An automatic driving control method for a vehicle to exit a roundabout and related equipment

Abstract

The application discloses an automatic driving control method for a vehicle to drive out of a roundabout and related equipment. The method comprises the following steps: acquiring a current driving characteristic variable of a target vehicle; acquiring a set of motion characteristic variables of an occlusion obstacle in a first direction and a set of motion characteristic variables of a crossing obstacle in a second direction, wherein the first direction is not crossed with the driving direction of the target vehicle, and the second direction is crossed with the driving direction of the target vehicle; performing a game analysis operation on the set of motion characteristic variables of the occlusion obstacle and the set of motion characteristic variables of the crossing obstacle to acquire a set of key obstacle characteristic variables, wherein the game analysis operation is to filter the characteristic variables of the unaffected crossing obstacle in the set of motion characteristic variables of the crossing obstacle according to the set of motion characteristic variables of the occlusion obstacle to acquire the set of key obstacle characteristic variables; and performing a collision analysis on the set of key obstacle characteristic variables and the current driving characteristic variable to determine a roundabout driving-out strategy of the target vehicle.

Description

Technical Field

[0001] This specification relates to the field of intelligent driving, and more specifically, this application relates to an automatic driving control method and related equipment for a vehicle exiting a roundabout. Background Technology

[0002] For autonomous vehicles, roundabouts present a complex driving scenario, posing significant challenges to the implementation of autonomous driving algorithms. Roundabouts involve numerous vehicles traveling in various directions and with multiple lanes, requiring the processing of massive amounts of vehicle driving data within a short timeframe, rapid judgment, and the generation of control commands. Currently, research on autonomous driving control methods for this scenario is limited. Summary of the Invention

[0003] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0004] Firstly, this application proposes an automated driving control method for a vehicle exiting a roundabout, the method comprising:

[0005] Obtain the current driving characteristic variables of the target vehicle;

[0006] Obtain a set of motion characteristic variables of obstructing obstacles in a first direction and a set of motion characteristic variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle;

[0007] Game analysis is performed based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables. The game analysis is performed by filtering the characteristic variables of the unaffected crossing obstacles in the set of crossing obstacle characteristic variables based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables.

[0008] Collision analysis is performed based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

[0009] Optionally, the current driving feature variables include Frenet coordinates and vehicle length variables, and the motion feature variables include Frenet coordinates and motion speed direction;

[0010] The process of obtaining the set of motion characteristic variables of occluding obstacles in the first direction and the set of motion characteristic variables of crossing obstacles in the second direction includes:

[0011] The obstacle traversing motion feature variable set is constructed by constructing obstacle motion feature variables whose lateral value of Frenet coordinates is greater than that of the target vehicle's Frenet coordinates and whose motion speed direction coincides with the second direction;

[0012] The obstacle motion feature variables are constructed as the set of obstacle motion feature variables, where the lateral value of the Frenet coordinate is greater than the lateral value of the target vehicle's Frenet coordinate, the lateral value of the Frenet coordinate is greater than a first reference value, the lateral value of the Frenet coordinate is less than a second reference value, and the direction of the motion speed coincides with the first direction. The first reference value is the difference between the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body, and the second reference value is the sum of the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body.

[0013] Optionally, the set of motion feature variables may also include lane information.

[0014] The step of performing game theory analysis based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables includes:

[0015] In the same lane information, among the set of motion characteristic variables of obstacles crossing the lane, select the motion characteristic variables of obstacles crossing the lane with smaller lateral values ​​of Frenet coordinates to construct the set of obstacles crossing the front of the lane.

[0016] Game theory analysis is performed based on the set of obstacles crossing the front of the formation and the set of motion characteristic variables of the obstacles crossing the formation to obtain the set of key obstacle characteristic variables.

[0017] Optionally, the step of performing collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle includes:

[0018] Based on the set of key obstacle feature variables and the current driving feature variables, a collision analysis is performed to calculate the theoretical collision point and theoretical collision time.

[0019] If the theoretical collision time is less than the preset minimum collision time and / or the distance between the critical obstacle and the theoretical collision point is less than the preset minimum safe distance, the target vehicle is controlled to decelerate and avoid the obstacle.

[0020] Optionally, the above methods also include:

[0021] If the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, the speed of the target vehicle and the speed of the key obstacle are both less than or equal to the preset game speed, and the distance between the key obstacle and the theoretical collision point and the distance between the target vehicle and the theoretical collision point are both less than or equal to the preset game distance, and the distance between the target vehicle and the theoretical collision point is less than or equal to the distance between the key obstacle and the theoretical collision point, the target vehicle is controlled to continue driving at a predetermined speed.

