A method, system, and controller for correcting the direction of vehicle travel.

Abstract

This invention discloses a method, control system, and controller for correcting vehicle driving direction. The method includes: acquiring the vehicle's previous position information and updating the vehicle's current position information using the previous position information; obtaining a predicted driving trajectory for the vehicle based on the updated position information; calculating the front wheel steering angle value of the vehicle based on the positional relationship between the vehicle and a preset feedback boundary line, and the position indicated by a predicted point on the predicted driving trajectory; and correcting the vehicle's direction based on the front wheel steering angle value. This invention sets a feedback boundary line within a passable area, using the feedback boundary line as a reference for feedback correction of vehicle driving, thereby improving vehicle traffic safety.

Description

Technical Field

[0001] This invention relates to the field of low-speed autonomous driving technology, and in particular to a method, system, and controller for correcting the driving direction of a vehicle. Background Technology

[0002] Currently, driving control technologies for low-speed autonomous vehicles such as sweepers and logistics vehicles on unstructured roads generally use methods such as PID, PurePursuit, Stanley, and MPC to achieve the desired tracking effect. PID, PurePursuit, and Stanley are single-objective control methods, where the control objective is only tracking. MPC, on the other hand, can achieve multi-objective control, considering safety issues while tracking. Single-objective control does not consider vehicle safety, directly resulting in the vehicle's inability to respond to safety risks in advance. MPC multi-objective control can meet the requirements of safe and efficient passage through design, but it suffers from the drawback of large algorithm computation and high hardware performance requirements. Summary of the Invention

[0003] The purpose of this invention is to address the technical deficiencies in the prior art by providing a method, system, and controller for correcting the driving direction of a vehicle.

[0004] The technical solution adopted to achieve the purpose of this invention is:

[0005] A method for correcting the direction of travel of a vehicle, the method comprising:

[0006] Obtain the vehicle's previous location information and use the previous location information to update the vehicle's current location information;

[0007] The predicted driving trajectory of the vehicle is obtained based on the updated location information;

[0008] The front wheel steering angle of the vehicle is calculated based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory.

[0009] The vehicle's direction is corrected based on the front wheel steering angle value.

[0010] The step of calculating the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the predicted point on the predicted driving trajectory, includes:

[0011] When the positional relationship is such that the vehicle is outside the feedback boundary line, the distance by which the vehicle body enters the outside of the feedback boundary line is used as the correction value of the front wheel steering angle, and the front wheel steering angle value is calculated based on the correction value.

[0012] When the positional relationship is such that the vehicle is within the feedback boundary line, the front wheel steering angle value is calculated according to the preset control angle.

[0013] The step of calculating the front wheel steering angle value based on a preset control angle includes:

[0014]

[0015] In the formula, k_laterr and k_heading are adjustable parameters, v represents vehicle speed, heading_err represents heading deviation, lat_err represents lateral deviation, and δ1 is the preset control angle of the front wheel based on the aiming method.

[0016] Wherein, when the positional relationship is that the vehicle is outside the feedback boundary line, the distance by which the vehicle body enters the outside of the feedback boundary line is used as a correction value for the front wheel steering angle, and the front wheel steering angle value is calculated based on the correction value, including:

[0017] δ3=δ2+δ accurate δ accurate =atan(k_accur_con*d danger ),

[0018] In the formula, δ3 is the final output angle of the front wheel, k_accur_con is an adjustable parameter, and d danger This indicates the predetermined distance the vehicle has traveled beyond the feedback boundary line.

[0019] The preset control angle is calculated as follows:

[0020]

[0021] In the formula, δ1 is the preset control angle of the front wheel based on the pre-aiming method, L is the vehicle axle length, k is the adjustable proportional coefficient, α is the tangent angle of the vehicle steering arc, and l d This is the pre-aiming distance.

[0022] The lateral deviation and heading deviation are calculated from the vehicle's actual heading angle and the desired vehicle heading angle.

