Method, device and system for automatically driving to avoid parallel cart and medium

Abstract

The invention provides a method, device and system for automatically driving to avoid parallel carts and a medium, and the method comprises the steps: merging cart targets as a motorcade target when the vehicle speed and the vehicle distance are within a preset value within a preset duration; calculating to obtain the predicted parallel duration of the vehicle and the fleet target; when the vehicle accelerates to avoid the motorcade target, the acceleration of the vehicle is calculated, and the speed of the vehicle is increased to the acceleration target speed of the vehicle according to the acceleration of the vehicle; when the vehicle slows down to avoid the motorcade target, the deceleration of the vehicle is calculated, and the following distance from the vehicle to the target is slowed down according to the deceleration of the vehicle. And fusion processing is performed on continuous cart fleet targets, so that the function triggering integrity is higher, and uncomfortable driving caused by frequent acceleration and deceleration of the own vehicle due to repeated advancing and retreating of functions is avoided. And the predicted parallel duration more truly reflects the motion relationship between the vehicle and the fleet target, and unnecessary avoidance is avoided. Acceleration and deceleration are managed according to the lane information and the surrounding vehicle information, and the driving safety is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, system and medium for automatic driving to avoid parallel vehicles. Background Art

[0002] With the continuous development of vehicle autonomous driving, OEMs are paying more and more attention to it, and more and more models are equipped with autonomous driving systems.

[0003] Correspondingly, manufacturers and car owners have increasingly higher requirements for its intelligence level, and the autonomous driving function has gradually developed from simple L2 autonomous driving such as adaptive cruise control (ACC, Adaptive Cruise Control) to L2.5 autonomous driving with navigation function.

[0004] To meet the functional requirements of advanced autonomous driving, the vehicle-side perception level has also been greatly improved, from a single radar and single camera combination to a combination of multiple radars and multiple cameras, and the detectable environmental targets have also been upgraded from a single target in front to multiple targets around the vehicle. At the same time, the introduction of high-precision maps allows the vehicle to obtain more road environment information for behavioral decision-making.

[0005] However, current adaptive cruise control systems pay little attention to the status of vehicles in the side lanes, which results in the risk of the self-controlled vehicle running parallel to large vehicles in the side lanes for a long time, causing a greater sense of driving pressure on the driver and affecting driving safety. Summary of the invention

[0006] In view of this, this summary of the invention is provided to introduce the concepts in a brief form, which will be described in detail in the detailed description section below. This summary of the invention is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to be used to limit the scope of the technical solution claimed for protection.

[0007] The purpose of this application is to provide a method, device, system and medium for automatic driving to avoid parallel large vehicles, which can timely avoid parallel large vehicles in the side lanes and improve driving safety.

[0008] To achieve the above purpose, this application has the following technical solutions:

[0009] In a first aspect, an embodiment of the present application provides a method for automatically driving to avoid parallel vehicles, comprising:

[0010] Obtaining vehicle information of the side lane; comparing the vehicle information of the side lane with preset vehicle type information to screen out large vehicle targets;

[0011] When it is detected that both the front and rear sides of the vehicle are the large vehicle targets, the speed and distance of the large vehicle targets are obtained; when the speed and distance are within the preset values ​​within the preset time, the large vehicle targets are merged as the fleet targets;

[0012] The predicted parallel time between the self-vehicle and the convoy target is calculated based on the absolute value of the difference between the front distance and the rear distance of the self-vehicle and the convoy target along the travel direction, the self-vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost large vehicle among the large vehicle targets;

[0013] When the self-vehicle accelerates to avoid the convoy target, the minimum value among the value of the self-vehicle set speed multiplied by the set speed gain coefficient, the road speed limit value and the curve speed limit value is used as the self-vehicle acceleration target speed;

[0014] The acceleration of the vehicle is calculated according to a preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the speed of the vehicle and a pre-judged acceleration level coefficient, and the speed of the vehicle is accelerated to the acceleration target speed of the vehicle according to the acceleration of the vehicle, so as to accelerate and avoid the vehicle group target;

[0015] When the ego vehicle decelerates to avoid the convoy target, the ego vehicle deceleration is calculated according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the convoy target along the driving direction, the target following distance, the ego vehicle speed and the convoy target speed, and the ego vehicle is decelerated to the target following distance according to the ego vehicle deceleration to decelerate and avoid the convoy target.

[0016] In a possible implementation, the acceleration of the vehicle is calculated according to the preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the vehicle speed and the pre-judged acceleration level coefficient, and is specifically calculated by the following formula:

[0017] a Acc =k 3 *(v Tgt -v Ego )*k Lvl ;

[0018] Among them, a Acc is the acceleration of the vehicle, k 3 is the preset acceleration proportional coefficient, v Tgt is the target vehicle acceleration speed, v Ego is the vehicle speed, k Lvl is the pre-judged acceleration level coefficient.

[0019] In a possible implementation, the deceleration of the vehicle is calculated according to a preset deceleration ratio coefficient, the distance between the vehicle and the target of the convoy along the driving direction, the target following distance, the speed of the vehicle and the target speed of the convoy, and is specifically calculated by the following formula:

[0020] a Dece =k 1 *(d Tuk -d Tgt )+k 2 *(v Ego -v Tuk );

[0021] Among them, a Dece is the vehicle deceleration, k 1 and k 2 is the preset deceleration proportional coefficient, d Tuk is the distance between the vehicle and the convoy target along the driving direction, d Tgt is the target following distance, v Ego is the vehicle speed, v Tuk is the target speed of the fleet.

