Self-adaptive emergency braking method and system

Abstract

The invention discloses a self-adaptive emergency braking method and system, and relates to the technical field of vehicle control, and the method comprises the steps: carrying out the clustering analysis based on periodically obtained driving behavior original data, and constructing a driving style model; based on the driving style model, analyzing the driving behavior data of the target vehicle, and judging a driver style label of the target vehicle; and on the basis of the driver style label of the target vehicle, a TTC trigger threshold value and a braking curve of the target vehicle are adjusted in combination with a preset adjustment rule. According to the method, the driver style portrait is constructed through machine learning, and the triggering strategy of vehicle braking is dynamically adjusted, so that prospective personalized safety protection is realized.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, specifically to an adaptive emergency braking method and system. Background Technology

[0002] Currently, automatic emergency braking systems have become an important active safety feature in modern automobiles. However, existing AEB systems have the following significant drawbacks: 1. Standardized calibration, lack of personalization: The system's trigger thresholds (such as Time to Collision (TTC)) and braking intensity are fixed, failing to adapt to drivers with different driving styles. For aggressive drivers, the system may intervene too early, creating "phantom braking" and interfering with driving; for mild-mannered drivers, the system may intervene too late, failing to provide optimal protection.

[0003] 2. Limited perception and lack of foresight: The system relies entirely on onboard sensors (radar, cameras) to perceive risks ahead. In complex scenarios such as curves, slopes, or when obstructed by other vehicles, its perception capabilities are limited, making it unable to provide early warnings and pre-braking.

[0004] Therefore, in order to address the above problems and meet practical needs, an adaptive emergency braking technology is proposed. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this application is to provide an adaptive emergency braking method and system that uses machine learning to construct a driver style profile and dynamically adjusts the vehicle braking trigger strategy, thereby achieving forward-looking personalized safety protection.

[0006] To achieve the above objectives, the technical solution adopted in this application is as follows: In a first aspect, this application provides an adaptive emergency braking method, the method comprising the following steps: Cluster analysis is performed on periodically acquired raw driving behavior data to construct a driving style model; Based on the driving style model, the driving behavior data of the target vehicle is analyzed to determine the driver style label of the target vehicle. Based on the driver style tags of the target vehicle and combined with preset adjustment rules, the TTC trigger threshold and braking curve of the target vehicle are adjusted. The driver style labels include aggressive, standard, and mild.

[0007] Based on the above technical solution, the target vehicle has pre-stored a standard TTC trigger threshold, a mild TTC trigger threshold, and an aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

[0008] Based on the above technical solution, the original driving behavior data and the types of driving behavior data both include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

[0009] Based on the above technical solution, the method further includes the following steps: When there is a risk beyond visual range ahead of the target vehicle, a preset pre-braking strategy is executed; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

[0010] Based on the above technical solution, the pre-braking strategy includes the following steps: The braking system of the target vehicle is pre-pressurized, and a pre-braking warning message is issued; If, after the pre-braking warning information is issued, an active braking signal from the target vehicle is received within the preset warning time, braking is performed based on the adjusted TTC trigger threshold and the braking curve. If, after issuing the pre-braking warning information, no active braking signal is received from the target vehicle within the preset warning time, the main AEB system of the target vehicle is controlled to brake based on the adjusted TTC trigger threshold and the braking curve.

[0011] Secondly, this application provides an adaptive emergency braking system, the system comprising: The model building module is used to perform cluster analysis on periodically acquired raw driving behavior data to build a driving style model; The style judgment module is used to analyze the driving behavior data of the target vehicle based on the driving style model and determine the driver style label of the target vehicle. The braking adjustment module is used to adjust the TTC trigger threshold and braking curve of the target vehicle based on the driver style label of the target vehicle and in combination with preset adjustment rules. The driver style labels include aggressive, standard, and mild.

