A vehicle driving method, device, computer equipment and storage medium

Abstract

The present disclosure provides a vehicle driving method, device, computer equipment and storage medium, wherein the method comprises: in the process of driving a first vehicle, determining a plurality of possible interaction modes between the first vehicle and a second vehicle; for each possible interaction mode, determining first predicted driving state information of the first vehicle in the possible interaction mode, and second predicted driving state information of the second vehicle in the possible interaction mode; based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode, determining a target interaction mode from the plurality of possible interaction modes; and based on the target interaction mode, controlling the first vehicle to drive.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of automatic driving, in particular to a vehicle driving method and device, computer equipment and storage medium. BACKGROUND

[0002] With the development of artificial intelligence technology, the application of automatic driving technology is also more and more extensive. In the driving process of an automatic driving vehicle, in the presence of other vehicles around, it may need to make decisions related to other vehicles, such as whether to change lanes to the lane where the other vehicle is currently located.

[0003] When an automatic driving vehicle makes specific interaction decisions, if the decisions are unreasonable, it may lead to traffic accidents, or overly conservative decisions will affect the driving efficiency of the vehicle. SUMMARY

[0004] The embodiments of the present disclosure at least provide a vehicle driving method, device, computer equipment and storage medium.

[0005] In a first aspect, the embodiments of the present disclosure provide a vehicle driving method, comprising:

[0006] In the driving process of a first vehicle, a plurality of possible interaction modes between the first vehicle and a second vehicle are determined;

[0007] For each possible interaction mode, first predicted driving state information of the first vehicle under the possible interaction mode and second predicted driving state information of the second vehicle under the possible interaction mode are determined;

[0008] Based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode, a target interaction mode is determined from the plurality of possible interaction modes;

[0009] The driving of the first vehicle is controlled based on the target interaction mode.

[0010] In this embodiment, by determining the predicted driving state information of the first vehicle and the second vehicle corresponding to a plurality of future time points under each possible interaction mode, the interaction behavior results of the first vehicle and the second vehicle under various possible interaction modes are simulated, so that a relatively reasonable target interaction mode can be selected from the plurality of possible interaction modes, that is, a reasonable behavior decision is made. Further, the driving of the first vehicle is controlled based on the target interaction mode, which can take into account the driving safety and driving efficiency of the vehicle.

[0011] In a possible implementation, the determination of the plurality of possible interaction modes between the first vehicle and the second vehicle comprises:

[0012] In a case where it is determined that the first vehicle has a lane-changing demand, determining the multiple possible interaction modes between the first vehicle and the second vehicle includes allowing the first vehicle to change lanes to the lane in which the second vehicle is located and prohibiting the first vehicle from changing lanes to the lane in which the second vehicle is located.

[0013] In this embodiment, based on the lane-changing demand of the first vehicle, the multiple possible interaction modes corresponding to the lane-changing demand can be accurately determined.

[0014] In a possible implementation, the first predicted driving state information includes first accelerations of the first vehicle in a lane direction at multiple future time points, and the second predicted driving state information includes second accelerations of the second vehicle in the lane direction at the multiple future time points.

[0015] The target interaction mode is determined from the multiple possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode.

[0016] For each possible interaction mode, a minimum acceleration is determined from the first accelerations at the multiple future time points indicated by the first predicted driving state information corresponding to the possible interaction mode and the second accelerations at the multiple future time points indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0017] The target interaction mode is determined from the multiple possible interaction modes based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold.

[0018] Here, in a process in which the vehicle has a braking behavior, the acceleration of the vehicle is a negative value, that is, the smaller the acceleration, the greater the deceleration, and the more urgent the braking behavior. Therefore, the acceleration of the vehicle in the lane direction can reflect whether the vehicle has an urgent braking behavior. When there is an urgent braking behavior, the difficulty of vehicle control increases, more uncontrollable factors of vehicle driving will be generated, and the driving safety will be affected. Therefore, by using the determined minimum accelerations of the first vehicle and the second vehicle in the multiple possible interaction modes, a reasonable interaction mode in which the vehicle has an urgent braking behavior can be screened, and the driving safety of the vehicle is improved.

[0019] In a possible implementation, the acceleration of the target vehicle is determined according to the following steps:

[0020] determining, for each of the plurality of future time points, a distance difference between the target vehicle and a third vehicle in a lane direction at a previous time point based on positions of the target vehicle and the third vehicle at the previous time point, and a speed difference between the target vehicle and the third vehicle at the previous time point based on speeds of the target vehicle and the third vehicle at the previous time point;

[0021] determining an acceleration of the target vehicle in the lane direction at the future time point based on the distance difference, the speed difference, and a preset acceleration of the target vehicle at the previous time point;

[0022] wherein, when the acceleration is a first acceleration, the target vehicle is the first vehicle, and the third vehicle includes a vehicle in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle in a lane where the second vehicle is located and in front of the target vehicle; and the third vehicle includes the second vehicle.

[0023] when the acceleration is a second acceleration, the target vehicle is the second vehicle, and the third vehicle includes a vehicle in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle in a lane where the first vehicle is located and in front of the target vehicle; and the third vehicle includes the first vehicle.

[0024] Here, through the position difference, the speed difference, and other information corresponding to the third vehicle at a time point in a possible interaction mode of the target vehicle (i.e. the first vehicle or the second vehicle), the acceleration of the target vehicle in the lane direction at the next time point in the interaction mode can be accurately determined. Based on the position difference, the speed difference, and other information corresponding to each time point, the acceleration of the vehicle in the lane direction at each time point in various possible interaction modes can be accurately determined.

[0025] In one possible implementation, the position of the target vehicle at the previous time point is determined according to the following steps:

[0026] determining the position of the target vehicle at the previous time point based on an acceleration of the target vehicle at the previous time point and a position of the target vehicle before the previous time point; wherein, when the acceleration is a first acceleration, the target vehicle is the first vehicle; and when the acceleration is a second acceleration, the target vehicle is the second vehicle.

[0027] Here, through the acceleration of the target vehicle at the previous time point, the position increment of the target vehicle in the lane direction can be determined, and based on the position of the target vehicle before the previous time point, the position of the target vehicle at the previous time point can be accurately determined.

[0028] In a possible implementation, the first predicted driving state information comprises a plurality of first steering angles of the first vehicle perpendicular to a lane direction at a plurality of future time points, and the second predicted driving state information comprises a plurality of second steering angles of the second vehicle perpendicular to the lane direction at the plurality of future time points.

[0029] The target interaction mode is determined from the plurality of possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode, comprising:

[0030] For each possible interaction mode, a maximum steering angle is determined from the first steering angles at the plurality of future time points indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second steering angles at the plurality of future time points indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0031] The target interaction mode is determined from the plurality of possible interaction modes based on the maximum steering angle corresponding to each possible interaction mode and a preset steering angle threshold.

[0032] Here, the greater the steering angle, the more rapid the turning behavior, and thus the maximum steering angle of the vehicle perpendicular to the lane direction can reflect whether the vehicle has a rapid turning behavior. When there is a rapid turning behavior, more uncontrollable factors will be generated for the vehicle, the vehicle control difficulty will increase, and the driving safety will be affected. Therefore, the maximum steering angles of the first vehicle and the second vehicle in each possible interaction mode are determined, which can filter out reasonable interaction modes that avoid rapid turning behaviors of the vehicles, and improve the driving safety of the vehicles.

[0033] In a possible implementation, the steering angle is determined according to the following steps:

[0034] For each future time point in the plurality of future time points, an observation distance of a target vehicle along a driving direction of the target vehicle at the future time point is determined based on a speed of the target vehicle at a previous time point; wherein the target vehicle is the first vehicle when the steering angle is the first steering angle, and the target vehicle is the second vehicle when the steering angle is the second steering angle.

[0035] An observation position point of the target vehicle along the driving direction of the target vehicle at the future time point is determined based on the observation distance, and an included angle between a straight line connecting the observation position point and a position of the target vehicle at the previous time point and a lane line of a lane where the target vehicle is located is determined.

[0036] determine a steering angle of the target vehicle at the future moment based on the observation distance, the included angle, and a wheelbase of the target vehicle.

[0037] Here, a reasonable observation distance can be determined according to the speed of the target vehicle at the previous moment, and an observation position point of the target vehicle in the driving direction of the target vehicle can be determined by using the determined observation distance and the position of the target vehicle at the previous moment, that is, the farthest position point that the target vehicle can reach in the driving direction of the target vehicle at the next moment at the current speed; further, the included angle of the target vehicle can be determined based on the observation position point and the position of the target vehicle at the previous moment, and finally, the accurate steering angle of the target vehicle can be determined according to the wheelbase, the included angle, and the observation distance.