[0022] In a possible implementation, the deceleration and avoidance is determined by the following steps:

[0023] When the vehicle speed is greater than or equal to the first vehicle speed, and the vehicle does not request braking, and the distance between the vehicle and the convoy target along the driving direction is less than or equal to the first distance, and the predicted parallel time is greater than or equal to the first time and the vehicle speed is within the preset value within the preset time, it is determined to perform the deceleration avoidance.

[0024] In a possible implementation, the acceleration avoidance is determined by the following steps:

[0025] After the deceleration avoidance is performed, and there are no vehicles within the second distance in front of and to the side of the vehicle, and the convoy target is not driving on the side lane line of the vehicle's driving lane, and the predicted parallel time is less than or equal to the second time, and there is no ramp entrance within the third distance in front of the vehicle, it is determined to perform the acceleration avoidance.

[0026] In a possible implementation, the pre-determined acceleration level coefficient is determined by the following steps:

[0027] The pre-judged acceleration level coefficient is calculated based on the distance between the own vehicle and the convoy target perpendicular to the driving direction, as well as the speed of the vehicle in front of the own vehicle and the speed limit of the overtaking lane.

[0028] In a possible implementation, the method further includes:

[0029] When it is detected that the speed of the vehicle in front of the vehicle is lower than the speed of the large vehicle target in front of the vehicle by more than a preset threshold, the speed of the vehicle in front of the vehicle is lower than the lane speed limit by more than a preset threshold, or the large vehicle target in front of the vehicle is less than a preset distance from the driving lane of the vehicle, the acceleration of the vehicle is reduced by a preset level.

[0030] In a second aspect, an embodiment of the present application provides a device for automatically driving to avoid parallel vehicles, comprising:

[0031] A screening unit is used to obtain the vehicle information of the side lane; compare the vehicle information of the side lane with the preset vehicle type information to screen out the large vehicle target;

[0032] A merging unit is used to obtain the vehicle speed and distance of the large vehicle target when it is detected that the vehicle is located in front of and behind the vehicle; when the vehicle speed and the distance are within a preset value within a preset time, merge the large vehicle target as a fleet target;

[0033] A prediction unit is used to calculate the predicted parallel time between the ego vehicle and the convoy target according to the absolute value of the difference between the front distance and the rear distance of the ego vehicle and the convoy target along the travel direction, the ego vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost large vehicle among the large vehicle targets;

[0034] A vehicle speed unit, used for, when the self-vehicle accelerates to avoid the convoy target, using the minimum value of the value of the self-vehicle set speed multiplied by the set vehicle speed gain coefficient, the road speed limit value, and the curve speed limit value as the self-vehicle acceleration target speed;

[0035] an acceleration unit, configured to calculate the acceleration of the vehicle according to a preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the speed of the vehicle and a pre-determined acceleration level coefficient, and accelerate the speed of the vehicle to the acceleration target speed of the vehicle according to the acceleration of the vehicle, so as to accelerate and avoid the vehicle group target;

[0036] The deceleration unit is used to calculate the deceleration of the ego vehicle according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the ego vehicle target along the driving direction, the target following distance, the ego vehicle speed and the ego vehicle target speed when the ego vehicle decelerates to avoid the ego vehicle group target, and decelerate the ego vehicle to the target following distance according to the ego vehicle deceleration to decelerate and avoid the ego vehicle group target.

[0037] In a possible implementation, the acceleration unit is specifically used to calculate the vehicle acceleration, which is specifically calculated by the following formula:

[0038] a Acc =k 3 *(v Tgt -v Ego )*k Lvl ;

[0039] Among them, a Acc is the acceleration of the vehicle, k 3 is the preset acceleration proportional coefficient, v Tgt is the target vehicle acceleration speed, v Ego is the vehicle speed, k Lvl is the pre-judged acceleration level coefficient.

[0040] In a third aspect, an embodiment of the present application provides a system for automatically driving to avoid parallel vehicles, including:

[0041] Memory for storing computer programs;

[0042] A processor is used to implement the steps of the method for automatically driving to avoid parallel vehicles as described above when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, and when the computer program is processed and executed, the steps of the method for automatically driving to avoid parallel vehicles as described above are implemented.

[0044] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0045] The embodiment of the present application provides a method, device, system and medium for automatic driving to avoid parallel large vehicles, the method comprising: obtaining vehicle information of a side lane; comparing the vehicle information of the side lane with preset vehicle type information to screen out large vehicle targets; when it is detected that both the side front and side rear of the own vehicle are large vehicle targets, obtaining the vehicle speed and vehicle distance of the large vehicle targets; when the vehicle speed and vehicle distance are within preset values ​​within a preset time period, merging the large vehicle targets as convoy targets; calculating the predicted parallel time between the own vehicle and the convoy targets based on the absolute value of the difference between the front distance and the rear distance between the own vehicle and the convoy targets along the driving direction, the own vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost large vehicle among the large vehicle targets; when the own vehicle accelerates to avoid When giving way to the convoy target, the minimum value among the set speed of the self-vehicle multiplied by the set speed gain coefficient, the road speed limit value and the curve speed limit value is used as the acceleration target speed of the self-vehicle; the acceleration of the self-vehicle is calculated according to the preset acceleration ratio coefficient, the acceleration target speed of the self-vehicle, the self-vehicle speed and the pre-judged acceleration level coefficient, and the self-vehicle speed is accelerated to the acceleration target speed according to the self-vehicle acceleration to accelerate and avoid the convoy target; when the self-vehicle slows down to avoid the convoy target, the deceleration of the self-vehicle is calculated according to the preset deceleration ratio coefficient, the distance between the self-vehicle and the convoy target along the driving direction, the target following distance, the self-vehicle speed and the convoy target speed, and the self-vehicle deceleration is decelerated to the target following distance according to the self-vehicle deceleration to slow down and avoid the convoy target. This application makes the function triggering more integrated by integrating the continuous large vehicle convoy targets, avoiding the driving discomfort caused by the frequent acceleration and deceleration of the self-vehicle due to the repeated advance and retreat of the function. The predicted parallel duration is used as the core indicator for issuing control commands, which more realistically reflects the motion relationship between the vehicle and the team target, avoiding unnecessary triggering and unnecessary braking when the speed difference between the vehicle and the team target is high, making the function more comfortable and intelligent. Acceleration and deceleration are managed according to the map lane information and surrounding vehicle information, defensive driving is performed, and driving safety is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0048] Figure 1A flow chart of a method for automatic driving to avoid parallel vehicles provided in an embodiment of the present application is shown;

