A vehicle congestion assisted following method, device, and vehicle

Abstract

The application provides a vehicle congestion auxiliary following method and device and a vehicle, and relates to the technical field of vehicle control. The method comprises the following steps: in the driving process of a vehicle, obtaining pose information of a plurality of front vehicles in surrounding obstacles according to perception data of the surrounding obstacles collected by a perception module on the vehicle; determining a target vehicle to be followed from the plurality of front vehicles according to the pose information of the plurality of front vehicles; planning a following trajectory of the vehicle for the target vehicle according to the pose information of the target vehicle and historical trajectory points of the target vehicle; performing curve fitting on the following trajectory to obtain a fitting curve equation corresponding to the following trajectory; and performing angle control on a steering wheel of the vehicle according to the fitting curve equation, so that the vehicle follows the target vehicle along the following trajectory. The application improves the response speed and driving stability of lateral control, realizes automatic following in a congestion scene, and improves driving safety and comfort.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and more specifically, to a vehicle congestion assist following method, device, and vehicle. Background Technology

[0002] In urban traffic environments, vehicles frequently encounter traffic congestion, especially during peak hours or on complex urban roads, where they often operate at low speeds, following other vehicles frequently and stopping and starting. Drivers must maintain concentration for extended periods to control direction and maintain distance, which can easily lead to fatigue, reducing driving safety and impacting transportation efficiency.

[0003] Currently, traffic congestion assistance systems typically rely on multi-sensor fusion perception technology, combining millimeter-wave radar, cameras, and lidar to obtain information on the position, speed, and heading of target vehicles ahead, and generating local path planning results based on this perception data.

[0004] However, existing technologies lack effective utilization of the historical motion trends of the target vehicle, resulting in strong lag and insufficient predictability in the planned trajectory. This makes it impossible to fully integrate the vehicle's position and pose information for trajectory optimization, leading to poor control response in the generated trajectory and affecting driving smoothness. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing a vehicle congestion assist following method, device, and vehicle, thereby improving the response speed and driving stability of lateral control, enabling automatic following in congested scenarios, and enhancing driving safety and comfort.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, one embodiment of this application provides a vehicle congestion-assisted following method, the method comprising: During the driving process of the vehicle, the position and pose information of multiple vehicles ahead in the surrounding obstacles is obtained based on the perception data of the surrounding obstacles collected by the perception module on the vehicle. Based on the pose information of multiple vehicles ahead, determine the target vehicle to be followed from among the multiple vehicles ahead; Based on the pose information of the target vehicle and the historical trajectory points of the target vehicle, the following trajectory of the vehicle is planned for the target vehicle; Perform curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory; Based on the fitted curve equation, the steering wheel of the vehicle is controlled to turn, so that the vehicle follows the target vehicle along the following trajectory.

[0007] Optionally, the sensing module includes multiple sensors, and the sensing data of the surrounding obstacles includes multiple sensing data. The step of obtaining the pose information of multiple vehicles ahead among the surrounding obstacles based on the perception data of the surrounding obstacles collected by the on-vehicle perception module includes: Multiple perception data of the same obstacle in the surrounding obstacles are fused to obtain multiple perception data of the vehicle in front; Based on the perception data of multiple vehicles ahead, the pose information of multiple vehicles ahead is obtained respectively.

[0008] Optionally, the position and pose information of the vehicle in front includes: lateral offset information, driving direction information, longitudinal distance information, and longitudinal speed information; The step of determining the target vehicle to be followed from the plurality of vehicles ahead based on their pose information includes: Based on the lateral offset information of multiple vehicles ahead, a first candidate vehicle that meets the lateral offset threshold is determined from the multiple vehicles ahead; Based on the driving direction information of the first candidate vehicle, a second candidate vehicle that is consistent with the driving direction of the vehicle is determined from the first candidate vehicle; Based on the longitudinal distance information of the second candidate vehicles, a third candidate vehicle that meets the longitudinal distance threshold is determined from the second candidate vehicles. Based on the longitudinal speed information of the third candidate vehicle, a vehicle that meets the longitudinal speed threshold is selected from the third candidate vehicle as the target vehicle.

[0009] Optionally, the step of planning the following trajectory of the vehicle relative to the target vehicle based on the pose information of the target vehicle and the historical trajectory points of the target vehicle includes: Based on the current position of the vehicle, the current position of the target vehicle, and the historical trajectory points, the longitudinal region between the vehicle and the target vehicle is divided into a first region and a second region; wherein, the first region is the region closer to the target vehicle, and the second region is the region closer to the vehicle. Based on the historical trajectory points of the target vehicle, the trajectory of the target vehicle is predicted to obtain the first planned trajectory of the vehicle in the first area; Based on the first planned trajectory, trajectory planning is performed on the second area to obtain the second planned trajectory of the vehicle in the second area; The following trajectory is obtained based on the first planned trajectory and the second planned trajectory.

[0010] Optionally, the step of predicting the trajectory of the target vehicle based on its historical trajectory points to obtain a first planned trajectory of the vehicle in the first area includes: Based on the historical trajectory points, obtain the trajectory change rate of the target vehicle; Based on the trajectory change rate and the current position of the target vehicle, the trajectory of the target vehicle is predicted to obtain the first planned trajectory.

[0011] Optionally, before performing trajectory planning on the second region based on the first planned trajectory to obtain the second planned trajectory of the vehicle in the second region, the method further includes: Perform Kalman filtering on the first planned trajectory; The step of planning a trajectory for the second region based on the first planned trajectory to obtain a second planned trajectory for the vehicle in the second region includes: Based on the filtered first planned trajectory, trajectory planning is performed on the second region to obtain the second planned trajectory of the vehicle in the second region.

