Vehicle lane changing decision-making method, system and equipment based on closed park

Abstract

The invention provides a vehicle lane changing decision-making method, system and device based on a closed park, and the method comprises the steps: preliminarily judging the behavior of a vehicle based on a road rule of the closed park; if the vehicle is in the driving behavior and a dangerous obstacle exists in a target area in front of the driving direction of the immutable lane where the vehicle is located, the vehicle is stopped; if the vehicle is in a driving behavior and a dangerous obstacle exists in a target area in front of the driving direction of the variable lane where the vehicle is located, obtaining the target areas of the variable lane where the vehicle is located, the left lane and the right lane and absolute coordinates and speed information of the dangerous obstacle on the corresponding target areas, and calculating a danger coefficient of the corresponding dangerous obstacle; and comparing with a set standard danger coefficient to obtain a lane changing decision of the vehicle. The problem that in the related technology, the lane changing decision is based on a complex model and cannot meet the lane changing decision requirement in a specific scene of a closed park is solved.

Description

Technical Field

[0001] The present application relates to the technical field of autonomous driving systems, and specifically to a vehicle lane changing decision method, system and equipment based on a closed park. Background Art

[0002] The core of autonomous driving lane changing decision is to comprehensively consider the current driving status of the vehicle, the driving intentions of other vehicles and traffic environment factors, and determine whether to change lanes and the timing and path of the lane change through decision models and algorithms.

[0003] The characteristics of the closed park scene: relatively fixed, with little change, for a specific scene environment; secondly, the speed of vehicles in the closed park is relatively low, which is generally suitable for sanitation vehicles. In the existing technology, the mainstream lane change decision is based on complex models designed for complex scenes, and requires a lot of calculations to achieve, with high requirements for models and hardware, and cannot meet the lane change decision needs in the specific scene of the closed park; according to the unique characteristics of the closed park, a combination of light decision and heavy decision is adopted to reduce computing power to make the best decision. Summary of the invention

[0004] The present application provides a vehicle lane changing decision method, system and device based on a closed park, which can solve the problem that the lane changing decision in the prior art is based on a complex model and cannot meet the lane changing decision needs in the specific scenario of a closed park.

[0005] In a first aspect, an embodiment of the present application provides a vehicle lane changing decision method based on a closed park, which includes preliminarily judging the behavior of the vehicle based on the road rules of the closed park; if the vehicle is in a driving behavior and the vehicle is in a fixed lane, when there is a dangerous obstacle in the target area ahead in the driving direction, stopping the vehicle; if the vehicle is in a driving behavior and the vehicle is in a variable lane, when there is a dangerous obstacle in the target area ahead in the driving direction, obtaining the target areas of the variable lane and the left and right lanes where the vehicle is located, and the absolute coordinates and speed information of the dangerous obstacles in the corresponding target areas, calculating the risk coefficient of the corresponding dangerous obstacle, and comparing it with the set standard risk coefficient to obtain the lane changing decision of the vehicle.

[0006] In combination with the first aspect, in one embodiment, based on the road rules of the closed park, judging the vehicle behavior includes the following steps: if there is a gate in the target area in front of the driving direction of the lane where the vehicle is located, the vehicle is parking for collision avoidance; if the vehicle is about to reach the parking point and there is an obstacle between the vehicle and the parking point, the vehicle is parking for collision avoidance; if the vehicle is about to reach the parking point and there is no obstacle between the vehicle and the parking point, the vehicle is precisely parking; if the vehicle is not parking for collision avoidance or precise parking, it is driving, and the driving behavior includes forward driving and reverse driving.