[0049] Figure 2 A schematic diagram of the module structure of an automatic driving avoidance parallel vehicle control system provided in an embodiment of the present application is shown;

[0050] Figure 3 A schematic diagram of an automatic driving device for avoiding parallel vehicles provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below with reference to the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0053] As described in the background technology, with the continuous development of vehicle autonomous driving, OEMs are paying more and more attention to it, and more and more models are equipped with autonomous driving systems.

[0054] Correspondingly, manufacturers and car owners have increasingly higher requirements for its intelligence level, and the autonomous driving function has gradually developed from simple L2 autonomous driving such as adaptive cruise control (ACC, Adaptive Cruise Control) to L2.5 autonomous driving with navigation function.

[0055] To meet the functional requirements of advanced autonomous driving, the vehicle-side perception level has also been greatly improved, from a single radar and single camera combination to a combination of multiple radars and multiple cameras, and the detectable environmental targets have also been upgraded from a single target in front to multiple targets around the vehicle. At the same time, the introduction of high-precision maps allows the vehicle to obtain more road environment information for behavioral decision-making.

[0056] However, current adaptive cruise control systems pay little attention to the status of vehicles in the side lanes, which results in the risk of the self-controlled vehicle running parallel to large vehicles in the side lanes for a long time, causing a greater sense of driving pressure on the driver and affecting driving safety.

[0057] In order to solve the above technical problems, the embodiments of the present application provide a method, device, system and medium for automatic driving to avoid parallel large vehicles, the method comprising: obtaining vehicle information of the side lane; comparing the vehicle information of the side lane with preset vehicle type information to screen out large vehicle targets; when it is detected that both the side front and side rear of the own vehicle are large vehicle targets, obtaining the vehicle speed and vehicle distance of the large vehicle targets; when the vehicle speed and vehicle distance are within preset values ​​within a preset time period, merging the large vehicle targets as convoy targets; according to the absolute value of the difference between the front distance and the rear distance of the own vehicle and the convoy targets along the driving direction, the speed of the own vehicle and the convoy target speed, calculating the predicted parallel time between the own vehicle and the convoy target; the convoy target speed is the speed of the frontmost large vehicle among the large vehicle targets; when the own vehicle When accelerating to avoid a convoy target, the minimum value of the self-vehicle speed multiplied by the set speed gain coefficient, the road speed limit and the curve speed limit is used as the self-vehicle acceleration target speed; the self-vehicle acceleration is calculated based on the preset acceleration ratio coefficient, the self-vehicle acceleration target speed, the self-vehicle speed and the pre-judged acceleration level coefficient, and the self-vehicle speed is accelerated to the self-vehicle acceleration target speed according to the self-vehicle acceleration to accelerate and avoid the convoy target; when the self-vehicle slows down to avoid a convoy target, the self-vehicle deceleration is calculated based on the preset deceleration ratio coefficient, the distance between the self-vehicle and the convoy target along the driving direction, the target following distance, the self-vehicle speed and the convoy target speed, and the self-vehicle deceleration is decelerated to the target following distance according to the self-vehicle deceleration to slow down and avoid the convoy target. This application integrates the continuous large vehicle convoy targets to make the function trigger more integrated and avoid the driving discomfort caused by the frequent acceleration and deceleration of the self-vehicle due to the repeated advance and retreat of the function. The predicted parallel duration is used as the core indicator for issuing control commands, which more realistically reflects the motion relationship between the vehicle and the team target, avoiding unnecessary triggering and unnecessary braking when the speed difference between the vehicle and the team target is high, making the function more comfortable and intelligent. Acceleration and deceleration are managed according to the map lane information and surrounding vehicle information, defensive driving is performed, and driving safety is improved.

[0058] Exemplary Methods

[0059] See also Figure 1 As shown, it is a flow chart of a method for automatic driving to avoid parallel vehicles provided in an embodiment of the present application, including:

[0060] S101: Acquire side lane vehicle information; compare the side lane vehicle information with preset vehicle type information to screen out large vehicle targets.

[0061] S102: When it is detected that the front and rear sides of the vehicle are both large vehicle targets, the speed and distance of the large vehicle targets are obtained; when the speed and the distance are within preset values ​​within a preset time period, the large vehicle targets are merged as fleet targets.

[0062] In the embodiment of the present application, with the improvement of environmental target detection capability and accuracy, the adaptive cruise control function is no longer limited to the target in the lane, and the target in the side lane can also be taken into consideration, so that the function can intelligently dodge the risky vehicles on the side while ensuring the original cruising and following performance. While maintaining a safe distance from the target in front, avoid long-term parallel driving with risky vehicles such as large vehicles on the side, reduce the pressure on the driver, and improve driving safety.

[0063] Therefore, in the embodiment of the present application, the side lane vehicle information must first be obtained, and the side lane vehicle information must be compared with the preset vehicle type information to screen out large vehicle targets.