[0012] Based on the above technical solution, the target vehicle has pre-stored a standard TTC trigger threshold, a mild TTC trigger threshold, and an aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

[0013] Based on the above technical solution, the original driving behavior data and the types of driving behavior data both include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

[0014] Based on the above technical solution, the system further includes: A pre-braking module is used to execute a preset pre-braking strategy when there is a beyond-visual-range risk ahead of the target vehicle; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

[0015] Based on the above technical solution, the pre-braking module is also used to pre-pressurize the braking system of the target vehicle and issue pre-braking warning information; The pre-braking module is also used to perform braking based on the adjusted TTC trigger threshold and the braking curve if, after issuing the pre-braking warning information, an active braking signal of the target vehicle is received within a preset warning time. The pre-braking module is also used to control the main AEB system of the target vehicle to brake based on the adjusted TTC trigger threshold and the braking curve if no active braking signal is received from the target vehicle within a preset warning time after the pre-braking warning information is issued.

[0016] Compared with the prior art, the advantages of this application are: This application constructs a driver style profile through machine learning and dynamically adjusts the vehicle braking triggering strategy to achieve forward-looking personalized safety protection. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the steps of the adaptive emergency braking method according to an embodiment of this application; Figure 2 This is a schematic diagram of the adaptive emergency braking method according to an embodiment of this application. Figure 3 This is a timing diagram of the adaptive emergency braking method according to an embodiment of this application; Figure 4 This is a structural block diagram of the adaptive emergency braking system according to an embodiment of this application. Detailed Implementation

[0019] Terminology Explanation: TTC: Time To Collision; AEB: Automatic Emergency Braking.

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0022] This application provides an adaptive emergency braking method and system that uses machine learning to construct a driver style profile and dynamically adjusts the vehicle braking triggering strategy to achieve forward-looking personalized safety protection.

[0023] To achieve the aforementioned technical effects, the overall concept of this application is as follows: An adaptive emergency braking method, comprising the following steps: S1. Perform cluster analysis on the raw driving behavior data acquired periodically to construct a driving style model; S2. Based on the driving style model, analyze the driving behavior data of the target vehicle to determine the driver style label of the target vehicle. S3. Based on the driver style tags of the target vehicle and combined with preset adjustment rules, adjust the TTC trigger threshold and braking curve of the target vehicle. The driver style tags include aggressive, standard, and mild.

[0024] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0025] Firstly, see [the following] Figures 1-3 As shown in the figure, this application provides an adaptive emergency braking method, which includes the following steps: S1. Perform cluster analysis on the raw driving behavior data acquired periodically to construct a driving style model; S2. Based on the driving style model, analyze the driving behavior data of the target vehicle to determine the driver style label of the target vehicle. S3. Based on the driver style tags of the target vehicle and combined with preset adjustment rules, adjust the TTC trigger threshold and braking curve of the target vehicle. The driver style tags include aggressive, standard, and mild.

[0026] In this embodiment, a driver style profile is constructed through machine learning, and the vehicle braking triggering strategy is dynamically adjusted to achieve forward-looking personalized safety protection.

[0027] Furthermore, the target vehicle has pre-stored a standard TTC trigger threshold, a mild TTC trigger threshold, and an aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

[0028] Furthermore, the types of raw driving behavior data and driving behavior data include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

[0029] Furthermore, the method also includes the following steps: When there is a risk beyond visual range ahead of the target vehicle, a preset pre-braking strategy is executed; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

[0030] Furthermore, the pre-braking strategy includes the following steps: The braking system of the target vehicle is pre-pressurized, and a pre-braking warning message is issued; If, after the pre-braking warning information is issued, an active braking signal from the target vehicle is received within the preset warning time, braking is performed based on the adjusted TTC trigger threshold and the braking curve. If, after issuing the pre-braking warning information, no active braking signal is received from the target vehicle within the preset warning time, the main AEB system of the target vehicle is controlled to brake based on the adjusted TTC trigger threshold and the braking curve.

[0031] In specific implementation, the technical solution based on the embodiments of this application is as follows: Part 1: Constructing Adaptive AEB Based on "Driving Style Profile": 1. Data Acquisition and Feature Extraction: The system periodically collects raw driving behavior data from the vehicle's CAN bus and sensors, including but not limited to: Longitudinal behavior signals: accelerator pedal opening change rate, brake pedal force / depth, average following distance, and maximum deceleration relative to the vehicle in front; Lateral behavior signals: steering wheel angular velocity, frequency and magnitude of lateral position deviation within the lane, and average cornering speed; Time and frequency signals: overtaking frequency, frequency of rapid acceleration / braking events.

