Vehicle control method and device, electronic device and storage medium

Abstract

The application discloses a vehicle control method and device based on automatic driving, an electronic device and a storage medium, and the method comprises the following steps: acquiring scene information of a target vehicle; judging whether the target vehicle is located at a lane changing detection point based on the scene information; if yes, determining whether the target vehicle is located at a safe lane changing region based on a longitudinal speed difference and a longitudinal distance between the target vehicle and a front vehicle and a target lane changing time of the target vehicle, wherein the front vehicle is a front vehicle in a target lane of the target vehicle; and if no, determining a longitudinal safe lane changing acceleration of the target vehicle in a current step length of a lane coordinate system based on the target lane changing time, so as to control the target vehicle to force lane changing. In this way, the safety requirement of vehicle lane changing can be met.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer data processing, and particularly relates to a vehicle control method and device based on automatic driving, an electronic device and a storage medium. BACKGROUND

[0002] With the continuous development of highway and urban road network in China in recent years, the number of traffic safety accidents caused by lane changing and merging of vehicles is increasing. Part of the accident is due to the fact that the lane changing vehicle cannot timely and comprehensively obtain the driving information of other vehicles when changing lanes and merging, so that the driver makes a wrong decision.

[0003] Vehicle lane changing and merging is an important function of automatic driving technology, which needs to fully consider the road environment information and the driving conditions of surrounding vehicles, and the decision-making process is complex. How to reduce the safety hazards of vehicle lane changing and improve the driving efficiency and comfort of the driver is of great significance.

[0004] The information disclosed in the background section of this document is only intended to increase the understanding of the overall background of the present application and should not be considered as an acknowledgment or any form of suggestion that this information forms the prior art known to those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a vehicle control method based on automatic driving, which solves the problem of low safety of current vehicle lane changing.

[0006] To achieve the above-mentioned purpose, the present application provides a vehicle control method based on automatic driving, which comprises:

[0007] obtaining scene information of a target vehicle;

[0008] determining whether the target vehicle is located at a lane changing detection point based on the scene information; if yes,

[0009] determining whether the target vehicle is located in a safe lane changing area based on the longitudinal speed difference and longitudinal distance between the target vehicle and a front vehicle in the current step, and the target lane changing time of the target vehicle, wherein the front vehicle is a front vehicle in the target lane changing lane of the target vehicle; if no,

[0010] determining the longitudinal safe lane changing acceleration of the target vehicle in the current step of the lane coordinate system based on the target lane changing time, so as to control the target vehicle to forcibly change lanes.

[0011] In an embodiment, the longitudinal safe lane changing acceleration of the target vehicle in the current step of the lane coordinate system is determined based on the target lane changing time, so as to control the target vehicle to forcibly change lanes, which specifically comprises:

[0012] calculating a lane change adjustment time of the target vehicle, wherein the lane change adjustment time is a time required for the target vehicle to adjust to the set longitudinal acceleration at a speed equal to the longitudinal speed of the front vehicle;

[0013] determining whether the set longitudinal acceleration is a longitudinal safe lane change acceleration based on the lane change adjustment time and a target lane change time.

[0014] In an embodiment, the method specifically comprises:

[0015] selecting the set longitudinal acceleration in a preset longitudinal acceleration strategy interval in an order from small to large absolute value to calculate the lane change adjustment time; and / or,

[0016] determining that the set longitudinal acceleration is the longitudinal safe lane change acceleration when the lane change adjustment time is less than or equal to the target lane change time.

[0017] In an embodiment, the method specifically comprises:

[0018] determining a lateral safe lane change acceleration of a current step of the target vehicle based on the lane change adjustment time, the target lane change time, and a lateral lane change distance;

[0019] determining a heading angle of the current step of the target vehicle based on the lateral safe lane change acceleration and the longitudinal safe lane change acceleration of the current step of the target vehicle.

[0020] In an embodiment, after controlling the target vehicle to forcibly change lanes, the method further comprises:

[0021] determining a longitudinal safe acceleration of a corresponding current step of the target vehicle based on a remaining time of the target vehicle in the current step based on the target lane change time.

[0022] In an embodiment, determining whether the target vehicle is in a safe lane change region based on a longitudinal speed difference and a longitudinal distance between the target vehicle and the front vehicle in the current step, and the target lane change time of the target vehicle specifically comprises:

[0023] determining a collision reference relationship based on the target lane change time of the target vehicle and a time at which the target vehicle reaches the lane change detection point, wherein the collision reference relationship represents an association between the longitudinal speed difference and the initial longitudinal distance between the target vehicle and the front vehicle;

[0024] determining whether the target vehicle is in a safe lane change region based on the longitudinal speed difference and the longitudinal distance between the target vehicle and the front vehicle in the current step, and the collision reference relationship.

[0025] In an embodiment, the scene information comprises coordinates of the target vehicle and the front vehicle in a lane coordinate system;

[0026] determining whether the target vehicle is located at the lane-changing detection point based on the scene information, specifically comprising:

[0027] determining whether a lateral coordinate difference between a collision reference point of the target vehicle and a collision reference line of the front vehicle in a lane coordinate system is less than a set threshold; if yes,

[0028] determining that the target vehicle is located at the lane-changing detection point.