[0064] Specifically, the embodiment of the present application can obtain the vehicle information of the side lane through the perception system, and select the large vehicle target from it according to the preset vehicle type information. The large vehicle target can be a truck, a bus, or other vehicle that is larger than a car and easily causes a sense of pressure when driving.

[0065] In an embodiment of the present application, when it is detected that there are large vehicle targets in front and behind the vehicle, the speed and distance of the large vehicle targets can be further obtained; when the speed and distance are within the preset values ​​within the preset time, the large vehicle targets are merged as fleet targets.

[0066] Specifically, when it is found after screening that the vehicles in front and behind the vehicle are both large vehicles, it is decided whether to merge them into a convoy target based on whether the adjacent large vehicles continue to be close to each other in the future. That is, they are merged into a convoy target when the relative distance relationship of the large vehicles meets the following conditions:

[0067] (1) The distance between the truck in front and the truck behind is relatively close (within the preset distance value) and the distance between the two vehicles will not be significantly different in the future; or the distance between the truck in front and the truck behind is relatively far and the distance between the two vehicles will be significantly closer in the future (within the preset time length); (2) The speed of the truck in front and the truck behind is similar (within the preset speed value).

[0068] When the above conditions are met, the adjacent large vehicles in front and behind are merged into a convoy. During the movement of the ego vehicle, the information of the vehicles in the convoy is adjusted according to the perception information. When a new large vehicle target enters the front or rear side of the ego vehicle, it is used to replace the original large vehicle target that has moved away from the front or rear side of the ego vehicle, thereby realizing the rolling update of the convoy target.

[0069] S103: Calculate the predicted parallel time between the ego vehicle and the convoy target based on the absolute value of the difference between the front distance and the rear distance between the ego vehicle and the convoy target along the travel direction, the ego vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost vehicle among the vehicle targets.

[0070] In an embodiment of the present application, after the large vehicle targets are merged into a fleet target, the identification number of the fleet target can be set to the identification number of the frontmost large vehicle, the fleet target vehicle front distance can be set to the distance from the front of the front large vehicle to the vehicle itself, the fleet target vehicle rear distance can be set to the distance from the rear of the rearmost large vehicle to the vehicle itself, the fleet target lateral distance can be set to the smaller value of the lateral distances of the large vehicles, the fleet target vehicle length can be set to the distance from the front of the front large vehicle to the rear of the rearmost large vehicle, the fleet target vehicle width can be set to the larger value of the vehicle width, the fleet target vehicle speed can be set to the speed of the frontmost large vehicle, and the fleet target vehicle acceleration can be set to the vehicle with the larger absolute value of the acceleration.

[0071] Specifically, the predicted parallel time between the ego vehicle and the convoy target can be calculated based on the absolute value of the difference between the front distance and the rear distance between the ego vehicle and the convoy target along the driving direction, the ego vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost vehicle among the vehicle targets.

[0072] d Far =d Tuk +l Tuk +v Ego *t

[0073]

[0074] T=(d Far -d Near ) / (v Ego -v Tuk )

[0075] Among them, d Far is the distance between the vehicle and the target of the convoy along the driving direction. If the front distance is farther, it is the distance between the vehicle and the target of the convoy. If the rear distance is farther, it is the distance between the vehicle and the target of the convoy. Near is the closest point distance between the ego vehicle and the convoy target along the driving direction. If the front distance is closer, it is the front distance between the ego vehicle and the convoy target. If the rear distance is closer, it is the rear distance between the ego vehicle and the convoy target. Tuk is the distance between the vehicle and the convoy target along the driving direction, l Tuk is the target length of the fleet, t is the preset compensation time interval, v Ego is the vehicle speed, v Tuk is the target speed of the fleet.

[0076] S104: When the ego vehicle accelerates to avoid the convoy target, the minimum value among the value of the ego vehicle set speed multiplied by the set speed gain coefficient, the road speed limit value and the curve speed limit value is used as the ego vehicle acceleration target speed.

[0077] S105: Calculate the acceleration of the vehicle according to a preset acceleration ratio coefficient, the target acceleration speed of the vehicle, the speed of the vehicle and a pre-judged acceleration level coefficient, and accelerate the speed of the vehicle to the target acceleration speed of the vehicle according to the acceleration of the vehicle to accelerate and avoid the convoy target.

[0078] S106: When the ego vehicle decelerates to avoid the convoy target, the ego vehicle deceleration is calculated according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the convoy target along the driving direction, the target following distance, the ego vehicle speed and the convoy target speed, and the ego vehicle is decelerated to the target following distance according to the ego vehicle deceleration to decelerate and avoid the convoy target.

[0079] In the embodiment of the present application, when decelerating to avoid, the control target is that the vehicle follows the convoy target at the same speed as the convoy target at a certain distance behind the convoy target; when accelerating to overtake, the control target is that the vehicle accelerates through the convoy target at the acceleration overtaking target speed, and slides and decelerates back to the actual target speed of the vehicle after exceeding the convoy target by a certain distance.

[0080] Specifically, when the ego vehicle accelerates to avoid the convoy target, the minimum value among the value of the ego vehicle set speed multiplied by the set speed gain coefficient, the road speed limit value, and the curve speed limit value is used as the ego vehicle acceleration target speed, which is specifically calculated by the following formula:

[0081] v Tgt =Min(v Set *Gx,v Road , v Bend )

[0082] where v Set is the vehicle speed setting, Gx is the speed gain coefficient, v Road is the road speed limit, v Bend It is the minimum value among the curve speed limits.

