Pedestrian protection system and method of controlling the same

Abstract

The application relates to the technical field of automobile safety, in particular to a pedestrian protection system and a control method thereof. The system comprises: a vehicle-end intelligent sensing and decision module, which is used for acquiring pedestrian information of a target direction of a vehicle, and predicting a collision risk and a collision posture of the vehicle and the pedestrian according to the pedestrian information; in response to the collision risk meeting a preset collision condition, a cooperative protection strategy of the vehicle and an external protection device is generated according to the collision posture; an active vehicle-outside protection execution module, which is used for dynamically adjusting working parameters and action forms of the external protection device according to the cooperative protection strategy; and a cooperative control module, which is used for controlling a motion state of the vehicle according to a system protection strategy. The system can realize a leap from passive deployment after a pedestrian collides with a vehicle to active decision and cooperative protection in a whole process before and after the collision, significantly reduces the injury risk of the pedestrian to the vehicle, and improves the driving safety of the vehicle.

Description

Technical Field

[0001] This application relates to the field of automotive safety technology, and in particular to a pedestrian protection system and its control method. Background Technology

[0002] With the acceleration of urbanization, traffic accidents between vehicles and pedestrians have become a significant safety issue.

[0003] Existing pedestrian protection technologies mainly fall into two categories: one is automatic emergency braking systems based on vision or radar, which aim to completely avoid accidents before a collision occurs; the other is passive protection devices, such as pop-up hoods and external airbags, which are typically triggered in a fixed pattern after sensors detect a collision.

[0004] However, the above-mentioned technical solutions are difficult to effectively reduce the degree of collision damage and have limited protection for pedestrians, which urgently need to be improved. Summary of the Invention

[0005] This application provides a pedestrian protection system and its control method, which can predict collisions and generate a human-vehicle integrated collaborative protection strategy by the vehicle-end intelligent perception and decision module. It synchronously links the active vehicle external protection execution module and the collaborative control module to adjust the form of the vehicle external protection device and the vehicle driving status, breaking down the information barriers between traditional braking and protection equipment. When a collision cannot be avoided, it can comprehensively reduce the overall damage to pedestrians and improve the vehicle's protection effect on pedestrians.

[0006] A first aspect of this application provides a pedestrian protection system, comprising: a vehicle-side intelligent perception and decision-making module, an active external protection execution module, and a collaborative control module. The vehicle-side intelligent perception and decision-making module is communicatively connected to both the active external protection execution module and the collaborative control module. The vehicle-side intelligent perception and decision-making module is used to acquire pedestrian information at the vehicle's target location, predict the collision risk and collision posture of the vehicle and pedestrian based on the pedestrian information, and generate a collaborative protection strategy for the vehicle and external protection devices based on the collision posture when the collision risk meets preset collision conditions. The active external protection execution module is used to dynamically adjust the operating parameters and operational mode of the external protection devices according to the collaborative protection strategy. The collaborative control module is used to control the vehicle's motion state according to the system protection strategy.

[0007] In one embodiment of this application, the vehicle-side intelligent perception and decision-making module includes: a heterogeneous sensor fusion unit, used to generate pedestrian information based on perception data from vehicle-mounted sensors, wherein the pedestrian information includes pedestrian position, pedestrian speed, pedestrian body size, pedestrian orientation, and pedestrian coordinates; a behavior and trajectory prediction unit, used to predict the pedestrian's movement trajectory and behavioral intention within a preset time period based on the pedestrian information; and a risk decision and strategy generation unit, used to predict the collision risk and collision posture of the vehicle and pedestrian based on the movement trajectory and behavioral intention, and in response to the collision risk meeting preset collision conditions, generate a collaborative protection strategy for the vehicle and external protection devices based on the collision posture. In one embodiment of this application, the risk decision and strategy generation unit is specifically used to: calculate the motion trajectory and the behavioral intention based on a preset multi-objective optimization algorithm and a pedestrian human injury biomechanical model, so as to predict the collision risk and collision posture of the vehicle and the pedestrian.

[0008] In one embodiment of this application, it further includes: a vehicle-road cooperative interface module, used to receive beyond-line-of-sight pedestrian information and / or area risk warning information from roadside sensing devices; the heterogeneous sensor fusion unit is specifically used to generate the pedestrian information based on the beyond-line-of-sight pedestrian information and / or the area risk warning information, as well as the sensing data from the vehicle-mounted sensors.

