Method, device, equipment, vehicle and medium for determining understeering gradient

Abstract

The invention relates to a method, device and equipment for determining an understeering gradient, a vehicle and a medium. The method includes determining a compensation value for a first understeer gradient for feed-forward control of a first steering behavior based on the first steering behavior of the vehicle on the first curve. The method further includes determining a second understeer gradient based on the first understeer gradient and the compensation value. In this way, the new understeering gradient can be determined based on the steering behavior of the vehicle, the understeering gradient used for controlling the steering behavior of the vehicle is updated, the understeering gradient can better conform to the actual situation of the vehicle, and therefore feedforward control over the steering behavior of the vehicle based on the understeering gradient is more accurate, and the control accuracy of the vehicle is improved. Therefore, the number of times of feedback adjustment on the steering behavior of the vehicle can be reduced, and the steering behavior of the vehicle is more stable.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and more particularly, to a method, a device, a apparatus, a vehicle and a medium for determining an understeer gradient. Background Art

[0002] With the continuous development of vehicle intelligence, intelligent driving technology is being applied to more and more vehicles. For example, in intelligent driving technologies such as advanced driver assistance system (ADAS), lane keeping function is an important function to improve driving safety and user driving experience. The lane keeping function can automatically correct the vehicle's driving route in the lane when it detects that the vehicle has deviated from the lane, so that the vehicle's driving route does not deviate from the lane.

[0003] When a vehicle is driving on a curve, the vehicle's steering behavior can be automatically controlled through assisted or autonomous driving technology. If the vehicle's route deviates from the curve during the steering process, the vehicle's lane keeping function can correct the deviation through continuous feedback adjustment to prevent the vehicle from deviating from the curve. Summary of the invention

[0004] The embodiments of the present disclosure propose a method, device, equipment, vehicle and medium for determining an understeer gradient. In the embodiments of the present disclosure, a compensation value for a first understeer gradient can be determined by a first steering behavior of the vehicle on a first curve, wherein the first understeer gradient is used to perform feedforward control on the first steering behavior. Then, the embodiments of the present disclosure can determine a second understeer gradient. In this way, a new understeer gradient can be determined based on the steering behavior actually performed by the vehicle, and the understeer gradient can be updated so that the understeer gradient is more in line with the actual steering characteristics of the vehicle, thereby making the feedforward control of the steering behavior on this basis more accurate. In this way, the number of interventions of feedback adjustment during the vehicle steering process can be reduced, making the vehicle's steering behavior more stable.

[0005] In a first aspect of the present disclosure, a method for determining an understeering gradient is provided. The method includes determining a compensation value for a first understeering gradient based on a first steering behavior of a vehicle on a first curve, wherein the first understeering gradient is used to perform feedforward control on the first steering behavior. The method also includes determining a second understeering gradient based on the first understeering gradient and the compensation value.

[0006] In a second aspect of the present disclosure, a device for determining an understeering gradient is provided. The device includes a compensation value determination module configured to determine a compensation value for a first understeering gradient based on a first steering behavior of a vehicle on a first curve, wherein the first understeering gradient is used to perform feedforward control on the first steering behavior. The device also includes an update module configured to determine a second understeering gradient based on the first understeering gradient and the compensation value.

[0007] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes one or more processors; and a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided according to the first aspect of the present disclosure.

[0008] In a fourth aspect of the present disclosure, a vehicle is provided, comprising the electronic device provided according to the third aspect of the present disclosure.

[0009] In a fifth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method provided according to the first aspect of the present disclosure.

[0010] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0012] Figure 1 A schematic diagram showing a scene of a turning behavior of a vehicle on a curve in some embodiments of the present disclosure;

[0013] Figure 2 A schematic diagram showing an example scenario in which various embodiments of the present disclosure may be implemented;

[0014] Figure 3 A flow chart showing a method for determining an understeer gradient according to some embodiments of the present disclosure is shown;

[0015] Figure 4 A schematic diagram showing a scenario of controlling a steering behavior of a vehicle according to some embodiments of the present disclosure;

[0016] Figure 5A schematic diagram showing a scenario of controlling a steering behavior of a vehicle according to some embodiments of the present disclosure;

[0017] Figure 6 A schematic diagram showing a method for controlling the steering behavior of a vehicle according to some embodiments of the present disclosure;

[0018] Figure 7 A block diagram showing an apparatus for determining an understeer gradient according to some embodiments of the present disclosure; and

[0019] Figure 8 A schematic block diagram of an example device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0021] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0022] In the embodiments of the present disclosure, vehicles may include but are not limited to cars, trucks, electric vehicles, motorcycles, buses, ships, airplanes, drones, recreational vehicles, construction equipment, intelligent robots, etc., and the embodiments of the present disclosure are not particularly limited. For ease of explanation, in the embodiments of the present disclosure, the method provided by the present disclosure is described using a car as an example. It should be understood that this cannot be a limitation on the embodiments of the present disclosure. In the embodiments of the present disclosure, the intelligent driving function refers to the function of assisting the driver in controlling the vehicle through sensors, controllers, communication modules and other devices, or even completely replacing the driver to achieve unmanned driving. It may include but is not limited to unmanned driving, assisted driving and other functions of the vehicle. These functions can be achieved through a controller configured in the vehicle, or through a cloud controller.

