Unmanned vehicle control method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to an unmanned vehicle control method and device, electronic equipment and storage medium. The method comprises: obtaining an initial speed limit curve and a current speed of the unmanned vehicle; performing deceleration filtering processing on the initial speed limit curve according to a first deceleration parameter; if the speed corresponding to the current position of the obtained first deceleration filtering curve is less than the current speed, adjusting the first deceleration parameter according to a target step length to obtain an updated deceleration parameter, and performing deceleration filtering processing on the initial speed limit curve based on the updated deceleration parameter to obtain a target deceleration filtering curve; performing acceleration filtering processing on the initial speed limit curve to obtain an acceleration filtering curve; obtaining a first fusion filtering curve by fusing the above curves; and performing driving control on the unmanned vehicle according to the first fusion filtering curve. In this way, the unmanned vehicle can be smoothly controlled when driving at the speed corresponding to the first fusion filtering curve.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to autonomous vehicle control methods, devices, electronic equipment and storage media. Background Technology

[0002] For speed planning of autonomous vehicles, factors such as the vehicle's dynamic performance or kinematic constraints need to be considered, and corresponding speeds need to be planned for each point on the path in order to achieve control of the autonomous vehicle.

[0003] However, speed planning algorithms in related technologies typically rely on optimizers. These optimizers treat the speed limit curve as the optimization target and solve within the space defined by the curve. But when the speed limit curve has complex shapes with many undulations, direct optimization by the optimizer increases computational complexity and can lead to abnormally long processing times or timeouts. Therefore, these technologies require significant post-processing, which reduces the accuracy and precision of the solution, resulting in inaccurate vehicle control. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for controlling unmanned vehicles.

[0005] According to a first aspect of this disclosure, an autonomous vehicle control method is provided, the method comprising:

[0006] Obtain the initial speed limit curve of the autonomous vehicle and the current speed of the autonomous vehicle at the current location point;

[0007] The initial speed limit curve is subjected to deceleration filtering processing according to the first deceleration parameter to obtain the first deceleration filtered curve.

[0008] If the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter. Based on the updated deceleration parameter, the initial speed limit curve is decelerated and filtered to obtain the updated deceleration filter curve. The process continues until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, and the target deceleration filter curve is obtained.

[0009] The initial speed limit curve is subjected to acceleration filtering to obtain an acceleration filtered curve;

[0010] The initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve are fused together to obtain a first fused filter curve.

[0011] The autonomous vehicle is controlled to drive based on the first fusion filter curve.

[0012] According to a second aspect of this disclosure, an autonomous vehicle control device is provided, the device comprising:

[0013] The acquisition module is used to acquire the initial speed limit curve of the autonomous vehicle and the current speed of the autonomous vehicle at the current location point;

[0014] The first deceleration filter curve acquisition module is used to perform deceleration filtering on the initial speed limit curve according to the first deceleration parameter to obtain the first deceleration filter curve.

[0015] The target deceleration filter curve acquisition module is used to adjust the first deceleration parameter according to the target step size when the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, to obtain the updated deceleration parameter, and to perform deceleration filtering processing on the initial speed limit curve based on the updated deceleration parameter to obtain the updated deceleration filter curve, until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, to obtain the target deceleration filter curve.

[0016] An acceleration filtering processing module is used to perform acceleration filtering processing on the initial speed limit curve to obtain an acceleration filtered curve.

[0017] The first fusion processing module is used to fuse the initial speed limit curve, the acceleration filter curve and the target deceleration filter curve to obtain the first fused filter curve.

[0018] The control module is used to control the driving of the autonomous vehicle based on the first fused filtering curve.

[0019] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0020] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods described above.

[0021] The autonomous vehicle control method, apparatus, electronic device, and storage medium provided in this disclosure acquire an initial speed limit curve and the current speed of the autonomous vehicle at its current position. The initial speed limit curve is then subjected to deceleration filtering according to a first deceleration parameter to obtain a first deceleration filtered curve. If the speed at the current position corresponding to the first deceleration filtered curve is less than the current speed, the first deceleration parameter is adjusted according to a target step size to obtain an updated deceleration parameter. Based on the updated deceleration parameter, the initial speed limit curve is then subjected to deceleration filtering to obtain an updated deceleration filtered curve. This process continues until the speed at the current position corresponding to the updated deceleration filtered curve is greater than or equal to the current speed, resulting in a target deceleration filtered curve. The initial speed limit curve is then subjected to acceleration filtering to obtain an acceleration filtered curve. The initial speed limit curve, acceleration filtered curve, and target deceleration filtered curve are then fused to obtain a first fused filtered curve. Finally, the autonomous vehicle is controlled based on the first fused filtered curve. Based on the first deceleration parameter, the deceleration parameter is gradually adjusted by the target step size. This makes the target filtered curve obtained by filtering the initial speed limit curve with the adjusted deceleration parameter smoother. Consequently, the first fused filtered curve obtained by fusing the initial speed limit curve, the acceleration filtered curve, and the target deceleration filtered curve is even smoother. This disclosure can obtain a smoother fused filtered curve without increasing computational complexity, and thus achieve more accurate and stable driving control of autonomous vehicles through the fused filtered curve. Attached Figure Description

[0022] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0023] Figure 1a This is a schematic diagram of the filtering curve in related technologies;

[0024] Figure 1b This is a schematic diagram of another filtering curve in a related technology;

[0025] Figure 2 A flowchart of an exemplary embodiment of the present disclosure of an unmanned vehicle control method;