[0032] 2. Driving style model construction and classification: 2.1 Model Training: Unsupervised learning algorithms (such as K-Means clustering) are used to perform cluster analysis on a large amount of collected driving feature data, and the driver style is divided into three main categories: "aggressive", "standard", and "mild".

[0033] 2.2 Online Recognition: During daily vehicle use, the system continuously collects recent driving data (such as the past 30 days) and compares it with the established clustering model to identify and update the current driver's style label in real time.

[0034] 3. Adaptive AEB Strategy Mapping: The system dynamically adjusts the AEB control parameters based on the driving style identified in real time. 3.1 For "aggressive" drivers: Trigger threshold adjustment: The TTC trigger threshold is appropriately lowered (for example, 2.1 seconds for the standard model and 1.8 seconds for the aggressive model) to avoid premature intervention that interferes with driving.

[0035] Braking style adjustment: When the system finally triggers, it adopts a "faster and more decisive" braking curve, that is, it reaches the maximum braking force in a very short time to make up for the braking distance lost due to the later trigger.

[0036] 3.2 For "mild" drivers: Trigger threshold adjustment: Increase the TTC trigger threshold appropriately (e.g., adjust to 2.4 seconds) to provide earlier and more reassuring warnings and protection.

[0037] Braking style adjustment: Adopting a "smoother, more linear" braking curve, the braking pressure is built up in stages, which greatly improves comfort and reduces fright while ensuring safety.

[0038] 3.3 For "standard" drivers: the factory default calibration strategy is adopted.

[0039] Part Two: Constructing a "Vehicle-Road Cooperative" Pre-Braking System: 1. Beyond visual range risk perception: Vehicles receive risk information beyond visual range ahead via V2X communication modules (V2V: vehicle-to-vehicle, V2I: vehicle-to-infrastructure), including: The vehicle ahead braked suddenly; Information on the location of traffic accidents or road construction; Information on pedestrians or obstacles in blind spots (bends, behind the crest of a hill); Warnings for road sections affected by severe weather (such as icing or flooding).

[0040] 2. Pre-braking strategy: When V2X risk information is received and the onboard computing unit confirms the existence of the risk and that it is located on the vehicle's travel path, the system activates a pre-braking strategy. This strategy is independent of and takes precedence over AEB decisions based on onboard sensors. Phase 1: Pre-pressurization and warning: The system will silently and slightly (e.g., 0.2-0.3g deceleration) pre-pressurize the braking system to eliminate the gap between the brake pads and brake discs, while issuing a high-level visual / auditory warning to the driver through steering wheel vibration or head-up display.

[0041] Phase Two: Collaborative Decision Making If the driver responds to the warning within a preset time (e.g., 1 second) by pressing the brake, the system will assist in achieving the required braking force.

[0042] If the driver does not react and the risk continues to approach, the system will seamlessly switch to the main AEB system. At this time, because the braking system has been pre-pressurized, the response time of the main AEB is significantly shortened, and the braking distance is significantly optimized.

[0043] Part Three, Workflow: 1. System initialization, loading driving style model.

[0044] 2. Collect driving data in real time and update driver style profiles.

[0045] 3. Continuously monitor V2X communication to obtain beyond-line-of-sight risk information.

[0046] 4. If V2X risks exist, a pre-braking strategy will be activated.

[0047] 5. At the same time, the vehicle-mounted sensors (radar, camera) continuously detect short-range targets.

[0048] 6. When the risk detected by the sensors reaches the dynamic threshold mapped by the current driving style, the main AEB system is triggered.

[0049] 7. The main AEB system executes a corresponding personalized braking curve based on the driving style.

[0050] The technical advantages of the technical solution based on the embodiments of this application are as follows: Personalization and Humanization: The system is no longer a cold machine, but a "partner" that understands and adapts to the driver, effectively solving user pain points such as "false triggering" and "excessive interference" in the AEB system, and improving user experience and system acceptance. It makes full use of standard sensors already in mass production in vehicles (ultrasonic radar, surround view camera), without adding any hardware costs, and achieves a leap in perception capabilities through algorithmic innovation.

