Auxiliary deceleration control method based on electronic mechanical braking and related equipment

Abstract

The invention relates to the technical field of vehicles, in particular to an auxiliary deceleration control method and related equipment based on electronic mechanical braking, and the method comprises the steps: obtaining the current running speed of a vehicle, the width of a road capable of passing through a preview point and the curvature of the road; inputting the passable road width, the road curvature and the current driving speed into a trained LSTM neural network, and outputting a vehicle speed set in a period of time in the future; calculating a target deceleration at the current moment based on the speed at the latest future moment in the speed set and the current driving speed; whether an upper-layer controller sends out a braking request or not is judged, if yes, whether the temperatures of four-wheel brake discs are all smaller than or equal to 450 DEG C and whether the vehicle is in a non-static state or not is detected, and if yes, a lower-layer controller outputs braking torque according to the target deceleration and the vehicle environment information, and auxiliary deceleration control is implemented; according to the invention, personalized and smooth auxiliary deceleration experience can be provided for drivers with different driving styles.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and specifically to an auxiliary deceleration control method and related equipment based on electromechanical braking. Background Technology

[0002] Electromechanical braking (EMB) systems, as an important component of vehicle braking systems, use electronic control units to drive motors to clamp and release brakes. Compared to traditional mechanical braking, EMB systems offer advantages such as faster response, higher control precision, and greater integration, and are widely used in modern passenger and commercial vehicles. During vehicle operation, driver-assisted deceleration functions aim to reduce driver workload and improve driving safety. Systems such as adaptive cruise control (ACC) and automatic emergency braking (AEB) work in conjunction with the braking system.

[0003] However, existing technologies include methods for calculating the current target deceleration of a vehicle: Based on the vehicle dynamics model, the maximum speed boundary of the vehicle is calculated with road curvature and road surface adhesion as constraints, thereby calculating the target deceleration, which can effectively improve the vehicle's extreme performance.

[0004] Based on the minimum safe distance from the vehicle in front and the actual fuel consumption of the vehicle, the future vehicle speed set is inferred using model predictive control methods, thereby calculating the target acceleration required at the current time.

[0005] The two methods mentioned above can ensure the vehicle's maximum speed and optimal fuel efficiency under specific circumstances, but they cannot meet the driver's driving habits and may cause motion sickness and other symptoms for passengers. Summary of the Invention

[0006] In view of this, the purpose of this invention is to provide an auxiliary deceleration control method and related equipment based on electromechanical braking, which aims to achieve auxiliary deceleration control that mimics the driving habits of a driver and improve the driving experience for both the driver and passengers.

[0007] On one hand, embodiments of the present invention provide an auxiliary deceleration control method based on electromechanical braking, the method comprising the following steps: The vehicle's current speed, the width of the passable road at the target point, and the road curvature can be obtained. The road width, road curvature, and current driving speed are input into the trained LSTM neural network to output a set of vehicle speeds over a future period of time. Calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; The system determines whether the upper-level controller has issued a braking request. If so, it checks whether the temperature of all four brake discs is ≤450°C and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

[0008] Optionally, the acquisition of the pre-aiming point can be achieved through road width and road curvature, including: When the vehicle is entering a curve or there is a road obstacle ahead, the aiming point is set to the entry point of the curve or the location of the road obstacle; when the vehicle is driving in a normal straight line, the aiming point distance is calculated by the formula S=V*K+D, where S is the aiming point distance, V is the current driving speed, K is the proportional coefficient, and D is the fixed increment. Collect the total road width and roadblock width at the pre-aiming point, and subtract the roadblock width from the total road width to obtain the passable road width; The road curvature at the pre-aiming point is collected. When the road is straight, the curvature is set to a preset fixed value.