[0038] In a possible implementation, the position of the target vehicle at the previous moment is determined according to the following steps:

[0039] determine the position of the target vehicle at the previous moment based on the steering angle of the target vehicle at the previous moment, the acceleration of the target vehicle at the previous moment, and the position of the target vehicle before the previous moment; wherein, when the steering angle is a first steering angle, the target vehicle is a first vehicle, and the acceleration is a first acceleration; when the steering angle is a second steering angle, the target vehicle is a second vehicle, and the acceleration is a second acceleration.

[0040] Here, the position increment of the target vehicle in the lane direction can be determined by the acceleration of the target vehicle at the previous moment, and the position increment of the target vehicle in the direction perpendicular to the lane direction can be determined by the steering angle of the target vehicle at the previous moment, and further, the accurate position of the target vehicle at the previous moment can be determined based on the increments in the two directions and the position of the target vehicle before the previous moment.

[0041] In a possible implementation, the control of the first vehicle driving based on the target interaction mode comprises:

[0042] determine a planned driving track of the first vehicle based on the target interaction mode;

[0043] control the first vehicle to drive according to the planned driving track.

[0044] In this implementation, a reasonable planned driving track that matches the target interaction mode can be planned according to the target interaction mode, and then the first vehicle can be controlled to drive according to the planned driving track, so as to ensure the safety of the first vehicle driving.

[0045] In a second aspect, the embodiments of the present disclosure further provide a vehicle driving device, comprising:

[0046] The first determining module is configured to determine a plurality of possible interaction modes between the first vehicle and the second vehicle during driving of the first vehicle.

[0047] The second determining module is configured to determine, for each possible interaction mode, first predicted driving state information of the first vehicle in the possible interaction mode and second predicted driving state information of the second vehicle in the possible interaction mode.

[0048] The third determining module is configured to determine, from the plurality of possible interaction modes, a target interaction mode based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode.

[0049] The control module is configured to control driving of the first vehicle based on the target interaction mode.

[0050] In a possible implementation, the first determining module is configured to, in a case where it is determined that the first vehicle has a lane-changing demand, determine the plurality of possible interaction modes between the first vehicle and the second vehicle, including allowing the first vehicle to change lanes to a lane where the second vehicle is located and prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located.

[0051] In a possible implementation, the first predicted driving state information includes first accelerations of the first vehicle in a lane direction at a plurality of future time points, and the second predicted driving state information includes second accelerations of the second vehicle in the lane direction at the plurality of future time points.

[0052] The third determining module is configured to, for each possible interaction mode, determine a minimum acceleration from the first accelerations at the plurality of future time points indicated by the first predicted driving state information corresponding to the possible interaction mode and the second accelerations at the plurality of future time points indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0053] The target interaction mode is determined from the plurality of possible interaction modes based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold.

[0054] In a possible implementation, the apparatus further includes:

[0055] The fourth determining module is configured to determine an acceleration of the target vehicle by performing the following steps:

[0056] determining, for each of the plurality of future time points, a distance difference between the target vehicle and a third vehicle in a lane direction at a previous time point based on positions of the target vehicle and the third vehicle at the previous time point, and a speed difference between the target vehicle and the third vehicle at the previous time point based on speeds of the target vehicle and the third vehicle at the previous time point;

[0057] determining an acceleration of the target vehicle in the lane direction at the future time point based on the distance difference, the speed difference, and a preset acceleration of the target vehicle at the previous time point;

[0058] wherein, when the acceleration is a first acceleration, the target vehicle is a first vehicle, and the third vehicle includes a vehicle in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle in a lane where the second vehicle is located and in front of the target vehicle; the third vehicle includes the second vehicle;

[0059] when the acceleration is a second acceleration, the target vehicle is the second vehicle, and the third vehicle includes a vehicle in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle in a lane where the first vehicle is located and in front of the target vehicle; the third vehicle includes the first vehicle.

[0060] In a possible implementation, the fourth determining module determines the position of the target vehicle at the previous time point according to the following steps:

[0061] determining the position of the target vehicle at the previous time point based on an acceleration of the target vehicle at the previous time point and a position of the target vehicle before the previous time point; wherein, when the acceleration is a first acceleration, the target vehicle is a first vehicle; when the acceleration is a second acceleration, the target vehicle is a second vehicle.

[0062] In a possible implementation, the first predicted driving state information includes a plurality of first steering angles of the first vehicle perpendicular to the lane direction at a plurality of future time points, and the second predicted driving state information includes a plurality of second steering angles of the second vehicle perpendicular to the lane direction at a plurality of future time points;

[0063] The third determining module is configured to determine, for each of the possible interaction modes, a maximum steering angle from a first steering angle at a plurality of future time points indicated by the first predicted driving state information corresponding to the possible interaction mode, and a second steering angle at a plurality of future time points indicated by the second predicted driving state information corresponding to the possible interaction mode;

[0064] determine the target interaction mode from the plurality of possible interaction modes based on a maximum steering angle corresponding to each of the possible interaction modes and a preset steering angle threshold.

[0065] In a possible implementation, the apparatus further includes:

[0066] a fifth determining module configured to determine the steering angle by the following steps:

[0067] For each of the plurality of future time points, determine an observation distance of the target vehicle along a driving direction of the target vehicle at the future time point based on a speed of the target vehicle at a previous time point; wherein the target vehicle is the first vehicle when the steering angle is the first steering angle, and the target vehicle is the second vehicle when the steering angle is the second steering angle;

[0068] determine an observation position point of the target vehicle along the driving direction of the target vehicle at the future time point based on the observation distance, and determine an included angle between a straight line connecting the observation position point and a position of the target vehicle at the previous time point and a lane line of a lane where the target vehicle is located;

[0069] determine a steering angle of the target vehicle perpendicular to the lane direction at the future time point based on the observation distance, the included angle, and a wheelbase of the target vehicle.

[0070] In a possible implementation, the fifth determining module is configured to determine the position of the target vehicle at the previous time point by the following steps:

[0071] determine the position of the target vehicle at the previous time point based on a steering angle of the target vehicle at the previous time point, an acceleration of the target vehicle at the previous time point, and a position of the target vehicle before the previous time point; wherein the target vehicle is the first vehicle and the acceleration is the first acceleration when the steering angle is the first steering angle, and the target vehicle is the second vehicle and the acceleration is the second acceleration when the steering angle is the second steering angle.

[0072] In a possible implementation, the control module is configured to determine a planned driving track of the first vehicle based on the target interaction mode.

[0073] control the first vehicle to drive according to the planned driving track.

[0074] In a third aspect, the optional implementation of the present disclosure further provides a computer device, a processor and a memory, the memory stores machine readable instructions executable by the processor, and the processor is configured to execute the machine readable instructions stored in the memory, and the machine readable instructions are executed by the processor to execute the steps of the first aspect or any possible implementation of the first aspect.

[0075] In a fourth aspect, the optional implementation of the present disclosure further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed to execute the steps of the first aspect or any possible implementation of the first aspect.

[0076] The effects of the vehicle driving device, the computer device and the computer readable storage medium are described in the description of the vehicle driving method, and will not be repeated here.

[0077] In order to make the above objectives, characteristics and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments, the drawings herein are incorporated into the description and form a part of the description, the drawings show the embodiments consistent with the present disclosure, and are used to illustrate the technical solutions of the present disclosure together with the description. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0079] Figure 1 A flow chart of a vehicle driving method provided by an embodiment of the present disclosure is shown;

[0080] Figure 2 A schematic diagram of a first vehicle having a lane changing demand provided by an embodiment of the present disclosure is shown;

[0081] Figure 3 A simulation trajectory schematic diagram of a first vehicle and a second vehicle in a possible interaction mode provided by an embodiment of the present disclosure is shown;

[0082] Figure 4 An implementation flow schematic diagram of a vehicle driving method provided by an embodiment of the present disclosure is shown;

[0083] Figure 5 A schematic diagram of a vehicle driving device provided by an embodiment of the present disclosure is shown;

[0084] Figure 6 A structural schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0085] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will be combined with the accompanying drawings for the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Apparently, the described embodiments are only part of the embodiments of the present disclosure and not all the embodiments. The components of the embodiments of the present disclosure generally described and shown herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0086] In addition, the terms “first”, “second”, and the like in the specification and claims of the embodiments of the present disclosure and the above-described accompanying drawings are used to distinguish similar objects and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0087] “Multiple or several” mentioned herein refers to two or more than two. “And / or” describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. The character “ / ” generally represents that the front and rear associated objects are in an “or” relationship.