[0026] Figure 3 A schematic diagram of an initial speed limit curve provided for an exemplary embodiment of this disclosure;

[0027] Figure 4a A schematic diagram of a filter curve provided as yet another exemplary embodiment of this disclosure;

[0028] Figure 4b A schematic diagram of a filter curve provided as yet another exemplary embodiment of this disclosure;

[0029] Figure 4c A schematic diagram of a filter curve provided as yet another exemplary embodiment of this disclosure;

[0030] Figure 4d A schematic diagram of a filter curve provided as yet another exemplary embodiment of this disclosure;

[0031] Figure 5 A schematic diagram of an overshoot deceleration filter curve and a fusion filter curve provided as yet another exemplary embodiment of this disclosure;

[0032] Figure 6 A flowchart of an autonomous vehicle control method provided as yet another exemplary embodiment of this disclosure;

[0033] Figure 7 A schematic block diagram of the functional modules of an unmanned vehicle control device provided for an exemplary embodiment of this disclosure;

[0034] Figure 8 A structural block diagram of an electronic device provided as an exemplary embodiment of this disclosure;

[0035] Figure 9 A block diagram of a computer system provided for an exemplary embodiment of this disclosure. Detailed Implementation

[0036] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0037] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0038] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0039] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0040] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0041] In the field of autonomous driving, speed planning for autonomous vehicles typically needs to consider factors such as vehicle dynamics, kinematic constraints, or speed limits along the path. By planning the speed at each point on the path, a controllable trajectory for the vehicle is obtained, which has significant guiding implications for the comfort and safety of autonomous vehicles. Autonomous vehicles often face complex and changing environments during autonomous driving, including traffic rules, obstacles, or curvature constraints along the path, resulting in varying initial speed limit curve shapes.

[0042] When speed planning algorithms are processed using optimizers, they can include linear and nonlinear optimization. The optimizer can directly use the initial speed limit curve as the optimization object and solve within the space defined by the initial speed limit curve. If the actual vehicle speed is higher than the initial speed limit curve, the initial state obtained by the optimizer may not be within the solvable space, resulting in no result. Furthermore, if the initial speed limit curve has a complex shape with many undulations, directly solving it through the optimizer will increase computational complexity, leading to abnormally long processing times or timeouts. Therefore, extensive post-processing is required, which in turn reduces the accuracy and precision of the solution.

[0043] like Figure 1a As shown, if the deceleration parameter is too small, the first speed of the deceleration filter will be less than the vehicle's initial speed. The speed planning algorithm in related technologies will then assume that the vehicle will not reach the desired speed even with deceleration filtering. In this case, the fusion filter only takes the result of the acceleration filter, leading to abrupt changes in the output speed or the deceleration filter failing. Figure 1b As shown, excessively large deceleration parameters can lead to excessively rapid deceleration during the deceleration phase. Setting larger deceleration parameters can reduce the occurrence of deceleration filter failure, but it challenges the vehicle's maximum deceleration capability, resulting in very abrupt braking in most situations. However, in many cases, the vehicle does not need to have a large deceleration, especially when equipped with a main radar, the perception range can be within the range of 60m-80m.

[0044] In the embodiments disclosed herein, such as Figure 5As shown, when the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter. Based on the updated deceleration parameter, the initial speed limit curve is then subjected to deceleration filtering to obtain the updated deceleration filter curve. This process continues until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed. In other words, an iterative process to improve the deceleration parameter is provided. Furthermore, if the deceleration parameter exceeds the vehicle's maximum deceleration capability, this disclosure will not continue iterating but will instead perform overshoot deceleration filtering on the deceleration filter curve, using the vehicle's maximum deceleration as the overshoot deceleration input to the overshoot filter. Ultimately, a smoother fused filter curve can be obtained without increasing computational complexity, thereby enabling more accurate and stable driving control of the autonomous vehicle.

[0045] It should be noted that the accompanying drawings provided in this disclosure include the following interpretations: "the input velocity" represents the initial speed limit curve, "the rise velocity" represents the acceleration filter curve, "the current velocity" represents the current speed, "the drop velocity" represents the deceleration filter curve, "the filter velocity" represents the fusion filter curve, and "the exceed velocity" represents the overshoot deceleration filter curve. In the accompanying drawings, the horizontal axis represents distance and the vertical axis represents speed.

[0046] Therefore, by setting corresponding acceleration parameters, deceleration parameters, or overshoot deceleration parameters based on the maximum deceleration under different conditions, the initial speed limit curve can be filtered using different parameters. This can effectively simplify the shape of the initial speed limit curve, reduce the computational complexity of the optimizer, ensure the solvability of the overshoot condition, and improve the robustness of the planning.

[0047] To further improve the stability of vehicles during operation and better control autonomous vehicles, this disclosure provides a parameter self-adjustment method for autonomous driving speed filtering, which can achieve the function of self-adjusting parameters based on acceleration filters, deceleration filters and overshoot filters.

[0048] As shown in Figure 1, in step S11, the current speed and initial speed limit curve of the autonomous vehicle are obtained (the initial speed limit curve is shown in Figure 1). Figure 3 (As shown). Figure 2This disclosure provides a schematic diagram of an initial speed limit curve for embodiments of the invention. The speed limit corresponding to each point on the path in the initial speed limit curve can be determined based on speed limit signs along the path, the maximum turning speed of the autonomous vehicle on curves, or the distance of the autonomous vehicle to obstacles ahead. This allows the autonomous vehicle to obtain its initial speed limit curve during its journey. The autonomous vehicle can drive based on the initial speed limit curve, ensuring its speed does not exceed the speed corresponding to the initial speed limit curve, thus avoiding problems such as traffic accidents. The initial speed limit curve in this embodiment can be dynamically adjusted based on factors such as the distance or speed between the autonomous vehicle and vehicles ahead. However, since the speed on the initial speed limit curve may sometimes suddenly increase or decrease, driving according to the initial speed limit curve could lead to frequent sudden braking and unstable vehicle operation. Therefore, filtering of the initial speed limit curve is necessary to better control the smooth driving of the autonomous vehicle.

