Method and device for determining transverse distance of target vehicle, equipment and medium

Abstract

The invention discloses a method, device and equipment for determining the transverse distance of a target vehicle and a medium, and belongs to the field of automatic driving, and the method comprises the steps: obtaining the target driving parameters of the target vehicle and obtaining the driving parameters of the vehicle when the target vehicle exists in front of a road on which the vehicle travels; performing risk assessment according to the target driving parameter and the self-driving parameter to obtain an assessment result; if the assessment result is that the collision risk exists, the transverse distance of the target vehicle is determined based on the target driving parameters and the driving parameters of the vehicle, and the transverse distance is the distance between the vehicle body edge of the target vehicle and the left and right channel sidelines of the road. According to the method, the transverse distance detection is triggered only when the two vehicles have the collision risk, frequent calculation of non-threat targets is avoided, calculation power resource occupation is reduced, the resource utilization rate is improved, response delay of the vehicle control end due to frequent data input can be avoided, unnecessary forced movement is reduced, and the driving smoothness is improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus, device, and medium for determining the lateral distance of a target vehicle. Background Technology

[0002] With the rapid development of automotive intelligence, vehicles are becoming increasingly sophisticated in their intelligent features, and driver assistance functions are becoming more and more widespread. Typical driver assistance systems operate based on the driver's set cruise speed and following distance. When there are no vehicles ahead, the system controls the vehicle to travel at the driver's set cruise speed; when there are vehicles ahead and their speed is less than or equal to the driver's set cruise speed, the system controls the vehicle to follow the vehicle ahead based on the following distance; when the speed of the vehicle ahead exceeds the driver's set cruise speed, the system controls the vehicle to travel at the driver's set cruise speed.

[0003] The presence of a target vehicle making a lane-changing maneuver (including cutting in and out) significantly impacts the control of assisted driving. Therefore, lane-changing behavior detection and judgment are necessary when using assisted driving. One common method is as follows: when lane markings are present, the front camera detects when the vehicle in front crosses the left or right lane line, indicating that the vehicle in front is cutting out; when lane markings are absent, the vehicle's path is first estimated, and then the lateral distance to the vehicle in front is detected using the front millimeter-wave radar and / or the front camera. When the lateral distance of the vehicle in front exceeds the left or right lane line estimated by the assisted driving system, it is determined that the vehicle in front has cut out.

[0004] However, the above method has the following technical problems: When the target vehicle on the road ahead maintains a sufficient distance from the vehicle or is traveling at a faster speed than the vehicle ahead, the current driver assistance function of the vehicle will not be affected regardless of whether the target vehicle changes lanes (enters or exits). However, after activating the driver assistance function, it is necessary to constantly detect lateral distances and predict lane exits of vehicles around the vehicle ahead, which will consume a large amount of the vehicle's computing resources, causing response delays on the vehicle control end. In high-speed driving or complex multi-target scenarios, this delay may lead to a collision risk. Summary of the Invention

[0005] This invention provides a method, apparatus, circuit, device, and medium for determining the lateral distance of a target vehicle, which can solve one or more technical problems existing in the prior art.

[0006] A first aspect of the present invention provides a method for determining the lateral distance of a target vehicle, the method comprising: When there is a target vehicle ahead of the vehicle on the road it is traveling on, obtain the target vehicle's driving parameters and obtain the vehicle's own driving parameters. A risk assessment is performed based on the target driving parameters and the vehicle's own driving parameters to obtain an assessment result. The risk assessment is a process to determine whether there is a risk of collision between the target vehicle and the vehicle itself. If the assessment result indicates a collision risk, the lateral distance of the target vehicle is determined based on the target driving parameters and the vehicle's own driving parameters. The lateral distance is the distance between the edge of the target vehicle's body and the left and right lane lines of the road.

[0007] A second aspect of the present invention provides a device for determining the lateral distance of a target vehicle, the device comprising: The acquisition module is used to acquire the target driving parameters of the target vehicle and the driving parameters of the vehicle itself when there is a target vehicle ahead of the vehicle on the road it is traveling on. The assessment module is used to perform a risk assessment based on the target driving parameters and the vehicle's own driving parameters, and obtain an assessment result. The risk assessment is a process to determine whether there is a collision risk between the target vehicle and the vehicle itself. The determination module is used to determine the lateral distance of the target vehicle based on the target driving parameters and its own driving parameters if the assessment result indicates a collision risk. The lateral distance is the distance between the edge of the target vehicle and the left and right lane lines of the road.