[0029] The application also provides a vehicle control device based on automatic driving, comprising:

[0030] an acquisition module configured to acquire scene information of a target vehicle;

[0031] a determination module configured to determine whether the target vehicle is located at a lane-changing detection point based on the scene information;

[0032] a determination module configured to, when the target vehicle is located at the lane-changing detection point, determine whether the target vehicle is located at a safe lane-changing region based on a longitudinal speed difference and a longitudinal distance between the target vehicle and the front vehicle at a current step length, and a target lane-changing time of the target vehicle;

[0033] a control module configured to, when the target vehicle is not located at the safe lane-changing region, determine a longitudinal safe lane-changing acceleration of the target vehicle at the current step length based on the target lane-changing time, so as to control the target vehicle to forcibly change lanes.

[0034] The application also provides an electronic device, comprising:

[0035] at least one processor; and

[0036] a memory storing instructions, when the instructions are executed by the at least one processor, causing the at least one processor to perform the vehicle control method based on automatic driving as described above.

[0037] The application also provides a machine-readable storage medium storing executable instructions, when the instructions are executed, causing the machine to perform the vehicle control method based on automatic driving as described above.

[0038] Compared with the prior art, the vehicle control method based on automatic driving according to the application can realize forced lane changing of the target vehicle by determining the longitudinal safe lane-changing acceleration of the target vehicle at the current step length when the target vehicle is located at a non-safe lane-changing region, and can guarantee the safety of lane changing.

[0039] In another aspect, the longitudinal safety acceleration corresponding to the current step is determined based on the remaining time of the target lane-changing time at each current step, i.e., the optimal solution of the current step longitudinal safety lane-changing acceleration is solved at each step, which improves the lane-changing efficiency while further ensuring the safety of lane-changing.

[0040] In another aspect, the longitudinal set longitudinal acceleration of the target vehicle can be selected from the preset longitudinal acceleration strategy interval in the order of absolute value from small to large, so that the finally determined longitudinal safety lane-changing acceleration can maximize the driving comfort and driving experience of the user. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is an application scenario diagram of a vehicle control method based on automatic driving according to an embodiment of the present application;

[0042] Figure 2 is a scenario diagram before lane-changing of a target vehicle in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0043] Figure 3 is a flowchart of a vehicle control method based on automatic driving according to an embodiment of the present application;

[0044] Figure 4 is a scenario diagram of lane-changing of a target vehicle in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0045] Figure 5 is a phase plane diagram of a collision reference relationship when the acceleration of a target vehicle is assumed to be 0 in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0046] Figure 6 is an acceleration change diagram when a target vehicle lane changes in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0047] Figure 7 is a phase plane diagram of a collision reference relationship when the lane-changing adjustment time of a target vehicle is assumed to be 0 in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0048] Figure 8 is a phase plane diagram of a collision reference relationship and a state transition curve when a target vehicle lane changes at different accelerations in a vehicle control method based on automatic driving according to an embodiment of the present application;

[0049] Figure 9 is a module diagram of a vehicle control device based on automatic driving according to an embodiment of the present application;

[0050] Figure 10is a hardware structure diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] The present application will be described in detail below with reference to the embodiments shown in the drawings. However, the embodiments are not intended to limit the present application, and the structural, methodological, or functional changes made by those skilled in the art based on the embodiments are included in the scope of the present application.

[0052] The terms "first", "second", "third", "fourth" and the like used in the description and the claims of the present application and the above-described drawings, if any, are used to distinguish similar objects, and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present application described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "comprising" and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are clearly recited, but can include other steps or elements that are not expressly listed or inherent to such process, method, product, or apparatus.

[0053] Before introducing the embodiments of the present application, the basic technologies and some technical terms related to the embodiments of the present application are schematically explained:

[0054] Autonomous driving: refers to a function that can guide and decide vehicle driving tasks without the need for a test driver to perform physical driving operations, and replace the test driver to operate the vehicle to complete safe driving. Autonomous driving technology usually includes high-precision map, environment perception, behavior decision, path planning, motion control, etc.

[0055] Autonomous driving system: a system that realizes different levels of autonomous driving functions of a vehicle, such as an auxiliary driving system (L2), a high-speed autonomous driving system requiring human supervision (L3), and a high / fully autonomous driving system (L4 / L5).

[0056] Intelligent traffic system (ITS), also known as intelligent transportation system (Intelligent Transportation System), is a comprehensive transportation system that effectively integrates advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, and artificial intelligence) in transportation, service control, and vehicle manufacturing, and strengthens the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy.

[0057] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS), referred to as vehicle infrastructure cooperative systems, is a development direction of intelligent transportation systems. The vehicle infrastructure cooperative system is to implement dynamic real-time information interaction of vehicle and vehicle, vehicle and road in all directions by using advanced wireless communication and new generation Internet technologies, and to carry out vehicle active safety control and road cooperative management on the basis of full-time and space dynamic traffic information collection and fusion, fully realize effective cooperation of man, vehicle and road, ensure traffic safety, improve traffic efficiency, so as to form a safe, efficient and environmentally friendly road traffic system.

[0058] The vehicle control method based on automatic driving provided by the embodiments of the application can be applied to an automatic driving car, including L2, L3, L4 and above level automatic driving system, and is mainly applied to a vehicle lane changing scene.

[0059] In the design of vehicle lane changing strategy, if the lane changing operation is to be performed, the distance between the target vehicle driven by the user and the front vehicle must be greater than the safe lane changing distance. The safe lane changing distance refers to the distance between the target vehicle and the front vehicle that can just ensure no collision and rear-end in the normal driving process of the target vehicle if the front vehicle suddenly brakes and decelerates.