[0083] The acceleration of the self-vehicle is calculated based on the preset acceleration ratio coefficient, the self-vehicle acceleration target speed, the self-vehicle speed and the pre-judged acceleration level coefficient. The self-vehicle speed is accelerated to the self-vehicle acceleration target speed according to the self-vehicle acceleration to accelerate and avoid the convoy target.

[0084] Specifically, it is calculated by the following formula:

[0085] a Acc =k 3 *(v Tgt -v Ego )*k Lvl ;

[0086] Among them, a Accis the vehicle acceleration, k 3 is the preset acceleration proportional coefficient, v Tgt is the target speed of the vehicle, v Ego is the vehicle speed, k Lvl It is the pre-judged acceleration level coefficient.

[0087] Optionally, in order to avoid the risk of collision with the vehicle in front and excessive speed when the vehicle is avoiding or overtaking, and to ensure driving safety, the smaller of the calculated acceleration of the vehicle, the acceleration of the following vehicle, and the acceleration of the curve speed limit is used as the final output of the vehicle control acceleration.

[0088] When the ego vehicle slows down to avoid the convoy target, the ego vehicle deceleration can be calculated based on the preset deceleration ratio coefficient, the distance between the ego vehicle and the convoy target along the driving direction, the target following distance, the ego vehicle speed and the convoy target speed. The ego vehicle can be decelerated to the target following distance based on the ego vehicle deceleration to slow down and avoid the convoy target.

[0089] It is calculated by the following formula:

[0090] a Dece =k 1 *(d Tuk -d Tgt )+k 2 *(v Ego -v Tuk );

[0091] Among them, a Dece is the vehicle deceleration, k 1 and k 2 is the preset deceleration ratio coefficient, d Tuk is the distance between the vehicle and the convoy target along the driving direction, d Tgt is the target following distance, v Ego is the vehicle speed, v Tuk is the target speed of the fleet.

[0092] In a possible implementation, the deceleration avoidance performed in the embodiment of the present application can be determined by the following steps:

[0093] When the vehicle speed is greater than or equal to the first speed, the vehicle does not request braking, the distance between the vehicle and the convoy target along the driving direction is less than or equal to the first distance, the predicted parallel time is greater than or equal to the first time, and the vehicle speed is within the preset value within the preset time, it is determined to slow down and avoid.

[0094] Specifically, when the ego vehicle is traveling at a relatively high speed (greater than or equal to the first speed) and the predicted parallel time calculated with a stably traveling target vehicle within a certain distance (less than or equal to the first distance) is relatively long (greater than or equal to the first time duration), that is, when there is a risk of long-term parallelism between the ego vehicle and the convoy target, consider slowing down the ego vehicle and following behind the convoy target to avoid long-term parallelism.

[0095] On the basis that deceleration and avoidance can be activated, when there is enough space in front of and to the side of the vehicle, and the vehicle is traveling at the set speed without the risk of long-term parallel operation, consider accelerating the vehicle to quickly overtake the team target, thereby improving traffic efficiency while avoiding the risk of long-term parallel operation. However, when the high-precision map is turned on and a ramp entrance is detected not far ahead and the vehicle is in the lane on the side of the entrance, accelerating and overtaking when the merging vehicle cuts into the lane will increase the risk of collision, and the activation of the acceleration and overtaking command is restricted at this time. That is, the acceleration and overtaking command is issued when the following conditions are met:

[0096] After deceleration to avoid, and there are no vehicles within the second distance in front of and to the side of the vehicle, and the convoy target is not driving on the side lane line of the vehicle's lane, and the predicted parallel time is less than or equal to the second time, and there is no ramp entrance within the third distance in front of the vehicle (or the vehicle is not in the ramp entrance side lane), it is determined to accelerate to avoid.

[0097] In a possible implementation, the pre-judged acceleration level coefficient provided in the embodiment of the present application can be obtained by judging through the following steps:

[0098] The pre-judged acceleration level coefficient is calculated based on the distance between the own vehicle and the convoy target perpendicular to the driving direction, as well as the speed of the vehicle in front of the own vehicle and the speed limit of the overtaking lane.

[0099] Specifically, the acceleration level is divided according to the side lane environmental information. According to daily driving habits and highway lane speed limit requirements, large vehicles usually travel in the right lane. It can be seen that the closer to the right of the lane where the ego vehicle is located, the greater the probability of a large vehicle cutting into this lane. Therefore, the acceleration is divided into three levels according to the lane position of the ego vehicle on the highway. The closer to the right lane, the lower the acceleration, and the closer to the left lane, the higher the acceleration. In addition, when it is detected that the speed of the vehicle in front of the ego vehicle is lower than the speed of the large vehicle target in front of the ego vehicle by more than a preset threshold, the speed of the vehicle in front of the ego vehicle is lower than the lane speed limit by more than a preset threshold, or the distance between the large vehicle target in front of the ego vehicle and the driving lane of the ego vehicle is less than a preset distance, the acceleration of the ego vehicle is reduced by a preset level.

[0100] That is, in the embodiment of the present application, the acceleration level is downgraded when one of the following two conditions is detected: (1) the speed of the vehicle in front is significantly lower than the speed of the large vehicle in front or the speed limit of the lane; (2) the large vehicle in front is driving in its lane close to the side of the vehicle.

[0101] It should be noted that the embodiments of the present application do not specifically limit the preset thresholds and preset levels, and they can be set by those skilled in the art according to actual conditions.

[0102] See also Figure 2 As shown, it is a schematic diagram of the module structure of an automatic driving avoidance parallel vehicle control system provided in an embodiment of the present application, including a vehicle state information acquisition module 100, a vehicle target information acquisition module 200, a map lane information acquisition module 300, a vehicle target screening and fusion module 400, a parallel time prediction module 500, an avoidance instruction decision module 600, an acceleration level division module 700, and an avoidance acceleration calculation module 800.

