Automatic emergency avoidance method, medium, program, controller and vehicle

Abstract

The invention provides an automatic emergency avoidance method, a medium, a program, a controller and a vehicle, according to the method provided by the invention, a road adhesion coefficient, environment perception data and vehicle operation data are acquired in real time, and after an AES is triggered, trajectory planning is performed according to the road adhesion coefficient, the environment perception data and the vehicle operation data, so that the accuracy of the AES is improved. And finally, according to the emergency avoidance track, the vehicle is controlled to perform emergency avoidance. By adopting the automatic emergency avoidance method provided by the invention, automatic emergency avoidance trajectory planning is performed in combination with the road adhesion coefficients, so that the vehicle emergency avoidance function can stably work on the road surfaces with different road adhesion coefficients, vehicle instability is prevented while collision is avoided, and the robustness of the automatic emergency avoidance function is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to an automatic emergency avoidance method, medium, program, controller and vehicle. BACKGROUND

[0002] The automatic emergency steering (AES) system is an advanced vehicle active safety technology, aiming to assist the driver to avoid or mitigate potential collision accidents by automatically controlling the vehicle steering. The system usually uses on-board sensors (such as cameras, radars, lidars) to perceive the front obstacles or dangers, and when it is judged that the collision risk is high and the driver does not respond in time, the AES system will actively intervene, generate and execute an obstacle avoidance trajectory to guide the vehicle to deviate from the original lane to avoid collision. The core goal is to improve driving safety, especially in emergency situations where the driver's reaction is not timely.

[0003] However, the existing AES system is mainly designed and optimized for high adhesion coefficient (such as dry asphalt pavement) conditions, and has significant performance limitations and safety hazards on low adhesion coefficient pavements (such as ice and snow, water accumulation, gravel pavement). On low adhesion pavements, due to the significant reduction of adhesion between tires and pavement, the actual driving trajectory of the vehicle is difficult to accurately follow the target avoidance trajectory planned by the AES system, and trajectory deviation is easy to occur. Such deviation not only reduces the success rate of obstacle avoidance, but also may cause the vehicle to slide, spin or even completely lose control (instability risk) due to the saturation of tire force. In addition, to avoid losing control or performing actions beyond the physical limits of the vehicle, many existing systems will automatically deactivate when detecting a large trajectory deviation or predicting an instability risk, thereby losing the protection ability of the vehicle at a critical moment. Therefore, how to ensure that the AES system can still work safely, stably and effectively on various road adhesion conditions, especially on low adhesion coefficient pavements, to avoid collisions and prevent vehicle instability, has become a key problem that needs to be solved in the current technical field. SUMMARY

[0004] The present application provides an automatic emergency avoidance method, medium, program, controller and vehicle, which uses the method to read the road adhesion coefficient currently obtained by the system when the AES emergency avoidance is triggered, and then combines the road adhesion coefficient to plan the trajectory of automatic emergency avoidance, so that the emergency avoidance function can work stably on pavements with different road adhesion coefficients, avoid collisions while preventing vehicle instability, and improve the robustness of the automatic emergency avoidance function.

[0005] In one aspect, the present application provides an automatic emergency avoidance method, comprising:

[0006] obtaining road adhesion coefficient, environment perception data and vehicle operation data;

[0007] planning a trajectory based on the road adhesion coefficient, the environment perception data and the vehicle running data to obtain an emergency avoidance trajectory;

[0008] controlling the vehicle to perform emergency avoidance according to the emergency avoidance trajectory.

[0009] Further, in some embodiments, the planning a trajectory based on the road adhesion coefficient, the environment perception data and the vehicle running data to obtain an emergency avoidance trajectory comprises:

[0010] calculating a maximum lateral acceleration and a maximum trajectory curvature based on the road adhesion coefficient;

[0011] planning a trajectory based on the maximum lateral acceleration and the maximum trajectory curvature as constraint conditions in combination with the environment perception data and the vehicle running data to obtain at least one trajectory;

[0012] determining an emergency avoidance trajectory in the at least one trajectory based on a dynamic cost function.

[0013] Further, in some embodiments, the determining an emergency avoidance trajectory in the at least one trajectory based on a predefined cost function comprises:

[0014] determining a weight set corresponding to the road adhesion coefficient, configuring weights of each cost term of the dynamic cost function based on the weight set, and each cost term in the weight set corresponding to a weight respectively;

[0015] determining an emergency avoidance trajectory in the at least one trajectory based on the dynamic cost function with the completed weight configuration.

