Control method and device of autonomous vehicle

Abstract

The application discloses a kind of control method and device of automatic driving vehicle.Therein, the method includes: determining the collision time required when automatic driving vehicle travels in current motion state to collide with obstacle;According to the actual steering wheel angle of steering wheel and the maximum steering ability parameter, the steering wheel angle proportion is determined;According to the current actual position of automatic driving vehicle and planning path, the lateral control deviation of automatic driving vehicle is determined;According to collision time, steering wheel angle proportion and lateral control deviation, the total risk value of vehicle is determined;According to total risk value, the target speed limit value of vehicle is calculated by linear interpolation method;The current driving speed of vehicle is constrained using target speed limit value, to control automatic driving vehicle.The present application solves the technical problem that in the related art, in the automatic driving system, planning and control module may have errors in some limited scenarios, so that the actual driving trajectory of the vehicle may deviate from the planned trajectory, which may lead to collision.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and more specifically, to a control method and apparatus for an autonomous vehicle. Background Technology

[0002] In autonomous driving systems, the planning and control modules often have errors, especially in restricted scenarios such as turning and U-turns, where the actual driving trajectory of the vehicle may deviate from the planned trajectory.

[0003] Specifically, factors such as steering wheel speed limitations, vehicle weight variations (e.g., weight fluctuations in the cargo box), and calculation errors in the control algorithm can cause the control module to fail to fully execute the instructions of the planning module, resulting in lateral control errors. In this case, the vehicle's front may deviate from the planned trajectory, meaning that the vehicle may have turned the corner from the planned perspective, but the actual front of the vehicle may still be facing obstacles such as bollards or guardrails.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a control method and apparatus for autonomous vehicles, which at least solves the technical problem in related technologies where the planning and control modules in autonomous driving systems are prone to errors in some limited scenarios, causing the actual driving trajectory of the vehicle to deviate from the planned trajectory, which can easily lead to collisions.

[0006] According to one aspect of the present invention, a control method for an autonomous vehicle is provided, comprising: determining the collision time required for the autonomous vehicle to travel in its current motion state until it collides with an obstacle; determining the steering wheel angle percentage of the steering wheel based on the actual steering wheel angle of the autonomous vehicle and the maximum steering capability parameter of the steering wheel; determining the lateral control deviation of the autonomous vehicle based on the current actual position of the autonomous vehicle and the planned path; determining the total risk value of the autonomous vehicle based on the collision time, the steering wheel angle percentage, and the lateral control deviation; calculating a target speed limit value of the autonomous vehicle using linear interpolation based on the total risk value; and using the target speed limit value to constrain the current driving speed of the autonomous vehicle to control the autonomous vehicle.

[0007] Optionally, determining the collision time required for the autonomous vehicle to collide with the obstacle while in its current state of motion includes: acquiring the current driving speed, estimated acceleration, and obstacle distance of the autonomous vehicle along the planned path direction; generating a distance-time relationship curve of the autonomous vehicle along the planned path based on the current driving speed and the estimated acceleration, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and the estimated acceleration as parameters; and determining the collision time required for the autonomous vehicle to collide with the obstacle while in its current state of motion based on the obstacle distance and the distance-time relationship curve.

[0008] Optionally, determining the steering wheel angle percentage based on the actual steering wheel angle of the autonomous vehicle and the maximum steering capability parameter of the steering wheel includes: performing a division operation on the actual steering wheel angle and the maximum steering capability parameter to obtain the division result; and determining the division result as the steering wheel angle percentage.

[0009] Optionally, determining the lateral control deviation of the autonomous vehicle based on its current actual position and the planned path includes: determining the heading of the autonomous vehicle based on its current actual position; and calculating the shortest Euclidean distance from the centerline of the autonomous vehicle's front end to the planned path along a direction perpendicular to the heading, using the centerline of the autonomous vehicle's front end as a reference point, to obtain the lateral control deviation.

[0010] Optionally, determining the total risk value of the autonomous vehicle based on the collision time, the steering wheel angle percentage, and the lateral control deviation includes: determining the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and each lateral control deviation level threshold; determining a risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold; determining a lateral error weight value based on the level identifier corresponding to the lateral control deviation level; obtaining the theoretical turning time of the autonomous vehicle; and calculating the total risk value based on the product of the collision time and the collision risk weight factor, the product of the steering wheel angle percentage and the risk weight value, the product of the theoretical turning time and the turning risk weight factor, and the product of the lateral control deviation and the lateral error weight value.

[0011] Optionally, the lateral control deviation level thresholds include: a first threshold and a second threshold, wherein the first threshold is less than the second threshold. Determining the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and each lateral control deviation level threshold includes: determining the lateral control deviation level as a low error level when the lateral control deviation is less than the first threshold; determining the lateral control deviation level as a medium error level when the lateral control deviation is not less than the first threshold and less than the second threshold; and determining the lateral control deviation level as a high error level when the lateral control deviation is not less than the second threshold.

[0012] Optionally, obtaining the theoretical turning time of the autonomous vehicle includes: obtaining the planned heading angle of the autonomous vehicle based on the planned path, and determining the current actual heading of the autonomous vehicle based on the current actual position; calculating the heading deviation of the autonomous vehicle based on the planned heading angle and the current actual heading; and performing a division operation between the maximum steering wheel turning rate of the autonomous vehicle and the heading deviation to obtain the theoretical turning time.

[0013] Optionally, the risk threshold includes: a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. Determining a risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold includes: determining the risk weight value as a first risk weight value when the steering wheel angle percentage is less than the first risk threshold; determining the risk weight value as a second risk weight value when the steering wheel angle percentage is not less than the first risk threshold and the steering wheel angle percentage is less than the second risk threshold, wherein the first risk weight value is less than the second risk weight value; and determining the risk weight value as a third risk weight value when the steering wheel angle percentage is not less than the second risk threshold, wherein the second risk weight value is less than the third risk weight value.

[0014] Optionally, the target speed limit of the autonomous vehicle is calculated by linear interpolation based on the total risk value, including: obtaining the minimum risk value and the maximum risk value of the autonomous vehicle in the current motion state; obtaining the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in the current motion state; determining a first risk difference between the maximum risk value and the total risk value, and determining a second risk difference between the total risk value and the minimum risk value; and summing the product of the ratio between the first risk difference and the second risk difference and the speed limit difference with the minimum speed limit as the target speed limit value.

[0015] According to another aspect of the present invention, a control device for an autonomous vehicle is also provided, comprising: a first determining unit, configured to determine the collision time required for the autonomous vehicle to travel in its current motion state to collide with an obstacle; a second determining unit, configured to determine the steering wheel angle percentage of the steering wheel based on the actual steering wheel angle of the steering wheel and the maximum steering capability parameter of the steering wheel; a third determining unit, configured to determine the lateral control deviation of the autonomous vehicle based on the current actual position of the autonomous vehicle and the planned path; a fourth determining unit, configured to determine the total risk value of the autonomous vehicle based on the collision time, the steering wheel angle percentage, and the lateral control deviation; a calculation unit, configured to calculate a target speed limit value of the autonomous vehicle using linear interpolation based on the total risk value; and a constraint unit, configured to constrain the current driving speed of the autonomous vehicle using the target speed limit value to control the autonomous vehicle.