[0103] The vehicle status information acquisition module 100 is responsible for acquiring the current actual vehicle speed, set vehicle speed, acceleration, functional status and other status information of the vehicle; the vehicle target information acquisition module 200 is responsible for acquiring the physical information such as the distance, speed, acceleration, vehicle type and other physical information of the vehicle targets around the vehicle such as the front vehicle target and the side lane target; the map lane information acquisition module 300 is responsible for acquiring the road information such as the ramp distance and the lane where the vehicle is currently located given by the high-precision map; the large vehicle target screening and fusion module 400 is responsible for screening the surrounding vehicle information, obtaining the large vehicle targets therein, and performing fleet fusion processing on the adjacent large vehicle targets; the parallel time prediction module 500 is responsible for predicting the parallel time of the vehicle relative to the target large vehicle; the avoidance command decision module 600 is responsible for making a decision on whether to issue a deceleration avoidance or acceleration overtaking command by judging the vehicle and environmental information; the acceleration level division module 700 is responsible for determining the acceleration level when accelerating overtaking by judging the environmental information; the avoidance acceleration calculation module 800 is responsible for calculating the acceleration that ultimately controls the acceleration and deceleration avoidance of the vehicle.

[0104] In the above-mentioned multi-target fusion-based automatic driving parallel vehicle avoidance control system, the vehicle target information acquisition module 200 is connected to the vehicle target screening and fusion module 400, which is used to screen out the vehicle targets among the vehicle targets around the vehicle and perform fleet fusion when necessary. The vehicle state information acquisition module 100 and the vehicle target screening and fusion module 400 are connected to the parallel time prediction module 500, which is used to calculate the predicted parallel time of the vehicle when crossing the target vehicle as the core criterion for whether the avoidance instruction is issued. The vehicle state information acquisition module 100, the vehicle target information acquisition module 200, the map lane information acquisition module 300, and the parallel time prediction module 500 are connected to the avoidance instruction decision module 600, which is used to comprehensively consider the information from all parties to obtain the decision instruction of deceleration avoidance or acceleration overtaking. The map lane information acquisition module 300 and the avoidance instruction decision module 600 are connected to the acceleration level division module 700, which is used to determine the acceleration level limit when accelerating overtaking through road environment information. The avoidance instruction decision module 600 and the acceleration level classification module 700 are connected to the avoidance acceleration calculation module 800, and are used to finally calculate the acceleration control amount of the vehicle according to the acceleration and deceleration decision instructions and the acceleration level limit.

[0105] The embodiment of the present application provides a method for automatic driving to avoid parallel large vehicles, the method comprising: obtaining vehicle information of a side lane; comparing the vehicle information of the side lane with preset vehicle type information to screen out large vehicle targets; when it is detected that both the front and rear sides of the own vehicle are large vehicle targets, obtaining the vehicle speed and vehicle distance of the large vehicle targets; when the vehicle speed and vehicle distance are within preset values ​​within a preset time period, merging the large vehicle targets as convoy targets; according to the absolute value of the difference between the front distance and the rear distance of the own vehicle and the convoy targets along the driving direction, the speed of the own vehicle and the convoy target speed, calculating the predicted parallel time of the own vehicle and the convoy targets; the convoy target speed is the speed of the frontmost large vehicle among the large vehicle targets; when the own vehicle accelerates to avoid the convoy targets When the vehicle speed is multiplied by the set speed gain coefficient, the road speed limit and the curve speed limit, the minimum value is used as the acceleration target speed of the vehicle; the acceleration of the vehicle is calculated according to the preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the vehicle speed and the pre-judged acceleration level coefficient, and the vehicle speed is accelerated to the acceleration target speed according to the acceleration of the vehicle to accelerate and avoid the fleet target; when the vehicle slows down to avoid the fleet target, the deceleration of the vehicle is calculated according to the preset deceleration ratio coefficient, the distance between the vehicle and the fleet target along the driving direction, the target following distance, the vehicle speed and the fleet target speed, and the vehicle deceleration is decelerated to the target following distance according to the deceleration of the vehicle to slow down and avoid the fleet target. This application makes the function trigger more integrated by integrating the continuous large vehicle fleet targets, avoiding driving discomfort caused by frequent acceleration and deceleration of the vehicle due to repeated advance and retreat of the function. The predicted parallel duration is used as the core indicator for issuing control commands, which more realistically reflects the motion relationship between the vehicle and the team target, avoiding unnecessary triggering and unnecessary braking when the speed difference between the vehicle and the team target is high, making the function more comfortable and intelligent. Acceleration and deceleration are managed according to the map lane information and surrounding vehicle information, defensive driving is performed, and driving safety is improved.

