Vehicle avoidance method and device, electronic equipment and computer readable storage medium

Abstract

The application discloses a vehicle avoidance method and device, an electronic device and a computer readable storage medium. The method comprises the following steps: acquiring current lane information of a self vehicle and current position information of the self vehicle on the current lane; acquiring vehicle information of other vehicles from other adjacent lanes according to the current lane information and the current position information; if a transverse distance between a target vehicle and the self vehicle on the other lane is less than a preset transverse distance, determining longitudinal time-distance information between the self vehicle and the target vehicle according to vehicle information of the self vehicle and vehicle information of the target vehicle, the transverse direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to a driving direction of the self vehicle; determining whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the self vehicle; if there is the avoidance vehicle, determining a target avoidance distance of the self vehicle according to vehicle information of the avoidance vehicle and vehicle information of the self vehicle, and controlling the self vehicle to perform avoidance processing. Thus, the accuracy of vehicle avoidance is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle processing, in particular to a vehicle avoidance method, a vehicle avoidance device, an electronic device and a computer readable storage medium. BACKGROUND

[0002] In intelligent driving, when the vehicle in the adjacent lane is close to or even encroaches on the self-lane, the self-vehicle needs to actively make lateral position offset adjustment to relieve the oppression of the two vehicles being too close. The avoidance logic currently adopted is to make avoidance action for a single target vehicle, but in actual application, there are usually more than one vehicle adjacent to the self-vehicle. Therefore, if only considering the avoidance of a single target vehicle, when the self-vehicle avoids the target vehicle on one side, it may cause the dangerous behavior of actively approaching the vehicle on the other side. SUMMARY

[0003] The technical problem solved by the present application is to provide a vehicle avoidance method, a vehicle avoidance device, an electronic device and a computer readable storage medium, which can improve the accuracy of vehicle avoidance.

[0004] To solve the above technical problem, one technical solution adopted by the present application is to provide a vehicle avoidance method, comprising: acquiring vehicle information of a self-vehicle, the vehicle information comprising current lane information of the self-vehicle and current position information of the self-vehicle on the current lane; acquiring vehicle information of other vehicles from other lanes adjacent to the current lane according to the current lane information and the current position information; in response to the existence of a target vehicle between the self-vehicle and the other lanes, determining longitudinal time-distance information between the self-vehicle and the target vehicle according to the vehicle information of the self-vehicle and the vehicle information of the target vehicle, the longitudinal direction being perpendicular to the lateral direction, and the longitudinal direction being parallel to the driving direction of the self-vehicle; determining whether there is an avoidance vehicle in the other lanes according to the longitudinal time-distance information between the target vehicle and the self-vehicle; in response to the existence of the avoidance vehicle, determining a target avoidance distance of the self-vehicle relative to the avoidance vehicle according to the vehicle information of the avoidance vehicle and the vehicle information of the self-vehicle; and controlling the self-vehicle to perform avoidance processing according to the target avoidance distance.

[0005] In some embodiments, the longitudinal time-to-collision information comprises a longitudinal distance and a longitudinal collision time, the vehicle information comprises coordinate information, size information and motion information of the vehicle, and the step of determining the longitudinal time-to-collision information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle comprises: determining the longitudinal distance between the ego vehicle and the target vehicle according to the coordinate information and the size information of the ego vehicle and the coordinate information and the size information of the target vehicle; and predicting the longitudinal collision time of the ego vehicle and the target vehicle according to the longitudinal distance between the ego vehicle and the target vehicle, the motion information of the ego vehicle and the motion information of the target vehicle.

[0006] In some embodiments, the size information comprises a vehicle body length, and the motion information comprises a speed, and the step of predicting the longitudinal collision time of the ego vehicle and the target vehicle according to the longitudinal distance between the ego vehicle and the target vehicle, the motion information of the ego vehicle and the motion information of the target vehicle comprises: determining a speed difference between the ego vehicle and the target vehicle according to the speed of the ego vehicle and the speed of the target vehicle; and determining a ratio between the longitudinal distance and the speed difference as the longitudinal collision time of the ego vehicle and the target vehicle.

[0007] In some embodiments, the other lane comprises a first lane and a second lane, the longitudinal time-to-collision information comprises a longitudinal collision time and a longitudinal distance, the avoiding vehicle comprises a first avoiding vehicle and a second avoiding vehicle, and the step of determining whether there is an avoiding vehicle in the other lane according to the longitudinal time-to-collision information between the target vehicle and the ego vehicle comprises: determining whether there is an avoiding vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle; in response to the existence of an avoiding vehicle on the first lane, determining whether there is an avoiding vehicle on the target vehicle in the second lane according to the longitudinal distance between each target vehicle and the ego vehicle; and in response to the longitudinal distance of a target vehicle on the second lane being less than a preset longitudinal distance, determining the corresponding target vehicle as an avoiding vehicle.

[0008] In some embodiments, the step of determining whether there is an avoiding vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle comprises: determining whether the longitudinal collision time between each target vehicle and the ego vehicle is less than a preset collision time; and if yes, determining that there is an avoiding vehicle on the other lane.

[0009] In some embodiments, the other lanes include a first lane and a second lane, the avoiding vehicles include a first avoiding vehicle in the first lane and a second avoiding vehicle in the second lane, and the step of determining the target avoiding distance of the ego vehicle relative to the avoiding vehicles according to the vehicle information of the avoiding vehicles and the vehicle information of the ego vehicle includes: determining a first initial avoiding distance according to the vehicle information of the first avoiding vehicle and the vehicle information of the ego vehicle; determining a second initial avoiding distance according to the vehicle information of the second avoiding vehicle, the vehicle information of the ego vehicle and the vehicle information of the first avoiding vehicle; and selecting the target avoiding distance from the first initial avoiding distance and the second initial avoiding distance according to the size relationship between the first initial avoiding distance and the second initial avoiding distance.

[0010] In some embodiments, the current lane information includes a lane center line, and the step of determining the first initial avoiding distance according to the vehicle information of the first avoiding vehicle and the vehicle information of the ego vehicle includes: determining a distance between a target boundary of a vehicle body of the first avoiding vehicle and the lane center line of the ego vehicle, the target boundary of the vehicle body representing a boundary of the vehicle body of the first avoiding vehicle close to the ego vehicle according to the vehicle information of the first avoiding vehicle and the vehicle information of the ego vehicle; calculating a distance difference between the distance and a first preset safety distance; and determining a sum of the distance difference and a preset avoiding distance as the first initial avoiding distance.

[0011] To solve the above technical problems, another technical solution adopted by the present application is to provide a vehicle avoiding device, which includes: the device includes a first acquisition module, a second acquisition module, a first determination module, a second determination module, a third determination module and an avoiding module; the first acquisition module is configured to acquire vehicle information of an ego vehicle, the vehicle information including current lane information of the ego vehicle and current position information of the ego vehicle on the current lane; the second acquisition module is configured to acquire vehicle information of other vehicles on other lanes adjacent to the current lane according to the current lane information and the current position; the first determination module is configured to, in response to a transverse distance between a target vehicle on the other lanes and the ego vehicle being less than a preset transverse distance, determine longitudinal time-distance information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle, the transverse direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to a driving direction of the ego vehicle; the second determination module is configured to determine whether there is an avoiding vehicle in the other lanes according to the longitudinal time-distance information between the target vehicle and the ego vehicle; the third determination module is configured to, in response to the existence of the avoiding vehicle, determine a target avoiding distance of the ego vehicle relative to the avoiding vehicle according to the vehicle information of the avoiding vehicle and the vehicle information of the ego vehicle; and the avoiding module is configured to control the ego vehicle to perform avoiding processing according to the target avoiding distance.