[0060] Referring to Figure 1 Take an application scene of the vehicle control method based on automatic driving provided by the embodiments of the application as an example. The user can manually drive the vehicle, or can drive the vehicle by means of the intelligent driving system of the vehicle. In the process of manual driving or automatic driving, the terminal can collect environmental information based on sensors, laser radars, cameras, millimeter wave radars, navigation systems, positioning systems, high-precision maps, etc., and provide some decision basis information for vehicle control. The terminal can be the vehicle driven by the user, or the intelligent vehicle-mounted device / module on the vehicle, or the desktop computer, notebook computer, smart phone and tablet computer configured on the vehicle during driving the vehicle by the user, and the portable wearable device carried by the user, etc.

[0061] Referring to Figure 2 Introduce the scene of lane changing based on the vehicle control method of automatic driving of the application. The target vehicle M driven by the user travels in the current lane A, and the vehicle L0 and the vehicle F0 are located in front of and behind the target vehicle M on the lane A, and the vehicle L1 and the vehicle F1 travel on the lane B adjacent to the lane A.

[0062] Based on Figure 2The shown scenario establishes a lane coordinate system, sets the origin of the lane coordinate system at the tangent of the left outer edge line of the target vehicle M, the x-axis of the lane coordinate system points to the driving direction of the target vehicle M, and the y-axis points from lane A to lane B. In this way, taking the target vehicle M as an example, the movement of the target vehicle along the x-axis can be referred to as longitudinal movement, and the movement along the y-axis can be referred to as lateral movement.

[0063] Taking the target vehicle M needing to change lanes from lane A to lane B as an example, since the target vehicle M is located in front of the vehicle F0, the braking or acceleration of the target vehicle M to a certain extent can cause the vehicle F0 to perform longitudinal control. Here, it is assumed that the target vehicle M and the vehicle F0 will not collide, that is, the influence of the vehicle F0 on the lane change of the target vehicle M is not considered.

[0064] In Figure 1 Under some conditions of the shown scenario, for example, the vehicle speed of the vehicle L0 located in front of the target vehicle M is less than the target vehicle M, and at the same time, the vehicle speed of the vehicle L0 is lower than a preset vehicle speed (for example, 80 km / h), the target vehicle M can run the vehicle control method based on automatic driving provided by the present application to change lanes to lane B. Of course, the lane change scenarios that can be intervened by the vehicle control method of the present application are not limited to the above combined with the accompanying drawings. Figure 2 The above description of the lane change scenario should not be regarded as a limitation of the embodiments of the present application.

[0065] When the target vehicle M expects to change lanes from lane A to lane B (i.e., the target change direction lane), in the lane coordinate system, the longitudinal coordinate of the vehicle L1 on lane B is greater than the target vehicle M. In the embodiments of the present application, it is assumed that the vehicle L1 is considered as the obstacle vehicle on lane B with the smallest longitudinal distance from the target vehicle M, and the vehicle L1 at this time is referred to as the front vehicle of the target vehicle M. In this case, when the target vehicle M changes lanes, at least the collision with the vehicle L1 needs to be considered.

[0066] When the target vehicle M changes lanes from lane A to lane B, due to the speed difference that may exist between the target vehicle and the vehicle L1, a longitudinal collision may occur within the lane change time. The present application proposes that the target vehicle and the front vehicle can always be prevented from colliding within the lane change time by controlling the acceleration of the target vehicle during lane change.

[0067] It should be noted that the "acceleration" mentioned in the embodiments of the present application is represented as a directional quantity. For example, if the target vehicle M expects to increase the vehicle speed during lane change, a "positive acceleration" pointing in the same direction as the x-axis of the lane coordinate system can be applied by controlling the vehicle chassis execution layer, and vice versa. For example, corresponding to the target vehicle M expecting to reduce the vehicle speed during lane change, a "negative acceleration" pointing in the opposite direction of the x-axis of the lane coordinate system can be applied by controlling the vehicle chassis execution layer. Figure 2In the illustrated scenario, the target vehicle M can accelerate to the front of the vehicle L1 on the lane B by positive acceleration, or decelerate to the rear of the vehicle L1 on the lane B by negative acceleration, so that different lane changing strategies can be implemented based on the vehicle control method proposed in the following embodiments.

[0068] In addition, the "longitudinal direction" and "transverse direction" mentioned in the embodiments of the present application can be referred to the lane extension direction, for example, the lane extension direction can be referred to as the "longitudinal direction" herein, and the width direction of the lane can be referred to as the "transverse direction" herein.

[0069] Referring to Figure 3 , an embodiment of the vehicle control method based on automatic driving is introduced. In this embodiment, the method comprises:

[0070] S11, obtaining scenario information of a target vehicle.

[0071] In the automatic driving of the vehicle, the scenario information can include positioning information, map information, environment information, terminal point information, and vehicle related information, etc. Among them, the vehicle related information can be the related information of the target vehicle and the vehicles adjacent to it, that is, the vehicle related information can include the speed and acceleration of the target vehicle, the speed and acceleration of the vehicles adjacent to the target vehicle, and the vehicle related information can also include the positional relationship between the target vehicle and the vehicles adjacent to it.