[0022] Optionally, the above methods also include:

[0023] If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the critical obstacle and the theoretical collision point is greater than or equal to the preset minimum safe distance, or if any one of the target vehicle's speed and the critical obstacle's speed is greater than the preset game speed, or if any one of the distance between the critical obstacle and the theoretical collision point and the target vehicle's distance from the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle arrives at the theoretical collision point and the time the critical obstacle arrives at the theoretical collision point is less than the preset game time, then the target vehicle is controlled to decelerate and avoid the collision.

[0024] Optionally, the above methods also include:

[0025] If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, or if any one of the speeds of the target vehicle and the key obstacle is greater than the preset game speed, or if any one of the distances between the key obstacle and the theoretical collision point and the target vehicle and the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle reaches the theoretical collision point and the time the key obstacle reaches the theoretical collision point is greater than or equal to the preset game time, then the target vehicle is controlled to continue traveling at a predetermined speed.

[0026] Secondly, this application also proposes an automatic driving control device for a vehicle exiting a roundabout, comprising:

[0027] The first acquisition unit is used to acquire the current driving characteristic variables of the target vehicle;

[0028] The second acquisition unit is used to acquire a set of motion feature variables of occluding obstacles in a first direction and a set of motion feature variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle.

[0029] The third acquisition unit is used to perform a game analysis operation based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain a set of key obstacle characteristic variables. The game analysis operation is to filter the characteristic variables of the unaffected crossing obstacles in the set of cross-obstacle characteristic variables based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables.

[0030] The determination unit is used to perform collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

[0031] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the automatic driving control method for a vehicle to exit a roundabout as described in any of the first aspects above.

[0032] Fourthly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the automatic driving control method for a vehicle to exit a roundabout as described in any of the first aspects.

[0033] In summary, the autonomous driving control method for a vehicle exiting a roundabout according to embodiments of this application includes: acquiring the current driving characteristic variables of the target vehicle; acquiring a set of motion characteristic variables of obstructing obstacles in a first direction and a set of motion characteristic variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle; performing a game analysis operation based on the set of motion characteristic variables of obstructing obstacles and the set of motion characteristic variables of crossing obstacles to obtain a set of key obstacle characteristic variables, wherein the game analysis operation is to filter the characteristic variables of unaffected crossing obstacles in the set of motion characteristic variables of crossing obstacles based on the set of motion characteristic variables of obstructing obstacles to obtain the set of key obstacle characteristic variables; and performing collision analysis based on the set of key obstacle characteristic variables and the current driving characteristic variables to determine the roundabout exit strategy of the target vehicle. This application proposes an autonomous driving control method for a vehicle exiting a roundabout. It acquires a set of motion characteristic variables for obstructing obstacles in a first direction and a set of motion characteristic variables for crossing obstacles in a second direction. The method also identifies the motion relationships between the obstructing and crossing obstacles and the target vehicle within these two sets. Game theory analysis can effectively filter out characteristic variables affecting crossing obstacles, thereby obtaining a set of key obstacle characteristic variables. This reduces the number of crossing obstacle characteristic variables in the collision analysis process, enabling rapid decision-making and ensuring the vehicle safely and quickly exits the roundabout.

[0034] The autonomous driving control method for vehicles exiting roundabouts proposed in this application, along with other advantages, objectives, and features of this application, will be partly apparent from the following description and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0035] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0036] Figure 1 This application provides a schematic flowchart of an automated driving control method for a vehicle exiting a roundabout, as illustrated in an embodiment of the present application.

[0037] Figure 2 This application provides a schematic diagram illustrating a scenario where a vehicle exits a roundabout.

[0038] Figure 3 A schematic flowchart of another automatic driving control method for a vehicle exiting a roundabout, provided as an embodiment of this application;

[0039] Figure 4 This application provides a schematic diagram of the structure of an automatic driving control device for a vehicle exiting a roundabout, as shown in the embodiments of the present application.

[0040] Figure 5 This is a schematic diagram of an electronic device for controlling the automatic driving of a vehicle exiting a roundabout, provided as an embodiment of this application. Detailed Implementation

[0041] This application proposes an autonomous driving control method for a vehicle exiting a roundabout. It acquires a set of motion characteristic variables for obstructing obstacles in a first direction and a set of motion characteristic variables for crossing obstacles in a second direction. The method also identifies the motion relationships between the obstructing and crossing obstacles and the target vehicle within these two sets. Game theory analysis can effectively filter out characteristic variables affecting crossing obstacles, thereby obtaining a set of key obstacle characteristic variables. This reduces the number of crossing obstacle characteristic variables in the collision analysis process, enabling rapid decision-making and ensuring the vehicle safely and quickly exits the roundabout.