[0012] To solve the above technical problems, another technical solution adopted by the present application is to provide an electronic device, comprising a memory and a processor, the memory stores program instructions, and the processor retrieves the program instructions from the memory to execute the vehicle avoidance method described above.

[0013] To solve the above technical problems, another technical solution adopted by the present application is to provide a computer-readable storage medium comprising program data stored therein, the program data being executed by a processor to implement the vehicle avoidance method described above.

[0014] The above scheme, obtaining vehicle information of the ego vehicle, the vehicle information including current lane information of the ego vehicle and current position information of the ego vehicle on the current lane; obtaining vehicle information of other vehicles from other lanes adjacent to the current lane according to the current lane information and the current position; in response to the existence of a target vehicle on the other lane and the lateral distance between the target vehicle and the ego vehicle being less than a preset lateral distance, determining longitudinal time-distance information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle, the lateral direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to the driving direction of the ego vehicle. Thus, it is ensured that the vehicle avoidance is started only when the vehicle on the other lane approaches the ego vehicle, reducing the computational burden. Then, it is determined whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle; in response to the existence of the avoidance vehicle, determining a target avoidance distance of the ego vehicle relative to the avoidance vehicle according to the vehicle information of the avoidance vehicle and the vehicle information of the ego vehicle; and controlling the ego vehicle to perform avoidance processing according to the target avoidance distance. Thus, the target vehicles on the other lane approaching the ego vehicle are all judged for avoidance by the longitudinal time-distance information, the spatial relationship between the ego vehicle and other vehicles is considered as a whole, the accuracy of the target avoidance distance is ensured, and the safety of vehicle avoidance is improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings:

[0016] Figure 1 is a flowchart of an exemplary embodiment of the vehicle avoidance method shown by the present application;

[0017] Figure 2 is Figure 1 is a flowchart of an exemplary embodiment of step S130 in the vehicle avoidance method shown by the present application;

[0018] Figure 3is a structural schematic diagram of vehicle avoidance shown in an example embodiment of the present application;

[0019] Figure 4 is a structural schematic diagram of a vehicle avoidance device shown in an example embodiment of the present application;

[0020] Figure 5 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0021] Figure 6 is a structural schematic diagram of a computer readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limit the present application. In addition, it should be noted that, for the convenience of description, only parts related to the present application are shown in the drawings, rather than all the structures. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0023] First of all, it should be noted that, with the continuous development of intelligent driving technology, LCC (Lane Centering Control) as an important function of intelligent driving can help the vehicle to keep driving in the center of the lane. However, in the LCC function scene, the obstacle in the adjacent lane often approaches or even occupies the lane where the ego vehicle is located, at which time the ego vehicle needs to actively adjust the lateral position offset. However, in actual application, there are many obstacles in other lanes, for example, when the ego vehicle avoids a target vehicle on one side, it also needs to consider whether there is a parallel vehicle on the other side to avoid dangerous behavior of the ego vehicle approaching the adjacent lane; for example, if there is a potential avoidance target on the other side or the same side of the target vehicle when avoiding, the lateral offset amount of avoidance needs to be considered comprehensively to avoid the lateral position of the ego vehicle swinging or even having a safety hazard when continuously avoiding.

[0024] Based on this, the present application provides a vehicle avoidance method, a vehicle avoidance device, an electronic device and a computer readable storage medium, which can comprehensively consider the spatial relationship between the ego vehicle and the surrounding vehicles to obtain a suitable and safe target avoidance distance under complex traffic flow. For details, please refer to Figure 1 , Figure 1 is a flowchart of a vehicle avoidance method shown in an example embodiment of the present application.

[0025] The execution subject of the vehicle avoidance method can be a terminal device or a server or other processing device, wherein the terminal device can be a user equipment (UE), a computer, a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The execution subject of the vehicle avoidance method can also be a vehicle avoidance apparatus. In some possible implementation manners, the vehicle avoidance method can be implemented by a processor invoking computer readable instructions stored in a memory.

[0026] Specifically, the vehicle avoidance method of the embodiment includes the following steps:

[0027] S110: Obtain vehicle information of the ego vehicle, wherein the vehicle information includes current lane information of the ego vehicle and current position information of the ego vehicle on the current lane.

[0028] The ego vehicle refers to a vehicle that actively avoids other vehicles in the embodiment. In actual application scenarios, the ego vehicle usually refers to a vehicle that can be controlled by the current vehicle avoidance apparatus, and the other vehicles refer to vehicles that are not controlled by the current vehicle avoidance apparatus.

[0029] The vehicle information refers to information generated by the ego vehicle during operation. Exemplarily, the vehicle information includes current lane information of the ego vehicle, current position information of the ego vehicle on the current lane, and a series of information related to the ego vehicle such as size information and version information of the ego vehicle. Among them, the current lane information and the current position information of the ego vehicle on the current lane can be obtained through a positioning system on the ego vehicle; the size information and the version information of the ego vehicle can be obtained through factory information of the ego vehicle.

[0030] The current lane information refers to information of a lane currently traveled by the ego vehicle, for example, including information such as a position of the current lane, a center line of the current lane, a width of the current lane, and a lane line. In some embodiments, the current lane information can be obtained from open source road data after determining the current lane of the ego vehicle through a positioning system of the ego vehicle. In other embodiments, the center line, the width, the lane line, and the current position information of the ego vehicle on the current lane can also be obtained through image recognition technology.

[0031] The current position information refers to current position information of the ego vehicle on the current lane. Exemplarily, the current position information includes a distance between a center point of the ego vehicle and a center line of the current lane, a distance between a boundary of the ego vehicle and an edge line of the current lane, etc. Exemplarily, the current position information of the ego vehicle on the current lane can be obtained through a high-definition map.

[0032] The vehicle avoidance device acquires current lane information and current position information of the ego vehicle in real time during driving of the ego vehicle.

[0033] S120: vehicle information of other vehicles is acquired from other lanes adjacent to the current lane according to the current lane information and the current position information.

[0034] The other lane is a lane adjacent to the current lane where the ego vehicle is located. For example, when the current lane is the leftmost lane, the other lane can be the right lane to the right of the current lane; when the current lane is the right lane, the other lane can be the left lane to the left of the current lane; when the current lane is the middle lane, the other lane includes the left lane and the right lane adjacent to the current lane.

[0035] The other vehicle is a vehicle located on the other lane. For example, after determining the other lane, the other vehicle is determined from the other lane according to the current position information of the ego vehicle, and vehicle information of the other vehicle is acquired. In some embodiments, vehicles on the other lane within a range from a first preset distance behind the ego vehicle to a second preset distance in front of the ego vehicle in the driving direction of the ego vehicle can be regarded as the other vehicle. For example, the vehicle information of the other vehicle on the other lane can be acquired by the perception system of the ego vehicle. The vehicle information of the other vehicle includes but is not limited to size information, position information and motion information of the other vehicle, etc. The first preset distance can be 20 meters, 30 meters, etc., and the second preset distance can be 100 meters, 200 meters, etc.

[0036] The vehicle avoidance device first determines the other lane adjacent to the current lane according to the current lane information of the ego vehicle, and then acquires the vehicle information of the other vehicle from the other lane within a range from 20 meters behind the ego vehicle to 100 meters in front of the ego vehicle according to the current position information of the ego vehicle on the current lane.

[0037] S130: in response to the transverse distance between the target vehicle on the other lane and the ego vehicle being less than a preset transverse distance, longitudinal time-distance information between the ego vehicle and the target vehicle is determined according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle, the transverse direction and the longitudinal direction are perpendicular to each other, and the longitudinal direction is parallel to the driving direction of the ego vehicle.

