probability threshold, the vehicle is controlled to brake suddenly.

[0009] Optionally, the control strategy includes at least one of the following: information prompts, audible / visual alarms, longitudinal control, and combined longitudinal and transverse control.

[0010] Optionally, the method further includes: In response to the control command, the vehicle is controlled to issue a warning / prompt message; And / or, Record the decision chain that generates the control command.

[0011] To achieve the above objectives, according to another aspect of the present invention, a vehicle control device based on the coordination of various safety functions is provided, comprising: a data receiving module, a risk assessment module, a control command generation module, and a control module, wherein, The data receiving module is used to receive the first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and the second state data of the vehicle itself. The risk assessment module is used to determine risk labels corresponding to multiple risk objects based on the first status data and the second status data. The control command generation module is used to generate control commands for the vehicle based on the risk tags for multiple risk objects; The control module is used to control the vehicle's actions based on the control commands, so as to warn of or avoid the risky object.

[0012] To achieve the above objectives, according to another aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the above embodiments.

[0013] To achieve the above objectives, according to another aspect of the present invention, a vehicle is provided, including the vehicle control device based on the coordination of various safety functions as described in the above embodiments.

[0014] One embodiment of the above invention has the following advantages or beneficial effects: by constructing a unified risk perception and collaborative control architecture, the command conflict and vehicle instability caused by the independent operation of multiple safety functions in the traditional way are fundamentally solved. It not only achieves global optimal control under multiple risk sources, but also improves the vehicle's safety performance, ride comfort and system robustness in complex driving scenarios.

[0015] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0016] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main steps of a vehicle control method based on the coordination of various safety functions according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the main modules of a vehicle control device based on the coordination of various safety functions according to an embodiment of the present invention; Figure 3 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 4 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0017] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0019] Figure 1 This is a schematic diagram of the main steps of a vehicle control method based on the coordination of various safety functions according to an embodiment of the present invention.

[0020] like Figure 1 As shown, the vehicle control method based on the coordination of various safety functions in this embodiment of the invention mainly includes steps S101-S104: Step S101: Receive the first state data of multiple risk objects collected by sensors corresponding to each safety function of the vehicle and the second state data of the vehicle itself. Step S102: Based on the first state data and the second state data, determine the risk labels corresponding to the multiple risk objects; Step S103: For multiple risk objects, generate control commands for the vehicle based on the risk tags; Step S104: Control the vehicle's actions based on the control command to warn of or avoid the risky object.

[0021] The vehicle's safety functions include, but are not limited to, automatic emergency braking, forward collision warning, lane departure warning, lane keeping assist, and adaptive cruise control. Sensors may include front / side / rear radar (millimeter-wave), cameras (front, rear / surround view), ultrasonic equipment, lidar, inertial measurement units, and vehicle speed / steering angle / brake pedal position sensors. Specifically, the system receives perception data from various safety functions for multiple risk objects (such as pedestrians ahead, vehicles to the side, stationary obstacles, and lane markings; for lane keeping assist, lane markings can also be considered risk objects). This perception data can originate from sensors such as millimeter-wave radar, lidar, and cameras. The initial state data includes at least the type of risk object (such as pedestrian, vehicle, non-motorized vehicle, static object, traffic sign), relative position (such as distance, azimuth angle), relative speed, and acceleration.

[0022] The second state data is the vehicle's own state data, including but not limited to the vehicle's current position coordinates, driving speed, acceleration, yaw rate, heading angle, tire adhesion coefficient, and vehicle mass.

[0023] The first-state data and the second-state data are spatiotemporally aligned (e.g., timestamps are synchronized and coordinate systems are unified) to construct a global vehicle-environment state matrix, providing basic data support for subsequent risk assessment.

[0024] Based on the first and second state data, the risk of each risk object relative to the vehicle is assessed, and each risk object is labeled with a risk tag according to the assessment results, such as risk object 1-100, risk object 2-90, risk object 3-80, etc.; or risk object 1-A, risk object 2-B, risk object 3-C, etc.