[0049] In step S12, the target deceleration parameter is obtained. In this embodiment, the target deceleration parameter may include an overshoot deceleration parameter, a deceleration parameter, and an acceleration parameter. In this embodiment, different deceleration parameters can be set for the autonomous vehicle. For example, a corresponding acceleration parameter can be set for the acceleration filter, a corresponding deceleration parameter can be set for the deceleration filter, and a corresponding overshoot deceleration parameter can be set for the overshoot filter. When the current speed of the autonomous vehicle is greater than the speed corresponding to the initial speed limit curve, the overshoot deceleration parameter is used to control the deceleration of the autonomous vehicle. This overshoot deceleration parameter can be determined based on vehicle parameters, which may include the vehicle model or load capacity, etc. This overshoot deceleration parameter represents the maximum deceleration capability of the autonomous vehicle, that is, the maximum deceleration that the autonomous vehicle can achieve during deceleration. For example, it demonstrates braking performance when the autonomous vehicle brakes at its maximum braking capacity according to the brake pedal. In addition, the acceleration parameter mentioned above is determined based on the vehicle's driving ability, that is, the acceleration that can be obtained by controlling the throttle of the autonomous vehicle; the deceleration parameter mentioned above is determined based on the vehicle's braking ability, that is, the deceleration that can be obtained by controlling the brake pedal of the autonomous vehicle, and this deceleration parameter is less than the overshoot deceleration parameter.

[0050] In step S13, it is determined whether the current speed of the autonomous vehicle is greater than the speed corresponding to the initial speed limit curve. If the current speed of the autonomous vehicle is greater than the speed corresponding to the initial speed limit curve, step S18 is executed. The initial speed limit curve can be overshoot-filtered using overshoot deceleration parameters to obtain a first overshoot deceleration filter curve. That is, when the current speed is greater than the speed corresponding to the initial speed limit curve, the autonomous vehicle can be controlled using overshoot deceleration parameters. When the current speed of the autonomous vehicle is greater than the speed corresponding to the initial speed limit curve at the current position, it indicates that the speed of the autonomous vehicle is too high and needs to be reduced quickly. At this time, the initial speed limit curve can be filtered using overshoot deceleration parameters as deceleration to obtain a first overshoot deceleration filter curve, so as to reduce the current speed of the autonomous vehicle to the greatest extent possible until the current speed of the autonomous vehicle is no greater than the speed corresponding to the initial speed limit curve. Then, in step S20, the initial speed limit curve is filtered using deceleration planned from the current speed with input overshoot filter parameters to obtain the overshoot deceleration filter curve.

[0051] If the current speed of the autonomous vehicle is not greater than the speed corresponding to the initial speed limit curve, step S14 is executed to perform deceleration filtering based on the deceleration parameter. In this embodiment, the deceleration filtering is performed by applying the deceleration parameter to the initial speed limit curve to obtain a deceleration filtered curve. In this embodiment, the initial value of the deceleration parameter can be a relatively small value. Then, step S15 is used to determine whether the speed corresponding to the deceleration filtered curve is less than the current speed of the autonomous vehicle. If the speed corresponding to the deceleration filtered curve is less than the current speed of the autonomous vehicle, step S16 is used to determine whether the deceleration parameter is greater than the maximum deceleration parameter of the autonomous vehicle. This maximum deceleration parameter is used as the overshoot deceleration parameter. If the deceleration parameter is greater than the maximum deceleration parameter of the autonomous vehicle, step S19 is executed to perform overshoot deceleration filtering on the first deceleration filtered curve using the overshoot deceleration parameter to obtain a second overshoot deceleration filtered curve. Otherwise, if the deceleration parameter is not greater than the maximum deceleration parameter of the autonomous vehicle, in step S17, the value of the deceleration parameter can be increased by the target step size, and then the initial speed limit curve can be decelerated and filtered in step S14. For example, the target step size is 2 m / s. 2 The initial value of the deceleration parameter is -2 m / s². 2 By increasing the deceleration parameter with a target step size, the improved deceleration parameter can be obtained as -4 m / s². 2 Repeat the above steps until step S15 determines that the speed corresponding to the deceleration filter curve is not less than the current speed of the autonomous vehicle.

[0052] In step S21, the initial speed limit curve is accelerated and filtered using acceleration parameters, and in step S22, the fused filtered curve is output.

[0053] In the embodiment, by continuously increasing the value of the deceleration parameter by the target step size, the vehicle can be decelerated smoothly. This avoids the situation where, when the vehicle is controlled by a fixed deceleration parameter, either the deceleration parameter is too small to effectively control the vehicle's deceleration, or the deceleration parameter is too large, causing the vehicle to brake suddenly, especially when the vehicle's effective braking distance is still large, resulting in unnecessary sudden braking.