[0012] Optionally, the step of performing trajectory planning on the second region based on the first planned trajectory to obtain the second planned trajectory of the vehicle in the second region includes: Based on the first planned trajectory, obtain the rate of change of the planned trajectory of the first planned trajectory; Based on the planned trajectory change rate and the current position of the vehicle, the trajectory of the vehicle is predicted to obtain the second planned trajectory.

[0013] Optionally, before performing curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory, the method further includes: Obtain the current attitude information and current acceleration information of the vehicle; Based on the vehicle's current attitude information and current acceleration information, the predicted attitude change information of the vehicle is obtained; Based on the predicted attitude change information, motion compensation is performed on the following trajectory to obtain the compensated following trajectory; The step of performing curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory includes: The compensated following trajectory is subjected to curve fitting to obtain the equation of the fitted curve.

[0014] Secondly, another embodiment of this application provides a vehicle congestion assist following device, the device comprising: The acquisition module is used to acquire the position and pose information of multiple vehicles ahead in the surrounding obstacles based on the perception data of the surrounding obstacles collected by the perception module on the vehicle during the driving process. The determination module is used to determine the target vehicle to be followed from the multiple vehicles ahead based on the pose information of the multiple vehicles ahead; The planning module is used to plan the following trajectory of the vehicle for the target vehicle based on the pose information of the target vehicle and the historical trajectory points of the target vehicle. The fitting module is used to perform curve fitting on the following trajectory to obtain the fitting curve equation corresponding to the following trajectory; The control module is used to control the steering wheel angle of the vehicle according to the fitted curve equation, so that the vehicle follows the target vehicle along the following trajectory.

[0015] Thirdly, another embodiment of this application provides an assisted driving control device, which includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the assisted driving control device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of any of the vehicle congestion assist following methods described in the first aspect above.

[0016] Fourthly, another embodiment of this application provides a storage medium storing a computer program, which, when executed by a processor, performs the steps of the vehicle congestion assist following method as described in any of the first aspects above.

[0017] Fifthly, another embodiment of this application also provides a vehicle, the vehicle comprising at least: a vehicle body and an auxiliary driving control device disposed on the vehicle body, the auxiliary driving control device being used to perform the steps of the vehicle congestion assist following method as described in any of the first aspects above.

[0018] The beneficial effects of this application are: This application provides a vehicle congestion-assisted following method, device, and vehicle. During the vehicle's operation, based on perception data of surrounding obstacles collected by the vehicle's perception module, the pose information of multiple vehicles ahead is obtained. Based on the pose information of these vehicles, a target vehicle to be followed is determined. Based on the target vehicle's pose information and its historical trajectory points, a following trajectory for the vehicle is planned. Curve fitting is performed on the following trajectory to obtain the corresponding fitted curve equation. Based on the fitted curve equation, the steering wheel of the vehicle is controlled to ensure the vehicle follows the target vehicle along the following trajectory. This application obtains the pose information of multiple vehicles ahead through a fusion perception module and combines it with the target vehicle's historical trajectory points for intelligent filtering and trajectory planning. It fully utilizes the advantages of multi-sensor fusion, improving the accuracy and robustness of target recognition, avoiding interference from complex traffic environments, enhancing path predictability and smoothness by introducing historical trajectory information, and generating a smooth fitted curve equation using curve fitting. Based on its geometric features, precise control of the steering wheel angle is achieved, improving the response speed of lateral control and driving stability. It achieves automatic following in congested scenarios, improving driving safety and comfort. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a vehicle congestion assist following method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the process of determining pose information in a vehicle congestion assist following method provided in an embodiment of this application. Figure 3 This is a schematic diagram illustrating the process of determining a target vehicle in a vehicle congestion assist following method provided in this application embodiment; Figure 4 A schematic diagram illustrating the process of determining the following trajectory in a vehicle congestion-assisted following method provided in an embodiment of this application; Figure 5 A flowchart illustrating the determination of a first planned trajectory in a vehicle congestion assist following method provided in an embodiment of this application; Figure 6 A flowchart illustrating the determination of a second planned trajectory in a vehicle congestion assist following method provided in this application embodiment; Figure 7A flowchart illustrating the determination of a second planned trajectory in a vehicle congestion assist following method provided in this application embodiment; Figure 8 A schematic flowchart illustrating the process of determining the fitted curve equation in a vehicle congestion assist following method provided in this application embodiment; Figure 9 This is a schematic diagram of the structure of a vehicle congestion assist following device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an assisted driving control device provided in an embodiment of this application; Figure 11 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0022] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0024] In congested urban traffic, frequent stops and starts of vehicles following other vehicles can easily lead to driver fatigue, affecting safety and efficiency. Currently, traffic jam assist systems utilize multi-sensor fusion perception technology to acquire real-time dynamic information about the vehicle ahead and generate local path planning to achieve automatic following and driving assistance in congested environments. However, existing technologies cannot effectively utilize the historical movement trends of the target vehicle, resulting in inaccurate trajectory control for the vehicle itself, impacting the driver's experience. The target vehicle is the vehicle the driver is following in congested conditions; the driver is the vehicle equipped with driver assistance control devices.

[0025] To address this issue, this application provides a vehicle congestion-assisted following method. Based on the target vehicle's position and pose information and its historical trajectory points, the method plans a following trajectory for the vehicle. It then performs curve fitting on the following trajectory to obtain the corresponding fitted curve equation. Based on the fitted curve equation, it controls the steering wheel angle of the vehicle to ensure the vehicle follows the target vehicle along the following trajectory. This method effectively addresses interference in complex traffic environments. By incorporating historical trajectory information, it enhances the predictability and continuity of the trajectory, improving driving smoothness and comfort.