[0088] It is found through research that in the case where an autonomous vehicle has the possibility of interacting with other vehicles, for example, an autonomous vehicle driving on lane A changes lane B, the autonomous vehicle usually only focuses on the behavior of other vehicles on lane B, predicts the trajectory of other vehicles, specifically, predicts the trajectory of other vehicles in a future period of time (5s-8s) and the speed corresponding to each position on the trajectory. Further, the autonomous vehicle will determine whether to change lanes and the lane change time and the like according to the predicted trajectory and speed of other vehicles. In actual driving, other vehicles can slightly decelerate or even not decelerate due to the lane change behavior of the autonomous vehicle, which can achieve the lane change of the autonomous vehicle. The way of only focusing on the behavior of other vehicles and ignoring the behavior of the autonomous vehicle leads to a conservative lane change behavior, which cannot achieve timely lane change and cannot achieve efficient and reasonable autonomous driving.

[0089] Based on the above research, this disclosure provides a vehicle driving method, apparatus, computer equipment, and storage medium. By determining the predicted driving state information of the first vehicle and the second vehicle at multiple future moments under each possible interaction mode, it simulates the interaction behavior of the first vehicle and the second vehicle under various possible interaction modes, fully considering the driving behavior of the first vehicle and the second vehicle. When the predicted driving state information can reflect the driving state of the first vehicle or the second vehicle (such as position, acceleration, steering angle, etc.), based on the analysis of the predicted driving state information corresponding to the first vehicle and the second vehicle respectively, the most reasonable target interaction mode can be selected from multiple possible interaction modes, that is, the most reasonable behavioral decision can be made. Furthermore, based on the target interaction mode, the first vehicle can be reasonably controlled, which can achieve reasonable and efficient interaction between the first vehicle and the second vehicle (that is, achieve efficient and reasonable driving) and improve the driving safety of the first vehicle.

[0090] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0091] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0092] To facilitate understanding of this embodiment, a vehicle driving method disclosed in this disclosure will first be described in detail. The vehicle driving method provided in this disclosure is generally executed by a computer device with certain computing capabilities. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a computing device, etc. In some possible implementations, the vehicle driving method can be implemented by a processor calling computer-readable instructions stored in memory.

[0093] The following describes the vehicle driving method provided in the embodiments of this disclosure, taking a computer device as the executing entity as an example.

[0094] like Figure 1 The flowchart shown is a method for driving a vehicle according to an embodiment of this disclosure, which may include the following steps:

[0095] S101: During the operation of the first vehicle, determine multiple possible interaction methods between the first vehicle and the second vehicle.

[0096] Here, the vehicle driving method provided by the embodiments of the present disclosure can be applied to an automatic driving scenario, the first vehicle can be an automatic driving vehicle, and the second vehicle can be a vehicle that can have an interaction behavior with the first vehicle during driving of the first vehicle. The second vehicle can be a vehicle driving in the same direction as the first vehicle or a vehicle driving in the opposite direction. For example, the second vehicle can be a vehicle located in the same lane as the first vehicle and located in front of or behind the first vehicle, a vehicle located in the adjacent lane of the first vehicle and located in front of or behind the first vehicle, a vehicle located in the same intersection as the first vehicle, and the like. The intersection can be, for example, a cross intersection, a T-shaped intersection, a sharp turn intersection, and the like.

[0097] During driving of the first vehicle, the second vehicle that can have an interaction behavior with the first vehicle can include one or more, which is not limited here.

[0098] The specific possible interaction mode can be determined according to the actual driving requirement of the first vehicle, and the actual driving requirement can be determined by different interaction scenarios. That is, in different interaction scenarios, the plurality of possible interaction modes corresponding to the first vehicle and the second vehicle can be different. For example, in a lane changing scenario, the plurality of possible interaction modes corresponding to the first vehicle and the second vehicle can be that the first vehicle is allowed to change lanes, the first vehicle is not allowed to change lanes, the second vehicle is allowed to change lanes, and the second vehicle is not allowed to change lanes. In a scenario of intersection merging, the plurality of possible interaction modes corresponding to the first vehicle and the second vehicle can be that the first vehicle is allowed to turn first, the first vehicle waits for the second vehicle to turn before turning, and the first vehicle is not allowed to turn, and the like. The embodiments of the present disclosure do not limit the specific interaction scenario and the specific interaction mode. In the driving process of the automatic driving vehicle, the interaction scenario and the interaction mode that can occur should fall within the protection scope of the present disclosure.

[0099] During driving of the first vehicle, there can be a plurality of second vehicles that have an interaction behavior with the first vehicle. In specific implementation, the plurality of possible interaction behaviors between the first vehicle and each second vehicle can be determined according to the driving requirement of the first vehicle and the position, driving direction and the like of each second vehicle. In addition, when determining the plurality of possible interaction behaviors between the first vehicle and a second vehicle, other vehicles in addition to the second vehicle and the actual road situation can also be considered.

[0100] S102: For each possible interaction mode, determine first predicted driving state information of the first vehicle under the possible interaction mode and second predicted driving state information of the second vehicle under the possible interaction mode.

[0101] Here, the predicted driving state information can reflect driving states of the vehicle at multiple future time points, specifically, the predicted driving state information can reflect one or more of accelerations, steering angles, positions of the vehicle at multiple future time points.

[0102] For each possible interaction mode, the behavior of the first vehicle and the second vehicle can be simulated in a closed loop based on the speed, position, and other information of the first vehicle, and the speed, position, and other information of the second vehicle, to determine the first predicted driving state information of the first vehicle in a future period of time, and the second predicted driving state information of the second vehicle in the future period of time.

[0103] Since the predicted driving state information is predicted under possible interaction modes, the first predicted driving state information corresponding to the first vehicle and the second predicted driving state information corresponding to the second vehicle will have mutual influences due to the possible interaction modes. In this way, for the first vehicle, the first predicted driving state information is determined not only considering the second vehicle, but also considering the first vehicle itself, which improves the rationality of the determined first predicted driving state information under each possible interaction mode, and is beneficial to subsequently determining an accurate target interaction mode.

[0104] In specific implementation, under each possible interaction mode, the first predicted driving state information corresponding to the first vehicle and the second predicted driving state information corresponding to the second vehicle predicted at each future time point can be used to respectively determine the first predicted driving state information corresponding to the first vehicle at the next time point, and the second predicted driving state information corresponding to the second vehicle at the next time point. Furthermore, based on the first predicted driving state information corresponding to the first vehicle at each future time point predicted under each possible interaction mode, the first predicted driving state information of the first vehicle under each possible interaction mode can be determined; based on the second predicted driving state information corresponding to the second vehicle at each future time point predicted under each possible interaction mode, the second predicted driving state information of the second vehicle under each possible interaction mode can be determined.

[0105] In the case where the second vehicle includes multiple second vehicles, the second predicted driving state information corresponding to each second vehicle can be determined respectively.

[0106] S103: Based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode, a target interaction mode is determined from the multiple possible interaction modes.

[0107] Here, the target interaction manner is an optimal interaction manner determined from the plurality of possible interaction manners, i.e., the interaction of the first vehicle and the second vehicle in accordance with the target interaction manner can not only achieve reasonable and efficient interaction of the first vehicle and the second vehicle (i.e., efficient and reasonable driving is achieved), but also improve the safety of the first vehicle driving. The first predicted driving state information corresponding to a possible interaction manner is the first predicted driving state information of the first vehicle under the possible interaction manner; the second predicted driving state information corresponding to a possible interaction manner is the second predicted driving state information of the second vehicle under the possible interaction manner.

[0108] In specific implementation, for each possible interaction manner, whether there is a predicted driving state information that does not meet the preset state requirement in the two predicted driving state information can be determined based on the first predicted driving state information and the second predicted driving state information corresponding to the possible interaction manner, and if yes, it is determined that the possible interaction manner is unreasonable; otherwise, it is determined that the possible interaction manner is reasonable.

[0109] For example, for a possible interaction manner, whether there is an acceleration less than the preset minimum acceleration in the accelerations corresponding to each future time in the two predicted driving state information can be determined, and if yes, it is determined that the possible interaction manner is unreasonable; otherwise, it is determined that the possible interaction manner is reasonable.