[0054] like Figures 4a to 4d As shown, in this embodiment, a small deceleration parameter can be used initially for deceleration filtering. If the deceleration filter fails, the deceleration parameter will be iteratively increased with a target step size until the deceleration filter no longer fails. Figure 4a It can be seen that the deceleration filter fails when using a small deceleration parameter, requiring an increase in the deceleration parameter. From Figure 4b It can be seen that increasing the deceleration parameter by the target step size does not resolve the deceleration filter; therefore, the deceleration parameter needs to be increased again based on the target step size. Figure 4c It can be seen that increasing the deceleration parameters again by the target step size does not resolve the issue; the deceleration filter remains ineffective. Therefore, it is necessary to further increase the deceleration parameters based on the target step size. Figure 4d It can be seen that by further increasing the deceleration parameter, the velocity corresponding to the current position of the deceleration filter curve is made closer to the current velocity, and a suitable deceleration parameter is obtained. The initial filter curve is then decelerated and filtered using this deceleration parameter to obtain the deceleration filter curve.

[0055] In step S21 above, when the initial speed limit curve is accelerated by using acceleration parameters, the vehicle can also be gradually accelerated by using the target step size to achieve smooth control of the vehicle.

[0056] In this embodiment, the current speed of the autonomous vehicle is continuously obtained. The process described above determines whether the current speed is greater than the speed corresponding to the initial speed limit curve. Then, overshoot deceleration filtering, deceleration filtering, or acceleration filtering is performed. In step S22, the obtained deceleration filter curve, initial speed limit curve, and acceleration filter curve can be fused to output a first fused filter curve; or, the obtained first overshoot deceleration filter curve, initial speed limit curve, and acceleration filter curve can be fused to output a second fused filter curve; or, the obtained second overshoot deceleration filter curve, initial speed limit curve, and acceleration filter curve can be fused to output a third fused filter curve. Figure 5 The lower part shows an exemplary fused filter curve. This allows the autonomous vehicle to travel based on the speed corresponding to the fused filter curve, enabling smoother control of the vehicle.

[0057] It should be noted that the above embodiments are merely exemplary embodiments. When performing acceleration filtering, step S21 can be performed before or after deceleration filtering. The embodiments are not limited to this.

[0058] Based on the above embodiments, this disclosure avoids the problem of poor filtering effect caused by using fixed acceleration and deceleration parameters when filtering the initial speed limit curve, as improper setting of deceleration or acceleration parameters can lead to this issue. For example, when using fixed deceleration parameters for filtering, if the deceleration parameter is too small, the first speed of the deceleration filter will be less than the initial speed of the vehicle, and the algorithm may consider that the vehicle will not decelerate to the desired speed even when using deceleration filtering. On the other hand, setting a larger deceleration parameter can reduce the occurrence of deceleration filter failure, but it will challenge the vehicle's maximum deceleration capability, resulting in very abrupt braking in most cases. However, in many cases, a large deceleration is not required, especially when encountering obstacles and braking within a range of 60m-80m after the main radar is equipped. This disclosure can gradually increase the deceleration parameter by the target step size, allowing the vehicle to brake slowly while avoiding accidents, thus improving the stability of vehicle operation.

[0059] In this embodiment, when an obstacle suddenly appears, the vehicle's braking can be controlled using the maximum deceleration parameter to ensure a safe distance. Therefore, in this embodiment, the values ​​of the acceleration or deceleration parameters can be dynamically adjusted based on different scenarios, vehicle states, or user-input speed limits.

[0060] Therefore, based on the above embodiments, in the embodiments provided in this disclosure, the distance between the autonomous vehicle and obstacles ahead can also be detected based on the autonomous vehicle's positioning information or sensors such as onboard radar. If the distance is within the safe range of the obstacle, for example, the safe range can be 60m to 80m, the autonomous vehicle can be decelerated by gradually increasing the deceleration parameter with a target step size, as described above. If the distance is greater than 80m, the autonomous vehicle can be accelerated by gradually increasing the acceleration parameter with a target step size. If the distance is less than 60m, the autonomous vehicle can be braked by overshooting the deceleration parameter to reduce the speed of the autonomous vehicle to the greatest extent. In this way, by dynamically adjusting the values ​​of the acceleration reference or deceleration parameter in different scenarios, the operation of the autonomous vehicle can be controlled more smoothly.

[0061] Based on the above embodiments, in another embodiment provided in this disclosure, such as Figure 6 As shown, a method for determining the speed of an autonomous vehicle is also provided, which may include the following steps:

[0062] In step S410, the initial speed limit curve of the autonomous vehicle and the current speed of the autonomous vehicle at the current location point are obtained.

[0063] In this embodiment, the initial speed limit curve of the autonomous vehicle can be determined based on factors such as speed limit signs on the road, the maximum speed of the vehicle when turning, or the distance to the vehicle in front. The initial speed limit curve can be pre-generated and can be related to factors such as road surface conditions or weather conditions. Each point on the initial speed limit curve represents the speed corresponding to different locations on the path, and the speed can be the maximum speed limit corresponding to the autonomous vehicle.

[0064] In this embodiment, the current speed of the autonomous vehicle at its current location can be acquired in real time, or it can be acquired intermittently, for example, every 100ms. In this embodiment, the interval between acquiring the current speed of the autonomous vehicle can be set as needed. A shorter interval results in smoother vehicle control as described below, but increases the computational load. Therefore, it can be determined based on the current driving environment of the autonomous vehicle; the more complex the driving environment, the shorter the interval can be, and the simpler the driving environment, the longer the interval can be.

[0065] For example, when an autonomous vehicle is traveling on a straight road, if there are few other vehicles or obstacles in the path, the current driving environment can be determined to be relatively simple. If the autonomous vehicle is traveling on a winding road, or if there are many other vehicles on the road, the current driving environment can be determined to be more complex. Therefore, the interval length can be inversely correlated with the complexity of the current driving environment.