[0016] Optionally, the first determining unit includes: a first acquiring module, configured to acquire the current driving speed, estimated acceleration, and obstacle distance of the autonomous vehicle along the planned path direction to the obstacle; a generating module, configured to generate a distance-time relationship curve of the autonomous vehicle along the planned path based on the current driving speed and the estimated acceleration, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and the estimated acceleration as parameters; and a first determining module, configured to determine the collision time required for the autonomous vehicle to travel in the current motion state to collide with the obstacle based on the obstacle distance and the distance-time relationship curve.

[0017] Optionally, the second determining unit includes: a first calculation module, used to perform a division operation on the actual steering wheel angle and the maximum steering capability parameter to obtain the division result; and a second determining module, used to determine the division result as the steering wheel angle percentage.

[0018] Optionally, the third determining unit includes: a third determining module, used to determine the heading of the autonomous vehicle based on the current actual position; and a second calculation module, used to calculate the shortest Euclidean distance from the reference point to the planned path along a direction perpendicular to the heading, with the center line of the autonomous vehicle's front as the reference point, so as to obtain the lateral control deviation.

[0019] Optionally, the fourth determining unit includes: a fourth determining module, used to determine the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and each lateral control deviation level threshold; a fifth determining module, used to determine a risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold; a sixth determining module, used to determine a lateral error weight value based on the level identifier corresponding to the lateral control deviation level; a second obtaining module, used to obtain the theoretical turning time of the autonomous vehicle; and a third calculating module, used to calculate the total risk value based on the product of the collision time and the collision risk weight factor, the product of the steering wheel angle percentage and the risk weight value, the product of the theoretical turning time and the turning risk weight factor, and the product of the lateral control deviation and the lateral error weight value.

[0020] Optionally, the lateral control deviation level threshold includes: a first threshold and a second threshold, wherein the first threshold is less than the second threshold, and the fourth determining module includes: a first determining submodule, configured to determine the lateral control deviation level as a low error level when the lateral control deviation is less than the first threshold; a second determining submodule, configured to determine the lateral control deviation level as a medium error level when the lateral control deviation is not less than the first threshold and less than the second threshold; and a third determining submodule, configured to determine the lateral control deviation level as a high error level when the lateral control deviation is not less than the second threshold.

[0021] Optionally, the second acquisition module includes: a fourth determining submodule, used to obtain the planned heading angle of the autonomous vehicle according to the planned path, and to determine the current actual heading of the autonomous vehicle according to the current actual position; a first calculation submodule, used to calculate the heading deviation of the autonomous vehicle according to the planned heading angle and the current actual heading; and a second calculation submodule, used to perform a division operation on the maximum steering wheel turning rate of the autonomous vehicle and the heading deviation to obtain the theoretical turning time.

[0022] Optionally, the risk threshold includes: a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold, and the fifth determining module includes: a fifth determining submodule, configured to determine the risk weight value as a first risk weight value when the steering wheel angle percentage is less than the first risk threshold; a sixth determining submodule, configured to determine the risk weight value as a second risk weight value when the steering wheel angle percentage is not less than the first risk threshold and the steering wheel angle percentage is less than the second risk threshold, wherein the first risk weight value is less than the second risk weight value; and a seventh determining submodule, configured to determine the risk weight value as a third risk weight value when the steering wheel angle percentage is not less than the second risk threshold, wherein the second risk weight value is less than the third risk weight value.

[0023] Optionally, the calculation unit includes: a third acquisition module, configured to acquire the minimum risk value and the maximum risk value of the autonomous vehicle in the current motion state; a fourth acquisition module, configured to acquire the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in the current motion state; a seventh determination module, configured to determine a first risk difference between the maximum risk value and the total risk value, and determine a second risk difference between the total risk value and the minimum risk value; and a fourth calculation module, configured to sum the product of the ratio between the first risk difference and the second risk difference and the speed limit difference with the minimum speed limit as the target speed limit value.

[0024] According to another aspect of the present invention, an autonomous driving vehicle is also provided, which uses the control method for an autonomous driving vehicle described in any one of the above embodiments.

[0025] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method for an autonomous vehicle described in any of the preceding embodiments.

[0026] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes the control method for an autonomous vehicle as described in any of the preceding embodiments.

[0027] According to another aspect of the present invention, a computer program product is also provided, including computer instructions that, when executed by a processor, perform the control method for an autonomous vehicle as described above.

[0028] By applying the above-mentioned technical solution of this application, the collision time required for an autonomous vehicle to collide with an obstacle while in its current motion state is determined; the steering wheel angle percentage is determined based on the actual steering wheel angle and maximum steering capability parameters; the lateral control deviation of the autonomous vehicle is determined based on its current actual position and planned path; the total risk value of the vehicle is determined based on the collision time, steering wheel angle percentage, and lateral control deviation; the target speed limit of the vehicle is calculated using linear interpolation based on the total risk value; and the target speed limit is used to constrain the current driving speed of the vehicle to control the autonomous vehicle. This achieves the following: by real-time monitoring of key parameters such as lateral control error, steering wheel angle percentage, planned heading angle deviation, steering time, and collision time, different risk weights are assigned to each parameter and integrated into a comprehensive risk cost. Furthermore, the vehicle speed limit is dynamically generated through a linear interpolation model, achieving closed-loop safety control where "the larger the error, the higher the risk, and the lower the speed." This solves the technical problem in related technologies where the planning and control modules in autonomous driving systems are prone to errors in some restricted scenarios, causing deviations between the actual driving trajectory and the planned trajectory, which can easily lead to collisions. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0030] Figure 1 This is a hardware structure block diagram of a mobile terminal for a control method of an autonomous vehicle according to an embodiment of the present invention.

[0031] Figure 2 This is a flowchart of a control method for an autonomous vehicle according to an embodiment of the present invention;

[0032] Figure 3 This is a schematic diagram of a control device for a self-driving vehicle according to an embodiment of the present invention.

[0033] The above figures include the following reference numerals:

[0034] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] As described in the background section, in related technologies, the planning and control modules in autonomous driving systems are prone to errors in certain constrained scenarios, which may cause deviations between the actual driving trajectory and the planned trajectory, potentially leading to collisions. Embodiments of this invention provide a control method and apparatus for an autonomous vehicle, an autonomous vehicle, a computer-readable storage medium, a processor, and a computer program product.

[0038] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0039] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a control method of an autonomous vehicle according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the control method for an autonomous vehicle in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] Example 1

[0042] According to an embodiment of the present invention, a method embodiment for controlling an autonomous vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] Figure 2 This is a flowchart of a control method for an autonomous vehicle according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0044] Step S202: Determine the collision time required for the autonomous vehicle to travel in its current motion state until it collides with the obstacle.

[0045] In this embodiment, based on the vehicle's current speed, estimated acceleration, and measured distance to obstacles ahead (such as bollards or guardrails), a uniform acceleration motion model calculates how long it will take for the vehicle to come into contact with the obstacle without any deceleration or avoidance measures. This collision time is a key indicator for measuring the degree of danger of the current driving state; the shorter the time, the higher the collision risk, providing a quantitative basis for subsequent speed limit decisions.