[0023] When the vehicle passes through a curve, the intelligent driving function can control and adjust the vehicle's steering behavior by means of feedforward control and feedback adjustment, so that the vehicle's driving route does not deviate from the lane and lane keeping is achieved. In an embodiment of the present disclosure, the feedforward control of the steering behavior refers to determining the feedforward control parameters used to control the vehicle's steering in advance by calculation, and then controlling the vehicle's steering behavior in the curve based on the feedforward control parameters when the vehicle enters the curve. In the feedforward control of the steering behavior, the intelligent driving function can calculate the steering angle that the wheel or steering wheel needs to perform in advance based on the detection of the curve on which the vehicle is traveling, thereby controlling the wheel or steering wheel to steer at the calculated steering angle, so that the vehicle completes the steering behavior in the curve. In an embodiment of the present disclosure, the feedback adjustment of the steering behavior refers to determining the feedback parameters based on the steering behavior that the vehicle has already performed, and adjusting the steering behavior that the vehicle is about to perform based on the feedback parameters. In the feedback adjustment of the steering behavior, the intelligent driving function can detect the error between the steering behavior performed by the vehicle and the curve in real time, and adjust the steering angle of the wheel or steering wheel accordingly, thereby adjusting the steering behavior of the vehicle on the curve.

[0024] At present, in the process of feedforward control of the steering behavior of the vehicle by the intelligent driving function, a predefined understeering gradient is set to compensate for understeering or oversteering that may occur due to factors such as sliding between the wheel and the ground during the feedforward calculation process. The inventor of the present application found that as the wheel wears, the problem of understeering or oversteering when the vehicle turns on a curve may worsen. Due to the influence of factors such as wheel wear, the steering characteristics of the vehicle will change, and the predefined understeering gradient will not reflect the actual state of the vehicle, resulting in the intelligent driving function of the vehicle in the feedforward control of the vehicle turning. The steering angle calculated based on the predefined understeering gradient is inaccurate, and then the actual driving route of the vehicle is greatly deviated from the target route, which will cause the vehicle to frequently deviate from the lane during the steering process. The intelligent driving function needs to frequently adjust the feedback to enable the vehicle to achieve lane keeping, causing the vehicle to vibrate due to frequent adjustments when turning. This will reduce the stability of the vehicle when turning, reduce the reliability of the intelligent driving function, and reduce the user experience.

[0025] To this end, an embodiment of the present disclosure proposes a scheme for determining an understeering gradient. In an embodiment of the present disclosure, a first steering behavior of a vehicle at a first curve may be performed on the basis of a first understeering gradient, and the first understeering gradient is used to perform feedforward control on the first steering behavior. An embodiment of the present disclosure may determine a compensation value for the first understeering gradient based on the first steering behavior, and determine a second understeering gradient based on the compensation value and the first understeering gradient.

[0026] In this way, the vehicle's understeer gradient can be updated based on the vehicle's historical steering behavior, so that the understeer gradient used for feedforward control of the current steering behavior can more accurately reflect the vehicle's current state. Feedforward control of the steering behavior on this basis will reduce the degree of deviation between the vehicle's actual driving route and the expected driving route, and reduce the number of feedback adjustments during the steering process, thereby increasing the vehicle's turning stability, increasing the reliability of the intelligent driving function, and improving the user experience.

[0027] Figure 1 A schematic diagram of an example scenario 100 in which multiple embodiments of the present disclosure can be implemented is shown. In the scenario 100, a vehicle 101 is included, and the vehicle 101 may have an intelligent driving function, which can be implemented by a controller configured on the vehicle 101 or in the cloud. The intelligent driving function can control the driving behavior of the vehicle 101 on the road, such as controlling the turning behavior of the vehicle 101 on the curve 102. On the curve 102, the driving route maintained by the vehicle 101 under the control of the intelligent driving function is the center line 103 of the road. When the vehicle 101 is about to enter the curve 102, the intelligent driving function of the vehicle 101 can calculate in advance the steering angle that the steering wheel or steering wheel of the vehicle 101 needs to perform by detecting the curvature or turning radius of the curve 102, and feed-forward control the steering behavior of the vehicle 101 on the curve 102. During the process of vehicle 101 executing steering behavior based on the feedforward control of the intelligent driving function, the actual driving route of the vehicle may deviate from the center line 103 of the curve 102 due to factors such as calculation error, execution error, road detection error or wheel wear. In order to achieve lane keeping, the intelligent driving function can make feedback adjustments to the steering behavior, such as increasing the steering angle of vehicle 102 when vehicle 102 understeers, and reducing the steering angle of vehicle 102 when vehicle 102 oversteers, so as to return the driving route of vehicle 102 to the center line 103. Under the feedforward control and multiple feedback adjustments of the intelligent driving function, the actual driving route of the vehicle on the curve 102 can be, for example, route 104 in scene 100.

[0028] Figure 2 2 is a schematic diagram of an example scenario 200 in which various embodiments of the present disclosure may be implemented. Figure 2As shown, scene 200 includes vehicle 201, which may be the same vehicle as vehicle 101 in scene 100. The intelligent driving function may control vehicle 201 to turn along the center line 203 of the curve 202. In some embodiments, the intelligent driving function may detect the curve 202 through sensors configured on vehicle 201 or sensors of roadside equipment, thereby determining the turning radius R of the curve 202, and determining the turning radius R of the curve 202 based on the predefined understeering gradient and the real-time speed V of the vehicle 201 along the direction of the front of the vehicle. x Based on the predefined wheelbase L of the vehicle 201, the steering angle θ is determined, and the steering wheel of the vehicle is controlled to output the steering angle θ, so that the vehicle 201 maintains the center line 203 of the curve 202 to perform the steering behavior. In some embodiments, the intelligent driving function can control the steering behavior of the vehicle 201 by controlling the steering wheel of the vehicle 201. In some embodiments, the intelligent driving function can control the steering angle of one or more wheels of the vehicle 201, thereby realizing the control of the steering behavior of the vehicle 201.

