Intelligent vehicle active obstacle avoidance control method and device, storage medium, and terminal

Abstract

A method and device for active obstacle avoidance control of an intelligent vehicle, a storage medium, and a terminal, the method comprising: obtaining status information of the vehicle and the status information of each traffic participant around the vehicle; estimating the risk posed by each traffic participant to the vehicle based on the status information of the vehicle and the status information of each traffic participant; determining whether there is a front obstacle in the current lane within a preset driving risk range based on the risk posed by each traffic participant to the vehicle; and, if there is a front obstacle, determining an obstacle avoidance strategy based on the relationship between the risk posed by each traffic participant to the vehicle and a braking obstacle avoidance risk threshold and a lane-changing obstacle avoidance risk threshold, and executing an obstacle avoidance operation corresponding to the determined obstacle avoidance strategy, wherein the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are both related to the status information of the vehicle and each traffic participant. The above-described scheme can improve the efficiency of determining the vehicle's active obstacle avoidance strategy and enhance driving safety.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of vehicle control, and in particular to a method and device, a storage medium, and a terminal for active obstacle avoidance control of an intelligent vehicle. Background Art

[0002] Obstacle avoidance is a key component of a vehicle's active safety system and an essential feature in autonomous driving. Currently, active obstacle avoidance technology primarily relies on information about the longitudinal relative motion between the controlled vehicle and obstacles ahead to determine the probability of a rear-end collision and implements linear braking to avoid the obstacle.

[0003] However, due to the real-time changing characteristics of the road environment, traffic conditions and other external factors in which the vehicle is located, this method is difficult to systematically consider the real-time changes of multiple traffic elements and their impacts in the complex traffic system composed of people, vehicles and roads, which affects the efficiency of determining the vehicle's obstacle avoidance strategy and may affect driving safety. Summary of the Invention

[0004] The technical problem solved by the embodiments of the present invention is how to improve the efficiency of determining a vehicle obstacle avoidance strategy and improve driving safety.

[0005] To solve the above technical problems, an embodiment of the present invention provides an active obstacle avoidance control method for an intelligent vehicle, comprising: obtaining status information of the vehicle and status information of each traffic participant around the vehicle, the status information including position information and motion information; estimating the risk posed to the vehicle by each traffic participant based on the status information of the vehicle and the status information of each traffic participant; judging whether there is a front obstacle in front of the current lane within a preset driving risk range based on the risk posed to the vehicle by each traffic participant, the current lane referring to the lane where the vehicle is currently located; when the front obstacle exists, determining an obstacle avoidance strategy based on the relationship between the risk posed to the vehicle by each traffic participant and a braking obstacle avoidance risk threshold and a lane changing obstacle avoidance risk threshold, and executing obstacle avoidance operations corresponding to the determined obstacle avoidance strategy, wherein the braking obstacle avoidance risk threshold and the lane changing obstacle avoidance risk threshold are both related to the status information of the vehicle and each traffic participant.

[0006] Optionally, estimating the risk posed to the vehicle by each traffic participant based on the vehicle's status information and the status information of each traffic participant includes: estimating the risk posed to the vehicle by each traffic participant using an equivalent dynamic model based on the vehicle's status information and the status information of each traffic participant.

[0007] Optionally, the use of an equivalent force model to estimate the risk posed by each traffic participant to the vehicle includes: estimating the equivalent force posed by each traffic participant on the vehicle based on the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle, and using the estimated equivalent force as the risk posed by each traffic participant to the vehicle.

[0008] Optionally, the use of an equivalent force model to estimate the risk posed by each traffic participant to the vehicle includes: estimating the equivalent force posed by each traffic participant to the vehicle based on the risk focus range, the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle, and using the estimated equivalent force as the risk posed by each traffic participant to the vehicle.

[0009] Optionally, the relative distance between each traffic participant and the vehicle is the relative distance after the actual relative distance between each traffic participant and the vehicle is adjusted using a first gradient adjustment coefficient. The first gradient adjustment coefficient is used to adjust the driving risk range. The first gradient adjustment coefficient is related to the relative distance between the vehicle and each traffic participant, the speed of the vehicle, and the speed of each traffic participant.

[0010] Optionally, the relative distance between each traffic participant and the vehicle is the relative distance after adjusting the actual relative distance between each traffic participant and the vehicle using a first gradient adjustment coefficient and a second gradient adjustment coefficient. The second gradient adjustment coefficient is used to adjust the driving risk range. The second gradient adjustment coefficient is related to the lane line width and / or the length of the vehicle.

[0011] Optionally, the braking obstacle avoidance risk threshold is calculated as follows: when the speed of the obstacle in front is less than the speed of the vehicle, the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the obstacle in front when the vehicle decelerates and brakes to avoid the obstacle at the maximum deceleration and does not collide with the obstacle in front is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the braking obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the obstacle in front reaches the braking obstacle avoidance safety distance threshold, braking obstacle avoidance is performed, and the risk of the obstacle in front to the vehicle at the start of braking is calculated based on the status information of the obstacle in front and the status information of the vehicle at the start of braking, and the calculated risk is used as the braking obstacle avoidance risk threshold, wherein the longitudinal direction refers to the extension direction of the current lane.

[0012] Optionally, the lane change obstacle avoidance risk threshold includes at least: a lane change obstacle avoidance leading vehicle risk threshold, a lane change obstacle avoidance target lane rear vehicle risk threshold, and a lane change obstacle avoidance target lane leading vehicle risk threshold.