[0106] Exemplary Devices

[0107] See also Figure 3 FIG. 1 is a schematic diagram of a device for automatically driving and avoiding parallel vehicles provided in an embodiment of the present application, including:

[0108] The screening unit 201 is used to obtain the vehicle information of the side lane; compare the vehicle information of the side lane with the preset vehicle type information to screen out the large vehicle target;

[0109] The merging unit 202 is used to obtain the vehicle speed and distance of the large vehicle target when it is detected that the vehicle is located in front of and behind the vehicle; when the vehicle speed and the distance are within a preset value within a preset time, merge the large vehicle target as a fleet target;

[0110] The prediction unit 203 is used to calculate the predicted parallel time between the ego vehicle and the convoy target according to the absolute value of the difference between the front distance and the rear distance of the ego vehicle and the convoy target along the travel direction, the ego vehicle speed and the convoy target speed; the convoy target speed is the speed of the frontmost vehicle among the vehicle targets;

[0111] A vehicle speed unit 204, for, when the ego vehicle accelerates to avoid the convoy target, using the minimum value of the value of the ego vehicle set speed multiplied by the set vehicle speed gain coefficient, the road speed limit value, and the curve speed limit value as the ego vehicle acceleration target speed;

[0112] The acceleration unit 205 is used to calculate the acceleration of the vehicle according to a preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the speed of the vehicle and the pre-judged acceleration level coefficient, and accelerate the speed of the vehicle to the acceleration target speed of the vehicle according to the acceleration of the vehicle, so as to accelerate and avoid the convoy target;

[0113] The deceleration unit 206 is used to calculate the deceleration of the ego vehicle according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the ego vehicle in the driving direction, the target following distance, the ego vehicle speed and the ego vehicle target speed when the ego vehicle decelerates to avoid the ego vehicle group target, and decelerate the ego vehicle to the target following distance according to the ego vehicle deceleration to decelerate and avoid the ego vehicle group target.

[0114] In a possible implementation, the acceleration unit is specifically used to calculate the vehicle acceleration, which is specifically calculated by the following formula:

[0115] a Acc =k 3 *(v Tgt -v Ego )*k Lvl ;

[0116] Among them, a Acc is the acceleration of the vehicle, k 3 is the preset acceleration proportional coefficient, v Tgt is the target vehicle acceleration speed, v Ego is the vehicle speed, k Lvl is the pre-judged acceleration level coefficient.

[0117] The embodiment of the present application provides an automatic driving device for avoiding parallel large vehicles, and the method applied to the device includes: obtaining vehicle information of the side lane; comparing the vehicle information of the side lane with preset vehicle type information to screen out large vehicle targets; when it is detected that there are large vehicle targets in front and behind the side of the own vehicle, obtaining the vehicle speed and vehicle distance of the large vehicle targets; when the vehicle speed and vehicle distance are within preset values ​​within a preset time period, merging the large vehicle targets as team targets; according to the absolute value of the difference between the front distance and the rear distance of the own vehicle and the team target along the driving direction, the speed of the own vehicle and the team target speed, calculating the predicted parallel time of the own vehicle and the team target; the team target speed is the speed of the frontmost large vehicle among the large vehicle targets; when the own vehicle accelerates to avoid the vehicle When approaching a convoy target, the minimum value among the set speed of the vehicle multiplied by the set speed gain coefficient, the road speed limit and the curve speed limit is used as the acceleration target speed of the vehicle; the acceleration of the vehicle is calculated according to the preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the vehicle speed and the pre-judged acceleration level coefficient, and the vehicle speed is accelerated to the acceleration target speed according to the acceleration of the vehicle to accelerate and avoid the convoy target; when the vehicle slows down to avoid the convoy target, the deceleration of the vehicle is calculated according to the preset deceleration ratio coefficient, the distance between the vehicle and the convoy target along the driving direction, the target following distance, the vehicle speed and the convoy target speed, and the vehicle deceleration is decelerated to the target following distance according to the deceleration of the vehicle to slow down and avoid the convoy target. This application makes the function triggering more integrated by integrating the continuous large vehicle convoy targets, avoiding the driving discomfort caused by the frequent acceleration and deceleration of the vehicle due to the repeated advance and retreat of the function. The predicted parallel duration is used as the core indicator for issuing control commands, which more realistically reflects the motion relationship between the vehicle and the team target, avoiding unnecessary triggering and unnecessary braking when the speed difference between the vehicle and the team target is high, making the function more comfortable and intelligent. Acceleration and deceleration are managed according to the map lane information and surrounding vehicle information, defensive driving is performed, and driving safety is improved.

[0118] Based on the above embodiments, the present application embodiment provides a system for automatically driving to avoid parallel vehicles, including:

[0119] Memory for storing computer programs;

[0120] A processor is used to implement the steps of the method for automatically driving to avoid parallel vehicles as described above when executing the computer program.

[0121] Based on the above embodiments, the embodiments of the present application further provide a computer-readable medium, on which a computer program is stored. When the computer program is processed and executed, the steps of the method for automatic driving to avoid parallel vehicles as described above are implemented.

[0122] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0123] The computer-readable medium may be included in the system; or may exist independently without being assembled into the system.

[0124] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart.

[0125] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0126] The above is only a preferred implementation of the present application. Although the present application has been disclosed as a preferred embodiment, it is not intended to limit the present application. Any technician familiar with the art can use the above disclosed methods and technical contents to make many possible changes and modifications to the technical solution of the present application without departing from the scope of the technical solution of the present application, or modify it into an equivalent embodiment of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application still falls within the scope of protection of the technical solution of the present application.

Claims

1. A method for automatically driving to avoid parallel vehicles, characterized in that: include: Get the vehicle information of the side lane; Comparing the side lane vehicle information with preset vehicle type information to screen out large vehicle targets; When it is detected that both the front and rear sides of the vehicle are the large vehicle targets, the speed and distance of the large vehicle targets are obtained; when the speed and distance are within the preset values ​​within the preset time, the large vehicle targets are merged as the fleet targets; The predicted parallel time between the ego vehicle and the convoy target is calculated based on the absolute value of the difference between the front distance and the rear distance between the ego vehicle and the convoy target along the travel direction, the ego vehicle speed and the convoy target speed; The target speed of the convoy is the speed of the frontmost vehicle in the vehicle target; When the self-vehicle accelerates to avoid the convoy target, the minimum value among the value of the self-vehicle set speed multiplied by the set speed gain coefficient, the road speed limit value and the curve speed limit value is used as the self-vehicle acceleration target speed; The acceleration of the vehicle is calculated according to a preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the speed of the vehicle and a pre-judged acceleration level coefficient, and the speed of the vehicle is accelerated to the acceleration target speed of the vehicle according to the acceleration of the vehicle, so as to accelerate and avoid the vehicle group target; When the ego vehicle decelerates to avoid the convoy target, the ego vehicle deceleration is calculated according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the convoy target along the driving direction, the target following distance, the ego vehicle speed and the convoy target speed, and the ego vehicle is decelerated to the target following distance according to the ego vehicle deceleration to decelerate and avoid the convoy target.