[0046] This method uses the current speed and estimated acceleration of the autonomous vehicle, combined with the actual distance between it and obstacles in front (such as stone blocks or guardrails), to calculate the time required for the vehicle to reach the collision point along the current trajectory without any intervention using a uniform acceleration motion model. This time is called the "collision time," which is a quantitative expression of the potential collision risk and reflects the remaining reaction window of the system in the current state before the danger occurs.

[0047] By implementing this control method and calculating the collision time in real time, the system can identify high-risk situations in advance. When the collision time is too short, it indicates that the vehicle is about to lose control and approach the obstacle at the current speed, thereby triggering the subsequent speed limiting mechanism. This provides accurate and timely decision-making basis for dynamic deceleration, effectively avoiding sudden collisions caused by control lag or trajectory deviation, and significantly improving the vehicle's active safety capabilities in narrow turns or areas with dense obstacles.

[0048] Step S204: Determine the steering wheel angle ratio based on the actual steering wheel angle and the maximum steering capability parameters of the steering wheel of the autonomous vehicle.

[0049] In this embodiment, the actual steering wheel angle is divided by the maximum steering angle allowed by the vehicle's design, resulting in a ratio between 0 and 1. This ratio characterizes whether the current steering operation is approaching the vehicle's physical limits. A higher ratio indicates that the vehicle is steering close to its limits, and the control module may have difficulty accurately tracking the planned trajectory, thus increasing the risk of lateral deviation. This parameter is used to assess the degree of control capability saturation during the steering process.

[0050] This method obtains the current actual steering angle of the steering wheel of the autonomous vehicle in real time and calculates the ratio with the maximum steering angle allowed by the vehicle design (i.e., the maximum steering capability parameter) to obtain a dimensionless steering wheel angle ratio. This ratio reflects the degree of use of the current steering operation relative to the vehicle's physical limits. The higher the ratio, the closer the steering system is to its maximum response capability, the smaller the execution margin of the control command, and the more likely it is to cause trajectory tracking deviation due to steering lag or transmission inertia.

[0051] By implementing this control method and quantifying the intensity of steering wheel use, the system can identify when the vehicle is in a high-difficulty steering condition (such as a sharp turn or U-turn). Even if the planned trajectory is reasonable, the control module may not be able to execute accurately due to steering capacity saturation. This provides an early warning of the risk of expanding control error and offers key steering capacity status information for subsequent comprehensive risk assessment, enhancing the system's ability to perceive and respond to steering limit scenarios.

[0052] Step S206: Determine the lateral control deviation of the autonomous vehicle based on its current actual position and the planned path.

[0053] In this embodiment, the absolute value of the distance from the center point of the vehicle's front to the normal direction of the planned trajectory is calculated, reflecting the degree of deviation between the actual trajectory executed by the control module and the planned instructions. This deviation is caused by steering response lag, load changes, or control algorithm errors. The larger the deviation, the further the vehicle deviates from the safe path, making it a key physical quantity for determining whether the vehicle is on the verge of losing control.

[0054] This method obtains the actual position of the center point of the front of the autonomous vehicle in the map coordinate system in real time and compares it with the expected trajectory generated by the planning module. The shortest vertical distance from the point to the planned path is calculated. This distance is the lateral control deviation. Its magnitude reflects the degree of deviation between the actual trajectory executed by the control module and the ideal planned trajectory. This deviation is affected by factors such as steering response delay, load change, road friction or control algorithm accuracy.

[0055] By implementing this control method, the system can objectively assess whether the vehicle has deviated from the safe driving lane in turning or restricted scenarios. When the deviation exceeds the threshold, it indicates that there is a significant lag or error accumulation in the control execution, which in turn triggers the risk weighting mechanism, prompting the system to reduce the vehicle speed to extend the correction time. This effectively prevents the risk of scraping or running over caused by trajectory deviation, and improves the trajectory tracking reliability and operational safety of the autonomous driving system in complex port environments.

[0056] Step S208: Determine the total risk value of the autonomous vehicle based on the collision time, steering wheel angle percentage, and lateral control deviation.

[0057] In this embodiment, the three risk factors mentioned above are assigned different weights and then summed in a weighted manner to form a single value that comprehensively assesses the current safety status of the vehicle. Among them, the collision time reflects the degree of urgency, the steering wheel angle percentage reflects the steering capability limit pressure, and the lateral control deviation reflects the trajectory tracking accuracy. The three factors together reflect the overall risk level caused by the superposition of control errors.

[0058] In this method, the three risk indicators—the collision time calculated in step S202, the steering wheel angle percentage obtained in step S204, and the lateral control deviation obtained in step S206—are multiplied by their corresponding empirical weights and then weighted and summed to form a total risk value that comprehensively reflects the current safety status of the vehicle. The shorter the collision time, the higher the steering wheel angle percentage, and the greater the lateral deviation, the greater their contribution to the total risk value. This process quantifies multi-dimensional dynamic risk factors into a single value, which facilitates rapid decision-making by the system.

[0059] By implementing this control method, the system can comprehensively assess the overall safety status of autonomous vehicles under complex operating conditions, avoid misjudgment based on a single indicator, and ensure that speed limit adjustments not only respond to emergency collision threats but also take into account the limits of control execution capabilities. This results in more accurate and robust risk warnings and provides a scientific and reliable input basis for the reasonable calculation of subsequent target speed limits.

[0060] Step S210: Calculate the target speed limit for the autonomous vehicle using linear interpolation based on the total risk value.

[0061] In this embodiment, the total risk value is mapped to a preset minimum and maximum speed limit range, and a target speed value between the two is dynamically output based on a linear relationship. This method ensures that the higher the risk, the lower the speed limit, thereby providing a buffer time and safety margin for control errors through smooth speed reduction without interrupting the task, and avoiding system jitter caused by sudden speed limits.

[0062] In this method, the total risk value calculated in step S208 is mapped to a preset range between the minimum and maximum risk costs. Based on a linear relationship, proportional interpolation is performed between the minimum and maximum speed limits of the vehicle to obtain a continuous and smooth target speed limit. This process does not use a step-by-step transition, but rather makes the speed limit gradually decrease as the risk increases, ensuring that the speed adjustment is consistent with the risk change.

[0063] By implementing this control method, dynamic and continuous adjustment of speed limits is achieved through linear interpolation. This allows vehicles to automatically reduce speed to increase safety margins during high-risk situations and maintain reasonable efficiency during low-risk situations. It not only ensures collision avoidance capabilities when steering limits or trajectory deviations are large, but also avoids operational efficiency losses caused by excessive speed limits. This achieves a balance between safety and operational smoothness, and enhances the system's adaptive control capabilities in complex port scenarios.

[0064] Step S212: Use the target speed limit value to constrain the current driving speed of the autonomous vehicle in order to control the autonomous vehicle.

[0065] In this embodiment, the target speed limit value calculated in the previous step is used as the upper limit command of the speed control module, forcing the actual vehicle speed not to exceed the value, thereby proactively mitigating risks by limiting kinetic energy without changing the path planning.