[0016] Further, in some embodiments, the controlling the vehicle to perform emergency avoidance according to the emergency avoidance trajectory comprises:

[0017] determining a feedforward control parameter according to a trajectory curvature indicated in the emergency avoidance trajectory and the road adhesion coefficient, the feedforward control parameter comprising a feedforward steering angle and a feedforward asymmetric braking force;

[0018] controlling the vehicle to perform emergency avoidance based on the feedforward control parameter.

[0019] Further, in some embodiments, the method further comprises:

[0020] calculating a target yaw rate based on a vehicle speed and a trajectory curvature indicated in the emergency avoidance trajectory;

[0021] when a yaw rate deviation between an actual yaw rate of the vehicle and the target yaw rate is detected to be greater than a preset deviation threshold, determining a feedback control parameter according to the yaw rate deviation, the feedback control parameter including a feedback steering angle and a feedback asymmetric braking force;

[0022] controlling the vehicle to perform the emergency avoidance based on the feedforward control parameter and the feedback control parameter.

[0023] Further, in some embodiments, the method further comprises:

[0024] when performing the feedforward control parameter calculation, adjusting a proportion of steering control and asymmetric braking control in the feedforward control according to the road adhesion coefficient;

[0025] when performing the feedback control parameter calculation, adjusting a proportion of steering control and asymmetric braking control in the feedback control according to the road adhesion coefficient.

[0026] Further, in some embodiments, the obtaining the road adhesion coefficient comprises:

[0027] obtaining road vibration data collected by a road vibration sensor, and determining the road adhesion coefficient based on the road vibration data.

[0028] In another aspect, the present application also provides a computer program product comprising a computer program, which, when executed, implements the method steps described above.

[0029] In another aspect, the present application provides a storage medium having stored thereon computer executable instructions adapted to be loaded and executed by a processor to perform the method steps described above.

[0030] In another aspect, the present application also provides a vehicle controller comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded and executed by the processor to perform the method steps described above.

[0031] In another aspect, the present application also provides a vehicle comprising the vehicle controller described above.

[0032] According to the automatic emergency avoidance method provided in the application, the road adhesion coefficient, the environment perception data and the vehicle operation data are acquired in real time, after the AES is triggered, the trajectory planning is performed according to the road adhesion coefficient, the environment perception data and the vehicle operation data, the emergency avoidance trajectory is obtained, and finally the vehicle is controlled according to the emergency avoidance trajectory to perform the emergency avoidance; the automatic emergency avoidance method provided in the embodiment of the application is adopted, the trajectory planning of the automatic emergency avoidance is performed in combination with the road adhesion coefficient, the vehicle emergency avoidance function can stably work on the road surface with different road adhesion coefficients, the vehicle instability is prevented while the collision is avoided, and the robustness of the automatic emergency avoidance function is improved.

[0033] It should be understood that the content described in the summary section is not intended to limit or important features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 A flowchart of an automatic emergency avoidance method provided in an embodiment of the application;

[0035] Figure 2 A flowchart of an automatic emergency avoidance method provided in an embodiment of the application;

[0036] Figure 3 A flowchart of an automatic emergency avoidance method provided in an embodiment of the application;

[0037] Figure 4 An example schematic diagram of a vehicle steering compensation by an asymmetric braking control provided in an embodiment of the application;

[0038] Figure 5 A flowchart of an automatic emergency avoidance method provided in an embodiment of the application;

[0039] Figure 6 A structural schematic diagram of a vehicle controller provided in an embodiment of the application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the application clearer, the technical scheme of the application will be described clearly and completely below in combination with specific embodiments of the application and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0041] In the description of one or more embodiments of the application, the term "includes" and its conjugations are to be understood as open-ended, i.e., "including but not limited to". The term "based on" is to be understood as "based, at least in part, on". The term "one embodiment" or "an embodiment" is to be understood as "at least one embodiment". The term "another embodiment" is to be understood as "at least one other embodiment". The terms "a" or "an" are to be understood as "one or more" in the context of describing technical features. The term "first" or "second" can refer to different or identical objects. Other explicit or implicit definitions can also be included below.

[0042] See Figure 1 An automatic emergency avoidance method flowchart is provided for an embodiment of the application. The execution subject of the flowchart can be a program for automatic emergency avoidance, or the execution subject of the flowchart can also be a vehicle or a domain controller carrying the above program, or other devices capable of communicating with the vehicle, the domain controller, etc., which are not specifically limited.