[0008] Compared to existing technologies, the lateral distance determination method, apparatus, device, and medium for a target vehicle provided in this invention have the following advantages: This invention can acquire the target vehicle's driving parameters and the vehicle's own driving parameters when a target vehicle is ahead on the road the vehicle is traveling on; perform a risk assessment based on the target and own driving parameters to obtain an assessment result; if the assessment result indicates a collision risk, determine the lateral distance to the target vehicle based on the target and own driving parameters; if the assessment result indicates no collision risk, maintain the current driving state. This invention can first determine whether there is a collision risk between the vehicle and the vehicle in front, and only trigger lateral distance detection when a collision risk exists, and then perform subsequent intelligent driving control based on the lateral distance detection result; triggering only when there is a collision risk avoids frequent calculations for non-threatening targets, not only reducing the computational resources occupied by frequent calculations and improving resource utilization, but also avoiding response delays at the vehicle control end caused by frequent data input, reducing unnecessary forced movements, avoiding jerking sensations, and improving driving smoothness. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating a method for determining the lateral distance of a target vehicle according to an embodiment of the present invention; Figure 2This is a schematic diagram of the road edge line of a vehicle provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a device for determining the lateral distance of a target vehicle according to an embodiment of the present invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] With the rapid development of automotive intelligence, vehicles are becoming increasingly sophisticated in their intelligent features, and driver assistance functions are becoming more and more widespread. Typical driver assistance systems operate based on the driver's set cruise speed and following distance. When there are no vehicles ahead, the system controls the vehicle to travel at the driver's set cruise speed; when there are vehicles ahead and their speed is less than or equal to the driver's set cruise speed, the system controls the vehicle to follow the vehicle ahead based on the following distance; when the speed of the vehicle ahead exceeds the driver's set cruise speed, the system controls the vehicle to travel at the driver's set cruise speed.

[0012] The presence of a target vehicle making a lane-changing maneuver (including cutting in and out) significantly impacts the control of assisted driving. Therefore, lane-changing behavior detection and judgment are necessary when using assisted driving. One common method is as follows: when lane markings are present, the front camera detects when the vehicle in front crosses the left or right lane line, indicating that the vehicle in front is cutting out; when lane markings are absent, the vehicle's path is first estimated, and then the lateral distance to the vehicle in front is detected using the front millimeter-wave radar and / or the front camera. When the lateral distance of the vehicle in front exceeds the left or right lane line estimated by the assisted driving system, it is determined that the vehicle in front has cut out.

[0013] However, the above method has the following technical problems: When the target vehicle on the road ahead maintains a sufficient distance from the vehicle or is traveling at a faster speed than the vehicle ahead, the current driver assistance function of the vehicle will not be affected regardless of whether the target vehicle changes lanes (enters or exits). However, after activating the driver assistance function, it is necessary to constantly detect lateral distances and predict lane exits of vehicles around the vehicle ahead, which will consume a large amount of the vehicle's computing resources, causing response delays on the vehicle control end. In high-speed driving or complex multi-target scenarios, this delay may lead to a collision risk.

[0014] To address the aforementioned issues, the following detailed description and explanation will be provided through specific embodiments of a method, apparatus, device, and medium for determining the lateral distance of a target vehicle as provided in this application.

[0015] To address the technical problem of existing technologies requiring constant lateral distance detection and cut-out prediction of vehicles on the road ahead after activating assisted driving functions, which consumes significant computing resources, this paper refers to... Figure 1 The diagram shows a flowchart of a method for determining the lateral distance of a target vehicle according to an embodiment of the present invention.

[0016] In one embodiment, the method for determining the lateral distance of the target vehicle is applicable to the vehicle's control system and may be an in-vehicle terminal.

[0017] As an example, the method for determining the lateral distance of the target vehicle may include: S11. When there is a target vehicle ahead of the road on which the vehicle is traveling, obtain the target vehicle's driving parameters and obtain the vehicle's own driving parameters.

[0018] In one embodiment, when the vehicle activates its intelligent assisted driving function, it can detect whether there are vehicles ahead using a front camera or a front millimeter-wave radar. Specifically, it can detect whether there are vehicles ahead of the vehicle's current lane or the road ahead. If a vehicle is found, it is identified as the target vehicle.

[0019] Since the lane markings on the road your vehicle is currently traveling on may be clear or unclear, to avoid misjudging a target vehicle ahead due to an incorrect lane marking, you can first determine the validity of the lane markings. Only if they are valid should you then determine the target vehicle ahead.

[0020] Specifically, the processor of the pre-set forward-facing camera can detect whether the lane lines are valid. Once the lane lines are determined to be valid, it can output the validity of the left and right lane lines, as well as the third-order polynomial fitted by the left and right lane lines.

[0021] Reference Figure 2 The diagram shows a schematic of the road edge line of a vehicle according to an embodiment of the present invention.

[0022] In one operating mode, the third-order fitting formula for the left lane line is as follows: ; In the above formula, x represents the longitudinal distance from the vehicle itself to the target vehicle, with the origin at the vehicle itself; P ll(x) represents the longitudinal distance to the target vehicle. Here, ll_C0, ll_C1, ll_C2, and ll_C3 are known parameters provided by the camera processor. The left lane line validity LL_Status is preset to be output.