[0110] In this way, by analyzing the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction manner, the most reasonable target interaction manner can be selected from the plurality of possible interaction manners.

[0111] S104: Control the first vehicle to drive based on the target interaction manner.

[0112] In specific implementation, according to the determined target interaction manner, how the first vehicle can drive can be determined, for example, the first vehicle is allowed to change lanes, the first vehicle is prohibited to change lanes, and the like. Further, the first vehicle can be controlled to drive in accordance with the target interaction manner.

[0113] In this way, by determining the predicted driving state information corresponding to a plurality of future times of the first vehicle and the second vehicle under each possible interaction manner, the interaction behavior result of the first vehicle and the second vehicle under each possible interaction manner is simulated, so that a relatively reasonable target interaction manner can be selected from the plurality of possible interaction manners, i.e., a reasonable behavior decision is made; further, the driving of the first vehicle is controlled based on the target interaction manner, which can take into account the driving safety and driving efficiency of the vehicle.

[0114] In an embodiment, for S104, the following steps can be implemented:

[0115] S104-1: Determine the planned driving trajectory of the first vehicle based on the target interaction method.

[0116] In practice, the positions of the first vehicle at various future moments can be determined based on the first predicted driving state information corresponding to the target interaction method, and these future positions can be used as the planned driving trajectory to be modified. Then, trajectory optimization and other methods can be used to optimize the planned driving trajectory to be modified, resulting in the planned driving trajectory of the first vehicle.

[0117] S104-2: Control the first vehicle to travel according to the planned trajectory.

[0118] Here, after determining the planned driving trajectory, the first vehicle can be controlled to drive according to the planned driving trajectory.

[0119] In one embodiment, regarding the step of determining multiple possible interaction methods between the first vehicle and the second vehicle in S101, if it is determined that the first vehicle has a lane-changing requirement, the multiple possible interaction methods between the first vehicle and the second vehicle can be determined to include: allowing the first vehicle to change lanes to the lane where the second vehicle is located, and prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located.

[0120] like Figure 2 The diagram shown is a schematic representation of a first vehicle having a lane-changing requirement according to an embodiment of this disclosure. Figure 2 The diagram shows four lanes: lane 0, lane 1, lane 2, and lane 3. A first vehicle is in lane 1, and a second vehicle is in lane 2, positioned behind the first vehicle. When the first vehicle needs to change lanes, various possible interactions between the first and second vehicles could include: allowing the first vehicle to change lanes from lane 1 to lane 2, and prohibiting the first vehicle from changing lanes from lane 1 to lane 2. Furthermore, in... Figure 4 The image shows a possible interaction that allows the first vehicle to change lanes from lane 1 to lane 2.

[0121] In one embodiment, the first predicted driving state information includes the first acceleration of the first vehicle along the lane direction at multiple future moments, that is, predicting the acceleration change of the first vehicle over a future period of time; the second predicted driving state information includes the second acceleration of the second vehicle along the lane direction at multiple future moments, that is, predicting the acceleration change of the second vehicle over a future period of time. The length of the future period and the number of future moments can be set as needed and are not limited here.

[0122] Here, the first acceleration can reflect whether the first vehicle has braking (or even emergency braking) behavior at each time, and the second acceleration can reflect whether the second vehicle has braking (or even emergency braking) behavior at each time.

[0123] For S103, the following steps can be implemented:

[0124] S103-1: For each possible interaction mode, a minimum acceleration is determined from the first acceleration at the multiple future time instants indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second acceleration at the multiple future time instants indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0125] Here, one interaction mode corresponds to one minimum acceleration, and the minimum acceleration is the minimum one of the multiple first accelerations and the multiple second accelerations corresponding to various interaction modes. In specific implementation, the minimum acceleration corresponding to each interaction mode can be the first acceleration corresponding to the first vehicle, or the second acceleration corresponding to the second vehicle. Since the acceleration of the vehicle is negative when the vehicle has braking behavior, the smaller the acceleration, the more urgent the braking behavior. By screening the minimum acceleration, the most urgent braking behavior of the vehicle can be accurately determined.

[0126] In specific implementation, for each possible interaction mode, a minimum acceleration can be screened from the first acceleration at the multiple future time instants indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second acceleration at the multiple future time instants indicated by the second predicted driving state information corresponding to the possible interaction mode, and the screened minimum acceleration is taken as the minimum acceleration corresponding to the possible interaction mode.

[0127] In this way, according to the above S103-1, the minimum acceleration corresponding to each possible interaction mode can be determined.

[0128] S103-2: Based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold, a target interaction mode is determined from the multiple possible interaction modes.

[0129] Here, the preset acceleration threshold is set according to experience, and when the acceleration is less than the acceleration threshold, it can be indicated that the vehicle has emergency braking behavior, and when the acceleration is not less than the acceleration threshold, it can be indicated that the vehicle does not have emergency braking behavior.

[0130] In specific implementation, the minimum acceleration corresponding to each possible interaction mode can be compared with the preset acceleration threshold respectively, and the possible interaction mode corresponding to the minimum acceleration not less than the acceleration threshold is taken as the target interaction mode.

[0131] Alternatively, in the case that the possible interaction mode corresponding to the minimum acceleration not less than the acceleration threshold value includes multiple cases, the maximum turning angle in the multiple possible interaction modes can be determined according to the turning angle corresponding to each possible interaction mode, and the interaction mode with a maximum turning angle less than the preset turning angle threshold value can be determined as the target interaction mode. The turning angle and the turning angle threshold value will be described in detail below.

[0132] For example, in the case that the possible interaction mode includes allowing the first vehicle to change lanes to the lane where the second vehicle is located and prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located, the minimum acceleration can be determined according to the first predicted driving state information and the second predicted driving state information in the first possible interaction mode. Here, since the first vehicle performs the lane changing operation, the second vehicle needs to avoid the first vehicle, so the first vehicle should not have a braking behavior, and the second vehicle will have a braking behavior or even a sudden braking behavior. Therefore, the minimum acceleration determined here should be a second acceleration.

[0133] Then, it is determined whether the minimum acceleration is less than the acceleration threshold value. If yes, it indicates that the second vehicle has a sudden braking behavior, the vehicle control difficulty increases, and the uncontrollable factors of vehicle driving will increase, and the driving safety will be affected. Therefore, it can be determined that the possible interaction mode is an unreasonable interaction mode, and the possible interaction mode is determined as a non-target interaction mode.

[0134] Further, the possible interaction mode of prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located can be directly determined as the target interaction mode. The reason is that in this interaction mode, the first vehicle and the second vehicle will always drive on the corresponding lanes, and neither of them will have a sudden braking behavior. Therefore, the possible interaction mode can be directly determined as the target interaction mode.

[0135] In one possible implementation, after determining the multiple possible interaction modes between the first vehicle and the second vehicle, the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode can be determined, and then the minimum acceleration in the possible interaction mode can be determined according to the multiple first accelerations indicated by the first predicted driving state information and the second acceleration indicated by the second predicted driving state information. The minimum acceleration is compared with the acceleration threshold value. In the case that the minimum acceleration is not less than the acceleration threshold value, the possible interaction mode can be directly determined as the target interaction mode. Otherwise, the first predicted driving state information and the second predicted driving state information in the next possible interaction mode are determined, and the target interaction mode is determined until the target interaction mode is determined.

[0136] In this way, in the case where there are multiple possible interaction modes, by sequentially determining whether each possible interaction mode can be the target interaction mode, in the case where a certain possible interaction mode can be the target interaction mode, the determination of other possible interaction modes, respectively corresponding first predicted driving state information and second predicted driving state information, which have not been determined whether they can be the target interaction mode, can be stopped, thereby reducing the amount of computation.

[0137] In an embodiment, the acceleration of the vehicle can be determined according to the following steps:

[0138] For each of the plurality of future time points, a distance difference between the target vehicle and the third vehicle in the lane direction at the previous time point can be determined based on positions of the target vehicle and the third vehicle at the previous time point, and a speed difference between the target vehicle and the third vehicle at the previous time point can be determined based on speeds of the target vehicle and the third vehicle at the previous time point. Then, the acceleration of the target vehicle in the lane direction at the future time point can be determined based on the distance difference, the speed difference, and a preset acceleration of the target vehicle at the previous time point.

[0139] In the case where the acceleration to be determined is the first acceleration, the target vehicle can be the first vehicle, and the third vehicle can include a vehicle located in the lane of the target vehicle and in front of the target vehicle, and / or a vehicle located in the lane of the second vehicle and in front of the target vehicle; the third vehicle can include the second vehicle.