[0043] The following will be described in detail with respect to the flowchart shown in Figure 1 The automatic emergency avoidance method can specifically include the following steps:

[0044] In step S102, road adhesion coefficients, environmental perception data and vehicle operation data are acquired.

[0045] During the operation of the AES system, the road adhesion coefficients, the environmental perception data and the vehicle operation data are acquired in real time by various sensors arranged on the vehicle body. It is determined whether the current operating environment meets the triggering condition of the AES system according to the environmental perception data and the vehicle operation data. If the triggering condition of the AES system is met, the vehicle automatic emergency avoidance function is triggered.

[0046] The environmental perception data can be collected based on front radar sensors and front camera sensors. The vehicle operation data includes real-time speed, acceleration, vehicle body mass, etc. When the vehicle continuously monitors the front road environment through front sensors (such as radar and camera), the system first calculates the time to collision (TTC) between the vehicle and potential obstacles (such as vehicles and pedestrians); if the TTC is lower than a preset safety threshold (for example, 1.5 seconds), and the system determines that simply relying on braking cannot avoid collision (such as insufficient braking distance or obstacle lateral deviation), the driver response detection stage is entered - whether the driver actively performs obstacle avoidance operation is judged by monitoring the steering torque, throttle / brake pedal action; if no effective driver input is detected within the last intervention window period (usually 0.8-1 second before collision), the system will finally trigger the AES in combination with the real-time road adhesion coefficient.

[0047] The road adhesion coefficient can be measured based on a dedicated road adhesion coefficient sensor, for example, an optical sensor, which can analyze road microtexture according to laser scattering to obtain the road adhesion coefficient. The road adhesion coefficient can also be calculated indirectly based on vehicle slip rate and the like. The road adhesion coefficient can also be obtained by analyzing a road image collected by a camera.

[0048] Further, the road adhesion coefficient can be calculated based on road vibration data. Specifically, the road vibration data is collected by a road vibration sensor, and then the road adhesion coefficient is determined based on the road vibration data.

[0049] At step S104, a trajectory is planned according to the road adhesion coefficient, the environmental perception data, and the vehicle operation data to obtain an emergency avoidance trajectory.

[0050] Specifically, after the AES system is triggered, the AES system plans a trajectory according to real-time road adhesion coefficient, environmental perception data, and vehicle operation data to obtain an emergency avoidance trajectory for the vehicle to perform emergency avoidance.

[0051] At step S106, the vehicle is controlled to perform emergency avoidance according to the emergency avoidance trajectory.

[0052] In the embodiments of the present application, the road adhesion coefficient, the environmental perception data, and the vehicle operation data are acquired in real time. After the AES is triggered, a trajectory is planned according to the road adhesion coefficient, the environmental perception data, and the vehicle operation data to obtain an emergency avoidance trajectory. Finally, the vehicle is controlled to perform emergency avoidance according to the emergency avoidance trajectory. The automatic emergency avoidance method provided in the embodiments of the present application combines the road adhesion coefficient to plan an automatic emergency avoidance trajectory, so that the vehicle emergency avoidance function can work stably on different road adhesion coefficients, avoiding collision while preventing vehicle instability, and improving the robustness of the automatic emergency avoidance function.

[0053] In one embodiment, please refer to Figure 2 The flowchart of the automatic emergency avoidance method provided in the embodiments of the present application is shown. The execution subject of the flowchart can be a program for automatic emergency avoidance, or the execution subject of the flowchart can also be a vehicle or a domain controller loaded with the above program, or other devices capable of communicating with the vehicle, the domain controller, and the like, which are not limited in detail.

[0054] The automatic emergency avoidance method will be described in detail below with reference to the flowchart shown in Figure 2 The automatic emergency avoidance method can specifically include the following steps:

[0055] At step S202, the road adhesion coefficient, the environmental perception data, and the vehicle operation data are acquired.

[0056] Specifically, step S202 can refer to the detailed description of step S102 in another embodiment of the present application, which will not be repeated here.

[0057] In step S204, the maximum lateral acceleration and the maximum trajectory curvature are calculated based on the road adhesion coefficient.

[0058] After the AES system is triggered, the AES system needs to plan a trajectory based on real-time road adhesion coefficient, environmental perception data and vehicle operation data to obtain an emergency avoidance trajectory for the vehicle to perform emergency avoidance.