[0038] The target vehicle refers to a vehicle in the other vehicles whose lateral distance from the ego vehicle is less than a preset lateral distance. When the lateral distance from the ego vehicle of the other vehicle is less than the preset lateral distance, it indicates that the other vehicle has the risk of approaching the ego vehicle, and therefore when this situation occurs, it is necessary to further determine whether the ego vehicle needs to avoid. When there is no other vehicle whose lateral distance from the ego vehicle is less than the preset lateral distance, it indicates that the other vehicle has no risk of approaching the ego vehicle, and the ego vehicle normally drives without the need to avoid. Illustratively, after the vehicle avoiding device obtains the vehicle information of the ego vehicle and the vehicle information of the other vehicles, the other vehicles are screened according to the vehicle information of the ego vehicle and the vehicle information of the other vehicles to obtain the target vehicle. Specifically, the other vehicles are screened according to the lateral distance between the ego vehicle and the other vehicles, and the other vehicles whose lateral distance is greater than or equal to the preset lateral distance are removed to obtain the target vehicle.

[0039] The longitudinal direction is parallel to the driving direction of the ego vehicle, and the lateral direction is perpendicular to the longitudinal direction, that is, the lateral direction is perpendicular to the driving direction of the ego vehicle. The lateral distance refers to the distance between the other vehicle and the ego vehicle along the lateral direction. In some embodiments, in the LCC scenario, the center line of the lane is generally used as the reference, and therefore the distance between the other vehicle and the center line of the current lane of the ego vehicle can be used as the lateral distance between the other vehicle and the ego vehicle. In other embodiments, the lateral distance between the other vehicle and the ego vehicle can also be determined by the position information of the other vehicle and the current position information of the ego vehicle.

[0040] The preset lateral distance is used to limit whether the other vehicle enters the dangerous area of the ego vehicle. Illustratively, the preset lateral distance can be determined according to the current lane information, for example, can be set according to the width of the current lane. Illustratively, the preset lateral distance can include a first preset safety distance and a second preset safety distance, the first preset safety distance is used to screen the other vehicles when determining the longitudinal collision time in the longitudinal time-distance information, and the second preset safety distance is used to screen the other vehicles when determining the longitudinal distance in the longitudinal time-distance information.

[0041] The longitudinal time-distance information refers to the time-distance information between the target vehicle and the ego vehicle along the longitudinal direction. In some embodiments, the longitudinal time-distance information includes the collision time when the ego vehicle catches up with the target vehicle, and also includes the longitudinal distance between the ego vehicle and the target vehicle in the longitudinal direction. In other embodiments, the longitudinal time-distance information refers to the collision time when the ego vehicle catches up with the target vehicle.

[0042] The vehicle avoidance device obtains a lateral distance between the other vehicle and the ego vehicle, and performs screening processing on the other vehicle according to the lateral distance, removes the other vehicle with a lateral distance greater than or equal to a preset lateral distance, and screens a target vehicle with a lateral distance less than the preset lateral distance. Then, the longitudinal time-distance information between the ego vehicle and the target vehicle in the longitudinal direction is determined according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle.

[0043] S140: Determine whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle.

[0044] After determining the longitudinal time-distance information between the target vehicle and the ego vehicle, the vehicle avoidance device determines whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information. For example, it can be determined whether the longitudinal time-distance information between each target vehicle and the ego vehicle meets a preset requirement. If it does, the corresponding target vehicle is determined as an avoidance vehicle. If none of the target vehicles meets the requirement, it is determined that there is no avoidance vehicle in the other lane. It should be noted that when there is an avoidance vehicle, the number of avoidance vehicles can be one or more, i.e. one, two, etc.

[0045] S150: In response to the presence of an avoidance vehicle, determine the target avoidance distance of the ego vehicle relative to the avoidance vehicle according to the vehicle information of the avoidance vehicle and the vehicle information of the ego vehicle.

[0046] The target avoidance distance refers to the target avoidance distance of the ego vehicle relative to the avoidance vehicle. In some embodiments, if there are multiple avoidance vehicles, one of them can be selected as the target avoidance vehicle. The initial avoidance distance is determined according to the vehicle information of the target avoidance vehicle and the vehicle information of the ego vehicle. The initial avoidance distance is adjusted according to the vehicle information of the other avoidance vehicles except the target avoidance vehicle and the vehicle information of the ego vehicle to obtain the target avoidance distance.

[0047] S160: Control the ego vehicle to perform avoidance processing according to the target avoidance distance.

[0048] The vehicle avoidance device controls the ego vehicle to perform avoidance processing according to the target avoidance distance. Specifically, the vehicle avoidance device first determines the avoidance direction of the ego vehicle according to the avoidance vehicle, and then avoids the target avoidance distance along the avoidance direction of the ego vehicle, thereby completing the vehicle avoidance of the ego vehicle. If there are multiple avoidance vehicles, the target avoidance vehicle is determined according to the longitudinal time-distance information between each avoidance vehicle and the ego vehicle, and the avoidance direction of the ego vehicle is determined according to the target avoidance vehicle. The avoidance direction can be the direction away from the target avoidance vehicle. If there is only one avoidance vehicle, the avoidance direction of the ego vehicle is directly determined according to the avoidance vehicle, i.e. the direction away from the avoidance vehicle.

[0049] It can be seen that the vehicle avoidance method of the embodiment of the application obtains vehicle information of the ego vehicle, the vehicle information including current lane information of the ego vehicle and current position information of the ego vehicle on the current lane; obtains vehicle information of other vehicles on other lanes adjacent to the current lane according to the current lane information and the current position; in response to the transverse distance between the target vehicle on the other lane and the ego vehicle being less than a preset transverse distance, determines longitudinal time-distance information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle, the transverse direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to the driving direction of the ego vehicle. Thus, it is ensured that the vehicle avoidance is started only when the vehicle on the other lane is close to the ego vehicle, and the calculation burden is reduced. Then, it is determined whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle; in response to the avoidance vehicle existing, a target avoidance distance of the ego vehicle relative to the avoidance vehicle is determined according to the vehicle information of the avoidance vehicle and the vehicle information of the ego vehicle; and the ego vehicle is controlled to perform avoidance processing according to the target avoidance distance. Thus, the target vehicles on the other lane close to the ego vehicle are all judged to perform avoidance by the longitudinal time-distance information, the spatial relationship between the ego vehicle and the other vehicles is considered as a whole, the accuracy of the target avoidance distance is ensured, and the safety of the vehicle avoidance is improved.

[0050] On the basis of the above-mentioned embodiment, the embodiment of the application adopts Figure 2 The flow chart details how to obtain the longitudinal time-distance information between the target vehicle and the ego vehicle. Please refer to Figure 2 , Figure 2 is Figure 1 The flow chart details how to obtain the longitudinal time-distance information between the target vehicle and the ego vehicle. Please refer to

[0051] S210: determining the longitudinal distance between the ego vehicle and the target vehicle according to the coordinate information and the size information of the ego vehicle and the coordinate information and the size information of the target vehicle.

[0052] The vehicle information of the ego vehicle includes the coordinate information, the size information and the motion information of the ego vehicle. The coordinate information of the ego vehicle represents the coordinate information of the geometric center of the ego vehicle. Exemplarily, the coordinate information of the ego vehicle can be the position information of the ego vehicle in the Frenet coordinate system established based on the lane center line of the current lane of the ego vehicle. The vehicle avoidance device obtains the positioning coordinate of the ego vehicle from the positioning system of the ego vehicle, the positioning coordinate belonging to the geodetic coordinate system, and then converts the positioning coordinate to the coordinate information in the Frenet coordinate system under the lane center line of the current lane of the ego vehicle. The size information of the ego vehicle includes the body length, the body width and the like of the ego vehicle. The motion information of the ego vehicle includes the speed of the ego vehicle and the like.