[0066] In this method, the target speed limit value calculated in step S210 is used as the maximum permissible speed command and input to the vehicle's underlying controller (such as a longitudinal PID or model predictive control module) to forcibly constrain the vehicle's current acceleration and deceleration behavior so that its actual speed does not exceed the speed limit threshold. This process does not change the planned path, but only reduces the kinetic energy and braking demand through longitudinal speed adjustment, providing a more sufficient response time window for lateral control.

[0067] By implementing this control method, the system can dynamically reduce the collision risk level without interrupting autonomous operations, significantly improving the controllability and stability of vehicles in high-risk conditions such as turning and U-turns. This mechanism can achieve "soft safety protection" without relying on path replanning or emergency braking, ensuring the continuity of port operations and effectively preventing collision accidents caused by control delays or execution deviations.

[0068] As described above, in this embodiment, the collision time required for the autonomous vehicle to collide with an obstacle while in its current motion state is determined; the steering wheel angle percentage is determined based on the actual steering wheel angle and the maximum steering capability parameters of the autonomous vehicle's steering wheel; the lateral control deviation of the autonomous vehicle is determined based on its current actual position and planned path; the total risk value of the autonomous vehicle is determined based on the collision time, steering wheel angle percentage, and lateral control deviation; the target speed limit is calculated for the autonomous vehicle using linear interpolation based on the total risk value; and the current speed of the autonomous vehicle is constrained by the target speed limit to control the autonomous vehicle. Through the above technical solution, the goal of dynamically adjusting the vehicle speed limit by real-time monitoring of lateral error, steering wheel angle percentage, planned heading deviation, and collision time, and weighted and fused into a risk cost, is achieved. This significantly reduces the collision probability of autonomous vehicles in restricted scenarios such as turning and U-turns in ports, and improves the safety and stability of the system in high-precision operating environments.

[0069] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problem in the related art that the planning and control module in an autonomous driving system is prone to errors in some limited scenarios, which may cause the actual driving trajectory of the vehicle to deviate from the planned trajectory and easily lead to collisions.

[0070] It should be noted that the technical solutions provided in the embodiments of the present invention can be applied to port areas. For example, in a port, an autonomous vehicle can use the control method for an autonomous vehicle provided in the embodiments of the present invention during a turn. Of course, this method can also be applied to other scenarios, which will not be elaborated here.

[0071] According to the above embodiments of the present invention, determining the collision time required for an autonomous vehicle to collide with an obstacle while in its current state of motion includes: acquiring the current driving speed, estimated acceleration, and obstacle distance of the autonomous vehicle along the planned path direction; generating a distance-time relationship curve of the autonomous vehicle along the planned path based on the current driving speed and estimated acceleration, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and estimated acceleration as parameters; and determining the collision time required for the autonomous vehicle to collide with the obstacle while in its current state of motion based on the obstacle distance and the distance-time relationship curve.

[0072] In this embodiment, the vehicle's current speed is taken into account. and predicted acceleration ( ) Calculate a reasonable And the vehicle's current actual position and the distance to obstacles in front (such as bollards or guardrails). The collision time is calculated using the formula: .

[0073] Optionally, It is a function based on a uniform acceleration model, used to calculate the distance the vehicle travels from its current state. The time. This function assumes the vehicle is moving at a constant speed or with uniform acceleration, and the formula is: in The initial velocity, For acceleration, This is the target distance. The function outputs the time required to reach that distance. (Collision time).

[0074] Optionally, It is the kinematic model output by the planning module, which is actually based on... The initial velocity is... The curve represents uniformly accelerated motion with acceleration, and the horizontal axis represents time. The vertical axis represents the distance moved along the path. .

[0075] This method is based on the uniformly accelerated motion model in vehicle dynamics. By acquiring the current driving speed of the autonomous vehicle and the estimated acceleration output by the planning module in real time, a function curve describing the displacement of the vehicle along the planned path changes with time is constructed. Combined with the longitudinal distance from the center of the vehicle's front to the obstacle in front, the function is solved in reverse to accurately calculate the time required for the vehicle to reach the obstacle position in its current motion state without taking any avoidance measures—that is, the collision time. This transforms spatial distance risk into a quantifiable and comparable time-dimensional safety indicator.

[0076] By implementing this control method, the system can assess the urgency of collisions at different vehicle speeds and accelerations using a unified and continuous time-domain standard, avoiding the lag and bias of relying solely on static distance judgments. This method significantly improves the real-time performance and accuracy of risk perception, providing a scientific and calculable input basis for subsequent dynamic speed limit strategies. It enables vehicles to reduce speed in advance and smoothly in high-risk scenarios such as turning and U-turns, effectively reducing the probability of collisions caused by control errors.

[0077] According to the above embodiments of the present invention, determining the steering wheel angle ratio of an autonomous vehicle based on the actual steering wheel angle and the maximum steering capability parameter of the steering wheel includes: performing a division operation on the actual steering wheel angle and the maximum steering capability parameter to obtain the division result; and determining the division result as the steering wheel angle ratio.

[0078] In this embodiment, for lateral control error, the current steering wheel angle is taken into account. Maximum steering wheel angle and the maximum speed of the steering wheel It can calculate the proportion of the current turning angle to the maximum turning angle. : .

[0079] This method involves performing a normalized division operation between the current actual steering wheel angle (in degrees) of the autonomous vehicle and the maximum steering capability (maximum steering wheel angle) allowed by the vehicle's design, to obtain a dimensionless ratio—the steering wheel angle percentage. Its physical meaning lies in characterizing the relative saturation of the current steering operation in the vehicle's steering capability spectrum. This ratio reflects whether the vehicle is currently in a low, medium, or high steering load state, and is a key input indicator for evaluating the steering system's response margin and trajectory tracking potential.

[0080] By implementing this control method, the system can determine in real time whether the vehicle is approaching its physical steering limit, thereby identifying high-risk conditions where insufficient steering ability may prevent the planned trajectory from being executed accurately. This parameter serves as an important input for risk weights, enabling the system to automatically trigger a stricter speed limit strategy when the steering pressure is high (e.g., the proportion is ≥2 / 3), effectively preventing front-end deviation collisions caused by steering lag or insufficiency, and significantly improving the trajectory following safety of the vehicle in narrow port turning scenarios.

[0081] According to the above embodiments of the present invention, determining the lateral control deviation of an autonomous vehicle based on its current actual position and the planned path includes: determining the heading of the autonomous vehicle based on its current actual position; and calculating the shortest Euclidean distance from the reference point to the planned path along a direction perpendicular to the heading, using the center line of the autonomous vehicle's front as a reference point, to obtain the lateral control deviation.

[0082] In this embodiment, lateral control deviation This refers to the distance from the planned path to the center line of the vehicle's front end, excluding the influence of the vehicle's length. The yaw angle is taken into account during the calculation, and the error varies with the vehicle's yaw angle.

[0083] This method extracts the current centerline position of the autonomous vehicle's front end and its heading angle. Using this point as a reference, a perpendicular line is drawn to the planned path along a direction perpendicular to the vehicle's heading. The Euclidean distance of this perpendicular line segment is calculated, thereby accurately quantifying the lateral offset of the vehicle's actual position relative to the ideal planned path, i.e., the lateral control deviation. This method does not rely on vehicle length or tire models, but is based solely on geometric relationships, ensuring simple calculations, strong real-time performance, and a true reflection of the control module's execution error in path tracking.