[0066] In step S420, the initial speed limit curve is subjected to deceleration filtering processing according to the first deceleration parameter to obtain the first deceleration filtering curve.

[0067] In this embodiment, the initial speed limit curve can be decelerated and filtered using a first deceleration parameter. Specifically, based on the current speed of the autonomous vehicle at its current position, the first deceleration parameter, and the distances between the current position and subsequent positions, the speeds at each subsequent position can be calculated, forming the first deceleration filter curve. This first deceleration parameter can be set as needed; for example, it can be a relatively small deceleration parameter, facilitating continuous adjustment in subsequent steps.

[0068] In this embodiment, if the current speed of the autonomous vehicle at the current position is less than or equal to the speed at the current position in the initial speed limit curve, the initial speed limit curve can be decelerated and filtered according to the first deceleration parameter to obtain the first deceleration filtered curve.

[0069] In step S430, if the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter. Based on the updated deceleration parameter, the initial speed limit curve is decelerated and filtered to obtain the updated deceleration filter curve. The process continues until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, thus obtaining the target deceleration filter curve.

[0070] In this embodiment, if the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, it indicates that the speed corresponding to the first deceleration filter curve obtained by decelerating the initial speed limit curve based on the first deceleration parameter is too small, and the deceleration is not significant enough, requiring further deceleration processing. Therefore, based on the first deceleration parameter, the first deceleration parameter can be adjusted by a target step size to make the value of the adjusted deceleration parameter larger (larger absolute value). By applying the adjusted deceleration parameter to the initial speed limit curve for deceleration filtering, an updated deceleration filter curve can be obtained. The above process can be repeated until the speed at the current position corresponding to the updated deceleration filter curve is not less than the current speed of the autonomous vehicle at the current position. At this point, the adjustment of the deceleration parameter can be stopped, and the updated target deceleration filter curve can be obtained.

[0071] In step S440, the initial speed limit curve is subjected to acceleration filtering to obtain an acceleration filtered curve.

[0072] In this embodiment, the initial speed limit curve can be subjected to acceleration filtering using an acceleration parameter. This acceleration parameter can be determined based on the acceleration capability of the autonomous vehicle. For example, it can be determined based on the power provided by the accelerator pedal from the minimum to the maximum power. For instance, the acceleration parameter can be 0 to a, where a is a positive number, and can be a value between 0 and a as needed. Similarly, the first deceleration parameter can be determined based on the braking capability of the autonomous vehicle. For example, it can be determined based on the braking capability provided by the brake pedal from the minimum to the maximum braking. For instance, the deceleration parameter can be b to 0, where b is a negative number, and can be a value between b and 0 as needed.

[0073] It should be noted that the above process can first perform deceleration filtering on the initial speed limit curve using the first deceleration parameter, and then perform acceleration filtering on the initial speed limit curve; alternatively, it can first perform acceleration filtering on the initial speed limit curve, and then perform deceleration filtering on the initial speed limit curve using the first deceleration parameter. The embodiments are not limited to these.

[0074] Similarly, in the acceleration filtering process of the initial speed limit curve using acceleration parameters, the acceleration parameters can be continuously adjusted based on the target step size. For example, a small acceleration parameter can be set, and the value of the acceleration parameter can be continuously increased by the target step size. The initial speed limit curve can be filtered using the updated acceleration parameter to obtain an updated acceleration filtering curve, until the speed at the current position corresponding to the updated acceleration filtering curve is not less than the current speed of the autonomous vehicle at the current position.

[0075] In step S450, the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve are fused to obtain the first fused filter curve.

[0076] In this embodiment, after obtaining the acceleration filter curve and the target deceleration filter curve in the above manner, the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve can be fused together to obtain a first fused filter curve. For example, the speeds at the same position point on the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve can be obtained, a target speed that meets specified conditions can be determined, and the first fused filter curve can be obtained based on the target speed. Determining the target speed that meets specified conditions can specifically involve obtaining the minimum value among the speeds and using this minimum value as the target speed. In this way, during the process of obtaining the first fused filter curve based on the target speed, the first fused filter curve described above can be formed based on the target speed corresponding to each position point.

[0077] In this embodiment, by acquiring the speeds at the same position point on the initial speed limit curve, acceleration filter curve, and target deceleration filter curve, a target speed meeting certain conditions can be obtained from each speed, and a first fusion filter curve can be obtained based on this target speed. For example, the target speed meeting the conditions can be the minimum speed at the same position point on the initial speed limit curve, acceleration filter curve, and target deceleration filter curve, or it can be the average of the three corresponding speeds, etc. The target speed can be determined as needed, and this embodiment is not limited to this. In this way, by acquiring the speeds corresponding to each position point, a first fusion filter curve containing the speeds corresponding to each position point can be formed.

[0078] In step S460, the autonomous vehicle is controlled to drive according to the first fusion filter curve.

[0079] In this embodiment, based on the first deceleration and acceleration parameters, the values ​​of the corresponding deceleration and acceleration parameters are gradually increased by a target step size. This makes the filter curves obtained by adjusting the acceleration and deceleration parameters smoother, and thus the first fused filter curve obtained by fusing the initial speed limit curve, acceleration filter curve, and target deceleration filter curve in the above manner is even smoother. In this way, when the autonomous vehicle travels at a speed determined based on the smoother first fused filter curve, stable vehicle control can be achieved.

