A vehicle control method, readable storage medium, program product and vehicle-mounted device

Abstract

The application relates to the technical field of assisted driving, in particular to a vehicle control method, a readable storage medium, a program product and a vehicle-mounted device. The vehicle control method comprises the following steps: detecting that a road condition of a driving road where a target vehicle is located meets a preset road condition; determining N candidate cruise targets of the target vehicle, and predicting motion trajectories of the candidate cruise targets within a preset time period; selecting at least one candidate cruise target meeting a preset cruise condition based on the motion trajectories of the candidate cruise targets and a motion trajectory of the target vehicle within the preset time period; determining a cruise target of the target vehicle from the N candidate cruise targets based on the at least one selected candidate cruise target; and controlling the target vehicle to drive based on the cruise target of the target vehicle. In this way, the best cruise target can be accurately identified when driving in a road condition without clear lane lines or wide lanes, and driving safety can be ensured.

Description

Technical Field

[0001] This application relates to the field of driver assistance technology, and in particular to a vehicle control method, a readable storage medium, a program product, and an in-vehicle device. Background Technology

[0002] Adaptive cruise control (ACC) is one of the core functions of advanced driver-assistance systems (ADAS) and is widely used in modern vehicles. Traditional ACC mainly relies on sensing the lane markings in front of the target vehicle to determine the "current lane." Then, within that lane, based on relative distance and speed, it identifies dynamic obstacles (such as other vehicles) as cruise targets and automatically adjusts the target vehicle's speed accordingly to maintain a safe distance, thereby ensuring driving safety.

[0003] However, in some complex road scenarios (such as intersections, roundabouts, roads without clear lane lines, and wide-lane roads), the lack of reliable lane line information (lane lines may be blurred or disappear) makes it difficult for traditional ACC to accurately determine the target vehicle's "current lane". This can lead to the system failing to accurately identify or losing the cruise target, or misjudging dynamic obstacles in other lanes as the cruise target, causing the target vehicle to accelerate or decelerate unnecessarily, thus affecting driving safety. Summary of the Invention

[0004] This application provides a vehicle control method, a readable storage medium, a program product, and an in-vehicle device that enables the ACC function to accurately identify the optimal cruise target and ensure driving safety when driving in road conditions such as the absence of clear lane markings or wide lanes.

[0005] In a first aspect, this application provides a vehicle control method, the method comprising: detecting that the road conditions of the road on which the target vehicle is traveling meet preset road condition conditions; determining N candidate cruise targets for the target vehicle and predicting the movement trajectory of each candidate cruise target within a preset time period; selecting at least one candidate cruise target that meets preset cruise conditions based on the movement trajectory of each candidate cruise target and the movement trajectory of the target vehicle within the preset time period; determining the cruise target of the target vehicle from the N candidate cruise targets based on the selected at least one candidate cruise target; and controlling the target vehicle to drive based on the cruise target of the target vehicle.

[0006] In some embodiments of this application, the target vehicle may refer to a self-driving vehicle.

[0007] Based on the aforementioned vehicle control method, this paper effectively solves the problem of inaccurate target identification, misjudgment, or loss of cruise targets caused by the reliance on lane lines in complex scenarios such as intersections, roundabouts, wide lanes, and roads without lane lines, which is often due to the traditional adaptive cruise control system. This application introduces a candidate cruise target trajectory prediction and evaluation mechanism, selecting the most reasonable cruise target from multiple candidate targets based on preset cruise conditions. This ensures that the vehicle can stably and safely adaptively follow the cruise target, significantly improving the applicability, safety, and smoothness of the ACC system in scenarios such as intersections, roundabouts, wide lanes, and roads without lane lines.

[0008] In one possible implementation of the first aspect above, when the adaptive cruise control function of the target vehicle is activated, it is detected whether the road conditions of the road on which the target vehicle is traveling meet preset road condition conditions, wherein the preset road condition conditions include at least one of the following: the target vehicle is traveling to an intersection, roundabout, or wide lane; the target vehicle is traveling to a section of road without clear lane markings.

[0009] It is understood that the preset road conditions in the embodiments of this application are merely illustrative. In other embodiments of this application, the preset road conditions may also include the target vehicle traveling to other road sections without clear lanes, such as rural roads. This application does not specifically limit this.

[0010] In one possible implementation of the first aspect above, determining N candidate cruise targets for the target vehicle includes: determining the drivable area of ​​the target vehicle within a preset time period based on road structure information and the location information of the target vehicle provided by a high-precision map; and determining N candidate cruise targets located within the drivable area based on the perception data of the target vehicle.

[0011] In some embodiments of this application, N candidate cruise targets for a target vehicle can be determined based on different road structure information. As an example, when the target vehicle is traveling on a structured road with clear lane markings (e.g., a highway), the onboard device can identify the lane the target vehicle is in and identify vehicles ahead of it in the same lane as the target vehicle as N candidate cruise targets. As another example, when the target vehicle is traveling on a road without clear lane markings (e.g., rural roads, construction zones, or some old urban roads), the onboard device cannot rely on lane marking information. In this case, the onboard device can determine the drivable area of ​​the target vehicle based on road structure information provided by a high-precision map and the target vehicle's location information. This drivable area can be defined by static elements such as road boundaries and obstacle boundaries. Simultaneously, the onboard device can also dynamically correct and complete the boundaries of the drivable area by integrating real-time perception data (such as camera and radar perception results). Based on this, the onboard device can identify all traffic participants (e.g., other vehicles) located ahead of the target vehicle and traveling in the same direction as the target vehicle within this drivable area as N candidate cruise targets.

[0012] In one possible implementation of the first aspect above, the preset cruise conditions include: when the target vehicle is traveling to an intersection, roundabout, or on a road segment without a clear lane, the trajectory overlap between the candidate cruise target and the target vehicle within a preset time period is greater than or equal to a trajectory overlap threshold; when the target vehicle is traveling on a wide lane and the candidate cruise target and the target vehicle have overlapping trajectories within a preset time period, the lateral overlap rate between the candidate cruise target and the target vehicle in the overlapping trajectories is greater than or equal to a lateral overlap rate threshold.

[0013] It is understood that the trajectory overlap threshold and the lateral overlap rate threshold can be preset parameter values. For example, the trajectory overlap threshold and the lateral overlap rate threshold can be 90% and 70%, respectively. In practical applications, they can be adjusted and optimized within a certain range (such as trajectory overlap threshold of 80%~95% and lateral overlap rate threshold of 50%~80%). This application does not make specific limitations on this.

[0014] In one possible implementation of the first aspect above, determining the cruise target of the target vehicle from N candidate cruise targets based on at least one selected candidate cruise target includes: determining a primary candidate cruise target and a secondary candidate cruise target from the N candidate cruise targets based on the distances between the N candidate cruise targets and the target vehicle, wherein the primary candidate cruise target has the smallest distance to the target vehicle among the N candidate cruise targets, and the secondary candidate cruise target has the second largest distance to the target vehicle among the N candidate cruise targets; and determining the primary candidate cruise target as the cruise target of the target vehicle if the primary candidate cruise target meets preset cruise conditions.

[0015] In one possible implementation of the first aspect above, determining the cruise target of the target vehicle from N candidate cruise targets based on at least one selected candidate cruise target further includes: determining the secondary candidate cruise target as the cruise target of the target vehicle when the primary candidate cruise target does not meet the preset cruise conditions and the secondary candidate cruise target meets the preset cruise conditions.

[0016] In one possible implementation of the first aspect above, determining the cruise target of the target vehicle from N candidate cruise targets based on at least one selected candidate cruise target further includes: when neither the primary candidate cruise target nor the secondary candidate cruise target satisfies the preset cruise conditions, selecting the candidate cruise target that satisfies the preset cruise conditions from among the candidate cruise targets other than the primary candidate cruise target and the secondary candidate cruise target from the N candidate cruise targets as the cruise target.

[0017] In one possible implementation of the first aspect above, the method for determining the trajectory of the target vehicle within a preset time period includes: acquiring the longitudinal velocity and yaw rate of the target vehicle; inputting the longitudinal velocity and yaw rate of the target vehicle into a trajectory prediction model to obtain the trajectory of the target vehicle within the preset time period.

[0018] In one possible implementation of the first aspect above, the longitudinal velocity and yaw rate of the target vehicle are input into the motion trajectory prediction model to obtain the motion trajectory of the target vehicle within a preset time period, including: calculating the target curvature of the target vehicle based on the longitudinal velocity and yaw rate of the target vehicle, and calculating the radius of the arc corresponding to the target curvature based on the target curvature; calculating the pose of the target vehicle at each predicted time point within the preset time period based on the radius of the arc corresponding to the target curvature and the target curvature; and using the combination sequence of the poses of the target vehicle at each predicted time point within the preset time period as the motion trajectory of the target vehicle within the preset time period.

[0019] In one possible implementation of the first aspect described above, the target curvature of the target vehicle is calculated based on its longitudinal speed and yaw rate, and the radius of the arc corresponding to the target curvature is calculated based on the target curvature. This includes: for targets whose longitudinal speed is greater than or equal to a high-speed threshold, a reference curvature is calculated as the target curvature based on the target vehicle's yaw rate and longitudinal speed; for targets whose longitudinal speed is less than or equal to a low-speed threshold, a smoothed curvature is calculated as the target curvature based on a preset sampling time, a preset filtering time constant, a preset center offset coefficient, and the rear axle center curvature of the target vehicle; for targets whose longitudinal speed is greater than a low-speed threshold and less than a high-speed threshold, the target curvature is calculated based on the reference curvature, the smoothed curvature, and the center offset coefficient; the radius of the arc corresponding to the target curvature is the reciprocal of the target curvature.