[0042] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0043] Please see Figure 1 This is a schematic flowchart of an automated driving control method for a vehicle exiting a roundabout, provided in an embodiment of this application. Specifically, it may include:

[0044] S110. Obtain the current driving characteristic variables of the target vehicle;

[0045] For example, the target vehicle is a vehicle preparing to exit the roundabout during autonomous driving, such as... Figure 2As shown, the target vehicle is identified by an ADC, and the driving characteristic variables may include: the array of points related to its driving trajectory, ADC_Traj = {<x1,y1,t1> ,<x2,y2,t2> …<xn,yn,tn>}, the Frenet coordinates are denoted as ADC_FP={ADC_s,ADC_l}, where ADC_s represents the Frenet ordinate and ADC_l represents the Frenet abscissa; the lane where the ADC is located on the map is denoted as ADC_Lane; the direction of travel of the ADC is denoted as ADC_Direction; the real-time speed of the ADC is denoted as ADC_V; and the length of the ADC is denoted as ADC_Len.

[0046] S120. Obtain the set of motion characteristic variables of the obstructing obstacle in the first direction and the set of motion characteristic variables of the traversing obstacle in the second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle.

[0047] For example, this application defines other moving vehicles as obstacles preventing the target vehicle from exiting the roundabout. The first direction is the same as but not intersecting with the target vehicle's direction of travel, such as... Figure 2 The direction of travel for vehicle O1 is defined by the direction of travel of the target vehicle, while the second direction refers to vehicles whose travel direction intersects with that of the target vehicle, such as... Figure 2The driving directions of O2, O3, and O4 in the diagram represent the obstacles. Obstacles in the first direction (O2, O3, and O4) will not hinder the target vehicle from exiting the roundabout, while obstacles in the second direction may collide with the target vehicle. The set of feature variables corresponding to obstacles in the first direction is defined as the set of motion feature variables for occluding obstacles, and the set of feature variables corresponding to obstacles in the second direction is defined as the set of feature variables for crossing obstacles. The motion feature variables of occluding obstacles and the feature variables of crossing obstacles are obtained by sensor devices carried in the target vehicle, such as radar sensors, infrared sensors, and image sensors. The sensors first acquire the feature variables of all obstacles to form an obstacle list O_list = {O1, O2, ..., On}. For the i-th obstacle Oi, the following features can be defined: the obstacle's unique identifier ID: Oi_ID; the obstacle's speed Oi_V; the obstacle's world coordinate system coordinates Oi_WP = {Oi_x, Oi_y}; the obstacle's Frenet coordinate system coordinates Oi_FP = {Oi_s, Oi_l}; the obstacle's lane on the map Oi_Lane; the obstacle's predicted driving direction Oi_Direction; and the obstacle's predicted trajectory point sequence Oi_Traj = {<xoi1,yoi1,toi1> ,<xoi2,yoi2,toi2> …<xoin,yoin,toin> By distinguishing the direction of movement and coordinate position of obstacles, obstacles can be divided into occluding obstacles and crossing obstacles, and sets of motion characteristic variables for occluding obstacles and crossing obstacles can be constructed.

[0048] S130. Perform a game analysis operation based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain a set of key obstacle characteristic variables. The game analysis operation is to filter the characteristic variables of the unaffected crossing obstacles in the set of cross-obstacle characteristic variables based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables.

[0049] For example, such as Figure 2 As shown, obstructing obstacles may block crossing obstacles during their movement, which objectively facilitates the target vehicle's exit from the roundabout. For example, if O1 enters the roundabout before O2 and O4 and intersects with its corresponding lane, O2, O3, and O4 may be obstructed by O1. If the ADC exits the roundabout normally at this time, it will not collide with O2, O3, and O4. At this time, based on the set of motion characteristic variables of the obstructing obstacles, the characteristic variables of the crossing obstacles in the set of characteristic variables are filtered to obtain the set of key obstacle characteristic variables, thereby reducing invalid variables in collision analysis, reducing the amount of computation, and improving the calculation speed.

[0050] S140. Perform collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

[0051] For example, a collision detection algorithm is used to analyze whether a cross-traversing obstacle in the key obstacle feature variable set is likely to collide with the target vehicle. Based on the theoretical collision location, collision time, obstacle speed, and target vehicle speed, a judgment is made to determine the strategy for exiting the roundabout and control the vehicle to safely leave the roundabout.

[0052] In summary, the autonomous driving control method for a vehicle exiting a roundabout proposed in this application obtains a set of motion characteristic variables of occluded obstacles in the first direction and a set of motion characteristic variables of traversing obstacles in the second direction. The motion relationship between the occluded obstacles, traversing obstacles and the target vehicle in the two sets of variables can be effectively screened out through game theory analysis to obtain a set of key obstacle characteristic variables. This reduces the characteristic variables of traversing obstacles in the collision analysis process, enabling rapid decision-making and ensuring that the vehicle safely and quickly exits the roundabout.