[0007] In combination with the first aspect, in one embodiment, obtaining the target area in front of the lane in which the vehicle is located and in the left and right lanes in the driving direction includes the following steps: setting the midpoint of the rear of the vehicle as the first projection point of the vehicle, and setting the length of the target area to n; obtaining the pre-driving trajectory n ahead of the first projection point in the driving direction as the first target area; horizontally projecting the first projection point on the center line of the left lane of the current vehicle, and setting it as the second projection point, obtaining the pre-driving trajectory n ahead of the second projection point as the second target trajectory; horizontally projecting the first projection point on the center line of the right lane of the current vehicle, and setting it as the third projection point, and obtaining the pre-driving trajectory n ahead of the third projection point as the third target trajectory.

[0008] In combination with the first aspect, in one embodiment, determining whether there are dangerous obstacles in the first target area, the second target area, and the third target area includes the following steps: setting half the width of the vehicle to d; obtaining the absolute coordinates of the contour points of the first obstacle on the first target trajectory, and if the minimum lateral distance between the contour points of the first obstacle and the first projection point is less than d+0.1m, setting it as the first dangerous obstacle; repeating the above steps to determine the second obstacle on the second target trajectory, and to determine the third obstacle on the third target trajectory.

[0009] In combination with the first aspect, in one embodiment, based on the ratio of the relative distance and relative speed between the first dangerous obstacle and the vehicle, a first collision time of the first dangerous obstacle is obtained; based on the minimum distance between the first dangerous obstacle and the first projection point of the vehicle, a first distance coefficient of the first dangerous obstacle is calculated; based on the first collision time and the first distance coefficient, a first risk coefficient is calculated; repeat the above steps to calculate the second risk coefficient of the second dangerous obstacle and the third risk coefficient of the third dangerous obstacle.

[0010] In combination with the first aspect, in one implementation, calculating the corresponding distance coefficient of the corresponding dangerous obstacle includes the following steps: based on the current vehicle, setting the corresponding standard distances d1 and d2, setting the minimum distance between the first dangerous obstacle and the first projection point of the vehicle to x, and setting the first distance coefficient to M1; if x>d1, then M1=0, that is, there is no safety hazard; if x<d2, then M1 is infinite, that is, a collision has occurred; if d2<x<d1, then Repeat the above steps to calculate the second distance coefficient of the second dangerous obstacle and the third distance coefficient of the third dangerous obstacle.

[0011] In combination with the first aspect, in one implementation, calculating the corresponding risk coefficient of the corresponding dangerous obstacle includes the following steps: setting the standard collision time to TTC0, the first risk coefficient to W1, and the first collision time to TTC1; if M1=0, then W1=0; if M1 is infinite, then W1 is infinite; if 0<M1<+∞, then Repeat the above steps to calculate the second risk coefficient W2 of the second dangerous obstacle and the third risk coefficient W3 of the third dangerous obstacle.

[0012] In combination with the first aspect, in one embodiment, obtaining a lane changing decision of a vehicle includes the following steps: based on the current vehicle, setting a corresponding standard risk coefficient W0; if the vehicle is reversing and W1>W0, the vehicle stops or follows the vehicle; if the vehicle is reversing and W1<W0, the vehicle reverses normally; if the vehicle is moving forward and W1<W0, the vehicle cruises adaptively; if the vehicle is moving forward and W1>W0 and W2<W0, the vehicle changes lanes to the left; if the vehicle is moving forward and W1>W0 and W2>W0 and W3<W0, the vehicle changes lanes to the right; if the vehicle is moving forward and W1>W0 and W2>W0 and W3>W0, the vehicle stops or follows the vehicle.

[0013] On the second aspect, an embodiment of the present application provides a vehicle lane changing decision system based on a closed park, which includes an information acquisition module, which is used to obtain the road rules of the closed park and the behavior of the vehicle, obtain the target areas of the variable lane and the left and right lanes where the vehicle is traveling, and obtain the absolute coordinates and speed information of the dangerous obstacles in the corresponding target areas; a vehicle management module, which is used to preliminarily judge the behavior of the vehicle based on the road rules of the closed park; calculate the risk coefficient of the corresponding dangerous obstacle, and compare it with the set standard risk coefficient to obtain the lane changing decision of the vehicle, and then apply the lane changing decision to the vehicle control end.