[0029] In an embodiment of the present disclosure, the historical steering behavior of the vehicle 201 may be performed on the basis of the first understeering gradient. On the basis of the historical steering behavior, a compensation value for the first understeering gradient may be determined, and on this basis, a new understeering gradient (referred to as the second understeering gradient for ease of explanation) may be determined, thereby updating the understeering gradient and making the current understeering gradient more consistent with the actual situation of the vehicle. In some embodiments, based on the determined second understeering gradient, the steering behavior of the vehicle 201 on the curve 202 may be feedforward controlled. In some embodiments, based on the feedforward control of the steering behavior of the vehicle 201 on the curve 202 based on the second understeering gradient, feedback adjustment may also be performed on the steering behavior of the vehicle 201. In some embodiments, based on the steering behavior actually performed by the vehicle 201 on the curve 202, a compensation value for the second understeering gradient may be determined again, and the second understeering gradient may be updated based on the compensation value, and a third understeering gradient may be determined for the next feedforward control of the steering behavior of the vehicle 201, thereby dynamically updating the understeering gradient.

[0030] Figure 3 A flow chart of a method 300 for determining an understeering gradient according to some embodiments of the present disclosure is shown. The method 300 may be executed by a management device for managing an understeering gradient, which may be configured in a vehicle or in a cloud, and may be implemented in software and / or hardware. In some embodiments, the management device may also control the steering behavior of the vehicle, that is, the management device may be a controller for controlling the steering behavior of the vehicle. Figure 3, method 300 may include block 302 and block 304 .

[0031] In box 302, the management device determines a compensation value for a first understeering gradient based on a first steering behavior of the vehicle on a first curve, wherein the first understeering gradient is used to perform feedforward control on the first steering behavior. In an embodiment of the present disclosure, the steering behavior of the vehicle may be controlled by a steering controller, which may be configured on the vehicle or on the cloud, for example, may be an electronic control unit of the vehicle's steering system. In the process of the vehicle entering the first curve, the steering controller may perform feedforward control on the first steering behavior based on the first understeering gradient. The steering controller may determine a first feedback parameter based on the steering behavior actually performed by the vehicle, and perform feedback adjustment on the first steering behavior based on the first feedback parameter. In some embodiments, the management device may obtain the first feedback parameter from the steering controller, thereby determining a compensation value for the first understeering gradient based on the first feedback parameter.

[0032] In some embodiments, the management device and the steering controller are two independent devices. In some embodiments, the management device can also realize the function of the steering controller to control the first steering behavior of the vehicle, that is, the management device can be the same device as the steering controller. Next, the management device is used as the execution subject, and the management device realizes the function of the steering controller and the control of the first steering behavior is described. In the process of driving on the road, the road state can be detected by sensors such as cameras and radars. For example, the camera can be used to identify whether the road in front of the vehicle is a curve, and the radar can be used to identify whether there are obstacles. In the case of identifying that the vehicle is about to enter the first curve, the management device can determine the turning radius of the first curve based on the sensor's perception data, and on this basis, based on the predefined first understeering gradient, determine the feedforward control parameter. The feedforward control parameter can be, for example, the steering angle that the steering wheel needs to perform or the steering angle that the steering wheel needs to turn, so that the management device can control the vehicle to perform the first steering behavior on the first curve, and realize the feedforward control of the first steering behavior.

[0033] In some embodiments, during the process of the vehicle performing the first steering behavior, the management device can obtain the perception data from the sensor in real time, determine the actual driving path of the vehicle on this basis, and compare it with the target path (for example, the center line of the curve determined by detecting the curve through a camera), so as to determine the error value between the first steering behavior actually performed by the vehicle and the first curve. In some embodiments, the first error value can also be the angle between the direction of the head of the vehicle and the tangent direction of the center line of the curve. In some embodiments, the management device can determine the first feedback parameter for reducing the error value when the error value is greater than a predetermined error threshold. In some embodiments, the first feedback parameter can be the steering angle that the steering wheel of the vehicle needs to change during the vehicle steering process, or the turning angle that the steering wheel of the vehicle needs to change. The management device can further control the steering wheel or steering wheel of the vehicle on this basis, so as to realize the feedback adjustment of the first steering behavior, so that the actual driving route of the vehicle does not deviate from the first curve, and lane keeping is realized. Exemplarily, during the process of the vehicle turning in the entire curve, the steering angle output by the wheel in real time can be θ+Δθ, where θ is the feedforward control parameter determined by the management device, Δθ is the first feedback parameter determined by the management device, and when Δθ is zero, it means that there is no feedback adjustment intervention. After the vehicle completes the first steering behavior in the first lane, the management device can obtain the first feedback parameter determined in the process of controlling the vehicle to perform the first steering behavior, and determine the compensation value for the first understeering gradient based on a predefined relationship.