[0080] In this embodiment, when adjusting the first deceleration parameter according to the target step size to obtain the updated deceleration parameter, it is possible to detect whether the first deceleration parameter exceeds a deceleration threshold. If the first deceleration parameter does not exceed the deceleration threshold, the first deceleration parameter is adjusted according to the target step size, thus obtaining the updated deceleration parameter. Furthermore, by detecting whether the first deceleration parameter exceeds the deceleration threshold, if the first deceleration parameter exceeds the deceleration threshold, the adjustment of the deceleration parameter according to the target step size can be stopped, and the deceleration threshold is used as the overshoot deceleration. Overshoot filtering is then applied to the first deceleration filter curve to obtain the first overshoot deceleration filter curve. This allows for the fusion of the initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve to obtain the second fused filter curve. The autonomous vehicle's driving control is then performed based on the second fused filter curve.

[0081] In this embodiment, the deceleration threshold can be the maximum deceleration of the autonomous vehicle, which can be determined by the maximum braking performance of the autonomous vehicle, such as the maximum deceleration obtained by the vehicle when the brake pedal reaches its maximum braking capacity. Specifically, vehicle parameters of the autonomous vehicle can be obtained, and the maximum deceleration of the autonomous vehicle can be determined based on these parameters. For example, the vehicle parameters can be the type of vehicle, the specific model corresponding to that type, etc., and can also include the vehicle's carrying status, such as empty or heavily loaded, etc., by pre-establishing a correspondence between vehicle parameters and maximum deceleration.

[0082] In this embodiment, during the process of fusing the initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve to obtain the second fused filter curve, the speeds at the same position point on the initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve can be obtained. A target speed that meets certain conditions can be obtained from these speeds, and the first fused filter curve can be generated based on this target speed. For example, the target speed can be the minimum speed at the same position point on the initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve, or it can be the average of the three corresponding speeds. The target speed can be determined as needed, and the second fused filter curve can be generated based on this target speed.

[0083] Based on the above embodiments, in the embodiments provided in this disclosure, if the current speed of the autonomous vehicle at its current position is greater than the speed at the corresponding current position in the initial speed limit curve, overshoot filtering can be applied to the initial speed limit curve until the current speed is no greater than the speed at the corresponding position obtained after overshoot filtering, thus obtaining a second overshoot deceleration filter curve. Furthermore, the initial speed limit curve, the acceleration filter curve, and the second overshoot deceleration filter curve can be fused to obtain a third fused filter curve, and the autonomous vehicle can be controlled based on the third fused filter curve.

[0084] In this embodiment, when performing overshoot filtering on the initial speed limit curve, the initial speed limit curve can be overshoot filtered using the maximum deceleration parameter until the current speed is no greater than the speed at the corresponding position point obtained after overshoot filtering, thus obtaining the second overshoot deceleration filter curve. This maximum deceleration parameter can be determined by the maximum braking performance of the autonomous vehicle, for example, the maximum deceleration obtained by the vehicle when the brake pedal reaches its maximum braking capacity.

[0085] When fusing the initial speed-limiting curve, the acceleration filter curve, and the second overshoot deceleration filter curve to obtain the third fused filter curve, the following steps can be taken: Obtain the speeds at corresponding points on the initial speed-limiting curve, the acceleration filter curve, and the second overshoot deceleration filter curve; identify the target speed that meets certain conditions among these speeds; and then use this target speed to generate the third fused filter curve. For example, the target speed could be the minimum speed at the corresponding point on the initial speed-limiting curve, the acceleration filter curve, and the second overshoot deceleration filter curve, or it could be the average of the three corresponding speeds. The target speed can be determined as needed, and the third fused filter curve can be generated based on this target speed.

[0086] In this embodiment, the current speed of the autonomous vehicle can be obtained, and when the current speed is greater than the initial speed limit curve (e.g., ... Figure 3 When the speed corresponds to the speed shown in the figure, the autonomous vehicle's movement can be controlled by the overshoot deceleration parameter. That is, if the current speed of the autonomous vehicle is greater than the speed corresponding to the initial speed limit curve at the current position, it indicates that the vehicle's speed is too high and it needs to be reduced quickly. In this case, the overshoot deceleration parameter can be used as a deceleration filter on the initial speed limit curve, such as... Figure 5As shown in the upper part of the figure, the overshoot deceleration filter curve can be obtained. In this embodiment, the overshoot deceleration parameter can be the aforementioned maximum deceleration parameter. Thus, when the current speed is greater than the speed corresponding to the initial speed limit curve, by obtaining the maximum deceleration parameter of the autonomous vehicle, the speed of the autonomous vehicle during operation can be controlled based on the maximum deceleration parameter. This allows for emergency braking of the vehicle in emergency situations, minimizing the risk of traffic accidents.

[0087] In this embodiment, for example, when an obstacle is detected in front of the autonomous vehicle, if the distance between the autonomous vehicles is still relatively large, such as within a safe distance range, the value of the deceleration parameter can be gradually increased based on the first deceleration parameter and the target step size. This can achieve gradual deceleration of the autonomous vehicle and thus achieve smooth vehicle control. Furthermore, when the adjusted deceleration parameter reaches or exceeds the maximum deceleration parameter of the autonomous vehicle, the speed limit curve can be filtered based on the maximum deceleration parameter to obtain the aforementioned overshoot deceleration filter curve.

[0088] In this embodiment, if no obstacle is detected in front of the autonomous vehicle, or the distance between the obstacle and the autonomous vehicle is large, or the speed of the obstacle in front of the autonomous vehicle is greater than the speed of the autonomous vehicle, and the current speed of the autonomous vehicle is low, the value of the acceleration parameter can be gradually increased by the target step size. This avoids traffic accidents caused by the sudden appearance of obstacles or other emergencies in front of the vehicle when the speed of the autonomous vehicle is planned by directly using a large acceleration parameter.