[0023] Similarly, the third-order fitting formula for the right lane line is as follows: ; In the above formula, x represents the longitudinal distance from the vehicle itself to the target vehicle, with the origin at the vehicle itself; P rl (x) represents the longitudinal distance to the target vehicle. Here, rl_C0, rl_C1, rl_C2, and rl_C3 are known parameters provided by the camera processor. The default setting is to output the validity of the right lane line as RL_Status.

[0024] Meanwhile, based on the vehicle's yaw rate and steering wheel angle, a third-order polynomial was derived for fitting the vehicle's trajectory, as follows: ; In the above formula, x is the longitudinal distance of the target vehicle with the vehicle itself as the origin; Pv(x) is the longitudinal distance of the target vehicle. v_C0, v_C1, v_C2, and v_C3 are known parameters given by the ADAS controller; this problem is commonly solved in the industry and therefore assumed to be known.

[0025] Based on the above known conditions, the boundary of the vehicle lane is designed as follows: 1. When both left and right lanes are valid, the boundaries of the vehicle lane are the left and right lanes. That is, the left side is... The right side is .

[0026] 2. If the left lane line is valid but the right lane line is invalid, the boundary of the vehicle lane needs to be supplemented by the right lane line. That is, the left lane is... The right side is designed as PLWCom represents lane width compensation, which is a calibrated value. The reference calibrated value given here is 3.8m.

[0027] 3. If the right-side line is valid but the left-side line is invalid, the boundary of the vehicle lane needs to be supplemented by the right-side line. That is, the right side is... The right side is designed as PLWCom represents the vehicle width compensation, which is a calibrated value. The reference calibration parameter given here is 3.8m.

[0028] 4. When both left and right lane lines are invalid, the left lane boundary is designed based on the trajectory reference line obtained from the vehicle's motion state as described above: The right-side passage boundary is: .

[0029] The formulas for the left and right lanes of the driving lane after the above process are given below.

[0030] The left-hand passage on the left is: .

[0031] The right passage on the right is: .

[0032] After determining the left and right lanes of the road, it is possible to determine whether there is a target vehicle in this lane, as well as the lateral distance between the target vehicle and the left and right lanes, and thus determine whether the vehicle has made any road-changing behavior of cutting in or out.

[0033] Alternatively, to simplify the process, when a vehicle in front crosses the left or right lane line, it can be determined that a vehicle has cut in or out.

[0034] To avoid misjudgment, the target vehicle's driving parameters and the vehicle's own driving parameters can be obtained.

[0035] In one operating mode, data on vehicles ahead is directly collected through the vehicle's own sensors, making it suitable for most common driving scenarios.

[0036] For example, a forward-facing camera (visual perception) can acquire target driving parameters, including the instantaneous speed, relative position, heading angle, and behavioral position (i.e., position within the lane) of the vehicle ahead. Acceleration can be estimated by combining this with inter-frame analysis. Its working principle involves capturing images of the road ahead using a camera, employing image recognition algorithms (such as YOLO and CNN) to detect features such as the vehicle's outline, license plate, and headlights, and calculating relative motion parameters based on inter-frame pixel displacement. Combined with the vehicle's speed and yaw rate, absolute parameters are obtained through coordinate system transformation.

[0037] For example, target driving parameters can be obtained through front millimeter-wave radar (radar sensing), including the longitudinal speed, lateral speed, and relative acceleration of the vehicle in front, indirectly inferring the heading angle (based on lateral movement trends). Its working principle involves emitting millimeter-wave signals, receiving reflected signals from vehicles in front, calculating relative speed and distance using the Doppler effect, fitting acceleration based on multi-frame data, determining the vehicle's lateral position through signal coverage, and deriving the heading angle of the vehicle in front by combining the vehicle's trajectory with the signal's own.

[0038] For example, target driving parameters can be obtained through LiDAR (high-precision perception), including: the three-dimensional position (x / y / z coordinates), precise speed, acceleration, heading angle, and behavioral position (centimeter-level lane positioning) of the vehicle in front, supporting short-term position prediction.

[0039] Alternatively, the vehicle can obtain its own driving parameters through its own sensors.

[0040] Specifically, the vehicle itself may include: a steering wheel angle sensor, a yaw rate sensor, a wheel speed sensor, an acceleration sensor, a forward-facing camera, a forward-facing camera processor, and an ADAS processor.

[0041] The steering wheel angle sensor transmits the steering wheel angle, and it has a known and clear correspondence with the front wheel angle.

[0042] A yaw rate sensor transmits the vehicle's yaw rate value, which is used to describe the vehicle's steering state.

[0043] Wheel speed sensors describe the rotational speed at the wheel end, which is used for corresponding vehicle speed estimation.

[0044] An acceleration sensor describes the vehicle's current acceleration, which is used to estimate the vehicle's future speed.

[0045] A forward-facing camera that transmits the images it captures.

[0046] The forward-facing camera processor processes the camera images and outputs lane line information, the position of the vehicle in front, and information such as lateral and longitudinal vehicle speeds and acceleration.

[0047] The ADAS processor receives information from the forward-looking camera and the vehicle's motion status information. After calculation, it outputs the required acceleration and deceleration information to the actuator.