[0026] To clearly describe the method in this application, the following set of multiple figures illustrates the vehicle congestion assist following method. Figure 1 This is a flowchart illustrating a vehicle congestion assist following method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes: Step 101: During the driving process of the vehicle, based on the perception data of surrounding obstacles collected by the perception module on the vehicle, obtain the position and pose information of multiple vehicles in front of the surrounding obstacles.

[0027] The "driving process" of the vehicle refers to its movement within traffic congestion. The perception module is used to sense the position and attitude of vehicles ahead. Obstacles refer to all traffic participants within the range of the perception module, including motor vehicles, non-motor vehicles, and pedestrians, etc., but this embodiment does not impose any restrictions. Multiple vehicles ahead refer to four-wheeled or more motor vehicles among the obstacles.

[0028] Optionally, during the driving process of the vehicle, based on the perception data of the surrounding obstacles of the vehicle collected by the perception module on the vehicle, the vehicle is identified as multiple vehicles with four or more wheels in the obstacles, and the position and pose information of the multiple vehicles in front is determined.

[0029] Step 102: Based on the pose information of multiple vehicles ahead, determine the target vehicle to be followed from among the multiple vehicles ahead.

[0030] Optionally, based on the pose information of multiple vehicles ahead, a vehicle that is associated with the pose information of the vehicle ahead is identified as the target vehicle to be followed.

[0031] Step 103: Based on the target vehicle's pose information and historical trajectory points, plan the vehicle's following trajectory for the target vehicle.

[0032] The historical trajectory points of the target vehicle are multiple location points of the target vehicle's movement over a historical period, obtained through the vehicle's onboard sensing module. These historical trajectory points are points on a coordinate system established with the vehicle's current position as the origin. The historical trajectory points include a set of the target vehicle's lateral and longitudinal positions at multiple points in time throughout the historical period.

[0033] Optionally, based on the pose information of the target vehicle and the historical trajectory points of the target vehicle, the difference between the pose information of the vehicle and the pose information of the target vehicle is determined, and the historical trajectory points are adjusted according to the difference between the pose information of the vehicle and the pose information of the target vehicle, thereby planning the following trajectory of the vehicle for the target vehicle.

[0034] Step 104: Perform curve fitting on the following trajectory to obtain the fitting curve equation corresponding to the following trajectory.

[0035] The fitted curve equation is the relationship between the horizontal and vertical positions. Once any horizontal position is determined, the corresponding vertical position can be determined based on the fitted curve equation.

[0036] Optionally, the following trajectory is fitted with a cubic curve using the least squares method to obtain the fitted curve equation corresponding to the following trajectory.

[0037] For example, constructing the equation of the fitted curve. Construct a matrix based on the cubic fitting curve. ,in, It is the vector of the polynomial system to be found, that is as well as . It is A dimensional matrix, containing data points. Using the least squares method, the sum of squared residuals is minimized. The formula for calculating the sum of squared residuals is: .in, Follow the lateral position of any point in the trajectory. for Calculate based on the fitted curve equation The result obtained, To follow the trajectory The corresponding vertical position. According to... and following trajectory pairs Solving for the problem yields the following results: as well as Thus, the equation of the fitted curve is obtained.

[0038] Step 105: Based on the fitted curve equation, control the steering wheel angle of the vehicle so that the vehicle follows the target vehicle along the following trajectory.

[0039] Optionally, based on the fitted curve equation, multiple lateral positions and multiple longitudinal positions corresponding to the multiple lateral positions are determined, which are multiple fitted trajectory points. Based on the multiple fitted trajectory points, the heading angle, curvature, and rate of change of curvature between the multiple fitted trajectory points are determined. Based on the heading angle, curvature, and rate of change of curvature, the steering wheel angle of the vehicle is determined by the lateral controller. The steering wheel of the vehicle is controlled by the steering wheel angle so that the vehicle follows the target vehicle along the following trajectory.

[0040] In this embodiment, during the vehicle's operation, the vehicle acquires the pose information of multiple vehicles ahead based on the perception data of surrounding obstacles collected by the vehicle's perception module. Based on the pose information of these vehicles, a target vehicle to be followed is determined. A following trajectory for the vehicle is planned based on the target vehicle's pose information and its historical trajectory points. Curve fitting is performed on the following trajectory to obtain the corresponding fitted curve equation. The steering wheel of the vehicle is then controlled according to the fitted curve equation, enabling the vehicle to follow the target vehicle along the following trajectory. This application acquires the pose information of multiple vehicles ahead through a fusion perception module and combines it with the target vehicle's historical trajectory points for intelligent filtering and trajectory planning. This fully utilizes the advantages of multi-sensor fusion, improving the accuracy and robustness of target recognition, avoiding interference from complex traffic environments, enhancing path predictability and smoothness by introducing historical trajectory information, generating a smooth fitted curve equation using curve fitting, and achieving precise control of the steering wheel angle based on its geometric features, thereby improving the response speed of lateral control and driving stability. It achieves automatic following in congested scenarios, improving driving safety and comfort.

[0041] Based on the above embodiments, the perception module includes multiple sensors, and the perception data of surrounding obstacles includes multiple perception data. Therefore, this application also provides a process for determining pose information in a vehicle congestion assist following method. Figure 2 This is a flowchart illustrating the process of determining pose information in a vehicle congestion assist following method provided in this application embodiment, as shown below. Figure 2 As shown, in step 101 above, based on the perception data of surrounding obstacles collected by the vehicle's onboard perception module, the position and pose information of multiple vehicles ahead among the surrounding obstacles is obtained, including: Step 201: Fuse multiple perception data of the same obstacle among surrounding obstacles to obtain multiple perception data of vehicles ahead.