[0089] By dividing each function into corresponding functional modules, this disclosure provides an autonomous vehicle control device, which can be a server or a chip applied to a server. Figure 7 A schematic block diagram of the functional modules of an autonomous vehicle control device provided for an exemplary embodiment of this disclosure. (See diagram below.) Figure 7 As shown, the autonomous vehicle control device includes:

[0090] The acquisition module 10 is used to acquire the initial speed limit curve of the unmanned vehicle and the current speed of the unmanned vehicle at the current position point;

[0091] The first deceleration filter curve acquisition module 20 is used to perform deceleration filtering on the initial speed limit curve according to the first deceleration parameter to obtain the first deceleration filter curve.

[0092] The target deceleration filter curve acquisition module 30 is used to adjust the first deceleration parameter according to the target step size when the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, to obtain the updated deceleration parameter, and to perform deceleration filtering processing on the initial speed limit curve based on the updated deceleration parameter to obtain the updated deceleration filter curve, until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, to obtain the target deceleration filter curve.

[0093] The acceleration filtering processing module 40 is used to perform acceleration filtering processing on the initial speed limit curve to obtain an acceleration filtering curve.

[0094] The first fusion processing module 50 is used to fuse the initial speed limit curve, the acceleration filter curve and the target deceleration filter curve to obtain the first fused filter curve.

[0095] The control module 60 is used to control the driving of the unmanned vehicle based on the first fusion filter curve.

[0096] In another embodiment provided in this disclosure, the target deceleration filter curve acquisition module is further configured to:

[0097] Detect whether the first deceleration parameter exceeds the deceleration threshold;

[0098] If the first deceleration parameter does not exceed the deceleration threshold, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter.

[0099] In another embodiment provided in this disclosure, the method further includes a first processing module, which is specifically used for:

[0100] Detect whether the first deceleration parameter exceeds the deceleration threshold;

[0101] If the first deceleration parameter exceeds the deceleration threshold, stop adjusting the deceleration parameter according to the target step size, and use the deceleration threshold as the overshoot deceleration. Perform overshoot filtering on the first deceleration filter curve to obtain the first overshoot deceleration filter curve.

[0102] The initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve are fused together to obtain a second fused filter curve.

[0103] The autonomous vehicle is controlled to drive based on the second fusion filter curve.

[0104] In another embodiment provided in this disclosure, the target deceleration filter curve acquisition module is further configured to:

[0105] If the current speed is less than or equal to the speed at the current position point in the initial speed limit curve, the initial speed limit curve is subjected to deceleration filtering according to the first deceleration parameter to obtain the first deceleration filtered curve.

[0106] In another embodiment provided in this disclosure, the method further includes a second processing module, which is specifically used for:

[0107] If the current speed is greater than the speed at the corresponding current position point in the initial speed limit curve, the initial speed limit curve is subjected to overshoot filtering until the current speed is not greater than the speed at the corresponding position point obtained after overshoot filtering, thus obtaining the second overshoot deceleration filter curve.

[0108] The initial speed limiting curve, the acceleration filter curve, and the second overshoot deceleration filter curve are fused together to obtain a third fused filter curve.

[0109] The autonomous vehicle is controlled based on the third fusion filter curve.

[0110] In another embodiment provided in this disclosure, the first fusion processing module is further configured to:

[0111] Obtain the speeds at the same location point on the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve;

[0112] Determine the target speed that meets the specified conditions among the various speeds;

[0113] The fusion filter curve is obtained based on the target velocity.

[0114] In another embodiment provided in this disclosure, the first fusion processing module is further configured to:

[0115] The minimum value among all speeds is obtained as the target speed;

[0116] The fusion filter curve is formed based on the target velocity corresponding to each location point.

[0117] Since the device embodiment is different from the method embodiment described above, please refer to the description of the method embodiment above for details, and it will not be repeated here.

[0118] The autonomous vehicle control device provided in this embodiment adjusts the deceleration parameters step by step based on a first deceleration parameter, making the target filtered curve obtained by filtering the initial speed limit curve with the adjusted deceleration parameter smoother. Furthermore, the first fused filtered curve obtained by fusing the initial speed limit curve, the acceleration filtered curve, and the target deceleration filtered curve becomes even smoother. Thus, when the autonomous vehicle travels at the speed corresponding to the first fused filtered curve, stable vehicle control can be achieved.

[0119] This disclosure also provides an electronic device, including: at least one processor; a memory for storing processor-executable instructions; wherein the at least one processor is configured to execute the instructions to implement the methods disclosed in this disclosure.

[0120] Figure 8 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this disclosure. For example... Figure 8 As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801. The processor 1801 can perform the corresponding steps in the methods disclosed in the embodiments of this disclosure.

[0121] The processor 1801 described above can also be called a central processing unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method disclosed in this embodiment can be implemented by the integrated logic circuitry in the processor 1801 or by software instructions. The processor 1801 can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this embodiment can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 1802, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 1801 reads information from the memory 1802 and, in conjunction with its hardware, completes the steps of the method described above.

[0122] Furthermore, various operations / processes according to this disclosure, implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, such as... Figure 9 The computer system 1900 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including those described above. Figure 9 A block diagram of a computer system provided for an exemplary embodiment of this disclosure.