[0013] Optionally, the lane change obstacle avoidance leading vehicle risk threshold is calculated in the following manner: the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the leading obstacle when the vehicle accelerates at the maximum lateral acceleration to perform lane change obstacle avoidance and does not collide with the leading obstacle is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the first lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the leading obstacle reaches the first lane change obstacle avoidance safety distance threshold, lane change obstacle avoidance is performed, and the risk of the leading obstacle to the vehicle at the start of the lane change is calculated based on the status information of the leading obstacle and the status information of the vehicle at the start of the lane change, and the calculated risk is used as the lane change obstacle avoidance leading vehicle risk threshold, wherein the longitudinal refers to the extension direction of the current lane.

[0014] Optionally, the calculation of the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the obstacle in front when the vehicle accelerates at the maximum lateral acceleration to perform lane change and avoids obstacle and does not collide with the obstacle in front includes: calculating the collision moment when the vehicle collides with the obstacle in front during the lane change process based on the lateral displacement of the vehicle, the mass of the vehicle and the maximum tire force along the lateral direction, the lateral displacement being the lateral displacement of the vehicle when the vehicle collides with the obstacle in front; calculating the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the obstacle in front based on the start time of the lane change, the speed of the vehicle, the speed of the obstacle in front, the acceleration of the vehicle, the acceleration / deceleration of the obstacle in front and the collision moment, wherein the lateral direction refers to the direction perpendicular to the extension direction of the current lane.

[0015] Optionally, the risk threshold for the vehicle behind the target lane for lane change and obstacle avoidance is calculated in the following manner: the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the vehicle behind the target lane when the vehicle performs lane change and obstacle avoidance at the maximum longitudinal acceleration and does not collide with the vehicle behind the target lane is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the second lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the vehicle behind the target lane reaches the second lane change obstacle avoidance safety distance, lane change and obstacle avoidance are performed, and the risk posed by the vehicle behind the target lane to the vehicle is calculated based on the status information of the vehicle at the start of the lane change and the status information of the vehicle behind the target lane, and the calculated risk is used as the risk threshold for the vehicle behind the target lane for lane change and obstacle avoidance, wherein the longitudinal direction refers to the extension direction of the current lane.

[0016] Optionally, the calculation of the longitudinal relative distance that the vehicle needs to maintain with the vehicle behind the target lane when the vehicle performs lane change obstacle avoidance at maximum longitudinal acceleration and does not collide with the vehicle behind the target lane includes: calculating the shortest time of the lane change process based on the lateral distance between the center lines of the current lane and the target lane, the mass of the vehicle and the maximum tire force of the vehicle in the lateral direction; calculating the longitudinal relative distance that the vehicle needs to maintain with the vehicle behind the target lane based on the start time of the lane change, the speed of the vehicle, the speed of the vehicle behind the target lane, the shortest time, the acceleration of the vehicle and the acceleration / deceleration of the vehicle behind the target lane, wherein the lateral direction refers to the direction perpendicular to the extension direction of the current lane.

[0017] Optionally, the risk threshold of the vehicle in front of the target lane for lane change and obstacle avoidance is calculated as follows: when the speed of the vehicle in front of the target lane is greater than the speed of the obstacle ahead and less than the speed of the vehicle, the longitudinal relative distance that the vehicle and the vehicle in front of the target lane need to maintain when the vehicle performs lane change and obstacle avoidance at the maximum longitudinal deceleration and does not collide with the vehicle in front of the target lane is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the third lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the vehicle in front of the target lane reaches the third lane change obstacle avoidance safety distance threshold, lane change and obstacle avoidance are performed, and the risk of the vehicle in front of the target lane to the vehicle at the start of the lane change is calculated based on the status information of the vehicle and the status information of the vehicle in front of the target lane at the start of the lane change, and the calculated risk is used as the risk threshold of the vehicle in front of the target lane for lane change and obstacle avoidance, wherein the longitudinal direction refers to the extension direction of the current lane.

[0018] Optionally, the calculation of the longitudinal relative distance that the vehicle needs to maintain with the vehicle in front of the target lane when the vehicle performs lane change and obstacle avoidance at the maximum longitudinal deceleration and does not collide with the vehicle in front of the target lane includes: calculating the shortest time of the lane change process based on the lateral distance between the center lines of the current lane and the target lane, the mass of the vehicle and the maximum tire force of the vehicle in the lateral direction; calculating the longitudinal relative distance that the vehicle needs to maintain with the vehicle in front of the target lane based on the start time of lane change and obstacle avoidance, the speed of the vehicle, the speed of the vehicle in front of the target lane, the shortest time, the deceleration of the vehicle and the acceleration / deceleration of the vehicle in front of the target lane, wherein the lateral direction refers to the direction perpendicular to the extension direction of the current lane.

[0019] Optionally, when the obstacle ahead exists, an obstacle avoidance strategy is determined based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold, including: judging whether the risk posed to the vehicle by the obstacle ahead is greater than a first critical risk threshold, the first critical risk threshold is related to the braking obstacle avoidance risk threshold and is less than the braking obstacle avoidance risk threshold; if the risk posed to the vehicle by the obstacle ahead is greater than the first critical risk threshold, determining the type of the obstacle ahead according to the motion state of the obstacle ahead, the types of the obstacle ahead including: static obstacles and dynamic obstacles; determining the obstacle avoidance strategy based on the type of the obstacle ahead, the risk posed to the vehicle by each traffic participant, the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold.

[0020] Optionally, the obstacle avoidance strategy is determined based on the relationship between the type of the obstacle ahead, the risk posed to the vehicle by each traffic participant, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold, including: when the type of the obstacle ahead is a dynamic obstacle, judging whether the risk posed to the vehicle by the obstacle ahead is greater than a second critical risk threshold, the second critical risk threshold is related to the braking obstacle avoidance risk threshold, and is between the first critical risk threshold and the braking obstacle avoidance risk threshold; if the risk posed to the vehicle by the obstacle ahead is not greater than the second critical risk threshold, determining the deceleration based on the status information of the vehicle and the status information of the obstacle ahead, and controlling the vehicle to decelerate and cruise after following the vehicle based on the determined deceleration.