[0014] In a third aspect, an embodiment of the present application provides a closed park-based vehicle lane changing decision device, which includes a processor, a memory, and a closed park-based vehicle lane changing decision program stored in the memory and executable by the processor, wherein when the closed park-based vehicle lane changing decision program is executed by the processor, the steps of the closed park-based vehicle lane changing decision method as described in any one of claims 1 to 8 are implemented.

[0015] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0016] A vehicle lane-changing decision method based on a closed park is proposed, wherein the behavior of the vehicle is preliminarily judged according to the road rules of the closed park. In the closed park, the road rules include specific gates, parking spots, single lanes or multi-lane scenarios, etc., and the behavior of the vehicle includes driving, parking, etc.; when the vehicle is driving, if there is an obstacle in the target area in front of the driving direction of the immutable lane, then if it is judged to be a dangerous obstacle, then the vehicle will stop directly, otherwise it will pass directly; if there is an obstacle in the target area in front of the driving direction of the variable lane, then if the obstacle is not a dangerous obstacle, then it will pass directly, otherwise it will be judged in turn whether the obstacles in the target areas of the left and right lanes are dangerous obstacles, and the information of the corresponding dangerous obstacles is obtained, and the corresponding risk coefficients of the dangerous obstacles in the corresponding lanes are calculated in turn, and compared with the standard risk coefficients, and finally the best lane-changing decision is obtained, thereby solving the problem that the lane-changing decision of the prior art is based on a complex model and cannot meet the lane-changing decision requirements in the specific scenario of the closed park. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the vehicle lane changing decision method based on a closed park in this application;

[0018] Figure 2 This is a flow chart of the vehicle lane-changing decision system based on a closed park for this application;

[0019] Figure 3 This is a schematic diagram of the first application scenario of the vehicle lane change decision method, system and device based on a closed park in this application;

[0020] Figure 4 This is a schematic diagram of a second application scenario of the vehicle lane change decision method, system and device based on a closed park in this application;

[0021] Figure 5 This is a schematic diagram of the third application scenario of the vehicle lane changing decision method, system and equipment based on a closed park in this application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0024] The reasons for the invention of this application are as follows: the characteristics of the closed park scene: relatively fixed, with little change, and a specific scene environment; secondly, the speed of vehicles in the closed park is relatively low, which is generally suitable for sanitation vehicles. In the prior art, the mainstream lane change decision is based on complex models designed for complex scenes, and requires a lot of calculations to achieve, with high requirements for models and hardware, and cannot meet the lane change decision needs in the specific scene of the closed park.

[0025] This method is mainly used in sanitation vehicles and can autonomously calculate lane-changing decisions under corresponding demand scenarios.

[0026] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0027] In the first aspect, the embodiment of the present application provides a vehicle lane change decision method based on a closed park, referring to Figure 1 , Figure 1 This is a flow chart of the vehicle lane change decision method based on a closed park in this application. Figure 1 As shown in FIG. 1 , the vehicle lane-changing decision method based on the closed park includes:

[0028] Step 101: Preliminarily determine the behavior of the vehicle based on the road rules of the closed park;

[0029] In a closed campus, road rules include specific gates, parking spots, single-lane or multi-lane scenarios, etc., and vehicle behaviors include driving, parking, etc.; preliminary judgments are made on the vehicle's behavior so that different decisions can be made for different behaviors.

[0030] Step 102: If the vehicle is in a driving behavior and the vehicle is in an immutable lane and there is a dangerous obstacle in the target area ahead of the driving direction, the vehicle stops;

[0031] Based on the vehicle's driving behavior, if there is an obstacle in the target area ahead of the driving direction of the immutable lane, if it is judged to be a dangerous obstacle, then stop directly, otherwise pass directly.