[0072] Different types of scenario information can be obtained by one or more vehicle-mounted devices. For example, the coordinates of the target vehicle in the lane coordinate system can be obtained by a global navigation satellite system (GNSS); the relative speed and relative distance between the target vehicle and the preceding vehicle can be obtained by an ultrasonic radar, a camera, or an ultrasonic radar combined with a camera.

[0073] S12, determining whether the target vehicle is located at a lane changing detection point based on the scenario information.

[0074] The lane changing detection point can be specifically set according to different lane changing strategies. Still taking Figure 2 the illustrated scenario as an example, in the lane coordinate system, if the target vehicle M and the preceding vehicle L1 have a gap in the transverse direction, it means that the target vehicle M and the preceding vehicle L1 are currently not at risk of collision. In combination with Figure 4 , further, if the target vehicle M expects to change lanes from lane A to lane B, at a moment, the gap between the target vehicle M and the preceding vehicle L1 in the transverse direction disappears, and the two vehicles are at risk of collision at this moment. Therefore, the relative positional relationship between the two vehicles at this moment can be referred to for determination of the lane changing detection point.

[0075] In this embodiment, whether the lateral coordinate difference between the collision reference point of the target vehicle and the collision reference line of the front vehicle in the lane coordinate system is less than a set threshold value can be determined through the coordinates of the target vehicle and the front vehicle in the lane coordinate system in the scene information; if yes, it is determined that the target vehicle is located at the lane change detection point.

[0076] The collision reference point of the target vehicle and the collision reference line of the front vehicle can be determined based on various ways. For example, when the target vehicle M changes lanes from lane A to lane B, in the lane change direction, the left front corner point P of the target vehicle M first cuts into lane B, that is, the lateral distance between point P and the front vehicle L1 before lane changing is the smallest, and then point P can be determined as the collision reference point of the target vehicle. Correspondingly, there is also a point on the front vehicle L1 that has the smallest lateral distance with the collision reference point P of the target vehicle M, and the x-axis in the lane coordinate system passing through the point can be taken as the collision reference line of the front vehicle.

[0077] It can be seen that the setting of the lane change detection point can take the possibility of whether the target vehicle is likely to collide with the front vehicle when changing lanes as a reference. Of course, the reference for setting the lane change detection point is not limited to this, for example, from the perspective of user style, a conservative or cautious user can expect the two vehicles to have a larger lateral distance when making a lane change detection point judgment, while an aggressive or adventurous user can expect the target vehicle to make a lane change detection point judgment at a relatively later time than the above time node.

[0078] S13, based on the longitudinal speed difference and longitudinal distance between the target vehicle and the front vehicle at the current step length, and the target lane changing time of the target vehicle, determine whether the target vehicle is located in a safe lane changing region.

[0079] In combination Figure 4 , it is set that the target vehicle M changes lanes, and the target vehicle is expected to change lanes to the rear of the front vehicle L1, and the vehicle control method of the embodiment of the application is explained. It should be understood that in some other lane changing strategies, the target vehicle can also be controlled to change lanes to the front of the front vehicle, and one or more formulas involved below are adaptively constructed.

[0080] It is set that the target vehicle reaches the lane change detection point at t c , the lane change adjustment time of the target vehicle after reaching the lane change detection point is t adj , and then it is known that from t c +t adj to the time point T when the lane changing process ends and the vehicle is stably driven, the longitudinal distance between the target vehicle and the front vehicle always needs to satisfy the following formula:

[0081]

[0082] Wherein, x M (t) is the longitudinal coordinate of the target vehicle in the lane coordinate system, xL (t) is the longitudinal coordinate of the front vehicle in the lane coordinate system, l L is the length of the front vehicle, w M is the width of the target vehicle, and θ(t) is the heading angle of the target vehicle, i.e., the angle between the heading direction of the target vehicle and the x-axis of the vehicle body coordinate system. In this embodiment, the coordinates of the vehicle in the lane coordinate system are calculated based on the left front corner point of the vehicle for the convenience of calculation.

[0083] The heading angle of the vehicle can be regarded as the ratio of the lateral velocity of the rear axle of the vehicle to the longitudinal velocity of the rear axle of the vehicle, and can be calculated as follows:

[0084]

[0085] wherein v lat (t) is the lateral velocity of the rear axle of the vehicle, v M (t) is the longitudinal velocity of the rear axle of the vehicle.

[0086] The formula (1) can be expanded as:

[0087]

[0088] Let Sr(t) be the longitudinal distance between the target vehicle and the front vehicle, and the following can be obtained:

[0089]

[0090] wherein x L (t) and x M (t) are quantities that change with time t, and therefore can be integrated to obtain the velocity and acceleration, and the following can be obtained:

[0091]

[0092] wherein a L (τ) is the acceleration of the front vehicle, a M (τ) is the acceleration of the target vehicle, v L (0) is the velocity of the front vehicle at t = 0, and v M (0) is the velocity of the target vehicle at t = 0.

[0093] The target vehicle determines whether it is located in the safe lane-changing region at the lane-changing detection point, which is equivalent to making a lane-changing decision at the lane-changing detection point. The above process is a state that rolls over with the time step of the state machine, and therefore, the acceleration of the front vehicle can be regarded as 0, i.e., the velocity is constant within a certain time domain. In this way, the lane-changing decision based on the vehicle control method provided in the present application is still effective even when the front vehicle has a velocity change.