[0034] Back to Figure 3 In box 304, the management device may determine the second understeering gradient based on the first understeering gradient and the compensation value. In some embodiments, the second understeering gradient may be the sum of the first understeering gradient and the compensation value. In some embodiments, the management device may determine multiple compensation values ​​based on multiple steering behaviors of the vehicle in multiple curves, each compensation value corresponding to the steering behavior of the vehicle in a curve, and the management device may determine the second understeering gradient based on the average value of these compensation values. In this way, it is possible to avoid determining an erroneous understeering gradient due to an accidental error in a curve, thereby affecting the next steering behavior of the vehicle, and the determination of the understeering gradient can better reflect the actual situation of the vehicle. In some embodiments, the first understeering gradient is stored in a memory of the management device, the steering controller or the vehicle, and the management device may obtain the first understeering gradient from the memory, add it to the compensation value, thereby determining the second understeering gradient, and store it in the memory as a new understeering gradient. In some embodiments, a feedforward control model including the first understeering gradient is predefined in the management device, and the management device may update the first understeering gradient in the feedforward control model to the sum of the first understeering gradient and the compensation value, that is, the second understeering gradient.

[0035] Through method 300, the management device can determine a new understeering gradient based on the previous (or previous multiple) steering behaviors. When the steering characteristics of the vehicle change due to factors such as tire wear, the understeering gradient can be updated in a timely manner based on the vehicle's steering behavior on the curve to make it consistent with the current actual situation of the vehicle. In this way, based on the updated understeering gradient, the feedforward control of the vehicle's steering behavior can be made more accurate, reducing the occurrence of vehicle deviation from the curve, thereby reducing feedback adjustments during the vehicle's steering process, making the vehicle run more smoothly on the curve, improving the reliability of the vehicle's intelligent driving function, and improving the user experience.

[0036] As mentioned above, in some embodiments, the management device can realize the function of the steering controller and can control the steering behavior of the vehicle. On this basis, the method 300 can also include box 306. In box 306, the management device performs feedforward control on the second steering behavior of the vehicle on the second curve based on the second understeering gradient. In some embodiments, when the sensor detects that the vehicle is about to enter the second curve, the management device can obtain the radius of the second curve and the current speed of the vehicle. For example, the management device can obtain the perception data of the second curve by the camera, identify and process the perception data, and thus determine the radius of the second curve. The management device can obtain the real-time speed of the vehicle from the control system of the vehicle, or obtain the real-time speed of the vehicle from the speed sensor of the vehicle. The management device can determine the feedforward control parameter based on the turning radius of the second curve, the real-time speed of the vehicle, and the second understeering gradient. The feedforward control parameter can be, for example, the steering angle that the steering wheel needs to perform or the steering angle that the steering wheel needs to turn on the second curve. In this way, the management device can achieve more accurate feedforward control of the second steering behavior based on the updated understeering gradient.

[0037] refer to Figure 4 , Figure 4A schematic diagram of a scenario 400 for controlling the steering behavior of a vehicle in an embodiment of the present disclosure is shown. In scenario 400, under the feedforward control and feedback adjustment of the steering controller, the vehicle 401 passes through the curve 402 at a first moment and passes through the curve 403 at a second moment. When it is detected that the vehicle 401 is about to enter the curve 402, the steering controller performs feedforward control on the first steering behavior of the vehicle 401 on the curve 402 based on the first understeering gradient, for example, the steering angle θ1 that the front wheel needs to output when the vehicle 401 passes through the curve 402 is determined based on the first understeering gradient. Due to wheel wear and other conditions, the first understeering gradient cannot accurately reflect the steering characteristics of the vehicle 401, and the θ1 calculated based on the first understeering gradient is inaccurate. Therefore, when the front wheels of the vehicle 401 turn on the curve 402 at the steering angle of θ1, a large deviation will occur from the expected path, resulting in frequent intervention of feedback adjustment and frequent correction of the steering angle θ1 output by the steering wheel. Schematically, under the combined effect of feedforward control and feedback adjustment, the actual route that the vehicle 401 passes through when performing the first steering behavior on the curve 402 may be the route 404 in the scene 400. In an embodiment of the present disclosure, after passing the curve 402, the management device may determine the second understeering gradient based on the first steering behavior performed by the vehicle 401 according to the methods in the aforementioned boxes 302 and 304. In this way, when it is detected that the vehicle 401 passes through the curve 403, the steering controller may perform feedforward control on the steering behavior of the vehicle 401 based on the second understeering gradient updated by the management device, for example, determining the steering angle θ2 that the front wheels need to output when the vehicle 401 passes through the curve 403. The second understeering gradient is a new understeering gradient determined based on the steering behavior actually performed by the vehicle 401, which can reflect the real steering characteristics of the vehicle 401. Therefore, based on the second understeering gradient, the second steering behavior of the vehicle 401 on the curve 403 can be accurately feedforward controlled, for example, a more accurate steering angle θ2 can be determined. On this basis, the second turning behavior of vehicle 401 on curve 403 will better conform to the expected path, which will reduce the intervention of feedback adjustment. Schematically, the actual route that vehicle 401 passes through when performing the second turning behavior on curve 403 can be route 405 in scene 400, and route 405 that vehicle 401 actually passes through on curve 403 is smoother than route 404 that vehicle 401 actually passes through on curve 402.

[0038] As described above, in some embodiments, the management device may implement the function of a steering controller. Taking scenario 400 as an example, in some embodiments, the curve 402 in scenario 400 may correspond to the first curve in box 302. In the aforementioned box 302, the management device may determine a feedforward control parameter θ1 for feedforward control of the first steering behavior of the vehicle 401 in the curve 402 based on the first understeering gradient. The feedforward control parameter θ1 may satisfy the following formula:

[0039] θ1=L / R1 + Kv0 × a y1 (1)

[0040] Where L is the wheelbase of the vehicle 401, R1 is the turning radius of the curve 402, that is, the radius of the center line of the curve 402, and a y1 is the lateral acceleration of the vehicle 401 traveling on the curve 402, and Kv0 is the first understeering gradient. Wherein, for the vehicle 401, the value of L is a predefined constant; the value of R1 can be determined by detecting the road through a sensor; a y1 =V x1 2 / R1,V x1 is the velocity of the vehicle 401 on the curve 402 along the front direction, V x1 The value of can be obtained from the speed sensor of the vehicle 401 in real time, or from the control system of the vehicle 401; the value of Kv0 can be a predefined constant. The meanings of the parameters L1 and R1 in formula (1) can also refer to the aforementioned Figure 2 It should be understood that the formulas provided in the embodiments of the present disclosure are only given for illustration purposes, and each formula may also be reasonably mathematically transformed, and the present disclosure does not limit the specific presentation of the formula.