[0020] In a second aspect, this application also provides an in-vehicle device, comprising: at least one memory and at least one processor, the memory being coupled to the processor; the one or more memories storing one or more programs; when the one or more memory programs are executed by the one or more processors, the in-vehicle device causes the in-vehicle device to perform the methods mentioned in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application also provides a vehicle that includes the vehicle-mounted equipment mentioned in the second aspect.

[0022] Fourthly, this application also provides a readable storage medium storing instructions that, when executed on an in-vehicle device, cause the in-vehicle device to perform the methods mentioned in the first aspect and any possible implementation thereof.

[0023] Fifthly, this application also provides a program product that, when run on an in-vehicle device, causes the in-vehicle device to perform the methods mentioned in the first aspect and any possible implementation thereof.

[0024] The beneficial effects of the second to fifth aspects mentioned above can be referred to the relevant descriptions in the first aspect and any possible implementation of the first aspect, which will not be repeated here. Attached Figure Description

[0025] Figure 1 According to an embodiment of this application, a schematic flowchart of a vehicle control method is shown.

[0026] Figure 2 According to an embodiment of this application, a logical architecture diagram of an adaptive cruise (ACC) target selection system is shown.

[0027] Figure 3 According to an embodiment of this application, a flowchart of another vehicle control method is shown.

[0028] Figure 4 According to an embodiment of this application, a structural schematic diagram of a vehicle 100 is shown. Detailed Implementation

[0029] The illustrative embodiments of this application include, but are not limited to, a vehicle control method, a readable storage medium, a program product, and an in-vehicle device.

[0030] It should be noted that the vehicle control method provided in this application embodiment can be applied to telematics devices, vehicle control units (VCUs), and advanced driver assistance systems (ADAS), etc.

[0031] As mentioned earlier, traditional ACC mainly relies on sensing the lane lines in front of the target vehicle to determine the "current lane". Then, within that lane, based on the relative distance and speed, it identifies dynamic obstacles (such as other vehicles) as cruise targets and automatically adjusts the speed of the target vehicle according to the cruise target to maintain a safe distance, thereby ensuring driving safety.

[0032] However, in some complex road scenarios (such as intersections, roundabouts, roads without clear lane lines, and wide-lane roads), the lack of reliable lane line information (lane lines may be blurred or disappear) makes it difficult for traditional ACC to accurately determine the target vehicle's "current lane". This can lead to the system failing to accurately identify or losing the cruise target, or misjudging dynamic obstacles in other lanes as the cruise target, causing the target vehicle to accelerate or decelerate unnecessarily, thus affecting driving safety.

[0033] To address the aforementioned problems, this application provides a vehicle control method, comprising: detecting that the road conditions on the road where the target vehicle is traveling meet preset road condition conditions; identifying N candidate cruise targets for the target vehicle and predicting the movement trajectory of each candidate cruise target within a preset time period; selecting at least one candidate cruise target that meets the preset cruise conditions based on the movement trajectory of each candidate cruise target and the movement trajectory of the target vehicle within the preset time period; determining the cruise target of the target vehicle from the N candidate cruise targets based on the selected at least one candidate cruise target; and controlling the target vehicle to drive based on the cruise target of the target vehicle.

[0034] In some embodiments of this application, when the adaptive cruise control function of the target vehicle is activated, it can detect whether the road conditions of the road on which the target vehicle is traveling meet preset road condition conditions. The preset road condition conditions include at least one of the following: the target vehicle is traveling to an intersection, roundabout, or wide lane; the target vehicle is traveling to a road section without clear lane markings.

[0035] Based on the aforementioned vehicle control method, this paper effectively solves the problem of inaccurate target identification, misjudgment, or loss of cruise targets caused by the reliance on lane lines in complex scenarios such as intersections, roundabouts, wide lanes, and roads without lane lines, which is often due to the traditional adaptive cruise control system. This application introduces a candidate cruise target trajectory prediction and evaluation mechanism, selecting the most reasonable cruise target from multiple candidate targets based on preset cruise conditions. This ensures that the vehicle can stably and safely adaptively follow the cruise target, significantly improving the applicability, safety, and smoothness of the ACC system in scenarios such as intersections, roundabouts, wide lanes, and roads without lane lines.

[0036] In some embodiments of this application, the target vehicle may refer to a self-driving vehicle. Preset road conditions may include at least one of the following: the target vehicle is traveling to an intersection, roundabout, or wide lane; the target vehicle is traveling to a road section without clear lane markings, such as a rural road, etc., which are not specifically limited in this application.

[0037] In some embodiments of this application, N candidate cruise targets for a target vehicle can be determined based on different road structure information. As an example, when the target vehicle is traveling on a structured road with clear lane markings (e.g., a highway), the onboard device can identify the lane the target vehicle is in and identify vehicles ahead of it in the same lane as the target vehicle as N candidate cruise targets. As another example, when the target vehicle is traveling on a road without clear lane markings (e.g., rural roads, construction zones, or some old urban roads), the onboard device cannot rely on lane marking information. In this case, the onboard device can determine the drivable area of ​​the target vehicle based on road structure information provided by a high-precision map and the target vehicle's location information. This drivable area can be defined by static elements such as road boundaries and obstacle boundaries. Simultaneously, the onboard device can also dynamically correct and complete the boundaries of the drivable area by integrating real-time perception data (such as camera and radar perception results). Based on this, the onboard device can identify all traffic participants (e.g., other vehicles) located ahead of the target vehicle and traveling in the same direction as the target vehicle within this drivable area as N candidate cruise targets.

[0038] It should be noted that the vehicle control method provided in this application embodiment can be applied to telematics devices, vehicle control units (VCUs), and advanced driver assistance systems (ADAS), etc.

[0039] The following is combined with Figure 1 The flowchart illustrating the vehicle control method is provided to illustrate the vehicle control method in the embodiments of this application. It should be understood that... Figure 1 In the vehicle control method shown, the executing entity for each process can be an on-board device.

[0040] S101: The road conditions on the road where the target vehicle is traveling meet the preset road condition conditions.

[0041] In some embodiments of this application, when the adaptive cruise control function of the target vehicle is activated, the on-board equipment can determine that the road conditions of the road on which the target vehicle is traveling meet the preset road condition conditions by fusing information from perception data and high-precision maps.

[0042] It is understood that the preset road conditions may include at least one of the following: the target vehicle is traveling to an intersection, roundabout, or wide lane; the target vehicle is traveling to a section of road without clear lane markings, such as a rural road, etc., and this application does not specifically limit this. It should be understood that a wide lane refers to a lane width on the road where the target vehicle is currently traveling that is greater than or equal to a preset lane width threshold (e.g., 5m).

[0043] It is understood that the perception data may include, but is not limited to, one or more of the following: image data collected by the vehicle's onboard camera, point cloud data collected by millimeter-wave radar, 3D point cloud data collected by lidar, and vehicle pose data from an inertial measurement unit (IMU) and a global navigation satellite system (GNSS). The onboard equipment can fuse the above perception data and combine it with pre-stored road topology, lane line information, lane width, road type, and road boundary information in a high-precision map to comprehensively determine whether the current road conditions meet preset road condition requirements.

[0044] S102: Identify N candidate cruise targets for the target vehicle and predict the trajectory of each candidate cruise target within a preset time period.

[0045] In some embodiments of this application, N candidate cruise targets for a target vehicle can be determined based on different road structure information.

[0046] For example, when the target vehicle is traveling on a structured road with clear lane lines (such as a highway), the on-board equipment can determine the lane where the target vehicle is located based on the lane line recognition results of visual perception and / or the lane-level positioning information provided by high-precision maps, and can identify the vehicles in front of the target vehicle in the same lane as the target vehicle as N candidate cruise targets.

[0047] For example, when the target vehicle is traveling on roads without clear lane markings (such as rural roads, construction zones, or some older urban roads), the onboard equipment cannot rely on lane marking information. In this case, the onboard equipment can determine the drivable area of ​​the target vehicle based on road structure information provided by a high-precision map and the target vehicle's location information. This drivable area can be defined by static elements such as road boundaries and obstacle boundaries. Simultaneously, the onboard equipment can also dynamically correct and complete the boundaries of the drivable area by integrating real-time perception data (such as camera and radar results). Based on this, the onboard equipment can select all traffic participants (such as other vehicles) located in front of the target vehicle and traveling in the same direction as the target vehicle within this drivable area as N candidate cruise targets.

[0048] For example, when a target vehicle travels onto a road without clear lane markings, one implementation method for determining a drivable area based on a high-precision map, the target vehicle's location information, and perception data is as follows: The onboard device can obtain the reference boundary of the current road based on the high-precision map, and simultaneously identify the physical boundaries of the road (such as the edge of the shoulder, the edge of the green belt, guardrails, or temporary construction barriers) and the location of obstacles through perception data. The reference boundary and the real-time perceived boundary are then fused to generate a drivable area. The lateral range of the drivable area can be dynamically determined by the real-time perceived physical boundaries on both sides of the road, and the longitudinal range can be determined by the position of the target vehicle at a predetermined distance ahead.

[0049] Based on the identified drivable area, the on-board equipment can initially filter all traffic participants (such as other vehicles) located within the area, in front of the target vehicle, and traveling in the same direction as the target vehicle into N candidate cruise targets.

[0050] It is understood that the above-described implementation of determining a passable area is merely an illustrative example. In other embodiments of this application, it may be determined in other ways, and this application does not impose any specific limitations on this.