[0053] In some examples, the current driving feature variables include Frenet coordinates and vehicle length variables, and the motion feature variables include Frenet coordinates and motion speed direction;

[0054] The process of obtaining the set of motion characteristic variables of occluding obstacles in the first direction and the set of motion characteristic variables of crossing obstacles in the second direction includes:

[0055] The obstacle traversing motion feature variable set is constructed by constructing obstacle motion feature variables whose lateral value of Frenet coordinates is greater than that of the target vehicle's Frenet coordinates and whose motion speed direction coincides with the second direction;

[0056] The obstacle motion feature variables are constructed as the set of obstacle motion feature variables, where the lateral value of the Frenet coordinate is greater than the lateral value of the target vehicle's Frenet coordinate, the lateral value of the Frenet coordinate is greater than a first reference value, the lateral value of the Frenet coordinate is less than a second reference value, and the direction of the motion speed coincides with the first direction. The first reference value is the difference between the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body, and the second reference value is the sum of the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body.

[0057] Exemplarily, let the direction of the cross road at the roundabout exit be the first direction, denoted as Direction_Cut. Traverse the set of obstacle lists O_list, and calculate the condition for each obstacle Oi: {Oi_l > ADC_l && Oi_Direction == Direction_Cut}. If the condition is true, that is, the lateral value of the Frenet coordinate is greater than the lateral value of the Frenet coordinate of the target vehicle and the moving speed direction coincides with the second direction, then add Oi to the cross obstacle set Ocut = {Ocut1…Ocutn}, as Figure 2 shown, {O2, O3, O4} is the set of motion characteristic variables of the cross obstacles. It should be noted that the lateral value of the Frenet coordinate of the obstacle being greater than the lateral value of the Frenet coordinate of the target vehicle means that the surface obstacle is on the right side of the target vehicle, that is, there is a possibility of collision with the target vehicle when the obstacle travels forward.

[0058] Traverse the set O_list, and calculate the condition for each obstacle Oi: {Oi_l > ADC_l && Oi_s > ADC_s - 0.5 * ADC_Len && Oi_s < ADC_s + 0.5 * ADC_len && Oi_Direction == ADC_Direction}. If the condition is true, that is: the lateral value of the Frenet coordinate is greater than the lateral value of the Frenet coordinate of the target vehicle, the lateral value of the Frenet coordinate is greater than the first reference value, the lateral value of the Frenet coordinate is less than the second reference value, and the moving speed direction coincides with the first direction, then add Oi to the same-direction occlusion obstacle set Ocov = {Ocov1, Ocov2….Ocovn}, as Figure 2 shown, {O1} is the set of same-direction occlusion obstacles. It should be noted that during the process of determining the occlusion obstacles, it is considered that the occlusion obstacles should be on the right side of the target vehicle, and at least cover half of the body of the target vehicle, and the moving direction should be the same as the moving direction of the target vehicle.

[0059] In some examples, the set of motion characteristic variables further includes lane information

[0060] The operation of performing game analysis based on the set of motion characteristic variables of the occlusion obstacles and the set of motion characteristic variables of the cross obstacles to obtain the set of key obstacle characteristic variables includes:[[]]

[0061] In the set of motion characteristic variables of the cross obstacles in the same lane information, select the motion characteristic variables of the cross obstacles with smaller lateral values of the Frenet coordinate to construct the cross leading obstacle set;

[0062] Perform a game analysis operation based on the set of head-on obstacle collections and the set of head-on obstacle motion characteristic variables to obtain a set of key obstacle characteristic variables.

[0063] Exemplarily, traverse the set Ocut, for each obstacle Ocuti, calculate the condition: {There does not exist O_cutj in the set Ocut such that Ocutj_l < Ocuti_l, and Ocutj_lane == Ocuti_lane, and i ≠ j}. If the condition is true, that is, in the set of head-on obstacle motion characteristic variables in the same lane information, select the head-on obstacle motion characteristic variable with a smaller lateral value of the Frenet coordinate to construct the set of head-on obstacles Ohead = {Ohead1, Ohead2….Oheadn}, as Figure 2 shown, {O2, O4} is the set of head-on obstacles.

[0064] In summary, an automatic driving control method for a vehicle to drive out of a roundabout proposed in an embodiment of the present application further screens the head-on obstacles and only selects the obstacles at the head of the same lane to participate in the game analysis, thereby further shortening the computational amount of the game analysis.