[0025] Based on the risk labels of each risk object, the system comprehensively considers how to avoid collision risks with multiple risk objects or minimize collision risks, and generates control commands, such as deceleration + lane change to the left. Based on this control command, the system controls the vehicle to decelerate and change lanes to the left, thereby avoiding obstacles / or vehicles on the front and right sides; another example is deceleration + lane keeping, based on this control command, the system controls the vehicle to decelerate and keep in the lane, thereby avoiding collisions with vehicles in front and maintaining a reasonable distance between the vehicle and the lane lines on both sides.

[0026] This embodiment avoids the contradictions and conflicts in control commands caused by a single safety function responding independently to multiple risk objects in the prior art. By uniformly perceiving risk objects and coordinating various safety functions, it generates global control commands for multiple risk objects, thereby improving the stability of vehicle driving, enhancing the safety performance and ride comfort of the vehicle in complex driving scenarios, and improving the robustness of the vehicle control system.

[0027] In an optional embodiment of the present invention, when there is a moving object among the plurality of risk objects, determining the risk label corresponding to the plurality of risk objects based on the first state data and the second state data includes: predicting the movement trajectory and corresponding probability of each risk object within a preset time period in the future based on each risk object and its corresponding first state data; performing a risk score on each risk object based on the type of the risk object, the movement trajectory and corresponding probability of the risk object, and the second state data; and determining the risk label corresponding to each risk object based on the risk score result.

[0028] When the risk objects include movable risk objects (such as pedestrians or vehicles), the first state data of the movable risk object is obtained. The first state data may include position coordinates, velocity acceleration, turning angle, distance from the vehicle, azimuth angle, etc. The movement trajectory of the movable risk object is predicted based on the first state data. For example, for pedestrians in the vicinity, based on the pedestrian's location, walking speed, turning angle, acceleration, etc., the possible movement trajectory of the pedestrian within a preset time period (such as 5 seconds) is determined, such as going straight, turning left, turning right, making a U-turn, etc., and the probability of the pedestrian moving along the above movement trajectory is predicted respectively, such as 80% probability of going straight, 19% probability of turning left, 0.5% probability of turning right, and 0.5% probability of making a U-turn. For example, when dealing with surrounding vehicles, the system determines their possible trajectories based on their location, speed, acceleration, and steering angle. These trajectories might include maintaining a straight line, changing lanes to the right, or changing lanes to the left. The system then predicts the probability of each trajectory, such as an 80% probability of maintaining a straight line, a 19% probability of changing lanes to the left, and a 1% probability of changing lanes to the right. The perception and fusion layer of the control system integrates multi-sensor data with risk object tracking to uniformly detect, track, and estimate the states of surrounding vehicles, pedestrians, and static obstacles, generating a list of risk objects. This layer employs algorithms such as Kalman filtering, extended Kalman filtering, and unscented Kalman filtering to smooth and predict the motion states of risk objects. It uses multi-hypothesis tracking algorithms to perform cross-sensor risk object matching and continuous tracking, ultimately outputting a list of risk objects containing information such as confidence level, covariance matrix, classification probability, pose, and extended bounding boxes. This provides reliable environmental perception results for subsequent risk assessment.

[0029] Based on the movement trajectory of each risk object and its corresponding probability, as well as the vehicle's second state data (such as position, speed, acceleration, steering angle, etc.), it is determined which risk object the vehicle is more likely to collide with, at what location, at what time, and with what severity. Based on the type of each risk object (such as pedestrians, vehicles, or static obstacles), the hazard caused by the collision is assessed. Based on the above assessment results, a risk score is assigned to each risk object, and a risk label is assigned to each risk object based on the risk score results, such as risk object 1-A, risk object 2-B, risk object 3-C, etc., where A, B, and C are risk labels.