[0041] In some embodiments, the curve 403 in the scene 400 may correspond to the second curve in the box 306. In the box 306, the management device may determine the feedforward control parameter θ2 for feedforward control of the second steering behavior of the vehicle 401 in the curve 403 based on the second understeering gradient. The feedforward control parameter θ2 may satisfy the following formula:

[0042] θ2=L / R2 + (Kv0 + ΔKv) × a y2 (2)

[0043] Where L is the wheelbase of the vehicle, R2 is the turning radius of the curve 403, and a y2 is the lateral acceleration of the vehicle 401 traveling on the curve 403, a y1 =V x2 2 / R2,V x2is the speed of the vehicle 401 along the front direction on the curve 403, Kv0 is the first understeering gradient, and ΔKv is the compensation value for the first understeering gradient determined in the aforementioned box 302. In some embodiments, in the aforementioned box 302, the management device determines multiple compensation values ​​for the first understeering gradient based on the steering behavior of the vehicle in multiple curves (corresponding to the first curve in the box 302), and ΔKv is the average value of the compensation values ​​of the understeering gradient determined multiple times. The value of Kv0+ΔKv is the second understeering gradient. It should be understood that the meaning of each parameter in formula (2) can correspond to the meaning of each parameter in formula (1).

[0044] In some embodiments, in the aforementioned block 302 , the compensation value ΔKv1 for the first understeering gradient determined based on the first steering behavior may satisfy the following formula:

[0045] ΔKv1=Δθ1 / a y1 (3)

[0046] Where Δθ1 is the first feedback parameter used to perform feedback adjustment on the first steering behavior, a y1 is the lateral acceleration of the vehicle on the first curve. The first feedback parameter Δθ1 is used for lane keeping of the vehicle on the first curve, for example, it can be the steering angle that the steering wheel of the vehicle needs to change during the steering process determined by the steering controller or the management device based on the sensor perception data. In some embodiments, the steering controller or the management device performs multiple feedback adjustments on the first steering behavior of the vehicle on the first curve, and each feedback adjustment can correspond to a feedback sub-parameter for one feedback adjustment. The first feedback parameter obtained by the management device may include these feedback sub-parameters. In this case, Δθ1 in formula (3) is the average value of multiple feedback sub-parameters.

[0047] In some embodiments, when the steering controller or management device performs feedforward control on the second steering behavior of the vehicle based on the second understeering gradient, the steering controller or management device may determine the second feedback parameter based on the error value between the actual driving route of the vehicle and the second curve, thereby performing feedback adjustment on the second steering behavior of the vehicle. In some embodiments, after completing the second steering behavior, the management device may determine the second compensation value for the second understeering gradient based on the second feedback parameter, thereby determining the third understeering gradient based on the second understeering gradient and the second compensation value. When the vehicle enters the curve next time, the steering controller or management device may perform feedforward control on the next steering behavior based on the third understeering gradient. That is, the aforementioned method 300 may be performed in a loop, so that the management device may continuously update the understeering gradient so that the understeering gradient conforms to the actual steering characteristics of the vehicle, thereby reducing the error between the actual steering behavior of the vehicle and the curve during each feedforward control, thereby reducing the number of feedback adjustments when the vehicle passes the curve each time, so that the vehicle can pass the curve smoothly every time.

[0048] In some embodiments, the management device may determine the deviation distance between the vehicle and the curve on which the vehicle is traveling during the process of performing the steering behavior. When the deviation distance is greater than a predetermined distance threshold, the management device determines a compensation value based on the steering behavior of the vehicle on the curve, and determines a new understeering gradient based on the compensation value. That is, the management device may execute the aforementioned method 300 after the deviation distance between the vehicle and the curve during the steering process reaches a certain degree. In some embodiments, the deviation distance between the vehicle and the curve may be determined by the lateral distance between the center of the rear axle of the vehicle and the center line of the curve during the process of the vehicle passing through the curve. For example, the vehicle may be equipped with a sensor for detecting the lateral distance between the center of the rear axle of the vehicle and the center line of the curve, such as a camera. The management device may obtain the change of the lateral distance during the process of the vehicle passing through the curve from the sensor, calculate the average value of the absolute value of the lateral distance during the entire steering process after taking the absolute value of the lateral distance, and use it as the deviation distance between the vehicle and the curve on which the vehicle is traveling during the process of performing the steering behavior. In some embodiments, the deviation distance may also be determined by the lateral distance between the center of the vehicle and the center line of the curve.

[0049] Taking the above scenario 400 as an example, after the steering controller or management device controls the vehicle 401 to pass through the curve 402 based on the first understeering gradient, the management device can determine the deviation distance between the vehicle 401 and the curve 402 during the process of passing through the curve 402. When the deviation distance is greater than the predetermined distance threshold, the management device executes the above method 300 again to determine the compensation value of the understeering gradient and determine the second understeering gradient. If the deviation distance is less than or equal to the predetermined distance threshold, the management device may not execute the method 300. At this time, the steering controller or management device still controls the steering behavior of the vehicle 401 in the curve 403 based on the first understeering gradient. In this way, when the deviation between the vehicle and the curve is not obvious during the steering process, the understeering gradient is not updated, which can reduce the calculation load of the management device.