[0065] It should be noted that during the game analysis process, traverse the set Ohead, for each obstacle Oheadi, calculate the following condition: {In the set Ocov, there exists Ocovj such that Oheadi_ID ≠ Ocovj_ID and there is a collision between Oheadi_Traj and Ocovj_WP}. If the calculation is true, there is a game between the obstacle Oheadi and Ocovj, and Oheadi is ignored. If the calculation condition is false, Oheadi is added to the set of key obstacles Ocr = {Ocr1, Ocr2….Ocrn}. As Figure 1 shown, there is a competitive game between O1 and O2, then O2 is ignored. Until the road surface situation develops and the game between O1 and O2 disappears, then O2 is reconsidered. For example, during the process, O1 brakes and O2 does not decelerate, then the competitive game between O1 and O2 disappears. Then O2 is reconsidered. That is, it is judged whether the occluding obstacle can effectively occlude the head-on obstacle during the process of the target vehicle driving out of the roundabout. If it can produce an effective occlusion, the occluded head-on obstacle is discarded. If it cannot occlude, it is added to the set of key obstacles, and the game process changes in real time according to the movement of the obstacles.

[0066] In some examples, the collision analysis based on the set of key obstacle characteristic variables and the current driving characteristic variables to determine the roundabout exit strategy of the target vehicle includes:

[0067] Collision analysis is performed based on the set of key obstacle feature variables and the current driving feature variables to calculate the theoretical collision point and the theoretical collision time;

[0068] Exemplarily, traverse the set of key obstacle feature variables Ocr. For each obstacle Ocri, use a collision detection algorithm to calculate whether there is a collision between the expected driving trajectory point sequence Ocri_Traj of Ocri and the expected driving path point sequence ADC_Traj of the autonomous driving vehicle. If there is a collision, record the minimum time of the collision between Ocri and ADC_Traj as Ocoi_t, the collision point coordinates Pcoi = {Ocoi_x, Ocoi_y}, and the distance between Ocri and Pcoi currently is Ocoi_s. The time for the target vehicle to reach Pcoi at the vehicle speed ADC_V is ADCcoi_t, and the distance from Pcoi is ADCcoi_s. If Ocoi_t < Tc, then Ocri is added to the collision obstacle set Oco = {Oco1, Oco2... Ocon}. Tmc is the preset minimum collision time.

[0069] Control the driving strategy of the vehicle by analyzing parameters such as the theoretical collision point and the theoretical collision time. Specifically, the following strategies can be included:

[0070] Situation A: In the case where the theoretical collision time is less than the preset minimum collision time and / or the distance between the key obstacle and the theoretical collision point is less than the preset minimum safety distance, control the target vehicle to decelerate and avoid.

[0071] Exemplarily, if Ocoi_t < Tmc and / or Ocoi_s < Dms, the decision action for Ocoi is to decelerate and avoid. That is, in the case where the theoretical collision time is less than the preset minimum collision time and / or the distance between the key obstacle and the theoretical collision point is less than the preset minimum safety distance, control the target vehicle to decelerate and avoid, corresponding to Figure 3 in, steps S20 - S210 - S21 and / or S20 - S210 - S220 - S230 - S21.

[0072] Situation B: In the case where the theoretical collision time is greater than or equal to the preset minimum collision time, the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, the motion speeds of the target vehicle and the key obstacle are both less than or equal to the preset game vehicle speed, the distances between the key obstacle and the theoretical collision point and the target vehicle and the theoretical collision point are both less than or equal to the preset game distance, and the distance between the target vehicle and the theoretical collision point is less than or equal to the distance between the key obstacle and the theoretical collision point, control the target vehicle to continue driving at the established speed.

[0073] Exemplarily, if the obstacle does not satisfy Ocoi_t < Tmc and does not satisfy Ocoi_s < Dms, does not satisfy {Max(ADC_V, Ocoi_V) > Vp || Max(ADCcoi_s, Ocoi_s) > Dp}, and does not satisfy {ADC co i _s> O co i _s } , that is, when the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, the moving speeds of the target vehicle and the key obstacle are both less than or equal to the preset game vehicle speed, and the distances between the key obstacle and the theoretical collision point and between the target vehicle and the theoretical collision point are both less than or equal to the preset game distance, and the distance between the target vehicle and the theoretical collision point is less than or equal to the distance between the key obstacle and the theoretical collision point, then drive normally, that is, corresponding to steps S20 - S210 - S220 - S240 - S250 - S260 - S21. It should be noted that Vp is the preset game vehicle speed, Dp is the preset game distance, and Dp > Dms.

[0074] Situation C: When the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, and any one of the moving speeds of the target vehicle and the key obstacle is greater than the preset game vehicle speed, or any one of the distances between the key obstacle and the theoretical collision point and between the target vehicle and the theoretical collision point is greater than the preset game distance, and the time difference between the time when the target vehicle reaches the theoretical collision point and the time when the key obstacle reaches the theoretical collision point is less than the preset game time, control the target vehicle to decelerate and avoid.