[0048] S12. Perform a risk assessment based on the target driving parameters and the vehicle's own driving parameters to obtain an assessment result, wherein the risk assessment is a process to determine whether there is a collision risk between the target vehicle and the vehicle itself.

[0049] Risk assessment can be performed based on the target vehicle's driving parameters and the vehicle's own driving parameters. This risk assessment is a process to determine whether there is a risk of collision between the target vehicle and the vehicle itself, and an assessment result is obtained.

[0050] Specifically, a risk assessment value can be calculated using target driving parameters and the vehicle's own driving parameters, and the magnitude of the risk assessment value can be used to determine whether a collision between the two vehicles will occur.

[0051] If a collision is possible between the two vehicles, the current intelligent driving functions need to be adjusted to trigger subsequent detection and processing to ensure the driver's safety.

[0052] If there is no risk of collision between the two vehicles, the cutting-in or cutting-out behavior of the target vehicle ahead will not affect the driving status of the vehicle itself, and no further inspection or processing is required.

[0053] In an optional embodiment, a risk assessment value can be calculated based on target driving parameters and the vehicle's own driving parameters. The risk assessment value is then used to assess whether a collision between the two vehicles will occur. As an example, the step of performing a risk assessment based on the target driving parameters and the vehicle's own driving parameters to obtain the assessment result may include the following sub-steps: S121. Calculate the risk assessment value using the target driving parameters and the self-driving parameters.

[0054] S122. If the risk assessment value is greater than the preset risk value, the assessment result is determined to be that there is a collision risk.

[0055] S123. If the risk assessment value is less than or equal to the preset risk value, the assessment result is determined to be that there is no collision risk.

[0056] Specifically, a risk assessment value can be calculated using target driving parameters and the vehicle's own driving parameters. If the risk assessment value is greater than a preset risk value, the assessment result is determined to be a collision risk. If the risk assessment value is less than or equal to the preset risk value, the assessment result is determined to be no collision risk.

[0057] In one operating mode, the preset risk value can be 0. If the risk assessment value is less than or equal to 0, the vehicle terminal can output the Detected_Flg flag as 0, that is, the collision risk is 0; if the risk assessment value is greater than 0, the vehicle terminal can output the Detected_Flg flag as 1.

[0058] If the onboard terminal outputs a Detected_Flg flag of 1, it predicts that a collision between the two vehicles is likely. Detected_Flg is a collision prediction flag.

[0059] When the risk of collision is zero, no further action is taken, because regardless of whether the vehicle in front has a tendency to cut out, it will not affect your own vehicle.

[0060] In one embodiment, the target driving parameters include: target vehicle acceleration, target vehicle speed, and target vehicle longitudinal distance; the self-driving parameters include: self-vehicle acceleration and self-vehicle speed.

[0061] As an example, the step of calculating the risk assessment value using the target driving parameters and the self-driving parameters may include the following sub-steps: S1211. Determine the speed risk value using the target vehicle speed and the vehicle's own speed, and determine the acceleration risk value using the target vehicle acceleration, the target vehicle longitudinal distance, and the vehicle's own acceleration.

[0062] S1212. Calculate the difference between the velocity risk value and the acceleration risk value to obtain the risk assessment value.

[0063] In one embodiment, the difference between the speed of the target vehicle and the speed of the vehicle itself can be calculated, and then the square of the difference can be calculated to obtain the speed risk value.

[0064] In one embodiment, the difference between the acceleration of the target vehicle and the acceleration of the vehicle itself can be calculated, and then the product of the difference and the longitudinal distance of the target vehicle can be calculated to obtain the acceleration risk value.

[0065] Finally, the risk assessment value can be obtained by calculating the difference between the speed risk value and the acceleration risk value.

[0066] Specifically, the risk assessment value can be calculated as follows: ; In the above formula, The longitudinal speed of the target vehicle; The longitudinal acceleration of the target vehicle; The longitudinal position of the target vehicle; The longitudinal speed of the vehicle itself; The longitudinal acceleration of the vehicle itself.

[0067] S13. If the assessment result indicates a collision risk, the lateral distance of the target vehicle is determined based on the target driving parameters and the vehicle's own driving parameters. The lateral distance is the distance between the edge of the target vehicle's body and the left and right lane lines of the road.

[0068] In one embodiment, if the assessment result indicates a collision risk, the lateral distance of the target vehicle can be determined based on the target driving parameters and its own driving parameters, wherein the lateral distance is the distance between the edge of the target vehicle body and the left and right lane lines of the road.

[0069] Then, based on the distance between the edge of the target vehicle and the left and right lane lines of the road, it is determined whether the target vehicle will change lanes, and the intelligent driving function is adjusted according to the lane-changing behavior of the target vehicle in front.

[0070] In one embodiment, determining the lateral distance of the target vehicle based on the target driving parameters and the vehicle's own driving parameters may include the following sub-steps: S131. Calculate the collision time based on the target driving parameters and the self-driving parameters, wherein the collision time is the predicted time when the target vehicle and the self-driving vehicle will collide.