[0009] Optionally, the LSTM neural network is trained in the following manner: Collect real-time data from drivers with different driving styles in the simulator. The real-time data includes the width of the passable road, the road curvature, the current driving speed, and the actual driving speed for a corresponding period of time in the future at different aiming points. Aggressive driver data is aggregated and trained into a first LSTM network, while conservative driver data is aggregated and trained into a second LSTM network, forming LSTM neural networks trained with different driving styles.

[0010] Optionally, calculating the target deceleration at the current moment includes: Extract the speed at the nearest future moment and the current driving speed from the set of speeds; Calculate the target acceleration at the current moment based on the speed at the nearest future moment and the current driving speed. If the target acceleration is negative, then set the target deceleration at the current moment to the absolute value of the target acceleration; otherwise, set the target deceleration at the current moment to the target acceleration.

[0011] Optionally, after determining whether the upper-level controller has issued a braking request, the method further includes: If the upper controller does not issue a braking request, it determines whether to issue a stop request. If it does, it checks whether the vehicle is stationary and whether the EPB is not clamped. If both conditions are met, it enters the active state and outputs braking torque to keep the vehicle stationary. Once activated, the system continuously monitors whether the upper-level controller cancels braking, whether the driver activates EPB, whether the stationary time exceeds the set duration, whether the driver is not in the position, or whether the driver leaves the vehicle. If any of these conditions are met, the system exits the activation state and stops outputting braking torque.

[0012] Optionally, after detecting whether the temperature of all four brake discs is ≤450°C and whether the vehicle is in a non-stationary state, the method further includes: If the temperature of the four-wheel brake discs exceeds 450°C or the vehicle is stationary, the lower-level controller will not respond to the braking request and will maintain the current state.

[0013] Optionally, after implementing the auxiliary deceleration control, the method further includes: The system detects in real time whether the driver requests a deceleration greater than the target deceleration, whether vehicle sideslip is detected, or whether the upper-level controller cancels the braking request. If any of these conditions are met, the lower-level controller stops outputting braking torque and exits auxiliary deceleration control.

[0014] On the other hand, embodiments of the present invention provide an auxiliary deceleration control device based on electromechanical braking, comprising: The first module is used to obtain the vehicle's current speed, the width of the passable road at the pre-aiming point, and the road curvature. The second module is used to input the road width, road curvature and current driving speed into the trained LSTM neural network and output a set of vehicle speeds for a future period of time. The third module is used to calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; The fourth module is used to determine whether the upper-level controller has issued a braking request. If it has, it checks whether the temperature of all four brake discs is ≤450° and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

[0015] On the other hand, embodiments of the present invention provide an auxiliary deceleration control system based on electromechanical braking, comprising: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor performs the method described above.

[0016] On the other hand, embodiments of the present invention provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to perform the above-described method.

[0017] The embodiments of this invention include the following beneficial effects: This invention provides an auxiliary deceleration control method and related equipment based on electromechanical braking. By acquiring the vehicle's current speed, the width of the passable road at the target point, and the road curvature, this invention provides basic data support for subsequent speed prediction and deceleration calculation. These key road parameters and the current speed are input into a trained LSTM neural network. This network, trained based on real-world data from drivers with different driving styles, can simulate different driving habits, such as aggressive or conservative approaches, thereby outputting a set of future speeds that match the driver's expectations. After calculating the target deceleration based on this speed set, the upper-level braking request is first determined, followed by dual detection of brake disc temperature and vehicle status. Only when braking safety is ensured will the lower-level controller output braking torque in conjunction with environmental information, achieving auxiliary deceleration control that is both consistent with driving habits and safe and reliable. This invention effectively solves the problem of ride discomfort caused by traditional control methods failing to adapt to driver habits, thus improving the overall driving experience. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the steps of an auxiliary deceleration control method based on electromechanical braking provided in an embodiment of the present invention. Figure 2 This is a framework diagram of an auxiliary deceleration control method based on electromechanical braking provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a car passing through a road with obstacles, provided in an embodiment of the present invention; Figure 4 This is a state transition diagram of the lower-level controller provided in an embodiment of the present invention; Figure 5 This is a structural block diagram of an auxiliary deceleration control device based on electromechanical braking provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] It should be noted that although the device diagram shows a modular division and the flowchart illustrates a logical order, in some cases, the steps shown or described may be performed in a different order than the modular division in the device or the order shown in the flowchart. The terms "first," "second," etc., used in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0021] Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this invention is for descriptive purposes only and is not intended to limit the invention.