[0053] The vehicle information of the target vehicle includes coordinate information, size information and motion information of the target vehicle. The coordinate information of the target vehicle represents the coordinate information of the geometric center of the target vehicle. For example, the coordinate information of the target vehicle can be the position information of the target vehicle in the Frenet coordinate system established by the lane centerline of the current lane of the ego vehicle. The vehicle avoidance device obtains the positioning coordinates of the target vehicle in the geodetic coordinate system from the perception system of the ego vehicle, and then converts the positioning coordinates to the coordinate information in the Frenet coordinate system under the lane centerline of the current lane of the ego vehicle. The size information of the target vehicle includes the length and width of the body of the target vehicle. The motion information of the target vehicle includes the speed of the target vehicle.

[0054] The longitudinal distance can be the distance between the ego vehicle and the target vehicle in the longitudinal direction. For example, when the front of the ego vehicle lags behind the rear of the target vehicle, the longitudinal distance can be the longitudinal distance between the front of the ego vehicle and the rear of the target vehicle; when the front of the target vehicle lags behind the rear of the ego vehicle, the longitudinal distance can be the longitudinal distance between the rear of the ego vehicle and the front of the target vehicle; when the front of the ego vehicle is ahead of the rear of the target vehicle but behind the front of the target vehicle, and the front of the target vehicle is ahead of the rear of the ego vehicle but behind the front of the ego vehicle, the distance between the two can be calculated and then taken as a negative value to obtain the longitudinal distance. In other embodiments, the longitudinal distance between the current ego vehicle and the target vehicle can also be determined by image recognition technology, for example, an image including the target vehicle can be obtained according to the image sensor on the ego vehicle; the image is calibrated to obtain the longitudinal distance between the target vehicle and the ego vehicle in the image.

[0055] For ease of understanding, please refer to Figure 3 , Figure 3 is a structural schematic diagram of vehicle avoidance according to an exemplary embodiment of the present application. In the following description, the ego vehicle is represented by a rectangle, and the target vehicle is represented by a circle. Figure 3In some embodiments, the coordinate system is a Frenet coordinate system with a center line of a current lane where the ego vehicle is located as a reference line. The coordinate information refers to coordinate information of a geometric center of the ego vehicle in the coordinate system. Therefore, coordinate information of a front of the ego vehicle can be determined according to the coordinate information of the ego vehicle and a length of a body of the ego vehicle. As an example, the coordinate information of the ego vehicle includes coordinate values on an x-axis and a y-axis, the y-axis is parallel to the lateral direction, on the y-axis, a value to the right of the center line of the current lane where the ego vehicle is located is negative, and a value to the left of the center line of the current lane where the ego vehicle is located is positive; the x-axis is parallel to the longitudinal direction, and a value of the x-axis is greater along the forward direction. When determining the coordinate information of the front of the ego vehicle, a coordinate value on the y-axis in the coordinate information of the ego vehicle is determined as a coordinate value on the y-axis of the front of the ego vehicle, and a coordinate value on the x-axis of the ego vehicle plus half of the length of the body of the ego vehicle can obtain a coordinate value on the x-axis of the front of the ego vehicle. Based on the same reason, the coordinate information of the rear of the ego vehicle is determined by determining a coordinate value on the y-axis in the coordinate information of the ego vehicle as a coordinate value on the y-axis of the rear of the ego vehicle, and a coordinate value on the x-axis of the ego vehicle minus half of the length of the body of the ego vehicle can obtain a coordinate value on the x-axis of the rear of the ego vehicle; the coordinate information of the front of the target vehicle includes determining a coordinate value on the y-axis in the coordinate information of the target vehicle as a coordinate value on the y-axis of the front of the target vehicle, and a coordinate value on the x-axis of the target vehicle plus half of the length of the body of the target vehicle can obtain a coordinate value on the x-axis of the front of the target vehicle; the coordinate information of the rear of the target vehicle includes determining a coordinate value on the y-axis in the coordinate information of the target vehicle as a coordinate value on the y-axis of the rear of the target vehicle, and a coordinate value on the x-axis of the target vehicle minus half of the length of the body of the target vehicle can obtain a coordinate value on the x-axis of the rear of the target vehicle. Then, a longitudinal distance between the front of the ego vehicle and the rear of the target vehicle is determined according to the coordinate value on the x-axis of the front of the ego vehicle and the coordinate value on the x-axis of the rear of the target vehicle. On this basis, as an example, the coordinate information of the ego vehicle is represented as (s ego ,d ego ), the coordinate information of the target vehicle is represented as (s obj ,d obj ), and the calculation of the longitudinal distance between the ego vehicle and the target vehicle satisfies the following formula:

[0056]

[0057] wherein s obj -0.5*l obj >s ego +0.5*l ego represents that the front of the ego vehicle lags behind the rear of the target vehicle, s obj -0.5*l obj -s ego -0.5*l egorepresents the longitudinal distance between the rear of the target vehicle and the front of the ego vehicle; s obj + 0.5 * 1 obj < s ego - 0.5 * 1 ego represents that the front of the target vehicle lags behind the rear of the ego vehicle, s ego - 0.5 * 1 egi - s obj - 0.5 * 1 obj represents the longitudinal distance between the rear of the ego vehicle and the front of the target vehicle, other represents other cases, min represents taking the minimum value, s ibj + 0.5 * 1 obj - s ego + 0.5 * 1 ego represents the distance between the front of the target vehicle and the rear of the ego vehicle, s ego + 0.5 * 1 ego - s obj - 0.5 * 1 obj represents the distance between the front of the ego vehicle and the front of the target vehicle, and the longitudinal distance in other cases can be obtained by taking the negative value after taking the minimum value among the two distances.

[0058] S220: predicting the longitudinal collision time between the ego vehicle and the target vehicle according to the longitudinal distance between the ego vehicle and the target vehicle, the motion information of the ego vehicle, and the motion information of the target vehicle.

[0059] The longitudinal collision time can be the time when the front of the ego vehicle passes the rear of the target vehicle. Illustratively, when the front of the ego vehicle lags behind the rear of the target vehicle, the longitudinal collision time can be the time when the front of the ego vehicle catches up with the target vehicle and runs parallel to the rear of the target vehicle; when the front of the target vehicle lags behind the front of the ego vehicle or the speed of the target vehicle is greater than the speed of the ego vehicle, the longitudinal collision time can be given a default value. Illustratively, when the front of the ego vehicle lags behind the rear of the target vehicle, the longitudinal collision time can be determined according to the distance between the front of the ego vehicle and the rear of the target vehicle, and the speed of the ego vehicle and the speed of the target vehicle to determine the longitudinal collision time between the ego vehicle and the target vehicle.

[0060] Specifically, the size information includes the body length, and the motion information includes the speed. The step of predicting the longitudinal collision time between the ego vehicle and the target vehicle according to the motion information of the ego vehicle and the target vehicle and the longitudinal distance between the ego vehicle and the target vehicle includes: determining the speed difference between the ego vehicle and the target vehicle according to the speed of the ego vehicle and the speed of the target vehicle; and determining the ratio between the longitudinal distance and the speed difference as the longitudinal collision time between the ego vehicle and the target vehicle. In other embodiments, the vehicle avoidance device can also consider the acceleration of the ego vehicle to determine the speed difference between the ego vehicle and the target vehicle; and then determine the ratio between the longitudinal distance and the speed difference as the longitudinal collision time between the ego vehicle and the target vehicle.