[0042] The various sensors can include: cameras, millimeter-wave radar, lidar, ultrasonic radar, and global navigation satellite systems. Correspondingly, the various sensing data can include: target bounding boxes and labels in images captured by cameras; target relative distance, relative velocity, azimuth, and reflection intensity acquired by millimeter-wave radar; 3D point cloud clusters, target bounding boxes, center coordinates, length, width, height, and point cloud velocity acquired by lidar; and distance information to nearby obstacles acquired by ultrasonic radar.

[0043] Optionally, multiple perception data of the same obstacle among surrounding obstacles are fused using a fusion algorithm based on data acquisition time and location information to obtain perception data for each obstacle among the surrounding obstacles. Obstacles labeled as "motor vehicles" are identified from the surrounding obstacles as the vehicle in front, and perception data for the vehicle in front is determined.

[0044] Step 202: Based on the perception data of multiple vehicles ahead, obtain the pose information of multiple vehicles ahead.

[0045] Among them, the pose information is the pose information of the vehicle in front relative to the vehicle itself.

[0046] Optionally, the pose information of multiple vehicles ahead is determined based on the perception data of these vehicles and the vehicle's pose information. The vehicle's pose information is determined using inertial sensors and accelerometers installed on the vehicle.

[0047] In this embodiment of the application, by fusing multiple perception data from different sensors on the same obstacle, the advantages of sensors such as cameras, millimeter-wave radar, and lidar can be effectively integrated, overcoming the limitations of a single sensor in complex environments and improving the accuracy and robustness of target detection.

[0048] Based on the above embodiments, the pose information of the vehicle ahead includes: lateral offset information, driving direction information, longitudinal distance information, and longitudinal speed information. Therefore, this application also provides a process for determining the target vehicle in a vehicle congestion assist following method. Figure 3 This application provides a schematic diagram of the process for determining a target vehicle in a vehicle congestion assist following method, as illustrated in the embodiments of this application. Figure 3 As shown, in step 102 above, determining the target vehicle to be followed from the plurality of vehicles ahead based on their pose information includes: Step 301: Based on the lateral offset information of multiple vehicles ahead, determine the first candidate vehicle that meets the lateral offset threshold from the multiple vehicles ahead.

[0049] The lateral offset information refers to the lateral offset of the vehicle in front relative to the vehicle itself. This lateral offset is determined based on the lateral position of the vehicle in front and the lateral position of the vehicle itself. The lateral offset threshold is determined based on the lane width and the vehicle's trajectory, and is generally a set value.

[0050] Optionally, the lateral offset information of multiple vehicles ahead is compared with a lateral offset threshold. If the lateral offset information of the vehicles ahead is less than the lateral offset threshold, it is determined that the vehicles ahead meet the lateral offset threshold. Then, the first candidate vehicle that meets the lateral offset threshold is determined from the multiple vehicles ahead.

[0051] Step 302: Based on the driving direction information of the first candidate vehicle, determine the second candidate vehicle that is in the same driving direction as the vehicle from the first candidate vehicles.

[0052] Among them, the driving direction information is the vehicle's heading angle information.

[0053] Step 303: Based on the longitudinal distance information of the second candidate vehicle, determine the third candidate vehicle that meets the longitudinal distance threshold from the second candidate vehicle.

[0054] The longitudinal distance information refers to the longitudinal distance between the second candidate vehicle and the vehicle itself. The longitudinal distance threshold can be determined based on the vehicle's current speed and the speed limit of the current road segment.

[0055] Optionally, the longitudinal distance information of the second candidate vehicle is compared with the longitudinal distance threshold. If the longitudinal distance information of the second candidate vehicle is less than the longitudinal distance threshold, it is determined that the longitudinal distance threshold is met, and a third candidate vehicle that meets the longitudinal distance threshold is determined from the second candidate vehicle.

[0056] Step 304: Based on the longitudinal speed information of the third candidate vehicle, determine the vehicle that meets the longitudinal speed threshold from the third candidate vehicle as the target vehicle.

[0057] The longitudinal speed information refers to the speed of the vehicle in front relative to the vehicle itself. The longitudinal speed threshold is determined based on the current road speed limit and the vehicle's safe speed.

[0058] Optionally, if a preceding vehicle with a longitudinal speed less than the longitudinal speed threshold is determined based on the longitudinal speed information of the third candidate vehicle, then, in order to satisfy the vehicle longitudinal speed threshold, a vehicle that satisfies the vehicle longitudinal speed threshold is selected from the third candidate vehicles as the target vehicle.

[0059] In this embodiment, a progressive judgment logic based on lateral offset, driving direction, longitudinal distance, and longitudinal speed is used to filter out irrelevant or abnormal vehicles layer by layer, achieving accurate and stable identification of the optimal following target in a multi-vehicle environment. Especially in urban scenarios with traffic congestion, dense lanes, and complex traffic flow, there may be situations where lane lines cannot be determined. However, the method in this application can still quickly lock onto the leading vehicle in the same lane as the vehicle, enhancing the safety and smoothness of the assisted driving system.

[0060] Based on the above embodiments, this application also provides a process for determining the following trajectory in a vehicle congestion assist following method. Figure 4 This is a flowchart illustrating the process of determining the following trajectory in a vehicle congestion-assisted following method provided in an embodiment of this application, as shown below. Figure 4 As shown, in step 103 above, based on the target vehicle's pose information and historical trajectory points, the vehicle plans its following trajectory for the target vehicle, including: Step 401: Based on the current position of the vehicle, the current position of the target vehicle, and historical trajectory points, divide the longitudinal region between the vehicle and the target vehicle to obtain the first region and the second region.