[0075] Exemplarily, if the obstacle does not satisfy Ocoi_t < Tmc and does not satisfy Ocoi_s < Dms, satisfies {Max(ADC_V, Ocoi_V) > Vp || Max(ADCcoi_s, Ocoi_s) > Dp}, and satisfies {Abs(ADCcoi_t - Ocoi_t) < Tp}, that is, when the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, either the moving speed of the target vehicle or the moving speed of the key obstacle is greater than the preset game vehicle speed or either the distance between the key obstacle and the theoretical collision point or the distance between the target vehicle and the theoretical collision point is greater than the preset game distance, and the time difference between the time when the target vehicle reaches the theoretical collision point and the time when the key obstacle reaches the theoretical collision point is less than the preset game time, a deceleration operation is performed. Correspondingly Figure 3 S20 - S210 - S220 - S240 - S270 - S280 - S21

[0076] Situation D: When the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, either the moving speed of the target vehicle or the moving speed of the key obstacle is greater than the preset game vehicle speed or either the distance between the key obstacle and the theoretical collision point or the distance between the target vehicle and the theoretical collision point is greater than the preset game distance, and the time difference between the time when the target vehicle reaches the theoretical collision point and the time when the key obstacle reaches the theoretical collision point is greater than or equal to the preset game time, control the target vehicle to continue driving at the established speed.

[0077] Exemplarily, if the obstacle does not satisfy Ocoi_t < Tmc and does not satisfy Ocoi_s < Dms, satisfies {Max(AD C_V, Ocoi_V) > Vp || Max(ADCcoi_s, Ocoi_s) > Dp}, and does not satisfy {Abs(ADCcoi_t - Ocoi_t) < Tp}, that is, when the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, either the moving speed of the target vehicle or the moving speed of the key obstacle is greater than the preset game vehicle speed or either the distance between the key obstacle and the theoretical collision point or the distance between the target vehicle and the theoretical collision point is greater than the preset game distance, and the time difference between the time when the target vehicle reaches the theoretical collision point and the time when the key obstacle reaches the theoretical collision point is greater than or equal to the preset game time, control the target vehicle to continue driving at the established speed. Correspondingly Figure 3 S20 - S210 - S220 - S240 - S270 - S290 - S21

[0078] In summary, the autonomous driving control method for a vehicle exiting a roundabout proposed in this application comprises three main parts: perception and prediction, behavior decision-making, and planning and control. The perception and prediction module is responsible for perceiving obstacle information around the autonomous vehicle, including obstacle position, size, and speed, and predicting the obstacle's trajectory. The behavior decision-making module, based on the perception and prediction information and the driving task, determines the appropriate behavior to deal with surrounding obstacles. The planning and control module, based on the behavior decision results, plans a trajectory that can be executed by the vehicle. In the roundabout exit scenario, the behavior decision-making module focuses on vehicles crossing obstacles along the roundabout entry direction. The obstacle decision-making method for roundabout exit scenarios proposed in this invention, while ensuring the safety of the vehicle itself, fully considers the game between obstacle vehicles and the game between obstacle vehicles and the vehicle, thus improving the algorithm's efficiency.

[0079] Please see Figure 4 One embodiment of the automatic driving control device for a vehicle exiting a roundabout in this application may include:

[0080] The first acquisition unit 21 is used to acquire the current driving characteristic variables of the target vehicle;

[0081] The second acquisition unit 22 is used to acquire a set of motion feature variables of occluding obstacles in a first direction and a set of motion feature variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle.

[0082] The third acquisition unit 23 is used to perform a game analysis operation based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain a set of key obstacle characteristic variables. The game analysis operation is to filter the characteristic variables of the unaffected crossing obstacles in the set of cross-obstacle characteristic variables based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables.

[0083] The determining unit 24 is used to perform collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

[0084] like Figure 5 As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the above-mentioned methods for the safe operation management of the commercial satellite operation and control platform.

[0085] Since the electronic device described in this embodiment is the device used to implement an automatic driving control device for a vehicle to exit a roundabout in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application falls within the scope of protection of this application.

[0086] In practical implementation, when the computer program 311 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0087] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0088] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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.

[0089] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), 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 computer, 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, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] 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.

[0091] 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.

[0092] This application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device performs the automated driving control process for a vehicle exiting a roundabout in the corresponding embodiment, including:

[0093] Obtain the current driving characteristic variables of the target vehicle;

[0094] Obtain a set of motion characteristic variables of obstructing obstacles in a first direction and a set of motion characteristic variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle;

[0095] Game analysis is performed based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables. The game analysis is performed by filtering the characteristic variables of the unaffected crossing obstacles in the set of crossing obstacle characteristic variables based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables.