[0084] By implementing this control method, the system can perceive in real time the accumulated error of the control algorithm failing to fully follow the planned trajectory during turning or dynamic adjustment, providing direct and sensitive feedback signals for risk assessment. When the deviation exceeds the threshold (e.g., ≥20cm), the system can automatically increase the risk weight and trigger a deceleration mechanism, effectively preventing the vehicle from side-collision with obstacles such as guardrails and stone blocks due to trajectory tracking failure, and significantly enhancing the path safety and control stability of port autonomous vehicles in high-precision operating environments.

[0085] According to the above embodiments of the present invention, determining the total risk value of an autonomous vehicle based on collision time, steering wheel angle percentage, and lateral control deviation includes: determining the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and each lateral control deviation level threshold; determining the risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold; determining the lateral error weight value based on the level identifier corresponding to the lateral control deviation level; obtaining the theoretical turning time of the autonomous vehicle; and calculating the total risk value based on the product of collision time and collision risk weight factor, the product of steering wheel angle percentage and risk weight value, the product of theoretical turning time and steering risk weight factor, and the product of lateral control deviation and lateral error weight value.

[0086] In this embodiment, the risk weight is calculated based on the current turning angle percentage and the magnitude of the planning error.

[0087] This method constructs a comprehensive risk assessment model by weighted fusion of multi-dimensional risk factors: First, it classifies lateral control deviations into three levels—low, medium, and high—based on their magnitude, and assigns different lateral error weights accordingly. Second, it classifies steering load levels based on the proportion of steering wheel angle and dynamically matches the corresponding risk weights. Then, it combines the theoretical steering time (calculated from heading error and maximum steering rate) and collision time, multiplying them by empirically tuned steering risk weight factors and collision risk weight factors, respectively. Finally, it sums the four weighted products to form a unified total risk value that reflects path tracking error, steering capability constraints, and collision urgency, thereby achieving a quantitative and comprehensive assessment of the vehicle's safety status.

[0088] By implementing this control method, the limitations of single-index speed limits are overcome. By integrating four key safety factors—control error, steering capability, steering delay, and collision time—speed limit decisions become more intelligent and adaptable to different scenarios. In complex port conditions with small turning radii, large load variations, or significant planning deviations, the system can automatically improve the risk score and trigger a more conservative speed limit strategy, significantly reducing the risk of collisions caused by control lag or understeering. This enhances the overall safety redundancy and operational stability of autonomous vehicles in high-precision, high-risk operating environments.

[0089] According to the above embodiments of the present invention, the lateral control deviation level thresholds include: a first threshold and a second threshold, wherein the first threshold is less than the second threshold. The lateral control deviation level of the autonomous vehicle is determined based on the relationship between the lateral control deviation and each lateral control deviation level threshold, including: when the lateral control deviation is less than the first threshold, determining the lateral control deviation level as a low error level; when the lateral control deviation is not less than the first threshold and less than the second threshold, determining the lateral control deviation level as a medium error level; and when the lateral control deviation is not less than the second threshold, determining the lateral control deviation level as a high error level.

[0090] In this embodiment, lateral control deviation This reflects the deviation between the vehicle's current actual position and the planned path. The error can be divided into three levels: when... When using ;when When using ;when When using .

[0091] This method divides continuous lateral control deviation values ​​into three discrete level intervals (low, medium, and high) by setting two tiered thresholds (first threshold and second threshold), thereby achieving a qualitative classification of control accuracy. The basis for this classification is the difference in the degree of safety impact of port autonomous vehicles at different deviation levels. Low deviation (<10cm) is within the normal tracking range, medium deviation (10cm-20cm) indicates potential tracking deviation accumulation, and high deviation (≥20cm) indicates that the control module has seriously deviated from the planned path and requires emergency intervention. This tiered mechanism transforms continuous quantities into discrete state indicators that facilitate system decision-making, improving the interpretability and computational efficiency of risk assessment.

[0092] By implementing this control method, the system can implement differentiated safety response strategies for different risk levels—maintaining normal speed for low levels, moderately reducing speed and issuing warnings for medium levels, and triggering mandatory speed limits or emergency braking for high levels. This ensures traffic efficiency while accurately matching safety redundancy. This hierarchical design effectively avoids the jitter problem of frequent speed limit triggering due to minor errors, enhances the stability and engineering practicality of the speed limit mechanism, and significantly improves the trajectory safety control capability of port autonomous vehicles in complex operating environments.

[0093] According to the above embodiments of the present invention, obtaining the theoretical turning time of an autonomous vehicle includes: obtaining the planned heading angle of the autonomous vehicle based on the planned path, and determining the current actual heading of the autonomous vehicle based on the current actual position; calculating the heading deviation of the autonomous vehicle based on the planned heading angle and the current actual heading; and performing a division operation on the maximum steering wheel turning rate and the heading deviation of the autonomous vehicle to obtain the theoretical turning time.

[0094] In this embodiment, the deviation between the planned path and the actual vehicle direction can be calculated by measuring the planned heading angle. Compared to the current actual vehicle front orientation The difference between them is used to obtain: Maximum speed limit can be used. Calculate the time required for steering : .

[0095] Optionally, and All measurements are in degrees. Their heading angles are relative to the map coordinate system, indicating the vehicle's direction relative to the map coordinate system. This is the steering wheel angular rate (deg / s). This value takes into account the maximum rate of steering wheel rotation, but does not take into account the steering ratio, as this rate has already been corrected for the steering ratio.

[0096] This method calculates the angular deviation between the expected vehicle heading angle of the planned path and the actual vehicle heading direction. Based on the maximum steering wheel turning rate—that is, the maximum steering angle change that can be completed per unit time—the heading deviation is divided by this rate to obtain the theoretical time required for the vehicle to complete the angle correction under the current steering capability.

[0097] By implementing this control method, the system can quantify the "steering delay risk" caused by vehicle control lag or slow steering response, making up for the shortcomings of static evaluation that relies solely on the current deviation or turning angle percentage. When the theoretical turning time is long, it indicates that the vehicle has difficulty correcting its course quickly and is very likely to collide with obstacles during the turning process due to "the front of the vehicle not turning into place". This indicator prompts the system to slow down in advance, leaving sufficient time window for turning, and significantly improving the trajectory execution safety of port autonomous vehicles in narrow curves or dynamic obstacle environments.

[0098] According to the above embodiments of the present invention, the risk threshold includes: a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. A risk weight value is determined based on the relationship between the steering wheel angle percentage and each risk threshold, including: when the steering wheel angle percentage is less than the first risk threshold, determining the risk weight value as the first risk weight value; when the steering wheel angle percentage is not less than the first risk threshold and is less than the second risk threshold, determining the risk weight value as the second risk weight value, wherein the first risk weight value is less than the second risk weight value; and when the steering wheel angle percentage is not less than the second risk threshold, determining the risk weight value as the third risk weight value, wherein the second risk weight value is less than the third risk weight value.