[0030] This embodiment introduces a probabilistic trajectory prediction mechanism to quantify and capture the sudden behavior of risk objects (such as pedestrians turning back or vehicles cutting in) and the uncertainty of their behavior, effectively addressing complex driving scenarios. By combining collision simulation and multi-dimensional scoring to generate risk labels, the system can implement differentiated graded control strategies based on risk levels. This not only avoids collisions in extreme situations but also prevents frequent emergency braking due to oversensitivity during daily driving, thereby improving driving safety while ensuring a smooth and comfortable ride.

[0031] In an optional embodiment of the present invention, the step of scoring each risk object based on the type of the risk object, the movement trajectory of the risk object and its corresponding probability, and the second state data includes: predicting the vehicle's trajectory based on the second state data; and for each risk object: calculating the collision probability, collision time distribution, collision energy, and potential hazard between the vehicle and the risk object based on the vehicle's trajectory, the type of the risk object, the movement trajectory of the risk object and its corresponding probability, and determining the risk score / level of the risk object.

[0032] Among them, vehicle trajectory refers to the trajectory of this vehicle, and the types of risk objects include pedestrians, vehicles, static obstacles, etc.

[0033] For each identified risk object, a multi-dimensional collision situation assessment model is constructed. First, first-state data is acquired, and the kinematic characteristics and trajectory probability distribution of each risk object are determined based on this data. Second-state data is acquired, and the real-time state of the vehicle and its trajectory are determined based on this data. Spatiotemporal fusion calculations are performed on the possible movement trajectories of the risk objects and the vehicle's planned or predicted path. Specifically, based on the risk object's movement trajectory and its corresponding probability distribution, all possible movement trajectories of the risk object within a preset future timeframe are overlapped with the vehicle's trajectory to determine the collision probability between the vehicle and the risk object. Simultaneously, the time sequence of possible collision events is analyzed to generate a collision time distribution curve to identify the time window with the highest concentration of collision risk. Different weighting coefficients are assigned to the risk object type (e.g., pedestrians, non-motorized vehicles, motorized vehicles, static obstacles, etc.), and the expected collision energy is calculated using the kinetic energy formula, combined with the relative velocity at the moment of collision. Based on this, the severity of the collision consequences is comprehensively assessed, considering the type of collision object and the collision location, to determine the potential hazard value. Based on the collision probability, collision time distribution, collision energy, and potential hazards calculated above, a comprehensive assessment of the risk score / level of the object is conducted. The risk level corresponding to the object can be flexibly set as needed, such as low risk, medium risk, or high risk.

[0034] The collision risk assessment layer of the control system is the core decision-making layer of this scheme. It combines the trajectory prediction information of the vehicle and the trajectory of the risk object, and calculates the collision probability, expected collision energy, collision time distribution and potential hazards through methods such as Monte Carlo sampling, probabilistic occupancy grid, analytical approximation algorithm and cost function. Based on the calculation results, it generates a risk score for each risk object and outputs it in order of priority, providing a quantitative and reliable basis for risk avoidance for subsequent control decisions.

[0035] This embodiment can identify and quantify the hidden risks of collisions through collision simulation and multi-dimensional hazard quantification assessment. By comprehensively considering multi-dimensional indicators such as collision probability, time urgency, energy level, and object type, it generates an objective and quantifiable risk score / level, enabling the vehicle control system to implement graded and precise differentiated responses, thereby improving driving safety while ensuring passenger comfort.

[0036] In an optional embodiment of the present invention, the step of generating control instructions for the vehicle based on the risk tags for multiple risk objects includes: setting a priority for each risk object based on the risk score / level corresponding to the multiple risk objects; and generating a control strategy and corresponding control instructions for the vehicle based on the priority, road environment constraints, and passenger comfort / safety constraints.