[0096] Collision analysis is performed based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

[0097] In one feasible implementation, the current driving feature variables include Frenet coordinates and vehicle length variables, and the motion feature variables include Frenet coordinates and motion speed direction;

[0098] The process of obtaining the set of motion characteristic variables of occluding obstacles in the first direction and the set of motion characteristic variables of crossing obstacles in the second direction includes:

[0099] The obstacle traversing motion feature variable set is constructed by constructing obstacle motion feature variables whose lateral value of Frenet coordinates is greater than that of the target vehicle's Frenet coordinates and whose motion speed direction coincides with the second direction;

[0100] The obstacle motion feature variables are constructed as the set of obstacle motion feature variables, where the lateral value of the Frenet coordinate is greater than the lateral value of the target vehicle's Frenet coordinate, the lateral value of the Frenet coordinate is greater than a first reference value, the lateral value of the Frenet coordinate is less than a second reference value, and the direction of the motion speed coincides with the first direction. The first reference value is the difference between the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body, and the second reference value is the sum of the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body.

[0101] In one feasible implementation, the set of motion feature variables further includes lane information.

[0102] The step of performing game theory analysis based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables includes:

[0103] In the same lane information, among the set of motion characteristic variables of obstacles crossing the lane, select the motion characteristic variables of obstacles crossing the lane with smaller lateral values ​​of Frenet coordinates to construct the set of obstacles crossing the front of the lane.

[0104] Game theory analysis is performed based on the set of obstacles crossing the front of the formation and the set of motion characteristic variables of the obstacles crossing the formation to obtain the set of key obstacle characteristic variables.

[0105] In one feasible implementation, the step of performing collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle includes:

[0106] Based on the set of key obstacle feature variables and the current driving feature variables, a collision analysis is performed to calculate the theoretical collision point and theoretical collision time.

[0107] If the theoretical collision time is less than the preset minimum collision time and / or the distance between the critical obstacle and the theoretical collision point is less than the preset minimum safe distance, the target vehicle is controlled to decelerate and avoid the obstacle.

[0108] In one feasible implementation, the above method further includes:

[0109] If the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, the speed of the target vehicle and the speed of the key obstacle are both less than or equal to the preset game speed, and the distance between the key obstacle and the theoretical collision point and the distance between the target vehicle and the theoretical collision point are both less than or equal to the preset game distance, and the distance between the target vehicle and the theoretical collision point is less than or equal to the distance between the key obstacle and the theoretical collision point, the target vehicle is controlled to continue driving at a predetermined speed.

[0110] In one feasible implementation, the above method further includes:

[0111] If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the critical obstacle and the theoretical collision point is greater than or equal to the preset minimum safe distance, or if any one of the target vehicle's speed and the critical obstacle's speed is greater than the preset game speed, or if any one of the distance between the critical obstacle and the theoretical collision point and the target vehicle's distance from the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle arrives at the theoretical collision point and the time the critical obstacle arrives at the theoretical collision point is less than the preset game time, then the target vehicle is controlled to decelerate and avoid the collision.

[0112] In one feasible implementation, the above method further includes:

[0113] If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, or if any one of the speeds of the target vehicle and the key obstacle is greater than the preset game speed, or if any one of the distances between the key obstacle and the theoretical collision point and the target vehicle and the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle reaches the theoretical collision point and the time the key obstacle reaches the theoretical collision point is greater than or equal to the preset game time, then the target vehicle is controlled to continue traveling at a predetermined speed.

[0114] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0115] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An automated driving control method for a vehicle exiting a roundabout, characterized in that, include: Obtain the current driving characteristic variables of the target vehicle; Obtain a set of motion characteristic variables of obstructing obstacles in a first direction and a set of motion characteristic variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle; Game analysis is performed based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables. The game analysis is performed by filtering the characteristic variables of unaffected crossing obstacles in the set of motion characteristic variables of the crossing obstacles based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables. The unaffected crossing obstacles are crossing obstacles that are not affected by the obstructing obstacles. Collision analysis is performed based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

2. The method according to claim 1, characterized in that, The current driving feature variables include Frenet coordinates and vehicle length variables, and the motion feature variables include Frenet coordinates and motion speed direction; The process of obtaining the set of motion characteristic variables of occluding obstacles in the first direction and the set of motion characteristic variables of crossing obstacles in the second direction includes: The obstacle traversing motion feature variable set is constructed by constructing obstacle motion feature variables whose lateral value of Frenet coordinates is greater than that of the target vehicle's Frenet coordinates and whose motion speed direction coincides with the second direction; The obstacle motion feature variables are constructed as the set of obstacle motion feature variables, where the lateral value of the Frenet coordinate is greater than the lateral value of the target vehicle's Frenet coordinate, the lateral value of the Frenet coordinate is greater than a first reference value, the lateral value of the Frenet coordinate is less than a second reference value, and the direction of the motion speed coincides with the first direction. The first reference value is the difference between the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body, and the second reference value is the sum of the lateral value of the target vehicle's Frenet coordinate and half the length of the vehicle body.