[0099] In this embodiment, when When using a lower risk weight ;when At that time, use a medium risk weight. ;when When using risky_weight(high), a higher risk weight is used.

[0100] This method divides the steering load into three levels—low, medium, and high—based on a segmented comparison of the steering wheel angle percentage with two preset risk thresholds (such as 1 / 3 and 2 / 3), and assigns corresponding increasing risk weight values. The core idea is that the closer the steering operation is to the vehicle's physical limits (the higher the steering angle percentage), the more limited the system's response capability and the greater the potential risk of trajectory tracking failure. By mapping the nonlinear steering saturation degree to a linearly increasing risk weight, the method achieves a quantitative expression of the hidden danger of "steering capability approaching its limit," providing dynamic and scenario-adaptive input parameters for subsequent risk weighting.

[0101] By implementing this control method, the system can maintain efficient passage under low steering loads, provide appropriate warnings and reduce speed under medium loads, and actively strengthen safety constraints under high loads (such as sharp turns), significantly improving the sensitivity and responsiveness to high-risk steering conditions; by introducing a weighted ladder, a dynamic balance between safety and efficiency is achieved.

[0102] According to the above embodiments of the present invention, the target speed limit of an autonomous vehicle is calculated by linear interpolation based on the total risk value, including: obtaining the minimum risk value and the maximum risk value of the autonomous vehicle in its current motion state; obtaining the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in its current motion state; determining a first risk difference between the maximum risk value and the total risk value, and determining a second risk difference between the total risk value and the minimum risk value; and summing the product of the ratio between the first risk difference and the second risk difference and the speed limit difference with the minimum speed limit as the target speed limit value.

[0103] In this embodiment, the collision risk, steering wheel angle and planning error, and lateral control deviation are weighted and summed to obtain the total risk value. The specific calculation formula is as follows: Based on different levels of risk, the final speed limit for vehicles is determined using linear interpolation. The specific formula is as follows: ,in: and These are the minimum and maximum speed limits for vehicles. and That is the corresponding cost range.

[0104] Optionally, It is a weighting factor for measuring collision risk, mainly based on the relative speed between the vehicle and the obstacle, the distance to the obstacle, and the estimated collision time. It is a weighting factor for measuring the risk of a shift, used to assess... The longer the weighted average takes, the better. The larger. Both are empirical values ​​that have been adjusted manually based on actual test results.

[0105] Optionally, and It is each item of The weighted sum after that, specifically based on For example, The range of values ​​is ,So , . . .

[0106] This method uses linear interpolation to map the total risk value obtained from multi-dimensional comprehensive calculations to a continuously adjustable target speed limit. Its core lies in establishing a monotonically decreasing linear relationship between "risk and speed": by normalizing the relative position of the total risk value between the minimum risk (sufficient safety) and the maximum risk (critical danger), the difference between the maximum and minimum speed limits is scaled proportionally, and then the minimum speed limit is superimposed to output a real-time speed limit that accurately matches the current safety situation.

[0107] By implementing this control method, vehicles can smoothly decelerate when transitioning from low to high risk, avoiding sudden braking disturbances caused by minor errors and rapidly reducing speed in high-risk scenarios to reserve sufficient safety margins, significantly improving driving stability and passenger comfort. At the same time, this method has good configurability, requiring only adjustments to the minimum / maximum risk and speed limit boundaries to adapt to different vehicle types or operating environments, greatly enhancing the safety and adaptability of port autonomous driving systems in complex and dynamic scenarios.

[0108] As described above, the technical solution provided by the embodiments of this invention constructs a multi-dimensional risk weighted assessment mechanism. By real-time monitoring of key parameters such as lateral control error, steering wheel angle ratio, planned heading angle deviation, steering time, and collision time, different risk weights are assigned to each parameter and integrated into a comprehensive risk cost. Furthermore, a linear interpolation model is used to dynamically generate vehicle speed limits, achieving closed-loop safety control where "the greater the error, the higher the risk, and the lower the speed." This method overcomes the limitations of traditional fixed speed limits or single error feedback, and for the first time quantifies and integrates the multi-source characteristics of control errors into a calculable and responsive dynamic speed limit strategy, significantly improving the trajectory execution safety and system accuracy of autonomous vehicles in high-risk scenarios such as turning and U-turns in ports.

[0109] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0111] Example 2

[0112] According to embodiments of the present invention, a control device for an autonomous vehicle that implements the above-described control method for an autonomous vehicle is also provided. Figure 3 This is a schematic diagram of the control device for an autonomous vehicle according to an embodiment of the present invention, such as... Figure 3 As shown, the device includes: a first determining unit 301, a second determining unit 303, a third determining unit 305, a fourth determining unit 307, a calculation unit 309, and a constraint unit 311. The device will now be described in detail.

[0113] The first determining unit 301 is used to determine the collision time required for the autonomous vehicle to travel in its current motion state to collide with the obstacle.

[0114] The second determining unit 303 is used to determine the steering wheel angle ratio of the steering wheel based on the actual steering wheel angle and the maximum steering capability parameter of the steering wheel of the autonomous vehicle.

[0115] The third determining unit 305 is used to determine the lateral control deviation of the autonomous vehicle based on the current actual position of the autonomous vehicle and the planned path.

[0116] The fourth determining unit 307 is used to determine the total risk value of the autonomous vehicle based on the collision time, the proportion of steering wheel angle, and the lateral control deviation.

[0117] The calculation unit 309 is used to calculate the target speed limit of the autonomous vehicle by linear interpolation based on the total risk value.

[0118] The constraint unit 311 is used to constrain the current driving speed of the autonomous vehicle using the target speed limit value in order to control the autonomous vehicle.

[0119] It should be noted that the first determining unit 301, the second determining unit 303, the third determining unit 305, the fourth determining unit 307, the calculation unit 309, and the constraint unit 311 mentioned above correspond to steps S202 to S212 in the above embodiments. The six units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0120] As can be seen from the above, the solution described in the above embodiments of the present invention can utilize a first determining unit to determine the collision time required for the autonomous vehicle to collide with an obstacle while in its current motion state; a second determining unit to determine the steering wheel angle percentage based on the actual steering wheel angle and the maximum steering capability parameter of the autonomous vehicle's steering wheel; a third determining unit to determine the lateral control deviation of the autonomous vehicle based on its current actual position and planned path; a fourth determining unit to determine the total risk value of the autonomous vehicle based on the collision time, steering wheel angle percentage, and lateral control deviation; a calculation unit to calculate the target speed limit of the autonomous vehicle using linear interpolation based on the total risk value; and a constraint unit to constrain the current driving speed of the autonomous vehicle using the target speed limit value to control the autonomous vehicle. Through the above technical solution, the goal of dynamically adjusting the vehicle speed limit by real-time monitoring of lateral error, steering wheel angle percentage, planned heading deviation, and collision time, and weighted and fused into a risk cost, is achieved. This significantly reduces the collision probability of autonomous vehicles in restricted scenarios such as turning and U-turns in ports, and improves the safety and stability of the system in high-precision operating environments.