[0022] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of the invention. However, those skilled in the art will recognize that the technical solutions of the invention can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the invention.

[0023] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0025] This invention introduces a method based on real-world driver simulator data. This includes training an LSTM neural network at a pre-aiming point using road width, road curvature, and vehicle speed to predict vehicle speed over a future period. This network then calculates the vehicle's current target deceleration, enabling assisted deceleration control that mimics a driver's driving habits. By mimicking these habits, this method provides an assisted deceleration control mechanism, preventing driver motion sickness or fear. For example, it allows for early deceleration when entering a curve or avoiding obstacles ahead, thus improving the driving experience for both the driver and passengers.

[0026] like Figure 1 As shown, Figure 1 An auxiliary deceleration control method based on electromechanical braking is provided in this embodiment of the invention. The method includes the following steps: S100: Obtain the vehicle's current speed, the width of the passable road at the pre-aiming point, and the road curvature; S200, the road width, road curvature and current driving speed are input into the trained LSTM neural network to output a set of vehicle speeds for a future period of time; S300, calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; S400: Determine whether the upper-level controller has issued a braking request. If so, check whether the temperature of all four brake discs is ≤450° and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

[0027] In steps S100 to S400 of this embodiment, the road information at the target point and the current vehicle speed are deeply fused using an LSTM neural network. This enables more accurate simulation of the driver's speed prediction logic under different driving styles. By comparing the difference between the speed at the nearest future moment and the current driving speed, and combining this with the time interval, a smooth deceleration curve can be obtained, avoiding the abrupt deceleration problems caused by considering only a single constraint condition in traditional methods. When the lower-level controller receives a braking request, real-time monitoring of the brake disc temperature effectively prevents thermal fade caused by continuous braking, ensuring stable braking performance. The judgment of the vehicle's non-stationary state avoids accidental triggering of the auxiliary deceleration function when the vehicle is stationary. In summary, this embodiment of the invention provides a personalized and smooth auxiliary deceleration experience for drivers with different driving styles by incorporating the driver's driving habits into the auxiliary deceleration control logic.

[0028] In some embodiments, obtaining the pre-aiming point can be achieved through road width and road curvature, including: S110: When the vehicle is entering a curve or there is a road obstacle ahead, the aiming point is set to the entry point of the curve or the location of the road obstacle; when the vehicle is driving in a normal straight line, the aiming point distance is calculated by the formula S=V*K+D, where S is the aiming point distance, V is the current driving speed, K is the proportional coefficient, and D is the fixed increment. S120, Collect the total road width and roadblock width at the pre-aiming point, and subtract the roadblock width from the total road width to obtain the passable road width; S130, collect the road curvature at the pre-aiming point, and when the road is straight, set the curvature to a preset fixed value.

[0029] In this embodiment, the aiming point position is dynamically adjusted for different driving conditions, which better matches the driver's attention distribution characteristics during actual driving. In scenarios involving curves or road obstacles, the aiming point is directly positioned at the critical location, allowing for early identification of road shape changes and providing sufficient response time for deceleration control. During straight-line driving, the aiming distance is calculated using a speed coupling formula, ensuring long-distance prediction at high speeds to meet long-distance decision-making needs, while shortening the aiming distance in low-speed scenarios to improve control real-time performance. For the calculation of road width, the actual passage space parameter is obtained by the difference between the total road width and the obstacle width, providing accurate road constraints for subsequent speed prediction. When the road is straight, the curvature is set to a fixed value, simplifying the calculation logic for straight road sections, avoiding interference from small fluctuations in curvature on speed prediction results, and ensuring stable output of the model under various road conditions.