[0050] In some embodiments, when the management device determines that the deviation distance between the vehicle and the curve during the process of passing the curve is greater than a predetermined distance threshold, the management device may execute method 300 again when the vehicle passes the curve next time. Taking scenario 400 as an example, after the management device determines that the deviation distance between vehicle 401 and curve 402 during the turning process of vehicle 401 on curve 402 is greater than a predetermined distance threshold, the management device may determine the compensation value based on the steering behavior of the vehicle in curve 403 and update the understeer gradient through method 300 after vehicle 401 enters the next curve, i.e., curve 403. In some embodiments, when the management device determines that the deviation distance between the vehicle and the curve during the process of passing the curve is greater than a predetermined distance threshold, the management device may start executing method 300 after the vehicle exits the curve to update the understeer gradient. Taking scenario 400 as an example, after the management device determines that the deviation distance between vehicle 401 and curve 402 is greater than a predetermined distance threshold during the turning process of vehicle 401 on curve 402, the management device updates the understeer gradient, and then the steering controller or the management device can control vehicle 401 to pass through curve 403 based on the updated understeer gradient after vehicle 401 enters the next curve, i.e., curve 403.

[0051] In some embodiments, during the process of the management device cyclically executing the aforementioned method 300 to update the understeering gradient, the management device may continue to determine the deviation distance between the vehicle and the curve during the steering process. When the deviation distance is less than the second distance threshold, the management device may stop executing the method 300, stop determining the compensation value and stop updating the understeering gradient. After that, the steering controller or the management device may control the steering behavior of the vehicle in the curve based on the determined understeering gradient. In other words, after the deviation between the vehicle and the curve during the steering process is reduced to a certain extent by updating the understeering gradient, it is no longer necessary to continue to determine the compensation value and to continue to update the understeering gradient. In this way, the calculation load of the management device can be further reduced. It can be understood that the second distance threshold may be less than the aforementioned predetermined distance threshold, or may be equal to the aforementioned predetermined distance threshold.

[0052] In some embodiments, in the aforementioned box 306, the management device may control the steering behavior of the vehicle based on the understeer gradient only when the turning radius of the curve is less than a predetermined radius threshold and the vehicle speed is greater than a predetermined speed threshold. For example, in the aforementioned scenario 400, when feedforward control is performed on the first steering behavior of the vehicle at the first curve, the feedforward control parameter θ1 can be determined by the relationship θ1=L / R1. For another example, when feedforward control is performed on the second steering behavior of the vehicle at the second curve, the feedforward control parameter θ2 can be determined by the relationship θ2=L / R2. When the turning radius is large and the vehicle speed is low, the vehicle will not understeer or oversteer during the steering process. Therefore, the understeer gradient does not need to be considered when determining the feedforward control parameters, which can reduce the amount of calculation.

[0053] Figure 5 FIG. 5 is a schematic diagram of a scenario 500 for controlling the steering behavior of a vehicle according to some embodiments of the present disclosure. Figure 5As shown, the scene 500 includes a controller 501, which can obtain the perception data of the sensor 502 and control the steering behavior of the vehicle 503. The controller 501 can correspond to the aforementioned management device or steering controller. The controller 501 can include a feedforward module 504, a feedback module 505, an output module 506 and a learning module 507. Through these modules, the controller 501 can implement the aforementioned method 300. Exemplarily, the feedforward module 504 can determine the feedforward control parameters based on the perception data obtained from the sensor 502, such as the turning radius and the vehicle speed. The feedback module 505 is used to determine the feedback parameters based on the perception data obtained from the sensor 502, such as the angle between the vehicle orientation and the lane tangent direction. The output module 506 can control the steering wheel or steering wheel of the vehicle 503 to output the steering angle based on the feedforward control parameters. In the case of the presence of feedback parameters from the feedback module 505, the output module 506 can also control the steering wheel or steering wheel of the vehicle 503 to output the steering angle based on the feedforward control parameters and the feedback parameters. In some embodiments, the output module may also send the feedforward control parameters and / or feedback parameters to the control system of the vehicle, thereby controlling the steering behavior of the vehicle. The learning module 507 included in the controller 501 may obtain the feedback parameters from the feedback module 505, determine the compensation value for the understeer gradient on this basis, and provide it to the feedforward module 504, so that the feedforward module 504 may update the understeer gradient based on the compensation value, and determine the new feedforward control parameters with the updated understeer gradient. In some embodiments, the learning module 507 may determine the updated understeer gradient based on the determined compensation value for the understeer gradient, and provide it to the feedforward module 504, so that the feedforward module 504 may determine the new feedforward control parameters based on the updated understeer gradient. It should be noted that Figure 5 The illustrated scenario 500 is merely an example of the present disclosure, and in some embodiments, the sensor 502 and the controller 501 may both be configured in the vehicle 503. In some embodiments, the controller 501 may include more or fewer modules.

[0054] Figure 6 A schematic diagram of a method 600 for controlling the steering behavior of a vehicle according to some embodiments of the present disclosure is shown. Figure 6 The method shown may be executed by a controller, which may be, for example, a steering controller for controlling the steering behavior of the vehicle 101 in the scene 100, the vehicle 201 in the scene 200, or the vehicle 401 in the scene 400. In some embodiments, the controller may correspond to the aforementioned management device. The controller may also be Figure 5 The controller 501 in FIG. Figure 6 As shown, method 600 may include blocks 602 to 618 .