[0071] S132. Determine the edge distance and the predicted distance using the target driving parameters, wherein the edge distance is the lateral distance between the left and right edges of the target vehicle and its own center of mass when the collision time is reached, and the predicted distance is the lateral distance between the vehicle and the left and right lane lines of the road it is traveling on when the collision time is reached.

[0072] S133. Calculate the difference between the edge distance and the predicted distance to obtain the lateral distance.

[0073] In one embodiment, the collision time can be calculated based on the target driving parameters and the vehicle's own driving parameters. This collision time is the predicted time when the target vehicle and the vehicle itself will collide.

[0074] Based on the longitudinal motion mechanism model, assuming a collision at time t, the motion relationship between the vehicle and the vehicle in front at time t should be: ; in, It is the distance the car travels at time t. It represents the distance traveled by the vehicle in front at time t. It is the longitudinal distance between the vehicle in front and the vehicle itself at the initial moment.

[0075] That is, assuming the collision occurs at time t, the distance traveled by the vehicle is equal to the distance traveled by the vehicle in front plus the distance of the vehicle in front at the current time plus the preset safety distance.

[0076] In this patent, to prevent safety issues caused by backend processing, a safety distance compensation amount is introduced, which is related to the current vehicle speed. The revised formula is: ; For ease of software implementation and understanding of algorithm logic, here we set: This assumes that even in the event of a collision, there is still a safe distance from the vehicle in front, thus improving the safety of the algorithm.

[0077] in, ; in, ; Time T is the collision time, where Predict the longitudinal distance of the vehicle in front at time t. The current longitudinal distance is the distance to the vehicle in front. It is the longitudinal acceleration of the vehicle in front at the current moment.

[0078] It should be noted that, since accelerometers typically exhibit significant fluctuations, a filter is applied to the acceleration input to prevent abnormal results caused by large acceleration fluctuations. The filter formula is as follows: ; In the above formula, appropriately reducing the parameter s can ensure the smoothness of the target object's acceleration curve. Here, acceleration refers to the acceleration of the target vehicle.

[0079] It should also be noted that when the target vehicle's ID changes, i.e., the Reset flag is set to 1, the judgment logic is as follows: When the Reset flag is 1, and This ensures that different target vehicles are not affected by each other's previous filtering states.

[0080] Since an assessment can be made of the potential collision between the two vehicles, the collision time can be calculated, and the positional relationship between the two vehicles at the time of the collision can be determined.

[0081] For example, if the lateral distance to the target vehicle ahead is large enough at the time of collision, it indicates that the target vehicle may have cut out. If the lateral distance to the target vehicle ahead is small at the time of collision, it indicates that the target vehicle may have remained in its lane.

[0082] Next, the edge distance and predicted distance can be calculated using the target driving parameters. The edge distance is the lateral distance between the left and right edges of the target vehicle and its own center of gravity at the time of collision. The predicted distance is the lateral distance between the target vehicle and the left and right lane lines of the road at the time of collision. Finally, the difference between the edge distance and the predicted distance can be calculated to obtain the lateral distance. The lateral distance refers to the closest distance between the edge of the target vehicle and the left or right lane line.

[0083] As an example, the calculation of the collision time based on the target driving parameters and the self-driving parameters may include the following sub-steps: S1311. Calculate the first reference time and the second reference time using the target driving parameters and the self-driving parameters.

[0084] S1312. Determine the collision time based on the first reference time and the second reference time.

[0085] In one embodiment, the first reference time can be calculated as follows: ; The second reference time can be calculated as follows: ; In the above formula, △ is the risk assessment value, which can be represented by the following formula: .

[0086] The final collision time can be calculated as follows: .

[0087] In one embodiment, the target driving parameters include the heading angle of the target vehicle, wherein, as an example, the operation of determining the edge distance may include the following sub-steps: S21. Determine the position distance of the target vehicle when the collision time is reached, wherein the position distance is the lateral distance from the center of the target vehicle to the center of the vehicle itself.

[0088] S22. Determine the edge distance using the position distance and the heading angle.

[0089] The collision time has already been obtained based on longitudinal information and the assumption that the vehicle in front has no lateral speed. Here, we can introduce the lateral speed of the vehicle in front and predict the cutting intention based on the collision time.

[0090] As shown in the kinematic relationship diagram Figure 2 As shown, the lateral speed information of the vehicle itself is not considered here, because this invention assumes that the vehicle is driving normally along the predicted trajectory line, and only predicts and corrects the behavior and status of the vehicle in front.

[0091] Furthermore, a pre-defined coordinate system is used, with leftward movement from the vehicle's centerline considered positive and rightward movement negative. The target vehicle's position at time t is known to be: And assume the heading angle of the target object There is no change during this process. It should be noted that P... x_obj P is the longitudinal distance from the rear of the target vehicle to the front bumper of the vehicle itself. y_obj Let t be the lateral distance from the center of the target vehicle to the center of the vehicle itself. Therefore, referring to the diagram, based on the vehicle motion mechanism and geometric relationships, the lateral distance between the right edge of the target vehicle and the center of mass of the vehicle itself at time t is calculated to obtain the position distance.