[0032] Step 103: If the vehicle is in driving behavior and the vehicle is in an immutable lane, and there is a dangerous obstacle in the target area ahead of the driving direction, obtain the target areas of the variable lane and the left and right lanes where the vehicle is located, and the absolute coordinates and speed information of the dangerous obstacles in the corresponding target areas, calculate the risk coefficient of the corresponding dangerous obstacle, and compare it with the set standard risk coefficient to obtain the vehicle's lane change decision.

[0033] If there is an obstacle in the target area ahead of the variable lane driving direction, then if the obstacle is not a dangerous obstacle, it will be passed directly. Otherwise, it will be determined whether the obstacles in the target areas of the left and right lanes are dangerous obstacles, and the information of the corresponding dangerous obstacles will be obtained. The corresponding danger coefficients of the dangerous obstacles in the corresponding lanes will be calculated in turn and compared with the standard danger coefficients, and finally the best lane changing decision will be obtained, thereby solving the problem that the lane changing decision of the existing technology is based on a complex model and cannot meet the lane changing decision needs in the specific scenario of a closed park.

[0034] Based on the road rules of the closed park, judging the parking behavior of the vehicle includes the following steps:

[0035] If there is a gate in the target area ahead of the vehicle's lane in the direction of travel, the vehicle is parking to avoid a collision; if the vehicle is about to reach a parking spot and there is an obstacle between the vehicle and the parking spot, the vehicle is parking to avoid a collision; if the vehicle is about to reach a parking spot and there is no obstacle between the vehicle and the parking spot, the vehicle is precisely parking; if the vehicle is not parking to avoid a collision or precisely parking, it is driving, and driving includes forward driving and reverse driving.

[0036] This section specifically defines the road rules for the closed park. When the obstacle is a gate, no algorithm calculation is required, and the vehicle stops to avoid collisions. When precise parking is required, specific calculations are required for the obstacle, vehicle, and parking spot. The distance between the obstacle and the vehicle is x1, and the distance between the parking spot and the vehicle is x2. When parking to avoid collisions, if x2>(x1-x0), the behavior is parking to avoid collisions, otherwise the behavior is precise parking.

[0037] Obtaining the target area in front of the vehicle's lane and in the left and right lanes includes the following steps:

[0038] The midpoint of the rear of the vehicle is set as the first projection point of the vehicle, and the length of the target area is set to n; the pre-driving trajectory n ahead of the first projection point in the driving direction is obtained as the first target area; the first projection point is horizontally projected on the center line of the left lane of the current vehicle, and it is set as the second projection point, and the pre-driving trajectory n ahead of the second projection point is obtained as the second target trajectory; the first projection point is horizontally projected on the center line of the right lane of the current vehicle, and it is set as the third projection point, and the pre-driving trajectory n ahead of the third projection point is obtained as the third target trajectory.

[0039] In this step, n is generally set to 50m, and the midpoint of the rear of the vehicle is determined as the first projection point. According to the current direction of the vehicle, starting from the first projection point, it extends forward 50 meters to obtain the target area on the path. This section of the path is called the first target area. The first projection point is horizontally projected at the center line of the left lane of the current vehicle, and the target area on the path is obtained by extending forward 50 meters from the projection point. This section of the path is the second target area; the first projection point is horizontally projected at the center line of the right lane of the current vehicle, and the target area on the path is obtained by extending forward 50 meters from the projection point. This section of the path is the third target area; through the above steps, the target area in front of the lane where the vehicle is located, i.e., the first target area, the target area of ​​the left lane, i.e., the second target area, and the target area of ​​the right lane, i.e., the third target area, are obtained. This method provides an effective way to identify and judge the relationship between the vehicle and the surrounding environment during driving, laying the foundation for subsequent lane change decision-making.