[0051] Foresight and Safety: By using V2X technology, the physical limitations of single-vehicle perception are broken, enabling "beyond line of sight" perception. This provides the system with valuable pre-braking time, fundamentally shortening the braking distance, especially in complex scenarios where sensor performance is limited.

[0052] Smooth transition and comfort: The pre-braking strategy provides the driver with a buffer and reaction time, and transforms the emergency braking process from "abrupt" to "smooth", which greatly improves the driving comfort while ensuring safety.

[0053] Deep Synergy: This application deeply and organically integrates driver profiling, vehicle-road cooperation, and traditional AEB, forming a systemic advantage of 1+1+1>3, representing the development direction of the next generation of active safety systems.

[0054] Secondly, see Figure 4 As shown, this application provides an adaptive emergency braking system, which includes: The model building module is used to perform cluster analysis on periodically acquired raw driving behavior data to build a driving style model; The style judgment module is used to analyze the driving behavior data of the target vehicle based on the driving style model and determine the driver style label of the target vehicle. The braking adjustment module is used to adjust the TTC trigger threshold and braking curve of the target vehicle based on the driver style label of the target vehicle and in combination with preset adjustment rules. The driver style labels include aggressive, standard, and mild.

[0055] In this embodiment, a driver style profile is constructed through machine learning, and the vehicle braking triggering strategy is dynamically adjusted to achieve forward-looking personalized safety protection.

[0056] Furthermore, the target vehicle has pre-stored a standard TTC trigger threshold, a mild TTC trigger threshold, and an aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

[0057] Furthermore, the types of raw driving behavior data and driving behavior data include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

[0058] Furthermore, the system also includes: A pre-braking module is used to execute a preset pre-braking strategy when there is a beyond-visual-range risk ahead of the target vehicle; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

[0059] Furthermore, the pre-braking module is also used to pre-pressurize the braking system of the target vehicle and issue pre-braking warning information; The pre-braking module is also used to perform braking based on the adjusted TTC trigger threshold and the braking curve if, after issuing the pre-braking warning information, an active braking signal of the target vehicle is received within a preset warning time. The pre-braking module is also used to control the main AEB system of the target vehicle to brake based on the adjusted TTC trigger threshold and the braking curve if no active braking signal is received from the target vehicle within a preset warning time after the pre-braking warning information is issued.

[0060] In specific implementation, the technical solution based on the embodiments of this application is as follows: Part 1: Constructing Adaptive AEB Based on "Driving Style Profile": 1. Data Acquisition and Feature Extraction: The system periodically collects raw driving behavior data from the vehicle's CAN bus and sensors, including but not limited to: Longitudinal behavior signals: accelerator pedal opening change rate, brake pedal force / depth, average following distance, and maximum deceleration relative to the vehicle in front; Lateral behavior signals: steering wheel angular velocity, frequency and magnitude of lateral position deviation within the lane, and average cornering speed; Time and frequency signals: overtaking frequency, frequency of rapid acceleration / braking events.

[0061] 2. Driving style model construction and classification: 2.1 Model Training: Unsupervised learning algorithms (such as K-Means clustering) are used to perform cluster analysis on a large amount of collected driving feature data, and the driver style is divided into three main categories: "aggressive", "standard", and "mild".

[0062] 2.2 Online Recognition: During daily vehicle use, the system continuously collects recent driving data (such as the past 30 days) and compares it with the established clustering model to identify and update the current driver's style label in real time.

[0063] 3. Adaptive AEB Strategy Mapping: The system dynamically adjusts the AEB control parameters based on the driving style identified in real time. 3.1 For "aggressive" drivers: Trigger threshold adjustment: The TTC trigger threshold is appropriately lowered (for example, 2.1 seconds for the standard model and 1.8 seconds for the aggressive model) to avoid premature intervention that interferes with driving.

[0064] Braking style adjustment: When the system finally triggers, it adopts a "faster and more decisive" braking curve, that is, it reaches the maximum braking force in a very short time to make up for the braking distance lost due to the later trigger.