[0030] In some embodiments, the LSTM neural network is trained in the following manner: S210, Collect real-time data from drivers with different driving styles in the simulator. The real-time data includes the width of the road that can be accessed at different aiming points, the road curvature, the current driving speed, and the actual driving speed for a corresponding period of time in the future. S220 uses data from aggressive drivers to train a first LSTM network and data from conservative drivers to train a second LSTM network, thus forming LSTM neural networks trained with different driving styles.

[0031] In this embodiment, by collecting real-world data from drivers with different driving styles for neural network training, the model can accurately capture the speed adjustment characteristics of typical driving styles such as aggressive and conservative. The first LSTM network, trained on data from aggressive drivers, typically outputs a higher anticipation speed and a steeper rate of deceleration under the same road conditions, reflecting a fast-response, agile driving habit. Conversely, the second LSTM network, trained on data from conservative drivers, tends to output a lower anticipation speed and a smoother deceleration curve, prioritizing driving stability and safety. This driving style-based training method allows the assisted deceleration control to dynamically adapt to the driver's individual needs. For example, when the system detects that the current driver tends towards aggressive driving, it automatically calls the prediction results of the first LSTM network, providing a deceleration experience that better matches the driver's expectations while ensuring safety. Conversely, it calls the second LSTM network to avoid driver discomfort due to excessively rapid deceleration. Simultaneously, the diverse road conditions and speed combinations included in the real-world data ensure the generalization ability of the trained LSTM neural network under complex conditions, enabling it to meet speed prediction needs under different road conditions.

[0032] In some embodiments, calculating the target deceleration at the current moment includes: S310, extract the speed at the nearest future moment and the current driving speed from the speed set; S320: Calculate the target acceleration at the current moment based on the speed at the nearest future moment and the current driving speed. If the target acceleration is negative, set the target deceleration at the current moment to the absolute value of the target acceleration; otherwise, set the target deceleration at the current moment to the target acceleration.

[0033] In this embodiment, the calculation logic for the target deceleration achieves precise conversion of deceleration requirements by determining the sign of the target acceleration. When the target acceleration is negative, it indicates that the vehicle needs to decelerate; in this case, its absolute value is taken as the target deceleration, directly reflecting the intensity of the vehicle's speed reduction. Conversely, when the target acceleration is positive, it is set as the target deceleration. This approach provides a basic buffer control quantity for the system when the vehicle needs to maintain its current speed or accelerate slightly, by setting a non-negative deceleration value. This avoids frequent adjustments to the braking torque caused by small fluctuations in acceleration, thereby enhancing the stability and continuity of the auxiliary deceleration control. This dynamic adjustment mechanism ensures that the target deceleration always matches the current speed change trend of the vehicle, providing accurate and smooth control parameters for the subsequent output of the braking torque.

[0034] In some embodiments, after determining whether the upper-level controller has issued a braking request, the method further includes: S411 If the upper controller does not issue a braking request, it determines whether a stop request is issued. If it is issued, it checks whether the vehicle is stationary and whether the EPB is not clamped. If both conditions are met, it enters the active state and outputs braking torque to keep the vehicle stationary. S412, after entering the active state, continuously detects whether the upper controller cancels the braking, whether the driver activates EPB, whether the stationary time exceeds the set time, whether the driver is not in place, or whether the driver leaves. If any of the conditions are met, it exits the active state and stops outputting braking torque.