[0021] Optionally, the intelligent vehicle active obstacle avoidance control method further includes: if the risk posed by the front obstacle to the vehicle is greater than the second critical risk threshold, determining whether the risk posed by the front obstacle to the vehicle is greater than the braking obstacle avoidance risk threshold; if the risk posed by the front obstacle to the vehicle is not greater than the braking obstacle avoidance risk threshold, determining the deceleration based on the status information of the vehicle and the status information of the front obstacle, and controlling the vehicle to decelerate until it stops according to the determined deceleration.

[0022] Optionally, the intelligent vehicle active obstacle avoidance control method further includes: if the risk posed by the front obstacle to the vehicle is greater than the braking obstacle avoidance risk threshold, judging whether the lane changing conditions are met based on the risk of traffic participants in adjacent lanes to the vehicle, the risk of the front obstacle and the lane changing obstacle avoidance risk threshold; if the lane changing conditions are met, executing lane changing obstacle avoidance; if the lane changing conditions are not met, controlling the vehicle to decelerate at the maximum deceleration until it stops.

[0023] Optionally, the obstacle avoidance strategy is determined based on the relationship between the type of the obstacle ahead, the risk posed to the vehicle by each traffic participant, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold, including: when the type of the obstacle ahead is a static obstacle, judging whether the lane change condition is met based on the risk of the vehicle posed by traffic participants in an adjacent lane, the risk of the obstacle ahead, and the lane change obstacle avoidance risk threshold; if the lane change condition is met, executing lane change obstacle avoidance; if the lane change condition is not met, determining the deceleration based on the status information of the vehicle and the status information of the obstacle ahead, and controlling the vehicle to decelerate until it stops according to the determined deceleration.

[0024] Optionally, the lane change obstacle avoidance risk threshold includes: a lane change obstacle avoidance front vehicle risk threshold, a lane change obstacle avoidance target lane rear vehicle risk threshold, and a lane change obstacle avoidance target lane front vehicle risk threshold. The lane changing conditions include: the risk posed by the front obstacle to the vehicle is not greater than the lane change obstacle avoidance front vehicle risk threshold, and the risk posed by the rear vehicle in the target lane to the vehicle is not greater than the lane change obstacle avoidance target lane rear vehicle risk threshold, and the risk posed by the front vehicle in the target lane to the vehicle is not greater than the lane change obstacle avoidance target lane front vehicle risk threshold.

[0025] An embodiment of the present invention also provides an active obstacle avoidance control device for an intelligent vehicle, comprising: an acquisition unit for acquiring status information of the vehicle and status information of each traffic participant around the vehicle, wherein the status information includes position information and motion information; an estimation unit for estimating the risk posed to the vehicle by each traffic participant based on the status information of the vehicle and the status information of each traffic participant; a judgment unit for judging whether there is a front obstacle in front of the current lane within a preset driving risk range based on the risk posed to the vehicle by each traffic participant, wherein the current lane refers to the lane in which the vehicle is currently located; an obstacle avoidance strategy determination unit for determining an obstacle avoidance strategy when the front obstacle exists, based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane changing obstacle avoidance risk threshold, and executing obstacle avoidance operations corresponding to the determined obstacle avoidance strategy, wherein the braking obstacle avoidance risk threshold and the lane changing obstacle avoidance risk threshold are both related to the status information of the vehicle and each traffic participant.

[0026] An embodiment of the present invention also provides a storage medium, which is a non-volatile storage medium or a non-transient storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of any of the above-mentioned intelligent vehicle active obstacle avoidance control methods are executed.

[0027] An embodiment of the present invention also provides a method including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor runs the computer program, the steps of any of the above-mentioned intelligent vehicle active obstacle avoidance control methods are executed.

[0028] Compared with the prior art, the technical solution of the embodiment of the present invention has the following beneficial effects:

[0029] Based on the vehicle's state information and the state information of each traffic participant, the risk posed by each traffic participant to the vehicle is estimated. Based on the risk posed by each traffic participant to the vehicle, a determination is made as to whether there is a forward obstacle in the current lane within a preset driving risk range. If such an obstacle is present, an obstacle avoidance strategy is determined based on the relationship between the risk posed by each traffic participant to the vehicle and the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold. The braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are both related to the vehicle's state information and the state information of each traffic participant. Therefore, determining the obstacle avoidance strategy based on the relationship between the risk posed by each traffic participant to the vehicle and the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold can improve the accuracy of the formulated obstacle avoidance strategy. Therefore, based on the vehicle's state information and the state information of traffic participants in the road environment, an accurate and comprehensive quantitative assessment of road conditions and potential collision risk factors is performed. Based on the risk assessment results, real-time active obstacle avoidance behavior decisions are made, improving the efficiency of the vehicle's active obstacle avoidance decisions and enhancing driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of an active obstacle avoidance control method for an intelligent vehicle in an embodiment of the present invention;

[0031] Figure 2 This is a schematic diagram of a lane line constraint on driving risk in an embodiment of the present invention;

[0032] Figure 3 is a schematic diagram of a traffic scene in an embodiment of the present invention;

[0033] Figure 4 This is a schematic diagram of a braking obstacle avoidance process in an embodiment of the present invention;

[0034] Figure 5 Schematic diagram of the relative positions of the vehicle and the preceding vehicle in the current lane during a lane change and obstacle avoidance process in an embodiment of the present invention;

[0035] Figure 6 Schematic diagram of the relative positions between the vehicle and the following vehicle in the target lane during a lane change and obstacle avoidance process in an embodiment of the present invention;