[0121] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problem in the related art that the planning and control module in an autonomous driving system is prone to errors in some limited scenarios, which may cause the actual driving trajectory of the vehicle to deviate from the planned trajectory and easily lead to collisions.

[0122] Optionally, the first determining unit includes: a first acquiring module, used to acquire the current driving speed, estimated acceleration, and obstacle distance of the autonomous vehicle along the planned path direction to the obstacle; a generating module, used to generate a distance-time relationship curve of the autonomous vehicle along the planned path based on the current driving speed and estimated acceleration, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and estimated acceleration as parameters; and a first determining module, used to determine the collision time required for the autonomous vehicle to travel in its current motion state to collide with the obstacle based on the obstacle distance and the distance-time relationship curve.

[0123] Optionally, the second determining unit includes: a first calculation module, used to perform a division operation on the actual steering wheel angle and the maximum steering capability parameter to obtain the division result; and a second determining module, used to determine the division result as the steering wheel angle percentage.

[0124] Optionally, the third determining unit includes: a third determining module, used to determine the heading of the autonomous vehicle based on the current actual position; and a second calculation module, used to calculate the shortest Euclidean distance from the reference point to the planned path along a direction perpendicular to the heading, with the center line of the autonomous vehicle's front as the reference point, so as to obtain the lateral control deviation.

[0125] Optionally, the fourth determining unit includes: a fourth determining module, used to determine the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and the threshold values ​​of each lateral control deviation level; a fifth determining module, used to determine the risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold; a sixth determining module, used to determine the lateral error weight value based on the level identifier corresponding to the lateral control deviation level; a second obtaining module, used to obtain the theoretical turning time of the autonomous vehicle; and a third calculating module, used to calculate the total risk value based on the product of the collision time and the collision risk weight factor, the product of the steering wheel angle percentage and the risk weight value, the product of the theoretical turning time and the steering risk weight factor, and the product of the lateral control deviation and the lateral error weight value.

[0126] Optionally, the lateral control deviation level threshold includes: a first threshold and a second threshold, wherein the first threshold is less than the second threshold. The fourth determining module includes: a first determining submodule, used to determine the lateral control deviation level as a low error level when the lateral control deviation is less than the first threshold; a second determining submodule, used to determine the lateral control deviation level as a medium error level when the lateral control deviation is not less than the first threshold and less than the second threshold; and a third determining submodule, used to determine the lateral control deviation level as a high error level when the lateral control deviation is not less than the second threshold.

[0127] Optionally, the second acquisition module includes: a fourth determination submodule, used to obtain the planned heading angle of the autonomous vehicle based on the planned path, and to determine the current actual heading of the autonomous vehicle based on the current actual position; a first calculation submodule, used to calculate the heading deviation of the autonomous vehicle based on the planned heading angle and the current actual heading; and a second calculation submodule, used to perform a division operation on the maximum steering wheel turning rate and the heading deviation of the autonomous vehicle to obtain the theoretical turning time.

[0128] Optionally, the risk threshold includes: a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. The fifth determining module includes: a fifth determining submodule, used to determine a risk weight value as a first risk weight value when the steering wheel angle percentage is less than the first risk threshold; a sixth determining submodule, used to determine a risk weight value as a second risk weight value when the steering wheel angle percentage is not less than the first risk threshold and the steering wheel angle percentage is less than the second risk threshold, wherein the first risk weight value is less than the second risk weight value; and a seventh determining submodule, used to determine a risk weight value as a third risk weight value when the steering wheel angle percentage is not less than the second risk threshold, wherein the second risk weight value is less than the third risk weight value.

[0129] Optionally, the calculation unit includes: a third acquisition module for acquiring the minimum risk value and the maximum risk value of the autonomous vehicle in its current motion state; a fourth acquisition module for acquiring the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in its current motion state; a seventh determination module for determining a first risk difference between the maximum risk value and the total risk value, and determining a second risk difference between the total risk value and the minimum risk value; and a fourth calculation module for summing the product of the ratio between the first risk difference and the second risk difference and the speed limit difference with the minimum speed limit as the target speed limit value.

[0130] According to another aspect of the present invention, an autonomous driving vehicle is also provided, which uses the control method of any of the above-described autonomous driving vehicles.

[0131] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method of the autonomous vehicle described in any of the above embodiments.

[0132] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the control method for an autonomous vehicle described above.

[0133] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, which, when executed by a processor, perform a control method for an autonomous vehicle according to any of the above-described embodiments.

[0134] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0135] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the collision time required for the autonomous vehicle to travel in its current motion state to collide with the obstacle; determining the steering wheel angle percentage based on the actual steering wheel angle and the maximum steering capability parameter of the steering wheel of the autonomous vehicle; determining the lateral control deviation of the autonomous vehicle based on the current actual position and the planned path of the autonomous vehicle; determining the total risk value of the autonomous vehicle based on the collision time, the steering wheel angle percentage, and the lateral control deviation; calculating the target speed limit of the autonomous vehicle using linear interpolation based on the total risk value; and using the target speed limit to constrain the current driving speed of the autonomous vehicle to control the autonomous vehicle.

[0136] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining the current driving speed, estimated acceleration, and obstacle distance of the autonomous vehicle along the planned path direction to the obstacle; generating a distance-time relationship curve of the autonomous vehicle along the planned path based on the current driving speed and estimated acceleration, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and estimated acceleration as parameters; and determining the collision time required for the autonomous vehicle to travel in its current motion state to collide with the obstacle based on the obstacle distance and the distance-time relationship curve.

[0137] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: performing a division operation between the actual steering wheel angle and the maximum steering capability parameter to obtain the division result; and determining the division result as the steering wheel angle percentage.

[0138] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the heading of the autonomous vehicle based on the current actual position; using the center line of the autonomous vehicle's front as a reference point, calculating the shortest Euclidean distance from the reference point to the planned path along a direction perpendicular to the heading, in order to obtain the lateral control deviation.

[0139] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the lateral control deviation level of the autonomous vehicle based on the relationship between the lateral control deviation and the threshold values ​​of each lateral control deviation level; determining the risk weight value based on the relationship between the steering wheel angle percentage and each risk threshold; determining the lateral error weight value based on the level identifier corresponding to the lateral control deviation level; obtaining the theoretical steering time of the autonomous vehicle; and calculating the total risk value based on the product of the collision time and the collision risk weight factor, the product of the steering wheel angle percentage and the risk weight value, the product of the theoretical steering time and the steering risk weight factor, and the product of the lateral control deviation and the lateral error weight value.

[0140] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when the lateral control deviation is less than a first threshold, determining the lateral control deviation level as a low error level; when the lateral control deviation is not less than the first threshold and less than a second threshold, determining the lateral control deviation level as a medium error level; when the lateral control deviation is not less than the second threshold, determining the lateral control deviation level as a high error level.

[0141] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining the planned heading angle of the autonomous vehicle based on the planned path, and determining the current actual heading of the autonomous vehicle based on the current actual position; calculating the heading deviation of the autonomous vehicle based on the planned heading angle and the current actual heading; and performing a division operation on the maximum steering wheel turning rate and the heading deviation of the autonomous vehicle to obtain the theoretical turning time.