[0035] In this embodiment, a complete closed-loop auxiliary control logic is constructed by judging the state when the upper-level controller does not issue a braking request. When a stationary request is triggered, the system ensures that it only intervenes in scenarios requiring parking assistance through dual detection of the vehicle's stationary state and the EPB's unclamped state, avoiding interference with the driver's normal operation. After entering the active state, the system outputs braking torque to keep the vehicle stationary, effectively reducing the driver's operational burden in scenarios such as slopes and improving parking convenience. The multi-condition judgment mechanism for exiting the active state comprehensively covers various reasonable scenarios for terminating parking assistance: the upper-level controller canceling the braking request means that the driver may need to start again, and stopping the output of braking torque at this time can avoid affecting the normal driving of the vehicle; the driver activating the EPB indicates manual takeover of the parking function, and automatic exit ensures the priority of control; the stationary time exceeding the set time can prevent excessive battery consumption, which is in line with the vehicle's energy management strategy; if the driver is not in place or has driven away, from a safety perspective, the auxiliary control is terminated to avoid potential risks in an unattended state. This refined state switching logic not only expands the functional coverage of the auxiliary deceleration control device, but also ensures the safety and reliability of the control process through multiple condition constraints, achieving seamless coordination between auxiliary control and manual operation.

[0036] In some embodiments, after detecting whether the temperature of all four brake discs is ≤450°C and whether the vehicle is in a non-stationary state, the method further includes: S420: If the temperature of the four-wheel brake discs exceeds 450° or the vehicle is stationary, the lower-level controller will not respond to the braking request and will maintain the current state.

[0037] In this embodiment, a safety protection mechanism for auxiliary deceleration control is constructed by judging the conditions of brake disc overheating or vehicle stationary state. When the temperature of any of the four brake discs exceeds 450°C, the lower-level controller does not respond to the braking request, which can avoid the thermal fade phenomenon caused by the brake disc overheating leading to a sharp drop in the friction coefficient and a significant decrease in braking torque, thus preventing the safety hazard of brake failure. When the vehicle is stationary, the controller refuses to respond, which can prevent accidental triggering of braking control under parking conditions, avoiding resistance to vehicle start-up or unnecessary mechanical wear of the braking system. This "double-condition rejection" design logic uses hardware status and vehicle operating conditions as prerequisites for control intervention, ensuring that the auxiliary deceleration function is activated only when the braking system is in good condition and the vehicle is in motion, further improving the safety and rationality of the control strategy and providing reliable auxiliary braking support for the driver.

[0038] In some embodiments, after implementing the auxiliary deceleration control, the method further includes: S430 detects in real time whether the driver requests a deceleration greater than the target deceleration, whether vehicle sideslip is detected, or whether the upper-level controller cancels the braking request. If any of these conditions are met, the lower-level controller stops outputting braking torque and exits auxiliary deceleration control.

[0039] In this embodiment, a dynamic intervention mechanism for assisted deceleration control is constructed by setting multiple exit conditions, ensuring the driver's operational priority and vehicle driving safety in special scenarios. When the driver actively requests greater deceleration, the system stops outputting braking torque, allowing the driver to take over braking control via pedal operation to cope with sudden dangers or personalized deceleration needs. Detection of vehicle sideslip can immediately terminate assisted deceleration when the vehicle is at risk of losing control, avoiding the exacerbation of sideslip due to continuous braking and reserving control space for intervention by vehicle stability systems such as ESP. The upper-level controller cancels the braking request as a basic exit condition, which can terminate control in a timely manner when road conditions improve or assisted deceleration is no longer needed, preventing excessive intervention from affecting normal driving procedures. This multi-dimensional exit trigger logic not only ensures the driver's ultimate control over the vehicle but also quickly cuts off assisted control in abnormal vehicle conditions, forming a closed-loop protection from assistance to monitoring and exit, further improving the adaptability and safety of the assisted deceleration system under complex operating conditions.

[0040] The solution of the present invention will be described below by way of example: refer to Figure 2 This invention is an auxiliary deceleration control method based on electromechanical braking. This method consists of two parts: an upper layer and a lower layer. The upper layer calculates the vehicle speed range over a future period by using the passable road width and road curvature at the driver's pre-aiming point, combined with an LSTM neural network, thereby calculating the vehicle's target deceleration at the current moment. The lower layer receives the target deceleration and vehicle environment signals from the upper layer and outputs the braking torque.