[0037] Specifically, based on the risk labels of multiple risk objects and their corresponding quantified risk scores / levels, a hierarchical planning and control logic is executed. Specifically, a priority mapping matrix is ​​constructed based on the risk scores / levels of each risk object. The system sets high-risk objects (e.g., "high-risk") as the highest priority, medium-risk objects (e.g., "medium-risk") as the second-highest priority, and low-risk objects (e.g., "low-risk") as the lowest priority. Control strategies are generated based on this priority ranking to ensure that resources are prioritized for responding to high-risk objects. In addition to prioritizing risk objects, the generated control strategy also needs to consider real-time road environment constraints (such as lane topology, speed limits, and static obstacle distribution) and passenger comfort / safety constraints (such as maximum deceleration threshold and lateral acceleration threshold). An optimization algorithm is then used to solve for the optimal control strategy, enabling the vehicle to execute the following control logic: For the highest priority risk objects, the system prioritizes safety constraints, even at the cost of some comfort (such as triggering emergency braking or emergency avoidance); for lower priority risk objects, the system prioritizes comfort constraints while meeting basic safety requirements, employing smooth deceleration or trajectory deviation strategies; for basic priority risk objects, the system only makes minor adjustments when necessary to maintain driving stability.

[0038] Based on the generated optimal control strategy, the control system calculates specific control commands, including acceleration, yaw rate, or steering angle, and sends the control commands to the underlying actuators of the vehicle (such as motor controllers, steering gears, etc.).

[0039] This embodiment effectively resolves the contradiction between safety and comfort in vehicle driving by setting risk priorities, and can dynamically balance safety and riding experience under limited resources. At the same time, by integrating road environment constraints, it ensures that the generated control commands not only conform to the feasibility of the road environment, but also achieve globally optimal path planning and control decisions in complex driving scenarios, thereby improving the robustness and intelligence of the vehicle in dealing with multi-risk source conflict scenarios.

[0040] In an optional embodiment of the present invention, based on the first state data and the second state data, it is determined that the probability of one or more of the multiple risk objects colliding with the vehicle exceeds a preset probability threshold, and the vehicle is controlled to brake suddenly.

[0041] Based on the first state data (the motion characteristics of the risk object) and the second state data (the vehicle's own state), the collision probability between the vehicle and the risk object is determined. If the collision probability exceeds a preset probability threshold (e.g., 90%), an emergency avoidance maneuver is directly executed against that risk object. In other words, as soon as the predicted collision probability between a risk object and the vehicle exceeds the preset probability threshold, an avoidance maneuver is immediately executed against that risk object, without waiting for a series of operations such as collision probability assessment, risk scoring, and risk priority ranking of other risk objects before responding to that risk object. This embodiment can be implemented through a separate low-latency emergency stop submodule / system. This separate low-latency emergency stop submodule / system, as the last line of defense, does not rely on the complex calculations of the main controller and responds independently and with priority to emergency risk objects. In extreme scenarios, it enforces maximum braking torque, bringing the vehicle to a stop in the shortest possible time, thereby avoiding a collision or reducing the damage from a collision.

[0042] This embodiment employs a dual defense system of global safety defense and fallback safety defense to ensure that maximum braking can be triggered immediately in emergency situations, fundamentally guaranteeing vehicle safety in extreme scenarios.

[0043] In an optional embodiment of the present invention, the control strategy includes at least one of the following: information prompts, audible / visual alarms, longitudinal control, and combined longitudinal and transverse control.

[0044] Based on the generated control strategy, a multi-dimensional intervention mechanism is constructed, which includes an early warning strategy and / or an intervention strategy. Specifically, the control strategy includes at least one of the following strategies: Information prompting strategy: Through in-vehicle human-machine interaction systems, such as central control screen, instrument panel screen, head-up display, etc., display the real-time status of risk objects, collision probability and suggested actions to the driver or passengers to assist them in making proactive decisions.