[0142] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when the steering wheel angle percentage is less than a first risk threshold, determining a risk weight value as a first risk weight value; when the steering wheel angle percentage is not less than the first risk threshold and the steering wheel angle percentage is less than a second risk threshold, determining a risk weight value as a second risk weight value, wherein the first risk weight value is less than the second risk weight value; when the steering wheel angle percentage is not less than the second risk threshold, determining a risk weight value as a third risk weight value, wherein the second risk weight value is less than the third risk weight value.

[0143] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining the minimum risk value and the maximum risk value of the autonomous vehicle in its current motion state; obtaining the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in its current motion state; determining a first risk difference between the maximum risk value and the total risk value, and determining a second risk difference between the total risk value and the minimum risk value; and summing the product of the ratio between the first risk difference and the second risk difference and the speed limit difference with the minimum speed limit as the target speed limit value.

[0144] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0145] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0146] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0148] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0149] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0150] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for an autonomous vehicle, characterized in that, include: Determine the collision time required for the autonomous vehicle to travel from its current state of motion to the point of colliding with the obstacle; The steering wheel angle percentage of the steering wheel is determined based on the actual steering wheel angle of the steering wheel of the autonomous vehicle and the maximum steering capability parameter of the steering wheel. The lateral control deviation of the autonomous vehicle is determined based on its current actual position and the planned path. The total risk value of the autonomous vehicle is determined based on the collision time, the steering wheel angle percentage, and the lateral control deviation. Based on the total risk value, the target speed limit of the autonomous vehicle is calculated using linear interpolation. The target speed limit is used to constrain the current speed of the autonomous vehicle in order to control the autonomous vehicle.

2. The control method for an autonomous vehicle according to claim 1, characterized in that, Determine the collision time required for the autonomous vehicle to travel from its current state of motion to the point of collision with the obstacle, including: The current driving speed, estimated acceleration, and distance of the autonomous vehicle from the obstacle along the planned path direction are obtained. Based on the current driving speed and the estimated acceleration, a distance-time relationship curve of the autonomous vehicle along the planned path is generated, wherein the distance-time relationship curve represents the distance traveled by the autonomous vehicle along the planned path at any time with the current driving speed and the estimated acceleration as parameters; The collision time required for the autonomous vehicle to travel to the point of colliding with the obstacle is determined based on the obstacle distance and the distance-time relationship curve.

3. The control method for an autonomous vehicle according to claim 1, characterized in that, The steering wheel angle percentage of the autonomous vehicle is determined based on the actual steering wheel angle and the maximum steering capability parameter of the steering wheel, including: The actual steering wheel angle and the maximum steering capability parameter are divided to obtain the division result. The result of the division operation is determined as the percentage of the steering wheel angle.

4. The control method for an autonomous vehicle according to claim 1, characterized in that, The lateral control deviation of the autonomous vehicle is determined based on its current actual position and the planned path, including: The heading of the autonomous vehicle is determined based on the current actual location; Using the centerline of the front of the autonomous vehicle as a reference point, the shortest Euclidean distance from the reference point to the planned path is calculated along a direction perpendicular to the heading, in order to obtain the lateral control deviation.

5. The control method for an autonomous vehicle according to claim 1, characterized in that, The total risk value of the autonomous vehicle is determined based on the collision time, the steering wheel angle percentage, and the lateral control deviation, including: The lateral control deviation level of the autonomous vehicle is determined based on the relationship between the lateral control deviation and the threshold values ​​of each lateral control deviation level. The risk weight value is determined based on the relationship between the steering wheel angle percentage and each risk threshold. The lateral error weight value is determined based on the level identifier corresponding to the lateral control deviation level; Obtain the theoretical turning time of the autonomous vehicle; The total risk value is calculated based on the product of the collision time and the collision risk weight factor, the product of the steering wheel angle ratio and the risk weight value, the product of the theoretical steering time and the steering risk weight factor, and the product of the lateral control deviation and the lateral error weight value.

6. The control method for an autonomous vehicle according to claim 5, characterized in that, The lateral control deviation level thresholds include: a first threshold and a second threshold, wherein the first threshold is smaller than the second threshold. The lateral control deviation level of the autonomous vehicle is determined based on the relationship between the lateral control deviation and each lateral control deviation level threshold, including: When the lateral control deviation is less than the first threshold, the lateral control deviation level is determined to be a low error level; When the lateral control deviation is not less than the first threshold and less than the second threshold, the lateral control deviation level is determined to be the mean error level; When the lateral control deviation is not less than the second threshold, the lateral control deviation level is determined to be a high error level.

7. The control method for an autonomous vehicle according to claim 5, characterized in that, Obtaining the theoretical turning time of the autonomous vehicle includes: The planned heading angle of the autonomous vehicle is obtained based on the planned path, and the current actual heading of the autonomous vehicle is determined based on the current actual position. The heading deviation of the autonomous vehicle is calculated based on the planned heading angle and the current actual vehicle heading. The theoretical turning time is obtained by dividing the maximum steering wheel angle rate of the autonomous vehicle by the heading deviation.

8. The control method for an autonomous vehicle according to claim 6, characterized in that, The risk thresholds include: a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. Risk weight values ​​are determined based on the relationship between the steering wheel angle percentage and each risk threshold, including: When the steering wheel angle percentage is less than the first risk threshold, the risk weight value is determined to be the first risk weight value; When the percentage of steering wheel angle is not less than the first risk threshold and the percentage of steering wheel angle is less than the second risk threshold, the risk weight value is determined to be the second risk weight value, wherein the first risk weight value is less than the second risk weight value; When the steering wheel angle percentage is not less than the second risk threshold, the risk weight value is determined to be the third risk weight value, wherein the second risk weight value is less than the third risk weight value.

9. The control method for an autonomous vehicle according to any one of claims 1 to 8, characterized in that, Based on the total risk value, the target speed limit for the autonomous vehicle is calculated using linear interpolation, including: Obtain the minimum and maximum risk values ​​of the autonomous vehicle in the current motion state; Obtain the speed limit difference between the maximum speed limit and the minimum speed limit of the autonomous vehicle in the current motion state; Determine a first risk difference between the maximum risk value and the total risk value, and determine a second risk difference between the total risk value and the minimum risk value; The product of the ratio between the first risk difference and the second risk difference and the speed limit difference, plus the minimum speed limit, is used as the target speed limit.

10. A control device for an autonomous vehicle, characterized in that, include: The first determining unit is used to determine the collision time required for the autonomous vehicle to travel in its current motion state to collide with the obstacle. The second determining unit is used to determine the steering wheel angle ratio of the steering wheel based on the actual steering wheel angle of the steering wheel of the autonomous vehicle and the maximum steering capability parameter of the steering wheel. The third determining unit is used to determine the lateral control deviation of the autonomous vehicle based on the current actual position of the autonomous vehicle and the planned path. The fourth determining unit is used to determine the total risk value of the autonomous vehicle based on the collision time, the steering wheel angle percentage, and the lateral control deviation. The calculation unit is used to calculate the target speed limit of the autonomous vehicle using linear interpolation based on the total risk value. A constraint unit is used to constrain the current speed of the autonomous vehicle using the target speed limit value in order to control the autonomous vehicle.

Images