[0123] Computer System 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0124] like Figure 9 As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 into a random access memory (RAM) 1903. The RAM 1903 may also store various programs and data required for the operation of the computer system 1900. The computing unit 1901, ROM 1902, and RAM 1903 are interconnected via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0125] Multiple components in computer system 1900 are connected to I / O interface 1905, including: input unit 1906, output unit 1907, storage unit 1908, and communication unit 1909. Input unit 1906 can be any type of device capable of inputting information into computer system 1900. Input unit 1906 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. Output unit 1907 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1908 may include, but is not limited to, hard disks and optical disks. Communication unit 1909 allows computer system 1900 to exchange information / data with other devices via a network such as the Internet, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0126] The computing unit 1901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the methods disclosed in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1900 via ROM 1902 and / or communication unit 1909. In some embodiments, the computing unit 1901 can be configured to perform the methods disclosed in this disclosure by any other suitable means (e.g., by means of firmware).

[0127] This disclosure also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the methods disclosed in this disclosure.

[0128] The computer-readable storage medium in this disclosure can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The aforementioned computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the aforementioned computer-readable storage medium may include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0129] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0130] This disclosure also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the methods disclosed in the embodiments of this disclosure.

[0131] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer.

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0133] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0134] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0135] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0136] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for controlling an unmanned vehicle, characterized in that, The method includes: Obtain the initial speed limit curve of the autonomous vehicle and the current speed of the autonomous vehicle at the current location point; The initial speed limit curve is subjected to deceleration filtering processing according to the first deceleration parameter to obtain the first deceleration filtered curve. If the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter. Based on the updated deceleration parameter, the initial speed limit curve is decelerated and filtered to obtain the updated deceleration filter curve. The process continues until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, and the target deceleration filter curve is obtained. The initial speed limit curve is subjected to acceleration filtering to obtain an acceleration filtered curve; The initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve are fused together to obtain a first fused filter curve. The autonomous vehicle is controlled to drive based on the first fusion filter curve.

2. The method according to claim 1, characterized in that, The step of adjusting the first deceleration parameter according to the target step size to obtain the updated deceleration parameter includes: Detect whether the first deceleration parameter exceeds the deceleration threshold; If the first deceleration parameter does not exceed the deceleration threshold, the first deceleration parameter is adjusted according to the target step size to obtain the updated deceleration parameter.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Detect whether the first deceleration parameter exceeds the deceleration threshold; If the first deceleration parameter exceeds the deceleration threshold, stop adjusting the deceleration parameter according to the target step size, and use the deceleration threshold as the overshoot deceleration. Perform overshoot filtering on the first deceleration filter curve to obtain the first overshoot deceleration filter curve. The initial speed limit curve, the acceleration filter curve, and the first overshoot deceleration filter curve are fused together to obtain a second fused filter curve. The autonomous vehicle is controlled to drive based on the second fusion filter curve.

4. The method according to claim 1, characterized in that, The step of performing deceleration filtering on the initial speed limit curve according to the first deceleration parameter to obtain the first deceleration filtered curve includes: If the current speed is less than or equal to the speed at the current position point in the initial speed limit curve, the initial speed limit curve is subjected to deceleration filtering according to the first deceleration parameter to obtain the first deceleration filtered curve.

5. The method according to claim 1 or 4, characterized in that, The method further includes: If the current speed is greater than the speed at the corresponding current position point in the initial speed limit curve, the initial speed limit curve is subjected to overshoot filtering until the current speed is not greater than the speed at the corresponding position point obtained after overshoot filtering, thus obtaining the second overshoot deceleration filter curve. The initial speed limit curve, the acceleration filter curve, and the second overshoot deceleration filter curve are fused together to obtain a third fused filter curve. The autonomous vehicle is controlled based on the third fusion filter curve.

6. The method according to claim 1, characterized in that, The process of fusing the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve to obtain the first fused filter curve includes: Obtain the speeds at the same position point on the initial speed limit curve, the acceleration filter curve, and the target deceleration filter curve; Determine the target speed that meets the specified conditions among the various speeds; The fusion filter curve is obtained based on the target velocity.

7. The method according to claim 6, characterized in that, The determination of the target speed that meets the specified conditions among the various speeds includes: The minimum value among all speeds is obtained as the target speed; The step of obtaining the fusion filter curve based on the target velocity includes: The fusion filter curve is formed based on the target velocity corresponding to each location point.

8. A control device for an unmanned vehicle, characterized in that, The device includes: The acquisition module is used to acquire the initial speed limit curve of the autonomous vehicle and the current speed of the autonomous vehicle at the current location point; The first deceleration filter curve acquisition module is used to perform deceleration filtering on the initial speed limit curve according to the first deceleration parameter to obtain the first deceleration filter curve. The target deceleration filter curve acquisition module is used to adjust the first deceleration parameter according to the target step size when the speed at the current position corresponding to the first deceleration filter curve is less than the current speed, to obtain the updated deceleration parameter, and to perform deceleration filtering processing on the initial speed limit curve based on the updated deceleration parameter to obtain the updated deceleration filter curve, until the speed at the current position corresponding to the updated deceleration filter curve is greater than or equal to the current speed, to obtain the target deceleration filter curve. An acceleration filtering processing module is used to perform acceleration filtering processing on the initial speed limit curve to obtain an acceleration filtered curve. The first fusion processing module is used to fuse the initial speed limit curve, the acceleration filter curve and the target deceleration filter curve to obtain the first fused filter curve. The control module is used to control the driving of the autonomous vehicle based on the first fused filtering curve.

9. An electronic device, characterized in that, include: At least one processor; Memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-7.

Images