[0040] Determining whether dangerous obstacles exist in the first target area, the second target area, and the third target area includes the following steps:

[0041] Set the half width of the vehicle to d; obtain the absolute coordinates of the contour point of the first obstacle on the first target trajectory. If the minimum lateral distance between the contour point of the first obstacle and the first projection point is less than d+0.1m, set it as the first dangerous obstacle; repeat the above steps to determine the second obstacle on the second target trajectory, and determine the third obstacle on the third target trajectory.

[0042] In this step, first determine the vehicle parameters, that is, set the half width of the vehicle as d, collect the absolute coordinates of the contour points of the obstacles in the first target area, and for each contour point of the obstacle, calculate its lateral distance Y1 from the first projection point. If the minimum value of Y1 is less than d+0.1m, it is recorded as the first dangerous obstacle; collect the absolute coordinates of the contour points of all possible obstacles in the second target area, and for each contour point of the obstacle, calculate its lateral distance Y2 from the second projection point. If the minimum value of Y2 is less than d+0.1m, it is recorded as the second dangerous obstacle; collect the absolute coordinates of the contour points of all possible obstacles in the third target area, and for each contour point of the obstacle, calculate its lateral distance Y3 from the third projection point. If the minimum value of Y3 is less than d+0.1m, it is recorded as the third dangerous obstacle. Through the above steps, the dangerous obstacles in the first target area, the second target area and the third target area can be effectively judged to pave the way for subsequent lane change decisions and ensure the safety of vehicle driving. By judging obstacles according to the actual lateral distance, it can be identified in time and make corresponding adjustments.

[0043] Based on the ratio of the relative distance and relative speed between the first dangerous obstacle and the vehicle, the first collision time of the first dangerous obstacle is obtained; based on the minimum distance between the first dangerous obstacle and the first projection point of the vehicle, the first distance coefficient of the first dangerous obstacle is calculated; based on the first collision time and the first distance coefficient, the first danger coefficient is calculated; repeat the above steps to calculate the second danger coefficient of the second dangerous obstacle and the third danger coefficient of the third dangerous obstacle.

[0044] In this step, the risk factor of the corresponding dangerous obstacle is calculated by calculating the collision time and distance coefficient of each corresponding dangerous obstacle. It should be noted that the collision time can be recorded as TTC, that is, the ratio of the relative distance and relative speed between the dangerous obstacle and the vehicle; the distance coefficient of the dangerous obstacle is calculated according to the relative longitudinal distance between the dangerous obstacle and the vehicle. Based on the collision time and distance coefficient, the corresponding risk factor can be calculated in the subsequent steps.

[0045] Calculating the corresponding distance coefficient for the corresponding dangerous obstacle includes the following steps:

[0046] Based on the current vehicle, set the corresponding standard distances d1 and d2, set the minimum distance between the first dangerous obstacle and the first projection point of the vehicle to x, and set the first distance coefficient to M1; if x>d1, then M1=0, that is, there is no safety hazard; if x<d2, then M1 is infinite, that is, a collision has occurred; if d2<x<d1, then Repeat the above steps to calculate the second distance coefficient of the second dangerous obstacle and the third distance coefficient of the third dangerous obstacle.

[0047] In this step, the standard distance d1 is the maximum safety distance, and there is no safety hazard when it exceeds this distance; the standard distance d2 is the minimum safety distance, and a collision has occurred when it is lower than this distance; the minimum distance x1 between the first dangerous obstacle and the first projection point of the vehicle is the actual distance between the vehicle and the first dangerous obstacle; M1 is the risk factor for evaluating the first dangerous obstacle. If xi>d1, then Mi=0, that is, there is no safety hazard; if xi<d2, then Mi is infinite, that is, a collision has occurred; if d2<xi<d1, then Through the above steps, the distance coefficients of the first, second and third dangerous obstacles can be calculated. These distance coefficients can help evaluate the danger level of each obstacle and prepare for the subsequent calculation of the danger coefficients of the first, second and third dangerous obstacles.