[0009] In one embodiment of this application, the collaborative protection strategy includes: after a collision occurs, controlling the vehicle to decelerate or maintain a low speed, and automatically sending collision event information, pedestrian injury assessment information, and vehicle location information to an emergency rescue platform via an onboard communication unit.

[0010] In one embodiment of this application, the cooperative protection strategy includes: at least one adaptive braking or steering control command applied to the vehicle; and at least one trigger command applied to the external protection device.

[0011] A second aspect of this application provides a control method for a pedestrian protection system, comprising: acquiring pedestrian information at the target location of a vehicle, and predicting the collision risk and collision posture of the vehicle and the pedestrian based on the pedestrian information; in response to the collision risk meeting preset collision conditions, generating a collaborative protection strategy for the vehicle and an external protection device based on the collision posture; dynamically adjusting the operating parameters and function mode of the external protection device according to the collaborative protection strategy, and controlling the motion state of the vehicle.

[0012] A third aspect of this application provides a vehicle including the pedestrian protection system described above.

[0013] A fourth aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the control method of the pedestrian protection system as described in the above embodiments.

[0014] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the control method of the pedestrian protection system described above.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a block diagram of a pedestrian protection system provided according to an embodiment of this application; Figure 2 This is a schematic diagram of the overall architecture and information flow of a pedestrian protection system according to a specific embodiment of this application; Figure 3 This is a flowchart of a control method for a pedestrian protection system according to an embodiment of this application; Figure 4 This is a schematic diagram of the workflow and decision-making logic in a typical collision scenario according to a specific embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0017] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0018] The pedestrian protection system and control method of this application are described below with reference to the accompanying drawings. In view of the problem mentioned in the background section that the prior art is unable to effectively reduce the degree of collision damage and has limited protection effect on pedestrians, this application provides a pedestrian protection system.

[0019] Figure 1 This is a block diagram of a pedestrian protection system provided in an embodiment of this application.

[0020] like Figure 1 As shown, the pedestrian protection system 10 includes: a vehicle-side intelligent perception and decision-making module 100, an active vehicle-side external protection execution module 200, and a collaborative control module 300. The vehicle-side intelligent perception and decision-making module 100 is communicatively connected to the active vehicle-side external protection execution module 200 and the collaborative control module 300, respectively.

[0021] Among them, the vehicle-side intelligent perception and decision-making module 100 is used to acquire pedestrian information at the vehicle's target location, predict the collision risk and collision posture of the vehicle and pedestrian based on the pedestrian information, and generate a collaborative protection strategy for the vehicle and external protection devices based on the collision posture when the collision risk meets the preset collision conditions.

[0022] In actual implementation, pedestrian information can be obtained based on sensor signals collected by vehicle-mounted and roadside sensing devices, including but not limited to visual cameras, millimeter-wave radar, lidar, ultrasonic radar, etc. There are no specific limitations here, so as to obtain pedestrian information from all directions of the vehicle based on the above sensing devices.

[0023] In this system, collision risk can be used as a comprehensive hazard quantification index calculated based on pedestrian information to describe the probability, severity, and injury level of a collision between a vehicle and a pedestrian. The preset collision conditions are the judgment thresholds and logical rules pre-defined by the system. When the collision risk calculated in real time meets the conditions, the system abandons the "complete collision avoidance" logic and switches to a collaborative protection strategy of the vehicle and external protection devices with the goal of minimizing pedestrian damage.

[0024] To more clearly illustrate the vehicle-side intelligent perception and decision-making module 100 described above, in one embodiment of this application, the vehicle-side intelligent perception and decision-making module 100 includes a heterogeneous sensor fusion unit, a behavior and trajectory prediction unit, and a risk decision and strategy generation unit. The heterogeneous sensor fusion unit generates pedestrian information based on perception data from vehicle-mounted sensors. This pedestrian information includes pedestrian position, pedestrian speed, pedestrian body size, pedestrian orientation, and pedestrian coordinates. The behavior and trajectory prediction unit predicts the pedestrian's movement trajectory and behavioral intention within a preset time period based on the pedestrian information. The risk decision and strategy generation unit predicts the collision risk and collision posture of the vehicle and pedestrian based on the movement trajectory and behavioral intention. In response to the collision risk meeting preset collision conditions, it generates a collaborative protection strategy for the vehicle and external protection devices based on the collision posture.