[0061] The first area is the area closest to the target vehicle, and the second area is the area closest to the vehicle itself.

[0062] Optionally, the lower longitudinal boundary of the second region is determined based on the longitudinal position of the current location of the vehicle, the upper longitudinal boundary of the first region is determined based on the longitudinal position of the current location of the target vehicle, and the lower longitudinal boundary of the first region and the lower longitudinal boundary of the second region are determined based on the longitudinal position of the starting position of the historical trajectory point of the target vehicle. The lower longitudinal boundary of the first region and the lower longitudinal boundary of the second region are at the same location.

[0063] Step 402: Based on the historical trajectory points of the target vehicle, predict the trajectory of the target vehicle to obtain the first planned trajectory of the vehicle in the first area.

[0064] The first area is the region where the historical trajectory points of the target vehicle are located.

[0065] Optionally, the latest position of the target vehicle is predicted based on its historical trajectory points to obtain a first planned trajectory for the vehicle in the first area. The first planned trajectory includes the historical trajectory points of the target vehicle and the predicted latest position of the target vehicle.

[0066] Step 403: Based on the first planned trajectory, perform trajectory planning for the second region to obtain the second planned trajectory of the vehicle in the second region.

[0067] Optionally, the vehicle determines a second planned trajectory in a second area with the same rate of change as the first planned trajectory in the first area, so that the rates of change of the first and second planned trajectories are the same, thereby improving the stability of the vehicle.

[0068] Step 404: Obtain the following trajectory based on the first planned trajectory and the second planned trajectory.

[0069] Optionally, the first planned trajectory and the second planned trajectory are spliced ​​together according to the starting position of the first planned trajectory and the ending position of the second planned trajectory to obtain the following trajectory.

[0070] In this embodiment, by combining the current positions of the autonomous vehicle and the target vehicle, as well as the target vehicle's historical trajectory, the longitudinal space is divided, and differentiated trajectory planning is performed for each region, improving the rationality and safety of path planning. The first region, closer to the target vehicle, performs predictive trajectory planning based on its movement trend, enhancing adaptability to the behavior of the vehicle ahead; while the second region, closer to the autonomous vehicle, is collaboratively optimized based on the planning results of the first region, ensuring the continuity and smoothness of the entire vehicle trajectory. This improves the responsiveness of the autonomous driving system in dynamic environments and reduces the occurrence of uncomfortable driving behaviors such as sudden acceleration and braking, thus enhancing ride comfort and driving safety.

[0071] Based on the above embodiments, this application also provides a process for determining the first planned trajectory in a vehicle congestion assist following method. Figure 5 This is a flowchart illustrating the process of determining a first planned trajectory in a vehicle congestion assist following method provided in an embodiment of this application, as shown below. Figure 5 As shown, in step 402 above, the trajectory of the target vehicle is predicted based on its historical trajectory points to obtain the first planned trajectory of the vehicle in the first area, including: Step 501: Obtain the trajectory change rate of the target vehicle based on historical trajectory points.

[0072] The historical trajectory points include a set of horizontal trajectory points and a set of vertical trajectory points.

[0073] Optionally, the trajectory change rate of multiple adjacent trajectory points is calculated based on the adjacent trajectory points in the historical trajectory points, and the trajectory change rate of the target vehicle is determined based on the average of the trajectory change rates of multiple adjacent trajectory points.

[0074] For example, if the historical trajectory points include n trajectory points, then the trajectory change rate can be calculated using the trajectory change rate formula based on the n-1 trajectory points. .in, The rate of change of the trajectory. For historical trajectory points The vertical position of the point For historical trajectory points The vertical position of the point For historical trajectory points The horizontal position of the point For historical trajectory points The horizontal position of the point.

[0075] Step 502: Based on the trajectory change rate and the current position of the target vehicle, predict the trajectory of the target vehicle to obtain the first planned trajectory.

[0076] The target vehicle's current position includes both lateral and longitudinal observation positions.

[0077] Optionally, the current predicted position of the target vehicle is determined by the trajectory change rate, the lateral and longitudinal observation positions of the target vehicle's current position, and the position of the previous trajectory point in the historical trajectory points. The current predicted position includes the current longitudinal predicted position and the current lateral observation position. The calculated current predicted position result is placed at the end of the historical trajectory point container, i.e., the nth position. The container follows a first-in-first-out rule for trajectory updates. The set of trajectory points in the historical trajectory point container is used as the first planned trajectory.

[0078] For example, the rate of change of the trajectory Lateral observation position of the target vehicle's current location And the horizontal position of the previous trajectory point in the historical trajectory points. and vertical position Based on a preset prediction formula, the current longitudinal predicted position of the target vehicle is determined. .

[0079] In this embodiment, the trajectory change rate is calculated based on the historical trajectory points of the target vehicle, and trajectory prediction is performed in combination with the current position. This can more accurately reflect the dynamic motion trend of the target vehicle. Introducing the trajectory change rate can capture the acceleration and direction change characteristics of the vehicle's motion, thereby improving the foresight and reliability of the predicted trajectory.

[0080] Based on the above embodiments, this application also provides a process for determining the second planned trajectory in a vehicle congestion assist following method. Figure 6 This is a flowchart illustrating the process of determining a second planned trajectory in a vehicle congestion assist following method provided in an embodiment of this application, as shown below. Figure 6 As shown, before performing trajectory planning for the second region based on the first planned trajectory in step 403 above to obtain the second planned trajectory of the vehicle in the second region, the method further includes: Step 601: Perform Kalman filtering on the first planned trajectory.