[0140] In the case where the acceleration to be determined is the second acceleration, the target vehicle can be the second vehicle, and the third vehicle can include a vehicle located in the lane of the target vehicle and in front of the target vehicle, and / or a vehicle located in the lane of the first vehicle and in front of the target vehicle; the third vehicle can include the first vehicle.

[0141] For example, in the case of determining the first acceleration, the target vehicle can be the first vehicle, and the third vehicle can include the second vehicle. The third vehicle can include a vehicle located in the lane of the first vehicle and in front of the first vehicle, and / or a vehicle located in the lane of the second vehicle and in front of the first vehicle; the third vehicle can include the second vehicle. Specifically, in the case of determining the first acceleration of the first vehicle at each future time according to a possible interaction mode, the position of the first vehicle at each future time can also be determined, and in the process of closed-loop simulation according to a possible interaction mode, the position of the third vehicle at a certain time can be in front of the position of the first vehicle, becoming the front vehicle of the first vehicle, at this time, the third vehicle is the second vehicle. Alternatively, the third vehicle can also be other vehicles on the lane that are not the second vehicle, for example, other vehicles can appear in front of the first vehicle during the lane changing process of the first vehicle, at this time, the third vehicle is the other vehicle.

[0142] In specific implementation, the first acceleration of the first vehicle can be determined according to the following steps: for each future time in the plurality of future times, the third vehicle located in front of the first vehicle at the previous time can be determined first, and the positions of the first vehicle and the third vehicle at the previous time can be determined, and then the distance difference value of the first vehicle at the previous time can be determined according to the positions of the first vehicle and the third vehicle. Here, the distance difference value can be the distance difference value of the first vehicle and the third vehicle in the lane direction.

[0143] And the speed of the first vehicle and the third vehicle at the previous time can be obtained, and the speed difference value of the first vehicle and the third vehicle at the previous time can be determined according to the speeds of the two vehicles.

[0144] Then, the first acceleration of the first vehicle in the lane direction at the future time can be determined based on the distance difference value, the speed difference value of the first vehicle at the previous time, and the preset acceleration.

[0145] Here, the preset acceleration can be set according to experience, which is used to determine the acceleration of the vehicle at each future time.

[0146] In specific implementation, the intelligent driver model can be used to determine the first acceleration of the first vehicle in the lane direction at the future time.

[0147] Here, the intelligent driver model can be represented by the following formula one:

[0148] Formula one:

[0149] Wherein, where a represents an acceleration of the target vehicle, a represents a preset acceleration, v represents a current speed of the target vehicle, v0 represents a preset expected speed, δ represents a preset acceleration index, s represents a distance difference value, and Δv represents a speed difference value. The target vehicle can be the first vehicle or the second vehicle.

[0150] In a specific implementation, when the target vehicle is the first vehicle, the distance difference value, the speed difference value, and the preset acceleration of the first vehicle at a previous time can be substituted into Formula (1) to determine a first acceleration of the first vehicle in a future time along a lane direction.

[0151] For each future time, the first acceleration of the first vehicle in the future time along the lane direction can be determined according to Formula (1).

[0152] For example, when the second acceleration is determined, the target vehicle can be the second vehicle, and the third vehicle can include the first vehicle. The third vehicle can include a vehicle located in a lane where the second vehicle is located and in front of the second vehicle, and / or a vehicle located in a lane where the first vehicle is located and in front of the second vehicle; the third vehicle can include the first vehicle.

[0153] Specifically, when the second acceleration of the second vehicle corresponding to each future time is determined according to a possible interaction mode, the position of the second vehicle in each future time can also be determined, and in the process of closed-loop simulation according to a possible interaction mode, the position of the fourth vehicle can be in front of the position of the second vehicle at a certain time, becoming a front vehicle of the second vehicle, at this time, the fourth vehicle is the first vehicle. Alternatively, the fourth vehicle can also be a vehicle other than the first vehicle on the lane, for example, other vehicles can appear in front of the second vehicle during the driving of the second vehicle, at this time, the fourth vehicle is the other vehicle.

[0154] In a specific implementation, the second acceleration of the second vehicle can be determined according to the following steps: for each future time in a plurality of future times, the third vehicle located in front of the second vehicle at a previous time can be determined first, and the positions of the second vehicle and the third vehicle at the previous time can be determined, and then the distance difference value corresponding to the second vehicle at the previous time can be determined according to the positions of the second vehicle and the third vehicle. Here, the distance difference value can be a distance difference value of the second vehicle and the third vehicle in the lane direction.

[0155] Further, the speed of the determined second vehicle and the third vehicle at the previous time can be obtained, and the speed difference value corresponding to the second vehicle at the previous time can be determined according to the speeds of the two vehicles.

[0156] Then, the second acceleration of the second vehicle along the lane direction at the future time can be determined based on the distance difference value, the speed difference value and the preset acceleration of the second vehicle at the previous time.

[0157] In a specific implementation, the second acceleration of the second vehicle along the lane direction at the future time can be determined by using an intelligent driver model. The intelligent driver model is a model represented by the above Formula One.

[0158] Specifically, in the case where the target vehicle is the second vehicle, the distance difference value, the speed difference value and the preset acceleration of the second vehicle at the previous time can be substituted into the above Formula One, so as to determine the second acceleration of the second vehicle along the lane direction at the future time.

[0159] Similarly, for each future time, the second acceleration of the second vehicle along the lane direction at the future time can be determined according to Formula Two.

[0160] In an embodiment, the process of determining the acceleration of the target vehicle at each future time (wherein the target vehicle can be the first vehicle when the acceleration is the first acceleration, and the target vehicle can be the second vehicle when the acceleration is the second acceleration) mentioned in the above embodiment needs to use the position of the target vehicle at the previous time. In a specific implementation, the position of the target vehicle at the previous time can be determined according to the following steps:

[0161] The position of the target vehicle at the previous time is determined based on the acceleration of the target vehicle at the previous time and the position of the target vehicle before the previous time.

[0162] In a specific implementation, after the acceleration of the target vehicle at the previous time is determined, an ideal vehicle model can be used, that is, the acceleration at the previous time is integrated and multiplied by the interval between the previous time and the current time, so as to determine the speed increment of the target vehicle along the lane direction at the previous time. Then, based on the interval between the previous time and the current time and the speed increment, the position increment of the target vehicle at the previous time can be determined. Further, according to the position of the target vehicle before the previous time and the determined position increment, the position of the target vehicle at the previous time can be determined.

[0163] Alternatively, the position increment of the target vehicle at the previous time determined according to the first acceleration can be the increment of the target vehicle along the lane direction. Then, a preset increment in a direction perpendicular to the lane direction (or a steering angle introduced below), the determined increment of the target vehicle along the lane direction and the position of the target vehicle before the previous time can be used to determine the position of the target vehicle at the previous time.

[0164] In an embodiment, the first predicted driving state information comprises a plurality of first steering angles of the first vehicle perpendicular to a lane direction at a plurality of future time instants, i.e., predicting the steering angle change of the first vehicle in a future period of time; and the second predicted driving state information comprises a plurality of second steering angles of the second vehicle perpendicular to the lane direction at the plurality of future time instants, i.e., predicting the steering angle change of the second vehicle in the future period of time.

[0165] Here, the first steering angle can reflect the steering angle of the front wheel of the first vehicle, i.e., can reflect whether the first vehicle has a turning (even sharp turning) behavior; and the second steering angle can reflect the steering angle of the front wheel of the second vehicle, i.e., can reflect whether the second vehicle has a turning (even sharp turning) behavior.

[0166] For S103, the following steps can be implemented:

[0167] S1: For each possible interaction mode, determining a maximum steering angle from the first steering angles at the plurality of future time instants indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second steering angles at the plurality of future time instants indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0168] Here, one interaction mode corresponds to one maximum steering angle, and the maximum steering angle is the maximum one of the plurality of first steering angles and the plurality of second steering angles corresponding to various possible interaction modes respectively. In specific implementation, the maximum steering angle corresponding to each possible interaction mode can be a first steering angle corresponding to the first vehicle, or a second steering angle corresponding to the second vehicle.

[0169] In specific implementation, for each possible interaction mode, the maximum steering angle corresponding to the possible interaction mode can be selected from the first steering angles at the plurality of future time instants indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second steering angles at the plurality of future time instants indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0170] In this way, according to the above S103-1, the maximum steering angle corresponding to each possible interaction mode can be determined.