[0025] In this embodiment, the heterogeneous sensor fusion unit first performs noise reduction and target screening on the raw sensing data from sensors such as millimeter-wave radar, visual cameras, and lidar. It can also perform joint calibration with the sensors via a time synchronization protocol to achieve temporal alignment and spatial coordinate unification of multi-source data. Then, after matching the same pedestrian target using a target association algorithm, for example, based on a feature-level fusion architecture and an extended Kalman filter algorithm, it calculates the pedestrian's position, speed, body shape, orientation, and key joint coordinates. Finally, this information is encapsulated into standardized pedestrian information and transmitted in real-time to the downstream behavior and trajectory prediction unit via the vehicle's Ethernet / CAN bus. Here, pedestrian coordinates refer to the coordinates of key joint nodes of the pedestrian, such as the three-dimensional coordinates of the pedestrian's head, torso, and limbs.

[0026] The behavior and trajectory prediction unit is a mid-level prediction unit in the vehicle-side intelligent perception and decision-making module 100. Upstream, it receives standardized pedestrian information output from the heterogeneous sensor fusion unit; downstream, it outputs the pedestrian's short-term movement trajectory and behavioral trends (behavioral intentions), thus providing a basis for prediction for the risk decision-making and strategy generation unit. Its core function is to predict the pedestrian's future actions in advance, compensating for the limitation of sensors only being able to collect instantaneous data, and allowing sufficient time for the vehicle to activate braking and protective devices. In this embodiment, the preset time period refers to a future time period; for example, predicting the pedestrian's movement trajectory and behavioral intentions in the next 3-5 seconds based on pedestrian information.

[0027] The risk decision-making and strategy generation unit is the core decision-making hub of the vehicle-side intelligent perception and decision-making module 100. It acts as a bridge between upstream and downstream components. Upstream, it receives the pedestrian's predicted movement trajectory and behavioral intent from the behavior and trajectory prediction unit; downstream, it outputs an integrated collaborative protection strategy, which is then distributed to the collaborative control module and the active external protection execution module. The core logic is: first, based on the predicted trajectory, it assesses whether a collision will occur and how; once a danger threshold is reached, it outputs a coordinated control scheme for the vehicle and external protective equipment based on the estimated impact posture (e.g., an adult standing upright, a child bending over, a pedestrian sideways), thus achieving risk prediction, determining whether a collision is inevitable, and adaptively generating a damage reduction strategy.

[0028] In one embodiment of this application, the risk decision and strategy generation unit can be used to: calculate the motion trajectory and behavioral intention based on a preset multi-objective optimization algorithm and a pedestrian human injury biomechanical model, so as to predict the collision risk and collision posture of vehicles and pedestrians.

[0029] The preset multi-objective optimization algorithm refers to a lightweight multi-objective iterative solution algorithm that is pre-built into the risk decision and strategy generation unit, such as the multi-objective particle swarm optimization algorithm, which is not specifically limited in this embodiment.

[0030] The pedestrian human injury biomechanical model is essentially a digital simulation model library based on real vehicle pedestrian collision tests, human dummy tests, and medical biological data calibration. It is divided into adult models and children's models according to the population; into head injury sub-models, chest compression sub-models, and lower limb impact sub-models according to the impact location; and into frontal impact, side impact, and low-lying child impact sub-models according to the impact posture.