[0059] Firstly, the AES system calculates the maximum lateral acceleration and the maximum trajectory curvature based on the road adhesion coefficient. The maximum lateral acceleration refers to the maximum lateral acceleration that the tire can provide under the condition of the current road adhesion coefficient, and exceeding this value may cause side slip instability. The maximum trajectory curvature refers to the maximum trajectory curvature limit that the vehicle can reach under the condition of the current road adhesion coefficient.

[0060] In step S206, trajectory planning is performed based on the maximum lateral acceleration and the maximum trajectory curvature as constraint conditions in combination with the environmental perception data and the vehicle operation data to obtain at least one trajectory.

[0061] Specifically, after the AES system is triggered, the AES system can plan a collision-free avoidance trajectory based on the environmental perception data and the vehicle operation data. In this embodiment, trajectory planning is performed based on the environmental perception data and the vehicle operation data with the maximum lateral acceleration and the maximum trajectory curvature as constraint conditions to obtain at least one planned trajectory.

[0062] In step S208, an emergency avoidance trajectory is determined from the at least one trajectory based on a dynamic cost function.

[0063] After trajectory planning based on the environmental perception data and the vehicle operation data obtains at least one trajectory, an optimal emergency avoidance trajectory is then determined from the at least one trajectory based on a predefined cost function.

[0064] The predefined cost function can include multiple cost items, which can specifically include a curvature change rate, a maximum lateral acceleration, a reference trajectory deviation, a trigger time, a minimum obstacle distance, etc. Each cost item corresponds to a different weight. The curvature change rate refers to the change rate of the trajectory curvature; the lateral acceleration cost is used to represent the impact of lateral acceleration on passenger comfort and the risk of vehicle side slip; the reference trajectory deviation refers to the degree of fit with the global trajectory, which is used to represent avoidance efficiency; the trigger time refers to the timing of trajectory execution, and the earlier the time, the higher the safety; and the minimum obstacle distance refers to the minimum distance between the vehicle and the obstacle during avoidance execution, and the greater the minimum distance, the higher the safety.

[0065] Step S210, controlling the vehicle to perform emergency avoidance according to the emergency avoidance trajectory.

[0066] In the embodiment of the present application, the road adhesion coefficient, the environment perception data and the vehicle operation data are acquired in real time. After the AES is triggered, the maximum lateral acceleration and the maximum trajectory curvature are calculated based on the road adhesion coefficient, and then the trajectory planning is performed based on the maximum lateral acceleration and the maximum trajectory curvature as the constraint conditions in combination with the environment perception data and the vehicle operation data to obtain at least one trajectory. Then, the emergency avoidance trajectory is determined in the at least one trajectory based on the dynamic cost function, and finally the vehicle is controlled to perform emergency avoidance according to the emergency avoidance trajectory. By using the automatic emergency avoidance method provided in the embodiment of the present application, the trajectory planning for automatic emergency avoidance is performed in combination with the road adhesion coefficient, so that the vehicle emergency avoidance function can work stably on the road surface with different road adhesion coefficients, and the vehicle instability is prevented while avoiding collision, thereby improving the robustness of the automatic emergency avoidance function.

[0067] In one embodiment, in step S208, the emergency avoidance trajectory is determined in the at least one trajectory based on the dynamic cost function, which can specifically be: determining a weight group corresponding to the road adhesion coefficient, configuring the weight of each cost term of the dynamic cost function based on the weight group, and the weight group including the weight corresponding to each cost term; and determining the emergency avoidance trajectory in the at least one trajectory based on the dynamic cost function configured with the weight.

[0068] As can be easily understood, the predefined cost function can include multiple cost terms, which can specifically include the cost terms of the curvature change rate, the maximum lateral acceleration, the reference trajectory deviation, the trigger time, the minimum obstacle distance, etc. Each cost term corresponds to a different weight. In the embodiment of the present application, the corresponding relationship between the predefined road adhesion coefficient and the weight of each cost term is defined, and different cost term weights are adjusted for different road adhesion coefficients to achieve different trajectory selection strategies for different road adhesion coefficients. For example, in the case of high road adhesion coefficient, the efficiency-first principle is followed, i.e., the reference line deviation cost term is dominant and occupies a higher weight; in the case of low road adhesion coefficient, the safety-first principle is followed, i.e., the trigger time and the minimum obstacle distance cost terms are dominant and occupy higher weights.

[0069] In the embodiment, the different trajectory selection strategies are adjusted according to the road adhesion coefficient to select the emergency avoidance trajectory, which can make the automatic emergency avoidance function have higher adaptability to the road surface with different road adhesion coefficients, thereby improving the robustness of the automatic emergency avoidance function.