[0023] lat_err=dy*cosθ des -dx*sinθ des heading_err=θ-θ des

[0024] In the formula, dy and dx represent the deviations in the lateral and longitudinal directions of the vehicle coordinate system, θ represents the actual heading angle of the vehicle, and θ des Desired vehicle heading angle.

[0025] The step of updating the vehicle's current location information using the previous location information includes:

[0026]

[0027]

[0028]

[0029] In the formula, δ represents the steering angle of the front wheel, and L is the length of the vehicle axle. This is the previous location information. This indicates the current location information.

[0030] The present invention also provides a method for correcting the driving direction of a vehicle.

[0031] A system for correcting the direction of travel of a vehicle, the system comprising:

[0032] An update module is used to obtain the vehicle's previous location information and update the vehicle's current location information using the previous location information;

[0033] The prediction module is used to obtain the predicted driving trajectory of the vehicle based on the updated location information;

[0034] The correction module is used to calculate the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory; and to correct the direction of the vehicle based on the front wheel steering angle.

[0035] Another objective of this invention is to provide an autonomous driving controller, including a processor and a memory communicatively connected to the processor, the memory storing an autonomous driving control program configured to execute, when invoked by the processor, the steps of a method for correcting the vehicle's driving direction.

[0036] This invention improves the safety of unmanned vehicles by predicting future vehicle trajectories and thus anticipating vehicle safety risks.

[0037] The control module is configured to obtain a predicted future travel path based on the current control method and updated current location information. This predicted path is then used for vehicle frame verification. Finally, based on the verification results, emergency measures for potential hazards are evaluated to determine whether to stop the vehicle, correct its course in advance, or not correct it, and to preemptively correct the direction of travel for multiple vehicles. This allows for the early prediction of vehicle safety risks, improving the safety of autonomous vehicles.

[0038] In addition, this invention improves tracking accuracy by optimizing the vehicle control algorithm and optimizing the control of the front wheel steering angle, thus achieving precise tracking. Attached Figure Description

[0039] Figure 1 This is a flowchart of a method for correcting the driving direction of a vehicle according to the present invention;

[0040] Figure 2 This is a schematic diagram of a pre-set front wheel steering angle calculation model based on the anti-aiming method;

[0041] Figure 3 This is a schematic diagram illustrating driving within the non-feedback zone of a passable area;

[0042] Figure 4 This is a schematic diagram illustrating vehicle frame verification within a passable area.

[0043] Figure 5 This is a schematic diagram of a system for correcting the driving direction of a vehicle, provided by the present invention. Detailed Implementation

[0044] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0045] like Figure 1-4 As shown, a method for correcting the driving direction of a vehicle according to the present invention includes:

[0046] Step S1: Obtain the vehicle's previous location information and update the vehicle's current location information using the previous location information;

[0047] Step S2: Obtain the predicted driving trajectory of the vehicle based on the updated location information;

[0048] Step S3: Calculate the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory.

[0049] Step S4: Correct the vehicle's direction based on the front wheel steering angle value.

[0050] The step of calculating the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the predicted point on the predicted driving trajectory, includes:

[0051] When the positional relationship is such that the vehicle is outside the feedback boundary line, the distance by which the vehicle body enters the outside of the feedback boundary line is used as the correction value of the front wheel steering angle, and the front wheel steering angle value is calculated based on the correction value.

[0052] When the positional relationship is such that the vehicle is within the feedback boundary line, the front wheel steering angle value is calculated according to the preset control angle.

[0053] The step of calculating the front wheel steering angle value based on a preset control angle includes:

[0054]

[0055] In the formula, k_laterr and k_heading are adjustable parameters, v represents vehicle speed, heading_err represents heading deviation, lat_err represents lateral deviation, and δ1 is the preset control angle of the front wheels based on the pre-aiming method. Increasing k_laterr enhances the vehicle's ability to converge lateral deviation, while increasing k_heading enhances the vehicle's ability to converge heading deviation. When both increase simultaneously, the vehicle's dependence on pre-aiming decreases, thus achieving a complementary advantage between the pure pursuit method and the Stanley method, and compensating for the Stanley method's tendency to overshoot and the pure pursuit method's tendency to tangent.