[0094] Specifically, the collision reference relationship can be determined based on the target lane-changing time of the target vehicle and the time when the target vehicle reaches the lane-changing detection point, and then whether the target vehicle is located in the safe lane-changing region can be determined based on the longitudinal speed difference and the longitudinal distance between the target vehicle and the front vehicle at the current step and the reference relationship.

[0095] The collision reference relationship in the present application represents the correlation between the longitudinal speed difference between the target vehicle and the front vehicle and the initial longitudinal distance. In the present embodiment, in order to illustrate the collision reference relationship, further description will be made in combination with a phase plane. First, the overall safe lane-changing strategy will be introduced by assuming that the longitudinal acceleration of the target vehicle is 0, and then the case where the target vehicle has longitudinal acceleration will be analyzed.

[0096] ① Assuming that the longitudinal acceleration of the target vehicle is 0

[0097] When the longitudinal acceleration of the target vehicle and the front vehicle is 0, formula (5) can be expressed as:

[0098]

[0099] In order to ensure that no collision occurs before the end of lane changing (target lane-changing time T), the minimum longitudinal safety distance between the target vehicle and the front vehicle can be obtained as:

[0100]

[0101] Wherein, according to the target lane-changing time (for example, a suitable value in 5-7 seconds), the sum of the time when the target vehicle reaches the lane-changing detection point and the lane-changing adjustment time t C +t adj , the phase plane diagram shown in formula (7) can be established. Figure 5

[0102] Figure 5 In the phase plane diagram, the horizontal coordinate is the longitudinal speed difference between the target vehicle and the front vehicle, and the vertical coordinate is the initial longitudinal distance between the target vehicle and the front vehicle. At this time, the function of the minimum safety distance divides the phase plane into two parts, the left upper region of the phase plane is the safe lane-changing region, and the right lower region is the unsafe lane-changing region.

[0103] As can be seen, Figure 5 ​In the phase plane diagram shown, the greater the speed of the target vehicle relative to the vehicle ahead, the greater the initial longitudinal vehicle distance required to ensure safe lane change; conversely, when the speed of the target vehicle is less than that of the vehicle ahead, a relatively smaller initial longitudinal vehicle distance may be sufficient to ensure safe lane change. At this time, the reference line of the minimum safety distance MSS(L,M) in the phase plane diagram can be regarded as the "collision reference relationship". Based on the current speed difference and the initial longitudinal vehicle distance difference between the target vehicle and the vehicle ahead, the position can be determined in the phase plane diagram, thereby determining whether the target vehicle is in the safe lane change area.

[0104] ② Consider the longitudinal acceleration of the target vehicle

[0105] Ref. Figure 6 , which represents the change of the longitudinal acceleration of the target vehicle with time during lane change. Among them, t adj is the lane change adjustment time after the target vehicle reaches the lane change detection point, and t long is the target lane change time of the target vehicle.

[0106] First, assume that t adj is 0, that is, the initial phase plane coordinates are not pre-controlled.

[0107] During the lane change process of the target vehicle, the speed at the end of its lane change is the speed of the vehicle ahead. Therefore, the acceleration of the target vehicle can be expressed as:

[0108]

[0109] Therefore, after substituting the acceleration of the target vehicle in formula (8) into formula (5) and performing two integrations, formula (5) can be expressed as:

[0110] [[ID=二十九]]

[0111] On this basis, in order to ensure that no collision occurs before the end of lane change (target lane change time t long ), substituting the target lane change time into t in formula (9), the minimum safety distance between the target vehicle and the vehicle ahead can be sorted out as:

[0112]

[0113] Similarly, according to the target lane change time (for example, a suitable value within 5 to 7 seconds), the time t C (t adj is 0) when the target vehicle reaches the lane change detection point can be inferred, and thus a phase plane diagram as shown in Figure 7 can be established based on formula (10). It can be seen that when the target vehicle has acceleration, the slope of the dividing line representing the collision reference relationship changes.

[0114] Based on the above embodiment, since the speed difference and the longitudinal distance difference between the target vehicle and the front vehicle in the current step are known, the position of the target vehicle in the phase plane diagram can be determined, and whether the target vehicle is in the safe lane-changing region can be determined.

[0115] S14, based on the target lane-changing time, determining the longitudinal safe lane-changing acceleration of the target vehicle in the current step to control the target vehicle to force lane-changing.

[0116] In the above embodiment, it is assumed that t adj is 0. t adj 0 represents that the target vehicle does not need to adjust lane-changing after reaching the lane-changing detection point, that is, the target vehicle is in the safe lane-changing region in the current step.

[0117] If the target vehicle is not in the safe lane-changing region in the current step, that is, t adj is not 0, the chassis execution layer of the target vehicle needs to be controlled to control the vehicle with the longitudinal safe lane-changing acceleration, so that the target vehicle does not collide with the front vehicle during forced lane-changing.

[0118] The above target is achieved by relying on the target vehicle to complete lane-changing within the target lane-changing time. Therefore, the target lane-changing time can be used as a constraint condition, and the speed of the front vehicle at the end of lane-changing is controlled to be consistent with the speed of the target vehicle at the end of lane-changing, so that the target vehicle does not collide with the front vehicle.

[0119] Based on the above idea, in the present embodiment, the lane-changing adjustment time of the target vehicle can be calculated first, which is the time required for the target vehicle to adjust to the longitudinal speed of the front vehicle with a set longitudinal acceleration; then, based on the lane-changing adjustment time and the target lane-changing time, it is determined whether the set longitudinal acceleration is the longitudinal safe lane-changing acceleration.