[0070] In one embodiment, please refer to Figure 3 The automatic emergency avoidance method provided in the embodiment of the present application is shown in the flowchart.

[0071] In the following, the automatic emergency avoidance method provided in the embodiment of the present application is described in detail. Figure 3The flowchart is illustrated in detail, and the automatic emergency avoidance method can specifically include the following steps:

[0072] In step S302, the road adhesion coefficient, the environment perception data, and the vehicle operation data are acquired.

[0073] Specifically, step S302 can refer to the detailed description of step S102 in another embodiment of the present application, which is not repeated here.

[0074] In step S304, the maximum lateral acceleration and the maximum trajectory curvature are calculated based on the road adhesion coefficient.

[0075] Specifically, step S304 can refer to the detailed description of step S204 in another embodiment of the present application, which is not repeated here.

[0076] In step S306, trajectory planning is performed with the maximum lateral acceleration and the maximum trajectory curvature as constraint conditions in combination with the environment perception data and the vehicle operation data, to obtain at least one trajectory.

[0077] Specifically, step S306 can refer to the detailed description of step S206 in another embodiment of the present application, which is not repeated here.

[0078] In step S308, an emergency avoidance trajectory is determined in the at least one trajectory based on a dynamic cost function.

[0079] Specifically, step S308 can refer to the detailed description of step S208 in another embodiment of the present application, which is not repeated here.

[0080] In step S310, a feedforward control parameter is determined according to the trajectory curvature indicated in the emergency avoidance trajectory and the road adhesion coefficient, and the feedforward control parameter includes a feedforward steering angle and a feedforward asymmetric braking force.

[0081] The emergency avoidance trajectory can include a trajectory curvature, an avoidance trigger time, and the like.

[0082] Specifically, after the emergency avoidance trajectory is determined, the AES system calculates the vehicle control parameter according to the trajectory curvature indicated in the emergency avoidance trajectory and the road adhesion coefficient, and the vehicle control parameter can include a steering angle and an asymmetric braking force between wheels.

[0083] The steering angle and the asymmetric braking force are calculated in combination with the road adhesion coefficient, which can make the automatic emergency avoidance function have higher adaptability to different road adhesion coefficients, and improve the robustness of the automatic emergency avoidance function.

[0084] The vehicle can generate an asymmetric braking force by applying braking force to the single-side wheels, so as to generate a rotation torque around the center of mass of the vehicle, and assist the vehicle to change direction. That is, in the embodiment of the application, the vehicle is controlled to travel along the emergency avoidance trajectory by controlling the steering angle and the asymmetric braking force.

[0085] Optionally, the feedforward control parameter can be a pre-calibrated vehicle control parameter, and a mapping relationship between the road adhesion coefficient, the trajectory curvature and the feedforward control parameter is pre-stored in the feedforward controller. During the emergency avoidance of the vehicle, the corresponding feedforward control parameter can be determined according to the trajectory curvature and the road adhesion coefficient indicated in the emergency avoidance trajectory.

[0086] Optionally, the proportion of the steering angle control and the asymmetric braking control can be adjusted according to the size of the road adhesion coefficient. For example, on a road with high road adhesion coefficient, the vehicle has strong grip, and the vehicle is not easy to slide, at this time, the steering angle control is mainly relied on, and the proportion of the steering control is higher than that of the asymmetric braking control. On a road with low adhesion coefficient, the vehicle has weak grip, and is easy to slide, in this case, the proportion of the asymmetric braking is increased, and the vehicle is controlled to turn by the asymmetric braking.

[0087] Please refer to Figure 4 An example schematic diagram for compensating the turning of the vehicle by the asymmetric braking control is provided for the embodiment of the application. As shown in Figure 4 The diagram includes a left drawing L and a right drawing R, includes an obstacle vehicle X and a vehicle W, and the emergency avoidance trajectory includes three trajectory routes A-B-C. As shown in the left drawing L, during the turning of the vehicle W from the A trajectory to the B trajectory, the right wheels of the vehicle are braked to generate a right yaw angular velocity, so as to assist the vehicle to turn right. As shown in the right drawing L, during the turning of the vehicle W from the B trajectory to the C trajectory, the left wheels of the vehicle are braked to generate a left yaw angular velocity, so as to assist the vehicle to turn left.

[0088] In step S312, the vehicle is controlled to perform the emergency avoidance based on the feedforward control parameter.