[0056] Wherein, when the positional relationship is that the vehicle is outside the feedback boundary line, the distance by which the vehicle body enters the outside of the feedback boundary line is used as a correction value for the front wheel steering angle, and the front wheel steering angle value is calculated based on the correction value, including:

[0057] δ3=δ2+δ accurate δ accurate =atan(k_accur_con*d danger ),

[0058] In the formula, δ3 is the final output angle of the front wheel, k_accur_con is an adjustable parameter, and d danger This indicates the predetermined distance the vehicle has traveled beyond the feedback boundary line.

[0059] The preset control angle is calculated as follows:

[0060]

[0061] In the formula, δ1 is the preset control angle of the front wheel based on the pre-aiming method, L is the vehicle axle length, k is the adjustable proportional coefficient, α is the tangent angle of the vehicle steering arc, and l d The aiming distance is shown in the diagram. When vehicle 10 travels along the path, it uses a waypoint as a reference and controls the steering angle of its front wheels through aiming to achieve path-following.

[0062] The lateral deviation and heading deviation are calculated from the vehicle's actual heading angle and the desired vehicle heading angle.

[0063] lat_err=dy*cosθ des -dx*sinθ des heading_err=θ-θ des

[0064] In the formula, dy and dx represent the deviations in the lateral and longitudinal directions of the vehicle coordinate system, θ represents the actual heading angle of the vehicle, and θ des Desired vehicle heading angle.

[0065] The step of updating the vehicle's current location information using the previous location information includes:

[0066]

[0067]

[0068]

[0069] In the formula, δ represents the steering angle of the front wheel, and L is the length of the vehicle axle. This is the previous location information. This indicates the current location information. During driving, coordinate transformations are detected to calculate updated parameters, thus updating the vehicle's state.

[0070] To more clearly illustrate this solution, the following specific embodiments are provided:

[0071] Step 1. During the tracking process of vehicle 10, the current position information of the vehicle is updated by feeding back the previous position information of the vehicle, and a predicted driving trajectory 14 of the vehicle in the future is predicted based on the updated position information.

[0072] Step 2. Using the feedback boundary lines on both sides of the vehicle's passable area as a reference, perform vehicle frame verification at the predicted point of the predicted driving trajectory. Based on the verification results, correct the steering angle of the vehicle's front wheels to achieve tracking driving within the feedback boundary lines.

[0073] To better ensure vehicle safety and proactively address potential hazards, the control module in this invention is configured to obtain a predicted future travel path based on the current control method and updated current location information. This predicted path is then used for vehicle frame verification. Finally, based on the verification results, emergency measures for potential hazards are evaluated to determine whether to stop the vehicle, correct its course in advance, or not correct its course and adjust its travel direction accordingly. This allows for early prediction of vehicle safety risks, improving the safety of unmanned vehicles.

[0074] Specifically, when it is detected that the vehicle has traveled a predetermined distance outside the feedback boundary line, the front wheel steering angle is corrected by using the predetermined distance outside the feedback boundary line as the correction value. The angle of the front wheel steering is controlled to correct the vehicle to maintain tracking within the predetermined distance of the feedback boundary line, that is, to drive back to the non-feedback area formed inside the feedback boundary line, thereby achieving safe driving.

[0075] During the vehicle's tracking process within the feedback boundary line, the lateral deviation, heading deviation, and preset control angle of the front wheels are calculated. The steering angle of the front wheels is adjusted in real time based on the vehicle speed to achieve tracking control. The calculation of the front wheel steering angle is as follows:

[0076]

[0077] Figure 2 It is a pre-set front wheel deflection angle calculation model based on the pre-aiming method. Figure 2 In the middle, l d The aiming distance is α, the tangent angle of the turning arc is R, and the radius of the turning arc is (g x ,g y Given the waypoint coordinates, the preset control angle (aiming point preset angle) of the front wheel based on the pre-aiming method can be calculated using the following formula:

[0078]

[0079] In the formula, δ1 is the preset control angle of the front wheel based on the pre-aiming method, L is the vehicle axle length, k is the adjustable proportional coefficient, α is the tangent angle of the vehicle steering arc, and l d To predict the distance, as shown in the figure, when vehicle 10 travels along the path, it uses the waypoint as a reference and controls the turning angle of its front wheels through a predictive method to achieve path-following.