[0120] If the lane-changing adjustment time is greater than the target lane-changing time, it means that the current set longitudinal acceleration cannot ensure that the target vehicle safely completes lane-changing within the target lane-changing time; on the contrary, if the lane-changing adjustment time is less than or equal to the target lane-changing time, it means that the current set longitudinal acceleration can make the target vehicle safely complete lane-changing within the target lane-changing time, that is, the set longitudinal acceleration at this time can be determined as the longitudinal safe lane-changing acceleration of the current step.

[0121] Considering the comfort and safety of the user, the set longitudinal acceleration that the target vehicle can perform at this time can be limited in a preset longitudinal acceleration strategy interval, for example, [-0.1 to -2 m / s 2 ]. In the preset longitudinal acceleration strategy interval, the set longitudinal acceleration is selected in the order of absolute value from small to large to calculate the lane-changing adjustment time, and then it is determined whether the selected set longitudinal acceleration is the longitudinal safe lane-changing acceleration.

[0122] Correspondingly, if the goal is for the target vehicle to change lanes to the front of the vehicle in front, then the longitudinal acceleration can be selected one by one from a positive preset acceleration strategy range to determine whether the safe lane-changing conditions are met. This will not be elaborated further here.

[0123] To better illustrate the state of the target vehicle in the phase plane diagram when changing lanes with different set longitudinal accelerations, the following explanation will assume that the target vehicle's current step length is not within the safe lane-changing zone. In the specific calculation, a set of state equations can be determined first, as follows:

[0124]

[0125] As can be seen, x1 and x2 are the vertical and horizontal coordinates of the phase plane diagram shown above. Therefore, the relationship between x1 and x2 can be derived as follows:

[0126]

[0127] Among them, a adj This refers to setting the longitudinal acceleration.

[0128] Coordination Figure 8 By using the initial position of the target vehicle in the phase plane coordinates, combined with the state transition curves and formula (12) for different set accelerations, when the longitudinal speed difference between the target vehicle and the preceding vehicle is adjusted to 0, if the acceleration of the target vehicle is controlled to be 0, the value of x1 will immediately approach infinity, thus allowing the vehicle to cross from the unsafe lane-changing area to the safe lane-changing area. This proves that in this embodiment, it is only necessary to control the lane-changing adjustment time of the target vehicle to meet the requirements of the target lane-changing time, and to keep the longitudinal acceleration of the target vehicle at 0 when the speeds of the target vehicle and the preceding vehicle are the same, thus achieving a safe lane-changing for the target vehicle.

[0129] like Figure 8 As shown, if the longitudinal acceleration is set to -1, the lane change adjustment time required for the state transition curve to cross the horizontal axis 0 meets the target lane change time requirement. At the same time, the longitudinal acceleration of the target vehicle is controlled to be 0, which means that the target vehicle can achieve safe lane change with a smaller absolute value of longitudinal acceleration.

[0130] After determining the longitudinal safe lane-changing acceleration of the target vehicle in the current step, the heading angle of the target vehicle in the current step can be determined by combining the lateral safe lane-changing acceleration in the current step. The lane-changing process of the target vehicle can be regarded as a sinusoidal trajectory lane-changing with continuous curvature, so the lateral and longitudinal motions of the target vehicle can be decoupled. Based on the determined heading angle, the lateral safe lane-changing acceleration and the longitudinal safe lane-changing acceleration in the current step, the position of the target vehicle in the lane coordinate system during lane-changing can also be derived, and the acceleration instruction in the heading angle direction is executed by the chassis execution layer of the vehicle to complete the forced lane-changing.

[0131] The lateral safe lane-changing acceleration in the current step can be determined based on the lane-changing adjustment time, the target lane-changing time and the lateral lane-changing distance, and is expressed as:

[0132]

[0133] wherein H is the lane-changing distance (which can be approximately equal to the width of a single lane), t lat is the target lane-changing time, t adj is the lane-changing adjustment time.

[0134] After controlling the target vehicle to forcibly change lanes, when the next step arrives, it is necessary to repeatedly determine the longitudinal safe acceleration of the target vehicle in the corresponding step. Since the target lane-changing time is certain, in each step after forced lane-changing, the longitudinal safe acceleration of the target vehicle in the corresponding step needs to be determined based on the remaining time of the target lane-changing time (into formula (9)), which will not be described here.

[0135] Referring to Figure 9 An embodiment of a vehicle control device based on automatic driving according to the present application is introduced. In this embodiment, the vehicle control device based on automatic driving includes an acquisition module 21, a determination module 22, a determination module 23 and a control module 24.

[0136] The acquisition module 21 is configured to acquire scene information of a target vehicle; the determination module 22 is configured to determine whether the target vehicle is located at a lane-changing detection point based on the scene information; if yes, the determination module 23 is configured to determine whether the target vehicle is located in a safe lane-changing region based on the longitudinal speed difference and the longitudinal distance between the target vehicle and a front vehicle in the current step, and the target lane-changing time of the target vehicle when the target vehicle is located at the lane-changing detection point, wherein the front vehicle is a front vehicle in the target lane of the target vehicle; and the control module 24 is configured to determine the longitudinal safe lane-changing acceleration of the target vehicle in the current step in the lane coordinate system based on the target lane-changing time when the target vehicle is not located in the safe lane-changing region, so as to control the target vehicle to forcibly change lanes.