[0055] In box 602, the controller determines that the vehicle is about to enter a curve based on the perception data obtained from the sensor. In box 604, the controller determines the feedforward control parameters based on the understeering gradient, and on this basis, performs feedforward control on the steering behavior of the vehicle in the curve. In box 606, the controller obtains the perception data from the sensor and determines the error value between the steering behavior actually performed by the vehicle and the curve it is traveling on. In box 608, the controller determines the feedback parameters based on the error value. In box 610, the controller performs feedback adjustment on the steering behavior of the vehicle in the curve based on the feedback parameters. In box 612, the controller determines whether the vehicle has exited the curve. If not, return to box 606; if so, execute box 614. In box 614, the controller obtains relevant data on the vehicle's steering behavior in the curve, such as the turning radius, the vehicle's speed, the change in the vehicle's position in the curve, and the feedback parameters of each feedback adjustment made by the controller to the steering behavior. In box 615, the controller determines the deviation distance between the vehicle and the curve during the turning process in the curve based on the position change of the vehicle in the curve. For example, the controller can determine the average value of the lateral distance between the center of the rear axle of the vehicle and the center line of the curve during the entire turning process, and use it as the deviation distance between the vehicle and the curve. In box 616, the controller determines whether the deviation distance is greater than a predetermined distance threshold. If so, step 617 is executed. If not, step 602 is returned. In box 617, the controller determines a compensation value for updating the understeering gradient based on the feedback parameter. In box 618, the controller updates the understeering gradient based on the compensation value, for example, adding the compensation value to the understeering gradient stored locally and storing it as a new understeering gradient. In method 600, after box 618, the controller can continue to execute box 602. In some embodiments, method 600 can be combined with the aforementioned method 300. For example, the controller can execute box 302 in method 300 after executing box 612.

[0056] Figure 7 1 is a block diagram of an apparatus 700 for determining an understeer gradient according to some embodiments of the present disclosure. Figure 7 As shown, the device 700 includes a compensation value determination module 710, which is configured to determine the compensation value for the first understeering gradient based on the first steering behavior of the vehicle on the first curve, wherein the first understeering gradient is used to perform feedforward control on the first steering behavior. The device 700 also includes an updating module 720, which is configured to determine a second understeering gradient based on the first understeering gradient and the compensation value.

[0057] In some embodiments, the apparatus 700 further includes a control module configured to perform feed-forward control on a second steering behavior of the vehicle on a second curve based on a second understeer gradient.

[0058] In some embodiments, the compensation value determination module 710 includes: a feedback parameter acquisition module, configured to acquire a first feedback parameter of the vehicle, wherein the first feedback parameter is used to adjust the first steering behavior for lane keeping of the vehicle; and a first determination module, configured to determine the compensation value based on the first feedback parameter.

[0059] In some embodiments, the feedback parameter acquisition module includes: an error determination unit configured to determine a first error value between a first steering behavior of the vehicle and a first curve; and a feedback parameter determination unit configured to determine a first feedback parameter based on the first error value.

[0060] In some embodiments, the first determination module includes: a driving state acquisition unit, configured to acquire the turning radius of the first curve and the vehicle speed of the first steering behavior of the vehicle; and a first determination unit, configured to determine the compensation value based on the first feedback parameter, the vehicle speed and the turning radius.

[0061] In some embodiments, the first feedback parameter includes multiple feedback sub-parameters, wherein the multiple feedback sub-parameters are used to make multiple adjustments to the first steering behavior of the vehicle at the first curve, and wherein the first determination module includes: a second determination unit, configured to determine the compensation value based on an average value of the multiple feedback sub-parameters.

[0062] In some embodiments, the feedback parameter acquisition module includes: a parameter acquisition unit, configured to acquire multiple feedback parameters, wherein the multiple feedback parameters are respectively used to adjust multiple steering behaviors of the vehicle on multiple curves, the multiple feedback parameters include a first feedback parameter, the multiple curves include a first curve, and the multiple steering behaviors include a first steering behavior; the first determination module includes: a third determination unit, configured to determine multiple compensation values ​​corresponding to the multiple feedback parameters respectively; and the update module 720 includes: a first update unit, configured to determine a second understeering gradient based on an average value of the multiple compensation values ​​and a first understeering gradient.

[0063] In some embodiments, the compensation value determination module 710 includes: a deviation distance determination unit, configured to determine the deviation distance between the vehicle and the first curve during the execution of the first steering behavior; and a compensation value determination unit, configured to determine the compensation value based on the first steering behavior of the vehicle on the first curve when the deviation distance is greater than a predetermined distance threshold.

[0064] In some embodiments, the control module includes: a second driving state acquisition unit, configured to acquire the turning radius of the second curve and the vehicle speed; and a first control unit, configured to perform feed-forward control on the second steering behavior based on a second understeer gradient when the turning radius of the second curve is less than a predetermined radius threshold and the vehicle speed is greater than a predetermined speed threshold.

[0065] In some embodiments, the device 700 also includes: a second error determination module, configured to determine a second error value between the vehicle's second steering behavior and the second curve; a second feedback parameter determination module, configured to determine a second feedback parameter based on the second error value; and an adjustment module, configured to adjust the vehicle's second steering behavior based on the second feedback parameter.