[0092] Specifically, the distance between the right edge of the target vehicle and its own center of gravity can be represented by the following formula: ; The calculations for Ls1 and Ls2 are as follows: ; ; The lateral distance of the right edge of the target vehicle relative to its own center of gravity can be expressed as follows: ; in, The length of the vehicle in front. For the width of the vehicle in front, This is the heading angle.

[0093] Similarly, when the target vehicle cuts out to the right, the lateral distance of the target vehicle's left edge relative to its own center of mass at time t can be calculated. This gives the positional distance of the target vehicle's left edge relative to its own center of mass at time t. The specific calculation is shown in the following formula: ; Right now: .

[0094] As an example, the operation of determining the predicted distance may include the following sub-steps: S31. Determine the longitudinal distance of the target vehicle when the collision time is reached, wherein the longitudinal distance is the longitudinal distance between the target vehicle and its own vehicle when the collision time is reached.

[0095] S32. Calculate the predicted distance using the longitudinal distance.

[0096] In one embodiment, the longitudinal distance of the target vehicle at the time of collision can be determined, where the longitudinal distance is the longitudinal distance between the target vehicle and its own vehicle at time t of the collision time.

[0097] Specifically, the formula for calculating the longitudinal distance is: ; Due to limitations imposed by the boundaries of L2-level assisted driving functions and perception performance, a maximum value constraint is applied to the longitudinal distance to the target object here. .

[0098] It should be noted that since a safety distance was already reserved when calculating the collision time in the previous text, the longitudinal distance calculated here is smaller than the longitudinal distance of the actual collision time. It is also more conservative and safer for subsequent calculations.

[0099] Based on the longitudinal distance between the target vehicle and the vehicle at time t, and the polynomials of the left and right lane edges obtained earlier, the lateral distance between the left and right lane lines and the vehicle at time t can be obtained.

[0100] Next, the longitudinal distance of the target vehicle at time t is substituted into the left lane edge line to calculate the predicted distance on the left. Similarly, the longitudinal distance of the target vehicle at time t can be substituted into the right lane edge line to calculate the predicted distance on the right.

[0101] Specifically, the predicted distance on the left can be calculated as follows: .

[0102] The predicted distance on the right can be calculated as follows: .

[0103] After calculating the edge distance and the predicted distance, the difference between the edge distance and the predicted distance can be calculated to obtain the lateral distance.

[0104] It should be noted that, as mentioned above, the origin of the coordinate system is the vehicle, with the left side being positive and the right side being negative.

[0105] Because the calculations are extensive and the input information is highly unstable, a low-pass filter can be applied to the edge distance and predicted distance of the target vehicle to reduce input fluctuations. Furthermore, the change in the target vehicle ID can be used as a reset condition to prevent the later selected target from being affected by the previously selected target.

[0106] Specifically, the lateral distance between the edge of the target vehicle and the left side line at time t can be calculated as follows: .

[0107] The lateral distance between the edge of the target object and the right side line at time t can be calculated as follows: .

[0108] The four inputs are: the lateral distance of the left channel at time t. Horizontal distance of the right channel at time t The lateral distance from the left edge of the target vehicle to its own center of mass at time t. The lateral distance from the right edge of the target vehicle to its own center of mass at time t. .

[0109] By combining "collision time prediction (threat assessment) + lateral distance detection (intent analysis)," we can avoid over-braking targets that are "at risk of collision but about to cut out," while not overlooking real threats that are "at risk of collision but have no intention to cut out."

[0110] For targets that are "at risk of collision but about to cut out" (such as vehicles that cut in at low speed from a distance and then quickly cut out), the intention to cut out is identified by lateral distance detection, the braking intensity of the vehicle is reduced, and the "braking-release" jerking cycle is avoided.

[0111] S14. If the assessment result indicates that there is no risk of collision, then maintain the current driving state.

[0112] As explained above, if the assessment results indicate that there is no risk of collision, the current driving status can be maintained without further inspection or processing.

[0113] If the assessment result indicates that there is no risk of collision, it means that there is no conflict in the longitudinal movement of the vehicle in front and the vehicle itself (such as the vehicle in front moving much faster than the vehicle itself, or the longitudinal distance continuously increasing). Regardless of whether the vehicle in front cuts out, it will not pose a threat to the vehicle itself, and there is no need to activate the lateral distance detection.

[0114] Lateral distance detection involves multi-sensor data fusion, geometric relationship calculation, and low-pass filtering, which are complex computations. Triggering only when there is a collision risk avoids frequent calculations for non-threatening targets, reduces unnecessary fluctuations in control input parameters, and improves driving smoothness.