[0036] Figure 7Schematic diagram of the relative position between the host vehicle and the preceding vehicle in the target lane during a lane change and obstacle avoidance process in an embodiment of the present invention;

[0037] Figure 8 This is a specific implementation of step S14 in the embodiment of the present invention;

[0038] Figure 9 This is a specific implementation of step S143 in the embodiment of the present invention;

[0039] Figure 10 is a flow chart of another intelligent vehicle active obstacle avoidance control method in an embodiment of the present invention;

[0040] Figure 11 Schematic diagram of the structure of an active obstacle avoidance control device for an intelligent vehicle in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] As mentioned above, due to the real-time changing characteristics of the road environment, traffic conditions and other external factors in which the vehicle is located, this method is difficult to systematically consider the real-time changes of multiple traffic elements and their impacts in the complex traffic system composed of people, vehicles and roads, thereby affecting the efficiency of determining the vehicle's obstacle avoidance strategy, and may further affect driving safety.

[0042] To address the above-mentioned issues, in an embodiment of the present invention, the risk posed by each traffic participant to the vehicle is estimated based on the vehicle's state information and the state information of each traffic participant. Based on the risk posed by each traffic participant to the vehicle, a determination is made as to whether there is a forward obstacle in the current lane within a preset driving risk range. If such an obstacle is present, an obstacle avoidance strategy is determined based on the relationship between the risk posed by each traffic participant to the vehicle and the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold. Both the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are related to the vehicle's state information and that of each traffic participant. Therefore, determining the obstacle avoidance strategy based on the relationship between the risk posed by each traffic participant to the vehicle and the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold can improve the accuracy and optimization of the formulated obstacle avoidance strategy, thereby obtaining a more optimal obstacle avoidance strategy. Therefore, based on the vehicle's state information and the state information of traffic participants in the road environment, an accurate and comprehensive quantitative assessment of road conditions and potential collision risk factors is performed. Based on the risk assessment results, real-time active obstacle avoidance behavior decisions are made, improving the efficiency of the vehicle's active obstacle avoidance decisions and enhancing driving safety.

[0043] In order to make the above-mentioned objects, features and beneficial effects of the embodiments of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] The embodiment of the present invention provides an intelligent vehicle active obstacle avoidance control method, referring to Figure 1 , a flow chart of an active obstacle avoidance control method for an intelligent vehicle in an embodiment of the present invention is given, which may specifically include the following steps:

[0045] Step S11: Acquire the status information of the vehicle and the status information of each traffic participant around the vehicle.

[0046] In a specific implementation, the state information may include: position information and motion information. The position information is used to characterize the position of the vehicle or the position of each traffic participant. For example, the position information of the vehicle is used to characterize the position of the vehicle; the position information of each traffic participant is used to characterize the position of each traffic participant. The position of each traffic participant may be the position of each traffic participant relative to the vehicle, that is, the relative position to the vehicle. The motion information may be used to characterize the motion state of the vehicle and the motion state of each traffic participant. The motion information of the vehicle is used to characterize the motion state of the vehicle; the motion information of each traffic participant is used to characterize the motion state of each traffic participant. The motion information may include speed, etc.

[0047] In specific implementations, the vehicle can obtain the location and movement information of the vehicle and surrounding traffic participants through on-board sensing sensors (such as on-board laser radar or cameras), navigation and positioning devices, and networked communication system equipment. Traffic participants may include vehicles, pedestrians, obstacles such as rocks or trees, and cyclists.

[0048] In a specific implementation, the type of the traffic participant may include a static type and a dynamic type. When the type of the traffic participant is a static type, the speed of the traffic participant is zero.

[0049] For example, the state information of static obstacles can be obtained based on the vehicle-mounted LiDAR point cloud data, and the position of static obstacles can be determined. The state information of dynamic obstacles can also be obtained based on the vehicle-mounted LiDAR point cloud data, and the relative position of dynamic obstacles to the vehicle and the speed of dynamic obstacles can be determined.

[0050] For another example, based on the image data collected by the camera, the status information of static obstacles and the status information of dynamic obstacles are determined.

[0051] It is understandable that the status information of each traffic participant can also be determined by combining data collected by one or more of the vehicle-mounted laser radar, camera, or navigation and positioning device.

[0052] In the specific implementation, the coordinate system of the vehicle is used as a reference, and the positions of the traffic participants around the vehicle in the coordinate system of the vehicle (x 1i ,y 1i ;x2i ,y 2i ;...x ji ,y ji ), where (x ji ,y ji ) is the coordinate of one of the traffic participants j.

[0053] Step S12: estimating the risk posed by each traffic participant to the vehicle based on the vehicle's status information and the status information of each traffic participant.

[0054] In a specific implementation, an equivalent dynamics model may be used to estimate the risk posed by each traffic participant to the vehicle based on the vehicle's state information and the state information of each traffic participant.

[0055] In some non-limiting embodiments, the risk posed by each traffic participant to the vehicle is estimated based on the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle.

[0056] Based on the idea of the equivalent force model, the equivalent force model can be used to quantitatively evaluate the risks caused by each traffic participant to the vehicle in the form of equivalent force, that is, the risks caused by each traffic participant to the vehicle are quantified into equivalent forces on the vehicle.

[0057] The equivalent force exerted by each traffic participant on the vehicle can be estimated based on the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle, and the estimated equivalent force can be used as the risk posed by each traffic participant to the vehicle.

[0058] Specifically, the absolute kinetic energy of each traffic participant and the relative kinetic energy between each traffic participant and the vehicle can be calculated based on the speed of the vehicle and the speed of each traffic participant. The equivalent force generated by each traffic participant on the vehicle can be estimated based on the absolute kinetic energy of each traffic participant, the relative kinetic energy between each traffic participant and the vehicle, the relative distance between each traffic participant and the vehicle, etc., and the estimated equivalent force can be used as the risk of each traffic participant to the vehicle.