[0061] For example, the coordinate information of the ego vehicle is represented as (s ego ,d ego ), the coordinate information of the target vehicle is represented as (s obj ,d obj ), and the calculation of the longitudinal collision time between the ego vehicle and the target vehicle satisfies the following formula:

[0062]

[0063] wherein TTC represents the longitudinal collision time, 40 represents a default value, s obj +0.5*l obj represents the coordinate value of the front of the target vehicle on the x-axis, s ego -0.5*l ego represents the coordinate value of the rear of the ego vehicle on the x-axis, s obj +0.5*l oboj <s ego -0.5*l ego represents that the rear of the target vehicle lags behind the front of the ego vehicle, v obj represents the speed of the target vehicle, v ego represents the speed of the ego vehicle, other represents other cases, (s obj -0.5*l obj -s ego -0.5*l ego ) / (v ego -v obj ) represents the time for the front of the ego vehicle to catch up with the rear of the target vehicle, s obj -0.5*l obj -s ego -0.5*l ego represents the longitudinal collision distance between the front of the ego vehicle and the rear of the target vehicle.

[0064] After determining the longitudinal time-distance information, it is determined whether there is an avoiding vehicle on the other lane according to the longitudinal time-distance information. Specifically, it is determined whether there is an avoiding vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle; in response to the existence of an avoiding vehicle on the first lane, it is determined whether there is an avoiding vehicle from the target vehicles on the second lane according to the longitudinal distance between each target vehicle and the ego vehicle; and in response to the longitudinal distance of a target vehicle on the second lane being less than a preset longitudinal distance, the corresponding target vehicle is determined as an avoiding vehicle.

[0065] The vehicle avoidance device first determines whether there is an avoidance vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle, and then determines whether there is an avoidance vehicle on the other lane according to the longitudinal distance between each target vehicle and the ego vehicle. In other embodiments, the vehicle avoidance device can first determine whether there is an avoidance vehicle on the other lane according to the longitudinal distance between each target vehicle and the ego vehicle, and then determine whether there is an avoidance vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle. In other embodiments, the vehicle avoidance device can determine whether there is an avoidance vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle, and determine whether there is an avoidance vehicle on the other lane according to the longitudinal distance between each target vehicle and the ego vehicle, respectively, without any sequence.

[0066] In some embodiments, the step of determining whether there is an avoidance vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle can include: determining whether the longitudinal collision time between each target vehicle and the ego vehicle is less than a preset collision time; if yes, determining that there is an avoidance vehicle on the other lane.

[0067] Specifically, for each other lane, the target vehicles are sorted according to the longitudinal collision time from small to large, and the target vehicle ranked first on each other lane is selected as the time target corresponding to the other lane. Then it is determined whether the longitudinal collision time between the time target and the ego vehicle is less than a preset collision time; if yes, it is determined that there is an avoidance vehicle on the other lane. As an example, the other lanes include a first lane and a second lane. For the first lane, the target vehicles on the first lane are sorted according to the longitudinal collision time from small to large, and the target vehicle ranked first is selected as the time target of the first lane. The target vehicle ranked first can be represented as left_obj_ttc1, and the target vehicle ranked first on the second lane can be represented as right_obj_ttc1. Then the target vehicle with the smallest longitudinal collision time is selected from the target vehicle ranked first on the first lane and the target vehicle ranked first on the second lane as the time target. If the longitudinal collision time between the time target and the ego vehicle is less than the preset collision time, the time target is determined as the final avoidance vehicle. The preset collision time can be set to 4 seconds, 5 seconds, etc.

[0068] After determining the evasive vehicles on other lanes according to the longitudinal collision time, lane information of the evasive vehicles is obtained. For example, for each target vehicle on each other lane, the target vehicles are sorted according to the longitudinal distance between each target vehicle and the ego vehicle from small to large, and the first target vehicle in the sorting is selected as the distance target on each other lane. For example, the other lanes include the first lane and the second lane, for the first lane, the first target vehicle in the sorting can be denoted as left_obj_s1, and for the second lane, the first target vehicle in the sorting can be denoted as right_obj_s1.

[0069] For example, if the evasive vehicle is determined to be on the first lane according to the longitudinal collision time, whether there is an evasive vehicle on the second lane is determined according to the longitudinal distance between each target vehicle and the ego vehicle. For example, the longitudinal distance of the first target vehicle in the sorting on the second lane is compared with a preset longitudinal distance, and if the longitudinal distance is less than the preset longitudinal distance, the first target vehicle in the sorting is determined as the evasive vehicle.

[0070] Further, if there is an evasive vehicle, a target evasive distance of the ego vehicle is determined according to the evasive vehicle. In some embodiments, the evasive vehicle includes a first evasive vehicle on the first lane and a second evasive vehicle on the second lane, a first initial evasive distance is determined according to vehicle information of the first evasive vehicle and vehicle information of the ego vehicle, a second initial evasive distance is determined according to vehicle information of the second evasive vehicle, vehicle information of the ego vehicle, and vehicle information of the first evasive vehicle, and the target evasive distance is selected from the first initial evasive distance and the second initial evasive distance according to the size relationship between the first initial evasive distance and the second initial evasive distance.

[0071] The first evasive vehicle on the first lane and the second evasive vehicle on the second lane can be determined according to the longitudinal collision time and the longitudinal distance, respectively. When the first evasive vehicle on the first lane is determined according to the longitudinal collision time, the second evasive vehicle on the second lane is determined according to the longitudinal distance; when the first evasive vehicle on the first lane is determined according to the longitudinal collision time, the second evasive vehicle on the second lane is determined according to the longitudinal distance.

[0072] Taking the first vehicle in the first lane, whose distance is determined by longitudinal collision time, and the second vehicle in the second lane, whose distance is determined by longitudinal distance, as an example, the vehicle avoidance device first determines the first initial avoidance distance based on the vehicle information of the first avoidance vehicle and the vehicle information of the vehicle itself. Specifically, the lateral distance between the first avoidance vehicle and the vehicle itself is obtained, and the sum of the lateral distance and the preset avoidance distance is used as the first initial avoidance distance. Specifically, the distance between the target boundary of the first avoidance vehicle and the center line of the vehicle's lane is determined based on the vehicle information of the first avoidance vehicle and the vehicle information of the vehicle itself. The target boundary represents the boundary of the first avoidance vehicle closest to the vehicle itself; the distance difference between this distance and the first preset safety distance is calculated; and the sum of the distance difference and the preset avoidance distance is used as the first initial avoidance distance. Please continue reading. Figure 3 When the first lane is the left lane of the current lane of the vehicle, the target boundary of the first vehicle to avoid is the right boundary of the first vehicle to avoid; calculate the distance between the right boundary of the first vehicle to avoid and the center line of the current lane; the first preset safety distance can be the sum of half the width of the current lane and the first preset danger distance. Figure 3 In the middle, the first vehicle to give way was Figure 3 The target vehicle in the image, the coordinates of the first vehicle to avoid it are represented as (s obj ,d obj The distance between the right edge of the first vehicle's body and the lane centerline of the vehicle being avoided can be calculated by subtracting half the vehicle's width w from the y-axis coordinate of the first vehicle being avoided. obj The value of d, that is, d obj -0.5*w obj The first preset danger distance is denoted as d. threat The first preset safe distance is the first preset danger distance plus half the lane width, which is d. threat +0.5*w lane Then, the difference between the distance between the target boundary of the first avoidance vehicle and the lane centerline of the own vehicle and the first preset safety distance is calculated. This difference represents the intrusion distance of the first avoidance vehicle. Adding the preset avoidance distance to this difference determines the first avoidance distance. For example, the calculation of the first avoidance distance satisfies the following formula:

[0073] d desired =-0.2-(d threat +0.5*w lane )+(d obj -0.5*w obj )

[0074] Where, d desired d represents the first avoidance distance, 0.2 represents the preset avoidance distance. threat w represents the first preset danger distance. lanelane width of the current lane, d obj a coordinate value on the y-axis in the coordinate information of the first avoiding vehicle, i.e., a lateral distance between the geometric center of the first avoiding vehicle and the lane center line of the current lane where the ego vehicle is located, d threat + 0.5 * w lane a first preset safety distance.