[0115] Only when a target object is likely to collide with the vehicle does its "intent to cut out" become crucial in influencing the control strategy. Triggering lateral distance detection at this point can accurately determine whether the target object is "continuously occupying the vehicle's lane (requiring forced braking)" or "about to cut out of the lane (requiring reduced braking)," thus solving the "balance problem between safety and smoothness."

[0116] Since no further detection or processing is required, computing resources can be released, thereby improving resource utilization and avoiding delays caused by the occupation of computing resources.

[0117] In this embodiment, the present invention provides a method for determining the lateral distance of a target vehicle. Its advantages are as follows: When a target vehicle is located ahead of the vehicle on the road it is traveling on, the present invention can acquire the target vehicle's driving parameters and the vehicle's own driving parameters; perform a risk assessment based on the target and own driving parameters to obtain an assessment result; if the assessment result indicates a collision risk, then determine the lateral distance of the target vehicle based on the target and own driving parameters; if the assessment result indicates no collision risk, then maintain the current driving state. The present invention can first determine whether there is a collision risk between the vehicle and the vehicle in front, and only trigger lateral distance detection when a collision risk exists, and then perform subsequent intelligent driving control based on the lateral distance detection result; triggering only when there is a collision risk avoids frequent calculations for non-threatening targets, not only reducing the computational resources occupied by frequent calculations and improving resource utilization, but also avoiding response delays at the vehicle control end caused by frequent data input, reducing unnecessary forced movements, avoiding jerking sensations, and improving driving smoothness.

[0118] This invention also provides a device for determining the lateral distance of a target vehicle, see [link to relevant documentation]. Figure 3 The diagram shows a schematic representation of a device for determining the lateral distance of a target vehicle according to an embodiment of the present invention.

[0119] As an example, the lateral distance determination device for the target vehicle may include: The acquisition module 201 is used to acquire the target driving parameters of the target vehicle and the driving parameters of the vehicle itself when there is a target vehicle in front of the vehicle on the road it is traveling on. The assessment module 202 is used to perform a risk assessment based on the target driving parameters and the vehicle's own driving parameters, and obtain an assessment result, wherein the risk assessment is a process of determining whether there is a collision risk between the target vehicle and the vehicle itself; The determination module 203 is used to determine the lateral distance of the target vehicle based on the target driving parameters and its own driving parameters if the assessment result indicates that there is a collision risk. The lateral distance is the distance between the edge of the target vehicle body and the left and right lane lines of the road.

[0120] Optionally, the step of performing a risk assessment based on the target driving parameters and the user's own driving parameters to obtain an assessment result includes: The risk assessment value is calculated using the target driving parameters and the vehicle's own driving parameters; If the risk assessment value is greater than the preset risk value, the assessment result is determined to be that there is a collision risk; If the risk assessment value is less than or equal to the preset risk value, the assessment result is determined to be that there is no collision risk.

[0121] Optionally, the target driving parameters include: target vehicle acceleration, target vehicle speed, and target vehicle longitudinal distance; the self-driving parameters include: self-driving vehicle acceleration and self-driving vehicle speed; the calculation of the risk assessment value using the target driving parameters and the self-driving parameters includes: A speed risk value is determined using the target vehicle speed and the vehicle's own speed, and an acceleration risk value is determined using the target vehicle acceleration, the target vehicle longitudinal distance, and the vehicle's own acceleration. The risk assessment value is obtained by calculating the difference between the speed risk value and the acceleration risk value.

[0122] Optionally, determining the lateral distance of the target vehicle based on the target driving parameters and the vehicle's own driving parameters includes: The collision time is calculated based on the target driving parameters and the vehicle's own driving parameters. The collision time is the predicted time when the target vehicle and the vehicle itself will collide. The edge distance and predicted distance are determined using the target driving parameters, wherein the edge distance is the lateral distance between the left and right edges of the target vehicle and its own center of mass at the time of collision, and the predicted distance is the lateral distance between the vehicle and the left and right lane lines of the road it is traveling on at the time of collision. The difference between the edge distance and the predicted distance is calculated to obtain the lateral distance.

[0123] Optionally, calculating the collision time based on the target driving parameters and the self-driving parameters includes: Calculate the first reference time and the second reference time using the target driving parameters and the self-driving parameters; The collision time is determined based on the first reference time and the second reference time.

[0124] Optionally, the target driving parameters include the heading angle of the target vehicle, and the operation of determining the edge distance includes: Determine the position distance of the target vehicle at the time of the collision, wherein the position distance is the lateral distance from the center of the target vehicle to the center of the vehicle itself; The edge distance is determined using the positional distance and the heading angle.

[0125] Optionally, the operation of determining the predicted distance includes: Determine the longitudinal distance of the target vehicle at the time of collision, wherein the longitudinal distance is the longitudinal distance between the target vehicle and its own vehicle at the time of collision. The predicted distance is calculated using the longitudinal distance.

[0126] Those skilled in the art will understand that, for ease of description and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0127] Furthermore, this application also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the lateral distance of a target vehicle as described in the above embodiments.

[0128] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a computer-executable program for causing a computer to perform the method for determining the lateral distance of a target vehicle as described in the above embodiments.