[0059] Furthermore, the absolute kinetic energy of each traffic participant can be calculated based on the speed and mass of each traffic participant. The relative kinetic energy between each traffic participant and the host vehicle can be calculated based on the mass of the host vehicle, the speed of the host vehicle, and the speed of each traffic participant.

[0060] In some embodiments, the relative distance between each traffic participant and the vehicle may include a lateral relative distance between each traffic participant and the vehicle and a longitudinal relative distance between each traffic participant and the vehicle.

[0061] In this embodiment of the present invention, the longitudinal direction refers to the extension direction of the current lane, and the transverse direction refers to the direction perpendicular to the extension direction of the current lane.

[0062] In practice, to improve the alignment of the determined relative distances between each traffic participant and the vehicle with the actual risk impact of each traffic participant on the vehicle in actual traffic scenarios, in some embodiments of the present invention, a first gradient adjustment coefficient may be used to adjust the actual relative distances between each traffic participant and the vehicle, with the relative distances adjusted using the first gradient adjustment coefficient being used as the relative distances between each traffic participant and the vehicle. The first gradient adjustment coefficient may be used to adjust the driving risk range and is related to the relative distances between the vehicle and each traffic participant, the vehicle's speed, and the speeds of each traffic participant.

[0063] In a specific implementation, when the relative distances between each traffic participant and the vehicle include both the lateral relative distances between each traffic participant and the vehicle and the longitudinal relative distances between each traffic participant and the vehicle, the first gradient adjustment coefficient may include a first lateral gradient adjustment coefficient and a second longitudinal gradient adjustment coefficient. The first lateral gradient adjustment coefficient is used to adjust the lateral relative distances between each traffic participant and the vehicle, and the first longitudinal gradient adjustment coefficient is used to adjust the longitudinal relative distances between each traffic participant and the vehicle.

[0064] When constructing the coordinate system of the vehicle, the longitudinal direction can be used as the x-axis, and the forward direction of the vehicle can be used as the positive direction of the x-axis; the transverse direction can be used as the y-axis, and the direction rotated 90° counterclockwise along the positive direction of the x-axis can be used as the positive direction of the y-axis.

[0065] Furthermore, the risk posed by each traffic participant to the vehicle can be estimated by combining the Driving Safety Field Theory and the equivalent dynamics model. The Driving Safety Field Theory can also take into account the risk focus range to improve the accuracy of the estimated risk posed by traffic participants to the vehicle.

[0066] In some non-limiting embodiments, when estimating the risk posed by each traffic participant to the host vehicle, the risk focus range can be considered. Thus, based on the risk focus range, the speed of each traffic participant, the speed of the host vehicle, and the relative distance between each traffic participant and the host vehicle, the equivalent force exerted by each traffic participant on the host vehicle can be estimated, and the estimated equivalent force can be used as the risk posed by each traffic participant to the host vehicle.

[0067] In some non-limiting embodiments, the risk posed by a traffic participant to the vehicle can be estimated using the following formula (1). The relative kinetic energy between the traffic participant and the vehicle can be calculated using the following formula (2), and the absolute kinetic energy of the traffic participant can be calculated using the following formula (3).

[0068]

[0069]

[0070]

[0071] Among them, (x j,i ,y j,i ) is the coordinate of traffic participant j in the coordinate system of vehicle i; k x,0 is the longitudinal gradient adjustment coefficient of the traffic perspective, k x,p is the longitudinal gradient adjustment coefficient of the vehicle’s viewing angle, k y,0 is the lateral gradient adjustment coefficient of the traffic perspective, k y,p is the lateral gradient adjustment coefficient of the vehicle's perspective; r0 is the driver's attention range to the risk, which is related to the driver's following distance; r max is the free flow vehicle spacing, used to indicate the maximum risk impact range; m i is the mass of vehicle i; m j is the mass of traffic participant j; v i is the speed of vehicle i; v j is the speed of traffic participant j; E j,0 is the absolute kinetic energy of traffic participant j; E j,i is the relative kinetic energy between traffic participant j and vehicle i.

[0072] In a specific implementation, the first longitudinal and transverse gradient adjustment coefficient may include the longitudinal gradient adjustment coefficient k of the traffic perspective. x,0 and the longitudinal gradient adjustment coefficient k of the vehicle's viewing angle x,p The first lateral gradient adjustment coefficient may include the lateral gradient adjustment coefficient k of the traffic perspective. y,0 and the lateral gradient adjustment coefficient k of the vehicle's viewing angle y,p . Among them, the longitudinal gradient adjustment coefficient from the traffic perspective is related to the longitudinal risk propagation speed, the position information of the vehicle, the position information of the traffic participants, the longitudinal velocity component of the vehicle, and the longitudinal velocity component of the target participant. The longitudinal gradient adjustment coefficient from the vehicle perspective is related to the longitudinal risk propagation speed, the position information of the vehicle, the position information of the traffic participants, and the longitudinal velocity component of the vehicle. The lateral gradient adjustment coefficient from the traffic perspective is related to the lateral risk propagation speed, the position information of the vehicle, the position information of the traffic participants, the lateral velocity component of the vehicle, and the lateral velocity component of the target participant. The lateral gradient adjustment coefficient from the vehicle perspective is related to the lateral risk propagation speed, the position information of the vehicle, the position information of the traffic participants, and the lateral velocity component of the vehicle.