[0089] The feedforward control parameter includes a feedforward steering angle and a feedforward asymmetric braking force. The feedforward controller sends the feedforward steering angle to the steering system of the vehicle, and the steering system controls the steering angle of the vehicle according to the feedforward steering angle. The feedforward controller sends the feedforward asymmetric braking force to the braking system of the vehicle, and the braking system applies braking to each wheel of the vehicle according to the feedforward asymmetric braking force.

[0090] The feedforward asymmetric braking force includes the braking force of each wheel.

[0091] In the embodiment of the present application, the vehicle is controlled to steer and travel according to the emergency avoidance trajectory in a manner of steering angle control and asymmetric braking control. The asymmetric braking can enable the vehicle to maintain good emergency avoidance performance on a road surface with low adhesion coefficient.

[0092] In one embodiment, the vehicle can be controlled to perform emergency avoidance in a manner of combination of feedforward and feedback. Please refer to Figure 5 An automatic emergency avoidance method provided by the embodiment of the present application is shown in a flowchart.

[0093] The automatic emergency avoidance method will be described in detail below with reference to the flowchart shown in Figure 5 The automatic emergency avoidance method can specifically include the following steps:

[0094] In step S402, the road adhesion coefficient, the environmental perception data and the vehicle operation data are acquired.

[0095] Specifically, step S402 can refer to the detailed description of step S102 in another embodiment of the present application, which will not be repeated here.

[0096] In step S404, the maximum lateral acceleration and the maximum trajectory curvature are calculated based on the road adhesion coefficient.

[0097] Specifically, step S404 can refer to the detailed description of step S204 in another embodiment of the present application, which will not be repeated here.

[0098] In step S406, trajectory planning is performed in combination of the environmental perception data and the vehicle operation data with the maximum lateral acceleration and the maximum trajectory curvature as constraint conditions to obtain at least one trajectory.

[0099] Specifically, step S406 can refer to the detailed description of step S206 in another embodiment of the present application, which will not be repeated here.

[0100] In step S408, an emergency avoidance trajectory is determined from the at least one trajectory based on a dynamic cost function.

[0101] Specifically, step S408 can refer to the detailed description of step S208 in another embodiment of the present application, which will not be repeated here.

[0102] In step S410, feedforward control parameters including feedforward steering angle and feedforward asymmetric braking force are determined according to the trajectory curvature indicated in the emergency avoidance trajectory and the road adhesion coefficient.

[0103] The emergency avoidance trajectory can include parameters such as trajectory curvature and avoidance trigger time.

[0104] Specifically, after determining the emergency avoidance trajectory, the AES system calculates vehicle control parameters according to the trajectory curvature and the road adhesion coefficient indicated in the emergency avoidance trajectory, and the vehicle control parameters can include a steering angle and an asymmetric braking force between wheels.

[0105] The steering angle and the asymmetric braking force are calculated in combination with the road adhesion coefficient, so that the automatic emergency avoidance function has higher adaptability to roads with different road adhesion coefficients, and the robustness of the automatic emergency avoidance function is improved.

[0106] The asymmetric braking force can be generated by applying a braking force to the single-side wheels, so that the vehicle generates a rotation torque around the center of mass of the vehicle, thereby assisting the vehicle in changing direction. That is, in the embodiments of the present application, the vehicle is controlled to travel along the emergency avoidance trajectory by controlling the steering angle and the asymmetric braking force of the vehicle.

[0107] Optionally, the feedforward control parameter can be a pre-calibrated vehicle control parameter, and a mapping relationship between the road adhesion coefficient, the trajectory curvature and the feedforward control parameter is pre-stored in the feedforward controller. During the emergency avoidance of the vehicle, the corresponding feedforward control parameter can be determined according to the trajectory curvature and the road adhesion coefficient indicated in the emergency avoidance trajectory.

[0108] Optionally, the proportion of the steering angle control and the asymmetric braking control can be adjusted according to the size of the road adhesion coefficient. For example, on a road with a high road adhesion coefficient, the vehicle has strong grip and is not prone to side slipping, so the steering angle control is mainly relied on at this time, and the proportion of the steering control is higher than that of the asymmetric braking control. On a road with a low adhesion coefficient, the vehicle has weak grip and is prone to side slipping, so the proportion of the asymmetric braking is adjusted to be high, and the vehicle is controlled to change direction by the asymmetric braking.

[0109] In step S412, a target yaw rate is calculated according to the vehicle speed and the trajectory curvature indicated in the emergency avoidance trajectory, and when a yaw rate deviation between an actual yaw rate of the vehicle and the target yaw rate is greater than a preset deviation threshold, a feedback control parameter is determined according to the yaw rate deviation, and the feedback control parameter includes a feedback steering angle and a feedback asymmetric braking force.