[0045] Audible / visual warning strategy: Utilize voice assistants, in-vehicle speakers, buzzers, or indicator lights to issue tiered warning signals (such as prompt voices, buzzers of different frequencies, and warning lights of different colors) to quickly attract the driver's attention in the form of sensory stimulation, so that the driver is alert to the risk object and can respond in a timely manner.

[0046] Longitudinal control strategy: Performing operations such as deceleration, acceleration, or maintaining a constant speed to shorten or lengthen the safe distance and mitigate the risk of collision.

[0047] Combined longitudinal and lateral control strategy: Coordinated control of the vehicle's longitudinal speed and lateral steering to perform emergency avoidance, lane keeping or trajectory deviation, achieving optimal path planning and obstacle avoidance in complex traffic flow.

[0048] The system dynamically combines the above control strategies according to the risk level indicated by the risk label to form a hierarchical and progressive response sequence. For example, in low-risk scenarios, information prompts are given priority; in medium-risk scenarios, audible and visual alarms are superimposed and longitudinal deceleration is combined; and in high-risk scenarios, longitudinal and transverse joint control or emergency braking is directly activated to avoid vehicle collision accidents.

[0049] This embodiment constructs a hierarchical and progressive multi-dimensional intervention mechanism, which can improve human-machine collaboration efficiency through auxiliary prompts in normal scenarios, and control the vehicle to perform longitudinal or lateral movements in emergency situations, effectively avoiding collision risks and improving the vehicle's robustness and safety in dealing with complex driving scenarios.

[0050] In an optional embodiment of the present invention, the method further includes: controlling the vehicle to issue a warning / prompt information in response to the control command.

[0051] For example, through in-vehicle human-machine interaction systems, such as the central control screen, instrument panel, and head-up display, the real-time status of the risk object, the probability of collision, and suggested actions can be displayed to the driver or passengers to assist them in making proactive decisions. By using voice assistants, in-vehicle speakers, buzzers, or indicator lights, graded warning signals can be issued (such as prompt voices, buzzers of different frequencies, and warning lights of different colors) to quickly attract the driver's attention in the form of sensory stimulation, so that the driver is alert to the risk object and can respond in a timely manner.

[0052] In an optional embodiment of the present invention, the decision chain that generates the control command is recorded.

[0053] By generating operational logs and recording the decision chain for generating control commands, data from every step—from risk perception and risk assessment to decision-making and control—is completely saved, forming a replayable decision-making process. This allows for the replay of the system state at the time of an accident, enabling the determination of whether the system was functioning properly and how responsibility was assigned. In addition, engineers can use the logs to reproduce scenarios, optimize the parameters of perception and risk assessment algorithms, and improve the performance of the control system. These operational logs also meet the requirements of autonomous driving regulations regarding data retention and traceability.

[0054] The vehicle control method based on the coordination of various safety functions in this invention fundamentally solves the command conflicts and vehicle instability caused by the independent operation of multiple safety functions in the traditional way by constructing a unified risk perception and collaborative control architecture. It not only achieves global optimal control under multiple risk sources, but also improves the vehicle's safety performance, ride comfort and system robustness in complex driving scenarios.

[0055] Figure 2 This is a schematic diagram of the main modules of a vehicle control device 200 based on the coordination of various safety functions according to an embodiment of the present invention.

[0056] like Figure 2 As shown, the vehicle control device 200 based on the coordination of various safety functions in this embodiment of the invention includes: a data receiving module 201, a risk assessment module 202, a control command generation module 203, and a control module 204, wherein, The data receiving module 201 is used to receive the first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and the second state data of the vehicle itself. The risk assessment module 202 is used to determine risk labels corresponding to multiple risk objects based on the first status data and the second status data; The control command generation module 203 is used to generate control commands for the vehicle based on the risk tags for multiple risk objects; The control module 204 is used to control the vehicle's actions based on the control commands, so as to warn of or avoid the risk object.