[0171] S2: Based on the maximum steering angle corresponding to each possible interaction mode and a preset steering angle threshold, determining a target interaction mode from the plurality of possible interaction modes.

[0172] Here, the preset steering angle threshold is set according to experience, and in a case where the maximum steering angle is greater than the steering angle threshold, it can be indicated that the vehicle has a sharp turning behavior, and in a case where the maximum steering angle is not greater than the steering angle threshold, it can be indicated that the vehicle does not have a sharp turning behavior.

[0173] In a specific implementation, the maximum steering angle corresponding to each possible interaction mode can be compared with the steering angle threshold respectively, and the possible interaction mode corresponding to the maximum steering angle not greater than the steering angle threshold can be taken as the target interaction mode.

[0174] Alternatively, in a case where the possible interaction mode corresponding to the maximum steering angle not greater than the steering angle threshold includes multiple interaction modes, the minimum acceleration corresponding to each possible interaction mode can be determined, and the possible interaction mode corresponding to the minimum acceleration not less than the preset acceleration threshold can be taken as the target interaction mode from the multiple possible interaction modes screened by using the maximum steering angle.

[0175] For example, in a case where the possible interaction mode includes allowing the first vehicle to change lanes to the lane where the second vehicle is located and prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located, the maximum steering angle can be determined by using the first predicted driving state information and the second predicted driving state information in the first possible interaction mode.

[0176] Then, it is determined whether the maximum steering angle is greater than the steering angle threshold. If yes, it indicates that the target vehicle (the first vehicle or the second vehicle) corresponding to the maximum steering angle has a sharp turning behavior, the vehicle control difficulty increases, more uncontrollable factors of vehicle driving will be generated, and the driving safety will be affected, and it can be determined that the possible interaction mode is an unreasonable interaction mode, and the possible interaction mode is determined as a non-target interaction mode.

[0177] Further, the possible interaction mode of prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located can be directly taken as the target interaction mode, because in this possible interaction mode, the first vehicle and the second vehicle will always drive on the lanes corresponding to them respectively, and neither of them will have a sharp turning behavior, and the possible interaction mode can be directly taken as the target interaction mode.

[0178] In addition, regarding the minimum acceleration and the maximum steering angle, either one of them can be used alone to determine the target interaction mode, or both of them can be used together to determine the target interaction mode. Regarding the process of using the minimum acceleration and the maximum steering angle to determine the target interaction mode, the use order between the minimum acceleration and the maximum steering angle is not strictly limited, as long as the target interaction mode meeting the requirements of both the minimum acceleration and the maximum steering angle is screened.

[0179] In an embodiment, for the first turning angle and the second turning angle corresponding to each interaction mode, the following steps can be taken to determine:

[0180] ① For each of the plurality of future time points, based on the speed of the target vehicle at the previous time point, determine the observation distance of the target vehicle at the future time point in the direction of travel of the target vehicle; wherein the target vehicle is the first vehicle when the turning angle is the first turning angle, and the target vehicle is the second vehicle when the turning angle is the second turning angle.

[0181] Here, the observation distance is used to represent the distance that the target vehicle needs to observe forward (i.e., in the direction of travel of the target vehicle) at the next future time point.

[0182] In specific implementation, for each of the plurality of future time points, the speed of the target vehicle at the previous time point and a preset time value can be multiplied to obtain the observation distance of the target vehicle at the future time point, by using a pure tracking model.

[0183] ② Based on the observation distance, determine the observation position point of the target vehicle at the future time point in the direction of travel of the target vehicle, and determine the included angle between the straight line connecting the observation position point and the position of the target vehicle at the previous time point and the lane line of the lane where the target vehicle is located.

[0184] Here, the observation position point is the position point that the target vehicle needs to observe forward at the next future time point. The position corresponding to the position point may have a distance deviation in at least one of the vehicle direction and the direction perpendicular to the lane direction from the position of the target vehicle at the previous time point. Specifically, the distance deviation between the observation position point and the position of the target vehicle at the previous time point can be 0.

[0185] In specific implementation, the observation position point of the target vehicle at the future time point in the direction of travel of the target vehicle can be determined according to the observation distance and the position of the target vehicle at the previous time point, and the included angle between the straight line connecting the observation position point and the position of the target vehicle at the previous time point and the lane line of the lane where the target vehicle is located can be determined.

[0186] ③ Based on the observation distance, the included angle, and the wheelbase of the target vehicle, determine the turning angle of the target vehicle at the future time point corresponding to the direction perpendicular to the lane direction.

[0187] In specific implementation, the turning angle of the target vehicle at the future time point perpendicular to the lane direction can be determined by using a pure tracking model.

[0188] Here, the pure tracking model can be represented by the following formula two:

[0189] Formula two:

[0190] wherein, δ f represents the steering angle of the target vehicle perpendicular to the lane direction at the future time, B represents the wheelbase of the target vehicle, θ represents the included angle, and L represents the observation distance.

[0191] Specifically, in the case where the target vehicle is the first vehicle, the observation distance, the included angle and the wheelbase of the first vehicle at the previous time can be substituted into the above Formula Two, so as to determine the steering angle of the first vehicle perpendicular to the lane direction at the future time.

[0192] In the case where the target vehicle is the second vehicle, the observation distance, the included angle and the wheelbase of the second vehicle at the previous time can be substituted into the above Formula Two, so as to determine the steering angle of the second vehicle perpendicular to the lane direction at the future time.

[0193] In addition, as for the models involved in each embodiment of the present disclosure, i.e., the intelligent driver model, the pure tracking model and the ideal vehicle model, the embodiments of the present disclosure are not strictly limited, and other models with the same function can be used for replacement in specific applications.

[0194] In an embodiment, the process of determining the steering angle (the first steering angle or the second steering angle) of the target vehicle at each future time mentioned in the above embodiments needs to use the position of the target vehicle at the previous time. In specific implementation, the position of the target vehicle at the previous time can be determined according to the following steps:

[0195] determining the position of the target vehicle at the previous time based on the steering angle of the target vehicle at the previous time, the acceleration of the target vehicle at the previous time, and the position of the target vehicle before the previous time. Wherein, when the steering angle is the first steering angle, the target vehicle is the first vehicle, and the acceleration is the first acceleration; when the steering angle is the second steering angle, the target vehicle is the second vehicle, and the acceleration is the second acceleration.

[0196] In practice, after determining the target vehicle's initial acceleration and steering angle at the previous moment, an ideal vehicle model can be used. That is, assuming no reception delay, the acceleration at the previous moment is integrated and multiplied by a preset time interval to determine the velocity increment along the lane direction at the previous moment. Then, based on the preset time interval and the velocity increment, the target vehicle's position increment along the lane direction at the previous moment can be determined. Based on the determined steering angle, the angular velocity perpendicular to the lane direction can be determined, and the position increment perpendicular to the lane direction can be determined. Finally, based on the determined position increment along the lane direction, the position increment perpendicular to the lane direction, and the target vehicle's position before the previous moment, the target vehicle's position at the previous moment can be determined.

[0197] Furthermore, based on the determined positions of the first and second vehicles at each future moment under various possible interaction modes, the trajectories of the first and second vehicles under various possible interaction modes can also be simulated. For example... Figure 3 The diagram shown is a simulation trajectory diagram of a first vehicle and a second vehicle under a possible interaction mode, according to an embodiment of this disclosure. Figure 3 In this regard, the first vehicle is the aforementioned Figure 2 The first vehicle and the second vehicle are the aforementioned Figure 2 The first vehicle in the middle, Figure 3 The corresponding possible interaction method is to allow the first vehicle to change lanes to the lane where the second vehicle is located. Figure 3 In the diagram, the X-axis represents the target vehicle's coordinates in the direction perpendicular to the lane, and the Y-axis represents the target vehicle's coordinates in the direction of the lane. Figure 3 Trajectory 1, composed of multiple solid lines, corresponds to the simulated trajectory of the first vehicle, and trajectory 2, composed of multiple dashed lines, corresponds to the simulated trajectory of the second vehicle.