[0081] Optionally, calculate the prior error covariance. The Kalman gain is calculated based on the prior error covariance. .in, Let be the posterior error covariance matrix. Let be the prior error covariance matrix. R is the process noise covariance matrix, and R is the measurement noise covariance matrix, which is determined based on sensor parameters and vehicle parameters.

[0082] Optionally, the current longitudinal predicted position in the first planned trajectory Based on the current longitudinal prediction position and Kalman gain Perform Kalman filtering to obtain the current predicted target position. The current target's predicted position is then placed at the very end of the historical trajectory point container, i.e., the nth position. The container follows a first-in-first-out rule for trajectory updates.

[0083] In step 403 above, trajectory planning is performed on the second region based on the first planned trajectory to obtain the second planned trajectory of the vehicle in the second region, including: Step 602: Based on the filtered first planned trajectory, perform trajectory planning for the second region to obtain the second planned trajectory of the vehicle in the second region.

[0084] Optionally, the trajectory change rate of the filtered first planned trajectory is determined based on the filtered first planned trajectory, and trajectory planning is performed on the second region based on the trajectory change rate of the filtered first planned trajectory to obtain the second planned trajectory of the vehicle in the second region, such that the trajectory change rate of the second planned trajectory is the same as the trajectory change rate of the filtered first planned trajectory.

[0085] In this embodiment, Kalman filtering is applied to the first planned trajectory to suppress noise and jitter in trajectory prediction, improving trajectory smoothness and prediction accuracy. Based on this, trajectory planning for the second region is performed, making the vehicle's driving path in the region close to itself not only more stable and continuous, but also more accurately responding to the dynamic behavior of the vehicle in front. This avoids frequent acceleration / deceleration or trajectory oscillation caused by fluctuations in the original predicted trajectory, thereby improving driving comfort and safety.

[0086] Based on the above embodiments, this application also provides a process for determining the second planned trajectory in a vehicle congestion assist following method. Figure 7 This is a flowchart illustrating the process of determining a second planned trajectory in a vehicle congestion assist following method provided in an embodiment of this application, as shown below. Figure 7 As shown, in step 602 above, trajectory planning is performed on the second region based on the first planned trajectory to obtain the second planned trajectory of the vehicle in the second region, including: Step 701: Based on the first planned trajectory, obtain the rate of change of the planned trajectory of the first planned trajectory.

[0087] Optionally, the trajectory change rate of multiple adjacent trajectory points is calculated based on the adjacent trajectory points in the first planned trajectory, and the planned trajectory change rate is determined based on the average of the trajectory change rates of multiple adjacent trajectory points.

[0088] For example, if the first planned trajectory includes n trajectory points, then the rate of change of the planned trajectory is calculated based on a total of n trajectory points. .

[0089] Step 702: Based on the planned trajectory change rate and the current position of the vehicle, predict the trajectory of the vehicle to obtain the second planned trajectory.

[0090] Optionally, based on the vehicle's current position and the second region, the lateral distance of the second region is evenly divided to obtain multiple lateral coordinates with equal distances. Based on these multiple lateral coordinates with equal distances and the planned trajectory change rate... This yields multiple vertical coordinates corresponding to multiple horizontal coordinates.

[0091] For example, based on the i-th horizontal coordinate Based on the preset trajectory calculation formula, the i-th vertical coordinate corresponding to the i-th horizontal coordinate is obtained. .

[0092] In this embodiment, by extracting the trajectory change rate of the first planned trajectory and combining it with the vehicle's current position for trajectory prediction, the second planned trajectory can fully inherit the dynamic characteristics of the preceding vehicle's movement trend, thereby achieving smooth connection and behavioral consistency between the trajectories of the preceding and following areas. This enhances the vehicle's adaptability to the traffic situation ahead, avoids abrupt changes or discontinuities between local planned segments, improves the overall drivability and comfort of the trajectory, and enhances the response accuracy and stability of the autonomous driving system in complex dynamic environments.

[0093] Based on the above embodiments, this application also provides a process for determining the fitted curve equation in a vehicle congestion assist following method. Figure 8 This is a flowchart illustrating the process of determining the fitted curve equation in a vehicle congestion assist following method provided in this application embodiment, as shown below. Figure 8 As shown, before performing curve fitting on the following trajectory in step 105 above to obtain the fitted curve equation corresponding to the following trajectory, the method further includes: Step 801: Obtain the current attitude information and current acceleration information of the vehicle.

[0094] The current attitude information is determined based on inertial sensors installed on the vehicle. Acceleration information is determined using accelerometers installed on the vehicle. The current attitude information includes the vehicle's roll angle, pitch angle, and yaw angle.

[0095] Optionally, inertial sensors and accelerometers can be installed on the vehicle to obtain the vehicle's current attitude and current acceleration information.

[0096] Step 802: Based on the vehicle's current attitude information and current acceleration information, obtain the predicted attitude change information of the vehicle.

[0097] The predicted attitude change information includes: lateral displacement change information, longitudinal displacement change information, and heading angle change information.

[0098] Optionally, the trajectory of the bicycle can be predicted based on a preset bicycle model according to the current attitude information and current acceleration information of the bicycle, so as to obtain the predicted attitude change information of the bicycle.

[0099] Step 803: Based on the predicted attitude change information, perform motion compensation on the following trajectory to obtain the compensated following trajectory.

[0100] Optionally, motion compensation is performed on the lateral and longitudinal trajectory points in the following trajectory based on the predicted attitude change information to obtain the compensated following trajectory.

[0101] For example, based on the predicted attitude change information, motion compensation is performed on the lateral trajectory points in the following trajectory to obtain multiple compensated lateral trajectory points in the compensated following trajectory. .