[0057] In an optional embodiment of the present invention, if there is a moving object among the plurality of risk objects, the risk assessment module 202 is further configured to predict the movement trajectory of each risk object within a preset time period and its corresponding probability based on each risk object and its corresponding first state data; to perform a risk score on each risk object based on the type of the risk object, the movement trajectory of the risk object and its corresponding probability, and the second state data; and to determine the risk label corresponding to each risk object based on the risk score result.

[0058] In an optional embodiment of the present invention, the risk assessment module 202 is further configured to predict the vehicle's trajectory based on the second state data; and for each risk object: based on the vehicle's trajectory, the type of the risk object, the movement trajectory of the risk object and its corresponding probability, calculate the collision probability, collision time distribution, collision energy and potential hazard between the vehicle and the risk object, and determine the risk score / level of the risk object.

[0059] In an optional embodiment of the present invention, the control command generation module 203 is further configured to set a priority for each of the risk objects according to the risk scores / levels corresponding to the multiple risk objects; and to generate a control strategy and its corresponding control commands for the vehicle according to the priority, road environment constraints, and passenger comfort / safety constraints.

[0060] In an optional embodiment of the present invention, the control module 204 is further configured to determine, based on the first state data and the second state data, that the probability of one or more of the multiple risk objects colliding with the vehicle exceeds a preset probability threshold, and control the vehicle to brake suddenly.

[0061] In an optional embodiment of the present invention, the control strategy includes at least one of the following: information prompts, audible / visual alarms, longitudinal control, and combined longitudinal and transverse control.

[0062] In an optional embodiment of the present invention, the control module 204 is further configured to control the vehicle to issue a warning / prompt information in response to the control command; and / or to record the decision chain that generates the control command.

[0063] The vehicle control device based on the coordination of various safety functions in this invention fundamentally solves the command conflicts and vehicle instability caused by the independent operation of multiple safety functions in traditional systems by constructing a unified risk perception and collaborative control architecture. It not only achieves global optimal control under multiple risk sources, but also improves the vehicle's safety performance, ride comfort and system robustness in complex driving scenarios.

[0064] Figure 3 An exemplary system architecture 300 is shown, which can be applied to the vehicle control method or device based on the coordination of various safety functions according to embodiments of the present invention.

[0065] like Figure 3As shown, the system architecture 300 may include a sensor device 301 that collects data on risk objects in the surrounding environment, corresponding to various safety functions of the vehicle, a network 302, and a controller 303. The network 302 serves as a medium to provide a communication link between the sensor device 301 and the controller 303. The network 302 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0066] The controller 303 can interact with the sensor device 301 via the network 302 to receive or send data, etc. The sensor device 301 may include cameras, millimeter-wave radar, lidar, inertial measurement units, global positioning modules, etc. The controller 303 may be a controller that provides various vehicle control services.

[0067] Sensor device 301 collects risk object data in the surrounding environment. Based on the collected risk object data, controller 303 receives first state data of multiple risk objects collected by sensor device 301 and second state data of the vehicle itself. According to the first state data and second state data, controller 303 determines the risk labels corresponding to multiple risk objects. For multiple risk objects, according to the risk labels, controller 303 generates control commands for the vehicle. Based on the control commands, controller 303 controls the vehicle's actions to warn of or avoid risk objects.

[0068] It should be noted that the vehicle control method based on the coordination of various safety functions provided in this embodiment of the invention can be executed by the controller 303, and correspondingly, the vehicle control device based on the coordination of various safety functions can be set in the controller 303.

[0069] It should be understood that Figure 3 The number of sensor devices, networks, and controllers shown is merely illustrative. Any number of sensor devices, networks, and controllers can be used depending on implementation requirements.

[0070] The following is for reference. Figure 4 It shows a schematic diagram of the structure of a computer system 400 suitable for implementing an electronic device according to embodiments of the present invention. Figure 4 The sensor device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0071] like Figure 4As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage section 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the computer system 400. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0072] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0073] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the functions defined above in the system of this invention.