[0198] like Figure 4 The diagram shown is a schematic representation of the implementation process of a vehicle driving method provided in this embodiment. Specifically, during the driving process of the first vehicle, the possible interaction methods corresponding to the first vehicle and the second vehicle can be sampled first, that is, each possible interaction method corresponding to the first vehicle and the second vehicle can be determined. Figure 4Region R illustrates eight interaction methods corresponding to three second vehicles (second vehicle a, second vehicle b, and second vehicle c). Different shapes (circles and squares) within region R correspond to different interaction strategies. A circle indicates that the first vehicle is prohibited from changing lanes into the lane occupied by the second vehicle, while a square indicates that the first vehicle is allowed to change lanes into the lane occupied by the second vehicle. Region R includes regions r1, r2, and r3. The dashed line in region r1 represents second vehicle a, the solid line in region r2 represents second vehicle b, and the dotted line in region r3 represents second vehicle c. Furthermore, closed-loop simulations can be performed on each possible interaction method, that is, the first predicted driving state information corresponding to the first vehicle and the second predicted driving state information corresponding to the second vehicle can be determined under each possible interaction method. Finally, strategy evaluation can be performed on various interaction strategies, that is, the target interaction method can be determined from multiple possible interaction methods.

[0199] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0200] Based on the same inventive concept, this disclosure also provides a vehicle driving device corresponding to the vehicle driving method. Since the principle of the device in this disclosure for solving the problem is similar to the above-mentioned vehicle driving method in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0201] like Figure 5 The diagram shown is a schematic representation of a vehicle driving device provided in an embodiment of this disclosure, comprising:

[0202] The first determining module 501 is used to determine multiple possible interaction methods between the first vehicle and the second vehicle during the driving process of the first vehicle;

[0203] The second determining module 502 is used to determine, for each possible interaction method, the first predicted driving state information of the first vehicle under the possible interaction method, and the second predicted driving state information of the second vehicle under the possible interaction method;

[0204] The third determining module 503 is used to determine the target interaction method from the multiple possible interaction methods based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction method.

[0205] The control module 504 is used to control the movement of the first vehicle based on the target interaction method.

[0206] In a possible implementation, the first determining module 501 is configured to, when determining that the first vehicle has a lane-changing demand, determine the plurality of possible interaction modes between the first vehicle and the second vehicle, including allowing the first vehicle to change lanes to the lane in which the second vehicle is located, and prohibiting the first vehicle from changing lanes to the lane in which the second vehicle is located.

[0207] In a possible implementation, the first predicted driving state information includes first accelerations of the first vehicle in a lane direction at a plurality of future time points, and the second predicted driving state information includes second accelerations of the second vehicle in the lane direction at the plurality of future time points.

[0208] The third determining module 503 is configured to, for each possible interaction mode, determine a minimum acceleration from the first accelerations at the plurality of future time points indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second accelerations at the plurality of future time points indicated by the second predicted driving state information corresponding to the possible interaction mode.

[0209] The target interaction mode is determined from the plurality of possible interaction modes based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold.

[0210] In a possible implementation, the apparatus further includes:

[0211] The fourth determining module 505 is configured to determine the acceleration of the target vehicle by the following steps:

[0212] For each of the plurality of future time points, based on positions of the target vehicle and a third vehicle at a previous time point, determine a distance difference between the target vehicle and the third vehicle in a lane direction at the previous time point, and based on speeds of the target vehicle and the third vehicle at the previous time point, determine a speed difference between the target vehicle and the third vehicle at the previous time point.

[0213] Based on the distance difference, the speed difference, and a preset acceleration of the target vehicle at the previous time point, determine an acceleration of the target vehicle in the lane direction at the future time point.

[0214] In a possible implementation, when the acceleration is a first acceleration, the target vehicle is the first vehicle, the third vehicle includes a vehicle located in the lane of the target vehicle and in front of the target vehicle, and / or a vehicle located in the lane of the second vehicle and in front of the target vehicle; and the third vehicle includes the second vehicle.

[0215] In a case where the acceleration is a second acceleration, the target vehicle is a second vehicle, the third vehicle includes a vehicle located in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle located in a lane where the first vehicle is located and in front of the target vehicle; and the third vehicle includes the first vehicle.

[0216] In a possible implementation, the fourth determining module 505 determines the position of the target vehicle at the previous moment according to the following steps:

[0217] determines the position of the target vehicle at the previous moment based on the acceleration of the target vehicle at the previous moment and the position of the target vehicle before the previous moment; wherein, in a case where the acceleration is a first acceleration, the target vehicle is a first vehicle; and in a case where the acceleration is a second acceleration, the target vehicle is a second vehicle.

[0218] In a possible implementation, the first predicted driving state information includes a plurality of first steering angles of the first vehicle perpendicular to a lane direction at a plurality of future moments, and the second predicted driving state information includes a plurality of second steering angles of the second vehicle perpendicular to the lane direction at the plurality of future moments.

[0219] The third determining module 503 is configured to, for each of the possible interaction manners, determine a maximum steering angle from the first steering angles at the plurality of future moments indicated by the first predicted driving state information corresponding to the possible interaction manner and the second steering angles at the plurality of future moments indicated by the second predicted driving state information corresponding to the possible interaction manner.

[0220] The target interaction manner is determined from the plurality of possible interaction manners based on the maximum steering angle corresponding to each of the possible interaction manners and a preset steering angle threshold.

[0221] In a possible implementation, the apparatus further includes:

[0222] The fifth determining module 506 is configured to determine the steering angle according to the following steps:

[0223] For each of the plurality of future moments, an observed distance of the target vehicle along a driving direction of the target vehicle at the future moment is determined based on a speed of the target vehicle at a previous moment; wherein, in a case where the steering angle is the first steering angle, the target vehicle is the first vehicle, and in a case where the steering angle is the second steering angle, the target vehicle is the second vehicle.

[0224] determine an observation position point of the target vehicle in a target vehicle driving direction at the future time based on the observation distance, and determine an included angle between a straight line connecting the observation position point and a position of the target vehicle at a previous time and a lane line of a lane where the target vehicle is located;

[0225] determine a steering angle of the target vehicle perpendicular to a lane direction at the future time based on the observation distance, the included angle and an axle distance of the target vehicle.

[0226] In a possible implementation, the fifth determining module 506 is configured to determine the position of the target vehicle at the previous time according to the following steps:

[0227] determine the position of the target vehicle at the previous time based on a steering angle of the target vehicle at the previous time, an acceleration of the target vehicle at the previous time and a position of the target vehicle before the previous time; wherein when the steering angle is a first steering angle, the target vehicle is a first vehicle, and the acceleration is a first acceleration; when the steering angle is a second steering angle, the target vehicle is a second vehicle, and the acceleration is a second acceleration.

[0228] In a possible implementation, the control module 504 is configured to determine a planned driving track of the first vehicle based on the target interaction mode.

[0229] control the first vehicle to drive according to the planned driving track.

[0230] The description of the processing procedure of each module in the apparatus and the interaction procedure between the modules can refer to the related description in the above method embodiments, and will not be repeated here.

[0231] Based on the same technical concept, the embodiments of the present application also provide a computer device as shown in the accompanying drawings, which comprises: Figure 6 As shown in the accompanying drawings, the computer device provided by the embodiments of the present application comprises:

[0232] The processor 61, the memory 62 and the bus 63. The memory 62 stores machine readable instructions executable by the processor 61, and the processor 61 is configured to execute the machine readable instructions stored in the memory 62. When the processor 61 executes the machine readable instructions, the processor 61 performs the following steps: S101: determining a plurality of possible interaction modes between the first vehicle and the second vehicle during driving of the first vehicle; S102: for each possible interaction mode, determining first predicted driving state information of the first vehicle in the possible interaction mode and second predicted driving state information of the second vehicle in the possible interaction mode; S103: determining a target interaction mode from the plurality of possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode; and S104: controlling the first vehicle to drive based on the target interaction mode.

[0233] The memory 62 includes an internal memory 621 and an external memory 622. The internal memory 621 is also referred to as an internal storage, and is used to temporarily store operation data in the processor 61 and exchange data with the external memory 622 such as a hard disk. The processor 61 exchanges data with the external memory 622 through the internal memory 621. When the computer device is running, the processor 61 communicates with the memory 62 through the bus 63, so that the processor 61 executes the instructions mentioned in the above method embodiments.

[0234] The specific execution process of the instructions can refer to the steps of the vehicle driving method described in the embodiments of the present disclosure, which will not be described here.

[0235] The embodiments of the present disclosure also provide a computer readable storage medium having a computer program stored thereon. When the computer program is run by a processor, the steps of the vehicle driving method described in the above method embodiments are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0236] The computer program product of the vehicle driving method provided by the embodiments of the present disclosure includes a computer readable storage medium storing program codes. The instructions included in the program codes can be used to execute the steps of the vehicle driving method described in the above method embodiments. For details, refer to the above method embodiments, which will not be described here.