[0051] S103: Based on the motion trajectory of each candidate cruise target and the motion trajectory of the target vehicle within a preset time period, select at least one candidate cruise target that meets the preset cruise conditions.

[0052] In some embodiments of this application, the vehicle-mounted device can monitor the status information of N candidate cruise targets in real time within a preset time period (T) using sensing data. The status information of each candidate cruise target within the preset time period may include, but is not limited to: timestamp, unique identifier (ID) of the candidate cruise target, real-time position (which may include three-dimensional coordinates X, Y, Z, etc.), speed, acceleration, orientation angle, and type (such as vehicle, motorcycle, etc.). Based on the status information of each candidate cruise target within the preset time period, the vehicle-mounted device can accurately predict the motion trajectory of each candidate cruise target within the preset time period.

[0053] It is understood that a structured list of candidate cruise targets can be determined based on the state information of N candidate cruise targets. This list is a dynamically updated collection of state information for N candidate cruise targets, for example, updated every 100ms. This structured list of candidate cruise targets may include multiple entries, each corresponding to a candidate cruise target, and containing at least the following fields: timestamp (system time for data acquisition or update), candidate cruise target ID (used for unique identification and cross-cycle tracking of candidate cruise targets), real-time location (may include absolute coordinates (such as latitude, longitude, and altitude) and coordinates relative to the target vehicle (longitudinal distance, lateral distance)), motion state (including speed magnitude, speed direction (orientation), acceleration, and yaw rate, etc.), target attributes (type (such as car, truck), size (length, width), etc.), and prediction information (a sequence of motion trajectory points within a preset time period, each point containing position, speed, and time). In other embodiments of this application, each entry in the structured list of candidate cruise targets may also include other fields besides those listed in the examples above; this application does not specifically limit this.

[0054] In some embodiments of this application, the vehicle-mounted device can determine the movement trajectory of N candidate cruise targets within a preset time period, and can also predict the movement trajectory of the target vehicle within the same preset time period.

[0055] In some embodiments of this application, the method for determining the motion trajectory of the target vehicle within a preset time period may include: obtaining the longitudinal velocity and yaw rate of the target vehicle; inputting the longitudinal velocity and yaw rate of the target vehicle into a motion trajectory prediction model to obtain the motion trajectory of the target vehicle within the preset time period.

[0056] In some embodiments of this application, the longitudinal velocity and yaw rate of the target vehicle are input into the motion trajectory prediction model to obtain the motion trajectory of the target vehicle within a preset time period, including: calculating the target curvature of the target vehicle based on the longitudinal velocity and yaw rate of the target vehicle, and calculating the radius of the arc corresponding to the target curvature based on the target curvature; calculating the pose of the target vehicle at each predicted time point within the preset time period based on the radius of the arc corresponding to the target curvature and the target curvature; and using the combination sequence of the poses of the target vehicle at each predicted time point within the preset time period as the motion trajectory of the target vehicle within the preset time period.

[0057] The following section provides a detailed explanation of the process for determining the trajectory of a target vehicle within a preset time period, using formulas as examples.

[0058] In some embodiments of this application, the trajectory of the target vehicle within a preset time period (e.g., the next 5 or 10 seconds) consists of a series of trajectory points arranged in chronological order. Each trajectory point represents the predicted position of the target vehicle in its local coordinate system (e.g., with the vehicle's center of mass as the origin and the direction of the vehicle's front as the positive Y-axis) at the corresponding predicted time point. The trajectory prediction model can determine the predicted position of each trajectory point based on formulas (1) to (4), and then obtain the trajectory of the target vehicle within the preset time period by combining the trajectory points corresponding to each predicted time point within the preset time period into a sequence.

[0059] , formula (1);

[0060] , formula (2);

[0061] , formula (3);

[0062] , formula (4);

[0063] In formula (1), R can represent the radius of the arc corresponding to the target curvature of the target vehicle. It can represent the target curvature of the target vehicle, in meters (m). -1 . In formula (2), It can represent the central angle (i.e., the facing angle) corresponding to the arc length. This can represent the arc length along which the target vehicle travels from the current time to the i-th predicted time point. In formula (3), This can represent the lateral coordinate of the i-th trajectory point in the local coordinate system. In formula (4), It can represent the vertical coordinate of the i-th trajectory point in the local coordinate system.

[0064] in, It can be determined using formula (5). In formula (5), This can represent the arc length along which the target vehicle travels from the current time point to the i-th prediction time point. v can represent the longitudinal velocity of the target vehicle, in m / s. ti can represent the cumulative time from the current time point to the i-th prediction point.

[0065] , formula (5);

[0066] Discretize the preset time period T, and let , where Δt is the preset discretization time step. Substituting formula (1) into formula (3) and formula (4) and performing discretization, formula (6) and formula (7) can be obtained respectively. Based on formula (2), formula (6) and formula (7), the orientation angle, lateral position xi and longitudinal position yi of the trajectory point at each prediction time point can be obtained respectively, that is, the pose of each trajectory point. Then, by combining the poses of each trajectory point, a combined sequence is obtained as the motion trajectory of the target vehicle in the preset time period.

[0067] , formula (6);

[0068] , formula (7);

[0069] In formula (6), when the absolute value of the target curvature is... Less than the curvature threshold ,but for When the absolute value of the target curvature Greater than or equal to the curvature threshold ,but for .

[0070] In formula (7), when the absolute value of the target curvature is... Less than the curvature threshold ,but for When the absolute value of the target curvature Greater than or equal to the curvature threshold ,but for .

[0071] In some embodiments of this application, when the longitudinal speed of the target vehicle is greater than or equal to a high-speed threshold, a reference curvature can be calculated as the target curvature based on the yaw rate and longitudinal speed of the target vehicle; when the longitudinal speed of the target vehicle is less than or equal to a low-speed threshold, a smooth curvature can be calculated as the target curvature based on a preset sampling time, a preset filtering time constant, a preset center offset coefficient, and the rear axle center curvature of the target vehicle; when the longitudinal speed of the target vehicle is greater than a low-speed threshold and less than a high-speed threshold, the target curvature can be calculated based on the reference curvature, the smooth curvature, and the center offset coefficient; wherein, the radius of the arc corresponding to the target curvature is the reciprocal of the target curvature.

[0072] In some embodiments of this application, the target curvature of the target vehicle It can be calculated based on formula (8).

[0073] , formula (8);

[0074] Based on formula (8), it can be seen that when the longitudinal speed v of the target vehicle is greater than or equal to the high-speed threshold... At that time, the target curvature of the target vehicle can be , This can represent the theoretical curvature calculated based on a vehicle kinematics model. When the longitudinal velocity v of the target vehicle is less than or equal to a low-speed threshold... At that time, the target curvature of the target vehicle can be , This can represent the smooth curvature obtained through filtering algorithms (such as Kalman filtering). When the longitudinal velocity v of the target vehicle is less than a high-speed threshold... And greater than the low speed threshold At that time, the target curvature of the target vehicle can be .

[0075] In some embodiments of this application, after determining the target curvature Then, the lateral acceleration of the target vehicle can be monitored in real time. Lateral acceleration of the target vehicle Lateral acceleration constraints need to be met, i.e. ,in, , This represents the maximum lateral acceleration.

[0076] If lateral acceleration If the lateral acceleration constraint is not met, then the target curvature needs to be adjusted. Update to get the updated version. And will update Substitute these equations (2), (6), and (7) into formulas (7) to update the trajectory of the target vehicle. Wherein, .

[0077] In some embodiments of this application, the formula (8) above... This can represent the fusion weighting coefficients, when the longitudinal speed v of the target vehicle decreases from a low speed threshold. Increase to high speed threshold hour, It can linearly increase from 0 to 1 to achieve a smooth transition of the target vehicle from low speed to high speed. Based on formula (9), it can be calculated Refer to formula (9). It can be ( )and( The ratio of ).

[0078] , formula (9);

[0079] In some embodiments of this application, the theoretical curvature is calculated based on a vehicle kinematics model. Calculated using formula (10).

[0080] , formula (10);

[0081] In formula (10), It can represent the yaw rate of the target vehicle. The longitudinal velocity of the target vehicle can be represented by the theoretical curvature in formula (10). Represented as and The ratio of .

[0082] In some embodiments of this application, the smooth curvature is obtained by processing with a filtering algorithm (such as Kalman filtering). Calculated using formula (11).

[0083] ,(11)

[0084] Formula (11) is a first-order low-pass filter used to filter the dynamic curvature of the target vehicle. Perform smoothing to obtain the smoothed curvature at the current moment. ,in, It can represent the smooth curvature of the previous moment. This can represent the preset sampling time, which is also the filter update period. The filter time constant can be used to determine the degree of smoothing. This can represent the influence weight of the smooth curvature from the previous moment on the current moment. It can represent dynamic curvature The influence weight at the current moment, where the sum of the weights is 1.

[0085] In some embodiments of this application, the dynamic curvature of the target vehicle It can represent the instantaneous curvature calculated in real time based on the target vehicle's motion geometry, used to describe the degree of curvature of the target vehicle's steering intention or actual driving path. Dynamic curvature of the target vehicle. It can be calculated using formula (12).

[0086] , formula (12);

[0087] In formula (12), It can represent the center offset coefficient, used to measure the curvature of the rear axle center of the target vehicle. Converted to the curvature corresponding to the vehicle's center of gravity (or front axle), it is usually a function of the target vehicle's geometric parameters (such as wheelbase). It can represent the path curvature of the rear axle center point.

[0088] In some embodiments of this application, the rear axle curvature of the target vehicle It can be calculated using formula (13).