[0080] In this invention, the lateral deviation and heading deviation are calculated from the vehicle's actual heading angle and the desired vehicle heading angle:

[0081] lat_err=dy*cosθ des -dx*sinθ des heading_err=θ-θ des

[0082] In the formula, dy and dx represent the deviations in the lateral and longitudinal directions of the vehicle coordinate system, θ represents the actual heading angle of the vehicle, and θ des Desired vehicle heading angle.

[0083] The calculation formula for the vehicle location status update is as follows:

[0084]

[0085]

[0086]

[0087] In the formula, δ represents the steering angle of the front wheel, and L is the length of the vehicle axle. The value of the vehicle before the status update. This represents the corresponding value after the state update. The updated parameters can be calculated by detecting coordinate transformations during driving, thus realizing the state update process of the vehicle.

[0088] In this invention, the vehicle planning module provides the vehicle's passable boundary line 12. The two passable boundary lines 12 form the vehicle's passable area. The boundary of this passable area will narrow on one side as obstacles approach, thus achieving dynamic changes.

[0089] In this invention, to ensure stable boundary feedback, a feedback boundary line 11 is set to form a non-feedback region, such as... Figure 3 The area within the dashed line is the non-feedback area. In this area, the control of the front wheels of vehicle 10 is based on the preset angle of the front wheels and the lateral and directional deviations of the vehicle, as mentioned above.

[0090] When the vehicle extends beyond the feedback boundary line, i.e., enters the area between the feedback boundary line and the passable boundary line, for enhanced driving safety, this invention uses the distance the vehicle's frame 13 extends beyond the dotted line (feedback boundary line 11) as a control adjustment amount, which is fed back to the vehicle's tracking module and incorporated into the front wheel steering angle control calculation. The final output is the front wheel control angle, thus ensuring the vehicle always travels within a safe passage zone, improving traffic safety. By setting a non-feedback area, frequent vehicle corrections can also be prevented. Figure 4 In the process, the algorithm performs vehicle frame verification according to the predicted dotted line, uses the distance of the most dangerous vehicle frame (as shown in the black solid line frame) into the dotted line (feedback boundary line) as feedback, and incorporates the control quantity into the angle calculation to correct the front wheel angle, outputting the final front wheel angle to achieve vehicle tracking.

[0091] The formula is as follows:

[0092] δ3=δ2+δ accurate δ accurate =atan(k_accur_con*d danger ),

[0093] In the formula, δ3 is the final output angle of the front wheel, k_accur_con is an adjustable parameter, and increasing this adjustable parameter enhances the corresponding feedback. danger This indicates the distance the vehicle has traveled beyond the feedback boundary line.

[0094] like Figure 5 As shown, the present invention also provides a system for correcting the driving direction of a vehicle, the system comprising:

[0095] The update module 21 is used to obtain the vehicle's previous location information and update the vehicle's current location information using the previous location information;

[0096] The prediction module 22 is used to obtain the predicted driving trajectory of the vehicle based on the updated location information;

[0097] The correction module 23 is used to calculate the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory; and to correct the direction of the vehicle based on the front wheel steering angle.

[0098] The correction module 23 is further configured to, when the positional relationship is that the vehicle is outside the feedback boundary line, take the distance of the vehicle body entering the outside of the feedback boundary line as the correction value of the front wheel angle, and calculate the front wheel angle value based on the correction value; when the positional relationship is that the vehicle is inside the feedback boundary line, calculate the front wheel angle value based on the preset control angle.

[0099] Another objective of this invention is to provide an autonomous driving controller, including a processor and a memory communicatively connected to the processor, the memory storing an autonomous driving control program configured to execute the steps of the method for correcting the driving direction of a vehicle when invoked by the processor.