[0075] After determining the first initial avoiding distance, if there is a second avoiding vehicle, the vehicle avoiding device needs to determine a second initial avoiding distance according to the vehicle information of the second avoiding vehicle, the vehicle information of the ego vehicle and the vehicle information of the first avoiding vehicle; and select a target avoiding distance from the first initial avoiding distance and the second initial avoiding distance according to the size relationship between the first initial avoiding distance and the second initial avoiding distance. Specifically, the second initial avoiding distance can be determined according to the lateral distance between the first avoiding vehicle and the ego vehicle and the lateral distance between the second avoiding vehicle and the ego vehicle. As an example, the second initial avoiding distance can be the average value between the lateral distance corresponding to the first avoiding vehicle and the lateral distance corresponding to the second avoiding vehicle.

[0076] After determining the first initial avoiding distance and the second initial avoiding distance, the target avoiding distance is selected from the first initial avoiding distance and the second initial avoiding distance. For example, the largest distance can be selected as the target avoiding distance; and the ego vehicle is controlled to perform avoiding processing at the target avoiding distance.

[0077] Finally, in order to facilitate understanding, a comprehensive embodiment is used to elaborate the vehicle avoiding method applied in the present application, and the details are as follows:

[0078] The other lanes include a left lane located on the left side of the current lane where the ego vehicle is located and a right lane located on the right side of the current lane where the ego vehicle is located. The coordinates of the ego vehicle are represented as (s ego ,d ego ), the length of the body of the ego vehicle is represented as l ego , the width of the body of the ego vehicle is represented as w ego , the speed of the ego vehicle is represented as v ego , the coordinates of the target vehicle are represented as (s obj ,d obj ), the length of the body of the target vehicle is represented as l obj , the width of the body of the target vehicle is represented as w obj , the speed of the target vehicle is represented as v obj , a first preset dangerous distance is represented as d threat , a second preset dangerous distance is represented as d safe , a lane width is represented as w lane . It should be noted that for the coordinate value d objIn other words, a positive value is on the left of the lane centerline of the current lane of the ego vehicle, and a negative value is on the right of the lane centerline of the current lane of the ego vehicle.

[0079] First, other vehicles on the left and right lanes are screened and sorted in longitudinal collision time. The left lane and the right lane are screened to obtain target vehicles, and the longitudinal collision time between each target vehicle on the left lane and the right lane and the ego vehicle is calculated.

[0080] The screening process can be that the vehicle whose lateral distance between the ego vehicle and the other vehicle is less than the first preset safety distance is the target vehicle. Since the left lane and the right lane have positive and negative, for other vehicles on the left lane, the screening formula satisfies the following formula:

[0081] d obj -0.5*w obj <d threat +0.5*w lane

[0082] For other vehicles on the right lane, the screening formula satisfies the following formula:

[0083] d obj +0.5*w obj >-(d threat +0.5*w lane )

[0084] The expected avoidance distance of the ego vehicle relative to each target vehicle is calculated. For target vehicles on the left lane, the expected avoidance distance formula satisfies the following formula:

[0085] d desired =-0.2-(d threat +0.5*w lane )+(d obj -0.5*w obj )

[0086] For other vehicles on the right lane, the expected avoidance distance formula satisfies the following formula:

[0087] d desired =0.2+d threat +0.5*w labe +(d obj -0.5*w obj )

[0088] After obtaining the target vehicle, the longitudinal collision time between the ego vehicle and the target vehicle is determined according to the vehicle information of the target vehicle and the vehicle information of the ego vehicle; and the target vehicles on the left lane and the right lane are sorted in ascending order of the longitudinal collision time, to obtain a first target vehicle on the left lane, denoted as left_obj_ttc1, and a second target vehicle on the left lane, denoted as left_obj_ttc2; a first target vehicle on the right lane, denoted as right_obj_ttc1, and a second target vehicle on the right lane, denoted as right_obj_ttc2.

[0089] Then, other vehicles on the left lane and the right lane are screened and sorted in longitudinal distance. The left lane and the right lane are screened to obtain the target vehicles; and the longitudinal distances between the target vehicles on the left lane and the right lane and the ego vehicle are calculated.

[0090] In the determination of the longitudinal distance, the screening manner can be that a vehicle whose transverse distance between the ego vehicle and the vehicle is less than a second preset safety distance is taken as the target vehicle. Since the left lane and the right lane have positive and negative, for other vehicles on the left lane, the screening formula satisfies the following formula:

[0091] d obj -0.5*w obj <d safe +0.5*w lane

[0092] For other vehicles on the right lane, the screening formula satisfies the following formula:

[0093] d obj +0.5*w obj >-(d safe +0.5*w lane )

[0094] The longitudinal distance of the ego vehicle relative to each target vehicle is calculated. For the target vehicles on the left lane, the formula of the longitudinal distance satisfies the following formula:

[0095]

[0096] For the target vehicles on the right lane, the formula of the longitudinal distance satisfies the following formula:

[0097]

[0098] After obtaining the target vehicle, a longitudinal distance between the ego vehicle and the target vehicle is determined according to vehicle information of the target vehicle and vehicle information of the ego vehicle; and target vehicles on the left lane and the right lane are respectively sorted in ascending order of the longitudinal distance, to obtain a first target vehicle on the left lane, denoted as left_obj_s1, and a second target vehicle on the left lane, denoted as left_obj_s2; a first target vehicle on the right lane, denoted as right_obj_s1, and a second target vehicle on the right lane, denoted as right_obj_s2.

[0099] To improve the safety of vehicle avoidance, multiple potential avoidance targets can be considered simultaneously. Thus, the expected avoidance distance of the target vehicle on the same lane needs to be adjusted to obtain a target expected avoidance distance. If the time difference between the longitudinal collision time corresponding to left_obj_ttc1 and the longitudinal collision time corresponding to left_obj_ttc2 on the left lane is less than a preset time difference, for example, 4s. For other vehicles on the left lane, the ego vehicle is to avoid to the right, and the avoidance to the right is negative, so the expected avoidance distance with the minimum expected avoidance distance is selected from left_obj_ttc1 and left_obj_ttc2 as the first adjusted expected avoidance distance of the two, that is, the value with the maximum absolute value of the expected avoidance distance. Exemplarily, the formula satisfies the following formula:

[0100]

[0101] wherein, left_obj_ttc1 represents the first adjusted expected avoidance distance of left_obj_ttc1, left_obj_ttc2 represents the first adjusted expected avoidance distance of left_obj_ttc2, left_obj_ttc1 represents the expected avoidance distance of left_obj_ttc1, left_obj_ttc2 represents the expected avoidance distance of left_obj_ttc2.