[0102]

[0103] in, To compensate for the horizontal trajectory points, To follow the horizontal trajectory points in the trajectory. For heading angle change information, To follow the vertical trajectory points in the trajectory, This provides information on lateral displacement changes.

[0104] For example, based on the predicted attitude change information, motion compensation is performed on the longitudinal trajectory points in the following trajectory to obtain multiple compensated longitudinal trajectory points in the compensated following trajectory. .

[0105]

[0106] in, To compensate for longitudinal trajectory points, To follow the horizontal trajectory points in the trajectory. For heading angle change information, To follow the vertical trajectory points in the trajectory, This provides information on longitudinal displacement changes.

[0107] In step 105 above, curve fitting is performed on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory, including: Step 804: Perform curve fitting on the compensated following trajectory to obtain the fitted curve equation.

[0108] In this embodiment, by combining the vehicle's current attitude information and acceleration information, its short-term motion trend is accurately predicted, and motion compensation is performed on the original following trajectory. This effectively eliminates the trajectory deviation caused by vehicle dynamic response delay or attitude change. Curve fitting is performed on the compensated trajectory to obtain a smooth, continuous fitting curve equation that conforms to the actual motion capability of the vehicle, thereby improving the executability of the trajectory and driving comfort.

[0109] Based on the same inventive concept, this application also provides a vehicle congestion assist following device corresponding to the vehicle congestion assist following method. Since the principle of the device in this application is similar to the vehicle congestion assist following method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0110] Figure 9 This is a schematic diagram of the structure of a vehicle congestion assist following device provided in an embodiment of this application, as shown below. Figure 9 The device includes: The acquisition module 901 is used to acquire the position and pose information of multiple vehicles ahead in the surrounding obstacles based on the perception data of the surrounding obstacles collected by the perception module on the vehicle during the driving process. The determination module 902 is used to determine the target vehicle to be followed from multiple vehicles ahead based on the pose information of multiple vehicles ahead. The planning module 903 is used to plan the following trajectory of the vehicle for the target vehicle based on the pose information of the target vehicle and the historical trajectory points of the target vehicle. The fitting module 904 is used to perform curve fitting on the following trajectory to obtain the fitting curve equation corresponding to the following trajectory. The control module 905 is used to control the steering wheel angle of the vehicle according to the fitted curve equation, so that the vehicle follows the target vehicle along the following trajectory.

[0111] In one possible implementation, the perception module includes: multiple sensors, and the perception data of surrounding obstacles includes: multiple perception data; the acquisition module 901 is specifically used to: fuse multiple perception data of the same obstacle in the surrounding obstacles to obtain multiple perception data of the vehicle in front; Based on the perception data of multiple vehicles ahead, the position and pose information of multiple vehicles ahead is obtained respectively.

[0112] In one possible implementation, the pose information of the vehicle in front includes: lateral offset information, driving direction information, longitudinal distance information, and longitudinal speed information; the determination module 902 is specifically used to: determine a first candidate vehicle that meets the lateral offset threshold from the multiple vehicles in front based on the lateral offset information of the multiple vehicles in front. Based on the driving direction information of the first candidate vehicle, a second candidate vehicle with the same driving direction as the vehicle is determined from the first candidate vehicle. Based on the longitudinal distance information of the second candidate vehicles, a third candidate vehicle that meets the longitudinal distance threshold is determined from the second candidate vehicles. Based on the longitudinal speed information of the third candidate vehicle, the vehicle that meets the longitudinal speed threshold is selected as the target vehicle from the third candidate vehicle.

[0113] In one possible implementation, the planning module 903 is specifically used to: divide the longitudinal region between the self-vehicle and the target vehicle according to the current position of the self-vehicle, the current position of the target vehicle, and historical trajectory points to obtain a first region and a second region; wherein, the first region is the region closer to the target vehicle, and the second region is the region closer to the self-vehicle. Based on the historical trajectory points of the target vehicle, the trajectory of the target vehicle is predicted to obtain the first planned trajectory of the vehicle in the first area. Based on the first planned trajectory, trajectory planning is performed on the second region to obtain the second planned trajectory of the vehicle in the second region; Based on the first and second planned trajectories, the following trajectory is obtained.

[0114] In one possible implementation, the planning module 903 is specifically used to: obtain the trajectory change rate of the target vehicle based on historical trajectory points; Based on the trajectory change rate and the current position of the target vehicle, the trajectory of the target vehicle is predicted to obtain the first planned trajectory.

[0115] In one possible implementation, the planning module 903 is specifically used to: perform Kalman filtering on the first planned trajectory; and perform trajectory planning on the second region based on the filtered first planned trajectory to obtain the second planned trajectory of the vehicle in the second region.

[0116] In one possible implementation, the planning module 903 is specifically used to: obtain the rate of change of the planning trajectory of the first planning trajectory based on the first planning trajectory; Based on the rate of change of the planned trajectory and the current position of the vehicle, the trajectory of the vehicle is predicted to obtain the second planned trajectory.

[0117] In one possible implementation, the fitting module 904 is specifically used to: acquire the current attitude information and current acceleration information of the vehicle; Based on the vehicle's current attitude information and current acceleration information, obtain the vehicle's predicted attitude change information; Based on the predicted attitude change information, motion compensation is performed on the following trajectory to obtain the compensated following trajectory; curve fitting is then performed on the compensated following trajectory to obtain the fitted curve equation.