[0048] Calculating the corresponding risk factor of the corresponding dangerous obstacle includes the following steps:

[0049] Set the standard collision time to TTC0, the first risk factor to W1, and the first collision time to TTC1; if M1=0, then W1=0; if M1 is infinite, then W1 is infinite; if 0<M1<+∞, then Repeat the above steps to calculate the second risk coefficient W2 of the second dangerous obstacle and the third risk coefficient W3 of the third dangerous obstacle.

[0050] In this step, the standard collision time TTC0 is the preset standard time, which is used to evaluate the threshold of collision risk; the first risk coefficient W1, the first distance coefficient M1 and the first collision time TTC1; if Mi = 0, then Wi = 0; if Mi is infinite, then Wi is infinite; if 0 < Mi < +∞, then Through the above steps, you can calculate the risk factors W1, W2 and W3 corresponding to dangerous obstacles. These risk factors can be used as the basis for decision-making.

[0051] Obtaining the lane change decision of the vehicle comprises the following steps:

[0052] Based on the current vehicle, set the corresponding standard risk factor W0;

[0053] If the vehicle is driving in reverse and W1>W0, the vehicle is parked or following; if the vehicle is driving in reverse and W1<W0, the vehicle is reversing normally;

[0054] If the vehicle is moving forward and W1<W0, the vehicle will perform adaptive cruise control; if the vehicle is moving forward and W1>W0 and W2<W0, the vehicle will change lanes to the left; if the vehicle is moving forward and W1>W0 and W2>W0 and W3<W0, the vehicle will change lanes to the right; if the vehicle is moving forward and W1>W0 and W2>W0 and W3>W0, the vehicle will stop or follow a vehicle.

[0055] In this step, the risk coefficients corresponding to the dangerous obstacles in different target areas have been obtained, and based on these coefficients and the set standard risk coefficient W0, a reasonable lane change decision for the vehicle is obtained. Among them, when the vehicle is reversing, W1>W0, that is, there is a dangerous obstacle, then according to the actual application scenario, if the obstacle is stationary, the vehicle will make a parking decision, and if the obstacle is moving, the vehicle will make a following decision; if W1<W0, the vehicle can reverse normally; if the vehicle is moving forward, then the size of W1 and W0 is determined. If W1<W0, the vehicle will cruise adaptively, that is, the vehicle will make a normal driving decision. If W1>W0, the left lane is given priority. The size of W2 and W0, if W2<W0, the vehicle will make a left lane change decision, and if W2>W0, the right lane will be considered. The size of W3 and W0, if W3<W0, the vehicle makes a decision to change lanes right. If W3>W0, it means that it is impossible to change lanes. According to the actual application scenario, if the obstacle is stationary, the vehicle will make a decision to stop. If the obstacle is moving, the vehicle will make a decision to follow the vehicle.

[0056] In a second aspect, the embodiment of the present application further provides a vehicle lane changing decision system based on a closed park, and the vehicle lane changing decision system based on a closed park includes:

[0057] An information acquisition module is used to obtain the road rules of the closed park and the behavior of the vehicle, obtain the target areas of the variable lane and the left and right lanes where the vehicle is traveling, and obtain the absolute coordinates and speed information of the dangerous obstacles in the corresponding target areas; a vehicle management module is used to preliminarily judge the behavior of the vehicle based on the road rules of the closed park; calculate the risk coefficient of the corresponding dangerous obstacle, and compare it with the set standard risk coefficient to obtain the lane changing decision of the vehicle, and then apply the lane changing decision to the vehicle control end.