[0102] If the time difference between the longitudinal collision time corresponding to right_obj_ttc1 and the longitudinal collision time corresponding to right_obj_ttc2 on the right lane is less than a preset time difference, for example, 4s. For other vehicles on the right lane, the ego vehicle is to avoid to the left, and the avoidance to the left is positive, so the expected avoidance distance with the maximum expected avoidance distance is selected from right_obj_ttc1 and right_obj_ttc2 as the first adjusted expected avoidance distance of the two, that is, the value with the maximum absolute value of the expected avoidance distance. Exemplarily, the formula satisfies the following formula:

[0103]

[0104] wherein the left side of the equation represents the desired evasion distance of right_obj_ttc1 after the first adjustment, and the right side of the equation represents the desired evasion distance of right_obj_ttc2 after the first adjustment, and the right side of the equation represents the desired evasion distance of right_obj_ttc1. represents the desired evasion distance of right_obj_ttc2.

[0105] Finally, the longitudinal collision time of left_obj_ttc1 on the left lane and right_obj_ttc1 on the right lane are compared, and if the time difference between the longitudinal collision time corresponding to left_obj_ttc1 on the left lane and the longitudinal collision time corresponding to right_obj_ttc1 on the right lane is less than a preset time difference, for example, 4s, the target desired evasion distance is determined according to the desired evasion distance of left_obj_ttc1 after the first adjustment and the desired evasion distance of right_obj_ttc1 after the first adjustment. Exemplarily, the formula satisfies the following formula:

[0106]

[0107] wherein the left side of the equation represents the target desired evasion distance of left_obj_ttc1, and the left side of the equation represents the target desired evasion distance of right_obj_ttc1, and the right side of the equation represents the desired evasion distance of left_obj_ttc1 after the first adjustment, and the right side of the equation represents the desired evasion distance of right_obj_ttc1 after the first adjustment.

[0108] If the time difference between the longitudinal collision time corresponding to left_obj_ttc1 on the left lane and the longitudinal collision time corresponding to right_obj_ttc1 on the right lane is greater than or equal to the preset time difference, the target desired evasion distance of the corresponding target vehicle is directly determined as the desired evasion distance after the first adjustment.

[0109] The vehicle evasion device selects the target with the smallest longitudinal collision time from the target vehicle left_obj_ttc1 with the first longitudinal collision time on the left lane and the target vehicle right_obj_ttc1 with the first longitudinal collision time on the right lane as the time target. There are two cases as follows:

[0110] If the longitudinal collision time TTCleft_obj_ttc1 Longitudinal Time to Collision (TTC) of right_obj_ttc1 right_obj_ttc1 i.e. TTC left_obj_ttc1 < TTC right_obj_ttc1 If the time target is left_obj_ttc1, then determine whether the first ranked target vehicle right_obj_s1 in the right lane is less than the preset longitudinal distance, if yes, then the target evasion distance is calculated as follows:

[0111]

[0112] wherein, denotes the target evasion distance, denotes the target expected evasion distance of left_obj_ttc1, denotes the coordinate value of left_obj_ttc1 on the y-axis, denotes the body width of left_obj_ttc1, denotes the coordinate value of right_obj_s1 on the y-axis, denotes the body width of right_obj_s1.

[0113] If the longitudinal Time to Collision (TTC) of left_obj_ttc1 left_obj_stc1 is greater than the longitudinal Time to Collision (TTC) of right_obj_ttc1 right _obj_ttc1 i.e. TTC left_obj_ttc1 > TTC right_obj_ttc1 If the time target is right_obj_ttc1, then determine whether the first ranked target vehicle left_obj_s1 in the left lane is less than the preset longitudinal distance, if yes, then the target evasion distance is calculated as follows:

[0114]

[0115] wherein, denotes the target evasion distance, denotes the target expected evasion distance of right_obj_ttc1, denotes the coordinate value of right_obj_ttc1 on the y-axis, denotes the body width of right_obj_ttc1, denotes the coordinate value of left_obj_s1 on the y-axis, denotes the body width of left_obj_s1.

[0116] If the longitudinal collision time of the time target is less than the preset collision time, the time target is regarded as an avoidance target vehicle, and the ego vehicle is controlled to perform avoidance processing according to the target avoidance distance. In other embodiments, it can also be determined whether the longitudinal collision time of the time target is less than the preset collision time. If yes, the time target is regarded as a first avoidance target vehicle, and the target expected avoidance distance corresponding to the first avoidance target vehicle is a first initial avoidance distance. Then, a target vehicle with the first longitudinal distance on another lane is regarded as a second avoidance target vehicle, and a second initial avoidance distance is determined according to the first avoidance target vehicle and the second avoidance target vehicle. The target avoidance distance is determined according to the first initial avoidance distance and the second initial avoidance distance.

[0117] Referring to Figure 4 , Figure 4 is a structural schematic diagram of an exemplary embodiment of a vehicle avoidance device shown in the present application. The vehicle avoidance device 400 comprises a first acquisition module 410, a second acquisition module 420, a first determination module 430, a second determination module 440, a third determination module 450, and an avoidance module 460. The first acquisition module 410 is configured to acquire vehicle information of the ego vehicle, wherein the vehicle information comprises current lane information of the ego vehicle and current position information of the ego vehicle on the current lane. The second acquisition module 420 is configured to acquire vehicle information of other vehicles on other lanes adjacent to the current lane according to the current lane information and the current position. The first determination module 430 is configured to, in response to the existence of a target vehicle on the other lane and the transverse distance between the target vehicle and the ego vehicle being less than a preset transverse distance, determine longitudinal time-distance information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle. The transverse direction is perpendicular to the longitudinal direction, and the longitudinal direction is parallel to the driving direction of the ego vehicle. The second determination module 440 is configured to determine whether there is an avoidance target vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle. The third determination module 450 is configured to, in response to the existence of the avoidance target vehicle, determine a target avoidance distance of the ego vehicle relative to the avoidance target vehicle according to the vehicle information of the avoidance target vehicle and the vehicle information of the ego vehicle. The avoidance module 460 is configured to control the ego vehicle to perform avoidance processing according to the target avoidance distance.

[0118] According to the scheme, the vehicle avoidance device provided in the embodiment of the present application acquires vehicle information of the ego vehicle, the vehicle information including current lane information of the ego vehicle and current position information of the ego vehicle on the current lane; acquires vehicle information of other vehicles on other lanes adjacent to the current lane according to the current lane information and the current position; in response to the fact that a target vehicle exists on the other lane and the lateral distance between the target vehicle and the ego vehicle is less than a preset lateral distance, determines longitudinal time-distance information between the ego vehicle and the target vehicle according to the vehicle information of the ego vehicle and the vehicle information of the target vehicle, the lateral direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to the driving direction of the ego vehicle. In this way, it is ensured that the vehicle avoidance is started only when the vehicle on the other lane approaches the ego vehicle, and the calculation burden is reduced. Then, it is determined whether there is an avoidance vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle; in response to the fact that there is an avoidance vehicle, determines a target avoidance distance of the ego vehicle relative to the avoidance vehicle according to the vehicle information of the avoidance vehicle and the vehicle information of the ego vehicle; and controls the ego vehicle to perform avoidance processing according to the target avoidance distance. In this way, the target vehicle on the other lane that approaches the ego vehicle is all subjected to avoidance judgment through the longitudinal time-distance information, the spatial relationship between the ego vehicle and other vehicles is considered as a whole, the accuracy of the target avoidance distance is ensured, and the safety of the vehicle avoidance is improved.

[0119] The functions of the modules can be referred to the vehicle avoidance method embodiments, and will not be described herein.

[0120] To implement the vehicle avoidance method of the above embodiments, the present application provides another electronic device, which can be referred to Figure 5 , Figure 5 is a structural schematic diagram of an embodiment of the electronic device provided in the present application.