[0031] Specifically, this embodiment first performs temporal interpolation standardization on the predicted pedestrian trajectory, unifying the coordinate system and data format of multi-source sensing data, outputting a continuous and regular temporal trajectory of the pedestrian, and assigning risk weights to the multi-objective algorithm according to the pedestrian's behavioral intention (for example, if the behavioral intention is that the pedestrian wants to cross the road, the system defaults to the maximum risk level, and the algorithm prioritizes calculating the extreme case of collision, determining earlier that avoidance is impossible); then, the spatiotemporal coupling relationship between the vehicle and pedestrian trajectories can be iteratively solved through a preset multi-objective optimization algorithm, screening the critical collision condition with the most severe damage, and outputting the remaining collision... Parameters such as time, impact velocity, and impact angle are input into a matched pedestrian biomechanical model (e.g., head injury sub-model, chest compression sub-model, lower limb impact sub-model) to simulate the force and geometric posture of the human body during the impact process. This allows for the fusion of spatiotemporal collision indicators and human injury indicators to quantify and classify collision risks, and the simulated relative collision pattern between the pedestrian and the vehicle is extracted as the collision posture. When a collision is unavoidable, a collaborative protection strategy is generated, including vehicle motion adjustment commands and external protection device trigger commands, with the goal of minimizing the overall pedestrian injury.

[0032] The collaborative protection strategy may include control commands implemented on the vehicle and external protection devices before and after a collision, such as at least one adaptive braking or steering control command implemented on the vehicle to reduce the severity of the collision, at least one differentiated trigger command for the external protection devices based on the predicted collision point and the pedestrian's posture (collision posture), and after a collision, controlling the vehicle to decelerate or maintain a low speed to reduce the secondary impact of the pedestrian being thrown to the ground, and automatically sending collision event information, pedestrian's estimated injury information, and vehicle location information to the emergency rescue platform through the vehicle communication unit, etc.

[0033] For example, when the system predicts a collision with a bent-over child (the predicted point of impact is at the front of the hood and the lower edge of the windshield), the resulting strategy will differ from that for an upright adult. This strategy may include: triggering maximum bounce and maximum softening in the front area of ​​the hood, and simultaneously triggering external airbags covering the A-pillar and the lower edge of the windshield to address the higher position where the child's head may hit.

[0034] For example, in a low-speed collision scenario, a pedestrian is hit and falls in front of a vehicle. A traditional vehicle braking immediately could cause the pedestrian to fall and sustain injury. This system can control the vehicle to maintain a low speed (e.g., 5-10 km / h) and travel a very short distance smoothly after a collision, allowing the pedestrian's body to be relatively smoothly "placed" on the ground instead of being "thrown" away, thus significantly reducing secondary head and torso injuries caused by the fall.

[0035] Furthermore, in one embodiment of this application, the pedestrian protection system 10 may further include: a vehicle-road cooperative interface module, used to receive beyond-line-of-sight pedestrian information and / or area risk warning information from roadside sensing devices; and a heterogeneous sensor fusion unit, specifically used to generate pedestrian information based on beyond-line-of-sight pedestrian information and / or area risk warning information, as well as sensing data from vehicle-mounted sensors.

[0036] The roadside sensing equipment may include vehicle-to-everything (V2X) devices. These V2X devices are a complete hardware system that enables low-latency wireless interaction between vehicles and road infrastructure. They can be used to collect and acquire beyond-line-of-sight pedestrian information and regional risk warning information. Beyond-line-of-sight pedestrian information can be used to describe the position, movement, and posture of individual or group pedestrians, filling blind spots of vehicle-mounted or other sensors, and directly participating in pedestrian information fusion, trajectory prediction, and collision risk calculation. Regional risk warning information can describe the inherent danger attributes of the entire road area, used to raise the system's warning level in advance and dynamically adjust the preset collision judgment threshold. By setting up a vehicle-to-everything (V2X) interface module to receive beyond-line-of-sight pedestrian information or regional risk warnings from roadside units, the sensing range and decision-making foresight of the vehicle-side intelligent sensing and decision-making module 100 can be expanded.

[0037] The active external protection execution module 200 is used to dynamically adjust the working parameters and operating mode of the external protection device according to the collaborative protection strategy.

[0038] The active external protection execution module 200 includes at least one of the following adjustable external protection devices: The adaptive pop-up engine hood has adjustable pop-up height, stiffness in specific areas, and actuation timing. External airbags, whose deployment position, inflation capacity and deployment shape are adjustable, cover areas including the lower edge of the windshield, A-pillar and upper part of the front bumper; An active front bumper has adjustable crumple characteristics of its internal buffer structure or adjustable coefficient of friction of its external contact surface.