[0118] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0119] This application also provides an auxiliary driving control device. Figure 10 This is a schematic diagram of the structure of an assisted driving control device provided in an embodiment of this application, such as... Figure 10 As shown, it includes a processor 1001 and a memory 1002, and optionally, a bus 1003. The memory 1002 stores machine-readable instructions executable by the processor 1001. When the driver assistance control device 1000 is running, the processor 1001 and the memory 1002 communicate via the bus 1003. When the machine-readable instructions are executed by the processor 1001, the steps of the aforementioned vehicle congestion assist following method are performed. The driver assistance control device 1000 can be a vehicle controller, a driver assistance controller independent of the vehicle controller, or a vehicle control device in the cloud; this embodiment does not impose any limitations on these aspects.

[0120] Another embodiment of this application also includes a vehicle. Figure 11 This application provides a schematic diagram of the structure of a vehicle, as shown in the embodiment of the present application. Figure 11 As shown, the vehicle also includes: a vehicle body 1101 and an auxiliary driving control device 1000 disposed on the vehicle body, the auxiliary driving control device 1000 being used to perform the steps of the above-described vehicle congestion assist following method.

[0121] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described vehicle congestion assist following method.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0123] Furthermore, the functional units in the various embodiments of this application 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. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a 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 this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0124] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A vehicle congestion-assisted following method, characterized in that, The method includes: During the driving process of the vehicle, the position and pose information of multiple vehicles ahead in the surrounding obstacles is obtained based on the perception data of the surrounding obstacles collected by the perception module on the vehicle. Based on the pose information of multiple vehicles ahead, determine the target vehicle to be followed from among the multiple vehicles ahead; Based on the current position of the vehicle, the current position of the target vehicle, and the historical trajectory points of the target vehicle, the longitudinal region between the vehicle and the target vehicle is divided into a first region and a second region; wherein, the first region is the region closer to the target vehicle, and the second region is the region closer to the vehicle. Based on the historical trajectory points, obtain the trajectory change rate of the target vehicle; Based on the trajectory change rate and the current position of the target vehicle, the trajectory of the target vehicle is predicted to obtain the first planned trajectory; Based on the first planned trajectory, trajectory planning is performed on the second area to obtain the second planned trajectory of the vehicle in the second area; Based on the first planned trajectory and the second planned trajectory, the following trajectory of the target vehicle is obtained; Perform curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory; Based on the fitted curve equation, the steering wheel of the vehicle is controlled to turn, so that the vehicle follows the target vehicle along the following trajectory.

2. The method according to claim 1, characterized in that, The sensing module includes multiple sensors, and the sensing data of the surrounding obstacles includes multiple sensing data. The step of obtaining the pose information of multiple vehicles ahead among the surrounding obstacles based on the perception data of the surrounding obstacles collected by the on-vehicle perception module includes: Multiple perception data of the same obstacle in the surrounding obstacles are fused to obtain multiple perception data of the vehicle in front; Based on the perception data of multiple vehicles ahead, the pose information of multiple vehicles ahead is obtained respectively.

3. The method according to claim 1, characterized in that, The position and pose information of the vehicle ahead includes: lateral offset information, driving direction information, longitudinal distance information, and longitudinal speed information; The step of determining the target vehicle to be followed from the plurality of vehicles ahead based on their pose information includes: Based on the lateral offset information of multiple vehicles ahead, a first candidate vehicle that meets the lateral offset threshold is determined from the multiple vehicles ahead; Based on the driving direction information of the first candidate vehicle, a second candidate vehicle that is consistent with the driving direction of the vehicle is determined from the first candidate vehicle; Based on the longitudinal distance information of the second candidate vehicles, a third candidate vehicle that meets the longitudinal distance threshold is determined from the second candidate vehicles. Based on the longitudinal speed information of the third candidate vehicle, a vehicle that meets the longitudinal speed threshold is selected from the third candidate vehicle as the target vehicle.

4. The method according to claim 1, characterized in that, Before performing trajectory planning on the second region based on the first planned trajectory to obtain the second planned trajectory of the vehicle in the second region, the method further includes: Perform Kalman filtering on the first planned trajectory; The step of planning a trajectory for the second region based on the first planned trajectory to obtain a second planned trajectory for the vehicle in the second region includes: Based on the filtered first planned trajectory, trajectory planning is performed on the second region to obtain the second planned trajectory of the vehicle in the second region.

5. The method according to claim 1, characterized in that, The step of planning a trajectory for the second region based on the first planned trajectory to obtain a second planned trajectory for the vehicle in the second region includes: Based on the first planned trajectory, obtain the rate of change of the planned trajectory of the first planned trajectory; Based on the planned trajectory change rate and the current position of the vehicle, the trajectory of the vehicle is predicted to obtain the second planned trajectory.

6. The method according to claim 1, characterized in that, Before performing curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory, the method further includes: Obtain the current attitude information and current acceleration information of the vehicle; Based on the vehicle's current attitude information and current acceleration information, the predicted attitude change information of the vehicle is obtained; Based on the predicted attitude change information, motion compensation is performed on the following trajectory to obtain the compensated following trajectory; The step of performing curve fitting on the following trajectory to obtain the fitted curve equation corresponding to the following trajectory includes: The compensated following trajectory is subjected to curve fitting to obtain the equation of the fitted curve.

7. A driver assistance control device, characterized in that, The driver assistance control device includes a processor and a memory, the memory storing machine-readable instructions executable by the processor. When the computer device is running, the processor executes the machine-readable instructions to perform the steps of the vehicle congestion assist following method as described in any one of claims 1 to 6.

8. A vehicle, characterized in that, The vehicle includes at least: a vehicle body and an auxiliary driving control device disposed on the vehicle body, the auxiliary driving control device being used to perform the steps of the vehicle congestion assist following method as described in any one of claims 1 to 6.

Images