2. The method according to claim 1, characterized in that: The acceleration of the vehicle is calculated based on the preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the vehicle speed and the pre-judged acceleration level coefficient, and is specifically calculated by the following formula: a Acc =k3*(v Tgt -v Ego )*k Lvl ; Among them, a Acc is the vehicle acceleration, k3 is the preset acceleration proportional coefficient, v Tgt is the target vehicle acceleration speed, v Ego is the vehicle speed, k Lvl is the pre-judged acceleration level coefficient.

3. The method according to claim 1, characterized in that The deceleration of the vehicle is calculated based on the preset deceleration ratio coefficient, the distance between the vehicle and the team target along the driving direction, the target following distance, the vehicle speed and the team target speed, and is specifically calculated by the following formula: a Dece =k1*(d Tuk -d Tgt )+k2*(v Ego -v Tuk ); Among them, a Dece is the vehicle deceleration, k1 and k2 are the preset deceleration proportional coefficients, d Tuk is the distance between the vehicle and the convoy target along the driving direction, d Tgt is the target following distance, v Ego is the vehicle speed, v Tuk is the target speed of the fleet.

4. The method according to claim 1, characterized in that: The deceleration avoidance is determined by the following steps: When the vehicle speed is greater than or equal to the first vehicle speed, and the vehicle does not request braking, and the distance between the vehicle and the convoy target along the driving direction is less than or equal to the first distance, and the predicted parallel time is greater than or equal to the first time and the vehicle speed is within the preset value within the preset time, it is determined to perform the deceleration avoidance.

5. The method according to claim 4, characterized in that The acceleration avoidance is determined by the following steps: After the deceleration avoidance is performed, and there are no vehicles within the second distance in front of and to the side of the vehicle, and the convoy target is not driving on the side lane line of the vehicle's driving lane, and the predicted parallel time is less than or equal to the second time, and there is no ramp entrance within the third distance in front of the vehicle, it is determined to perform the acceleration avoidance.

6. The method according to claim 1, characterized in that The pre-judged acceleration level coefficient is obtained by judging in the following steps: The pre-judged acceleration level coefficient is calculated based on the distance between the own vehicle and the convoy target perpendicular to the driving direction, as well as the speed of the vehicle in front of the own vehicle and the speed limit of the overtaking lane.

7. The method according to claim 1, characterized in that Also includes: When it is detected that the speed of the vehicle in front of the vehicle is lower than the speed of the large vehicle target in front of the vehicle by more than a preset threshold, the speed of the vehicle in front of the vehicle is lower than the lane speed limit by more than a preset threshold, or the large vehicle target in front of the vehicle is less than a preset distance from the driving lane of the vehicle, the acceleration of the vehicle is reduced by a preset level.

8. An automatic driving device for avoiding parallel vehicles, characterized in that: include: A screening unit, used for obtaining vehicle information of a side lane; Comparing the side lane vehicle information with preset vehicle type information to screen out large vehicle targets; A merging unit is used to obtain the vehicle speed and distance of the large vehicle target when it is detected that the vehicle is located in front of and behind the vehicle; when the vehicle speed and the distance are within a preset value within a preset time, merge the large vehicle target as a fleet target; A prediction unit, configured to calculate a predicted parallel time between the ego vehicle and the convoy target according to an absolute value of a difference between a front distance and a rear distance between the ego vehicle and the convoy target along a travel direction, the ego vehicle speed, and the convoy target speed; The target speed of the convoy is the speed of the frontmost vehicle in the vehicle target; A vehicle speed unit, used for, when the self-vehicle accelerates to avoid the convoy target, using the minimum value of the value of the self-vehicle set speed multiplied by the set vehicle speed gain coefficient, the road speed limit value, and the curve speed limit value as the self-vehicle acceleration target speed; an acceleration unit, configured to calculate the acceleration of the vehicle according to a preset acceleration ratio coefficient, the acceleration target speed of the vehicle, the speed of the vehicle and a pre-determined acceleration level coefficient, and accelerate the speed of the vehicle to the acceleration target speed of the vehicle according to the acceleration of the vehicle, so as to accelerate and avoid the vehicle group target; The deceleration unit is used to calculate the deceleration of the ego vehicle according to a preset deceleration ratio coefficient, the distance between the ego vehicle and the ego vehicle target along the driving direction, the target following distance, the ego vehicle speed and the ego vehicle target speed when the ego vehicle decelerates to avoid the ego vehicle group target, and decelerate the ego vehicle to the target following distance according to the ego vehicle deceleration to decelerate and avoid the ego vehicle group target.

9. An automatic driving system for avoiding parallel vehicles, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the method for automatic driving to avoid parallel vehicles as described in any one of claims 1 to 4 when executing the computer program.

10. A computer-readable medium, characterized in that The computer-readable medium stores a computer program, which, when processed and executed, implements the steps of the method for automatic driving to avoid parallel vehicles as described in any one of claims 1-4.

Images