[0039] For example, if it is anticipated that a child crossing the road will be hit, and the point of impact is above the windshield at the front of the car, the engine hood can be adjusted: raise the pop-up height to give the hood more buffer space; adjust the external airbags: inflate in advance and increase the inflation volume to protect the child's head; adjust the front bumper: soften it to cushion the impact to the legs.

[0040] If an adult were to crash head-on into the center of the hood, the airbag inflation force would be reduced, and the hood would only be raised slightly.

[0041] The so-called working parameters may include, but are not limited to: launch height, airbag inflation speed, cushioning stiffness, and triggering timing; the so-called function may include, but are not limited to: how much the hood is raised, whether the airbag is fully or partially deployed, and whether the bumper is hard or soft.

[0042] The cooperative control module 300 is used to control the vehicle's motion state according to the cooperative protection strategy.

[0043] This module determines how the vehicle should be driven, adjusting braking, steering, and speed according to the protection strategy to reduce impact force and aim for the best impact area at the front of the vehicle. For example, it avoids sudden braking and locking up, gradually reducing the speed to around 30 km / h (at which external protective devices provide the best cushioning); or it slightly adjusts the steering wheel to move the point of impact to the softer area in the middle of the hood, avoiding the hard corners of the A-pillar; or it smoothly decelerates to prevent pedestrians from being thrown off balance and suffering secondary injuries from sudden braking. Vehicle motion status can include: speed, braking force, and wheel steering angle.

[0044] After calculating a complete protection plan (cooperative protection strategy), the risk decision and strategy generation unit simultaneously sends it to two modules: the cooperative control module 300 immediately controls the vehicle (such as deceleration and fine-tuning the direction) to reduce the impact kinetic energy; the active external protection execution module 200 synchronously adjusts the protection devices (such as the hardness and rebound of the hood, external airbags, and bumpers). The two sets of actions are executed simultaneously to minimize pedestrian injury.

[0045] Compared with the prior art, the pedestrian protection system of this application can be summarized by the following significant advantages: Strategic synergy: Breaking down information and decision-making barriers between AEB (Autonomous Emergency Braking) and passive protection devices to achieve globally optimal damage control in unavoidable collision scenarios.

[0046] Adaptive protection: External protection devices (such as engine hood and airbags) can be parametrically triggered based on real-time predicted pedestrian posture and collision point to provide personalized protection.

[0047] The process is comprehensive: the protective intervention is extended from the moment of collision to before the collision (speed and attitude management) and after the collision (secondary injury suppression), forming a closed-loop protection system that covers the entire accident process.

[0048] Harm minimization: By introducing a human injury model as the core of decision-making, the system's decisions are directly guided by biomechanical damage values, achieving a fundamental shift from reducing collisions to scientifically mitigating injuries.

[0049] To explain the above embodiments more clearly, as follows: Figure 2 As shown, the system can be divided into three main levels: perception module, decision-making module, and execution module. The perception module integrates a forward-facing perception fusion unit (combining millimeter-wave radar, camera, and lidar), a vehicle-to-everything (V2X) interface, and a pedestrian feature recognition and behavior prediction unit. After acquiring environmental and pedestrian data in real time, it outputs pre-collision and collision signals to the decision-making module. The decision-making module incorporates a multi-objective optimization algorithm and a pedestrian biomechanical injury model library. It can determine unavoidable collisions and generate an integrated collaborative protection strategy, then outputs control commands to the execution module. The execution module consists of two types of control units: one manages active external protection devices such as adaptive pop-up hoods, active bumpers, and external airbags; the other is a collaborative control unit responsible for vehicle braking, steering, and overall vehicle dynamics control. The arrows in the diagram clearly indicate the flow of information and commands between modules. The entire system relies on onboard sensors and V2X to acquire environmental data. The decision-making layer outputs a unified protection plan based on optimization algorithms and human injury models, synchronously linking external protection hardware and vehicle chassis motion control to achieve integrated pedestrian injury management in collision scenarios.