[0065] 3.2 For "mild" drivers: Trigger threshold adjustment: Increase the TTC trigger threshold appropriately (e.g., adjust to 2.4 seconds) to provide earlier and more reassuring warnings and protection.

[0066] Braking style adjustment: Adopting a "smoother, more linear" braking curve, the braking pressure is built up in stages, which greatly improves comfort and reduces fright while ensuring safety.

[0067] 3.3 For "standard" drivers: the factory default calibration strategy is adopted.

[0068] Part Two: Constructing a "Vehicle-Road Cooperative" Pre-Braking System: 1. Beyond visual range risk perception: Vehicles receive risk information beyond visual range ahead via V2X communication modules (V2V: vehicle-to-vehicle, V2I: vehicle-to-infrastructure), including: The vehicle ahead braked suddenly; Information on the location of traffic accidents or road construction; Information on pedestrians or obstacles in blind spots (bends, behind the crest of a hill); Warnings for road sections affected by severe weather (such as icing or flooding).

[0069] 2. Pre-braking strategy: When V2X risk information is received and the onboard computing unit confirms the existence of the risk and that it is located on the vehicle's travel path, the system activates a pre-braking strategy. This strategy is independent of and takes precedence over AEB decisions based on onboard sensors. Phase 1: Pre-pressurization and warning: The system will silently and slightly (e.g., 0.2-0.3g deceleration) pre-pressurize the braking system to eliminate the gap between the brake pads and brake discs, while issuing a high-level visual / auditory warning to the driver through steering wheel vibration or head-up display.

[0070] Phase Two: Collaborative Decision Making If the driver responds to the warning within a preset time (e.g., 1 second) by pressing the brake, the system will assist in achieving the required braking force.

[0071] If the driver does not react and the risk continues to approach, the system will seamlessly switch to the main AEB system. At this time, because the braking system has been pre-pressurized, the response time of the main AEB is significantly shortened, and the braking distance is significantly optimized.

[0072] Part Three, Workflow: 1. System initialization, loading driving style model.

[0073] 2. Collect driving data in real time and update driver style profiles.

[0074] 3. Continuously monitor V2X communication to obtain beyond-line-of-sight risk information.

[0075] 4. If V2X risks exist, a pre-braking strategy will be activated.

[0076] 5. At the same time, the vehicle-mounted sensors (radar, camera) continuously detect short-range targets.

[0077] 6. When the risk detected by the sensors reaches the dynamic threshold mapped by the current driving style, the main AEB system is triggered.

[0078] 7. The main AEB system executes a corresponding personalized braking curve based on the driving style.

[0079] The technical advantages of the technical solution based on the embodiments of this application are as follows: Personalization and Humanization: The system is no longer a cold machine, but a "partner" that understands and adapts to the driver, effectively solving user pain points such as "false triggering" and "excessive interference" in the AEB system, and improving user experience and system acceptance. It makes full use of standard sensors already in mass production in vehicles (ultrasonic radar, surround view camera), without adding any hardware costs, and achieves a leap in perception capabilities through algorithmic innovation.

[0080] Foresight and Safety: By using V2X technology, the physical limitations of single-vehicle perception are broken, enabling "beyond line of sight" perception. This provides the system with valuable pre-braking time, fundamentally shortening the braking distance, especially in complex scenarios where sensor performance is limited.

[0081] Smooth transition and comfort: The pre-braking strategy provides the driver with a buffer and reaction time, and transforms the emergency braking process from "abrupt" to "smooth", which greatly improves the driving comfort while ensuring safety.

[0082] Deep Synergy: This application deeply and organically integrates driver profiling, vehicle-road cooperation, and traditional AEB, forming a systemic advantage of 1+1+1>3, representing the development direction of the next generation of active safety systems.

[0083] In summary, the adaptive emergency braking system provided in this application embodiment is identical in technical principle to the adaptive emergency braking method provided in the first aspect in terms of technical problems, technical solutions, and technical effects, and therefore will not be described in detail here.

[0084] In the description of this application, it should be noted that the terms "upper," "lower," etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the system or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two components. For those skilled in the art, the specific meaning of the above terms in this application can be understood according to the specific circumstances.