[0129] In the description of the embodiments of the present invention, it should be noted that the terms "above," "below," etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. When an element such as a layer, region, or substrate is referred to as being "above" or "on top of" another element, it may be directly on the other element, or there may be an intermediate element. Conversely, when an element is referred to as being "directly on" or "above" another element, there is no intermediate element. It should also be understood that when an element is referred to as being "below" or "under" another element, it may be directly below or under the other element, or there may be an intermediate element. Conversely, when an element is referred to as being "directly below" or "under" another element, there is no intermediate element. Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0130] Those skilled in the art will understand that embodiments of this application may also include computer program products. Therefore, this application may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), devices, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0134] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the lateral distance of a target vehicle, characterized in that, The method includes: When there is a target vehicle ahead of the vehicle on the road it is traveling on, obtain the target vehicle's driving parameters and obtain the vehicle's own driving parameters. A risk assessment is performed based on the target driving parameters and the vehicle's own driving parameters to obtain an assessment result. The risk assessment is a process to determine whether there is a risk of collision between the target vehicle and the vehicle itself. If the assessment result indicates a collision risk, the lateral distance of the target vehicle is determined based on the target driving parameters and the vehicle's own driving parameters. The lateral distance is the distance between the edge of the target vehicle's body and the left and right lane lines of the road.

2. The method for determining the lateral distance of a target vehicle according to claim 1, characterized in that, The risk assessment based on the target driving parameters and the self-driving parameters, to obtain the assessment result, includes: The risk assessment value is calculated using the target driving parameters and the vehicle's own driving parameters; If the risk assessment value is greater than the preset risk value, the assessment result is determined to be that there is a collision risk; If the risk assessment value is less than or equal to the preset risk value, the assessment result is determined to be that there is no collision risk.

3. The method for determining the lateral distance of a target vehicle according to claim 2, characterized in that, The target driving parameters include: target vehicle acceleration, target vehicle speed, and target vehicle longitudinal distance; the self-driving parameters include: self-driving vehicle acceleration and self-driving vehicle speed; the calculation of the risk assessment value using the target driving parameters and the self-driving parameters includes: A speed risk value is determined using the target vehicle speed and the vehicle's own speed, and an acceleration risk value is determined using the target vehicle acceleration, the target vehicle longitudinal distance, and the vehicle's own acceleration. The risk assessment value is obtained by calculating the difference between the speed risk value and the acceleration risk value.

4. The method for determining the lateral distance of a target vehicle according to claim 1, characterized in that, Determining the lateral distance of the target vehicle based on the target driving parameters and its own driving parameters includes: The collision time is calculated based on the target driving parameters and the vehicle's own driving parameters. The collision time is the predicted time when the target vehicle and the vehicle itself will collide. The edge distance and predicted distance are determined using the target driving parameters, wherein the edge distance is the lateral distance between the left and right edges of the target vehicle and its own center of mass at the time of collision, and the predicted distance is the lateral distance between the vehicle and the left and right lane lines of the road it is traveling on at the time of collision. The difference between the edge distance and the predicted distance is calculated to obtain the lateral distance.

5. The method for determining the lateral distance of a target vehicle according to claim 4, characterized in that, The calculation of the collision time based on the target driving parameters and the self-driving parameters includes: Calculate the first reference time and the second reference time using the target driving parameters and the self-driving parameters; The collision time is determined based on the first reference time and the second reference time.

6. The method for determining the lateral distance of a target vehicle according to claim 4, characterized in that, The target driving parameters include the heading angle of the target vehicle, and the operation of determining the edge distance includes: Determine the position distance of the target vehicle at the time of the collision, wherein the position distance is the lateral distance from the center of the target vehicle to the center of the vehicle itself; The edge distance is determined using the positional distance and the heading angle.

7. The method for determining the lateral distance of a target vehicle according to claim 4, characterized in that, The operation of determining the predicted distance includes: Determine the longitudinal distance of the target vehicle at the time of collision, wherein the longitudinal distance is the longitudinal distance between the target vehicle and its own vehicle at the time of collision. The predicted distance is calculated using the longitudinal distance.

8. A device for determining the lateral distance of a target vehicle, characterized in that, The device includes: The acquisition module is used to acquire the target driving parameters of the target vehicle and the driving parameters of the vehicle itself when there is a target vehicle ahead of the vehicle on the road it is traveling on. The assessment module is used to perform a risk assessment based on the target driving parameters and the vehicle's own driving parameters, and obtain an assessment result. The risk assessment is a process to determine whether there is a collision risk between the target vehicle and the vehicle itself. The determination module is used to determine the lateral distance of the target vehicle based on the target driving parameters and its own driving parameters if the assessment result indicates a collision risk. The lateral distance is the distance between the edge of the target vehicle and the left and right lane lines of the road.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the program, it implements the method for determining the lateral distance of a target vehicle as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method for determining the lateral distance of a target vehicle as described in any one of claims 1-7.

Images