[0050] The pedestrian protection system proposed in this application can collect pedestrian information and predict collision risks and impact postures through the vehicle-side intelligent perception and decision-making module. When it is determined that a collision cannot be avoided, it generates an integrated collaborative protection strategy that takes into account both vehicle motion and external protection hardware. This strategy is simultaneously sent to the active external protection execution module and the collaborative control module for joint execution. This breaks down the barriers between the traditional braking system and passive pedestrian protection devices, which are independent and have fragmented information. The collaborative control module can regulate the vehicle's braking and steering to reduce impact kinetic energy and optimize the impact point. The active external protection execution module can also adaptively adjust the working mode of the hood, external airbags, and active bumpers. This optimizes both vehicle motion control and external buffer protection simultaneously. In the case of an unavoidable pedestrian collision, it minimizes the overall damage to pedestrians, significantly reduces the severity of injuries to the head, torso, and lower limbs, and significantly improves the vehicle's safety in protecting pedestrians.

[0051] Next, refer to the appendix. Figure 3 This application describes a control method for a pedestrian protection system proposed according to embodiments thereof.

[0052] Figure 3 This is a flowchart of the control method of the pedestrian protection system according to an embodiment of this application.

[0053] like Figure 3 As shown, the control method of this pedestrian protection system includes the following steps: Step S301: Obtain pedestrian information at the vehicle's target location, and predict the collision risk and collision posture of the vehicle and pedestrians based on the pedestrian information.

[0054] Step S302: In response to the collision risk meeting the preset collision conditions, generate a collaborative protection strategy for the vehicle and external protection devices based on the collision posture.

[0055] Step S303: Dynamically adjust the working parameters and function mode of the external protection device according to the collaborative protection strategy, and control the movement state of the vehicle.

[0056] To explain the above embodiments more clearly, the control flow of the pedestrian protection system will be described below in a typical scenario (a pedestrian suddenly crossing the road).

[0057] like Figure 4 As shown, the control flow is as follows: Step S401: Initial perception detection.

[0058] Once the process is initiated, the system uses sensors to identify pedestrians, predict their trajectories, and collect data on the vehicle's own driving status. It acquires all basic environmental and vehicle data, integrates sensor information to identify pedestrians and determine if they intend to cross the road, and predicts whether their trajectories will intersect with the vehicle's path.

[0059] Step S402: Collision risk assessment.

[0060] Based on the collected information, a collision risk assessment is conducted to identify whether a collision between a person and a vehicle is unavoidable in the current scenario.

[0061] Step S403: Determine the optimization objective.

[0062] If a collision is deemed unavoidable, the core optimization objective is set as follows: generate a protection strategy that minimizes the overall damage to pedestrians.

[0063] Step S404: Retrieve the simulation model library.

[0064] By combining pre-collision related data and calling the built-in pedestrian biomechanical injury model library, the degree of pedestrian injury under different intervention schemes is simulated and calculated.

[0065] Step S405: Multi-objective optimization iterative calculation.

[0066] Based on the model library, multi-objective optimization calculations were carried out, and three types of optional intervention schemes were derived: Strategy A: full braking; Strategy B: partial braking + coordinated optimization of protection devices; Strategy C: braking + minor steering adjustment.

[0067] Step S406: Filter the optimal solution and generate instructions.

[0068] By comparing the simulation damage results of the three schemes, the optimal strategy B with the least damage is selected (such as reducing the collision speed from 50km / h to 30km / h, at which the engine hood protection efficiency is the best, and at the same time, the collision point is biased towards the center area of ​​the engine hood by slight steering adjustment), and the corresponding vehicle control commands are generated simultaneously.

[0069] The instruction set of Strategy B may include: a) sending a target deceleration instruction to the braking system; b) sending a small angle compensation instruction to the steering system; c) instructing the hood to operate in "Mode 2" (higher bounce height, activation of the soft zone in the middle and rear) based on the predicted collision point (middle and rear of the hood) and the pedestrian's posture (upright).

[0070] Step S407: Issue control commands.

[0071] The generated optimal control command is sent to the execution module to simultaneously complete vehicle motion control and trigger external protection devices. After a collision, secondary injury suppression control will also be executed. For example, after a collision, if the system detects that the pedestrian has landed on the engine hood, the collaborative control module will control the vehicle to decelerate smoothly to a stop to prevent the pedestrian from being thrown to the ground due to inertia.

[0072] It should be noted that the foregoing explanation of the pedestrian protection system embodiment also applies to the control method of the pedestrian protection system in this embodiment, and will not be repeated here.