[0073] In some embodiments, the longitudinal gradient adjustment coefficient k of the traffic viewing angle x,0 , longitudinal gradient adjustment coefficient k of vehicle viewing angle x,p, lateral gradient adjustment coefficient k from traffic perspective y,0 and the lateral gradient adjustment coefficient k of the vehicle's viewing angle y,p It can be calculated using the following formulas (4) to (7):

[0074]

[0075]

[0076]

[0077]

[0078] Among them, v xmax is the vertical risk transmission speed; v ymax is the horizontal risk transmission speed; (x i ,y i ) is the position coordinate of the vehicle, (x j ,y j ) is the position coordinate of the traffic participant, v xi is the longitudinal velocity component of the vehicle, v yi is the lateral velocity component of the vehicle, v xj is the longitudinal velocity component of the traffic participant, v yj is the lateral velocity component of the traffic participant.

[0079] in,

[0080]

[0081]

[0082]

[0083] sign0(v xi )=1;

[0084] sign0(v yi )=1.

[0085] In specific implementation, the vertical risk propagation speed and the horizontal risk propagation speed can be configured according to the actual application scenario. xmax =200km / h, v ymax =50km / h. It is understandable that the longitudinal risk propagation speed and the lateral risk propagation speed may have other values, which are not limited here.

[0086] It should be noted that E in the above formula (1) j,0 With E j,i The ratio configuration can be 1:1. In practical applications, Ej,0 With E j,i The proportional configuration can also have other forms, which will not be listed here one by one.

[0087] In practice, vehicles typically travel in a single direction within a lane defined by lane markings, along the lane's extension direction. Lane markings constrain the vehicle's lateral movement, thereby limiting and reducing its impact on the traffic environment. In other words, lane markings influence the risk posed to the vehicle by various traffic participants.

[0088] To further improve the consistency between the determined risk posed by each traffic participant to the vehicle and the actual risk posed, in other embodiments, the relative distance between each traffic participant and the vehicle is calculated by adjusting the actual relative distance between each traffic participant and the vehicle using a first gradient adjustment coefficient and a second gradient adjustment coefficient. The second gradient adjustment coefficient is used to adjust the driving risk range and is related to the lane width and / or the length of the vehicle, where lane width refers to the vertical distance between two adjacent lane lines.

[0089] In some embodiments, after considering the constraints of lane lines on driving risks, as shown in FIG. Figure 2 The lane line shows a schematic diagram of driving risk constraints. The risk field contour lines generated by traffic participant j in the traffic environment are compressed to form an ellipse with dynamically changing major and minor axes, so that the second gradient adjustment coefficient is consistent with the semi-major axis A of the ellipse. j and semi-minor axis B j Related. Among them, is the semi-major axis A j Half the distance between the two endpoints A1 and A2 of the ellipse, the minor axis B j It is half the distance between the two endpoints B1 and B2 of the ellipse.

[0090] The semi-major axis A of the ellipse j Distance from free-flow vehicles r max and / or the length of the traffic participant j. The semi-minor axis B of the ellipse j Lane width l w , the distance l between traffic participant j and the lane centerline cj and the width of traffic participant j, wherein the lane centerline refers to a virtual line along the lane extension direction between the two lane lines forming the lane.

[0091] For example, the semi-major axis of the ellipse can be calculated using the following formula (8). The semi-minor axis of the ellipse can be calculated using the following formula (9).

[0092] A j =r max +l1; (8)

[0093] B j =lw +l2+l cj ; (9)

[0094] Among them, A j is the semi-major axis; B j is the semi-minor axis; r max is the free flow vehicle distance; l1 is half of the length of traffic participant j; l2 is half of the width of traffic participant j; l cj is the distance between traffic participant j and the lane centerline; l w Double the lane width.

[0095] It should be noted that the length of traffic participant j, the width of traffic participant j, the lane width, etc. can be calculated based on the lidar data, image data, etc. collected by the vehicle, or can be corresponding preset values.

[0096] In some embodiments, the second gradient adjustment coefficient may include a second transverse gradient adjustment coefficient and a second longitudinal gradient adjustment coefficient.

[0097] In some non-limiting embodiments, after considering the impact of lane lines on driving risks, the risk generated by a traffic participant (such as a vehicle) j traveling within the lane line to any external point (taking the vehicle i as an example) can be estimated using the following formula (10).

[0098]

[0099] Among them, k x,d is the second longitudinal gradient adjustment coefficient, k y,d is the second transverse gradient adjustment coefficient, E j,0 is the absolute kinetic energy of traffic participant j, E j,i is the relative kinetic energy between traffic participant j and vehicle i; r0 is the driver's risk focus range; r max is the free flow vehicle spacing, used to indicate the maximum risk impact range; (x j,i ,y j,i ) is the coordinate of traffic participant j in the coordinate system of vehicle i; k x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,0 and k y,p Both are the first transverse gradient adjustment coefficients.

[0100] In a specific implementation, the second transverse gradient adjustment coefficient k y,d It can be calculated using the following formula (11):

[0101]

[0102] The second longitudinal gradient adjustment coefficient kx,d Can be 1.

[0103] In some embodiments, when the vehicle is traveling straight in the lane, the lateral velocity component is usually 0. In this case, k y,0 =k y,p =1.

[0104] Therefore, in some embodiments, when k x,d =1 and k y,0 =k y,p When =1, formula (10) can be simplified to the following formula (12).

[0105]

[0106] Based on the above formulas (1), (10), or (12), a real-time quantitative driving risk assessment model can be constructed. The real-time quantitative driving risk assessment model is used to assess the risk posed to the vehicle by traffic participants around the vehicle. Furthermore, obstacle avoidance decisions and control can be made based on the risk posed to the vehicle by each traffic participant assessed by the real-time quantitative driving risk assessment model.