[0100] This invention optimizes the vehicle control algorithm, enabling the vehicle to achieve stable and accurate control. Furthermore, based on the calculated front wheel angle, this invention utilizes kinematics to update the future state and predict the trajectory, allowing for advance safety checks and thus the ability to anticipate safety risks.

[0101] This invention improves vehicle stability and safety by defining feedback boundary lines to delineate non-feedback and feedback zones within the traffic area. When a vehicle enters outside the correction boundary (indicated by the dotted line) or even outside the traffic area, it is prone to longitudinal stopping due to obstacles and map boundaries, significantly reducing traffic efficiency. Through advance prediction and feedback, vehicles can better stay within the traffic area, reducing the likelihood of stopping and thus improving traffic efficiency.

[0102] In addition, by setting feedback boundary lines based on the traffic area output by the planning layer, vehicles can stay within a safe area, avoiding excessive corrections. At the same time, the boundary can be identified to deal with dangers in advance, thus improving the safety of vehicle traffic.

[0103] 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 method for correcting the direction of travel of a vehicle, characterized in that, The method includes: Obtain the vehicle's previous location information and use the previous location information to update the vehicle's current location information; The predicted driving trajectory of the vehicle is obtained based on the updated location information; The front wheel steering angle of the vehicle is calculated based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory. The vehicle's direction is corrected based on the front wheel steering angle value; The step of calculating the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the predicted point on the predicted driving trajectory, includes: When the positional relationship is such that the vehicle is within the feedback boundary line, the front wheel steering angle value is calculated based on a preset control angle; when the positional relationship is such that the vehicle is outside the feedback boundary line, the distance by which the vehicle body enters the outer side of the feedback boundary line is used as a correction value for the front wheel steering angle, and the front wheel steering angle value is calculated based on the correction value, including: ， ， In the formula, This is the final output angle of the front wheels. It is an adjustable parameter. This indicates the predetermined distance the vehicle has traveled beyond the feedback boundary line. The front wheel steering angle value is calculated based on a preset control angle.

2. The method according to claim 1, characterized in that, The calculation of the front wheel steering angle value based on the preset control angle includes: ， In the formula, , These are adjustable parameters. Indicates vehicle speed. Indicates heading deviation. Indicates lateral deviation. This is the preset control angle for the front wheels based on the pre-aiming method.

3. The method according to claim 1, characterized in that, The preset control angle is calculated as follows: ； In the formula, The preset control angle for the front wheels is based on the pre-aiming method, where L is the vehicle axle length. This is an adjustable scaling factor. The tangent angle of the vehicle's steering arc. This is the pre-aiming distance.

4. The method according to claim 2, characterized in that, The lateral deviation and heading deviation are calculated from the vehicle's actual heading angle and the desired vehicle heading angle: ， ； In the formula, , This indicates the deviation in the horizontal and vertical directions within the vehicle coordinate system. Indicates the vehicle's actual heading angle. This represents the desired vehicle heading angle.

5. The method according to claim 1, characterized in that, The step of updating the vehicle's current location information using the previous location information includes: ； In the formula, δ represents the steering angle of the front wheel, and L is the length of the vehicle axle. This is the previous location information. , , This indicates the current location information.

6. A system for correcting the direction of travel of a vehicle, characterized in that, The system is used to implement the method for correcting the driving direction of a vehicle as described in any one of claims 1-5, comprising: An update module is used to obtain the vehicle's previous location information and update the vehicle's current location information using the previous location information; The prediction module is used to obtain the predicted driving trajectory of the vehicle based on the updated location information; The correction module is used to calculate the front wheel steering angle of the vehicle based on the positional relationship between the vehicle and the preset feedback boundary line, and the position indicated by the prediction point on the predicted driving trajectory; and to correct the direction of the vehicle based on the front wheel steering angle.

7. An autonomous driving controller, comprising a processor and a memory communicatively connected to the processor, the memory storing an autonomous driving control program configured to execute the method steps of correcting the driving direction of a vehicle as described in any one of claims 1-5 when invoked by the processor.

Images