[0073] According to the control method of the pedestrian protection system proposed in the embodiments of this application, pedestrian data can be collected first to predict collision risk and impact posture. When a collision cannot be avoided, a collaborative strategy that takes into account both the vehicle and the external protection hardware is generated. The vehicle driving status and the form of the external protection device are adjusted simultaneously to achieve human-vehicle linkage protection and minimize pedestrian collision damage.

[0074] This application also provides a vehicle that includes the pedestrian protection system described in the above embodiment.

[0075] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0076] The electronic device may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0077] When the processor 502 executes the program, it implements the control method of the pedestrian protection system provided in the above embodiments.

[0078] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0079] The memory 501 is used to store computer programs that can run on the processor 502.

[0080] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0081] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0082] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0083] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0084] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the control method of the pedestrian protection system described above.

[0085] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0086] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0087] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0088] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0089] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0090] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0092] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A pedestrian protection system, characterized in that, include: The system includes a vehicle-side intelligent perception and decision-making module, an active external protection execution module, and a collaborative control module. The vehicle-side intelligent perception and decision-making module is communicatively connected to both the active external protection execution module and the collaborative control module. The vehicle-side intelligent perception and decision-making module is used to acquire pedestrian information at the vehicle's target location, predict the collision risk and collision posture of the vehicle and pedestrian based on the pedestrian information, and generate a collaborative protection strategy for the vehicle and external protection devices based on the collision posture when the collision risk meets the preset collision conditions. The active external protection execution module is used to dynamically adjust the working parameters and operating mode of the external protection device according to the collaborative protection strategy; The collaborative control module is used to control the movement state of the vehicle according to the system protection strategy.

2. The system according to claim 1, characterized in that, The vehicle-side intelligent perception and decision-making module includes: The heterogeneous sensing fusion unit is used to generate the pedestrian information based on the sensing data of the vehicle-mounted sensors, wherein the pedestrian information includes pedestrian position, pedestrian speed, pedestrian body size, pedestrian orientation and pedestrian coordinates; The behavior and trajectory prediction unit is used to predict the movement trajectory and behavioral intentions of the pedestrian within a preset time period based on the pedestrian information. The risk decision and strategy generation unit is used to predict the collision risk and collision posture of vehicles and pedestrians based on the motion trajectory and the behavioral intention, and in response to the collision risk meeting the preset collision conditions, generate a collaborative protection strategy of vehicles and external protection devices based on the collision posture.

3. The system according to claim 2, characterized in that, The risk decision-making and strategy generation unit is specifically used for: Based on a preset multi-objective optimization algorithm and a pedestrian injury biomechanical model, the motion trajectory and the behavioral intention are calculated to predict the collision risk and collision posture of vehicles and pedestrians.

4. The system according to claim 2, characterized in that, Also includes: The vehicle-road cooperative interface module is used to receive beyond-line-of-sight pedestrian information and / or area risk warning information from roadside sensing devices; The heterogeneous sensor fusion unit is specifically used to generate the pedestrian information based on the beyond-line-of-sight pedestrian information and / or the area risk warning information, as well as the perception data from the vehicle-mounted sensors.

5. The system according to claim 1, characterized in that, The collaborative protection strategy includes: After a collision, the vehicle is controlled to decelerate or maintain a low speed, and the collision event information, pedestrian injury assessment information, and vehicle location information are automatically sent to the emergency rescue platform through the vehicle communication unit.

6. The system according to claim 1, characterized in that, The collaborative protection strategy includes: At least one adaptive braking or steering control command applied to the vehicle; and At least one trigger command for the external protection device.

7. A control method for a pedestrian protection system based on any one of claims 1-6, characterized in that, include: Obtain pedestrian information at the target location of the vehicle, and predict the collision risk and collision posture of the vehicle and pedestrians based on the pedestrian information; In response to the collision risk meeting preset collision conditions, a collaborative protection strategy for the vehicle and external protection devices is generated based on the collision posture. The working parameters and operational mode of the external protection device are dynamically adjusted according to the collaborative protection strategy, and the movement state of the vehicle is controlled.

8. A vehicle comprising a pedestrian protection system as claimed in any one of claims 1-6.

9. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the control method of the pedestrian protection system as described in claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the control method of the pedestrian protection system as described in any one of claims 7.

Images