[0089] , formula (13);

[0090] In formula (13), the rear axle curvature of the target vehicle Direction factor and geometric factors The ratio of the turning direction of the target vehicle to the curvature of the path can reflect the turning direction of the target vehicle. This can represent the turning radius corresponding to the center of gravity of the target vehicle, in meters. It can indicate a left turn, if It can indicate a right turn, if It can indicate going straight. It can represent the radius of curvature of the rear axle center of the target vehicle, that is, the geometric distance from the center point of the rear axle to the instantaneous center of the turning circle when the target vehicle is turning, in meters.

[0091] In some embodiments of this application, the rear axle center radius of curvature It can be calculated using formula (14).

[0092] , formula (14);

[0093] In formula (14), It can represent the lateral coordinates of the rear axle center in the global coordinate system. This can represent the longitudinal coordinate of the rear axle center in the global coordinate system, where, , , , It can represent the distance between the target vehicle's center of gravity and the rear axle. It can represent the curvature of the center of mass. It can represent the direction angle of the rear axle center relative to the center of the turning circle of the center of gravity, that is, the rear wheel slip angle.

[0094] In some embodiments of this application, the rear wheel slip angle It can be calculated using formula (15).

[0095] , formula (15);

[0096] In formula (15), It can represent the curvature of the center of mass of the target vehicle. It can represent the distance from the target vehicle's center of gravity to the rear axle. It can represent the wheelbase of the target vehicle. It can represent the rear wheel lateral stiffness of the target vehicle. It can represent the mass of the target vehicle, in kg. It can represent the square of the longitudinal velocity of the target vehicle. It can represent the distance from the target vehicle's center of gravity to the front axle.

[0097] In some embodiments of this application, the centroid curvature It can be calculated using formula (16).

[0098] , formula (16);

[0099] In formula (16), It can represent the front wheel steering angle of the target vehicle. K can represent the wheelbase of the target vehicle, and K can represent an intermediate variable.

[0100] In some embodiments of this application, the intermediate variable K can be calculated based on formula (17).

[0101] , formula (17);

[0102] In formula (17), It can represent the distance from the target vehicle's center of gravity to the rear axle. It can represent the front wheel lateral stiffness of the target vehicle. It can represent the distance from the target vehicle's center of gravity to the front axle. It can represent the rear wheel lateral stiffness of the target vehicle, and the unit of lateral stiffness is N / rad. It can represent the square of the wheelbase of the target vehicle.

[0103] In some embodiments of this application, the front wheel steering angle of the target vehicle It can be calculated based on formula (18).

[0104] , formula (18);

[0105] In formula (18), It can represent the front wheel steering angle of the target vehicle, and can characterize the actual average deflection angle of the left and right front wheels of the target vehicle relative to the longitudinal axis of the vehicle body. It can represent the preset steering gear ratio, which characterizes the proportional coefficient between the steering wheel angle and the front wheel angle. It can represent the steering wheel angle of the target vehicle, in rad.

[0106] In some embodiments of this application, some parameters in the above formulas are preset parameters, and are adjustable preset parameters. For example, see Table 1 below, which shows an adjustable parameter table.

[0107] Table 1

[0108]

[0109] It is understood that each adjustable parameter and its range in Table 1 is merely an illustrative example. In other embodiments of this application, the adjustable parameters may include larger or smaller ranges, which are not specifically limited in this application.

[0110] In some embodiments of this application, after determining the motion trajectory of each candidate cruise target and the motion trajectory of the target vehicle within a preset time period, at least one candidate cruise target that meets the preset cruise conditions can be selected from N candidate cruise targets based on the motion trajectory of each candidate cruise target and the motion trajectory of the target vehicle within the preset time period.

[0111] In some embodiments of this application, the preset cruise conditions may include: when the target vehicle is traveling to an intersection, roundabout, or on a road segment without clearly defined lanes, the overlap between the trajectory of the candidate cruise target and the trajectory of the target vehicle within a preset time period is greater than or equal to a trajectory overlap threshold. When the target vehicle is traveling on a wide lane, and the candidate cruise target and the target vehicle have overlapping trajectories within a preset time period, the lateral overlap rate between the candidate cruise target and the target vehicle in the overlapping trajectories is greater than or equal to a lateral overlap rate threshold.

[0112] The trajectory overlap can be understood as the degree of overlap between the trajectory of a candidate cruise target and the trajectory of the target vehicle (automobile) in a two-dimensional (XY) space within a preset time period. This can be determined by calculating the proportion of overlapping trajectory points. Specifically: the preset time period is discretized to generate a series of equally spaced prediction time points {t0, t1, ..., tn}, where t0 represents the current time point and tn represents the end time point of the prediction time period, with each prediction time point spaced 0.1 seconds apart. For each prediction time point ti, the predicted position coordinates (X_ego(ti), Y_ego(ti)) and (X_target(ti), Y_target(ti)) of the target vehicle and the candidate cruise target at that prediction time point are obtained, thus obtaining a sequence of trajectory points for the two trajectories. For each prediction time point ti, the Euclidean distance D(ti) between the two trajectory points can be calculated to determine whether they overlap. If D(ti) is less than or equal to a preset overlap tolerance distance (e.g., 1.5m), the two trajectory points at that prediction time point are considered to overlap. Then, by calculating the ratio between the number of overlapping trajectory points and the total number of trajectory points, the degree of trajectory overlap between the target vehicle's trajectory and the candidate cruise target's trajectory is determined. It should be understood that the higher the trajectory overlap (greater than or equal to the trajectory overlap threshold), the more consistent the candidate cruise target's trajectory is with the target vehicle's trajectory within a preset time period.

[0113] The lateral overlap rate can be understood as the degree of overlap between the candidate cruise target and the target vehicle (the self-vehicle) in the lateral space along their respective travel paths (i.e., their predicted trajectories) within a preset time period. This is determined by the lateral overlap area of ​​the two vehicle profiles along the travel path. Specifically: the overlapping time periods within the preset time period are discretized to generate a series of equally spaced prediction time points {t0, t1, ..., tm}. For each prediction time point ti, the predicted positions, orientation angles, and rectangular profiles defined by the length and width of the target vehicle and the candidate cruise target at that prediction time point are obtained. For each prediction time point ti, based on the predicted positions, orientation angles, and rectangular profiles of the two vehicles at prediction time point ti, defined by vehicle length and width, a scalar value representing the degree of lateral overlap is calculated, called the instantaneous lateral overlap, which can be denoted as L(ti). L(ti) reflects the spatial scale of the overlap between the two vehicle profiles in the lateral direction perpendicular to the self-vehicle's travel direction at prediction time point ti. Furthermore, L(ti) greater than a preset overlap threshold (e.g., 0.3) is selected from all instantaneous lateral overlap values. The arithmetic mean of all L(ti) greater than the preset overlap threshold (e.g., 0.3) is calculated to obtain the average lateral overlap value L_avg. The ratio of the average lateral overlap value L_avg to the width of the target vehicle is calculated. This ratio represents the lateral overlap rate between the candidate cruise target and the target vehicle within a preset time period. It should be understood that a higher lateral overlap rate (greater than or equal to the preset lateral overlap rate threshold) indicates a greater degree of lateral spatial overlap between the candidate cruise target's trajectory and the target vehicle in a wide lane scenario, and a more consistent driving path.

[0114] S104: Based on the selected at least one candidate cruise target, determine the cruise target of the target vehicle from the N candidate cruise targets.

[0115] In some embodiments of this application, after determining N candidate cruise targets for the target vehicle within a preset time period, a primary candidate cruise target (closest in path vehicle, CIPV) and a secondary candidate cruise target (second-closest in path vehicle, SIPV) can be determined based on the relative distance between the target vehicle and the N candidate cruise targets. The primary candidate cruise target has the smallest distance from the target vehicle among the N candidate cruise targets, and the secondary candidate cruise target has the second smallest distance from the target vehicle among the N candidate cruise targets.

[0116] In some embodiments of this application, when the primary candidate cruise target meets preset cruise conditions, such as when the primary candidate cruise target is one of the selected at least one candidate cruise targets, the primary candidate cruise target can be determined as the cruise target of the target vehicle.

[0117] For example, when the target vehicle approaches an intersection, roundabout, or travels on a road segment without clearly defined lanes, it can be determined whether the overlap between the trajectory of the primary candidate cruise target and the trajectory of the target vehicle is greater than or equal to a trajectory overlap threshold (such as 90%). If the overlap between the trajectory of the primary candidate cruise target and the trajectory of the target vehicle is greater than or equal to the trajectory overlap threshold, it indicates that the travel path of the primary candidate cruise target closest to the target vehicle is highly consistent with the trajectory of the target vehicle. Based on this, the primary candidate cruise target can be directly identified as a reliable cruise target for the target vehicle.

[0118] For example, when the target vehicle is traveling in a wide lane (such as a multi-lane urban arterial road), and the primary candidate cruise target and the target vehicle have overlapping trajectories within a preset time period, it can be determined whether the lateral overlap rate between the primary candidate cruise target and the target vehicle in the overlapping trajectory is greater than or equal to a lateral overlap rate threshold (such as 70%). If the lateral overlap rate between the primary candidate cruise target and the target vehicle in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold, it indicates that the primary candidate cruise target closest to the target vehicle has a good guiding effect on the target vehicle in lateral space. Based on this, the primary candidate cruise target can be directly identified as a reliable cruise target for the target vehicle.

[0119] In some embodiments of this application, when the primary candidate cruise target does not meet the preset cruise conditions, but the secondary candidate cruise target does meet the preset cruise conditions, for example, when the primary candidate cruise target is not any of the selected at least one candidate cruise target, and the secondary candidate cruise target is one of the selected at least one candidate cruise target, the secondary candidate cruise target can be determined as the cruise target of the target vehicle.