[0137] In an embodiment, the control module 24 is specifically configured to calculate a lane-changing adjustment time of the target vehicle, wherein the lane-changing adjustment time is a time required for the target vehicle to adjust to a set longitudinal acceleration to be equal to a longitudinal speed of the front vehicle; and determine whether the set longitudinal acceleration is a longitudinal safe lane-changing acceleration based on the lane-changing adjustment time and a target lane-changing time.

[0138] In an embodiment, the control module 24 is specifically configured to select the set longitudinal acceleration in a preset longitudinal acceleration strategy interval in an order of absolute values from small to large to calculate the lane-changing adjustment time.

[0139] In an embodiment, the control module 24 is specifically configured to determine that the set longitudinal acceleration is the longitudinal safe lane-changing acceleration when the lane-changing adjustment time is less than or equal to the target lane-changing time.

[0140] In an embodiment, the control module 24 is specifically configured to determine a lateral safe lane-changing acceleration of a current step of the target vehicle based on the lane-changing adjustment time, the target lane-changing time and a lateral lane-changing distance; and determine a heading angle of the current step of the target vehicle based on the lateral safe lane-changing acceleration and the longitudinal safe lane-changing acceleration of the current step of the target vehicle.

[0141] In an embodiment, the control module 24 is further configured to determine a longitudinal safe acceleration of the target vehicle corresponding to each current step based on a remaining time of the target lane-changing time for each current step.

[0142] In an embodiment, the determination module 23 is specifically configured to determine a collision reference relationship based on a target lane-changing time of the target vehicle and a time at which the target vehicle reaches the lane-changing detection point, wherein the collision reference relationship represents an association relationship between a longitudinal speed difference between the target vehicle and the front vehicle and an initial longitudinal vehicle distance; and determine whether the target vehicle is located in a safe lane-changing area based on the longitudinal speed difference and the longitudinal vehicle distance between the target vehicle and the front vehicle for a current step and the reference relationship.

[0143] In an embodiment, the scene information includes coordinates of the target vehicle and the front vehicle in a lane coordinate system; and the judgment module 22 is specifically configured to judge whether a lateral coordinate difference between a collision reference point of the target vehicle and a collision reference line of the front vehicle in the lane coordinate system is less than a set predetermined value; and determine that the target vehicle is located in the lane-changing detection point if yes.

[0144] As described above with reference to Figure 1 to Figure 8 The vehicle control method based on automatic driving according to the embodiments of the present specification is described. The details mentioned in the above description of the method embodiments are also applicable to the vehicle control device based on automatic driving of the embodiments of the present specification. The above vehicle control device based on automatic driving can be implemented by hardware, or by software or a combination of hardware and software.

[0145] Figure 10 A hardware structure diagram of an electronic device according to an embodiment of the present specification is shown. As shown, the electronic device 30 can include at least one processor 31, a memory 32 (e.g., a non-volatile memory), a memory 33, and a communication interface 34, and the at least one processor 31, the memory 32, the memory 33, and the communication interface 34 are connected together via an internal bus 35. The at least one processor 31 executes at least one computer-readable instruction stored or encoded in the memory 32. Figure 10

[0146] It should be understood that the computer-executable instructions stored in the memory 32, when executed, cause the at least one processor 31 to perform various operations and functions described above in connection with the various embodiments of the present specification. Figure 1 to Figure 8

[0147] In an embodiment of the present specification, the electronic device 30 can include, but is not limited to, a personal computer, a server computer, a workstation, a desktop computer, a laptop computer, a notebook computer, a mobile electronic device, a smart phone, a tablet computer, a cellular phone, a personal digital assistant (PDA), a handheld device, a messaging device, a wearable electronic device, a consumer electronic device, and the like.

[0148] According to an embodiment, a program product such as a machine-readable medium is provided. The machine-readable medium can have instructions (i.e., the above-described elements implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with the various embodiments of the present specification. Specifically, a system or apparatus equipped with a readable storage medium on which a software program code implementing the functions of any of the above-described embodiments is stored, and a computer or processor of the system or apparatus can be provided to read out and execute the instructions stored in the readable storage medium. Figure 1 - Figure 7

[0149] In this case, the program code read from the readable medium itself can implement the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of the present specification.

[0150] Embodiments of the readable storage medium include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., a CD-ROM, a CD-R, a CD-RW, a DVD-ROM, a DVD-RAM, a DVD- RW, a DVD-RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer or the cloud over a communication network.

[0151] ​​​Those skilled in the art should understand that the various embodiments disclosed above can be variously changed and modified without departing from the essence of the application. Therefore, the scope of protection of the present specification should be defined by the appended claims rather than by the detailed description.

[0152] It should be noted that not all steps and units in the above processes and system structure diagrams are necessary, and some steps or units can be omitted according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in each of the above embodiments can be a physical structure or a logical structure, that is, some units can be implemented by the same physical client, or some units can be implemented by multiple physical clients, or can be implemented by some components in multiple independent devices together.

[0153] In each of the above embodiments, a hardware unit or module can be implemented mechanically or with electronic components. For example, a hardware unit, module or processor can include dedicated circuitry or logic, such as an application specific integrated circuit (ASIC) or field programmable gate array (FPGA), for implementing the relevant operations. The hardware unit or processor can also include programmable logic or circuitry, such as microprocessor or other programmable processor, which can be temporarily configured by software to perform the relevant operations. The specific implementation (mechanical or dedicated permanent circuitry, or temporarily reconfigured circuitry) can be determined based on cost and time considerations.