[0085] It should be noted that in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0086] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An adaptive emergency braking method, characterized in that, The method includes the following steps: Cluster analysis is performed on periodically acquired raw driving behavior data to construct a driving style model; Based on the driving style model, the driving behavior data of the target vehicle is analyzed to determine the driver style label of the target vehicle. Based on the driver style tags of the target vehicle and combined with preset adjustment rules, the TTC trigger threshold and braking curve of the target vehicle are adjusted. The driver style labels include aggressive, standard, and mild.

2. The adaptive emergency braking method as described in claim 1, characterized in that: The target vehicle has pre-stored standard TTC trigger threshold, mild TTC trigger threshold, and aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

3. The adaptive emergency braking method as described in claim 1, characterized in that: The types of data in the original driving behavior data and the driving behavior data include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

4. The adaptive emergency braking method as described in claim 1, characterized in that, The method further includes the following steps: When there is a risk beyond visual range ahead of the target vehicle, a preset pre-braking strategy is executed; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

5. The adaptive emergency braking method as described in claim 4, characterized in that, The pre-braking strategy includes the following steps: The braking system of the target vehicle is pre-pressurized, and a pre-braking warning message is issued; If, after the pre-braking warning information is issued, an active braking signal from the target vehicle is received within the preset warning time, braking is performed based on the adjusted TTC trigger threshold and the braking curve. If, after issuing the pre-braking warning information, no active braking signal is received from the target vehicle within the preset warning time, the main AEB system of the target vehicle is controlled to brake based on the adjusted TTC trigger threshold and the braking curve.

6. An adaptive emergency braking system, characterized in that, The system includes: The model building module is used to perform cluster analysis on periodically acquired raw driving behavior data to build a driving style model; The style judgment module is used to analyze the driving behavior data of the target vehicle based on the driving style model and determine the driver style label of the target vehicle. The braking adjustment module is used to adjust the TTC trigger threshold and braking curve of the target vehicle based on the driver style label of the target vehicle and in combination with preset adjustment rules. The driver style labels include aggressive, standard, and mild.

7. The adaptive emergency braking system as described in claim 6, characterized in that: The target vehicle has pre-stored standard TTC trigger threshold, mild TTC trigger threshold, and aggressive TTC trigger threshold; The target vehicle has pre-stored standard braking curves, mild braking curves, and aggressive braking curves; The adjustment rules include: Based on the type of the driver style tag, a corresponding TTC trigger threshold and braking curve are configured for the target vehicle; wherein... The values ​​of the aggressive TTC trigger threshold, the standard TTC trigger threshold, and the mild TTC trigger threshold increase sequentially. The smoothness of the aggressive braking curve, the standard braking curve, and the mild braking curve increases sequentially.

8. The adaptive emergency braking system as described in claim 6, characterized in that: The types of data in the original driving behavior data and the driving behavior data include accelerator pedal opening change rate, brake pedal force, brake pedal depth, average following distance, maximum deceleration relative to the vehicle in front, steering wheel angular velocity, lane lateral position deviation frequency, lane lateral position deviation magnitude, average cornering speed, overtaking frequency, rapid acceleration frequency, and rapid braking frequency.

9. The adaptive emergency braking system as described in claim 6, characterized in that, The system also includes: A pre-braking module is used to execute a preset pre-braking strategy when there is a beyond-visual-range risk ahead of the target vehicle; wherein, The risks beyond visual range include sudden braking events by vehicles ahead, traffic accidents, road construction events, pedestrian or obstacle events in blind spots, and warning events for road sections in severe weather.

10. The adaptive emergency braking system as described in claim 9, characterized in that: The pre-braking module is also used to pre-pressurize the braking system of the target vehicle and issue pre-braking warning information; The pre-braking module is also used to perform braking based on the adjusted TTC trigger threshold and the braking curve if, after issuing the pre-braking warning information, an active braking signal of the target vehicle is received within a preset warning time. The pre-braking module is also used to control the main AEB system of the target vehicle to brake based on the adjusted TTC trigger threshold and the braking curve if no active braking signal is received from the target vehicle within a preset warning time after the pre-braking warning information is issued.

Images