[0120] For example, when the target vehicle approaches an intersection, roundabout, or travels on a road segment without clearly defined lanes, if the overlap between the trajectory of the primary candidate cruise target and the trajectory of the target vehicle is determined to be less than a trajectory overlap threshold (e.g., the primary candidate cruise target turns away from its current path), it can be further determined whether the overlap between the trajectory of the secondary candidate cruise target and the trajectory of the target vehicle is greater than or equal to the trajectory overlap threshold. If the overlap between the trajectory of the secondary candidate cruise target and the trajectory overlap threshold is greater than or equal to the trajectory overlap threshold, it indicates that the travel path of the second closest secondary candidate cruise target to the target vehicle is highly consistent with that of the target vehicle. Based on this, the secondary candidate cruise target can be identified as the target vehicle's cruise target.

[0121] For example, when the target vehicle is traveling in a wide lane (such as a multi-lane urban arterial road), if it is determined that the lateral overlap rate between the primary candidate cruise target and the target vehicle within a preset time period is less than a lateral overlap rate threshold (for example, the primary candidate cruise target always travels close to one side of the lane), it can be further determined whether the lateral overlap rate between the secondary candidate cruise target and the target vehicle in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold. If the lateral overlap rate of the secondary candidate cruise target is greater than or equal to the lateral overlap rate threshold, it indicates that the secondary candidate cruise target, which is the second closest to the target vehicle, is more closely bound to the target vehicle's path in lateral space and can provide more effective lateral guidance. Based on this, the secondary candidate cruise target can be identified as the target vehicle's cruise target.

[0122] In some embodiments of this application, when neither the primary candidate cruise target nor the secondary candidate cruise target meets the preset cruise conditions, the cruise target of the target vehicle can be determined from at least one candidate cruise target that meets the preset cruise conditions among N candidate cruise targets.

[0123] For example, when the target vehicle approaches an intersection, roundabout, or road segment without clearly defined lanes, if the trajectory overlap between the primary and secondary candidate cruise targets (such as vehicles making left and right turns respectively) and the target vehicle's trajectory is less than a trajectory overlap threshold, then the candidate cruise target with the highest trajectory overlap with the target vehicle's trajectory can be selected from at least one candidate cruise target that meets the preset cruise conditions among N candidate cruise targets. If the trajectory overlap of this candidate cruise target is greater than or equal to the trajectory overlap threshold, then this candidate cruise target can be designated as the target vehicle's cruise target.

[0124] For example, when the target vehicle is traveling in a wide lane, if the lateral overlap rate between the primary candidate cruise target, the secondary candidate cruise targets (such as vehicles traveling close to the leftmost and rightmost edges of the lane, respectively), and the target vehicle within a preset time period is all less than a lateral overlap rate threshold, then the candidate cruise target with the highest lateral overlap rate with the target vehicle can be selected from at least one candidate cruise target that meets the preset cruise conditions among N candidate cruise targets. If the lateral overlap rate of this candidate cruise target is greater than or equal to the lateral overlap rate threshold, then this candidate cruise target can be determined as the target vehicle's cruise target.

[0125] S105: Cruise target control based on target vehicle to control the movement of the target vehicle.

[0126] In some embodiments of this application, after the cruise target is determined, in order to ensure the safety and robustness of the target vehicle following the cruise target, the system can perform multi-level verification and monitoring based on the central processing unit before executing the final control. Specifically, it can include the following two parallel processing steps.

[0127] (1) Stability Adjudication and Suppression of Cruise Targets. Cut-out Handling of Cruise Targets: When the system determines that a currently identified cruise target is performing a cut-out operation (such as leaving the vehicle's drivable area or significantly changing its lateral position to intend to leave), the system will not immediately remove it from the tracking list. Instead, it will activate a "smooth transition" mechanism to prevent sudden changes in control commands and ensure the continuity of the target vehicle's following behavior. Within a short-term prediction window (e.g., the prediction period of the target vehicle's motion state in the next 2 to 3 seconds), the weight of the cut-out target in the longitudinal driving control decision of the target vehicle is gradually reduced based on a preset weight decay curve. Simultaneously, a new cruise target selection process is re-triggered, and the weight of the new cruise target in the longitudinal driving control decision of the target vehicle is gradually increased. This achieves a smooth transition in the longitudinal driving control of the target vehicle, avoiding unexpected acceleration of the vehicle due to the sudden loss of the cruise target.

[0128] Cut-out handling for cruise targets: When another traffic participant cuts into the driving area between the target vehicle and the cruise target from the side, the system can immediately identify it as a new candidate cruise target and initiate a high-priority reassessment. If the cutting-out vehicle meets the preset cruise conditions and its longitudinal distance to the target vehicle is less than the longitudinal distance between the target vehicle and the current cruise target, the system can quickly establish it as the new cruise target and initiate safe distance reconstruction control, establishing a new following distance by moderately decelerating. If the cutting-out vehicle does not meet the preset cruise conditions, the system maintains the target vehicle's following of the current cruise target, avoiding unnecessary control responses, thereby maintaining system stability and ride comfort in complex traffic scenarios.

[0129] (2) While completing the target stability assessment and determining the cruise target, the system continuously monitors and assesses the risks of all traffic participants around the target vehicle (including the determined cruise target and other vehicles) in parallel. Specifically, the on-board equipment can continuously predict the movement trajectories of the target vehicle, the cruise target, and other traffic participants around it within a preset time period. By comparing the predicted trajectory of the target vehicle with the predicted trajectory of each other participant in time and space, the system can identify any two predicted trajectory points that overlap or intersect at the same time and in the same spatial location, i.e., potential collision trajectory points. For each identified potential collision trajectory point, the system can calculate the time interval from the current time to the predicted trajectory point as the corresponding time to collision (TTC). If the calculated TTC is lower than the preset TTC threshold, it can be determined that there is an emergency collision risk, and a deceleration command exceeding the normal following requirements can be generated to prioritize driving safety. After the collision risk is eliminated, the cruise target assessment and selection process can be retried to ensure that the target vehicle follows the most stable cruise target.

[0130] In some embodiments of this application, after the vehicle-mounted device determines the cruise target, it can automatically adjust the following speed and distance of the target vehicle relative to the cruise target based on the relative speed and actual distance between the target vehicle and the cruise target, so as to generate acceleration or deceleration commands, thereby controlling the target vehicle to accelerate, decelerate or maintain speed, and achieve stable following of the cruise target.

[0131] Based on the aforementioned vehicle control method, when the target vehicle is traveling in pre-defined road conditions such as a lack of clear lane markings, this method effectively solves the problems of inaccurate target identification, misjudgment, or loss caused by the reliance on lane marking information in traditional adaptive cruise control systems. This application introduces the concept of a "candidate cruise target" and a trajectory prediction mechanism, eliminating the reliance on static lane markings and instead using the predicted motion trajectories of dynamic traffic participants for flexible cruise target selection. Under pre-defined road conditions, by quantitatively evaluating the trajectory overlap and lateral overlap rate between the candidate cruise target and the target vehicle, the most reasonable cruise target is selected from multiple candidate targets. This ensures that the vehicle can stably and safely adaptively follow the cruise target, significantly improving the applicability, safety, and smoothness of the ACC system in scenarios such as intersections, roundabouts, wide lanes, and roads without lane markings.

[0132] In one embodiment of this application, the in-vehicle device may include an adaptive cruise (ACC) target selection system, which may be integrated into the vehicle's driver assistance domain controller.

[0133] As one specific implementation method, the system uses Figure 2The diagram illustrates the logical architecture of the three-layer "input layer - processing layer - output layer" structure. Figure 2 As shown, the Adaptive Cruise Control (ACC) target selection system may include the following functional modules that coordinate efficiently based on the data bus or communication interface within the domain controller:

[0134] Environmental Perception Module: As the system's environmental input interface, the environmental perception module can connect to the target vehicle's onboard sensor network, including but not limited to forward-facing cameras, millimeter-wave radar, and lidar. The environmental perception module is responsible for fusing multi-source sensor data, perceiving road structure (such as lane lines and curbs) and dynamic traffic participants (such as other vehicles) in real time, and outputting structured environmental perception results, including a list of candidate cruise targets, drivable areas, etc.

[0135] Vehicle Status Interface Module: As the target vehicle (self-vehicle) status input interface of the system, the vehicle status interface module can connect to the vehicle communication network through the vehicle bus (such as CAN bus). The vehicle status interface module is responsible for real-time acquisition and analysis of the target vehicle's own dynamic parameters, including the target vehicle's speed, acceleration, yaw rate, steering angle, and operation commands (such as ACC function switch status).

[0136] High-precision map and positioning module: As the system's prior knowledge and global reference input interface, the high-precision map and positioning module can integrate or access high-precision map data and fuse feedback information from the Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU) and environmental perception module to provide the system with lane-level precision vehicle absolute position and orientation, as well as prior information such as road topology, curvature, and traffic rules.

[0137] Central Processing Unit: As the core computing and decision-making unit of the system, the central processing unit is connected to the three modules mentioned above and runs the vehicle control method in this embodiment. The central processing unit can be configured to execute the following core processing flow: receiving multi-source input information from the environmental perception module, the vehicle status interface module, and the high-precision map and positioning module; determining whether the current road conditions of the target vehicle meet preset road condition conditions; when the road conditions meet the preset conditions, determining N candidate cruise targets for the target vehicle based on the multi-source input information, and predicting the movement trajectories of the N candidate cruise targets and the target vehicle within a preset time period; furthermore, selecting the optimal cruise target from the N candidate cruise targets based on quantitative indicators such as trajectory overlap and lateral overlap rate; finally, generating longitudinal control commands for the vehicle based on the cruise target and real-time risk assessment results (such as TTC), controlling the vehicle to drive based on the cruise target, and ensuring driving safety.