[0041] refer to Figure 3 A diagram showing a car navigating a road with roadblocks is provided. Step 1: Determine the aiming point distance. The aiming point distance is generally positively correlated with the vehicle's position, as shown in the formula: ; Where S represents the distance to the driver's aiming point, V represents the vehicle speed, K is the proportional coefficient, and D is the fixed increment.

[0042] In particular, simulating the driver's driving experience, when the vehicle enters a curve or there is a road obstacle ahead, the driver's line of sight will focus on the entry point of the curve or the road obstacle, and will not change with the speed of the vehicle. That is, the aiming point is fixed at this time.

[0043] Step 2: Apply an LSTM neural network to predict the velocity set over a future period, using the following formula: ; Where V0 represents the current speed, V1, V2...Vn represent the set of speeds predicted for future times, d represents the passable road width at the preview point S, and p represents the road curvature at the preview point S.

[0044] Due to the presence of roadblocks, the passable road width is the total road width minus the roadblock width. If it is a straight road, the curvature is infinite (it can be set to a large fixed value).

[0045] The LSTM network is based on real-world driver data. It can train the first LSTM network with data from aggressive drivers and the second LSTM network with data from conservative drivers. Choosing different training networks means choosing different driving styles, which enables drivers to select different driving styles.

[0046] Step 3: Calculate the current acceleration based on the velocity at the nearest future moment and the current velocity, using the following formula: ;in, V1 represents the target acceleration at the current moment, V0 represents the predicted velocity at the next moment, and t represents the sampling time interval. If the calculated acceleration is negative, it represents the target deceleration, and its absolute value is the required auxiliary deceleration control force. In this way, the system can dynamically adjust the target deceleration according to the driver's aiming habits and driving style, making the vehicle's deceleration process more in line with human driving behavior characteristics.

[0047] The vehicle acceleration is calculated using the formula above and sent to the lower-level controller, which then requests braking.

[0048] Step 4: The lower-level controller determines whether to implement auxiliary deceleration control based on vehicle and environmental information.

[0049] refer to Figure 4 The state transition diagram of the lower-level controller is described below: Standby: The function is off; without activation, the system does not engage. Standstill: The function is active, generating braking force to keep the body stationary; DC (Deceleration Control): When there is a target deceleration, it responds and applies braking. When the temperature of all four brake discs is ≤450°C and the vehicle is not stationary, the braking torque of all four wheels is output.

[0050] The state transition conditions are as follows: Entering deceleration control mode from the off state: The upper-level controller requests braking; Furthermore, the temperature of all four brake discs is ≤450°C; And the vehicle is not stationary; Deceleration control enters off state: Upper-level controller cancels request; Or the driver requests a deceleration greater than the deceleration requested by the upper-level controller; Or a vehicle sideslip was detected; When a device transitions from a closed state to an active state, the upper-level controller issues a shutdown request. And the vehicle is stationary; Furthermore, the EPB was not clamped. When the active state transitions to the off state, the upper-level controller cancels the braking action. Or the driver activates the EPB; Or the static time exceeds 10 minutes; Or the driver is detected to be absent; Or the driver was detected leaving the premises; When the deceleration control is activated, the upper-level controller remains stationary. And the driver was in the driver's seat.

[0051] Specifically, the system first obtains the vehicle's current speed, the width of the passable road at the target point, and the road curvature. Then, it inputs the passable road width, road curvature, and current speed into a trained LSTM neural network, which outputs a set of vehicle speeds over a future period. Next, based on the speeds of the nearest future moments in the speed set and the current speed, it calculates the target deceleration at the current moment. Then, it determines whether the upper-level controller has issued a braking request. If so, it checks whether the temperature of all four brake discs is ≤450°C and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environmental information to implement auxiliary deceleration control. If the upper-level controller does not issue a braking request, it determines whether a stop request has been issued. If so, it checks whether the vehicle is stationary and whether the EPB is not clamped. If both conditions are met, it enters the active state and outputs braking torque to keep the vehicle stationary. If the temperature of the four-wheel brake discs exceeds 450°C or the vehicle is stationary, the lower-level controller does not respond to the braking request and maintains the current state. During the implementation of assisted deceleration control, it detects in real time whether the driver requests a deceleration greater than the target deceleration, whether vehicle sideslip is detected, or whether the upper-level controller cancels the braking request. If any of these conditions are met, the lower-level controller stops outputting braking torque and exits assisted deceleration control.