[0107] Reference Figure 3 A schematic diagram of a traffic scenario in an embodiment of the present invention is provided. In this scenario, there is a vehicle S, a preceding vehicle F in the current lane, a preceding vehicle LF in the target lane, and a following vehicle LR in the target lane. A real-time quantitative risk assessment model for driving risk constructed based on formulas (1), (10), or (12) can be used to assess the risks posed to the vehicle by the preceding vehicle F in the current lane, the preceding vehicle LF in the target lane, and the following vehicle LR in the target lane, respectively. The following description will be made using the real-time quantitative risk assessment model for driving risk constructed based on formula (12) as an example.

[0108] In some embodiments, the risk posed to the vehicle by the preceding vehicle in the current lane is as shown in formula (13):

[0109]

[0110] The risk posed to the vehicle by the preceding vehicle in the target lane is shown in formula (14):

[0111]

[0112] The risk posed to the vehicle by the following vehicle in the target lane is shown in formula (15):

[0113]

[0114] Among them, F F_S is the risk posed by the preceding vehicle F in the current lane to the vehicle S; E F,0 is the absolute kinetic energy of the preceding vehicle F in the current lane; EF,S is the relative kinetic energy between the preceding vehicle F and the vehicle S in the current lane; x F is the longitudinal relative distance between the preceding vehicle F and the vehicle S in the current lane; F is the lateral relative distance between the preceding vehicle F and the vehicle S in the current lane; F LF_S is the risk posed by the preceding vehicle LF in the target lane to the vehicle S; E LF,0 is the absolute kinetic energy of the preceding vehicle LF in the target lane; E LF,S is the relative kinetic energy between the preceding vehicle LF and the vehicle S in the target lane; x LF is the longitudinal relative distance between the preceding vehicle LF and the vehicle S in the target lane; y LF is the lateral relative distance between the preceding vehicle LF and the vehicle S in the target lane; F LR_S is the risk posed by the following vehicle LR in the target lane to the vehicle S; E LR,0 is the absolute kinetic energy of the following vehicle LR in the target lane; E LR,S is the relative kinetic energy between the following vehicle LR and the vehicle S in the target lane; x LR is the longitudinal relative distance between the following vehicle LR and the vehicle S in the target lane; LR k is the lateral relative distance between the rear vehicle LR and the vehicle S in the target lane; x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,d is the second transverse gradient adjustment coefficient; r max is the free-flow vehicle distance, which is used to indicate the maximum risk impact range.

[0115] Step S13: Based on the risk posed by each traffic participant to the vehicle, it is determined whether there is an obstacle ahead of the current lane within a preset driving risk range.

[0116] In a specific implementation, it is possible to determine whether there is an obstacle in front of the current lane within a preset driving range based on the risk posed to the vehicle by each traffic participant.

[0117] In some embodiments, the above formula (1), formula (10) or formula (12) can be used to calculate the risk posed by each traffic participant to the vehicle, and based on the relationship between the calculated risk posed by each traffic participant to the vehicle and the first critical risk threshold, it is determined whether there is an obstacle in front of the current lane.

[0118] If the risk posed by the traffic participant in the current lane to the vehicle is greater than zero, then it is determined that there is an obstacle in front of the current lane. Correspondingly, if the risk posed by the traffic participant in the current lane to the vehicle is zero, then it is determined that there is no obstacle in front.

[0119] Step S14: When there is the obstacle ahead, an obstacle avoidance strategy is determined based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold, and an obstacle avoidance operation corresponding to the determined obstacle avoidance strategy is executed.

[0120] In a specific implementation, the braking obstacle avoidance risk threshold is related to the status information of the vehicle and each traffic participant; the lane changing obstacle avoidance risk threshold is related to the status information of the vehicle and each traffic participant.

[0121] Since the braking obstacle avoidance risk threshold is calculated based on the status information of the vehicle and the status information of each traffic participant, when the status information of the vehicle and the status information of each traffic participant changes, the calculated braking obstacle avoidance risk threshold changes.

[0122] Since the lane change obstacle avoidance risk threshold is calculated based on the status information of the vehicle and the status information of each traffic participant, when the status information of the vehicle and the status information of each traffic participant changes, the calculated lane change obstacle avoidance risk threshold changes.

[0123] As can be seen above, based on the vehicle's state information and the state information of each traffic participant, the risk posed by each traffic participant to the vehicle is estimated. Based on the risk posed by each traffic participant to the vehicle, a determination is made as to whether there is a forward obstacle in the current lane within a preset driving risk range. If such an obstacle is present, an obstacle avoidance strategy is determined based on the relationship between the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane-changing obstacle avoidance risk threshold. Both the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are related to the vehicle's state information and that of each traffic participant. Therefore, determining the obstacle avoidance strategy based on the relationship between the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane-changing obstacle avoidance risk threshold can improve the accuracy and optimization of the formulated obstacle avoidance strategy, thereby obtaining a more optimal obstacle avoidance strategy. Therefore, based on the vehicle's state information and the state information of traffic participants in the road environment, an accurate and comprehensive quantitative assessment of road conditions and potential collision risk factors is performed. Based on the risk assessment results, real-time active obstacle avoidance behavior decisions are made, improving the efficiency of the vehicle's active obstacle avoidance decisions and enhancing driving safety.

[0124] In a specific implementation, when an obstacle is detected ahead, if the speed of the obstacle ahead is less than the speed of the vehicle or it is stationary, in order to avoid an accident, the vehicle must maintain a sufficient longitudinal relative distance from the obstacle ahead before starting to brake.