[0138] ACC Control Module: As the system's control command execution unit, the ACC control module receives cruise target decisions and related risk assessment information from the central processing unit. Based on the relative motion state of the cruise target (such as distance and speed) and TTC (Total Traffic Control), the ACC control module calculates the specific longitudinal control quantities (acceleration / deceleration) for the target vehicle and generates corresponding control commands. These commands are then sent to the steering, braking, and other actuators via the vehicle bus to achieve following control of the target vehicle.

[0139] It should be understood that the logical architecture diagram of the adaptive cruise (ACC) target selection system in the above example is only an exemplary illustration. In other embodiments of this application, the adaptive cruise (ACC) target selection system may also include more functional modules, and this application does not make specific limitations on this.

[0140] It should be understood that the aforementioned functional modules can efficiently collaborate through the data bus or communication interface within the domain controller. The environmental perception module, vehicle status interface module, and high-precision map and positioning module serve as the input layer, providing reliable multi-source input information for the central processing unit's cruise target decision-making. The central processing unit, as the decision-making and planning layer (i.e., the processing layer), can receive and integrate the multi-source input information from the input layer, enabling flexible decision-making from environmental perception to cruise target selection, and outputting the cruise target. The ACC control module, as the control execution layer, can receive the decision results from the central processing unit and, based on real-time risk assessment (such as TTC), generate specific vehicle longitudinal control commands. Finally, the control commands are sent to actuators such as steering and braking via the vehicle bus to complete the safe and stable following control of the target vehicle towards the cruise target.

[0141] based on Figure 2 The logical architecture diagram shown is as follows: Figure 3 According to an embodiment of this application, a flowchart of another vehicle control method is shown. Figure 3 The flowchart shown can be executed by vehicle-mounted equipment. Figure 3 As shown, specifically:

[0142] S201: Obtain multi-source input data.

[0143] In some embodiments of this application, based on Figure 2The system utilizes an environmental perception module, a vehicle status interface module, and a high-precision map and positioning module to acquire multi-source input data. The environmental perception module obtains a candidate cruise target list, including status information of dynamic traffic participants (such as other vehicles). This candidate target list typically includes a unique identifier (ID), real-time location, speed, acceleration, orientation angle, target type, and its rectangular outline for each target. The vehicle status interface module acquires real-time status parameters of the target vehicle (the driver), including but not limited to: vehicle speed, acceleration, yaw rate, front wheel steering angle, and ACC function activation / deactivation commands. The high-precision map and positioning module obtains the current road structure information and the vehicle's high-precision pose. Especially in complex areas such as intersections and roundabouts, this module provides road topology (such as lane connections), virtual lane lines, traffic rules, lane width, and other information, and combines this with positioning data to output the vehicle's lane-level position, orientation, and driving path.

[0144] S202: Update the road information of the target vehicle's current driving route based on multi-source input data.

[0145] In some embodiments of this application, based on Figure 2 The central processing unit in the system fuses and processes the multi-source input data acquired by S201 to update road structure information and the list of candidate cruise targets.

[0146] Road structure information: Based on the data provided by the high-precision map and positioning module, combined with the identification of static elements (such as curbs and stop lines) by the environmental perception module, update the drivable area boundary, lane topology, lane width, and whether it is an intersection / roundabout / wide lane and other road geometry and attribute information of the current driving area.

[0147] Candidate Cruise Target List: Based on the environmental perception module, the status information of all relevant dynamic traffic participants (i.e., candidate cruise targets) is updated. This may include, but is not limited to, timestamps, unique identifiers (IDs) for each candidate cruise target, real-time location (including 3D coordinates X, Y, Z), speed, acceleration, orientation angle, and type (e.g., vehicle, motorcycle, etc.). Simultaneously, based on data from the vehicle status interface module, the real-time dynamic parameters of the target vehicle (automobile) are updated, including the target vehicle's speed, acceleration, yaw rate, steering angle, and operational commands (e.g., ACC function on / off status).

[0148] It should be understood that the road information of the target vehicle's current driving route output by S202 is a complete and real-time updated environmental representation that integrates the static road structure and the dynamic traffic participant status. It serves as a reliable basis for subsequent trajectory prediction, risk assessment, and cruise target decision-making.

[0149] S203: Determine the first primary candidate cruise target and the first candidate cruise target based on the road information of the target vehicle's current driving road.

[0150] In some embodiments of this application, based on the candidate cruise target list, N candidate cruise targets located in front of the target vehicle and traveling in the same direction as the target vehicle (e.g., with an azimuth deviation within a preset range) can be selected first. Then, the N candidate cruise targets are sorted according to their longitudinal relative distances to the target vehicle. The candidate cruise target with the smallest longitudinal distance is determined as the first primary candidate cruise target, and the candidate cruise target with the second smallest longitudinal distance is determined as the first secondary candidate cruise target. The first secondary candidate cruise target serves as an alternative to the first primary candidate cruise target and can be used as a replacement if the first primary candidate cruise target does not meet the preset cruise conditions.

[0151] S204: Determine whether the target vehicle is approaching an intersection, roundabout, or a section of road without clearly defined lanes.

[0152] In some embodiments of this application, the central processing unit determines whether the target vehicle is traveling on a road with poor road conditions, a roundabout, or a road segment without clear lanes based on the road information of the target vehicle currently traveling on the road obtained in S202.

[0153] If the judgment result is "yes", then proceed to S205, determine the target vehicle's trajectory within a preset time period based on the motion trajectory prediction model, and determine the second primary candidate cruise target based on the target vehicle's trajectory within the preset time period.

[0154] If the result is "no", then proceed to S206 to determine whether the target vehicle is traveling in the wide lane.

[0155] S205: Determine the motion trajectory of the target vehicle within a preset time period based on the motion trajectory prediction model, and determine the second primary candidate cruise target based on the motion trajectory of the target vehicle within the preset time period.

[0156] In some embodiments of this application, the motion trajectory of a target vehicle within a preset time period can be determined using a motion trajectory prediction model based on the central processing unit. It is understood that the specific process of determining the motion trajectory of a target vehicle within a preset time period using the motion trajectory prediction model can be referred to the description in S103 above, and will not be repeated here.

[0157] In some embodiments of this application, when neither the first primary candidate cruise target nor the first candidate cruise target satisfies the preset cruise conditions (i.e., the trajectory overlap between the movement trajectory of the first primary candidate cruise target / the first candidate cruise target and the movement trajectory of the target vehicle is less than the trajectory overlap threshold), at least one second candidate cruise target that satisfies the preset cruise conditions and has the highest trajectory overlap can be selected from the candidate cruise targets other than the first primary candidate cruise target and the first candidate cruise target among the N candidate cruise targets.

[0158] S206: Determine whether the target vehicle is traveling in the wide lane.

[0159] In some embodiments of this application, after the central processing unit determines the second primary candidate cruise target, it can further determine whether the target vehicle is traveling in the wide lane.

[0160] In some embodiments of this application, based on the central processing unit's determination that the target vehicle has not reached an intersection, roundabout, or is traveling on a road segment without a clear lane, it can be further determined whether the target vehicle is traveling in a wide lane.

[0161] It should be understood that a wide lane refers to a lane width that is greater than or equal to a preset lane width threshold (e.g., 5m).

[0162] If the judgment result is "yes", then proceed to S207 to determine whether the lateral overlap rate between the target vehicle and the first primary candidate cruise target or the second primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold.

[0163] If the judgment result is "no", then proceed to S210 to determine the first primary candidate cruise target or the second primary candidate cruise target as the cruise target.

[0164] S207: Determine whether the lateral overlap rate between the target vehicle and the first primary candidate cruise target or the second primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold.

[0165] In some embodiments of this application, corresponding to S204 determining that the target vehicle has not traveled to the intersection, roundabout, or traveled on a road segment without a clear lane, it can be further determined in S206 that the target vehicle is traveling on a wide lane. Furthermore, it can be determined whether the lateral overlap rate between the target vehicle and the first primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold.

[0166] In some embodiments of this application, corresponding to determining the second primary candidate cruise target in S205, it can be further determined in S206 that the target vehicle is traveling in a wide lane. Furthermore, it can be determined whether the lateral overlap rate between the target vehicle and the second primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold.

[0167] If the judgment result is "yes", then proceed to S208 and determine the first primary candidate cruise target or the second primary candidate cruise target as the cruise target of the target vehicle;

[0168] If the judgment result is "no", then proceed to S209 and determine the first candidate cruise target or other candidate cruise targets that meet the preset cruise conditions as cruise targets.

[0169] S208: The first primary candidate cruise target or the second primary candidate cruise target is determined as the cruise target of the target vehicle.

[0170] In some embodiments of this application, after determining in S207 that the lateral overlap rate between the target vehicle and the first primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold, the first primary candidate cruise target can be determined as the cruise target of the target vehicle.

[0171] In some embodiments of this application, after determining in S207 that the lateral overlap rate between the target vehicle and the second primary candidate cruise target in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold, the second primary candidate cruise target can be determined as the cruise target of the target vehicle.

[0172] S209: The first candidate cruise target or other candidate cruise targets that meet the preset cruise conditions are determined as cruise targets.