[0052] Compared with related technologies, the present invention has the following advantages: The aiming point distance is set so that when the vehicle enters a curve or there is a road obstacle ahead, the driver's line of sight will focus on the entry point of the curve or the road obstacle, and will not change with the vehicle speed. In other words, the aiming point is fixed at this time.

[0053] The method for calculating the current deceleration of a vehicle involves training an LSTM neural network at a target point using the road width and curvature to predict the vehicle's speed over a future period, thereby calculating the vehicle's current target deceleration and allowing the driver to select different driving styles.

[0054] The auxiliary deceleration control method based on electromechanical braking involves an upper-level controller calculating the target deceleration and a lower-level controller collecting vehicle and environmental information to output braking torque.

[0055] refer to Figure 5 This invention also provides an auxiliary deceleration control device based on electromechanical braking, comprising: The first module is used to obtain the vehicle's current speed, the width of the passable road at the pre-aiming point, and the road curvature. The second module is used to input the road width, road curvature and current driving speed into the trained LSTM neural network and output a set of vehicle speeds for a future period of time. The third module is used to calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; The fourth module is used to determine whether the upper-level controller has issued a braking request. If it has, it checks whether the temperature of all four brake discs is ≤450° and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

[0056] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0057] This invention also provides an auxiliary deceleration control system based on electromechanical braking, including a memory, a processor, and a program stored in the memory and executable on the processor. When the program is executed by the processor, it implements the method described in the above embodiments.

[0058] Taking the example of a processor and memory in a vehicle controller being connected via a bus, the memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the control processor, and these remote memories can be connected to the control device via a network.

[0059] The non-transitory software program and instructions required to implement the methods of the above embodiments are stored in memory and executed by the processor to perform the methods of the above embodiments.

[0060] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0061] This invention also provides a vehicle including the control device described in the above embodiments.

[0062] The vehicle can be a private car, such as a sedan, SUV, MPV, or pickup truck. It can also be a commercial vehicle, such as a van, bus, small truck, or large semi-trailer. The vehicle must have an electric motor capable of outputting power or acting as a generator to store mechanical energy. When the vehicle is a new energy vehicle, it can be a hybrid or a pure electric vehicle.

[0063] Since the vehicle applies all the technical solutions of the above-mentioned control device or vehicle controller, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0064] Furthermore, one embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions for performing the above-described method.

[0065] It is worth noting that, since the computer-readable storage medium of the present invention is capable of executing the methods of any of the above embodiments, the specific implementation methods and technical effects of the computer-readable storage medium of the present invention can be referred to the specific implementation methods and technical effects of the methods of any of the above embodiments.

[0066] Furthermore, one embodiment of the present invention provides a computer program product, including a computer program or computer instructions, the computer program or computer instructions being stored in a computer-readable storage medium, a processor of a computer device reading the computer program or computer instructions from the computer-readable storage medium, and the processor executing the computer program or computer instructions to cause the computer device to perform the above-described method.

[0067] It is worth noting that, since the computer program product of the present invention can execute the methods of any of the above embodiments, the specific implementation methods and technical effects of the computer program product of the present invention can be referred to the specific implementation methods and technical effects of the methods of any of the above embodiments.