[0074] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0075] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0076] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor may be described as including a data receiving module, a risk assessment module, a control instruction generation module, and a control module. The names of these modules do not necessarily limit the module itself; for example, the control module may also be described as "a module that controls the vehicle's actions based on the control instructions."

[0077] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: receiving first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and second state data of the vehicle itself; determining risk tags corresponding to the multiple risk objects based on the first state data and the second state data; generating control commands for the vehicle based on the risk tags for the multiple risk objects; and controlling the vehicle's actions based on the control commands to warn of or avoid the risk objects.

[0078] According to the technical solution of the present invention, by constructing a unified risk perception and collaborative control architecture, the command conflict and vehicle instability caused by the independent operation of multiple safety functions in the traditional way are fundamentally solved. It not only achieves global optimal control under multiple risk sources, but also improves the safety performance, ride comfort and system robustness of the vehicle in complex driving scenarios.

[0079] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle control method based on the coordination of various safety functions, characterized in that, include: Receive first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and second state data of the vehicle itself; Based on the first state data and the second state data, risk labels corresponding to multiple risk objects are determined; For multiple risk objects, control commands are generated for the vehicle based on the risk tags; The vehicle's actions are controlled based on the control commands to provide warnings or avoid the risky object.

2. The method according to claim 1, characterized in that, When a moving object exists among the plurality of risk objects, determining the risk labels corresponding to the plurality of risk objects based on the first state data and the second state data includes: Based on each risk object and its corresponding first state data, predict the movement trajectory of each risk object within a preset time period and its corresponding probability. Based on the type of the risk object, the movement trajectory of the risk object and its corresponding probability, and the second state data, a risk score is given for each risk object; Based on the risk scoring results, a risk label is determined for each of the risk objects.

3. The method according to claim 2, characterized in that, The risk scoring for each risk object is based on its type, movement trajectory and corresponding probability, and the second state data, including: Based on the second state data, predict the vehicle's trajectory; For each of the aforementioned risk objects: Based on the vehicle's trajectory, the type of the risk object, the movement trajectory of the risk object and its corresponding probability, the collision probability, collision time distribution, collision energy and potential hazard between the vehicle and the risk object are calculated, and the risk score / level of the risk object is determined.

4. The method according to claim 3, characterized in that, The step of generating control commands for the vehicle based on the risk tags for multiple risk objects includes: Based on the risk scores / levels corresponding to the multiple risk objects, a priority is assigned to each of the risk objects; Based on the priorities, road environment constraints, and passenger comfort / safety constraints, a control strategy and its corresponding control commands are generated for the vehicle.

5. The method according to any one of claims 1-4, characterized in that, Also includes: Based on the first state data and the second state data, if it is determined that the probability of one or more of the multiple risk objects colliding with the vehicle exceeds a preset probability threshold, the vehicle is controlled to brake suddenly.

6. The method according to claim 4, characterized in that, The control strategy includes at least one of the following: information prompts, audible / visual alarms, longitudinal control, and combined longitudinal and transverse control.

7. The method according to any one of claims 1-4, characterized in that, Also includes: In response to the control command, the vehicle is controlled to issue a warning / prompt message; And / or, Record the decision chain that generates the control command.

8. A vehicle control device based on the coordination of various safety functions, characterized in that, include: The system comprises a data receiving module, a risk assessment module, a control command generation module, and a control module. The data receiving module is used to receive the first state data of multiple risk objects collected by sensors corresponding to various safety functions of the vehicle and the second state data of the vehicle itself. The risk assessment module is used to determine risk labels corresponding to multiple risk objects based on the first status data and the second status data. The control command generation module is used to generate control commands for the vehicle based on the risk tags for multiple risk objects; The control module is used to control the vehicle's actions based on the control commands, so as to warn of or avoid the risky object.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in claims 1-7.

10. A vehicle, characterized in that, include: The vehicle control device based on the coordination of various safety functions as described in claim 8.

Images