[0173] In some embodiments of this application, if it is determined that the lateral overlap rate between the target vehicle and the first primary candidate cruise target in the overlapping trajectory is less than the lateral overlap rate threshold, the first candidate cruise target can be determined as the cruise target based on the lateral overlap rate between the first candidate cruise target and the target vehicle in the overlapping trajectory being greater than or equal to the lateral overlap rate threshold.

[0174] In some embodiments of this application, if it is determined that the lateral overlap rate between the target vehicle and the second primary candidate cruise target in the overlapping trajectory is less than the lateral overlap rate threshold, at least one candidate cruise target that meets the preset cruise conditions and has the highest lateral overlap rate can be selected from the candidate cruise targets other than the second candidate cruise target among the N candidate cruise targets.

[0175] S210: The first primary candidate cruise target or the second primary candidate cruise target is determined as the cruise target.

[0176] In some embodiments of this application, if the target vehicle does not travel to an intersection, roundabout, or a section of road without a clear lane, and if it is determined in S206 that the target vehicle is not traveling in a wide lane, then the first primary candidate cruise target can be used as the cruise target of the target vehicle.

[0177] In some other embodiments of this application, when a second primary candidate cruise target is determined, and it is determined based on S206 that the target vehicle is not traveling in the wide lane, the second primary candidate cruise target can be used as the cruise target of the target vehicle.

[0178] In some embodiments of this application, after the cruise target is determined, in order to ensure the safety and robustness of the target vehicle following the cruise target, the system can perform multi-level verification and monitoring based on the central processing unit before executing the final control. Specifically, this includes the following two parallel processing steps.

[0179] (1) Cruise target stability adjudication and suppression. Cruise target cut-out processing: When the system determines that a currently identified cruise target is performing a cut-out operation (such as leaving the vehicle's drivable area or significantly changing its lateral position to intend to leave), the system will not immediately remove it from the tracking list. Instead, it will activate a "smooth transition" mechanism to prevent sudden changes in control commands and ensure the continuity of following behavior. Within a short prediction window (e.g., a prediction period of the vehicle's motion state for the next 2 to 3 seconds), the weight of the currently cut-out cruise target in determining acceleration or deceleration commands is gradually reduced based on a preset weight decay curve, making the vehicle's deceleration action smoother. Simultaneously, the cruise target selection process is retried to quickly and preferentially re-evaluate other candidate cruise targets in the current environment, achieving a smooth switch of cruise targets and avoiding unexpected vehicle acceleration due to sudden loss of the cruise target.

[0180] Cut-out handling for cruise targets: When another traffic participant cuts into the driving area between the target vehicle and the cruise target from the side, the system immediately identifies it as a new candidate cruise target and initiates a high-priority reassessment. If the cutting-out vehicle meets the preset cruise conditions and its longitudinal distance to the target vehicle is less than the longitudinal distance between the target vehicle and the current cruise target, the system can quickly establish it as the new cruise target and initiate safe distance reconstruction control, establishing a new following distance by moderately decelerating. If the cutting-out vehicle does not meet the preset cruise conditions, the system maintains the target vehicle's following of the current cruise target, avoiding unnecessary control responses, thereby maintaining system stability and ride comfort in complex traffic scenarios.

[0181] Through the aforementioned cut-out and cut-in stability processing mechanism, the system finally outputs a stable cruise target after adjudication to the ACC control module.

[0182] (2) While completing the target stability assessment and outputting a stable cruise target to the ACC control module, the system continuously monitors and assesses the risks of all traffic participants (including the identified cruise target and other vehicles) around the target vehicle in parallel. Specifically, the onboard equipment can continuously predict the movement trajectories of the target vehicle, the cruise target, and other traffic participants around it within a preset time period. These movement trajectories are compared with the movement trajectory of the target vehicle in real time to identify the trajectory points where different traffic participants (usually the target vehicle and other traffic participants) may collide within the preset time period, and calculate their corresponding time to collision (TTC). If the calculated TTC is lower than the preset TTC threshold, an emergency collision risk is determined, and a deceleration command exceeding the normal following requirements is generated to ensure driving safety. After the collision risk is eliminated, the cruise target assessment and selection process can be retried to ensure that the target follows the safest and most suitable cruise target.

[0183] S211: Control the movement of target vehicles based on cruise targets.

[0184] In some embodiments of this application, the ACC control module can generate longitudinal acceleration or deceleration control commands based on the final determined cruise target and combined with parameters such as the real-time relative distance and relative speed between the target vehicle and the cruise target, so as to achieve smooth and safe automatic adjustment of the following distance and driving speed of the target vehicle, thereby maintaining comfortable, consistent and reliable adaptive cruise performance in complex dynamic traffic environments.

[0185] based on Figure 3 The vehicle control method shown effectively solves the problem of inaccurate, misjudged, or lost cruise targets caused by the reliance on lane lines in complex scenarios such as intersections, roundabouts, wide lanes, and roads without clear lane lines in traditional adaptive cruise systems. This method determines the drivable area and candidate cruise targets through multi-source input data fusion, and dynamically evaluates the trajectory overlap or lateral overlap rate between the candidate cruise targets and the target vehicle (self-vehicle) within a preset time period based on trajectory prediction and quantitative matching mechanisms. Combined with the progressive screening logic of primary and secondary candidate cruise targets, the method finally selects the cruise target that best matches the driving intention of the target vehicle. Thus, it achieves accurate, continuous, and safe adaptive following control without the need for clear lane lines, significantly improving the applicability, robustness, and driving safety of the system in complex road conditions.

[0186] It is understood that the vehicle control method provided by the embodiments of this application provides a new and reliable basis for cruise target selection in scenarios such as intersections, roundabouts, and rural roads where there are no clear lane lines or the lane line information is unreliable. This enables the target vehicle to smoothly and continuously pass through complex road sections based on the cruise target, significantly improving the reliability of the ACC system and the user's driving experience.

[0187] Furthermore, for urban wide-lane (multi-lane) scenarios, this embodiment introduces a lateral overlap rate judgment mechanism, enabling the ACC system to intelligently assess the degree of path binding between the candidate cruise target in the same lane ahead and the target vehicle (the vehicle itself) in lateral space. This effectively distinguishes the cruise target that truly needs to be followed from other traffic participants who are only laterally adjacent. This avoids the unintended acceleration or deceleration caused by interference from other traffic participants in traditional ACC systems, greatly improving the following smoothness and driving experience when the target vehicle is driving in a wide lane.

[0188] Furthermore, in this embodiment of the application, the cruise target of the target vehicle is determined by the fusion decision of multi-source input information (high-precision map, visual perception, radar perception, vehicle status, etc.), which can reduce the dependence on a single sensor or a single information source (such as lane lines). When faced with actual situations such as sensor noise, bad weather, wear or temporary loss of road markings, the ACC system can identify the cruise target more stably and accurately through multi-source input information, thereby improving the robustness of the ACC system.

[0189] It is understood that the methods mentioned in the embodiments of this application can be applied to in-vehicle equipment in vehicles. Figure 4 This is a possible structural schematic diagram of a vehicle 100 provided in an embodiment of this application.

[0190] like Figure 4 As shown, the functional framework of vehicle 100 may include various subsystems, such as Figure 4 The diagram shows a sensor system 110, a control system 120, one or more peripheral devices 130 (one is shown as an example), a power supply 140, and an onboard device 150. Optionally, the vehicle 100 may also include other functional systems, such as an engine system that powers the vehicle 100, etc., which are not limited herein. Optionally, the vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 100 can be interconnected via wired or wireless means.

[0191] The sensor system 110 may include several detection devices that can sense the measured information and convert the sensed information into electrical signals or other desired forms of information output according to a certain rule. Figure 4As shown, these detection devices may include a global positioning system (GPS), a vehicle speed sensor (112), an inertial measurement unit (IMU), etc., and this application does not limit them.

[0192] The Global Positioning System (GPS) 111 is a system that uses GPS positioning satellites to perform real-time positioning and navigation globally. In this application, the GPS 111 can be used to achieve real-time positioning of vehicle 100, providing the geographical location information of vehicle 100. The vehicle speed sensor 112 is used to detect the vehicle speed of vehicle 100. The inertial measurement unit 113 may include a combination of an accelerometer and a gyroscope, and is a device for measuring the angular rate and acceleration of vehicle 100.

[0193] The control system 120 may include a steering unit 121 and a braking unit 122, etc.

[0194] Steering unit 121 can represent a system for adjusting the direction of travel of vehicle 100, and may include, but is not limited to, a steering wheel or other structural device for adjusting or controlling the direction of travel of vehicle 100. Braking unit 122 can represent a system for slowing down the speed of vehicle 100, and may also be referred to as a vehicle braking system. It may include, but is not limited to, a brake controller, a reducer, or other structural device for slowing down vehicle 100. In practical applications, braking unit 122 can use friction to slow down the tires of vehicle 100, thereby slowing down the speed of vehicle 100.

[0195] Peripheral device 130 may include several components, such as Figure 4 The diagram shows a communication system 131, a touchscreen 132, a user interface 133, etc. The communication system 131 is used to enable network communication between the vehicle 100 and other devices besides the vehicle.

[0196] In practical applications, the communication system 131 can use wireless communication technology or wired communication technology to realize network communication between the vehicle 100 and other devices. The wired communication technology can refer to communication between the vehicle 100 and other devices via network cables or optical fibers. The wireless communication technology includes, but is not limited to, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Wireless Local Area Networks (WLAN) (such as Wireless Fidelity (Wi-Fi) networks), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR) technology, etc.