[0110] During the control of the vehicle to perform emergency avoidance based on the feedforward control parameter, if the vehicle still has a problem of insufficient or excessive steering, the feedback control can be used for correction. Specifically, a target yaw rate is calculated according to the vehicle speed and the trajectory curvature indicated in the emergency avoidance trajectory, a yaw rate deviation is calculated according to an actual yaw rate of the vehicle and the target yaw rate, and if the yaw rate deviation is greater than a preset deviation threshold, it is determined that the vehicle has a problem of insufficient or excessive steering.

[0111] Further specifically, in a case that the actual yaw rate of the vehicle is detected to be greater than the target yaw rate, and a yaw rate deviation between the actual yaw rate and the target yaw rate is greater than a preset deviation threshold, it is determined that the vehicle has excessive steering; in a case that the actual yaw rate of the vehicle is detected to be less than the target yaw rate, and the yaw rate deviation between the actual yaw rate and the target yaw rate is greater than the preset deviation threshold, it is determined that the vehicle has insufficient steering; in a case that it is determined that the vehicle has excessive steering or insufficient steering, feedback control calculation is performed according to the yaw rate deviation to obtain feedback control parameters, the feedback control parameters including a feedback steering angle and a feedback asymmetric braking force.

[0112] Optionally, the feedback control parameters can be pre-calibrated vehicle control parameters, and a mapping relationship between the yaw rate deviation and the feedback control parameters is pre-stored in the feedback controller. During the emergency avoidance of the vehicle, the corresponding feedback control parameters can be determined according to the yaw rate deviation.

[0113] Further optionally, the proportion of the steering angle control and the asymmetric braking control in the feedback control can be adjusted according to the size of the road adhesion coefficient. For example, on a road with a high road adhesion coefficient, the vehicle has strong grip and is not prone to side slip, and in this case, the steering angle control is mainly relied on, and the proportion of the steering control is higher than that of the asymmetric braking control; on a road with a low adhesion coefficient, the vehicle has weak grip and is prone to side slip, and in this case, the asymmetric braking proportion is increased, and the vehicle steering is controlled by the asymmetric braking.

[0114] In step S414, the vehicle is controlled to perform emergency avoidance based on the feedforward control parameters and the feedback control parameters.

[0115] The feedforward control parameters include a feedforward steering angle and a feedforward asymmetric braking force, and the feedback control parameters include a feedback steering angle and a feedback asymmetric braking force. During the control of the vehicle to perform emergency avoidance based on the feedforward control parameters and the feedback control parameters, the target steering angle is determined by comprehensively determining the feedforward steering angle determined by the feedforward controller and the feedback steering angle determined by the feedback controller, and then the target steering angle is sent to the vehicle steering system, and the vehicle steering angle is controlled by the steering system according to the target steering angle; and the target asymmetric braking force is determined by comprehensively determining the feedforward asymmetric braking force determined by the feedforward controller and the feedback asymmetric braking force determined by the feedback controller, and then the target asymmetric braking force is sent to the vehicle braking system, and the corresponding braking force is applied to each wheel of the vehicle by the braking system according to the target asymmetric braking force.

[0116] In the embodiments of the present application, the vehicle is controlled to perform emergency avoidance in a manner combining feedforward control and feedback control, and the vehicle is controlled to steer and travel along the emergency avoidance trajectory in a manner combining steering angle control and asymmetric braking control. The asymmetric braking can enable the vehicle to maintain good emergency avoidance performance on a road surface with low adhesion coefficient, and the feedback control can further improve the avoidance performance of the vehicle in emergency avoidance.

[0117] In one embodiment, the present application further provides a computer program product, which can store a computer program. The computer program can be loaded and executed to perform the automatic emergency avoidance method of each of the above embodiments. The specific execution process can be referred to the specific description in each of the above embodiments, which will not be repeated here.

[0118] In one embodiment, the present application further provides a storage medium, which can store a plurality of instructions. The instructions are suitable for being loaded and executed by a processor to perform the automatic emergency avoidance method of each of the above embodiments. The specific execution process can be referred to the specific description in each of the above embodiments, which will not be repeated here.