[0154] The specific embodiments described above with reference to the drawings represent just example implementations. The description is not intended to be exhaustive or to limit the embodiments to the precise form disclosed. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the term "exemplary" is meant to mean "serving as an example, instance, or illustration," and is not meant to mean "preferred" or "advantageous over other embodiments." The specific implementations described above can be implemented in software or hardware, or a combination thereof. The specific implementations described above can be implemented in one or more computer programs executing on one or more programmable computer systems (hardware) to produce a computer implemented process, such that the one or more programs which execute on the one or more computers are arranged to carry out the methods.

[0155] The above description of the disclosure has been presented to enable any person skilled in the art to implement or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the scope of protection of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle control method based on autonomous driving, characterized in that, The method includes: Obtain scene information for the target vehicle; Based on the scenario information, determine whether the target vehicle is located at a lane change detection point; if so, Based on the longitudinal speed difference and longitudinal distance between the target vehicle and the vehicle in front at the current step size, and the target lane-changing time of the target vehicle, it is determined whether the target vehicle is located in the safe lane-changing zone, wherein the vehicle in front is the vehicle ahead in the lane where the target vehicle is targeting to change direction; if not. Based on the target lane change time, the longitudinal safe lane change acceleration of the target vehicle at the current step size in the lane coordinate system is determined to control the target vehicle to change lanes. Specifically, this includes: calculating the lane change adjustment time of the target vehicle, wherein the lane change adjustment time is the time required for the target vehicle to adjust to the same longitudinal speed as the preceding vehicle with a set longitudinal acceleration; when the lane change adjustment time is less than or equal to the target lane change time, the set longitudinal acceleration is determined as the longitudinal safe lane change acceleration.

2. The vehicle control method based on autonomous driving according to claim 1, characterized in that, The method specifically includes: Within the preset longitudinal acceleration strategy range, the set longitudinal acceleration is selected in ascending order of absolute value to calculate the lane change adjustment time.

3. The vehicle control method based on autonomous driving according to claim 1, characterized in that, The method specifically includes: Based on the lane change adjustment time, the target lane change time, and the lateral lane change distance, determine the lateral safe lane change acceleration of the target vehicle at its current step length; Based on the lateral safe lane-changing acceleration and longitudinal safe lane-changing acceleration of the target vehicle at its current step length, the heading angle of the target vehicle at its current step length is determined.

4. The vehicle control method based on autonomous driving according to claim 1, characterized in that, After controlling the target vehicle to force a lane change, the method further includes: Based on the remaining time of the target lane change time, determine the longitudinal safety acceleration of the target vehicle for each current step.

5. The vehicle control method based on autonomous driving according to claim 1, characterized in that, Based on the longitudinal speed difference and longitudinal distance between the target vehicle and the vehicle in front at the current step length, and the target lane-changing time of the target vehicle, determine whether the target vehicle is within the safe lane-changing zone, specifically including: Based on the target lane change time of the target vehicle and its arrival time at the lane change detection point, a collision reference relationship is determined, wherein the collision reference relationship represents the correlation between the longitudinal speed difference between the target vehicle and the preceding vehicle and the initial longitudinal distance. Based on the longitudinal speed difference and longitudinal distance between the target vehicle and the preceding vehicle at the current step length, as well as the collision reference relationship, it is determined whether the target vehicle is located in the safe lane-changing area.

6. The vehicle control method based on autonomous driving according to claim 1, characterized in that, The scene information includes the coordinates of the target vehicle and the vehicle in front in the lane coordinate system; Determining whether the target vehicle is located at a lane change detection point based on the aforementioned scene information specifically includes: Determine whether the difference in lateral coordinates between the collision reference point of the target vehicle and the collision reference line of the preceding vehicle in the lane coordinate system is less than a set threshold. if, The target vehicle is located at the lane change detection point.

7. A vehicle control device based on autonomous driving, characterized in that, include: The acquisition module is used to acquire scene information of the target vehicle; The judgment module is used to determine whether the target vehicle is located at the lane change detection point based on the scene information; The determination module is used to determine whether the target vehicle is in the safe lane-changing area when the target vehicle is located at the lane-changing detection point, based on the longitudinal speed difference and longitudinal distance between the target vehicle and the preceding vehicle at the current step size, as well as the target lane-changing time of the target vehicle. The control module is used to determine the longitudinal safe lane-changing acceleration of the target vehicle based on the target lane-changing time when the target vehicle is not located in the safe lane-changing area, so as to control the target vehicle to change lanes forcibly. Specifically, it is used to calculate the lane-changing adjustment time of the target vehicle, wherein the lane-changing adjustment time is the time required for the target vehicle to adjust to the same longitudinal speed as the preceding vehicle with a set longitudinal acceleration; when the lane-changing adjustment time is less than or equal to the target lane-changing time, the set longitudinal acceleration is determined to be the longitudinal safe lane-changing acceleration.

8. An electronic device, comprising: At least one processor; as well as A memory that stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the vehicle control method based on autonomous driving as described in any one of claims 1 to 6.

9. A machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the vehicle control method based on autonomous driving as described in any one of claims 1 to 6.

Images