[0197] The touchscreen 132 can be used to detect operation commands on the touchscreen 132. For example, the user can perform touch operations on the content data displayed on the touchscreen 132 according to actual needs to achieve the corresponding function, such as playing music, video, or other multimedia files. The user interface 133 can specifically be a touch panel, used to detect operation commands on the touch panel. The user interface 133 can also be a physical button or a mouse. The user interface 133 can also be a display screen, used to output data and display images or data. Optionally, the user interface 133 can also be at least one device belonging to the category of peripheral devices, such as a touchscreen, microphone, and speaker.

[0198] Several functions of vehicle 100 are controlled and implemented by on-board equipment 150. On-board equipment 150 may include multiple processors such as processor 151, chassis domain controller (CDC) 152, mobility domain controller (MDC) 153, telematics box (T-BOX) 154, as well as memory 155 (also referred to as storage device) and gateway 156. In practical applications, the memory 155 may be located inside or outside the on-board equipment 150, for example, as a cache in vehicle 100, etc., and this application does not limit this.

[0199] Among them, processors 151, CDC152, MDC153, and T-BOX154 can be used to run relevant programs or instructions corresponding to programs stored in memory 155 to realize the corresponding functions of vehicle 100, such as the function of calling vehicle camera.

[0200] Memory 155 may include volatile memory, such as RAM; it may also include non-volatile memory, such as ROM, flash memory, HDD, or SSD; or it may include a combination of the above types of memory. Memory 155 can be used to store a set of program code or instructions corresponding to program code, so that processor 151 can call the program code or instructions stored in memory 155 to implement the corresponding functions of vehicle 100. This function includes, but is not limited to, […]. Figure 4 The illustrated vehicle functional framework diagram shows some or all of the functions. In this application, the memory 155 can store a set of program codes for sensing and predicting obstacles. The processors 151, CDC 152, MDC 153, and T-BOX 154 can call the program codes to control the vehicle 100 to perform the methods shown in the example in this application.

[0201] Optionally, in addition to storing program code or instructions, the memory 155 may also store information such as road maps, driving routes, and sensor data. The on-board device 150 can be combined with other components in the vehicle functional framework diagram, such as sensors in the sensor system and GPS, to realize the relevant functions of the vehicle 100. For example, the on-board device 150 can control the driving direction or speed of the vehicle 100 based on data input from the sensor system 110; this application does not impose limitations on this.

[0202] This application provides a vehicle that may include the aforementioned on-board equipment.

[0203] This application provides a readable storage medium storing instructions that, when executed on an in-vehicle device, enable the in-vehicle device to perform the vehicle control method described in the above embodiments.

[0204] This application provides a program product that, when run on an in-vehicle device, causes the in-vehicle device to execute the vehicle control method described in the above embodiments.

[0205] The embodiments disclosed in this application can be implemented in hardware, software, firmware, or a combination of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0206] Program code can be applied to input instructions to execute the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor. The program code can be implemented using a high-level programming language or an object-oriented programming language to communicate with the processing system.

[0207] When necessary, the program code can also be implemented using assembly language or machine language. In fact, the mechanism described in this application is not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0208] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may be implemented as instructions carried or stored thereon on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, CD-ROMs, magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other propagation signals. Therefore, machine-readable media include any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0209] In the accompanying drawings, certain structural or methodological features are shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0210] It should be noted that all units / modules mentioned in the device embodiments of this application are logical units / modules. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important factor; the combination of functions implemented by these logical units / modules is the key to solving the technical problem proposed in this application. Furthermore, to highlight the innovative aspects of this application, the above-described device embodiments of this application have not introduced units / modules that are not closely related to solving the technical problem proposed in this application. This does not mean that the above-described device embodiments do not contain other units / modules.

[0211] It should be noted that in the examples and description of this patent, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. While this application has been illustrated and described with reference to certain preferred embodiments, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the scope of this application.

Claims

1. A vehicle control method, characterized in that, The method includes: The road conditions on the road where the target vehicle is traveling meet the preset road condition conditions. N candidate cruise targets of the target vehicle are identified, and the movement trajectory of each candidate cruise target within a preset time period is predicted. The longitudinal velocity and yaw rate of the target vehicle are obtained, and the longitudinal velocity and yaw rate of the target vehicle are input into the motion trajectory prediction model to obtain the motion trajectory of the target vehicle within the preset time period. Based on the movement trajectory of each candidate cruise target and the movement trajectory of the target vehicle within the preset time period, at least one candidate cruise target that meets the preset cruise conditions is selected. The preset cruise conditions include: the overlap between the trajectory of the candidate cruise target and the trajectory of the target vehicle within the preset time period is greater than or equal to a trajectory overlap threshold; or... The lateral overlap rate between the candidate cruise target and the target vehicle in the overlapping trajectory is greater than or equal to the lateral overlap rate threshold. Based on the selected at least one candidate cruise target, the cruise target of the target vehicle is determined from the candidate cruise targets; The target vehicle is controlled to drive based on its cruise target.

2. The method according to claim 1, characterized in that, With the adaptive cruise control function of the target vehicle activated, it is detected whether the road conditions of the road on which the target vehicle is traveling meet the preset road condition conditions, wherein the preset road condition conditions include at least one of the following: The target vehicle is driving to an intersection, roundabout, or wide lane; The target vehicle traveled to a section of road where there were no clear lane markings.

3. The method according to claim 1, characterized in that, The determination of the N candidate cruise targets for the target vehicle includes: Based on the road structure information provided by the high-precision map and the location information of the target vehicle, the drivable area of ​​the target vehicle within a preset time period is determined. Based on the perception data of the target vehicle, the N candidate cruise targets located within the drivable area are determined.

4. The method according to claim 1, characterized in that, The trajectory overlap is used to evaluate the degree of matching between the candidate cruise target and the target vehicle's trajectory when the target vehicle travels to an intersection, roundabout, or road segment without a clear lane. The lateral overlap rate is used to evaluate the degree of lateral overlap between the candidate cruise target and the target vehicle when the target vehicle is traveling in a wide lane and has an overlapping trajectory with the candidate cruise target.

5. The method according to claim 4, characterized in that, The step of determining the cruise target of the target vehicle from the N candidate cruise targets based on the selected at least one candidate cruise target includes: Based on the distances between the N candidate cruise targets and the target vehicle, a primary candidate cruise target and a secondary candidate cruise target are determined from the N candidate cruise targets. The primary candidate cruise target has the smallest distance to the target vehicle among the N candidate cruise targets, and the secondary candidate cruise target has the second smallest distance to the target vehicle among the N candidate cruise targets, which is second only to the distance between the primary candidate cruise target and the target vehicle. If the primary candidate cruise target meets the preset cruise conditions, the primary candidate cruise target is determined as the cruise target of the target vehicle.

6. The method according to claim 5, characterized in that, The step of determining the cruise target of the target vehicle from the N candidate cruise targets based on the selected at least one candidate cruise target further includes: If the primary candidate cruise target does not meet the preset cruise conditions, and the secondary candidate cruise target meets the preset cruise conditions, the secondary candidate cruise target is determined as the cruise target of the target vehicle.

7. The method according to claim 6, characterized in that, The step of determining the cruise target of the target vehicle from the N candidate cruise targets based on the selected at least one candidate cruise target further includes: If neither the primary candidate cruise target nor the secondary candidate cruise target meets the preset cruise conditions, a candidate cruise target that meets the preset cruise conditions is selected from the N candidate cruise targets excluding the primary candidate cruise target and the secondary candidate cruise target as the cruise target.

8. The method according to claim 1, characterized in that, The step of inputting the longitudinal velocity and yaw rate of the target vehicle into the motion trajectory prediction model to obtain the motion trajectory of the target vehicle within the preset time period includes: Based on the longitudinal velocity and yaw rate of the target vehicle, the target curvature of the target vehicle is calculated, and the radius of the arc corresponding to the target curvature is calculated based on the target curvature. The pose of the target vehicle at each predicted time point within a preset time period is calculated based on the arc radius corresponding to the target curvature and the target curvature. The combination sequence of the poses of the target vehicle at each predicted time point within a preset time period is taken as the motion trajectory of the target vehicle within the preset time period.

9. The method according to claim 8, characterized in that, The step of calculating the target curvature of the target vehicle based on its longitudinal velocity and yaw rate, and then calculating the radius of the arc corresponding to the target curvature, includes: For the longitudinal speed of the target vehicle being greater than or equal to a high-speed threshold, a reference curvature is calculated based on the yaw rate of the target vehicle and the longitudinal speed as the target curvature; For the longitudinal speed of the target vehicle being less than or equal to a low speed threshold, a smooth curvature is calculated as the target curvature based on a preset sampling time, a preset filtering time constant, a preset center offset coefficient, and the rear axle center curvature of the target vehicle. The target curvature is calculated based on the reference curvature, the smooth curvature, and the center offset coefficient, corresponding to the longitudinal speed of the target vehicle being greater than the low speed threshold and less than the high speed threshold. The radius of the arc corresponding to the target curvature is the reciprocal of the target curvature.

10. A vehicle-mounted device, characterized in that, include: At least one memory and at least one processor, the memory being coupled to the processor; the memory being used to store computer program code / instructions; when the computer program code / instructions are executed by the processor, causing the vehicle-mounted device to perform the method of any one of claims 1 to 9.

11. A vehicle, characterized in that, The vehicle includes the on-board equipment as described in claim 10.

12. A readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed on the vehicle-mounted device, cause the vehicle-mounted device to perform the method of any one of claims 1 to 9.

13. A program product, characterized in that, When the program product is run on an in-vehicle device, it causes the in-vehicle device to perform the method of any one of claims 1 to 9.

Images