[0058] In this system, the information acquisition module obtains the target trajectory information of the lane where the current vehicle is located and its left and right lanes, obtains the absolute coordinates of the first, second and third dangerous obstacles and the relative speed with the vehicle; uses sensors such as laser radar, camera or ultrasonic sensor to scan and obtain the target trajectory. Obstacle detection detects surrounding obstacles in real time and converts their coordinates into absolute coordinates based on the vehicle projection point. Using sensor data and vehicle speed, calculate the speed of each obstacle relative to the vehicle, and output the target trajectory and obstacle information of the current lane, left and right lanes for processing by the information processing module. It should be noted that the information processing module receives information from the information acquisition module, calculates the relevant data of dangerous obstacles and vehicles, and assigns standard parameters, and then passes the information processing results to the vehicle management module. The vehicle management module compares the processed data and makes a lane change decision based on the results, which is applied to the vehicle control end; this closed park vehicle lane change decision system can effectively improve the safety and intelligence level of vehicle driving through the collaborative work of three modules. Through real-time monitoring, data processing and decision execution, the safe lane change of vehicles in a dynamic environment is guaranteed.

[0059] On the third aspect, an embodiment of the present application provides a vehicle lane changing decision device based on a closed park. The vehicle lane changing decision device based on the closed park can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0060] In an embodiment of the present application, a closed park-based vehicle lane change decision device may include a processor, a memory, a communication interface, and a communication bus. Among them, the communication bus may be of any type, used to realize the interconnection between the processor, the memory, and the communication interface. The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to realize the interconnection of devices inside the closed park-based vehicle lane change decision device, and an interface for realizing the interconnection between the closed park-based vehicle lane change decision device and other devices (such as other computing devices or user devices). The physical interface may be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device may be a display (Display), a keyboard (Keyboard), etc.

[0061] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0062] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0063] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0064] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0065] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0067] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle lane-changing decision method based on a closed park, characterized in that: The vehicle lane-changing decision method based on a closed park includes: Make a preliminary judgement on the vehicle's behavior based on the road rules of the closed park; If the vehicle is in a moving behavior and is in an immutable lane, and there is a dangerous obstacle in the target area ahead of the moving direction, the vehicle stops; If the vehicle is in motion and is in a variable lane, and there is a dangerous obstacle in the target area ahead of the driving direction, the target areas of the variable lane and the left and right lanes where the vehicle is located, as well as the absolute coordinates and speed information of the dangerous obstacles in the corresponding target areas are obtained, the danger coefficient of the corresponding dangerous obstacle is calculated, and compared with the set standard danger coefficient to obtain the vehicle's lane changing decision.

2. The closed park-based vehicle lane-changing decision method according to claim 1, characterized in that: Based on the road rules of the closed park, judging vehicle behavior includes the following steps: If there is a gate in the target area ahead of the vehicle in the direction of travel, the vehicle stops to avoid collision. If the vehicle is about to reach the parking spot and there is an obstacle between the vehicle and the parking spot, the vehicle will perform a collision avoidance parking behavior; if the vehicle is about to reach the parking spot and there is no obstacle between the vehicle and the parking spot, the vehicle will perform a precise parking behavior; If the vehicle is not parking to avoid a collision or parking precisely, it is in driving behavior, and driving behavior includes forward driving and reverse driving.

3. The closed park-based vehicle lane-changing decision method according to claim 1, characterized in that: Obtaining the target area in front of the vehicle's lane and in the left and right lanes includes the following steps: The midpoint of the vehicle's rear end is set as the first projection point of the vehicle, and the length of the target area is set as n; Obtaining a pre-travel trajectory n ahead of the first projection point in the travel direction as a first target area; Project the first projection point horizontally onto the center line of the left lane of the current vehicle and set it as the second projection point, and obtain the pre-travel trajectory n ahead of the second projection point as the second target trajectory; The first projection point is horizontally projected onto the center line of the right lane of the current vehicle, and is set as the third projection point. The pre-driving trajectory n ahead of the third projection point is obtained as the third target trajectory.