[0066] In some embodiments, the device 700 also includes: a second compensation value determination module, configured to determine a second compensation value for a second understeer gradient based on a second feedback parameter; a second update module, configured to determine a third understeer gradient based on the second understeer gradient and the second compensation value; and a second control module, configured to perform feedforward control on a third steering behavior of the vehicle on a third curve based on the third understeer gradient.

[0067] It can be understood that by using the device 700 of the present disclosure, at least one of the advantages that can be achieved by the method or process described above can be achieved. For example, the device 700 can update the understeering gradient based on the previous steering behavior of the vehicle, so that the understeering gradient can reflect the current steering characteristics of the vehicle. In some embodiments, the device 700 can perform feedforward control on the steering behavior of the vehicle based on the updated understeering attitude, thereby reducing the degree of deviation between the steering behavior of the vehicle and the curve, reducing the number of feedback adjustments, and making the steering behavior of the vehicle smoother.

[0068] Figure 8 A schematic block diagram of an example device 800 that can be used to implement an embodiment of the present disclosure is shown. As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0069] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0070] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as method 300 or method 600. For example, in some embodiments, method 300 or method 600 may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the method XX described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method 300 or the method 600 in any other appropriate manner (eg, by means of firmware).

[0071] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip systems (SOCs), load programmable logic devices (CPLDs), and the like.

[0072] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0073] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In addition, although each operation is depicted in a specific order, this should be understood as requiring such operations to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination.

[0074] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for determining an understeer gradient, comprising: determining a compensation value for a first understeering gradient based on a first steering behavior of the vehicle on a first curve, wherein the first understeering gradient is used for feedforward control of the first steering behavior; and Based on the first understeer gradient and the compensation value, a second understeer gradient is determined.

2. The method according to claim 1, further comprising: Based on the second understeer gradient, a second steering behavior of the vehicle on the second curve is feed-forward controlled.

3. The method according to claim 2, wherein feed-forward controlling the second steering behavior based on the second understeer gradient comprises: Obtaining a turning radius of the second curve and a speed of the vehicle; as well as When the turning radius of the second curve is smaller than a predetermined radius threshold and the vehicle speed is greater than a predetermined vehicle speed threshold, the second steering behavior is feed-forward controlled based on the second understeering gradient.

4. The method according to any one of claims 1 to 3, wherein determining a compensation value for an understeering gradient based on a first steering behavior of the vehicle on a first curve comprises: Acquiring a first feedback parameter of the vehicle, wherein the first feedback parameter is used to adjust the first steering behavior for lane keeping of the vehicle; as well as Based on the first feedback parameter, the compensation value is determined.

5. The method according to claim 4, wherein obtaining the first feedback parameter of the vehicle comprises: determining a first error value between the first steering behavior of the vehicle and the first curve; as well as Based on the first error value, the first feedback parameter is determined.

6. The method of claim 4, wherein determining the compensation value based on the first feedback parameter comprises: Acquire a turning radius of the first curve and a vehicle speed of the vehicle during the first turning behavior; as well as The compensation value is determined based on the first feedback parameter, the vehicle speed, and the turning radius.

7. The method according to claim 4, wherein the first feedback parameter comprises a plurality of feedback sub-parameters, wherein the plurality of feedback sub-parameters are used to make multiple adjustments to the first steering behavior of the vehicle on the first curve, and Wherein determining the compensation value based on the first feedback parameter comprises: The compensation value is determined based on an average value of the plurality of feedback sub-parameters.

8. The method according to claim 4, wherein obtaining the first feedback parameter of the vehicle comprises: Acquire a plurality of feedback parameters, wherein the plurality of feedback parameters are respectively used to adjust a plurality of steering behaviors of the vehicle on a plurality of curves, the plurality of feedback parameters include the first feedback parameter, the plurality of curves include the first curve, and the plurality of steering behaviors include the first steering behavior; Wherein determining the compensation value based on the first feedback parameter comprises: determining a plurality of compensation values ​​respectively corresponding to the plurality of feedback parameters; and wherein determining the second understeering gradient comprises: The second understeer gradient is determined based on an average of the plurality of compensation values ​​and the first understeer gradient.

9. The method according to any one of claims 1 to 3, wherein determining a compensation value for a first understeering gradient based on a first steering behavior of the vehicle on a first curve comprises: determining a deviation distance between the vehicle and the first curve during the process of performing the first steering behavior; as well as In a case where the deviation distance is greater than a predetermined distance threshold, the compensation value is determined based on a first steering behavior of the vehicle on the first curve.

10. The method according to any one of claims 1 to 3, further comprising: determining a second error value between the second steering behavior of the vehicle and the second curve; determining a second feedback parameter based on the second error value; as well as Based on the second feedback parameter, the second steering behavior of the vehicle is adjusted.

11. The method according to claim 10, further comprising: determining a second compensation value of the second understeering gradient based on the second feedback parameter; determining a third understeer gradient based on the second understeer gradient and the second compensation value; as well as Based on the third understeering gradient, a third steering behavior of the vehicle on a third curve is feed-forward controlled.

12. An apparatus for determining an understeer gradient, comprising: a compensation value determination module configured to determine a compensation value for a first understeering gradient based on a first steering behavior of the vehicle on a first curve, wherein the first understeering gradient is used to perform feedforward control on the first steering behavior; as well as An updating module is configured to determine a second understeering gradient based on the first understeering gradient and the compensation value.

13. An electronic device comprising: at least one processor; as well as A memory coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, causing the apparatus to perform the method according to any one of claims 1-11.

14. A vehicle comprising the electronic device according to claim 13.

15. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 11.

Images