[0119] In one embodiment, the present application further provides Figure 6 The structure of the vehicle controller is shown in FIG. 1. As shown in FIG. 1, the vehicle controller includes a processor 11, an internal bus 12, a network interface 13, a memory 14, a non-volatile memory 15, and other hardware as required by the business. Figure 6 At the hardware level, the vehicle controller includes a processor 11, an internal bus 12, a network interface 13, a memory 14, a non-volatile memory 15, and other hardware as required by the business. The vehicle controller can be arranged in the vehicle, and the processor 11 reads the corresponding computer program from the non-volatile memory 15 into the memory and then runs to implement the automatic emergency avoidance method described above.

[0120] In one embodiment, the present application further provides a vehicle, which can include the vehicle controller described above to perform the automatic emergency avoidance method through the vehicle controller, to acquire the road adhesion coefficient, the environmental perception data and the vehicle operation data in real time, to plan the trajectory according to the road adhesion coefficient, the environmental perception data and the vehicle operation data after the AES is triggered, to obtain the emergency avoidance trajectory, and finally to control the vehicle to perform emergency avoidance according to the emergency avoidance trajectory. By using the automatic emergency avoidance method provided in the embodiments of the present application, the trajectory planning for automatic emergency avoidance is combined with the road adhesion coefficient, so that the vehicle emergency avoidance function can work stably on different road adhesion coefficient road surfaces, and the vehicle is prevented from losing stability while avoiding collision, thereby improving the robustness of the automatic emergency avoidance function.

[0121] Finally, each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0122] The above only describes the embodiments of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. An automatic emergency avoidance method, comprising: Obtain road adhesion coefficient, environmental perception data and vehicle operation data; performing trajectory planning based on the road adhesion coefficient, the environmental perception data, and the vehicle operation data to obtain an emergency avoidance trajectory; The vehicle is controlled to perform emergency avoidance according to the emergency avoidance trajectory.

2. The method according to claim 1, wherein the performing trajectory planning based on the road adhesion coefficient, the environmental perception data, and the vehicle operation data to obtain an emergency avoidance trajectory comprises: calculating a maximum lateral acceleration and a maximum track curvature based on the road adhesion coefficient; performing trajectory planning by combining the environmental perception data and the vehicle operation data with the maximum lateral acceleration and the maximum trajectory curvature as constraints to obtain at least one trajectory; An emergency avoidance trajectory is determined among the at least one trajectory based on a dynamic cost function.

3. The method according to claim 2, wherein determining the emergency avoidance trajectory in the at least one trajectory based on a predefined cost function comprises: Determining a weight group corresponding to the road adhesion coefficient, and configuring weights of each cost item of the dynamic cost function based on the weight group, wherein the weight group includes weights corresponding to each cost item; An emergency avoidance trajectory is determined in the at least one trajectory based on the dynamic cost function completed with the weight configuration.

4. The method according to claim 1, wherein controlling the vehicle to perform emergency avoidance according to the emergency avoidance trajectory comprises: determining a feedforward control parameter based on a trajectory curvature indicated in the emergency avoidance trajectory and the road adhesion coefficient, the feedforward control parameter including a feedforward steering angle and a feedforward asymmetric braking force; The vehicle is controlled to perform emergency avoidance based on the feedforward control parameters.

5. The method according to claim 4, further comprising: calculating a target yaw rate based on a vehicle speed and a trajectory curvature indicated in the emergency avoidance trajectory; When it is detected that a yaw rate deviation between the actual yaw rate of the vehicle and the target yaw rate is greater than a preset deviation threshold, a feedback control parameter is determined according to the yaw rate deviation, the feedback control parameter including a feedback steering angle and a feedback asymmetric braking force; The vehicle is controlled to perform emergency avoidance based on the feedforward control parameter and the feedback control parameter.

6. The method according to any one of claims 4 or 5, further comprising: When calculating the feedforward control parameters, the ratio of steering control and asymmetric braking control in the feedforward control is adjusted according to the road adhesion coefficient; When calculating the feedback control parameters, the ratio of the steering control and the asymmetric braking control in the feedback control is adjusted according to the road adhesion coefficient.

7. The method according to claim 1, wherein obtaining the road adhesion coefficient comprises: Acquire road surface vibration data collected by a road surface vibration sensor, and determine a road surface adhesion coefficient based on the road surface vibration data.

8. A storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are suitable for being loaded by a processor and executing the steps of the method according to any one of claims 1 to 7.

9. A computer program product comprising a computer program, wherein when the computer program is executed, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A vehicle controller comprising: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the steps of the method according to any one of claims 1 to 7.

11. A vehicle comprising the vehicle controller according to claim 10.

Images