[0121] The electronic device 500 includes a memory 510 and a processor 520, wherein the memory 510 and the processor 520 are coupled.

[0122] The memory 510 is configured to store program data, and the processor 520 is configured to execute the program data to implement the vehicle avoidance method of the above embodiments.

[0123] In this embodiment, the processor 520 can also be referred to as a CPU (Central Processing Unit). The processor 520 can be an integrated circuit chip having a processing capability of signals. The processor 520 can also be a general-purpose processor, a digital signal processor (DSP), an ASIC (Application-Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor 520 can also be any conventional processor.

[0124] The present application also provides a computer readable storage medium, such as Figure 6 As shown, the computer readable storage medium 600 is used to store program data 610, which when executed by a processor, is used to implement a vehicle avoidance method as in the method embodiments of the present application.

[0125] The method involved in the vehicle avoidance method embodiments of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the whole or part of the technical solutions that make a contribution to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0126] The above only describes the embodiments of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle evasion method characterized by, The vehicle avoidance method comprises: obtaining vehicle information of a host vehicle, the vehicle information comprising current lane information and current position information of the host vehicle in a current lane; obtaining vehicle information of other vehicles in other lanes adjacent to the current lane according to the current lane information and the current position information; in response to a transverse distance between the host vehicle and a target vehicle in the other lanes being less than a preset transverse distance, determining longitudinal time-distance information between the host vehicle and the target vehicle according to the vehicle information of the host vehicle and the vehicle information of the target vehicle, the transverse direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to a driving direction of the host vehicle; determining whether there is an avoidance vehicle in the other lanes according to the longitudinal time-distance information between the target vehicle and the host vehicle; in response to the avoidance vehicle existing, determining a target avoidance distance of the host vehicle relative to the avoidance vehicle according to the vehicle information of the avoidance vehicle and the vehicle information of the host vehicle; controlling the host vehicle to perform avoidance processing according to the target avoidance distance. The other lanes comprise a first lane and a second lane, the longitudinal time-distance information comprises longitudinal collision time and longitudinal distance, the avoidance vehicle comprises a first avoidance vehicle and a second avoidance vehicle, and the step of determining whether there is an avoidance vehicle in the other lanes according to the longitudinal time-distance information between the target vehicle and the host vehicle comprises: determining whether there is an avoidance vehicle in the first lane according to the longitudinal collision time between each target vehicle and the host vehicle; in response to the avoidance vehicle existing in the first lane, determining whether there is an avoidance vehicle in the second lane according to the longitudinal distance between each target vehicle and the host vehicle; in response to a target vehicle existing in the second lane and a longitudinal distance of the target vehicle being less than a preset longitudinal distance, determining the corresponding target vehicle as the avoidance vehicle.

2. The vehicle evasion method according to claim 1, characterized by, The longitudinal time-distance information comprises longitudinal distance and longitudinal collision time, the vehicle information comprises coordinate information, size information and motion information of the vehicle, and the step of determining the longitudinal time-distance information between the host vehicle and the target vehicle according to the vehicle information of the host vehicle and the vehicle information of the target vehicle comprises: determining the longitudinal distance between the host vehicle and the target vehicle according to the coordinate information and the size information of the host vehicle and the coordinate information and the size information of the target vehicle; predicting the longitudinal collision time of the host vehicle and the target vehicle according to the longitudinal distance between the host vehicle and the target vehicle, the motion information of the host vehicle and the motion information of the target vehicle.

3. The vehicle evasion method according to claim 2, characterized by, The size information comprises a vehicle body length, the motion information comprises a speed, and the step of predicting the longitudinal collision time of the host vehicle and the target vehicle according to the longitudinal distance between the host vehicle and the target vehicle, the motion information of the host vehicle and the motion information of the target vehicle comprises: determining a speed difference between the host vehicle and the target vehicle according to the speed of the host vehicle and the speed of the target vehicle; determining a ratio between the longitudinal distance and the speed difference as the longitudinal collision time of the host vehicle and the target vehicle.

4. The vehicle evasion method according to claim 1, characterized by, The step of determining whether there is an evading vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle comprises: determining whether the longitudinal collision time between each target vehicle and the ego vehicle is less than a preset collision time; if yes, determining that there is an evading vehicle on the other lane.

5. The vehicle evasion method according to claim 1, characterized by, The other lane comprises a first lane and a second lane, the evading vehicle comprises a first evading vehicle located in the first lane and a second evading vehicle located in the second lane, and the step of determining a target evading distance of the ego vehicle relative to the evading vehicle according to vehicle information of the evading vehicle and vehicle information of the ego vehicle comprises: determining a first initial evading distance according to vehicle information of the first evading vehicle and vehicle information of the ego vehicle; determining a second initial evading distance according to vehicle information of the second evading vehicle, vehicle information of the ego vehicle and vehicle information of the first evading vehicle; selecting the target evading distance from the first initial evading distance and the second initial evading distance according to the size relationship between the first initial evading distance and the second initial evading distance.

6. The vehicle evasion method according to claim 5, characterized by, The current lane information comprises a lane center line, and the step of determining a first initial evading distance according to vehicle information of the first evading vehicle and vehicle information of the ego vehicle comprises: determining a distance between a target boundary of a vehicle body of the first evading vehicle and a lane center line of the ego vehicle according to vehicle information of the first evading vehicle and vehicle information of the ego vehicle, the target boundary of the vehicle body representing a boundary of the vehicle body of the first evading vehicle close to the ego vehicle; calculating a distance difference value between the distance and a first preset safety distance; determining a sum of the distance difference value and a preset evading distance as the first initial evading distance.

7. A vehicle avoidance apparatus characterized by, The device comprises: a first obtaining module configured to obtain vehicle information of an ego vehicle, the vehicle information comprising current lane information of the ego vehicle and current position information of the ego vehicle on the current lane; a second obtaining module configured to obtain vehicle information of other vehicles on other lanes adjacent to the current lane according to the current lane information and the current position; a first determining module configured to, in response to a target vehicle existing on the other lane and a transverse distance between the target vehicle and the ego vehicle being less than a preset transverse distance, determine longitudinal time-distance information between the ego vehicle and the target vehicle according to vehicle information of the ego vehicle and vehicle information of the target vehicle, the transverse direction being perpendicular to the longitudinal direction, and the longitudinal direction being parallel to a driving direction of the ego vehicle; The second determining module is configured to determine whether there is an evading vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle; the other lane includes a first lane and a second lane, the longitudinal time-distance information includes a longitudinal collision time and a longitudinal distance, the evading vehicle includes a first evading vehicle and a second evading vehicle, and the step of determining whether there is an evading vehicle in the other lane according to the longitudinal time-distance information between the target vehicle and the ego vehicle includes: determining whether there is an evading vehicle on the other lane according to the longitudinal collision time between each target vehicle and the ego vehicle; in response to the existence of an evading vehicle on the first lane, determining whether there is an evading vehicle from the target vehicles on the second lane according to the longitudinal distance between each target vehicle and the ego vehicle; and in response to the longitudinal distance of a target vehicle on the second lane being less than a preset longitudinal distance, determining the corresponding target vehicle as an evading vehicle; The third determining module is configured to, in response to the existence of the evading vehicle, determine a target evading distance of the ego vehicle relative to the evading vehicle according to vehicle information of the evading vehicle and vehicle information of the ego vehicle; The evading module is configured to control the ego vehicle to perform evading processing according to the target evading distance.

8. An electronic device, comprising: The method comprises: A memory and a processor, wherein the memory stores program instructions, and the processor fetches the program instructions from the memory to execute the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The program data is stored in the memory and is executed by the processor to implement the method according to any one of claims 1-6. ​

Images