[0237] The computer program product can be specifically implemented by hardware, software or a combination thereof. In one optional embodiment, the computer program product is specifically embodied as a computer storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.

[0238] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the apparatus described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here. In several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are only schematic. For example, the division of the units is only a logical function division, and another division can be made in actual implementation. For example, a plurality of units or components can be combined, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, and can be electrical, mechanical or other forms.

[0239] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0240] In addition, the functional units in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0241] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present disclosure essentially or say the part of the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present disclosure. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various program codes that can be stored in the medium.

[0242] If the technical solution of the present application involves personal information, the product applying the technical solution of the present application has been explicitly informed of the personal information processing rules before processing the personal information, and has obtained the personal independent consent. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the personal independent consent before processing the sensitive personal information, and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as camera, a clear and prominent mark is set to inform that it has entered the personal information collection range and will collect personal information. If the individual voluntarily enters the collection range, it is considered to agree to collect personal information. Or on the device for processing personal information, through the pop-up information or by uploading personal information by the individual, the individual's authorization is obtained under the condition of using obvious mark / information to inform the individual of the personal information processing rules. The personal information processing rules can include personal information processor, personal information processing purpose, processing method, personal information type, etc.

[0243] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, and are not limitations thereof. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any skilled person familiar with the technical field can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features thereof within the technical range disclosed by the present disclosure. The modification, change or replacement does not make the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A vehicle travel method characterized by, The method comprises: determining a plurality of possible interaction modes between the first vehicle and the second vehicle during driving of the first vehicle; for each possible interaction mode, determining first predicted driving state information of the first vehicle in the possible interaction mode and second predicted driving state information of the second vehicle in the possible interaction mode, wherein the first predicted driving state information comprises first accelerations of the first vehicle in a lane direction at a plurality of future time points, and the second predicted driving state information comprises second accelerations of the second vehicle in the lane direction at the plurality of future time points; determining a target interaction mode from the plurality of possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode; wherein the determination of the target interaction mode from the plurality of possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode comprises: for each possible interaction mode, determining a minimum acceleration from the first accelerations at the plurality of future time points indicated by the first predicted driving state information corresponding to the possible interaction mode and the second accelerations at the plurality of future time points indicated by the second predicted driving state information corresponding to the possible interaction mode, and determining the target interaction mode from the plurality of possible interaction modes based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold; controlling driving of the first vehicle based on the target interaction mode.

2. The method of claim 1, wherein, The determination of the plurality of possible interaction modes between the first vehicle and the second vehicle comprises: in a case where it is determined that the first vehicle has a lane-changing demand, the determination of the plurality of possible interaction modes between the first vehicle and the second vehicle comprises: allowing the first vehicle to change lanes to a lane where the second vehicle is located, and prohibiting the first vehicle from changing lanes to the lane where the second vehicle is located.

3. The method according to claim 1 or 2, characterized in that, The acceleration of the target vehicle is determined according to the following steps: for each of the plurality of future time points, determining a distance difference between the target vehicle and a third vehicle in a lane direction at a previous time point based on positions of the target vehicle and the third vehicle at the previous time point, and determining a speed difference between the target vehicle and the third vehicle at the previous time point based on speeds of the target vehicle and the third vehicle at the previous time point; determining an acceleration of the target vehicle in the lane direction at the future time point based on the distance difference, the speed difference, and a preset acceleration at the previous time point; wherein, in a case where the acceleration is a first acceleration, the target vehicle is the first vehicle, the third vehicle comprises a vehicle located in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle located in a lane where the second vehicle is located and in front of the target vehicle; and the third vehicle comprises the second vehicle. In a case where the acceleration is a second acceleration, the target vehicle is a second vehicle, and the third vehicle includes a vehicle located in a lane where the target vehicle is located and in front of the target vehicle, and / or a vehicle located in a lane where the first vehicle is located and in front of the target vehicle; and the third vehicle includes the first vehicle.

4. The method of claim 3, wherein, The position of the target vehicle at a previous time is determined according to the following steps: The position of the target vehicle at the previous time is determined based on the acceleration of the target vehicle at the previous time and the position of the target vehicle before the previous time; wherein, in a case where the acceleration is a first acceleration, the target vehicle is a first vehicle; and in a case where the acceleration is a second acceleration, the target vehicle is a second vehicle.

5. The method according to any one of claims 1 to 2, characterized in that, The first predicted driving state information includes a plurality of first steering angles of the first vehicle perpendicular to a lane direction at a plurality of future times, and the second predicted driving state information includes a plurality of second steering angles of the second vehicle perpendicular to the lane direction at the plurality of future times. The target interaction mode is determined from the plurality of possible interaction modes based on the first predicted driving state information and the second predicted driving state information corresponding to each possible interaction mode, comprising: For each possible interaction mode, a maximum steering angle is determined from the first steering angles at the plurality of future times indicated by the first predicted driving state information corresponding to the possible interaction mode, and the second steering angles at the plurality of future times indicated by the second predicted driving state information corresponding to the possible interaction mode. The target interaction mode is determined from the plurality of possible interaction modes based on the maximum steering angle corresponding to each possible interaction mode and a preset steering angle threshold.

6. The method of claim 5, wherein, The steering angle is determined according to the following steps: For each of the plurality of future times, an observation distance of the target vehicle along a driving direction of the target vehicle at the future time is determined based on a speed of the target vehicle at a previous time; wherein, in a case where the steering angle is the first steering angle, the target vehicle is the first vehicle, and in a case where the steering angle is the second steering angle, the target vehicle is the second vehicle. An observation position point of the target vehicle along the driving direction of the target vehicle at the future time is determined based on the observation distance, and an included angle between a straight line connecting the observation position point and the position of the target vehicle at the previous time and a lane line of a lane where the target vehicle is located is determined. A steering angle of the target vehicle perpendicular to the lane direction at the future time is determined based on the observation distance, the included angle, and a wheelbase of the target vehicle.

7. The method of claim 6, wherein, The position of the target vehicle at a previous time is determined according to the following steps: determine a position of the target vehicle at the previous time based on a steering angle of the target vehicle at the previous time, an acceleration of the target vehicle at the previous time, and a position of the target vehicle before the previous time; wherein, when the steering angle is a first steering angle, the target vehicle is a first vehicle, and the acceleration is a first acceleration; when the steering angle is a second steering angle, the target vehicle is a second vehicle, and the acceleration is a second acceleration.

8. The method of claim 1, wherein, The control of the first vehicle traveling based on the target interaction mode comprises: determining a planned traveling trajectory of the first vehicle based on the target interaction mode; controlling the first vehicle to travel according to the planned traveling trajectory.

9. A vehicle travel device characterized by comprising: comprise: a first determining module configured to determine a plurality of possible interaction modes between the first vehicle and a second vehicle during traveling of the first vehicle; a second determining module configured to determine, for each possible interaction mode, first predicted traveling state information of the first vehicle in the interaction mode and second predicted traveling state information of the second vehicle in the possible interaction mode, wherein the first predicted traveling state information comprises first accelerations of the first vehicle along a lane direction at a plurality of future times, and the second predicted traveling state information comprises second accelerations of the second vehicle along the lane direction at the plurality of future times; a third determining module configured to determine a target interaction mode from the plurality of possible interaction modes based on the first predicted traveling state information and the second predicted traveling state information corresponding to each possible interaction mode; wherein the determination of the target interaction mode from the plurality of possible interaction modes based on the first predicted traveling state information and the second predicted traveling state information corresponding to each possible interaction mode comprises: determining, for each possible interaction mode, a minimum acceleration from the first accelerations at the plurality of future times indicated by the first predicted traveling state information corresponding to the possible interaction mode and the second accelerations at the plurality of future times indicated by the second predicted traveling state information corresponding to the possible interaction mode, and determining the target interaction mode from the plurality of possible interaction modes based on the minimum acceleration corresponding to each possible interaction mode and a preset acceleration threshold value; a control module configured to control the first vehicle to travel based on the target interaction mode.

10. A computer device, comprising: comprise: a processor and a memory, the memory storing machine readable instructions executable by the processor, the processor being configured to execute the machine readable instructions stored in the memory, and the machine readable instructions, when executed by the processor, causing the processor to perform the steps of the vehicle traveling method according to any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, A computer program is stored on the computer readable storage medium, and when the computer program is run by a computer device, the computer device performs the steps of the vehicle traveling method according to any one of claims 1 to 8.

Images