[0068] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0069] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. An auxiliary deceleration control method based on electromechanical braking, characterized in that, The method includes the following steps: The vehicle's current speed, the width of the passable road at the target point, and the road curvature can be obtained. The road width, road curvature, and current driving speed are input into the trained LSTM neural network to output a set of vehicle speeds over a future period of time. Calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; The system determines whether the upper-level controller has issued a braking request. If so, it checks whether the temperature of all four brake discs is ≤450°C and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

2. The method according to claim 1, characterized in that, The acquisition of the pre-aiming point can be achieved through road width and road curvature, including: When the vehicle is entering a curve or there is a road obstacle ahead, the aiming point is set to the entry point of the curve or the location of the road obstacle; when the vehicle is driving in a normal straight line, the aiming point distance is calculated by the formula S=V*K+D, where S is the aiming point distance, V is the current driving speed, K is the proportional coefficient, and D is the fixed increment. Collect the total road width and roadblock width at the pre-aiming point, and subtract the roadblock width from the total road width to obtain the passable road width; The road curvature at the pre-aiming point is collected. When the road is straight, the curvature is set to a preset fixed value.

3. The method according to claim 1, characterized in that, The LSTM neural network was trained in the following manner: Collect real-time data from drivers with different driving styles in the simulator. The real-time data includes the width of the passable road, the road curvature, the current driving speed, and the actual driving speed for a corresponding period of time in the future at different aiming points. Aggressive driver data is aggregated and trained into a first LSTM network, while conservative driver data is aggregated and trained into a second LSTM network, forming LSTM neural networks trained with different driving styles.

4. The method according to claim 1, characterized in that, The calculation of the target deceleration at the current moment includes: Extract the speed at the nearest future moment and the current driving speed from the set of speeds; Calculate the target acceleration at the current moment based on the speed at the nearest future moment and the current driving speed. If the target acceleration is negative, then set the target deceleration at the current moment to the absolute value of the target acceleration; otherwise, set the target deceleration at the current moment to the target acceleration.

5. The method according to claim 1, characterized in that, After determining whether the upper-level controller has issued a braking request, the process further includes: If the upper controller does not issue a braking request, it determines whether to issue a stop request. If it does, it checks whether the vehicle is stationary and whether the EPB is not clamped. If both conditions are met, it enters the active state and outputs braking torque to keep the vehicle stationary. Once activated, the system continuously monitors whether the upper-level controller cancels braking, whether the driver activates EPB, whether the stationary time exceeds the set duration, whether the driver is not in the position, or whether the driver leaves the vehicle. If any of these conditions are met, the system exits the activation state and stops outputting braking torque.

6. The method according to claim 1, characterized in that, After detecting whether the temperature of all four brake discs is ≤450°C and whether the vehicle is not stationary, the process also includes: If the temperature of the four-wheel brake discs exceeds 450°C or the vehicle is stationary, the lower-level controller will not respond to the braking request and will maintain the current state.

7. The method according to claim 1, characterized in that, After implementing the auxiliary deceleration control, it also includes: The system detects in real time whether the driver requests a deceleration greater than the target deceleration, whether vehicle sideslip is detected, or whether the upper-level controller cancels the braking request. If any of these conditions are met, the lower-level controller stops outputting braking torque and exits auxiliary deceleration control.

8. An auxiliary deceleration control device based on electromechanical braking, characterized in that, The device includes: The first module is used to obtain the vehicle's current speed, the width of the passable road at the pre-aiming point, and the road curvature. The second module is used to input the road width, road curvature and current driving speed into the trained LSTM neural network and output a set of vehicle speeds for a future period of time. The third module is used to calculate the target deceleration at the current moment based on the speed at the nearest future moment in the speed set and the current driving speed; The fourth module is used to determine whether the upper-level controller has issued a braking request. If it has, it checks whether the temperature of all four brake discs is ≤450° and whether the vehicle is not stationary. If both conditions are met, the lower-level controller outputs braking torque based on the target deceleration and vehicle environment information to implement auxiliary deceleration control.

9. An auxiliary deceleration control system based on electromechanical braking, characterized in that, It includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images