3. The method according to claim 2, characterized in that, The set of motion feature variables also includes lane information. The step of performing game theory analysis based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain the set of key obstacle characteristic variables includes: In the same lane information, among the set of motion characteristic variables of obstacles crossing the lane, select the motion characteristic variables of obstacles crossing the lane with smaller lateral values ​​of Frenet coordinates to construct the set of obstacles crossing the front of the lane. Game theory analysis is performed based on the set of obstacles crossing the front of the formation and the set of motion characteristic variables of the obstacles crossing the formation to obtain the set of key obstacle characteristic variables.

4. The method according to claim 1, characterized in that, The step of determining the roundabout exit strategy of the target vehicle by performing collision analysis based on the set of key obstacle feature variables and the current driving feature variables includes: Based on the set of key obstacle feature variables and the current driving feature variables, a collision analysis is performed to calculate the theoretical collision point and theoretical collision time. If the theoretical collision time is less than the preset minimum collision time and / or the distance between the critical obstacle and the theoretical collision point is less than the preset minimum safe distance, the target vehicle is controlled to decelerate and avoid the obstacle.

5. The method according to claim 4, characterized in that, Also includes: If the theoretical collision time is greater than or equal to the preset minimum collision time and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, the speed of the target vehicle and the speed of the key obstacle are both less than or equal to the preset game speed, and the distance between the key obstacle and the theoretical collision point and the distance between the target vehicle and the theoretical collision point are both less than or equal to the preset game distance, and the distance between the target vehicle and the theoretical collision point is less than or equal to the distance between the key obstacle and the theoretical collision point, the target vehicle is controlled to continue driving at a predetermined speed.

6. The method according to claim 5, characterized in that, Also includes: If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the critical obstacle and the theoretical collision point is greater than or equal to the preset minimum safe distance, or if any one of the target vehicle's speed and the critical obstacle's speed is greater than the preset game speed, or if any one of the distance between the critical obstacle and the theoretical collision point and the target vehicle's distance from the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle arrives at the theoretical collision point and the time the critical obstacle arrives at the theoretical collision point is less than the preset game time, then the target vehicle is controlled to decelerate and avoid the collision.

7. The method according to claim 6, characterized in that, Also includes: If the theoretical collision time is greater than or equal to the preset minimum collision time, and the distance between the key obstacle and the theoretical collision point is greater than or equal to the preset minimum safety distance, or if any one of the speeds of the target vehicle and the key obstacle is greater than the preset game speed, or if any one of the distances between the key obstacle and the theoretical collision point and the target vehicle and the theoretical collision point is greater than the preset game distance, or if the time difference between the time the target vehicle reaches the theoretical collision point and the time the key obstacle reaches the theoretical collision point is greater than or equal to the preset game time, then the target vehicle is controlled to continue traveling at a predetermined speed.

8. An automatic driving control device for a vehicle exiting a roundabout, characterized in that, include: The first acquisition unit is used to acquire the current driving characteristic variables of the target vehicle; The second acquisition unit is used to acquire a set of motion feature variables of occluding obstacles in a first direction and a set of motion feature variables of crossing obstacles in a second direction, wherein the first direction does not intersect with the driving direction of the target vehicle, and the second direction intersects with the driving direction of the target vehicle. The third acquisition unit is used to perform a game analysis operation based on the set of motion characteristic variables of the obstructing obstacles and the set of motion characteristic variables of the crossing obstacles to obtain a set of key obstacle characteristic variables. The game analysis operation is to filter the characteristic variables of unaffected crossing obstacles in the set of motion characteristic variables of the crossing obstacles based on the set of motion characteristic variables of the obstructing obstacles to obtain the set of key obstacle characteristic variables. The unaffected crossing obstacles are crossing obstacles that are not affected by the obstructing obstacles. The determination unit is used to perform collision analysis based on the set of key obstacle feature variables and the current driving feature variables to determine the roundabout exit strategy of the target vehicle.

9. An electronic device, comprising: The memory and processor are characterized in that the processor is used to implement the steps of the automatic driving control method for a vehicle to exit a roundabout as described in any one of claims 1-7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the automatic driving control method for a vehicle to exit a roundabout as described in any one of claims 1-7.

Images