4. The closed park-based vehicle lane-changing decision method according to claim 3, characterized in that: Determining whether the first target area, the second target area, and the third target area have dangerous obstacles includes the following steps: Set the half width of the vehicle to d; Obtaining the absolute coordinates of the contour point of the first obstacle on the first target trajectory, and setting it as the first dangerous obstacle if the minimum lateral distance between the contour point of the first obstacle and the first projection point is less than d+0.1m; Repeat the above steps to determine the second obstacle on the second target track and determine the third obstacle on the third target track.

5. The closed park-based vehicle lane-changing decision method according to claim 4, characterized in that: Obtaining a first collision time of the first dangerous obstacle based on a ratio of a relative distance and a relative speed between the first dangerous obstacle and the vehicle; Calculating a first distance coefficient of the first dangerous obstacle based on a minimum distance between the first dangerous obstacle and a first projection point of the vehicle; Calculate the first risk factor based on the first collision time and the first distance coefficient; Repeat the above steps to calculate the second risk factor of the second dangerous obstacle and calculate the third risk factor of the third dangerous obstacle.

6. The closed park-based vehicle lane-changing decision method according to claim 5, characterized in that: Calculating the corresponding distance coefficient for the corresponding dangerous obstacle includes the following steps: Based on the current vehicle, set corresponding standard distances d1 and d2, set the minimum distance between the first dangerous obstacle and the first projection point of the vehicle to x, and set the first distance coefficient to M1; If x>d1, then M1=0, which means there is no safety hazard; If x < d2, then M1 is infinite, which means a collision has occurred; If d2<x<d1, then Repeat the above steps to calculate the second distance coefficient of the second dangerous obstacle and the third distance coefficient of the third dangerous obstacle.

7. The closed park-based vehicle lane-changing decision method according to claim 5 or 6, characterized in that: Calculating the corresponding risk factor of the corresponding dangerous obstacle includes the following steps: The standard collision time is set to TTC0, the first risk factor is set to W1, and the first collision time is set to TTC1; If M1=0, then W1=0; If M1 is infinite, then W1 is infinite; If 0<M1<+∞, then Repeat the above steps to calculate the second risk coefficient W2 of the second dangerous obstacle and the third risk coefficient W3 of the third dangerous obstacle.

8. The closed park-based vehicle lane-changing decision method according to claim 7, characterized in that: Obtaining the lane change decision of the vehicle comprises the following steps: Based on the current vehicle, set the corresponding standard risk factor W0; If the vehicle is driving in reverse and W1>W0, the vehicle stops or follows; If the vehicle is driving in reverse and W1<W0, the vehicle is reversing normally; If the vehicle is moving forward and W1<W0, the vehicle will be driving in adaptive cruise mode; If the vehicle is moving forward and W1>W0 and W2<W0, the vehicle changes lanes to the left; If the vehicle is moving forward, and W1>W0 and W2>W0 and W3<W0, the vehicle changes lanes right; If the vehicle is moving forward and W1>W0 and W2>W0 and W3>W0, the vehicle stops or follows the vehicle.

9. A vehicle lane-changing decision system based on a closed park, characterized in that: The closed park-based vehicle lane-changing decision system comprises: An information acquisition module is used to obtain the road rules of the closed park and the behavior of the vehicle, obtain the target area of ​​the variable lane and the left and right lanes where the vehicle is traveling, and obtain the absolute coordinates and speed information of the dangerous obstacles in the corresponding target area; The vehicle management module is used to preliminarily judge the behavior of the vehicle based on the road rules of the closed park; calculate the risk coefficient of the corresponding dangerous obstacle and compare it with the set standard risk coefficient to obtain the vehicle's lane changing decision, and then apply the lane changing decision to the vehicle control end.

10. A vehicle lane-changing decision device based on a closed park, characterized in that: The closed park-based vehicle lane changing decision device comprises a processor, a memory, and a closed park-based vehicle lane changing decision program stored in the memory and executable by the processor, wherein when the closed park-based vehicle lane changing decision program is executed by the processor, the steps of the closed park-based vehicle lane changing decision method as described in any one of claims 1 to 8 are implemented.

Images