[0125] Calculate the longitudinal relative distance that the vehicle needs to maintain between the front obstacle and the front obstacle when decelerating and braking to avoid the obstacle at the maximum deceleration without colliding with the front obstacle. The minimum longitudinal relative distance that needs to be maintained is used as the braking obstacle avoidance safety distance threshold. If the longitudinal relative distance between the vehicle and the front obstacle reaches the braking obstacle avoidance safety distance threshold, braking obstacle avoidance is performed. Based on the status information of the front obstacle and the status information of the vehicle at the time when braking starts, calculate the risk of the front obstacle to the vehicle at the time when braking starts. The calculated risk is used as the braking obstacle avoidance risk threshold, where the longitudinal direction refers to the extension direction of the current lane.

[0126] For example, refer to Figure 4 , a schematic diagram of the braking obstacle avoidance process is given. To avoid accidents, the vehicle needs to maintain a sufficient relative longitudinal distance from the obstacle in front before braking. in, The following relationship (16) is satisfied:

[0127]

[0128] in, is the relative longitudinal distance between the vehicle and the obstacle in front before braking; d S is the distance traveled by the vehicle during braking; d F is the distance traveled by the obstacle in front during the braking process; d0 is the safe distance maintained between the vehicle and the obstacle in front at the end of braking.

[0129] In practice, the safety distance d0 can be configured as needed. Typically, d0 = L / 2, where L is the vehicle's length. It is understood that d0 can also have other values, which are not listed here.

[0130] If the braking time is t b , t b =t delay +t braking +t brake .

[0131] Among them, t delay is the system delay time; t braking The time taken for the braking deceleration to increase to the target deceleration; t brake The time it takes to continue braking at the target deceleration.

[0132] During the braking process, the relative distance between the vehicle and the obstacle in front is d S with d F The difference can be calculated using the following formula (17):

[0133]

[0134] Among them, t0 is the braking start time; t b is the braking end time; v0 is the speed of the vehicle at the braking start time; v F0 is the speed of the obstacle in front at the start of braking; a s (t) is the deceleration of the vehicle during braking; a F (t) is the acceleration or deceleration of the obstacle in front during braking.

[0135] The maximum deceleration a of the vehicle is determined by the road adhesion coefficient. smax Slowing down can ensure that there is no collision with the obstacle in front. Defined as the braking obstacle avoidance safety distance threshold In this scenario, the risk of the obstacle in front of the vehicle at the start of braking is defined as the risk threshold for obstacle avoidance by braking (RT). B_F According to the real-time quantitative assessment model of driving risk, RT B_F The speed of the vehicle v0 at the start of braking and the speed of the obstacle in front v at the start of braking F0 and braking obstacle avoidance safety distance threshold etc.

[0136] In some embodiments, RT B_F The calculation formula is shown in formula (18):

[0137]

[0138] Among them, m s is the mass of the vehicle; m F is the mass of the obstacle in front; v0 is the speed of the vehicle at the beginning of braking; v F0 is the speed of the obstacle in front at the start of braking; k x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,p is the first transverse gradient adjustment coefficient; r max is the free flow vehicle spacing, which is used to indicate the maximum risk impact range; FS is the vertical coordinate of the obstacle in front of the vehicle in the coordinate system, that is, the horizontal relative distance from the vehicle.

[0139] It should be noted that the above formula (18) is obtained based on the real-time quantitative evaluation model of driving risk constructed by formula (12). When the real-time quantitative evaluation model of driving risk is constructed based on formula (1) or formula (10), RT B_FThe real-time calculation formula can be adaptively changed according to formula (1) or (10).

[0140] During a lane change, the vehicle must avoid collisions with obstacles ahead (e.g., rear-ending the vehicle in the current lane), avoid rear-ending the vehicle in the target lane, and avoid collisions with the vehicle behind it. In other words, during a lane change, the vehicle must consider the risks posed by the vehicle in the current lane, the vehicle in the target lane, and the vehicle behind it.

[0141] In order to fully and comprehensively consider the influence of various factors during the lane changing process, in a specific implementation, the lane changing obstacle avoidance risk threshold may at least include: a lane changing obstacle avoidance leading vehicle risk threshold, a lane changing obstacle avoidance target lane rear vehicle risk threshold, and a lane changing obstacle avoidance target lane leading vehicle risk threshold.

[0142] In a specific implementation, the lane change obstacle avoidance leading vehicle risk threshold is calculated in the following manner: the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the leading obstacle when the vehicle accelerates at the maximum lateral acceleration to perform lane change obstacle avoidance and does not collide with the leading obstacle is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the first lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the leading obstacle reaches the first lane change obstacle avoidance safety distance threshold, lane change obstacle avoidance is performed, and the risk of the leading obstacle to the vehicle at the start of the lane change is calculated based on the status information of the leading obstacle and the status information of the vehicle at the start of the lane change, and the calculated risk is used as the lane change obstacle avoidance leading vehicle risk threshold, wherein the longitudinal direction refers to the extension direction of the current lane.

[0143] The collision moment at which the vehicle collides with the front obstacle during the lane change process is calculated based on the vehicle's lateral displacement, its mass, and the maximum tire force in the lateral direction. The lateral displacement is the displacement of the vehicle at the time of collision with the front obstacle. The longitudinal relative distance that the vehicle must maintain between the front obstacle is calculated based on the lane change start time, the vehicle's speed, the speed of the front obstacle, the vehicle's acceleration, the acceleration / deceleration of the front obstacle, and the collision moment. The lateral direction refers to a direction perpendicular to the extension direction of the current lane.

[0144] In the specific implementation, refer to Figure 5 A schematic diagram of the relative position of the vehicle and the preceding vehicle in the current lane during a lane change and obstacle avoidance process in an embodiment of the present invention is provided. The longitudinal relative distance that the vehicle needs to maintain with the preceding obstacle when the vehicle accelerates at maximum lateral acceleration to perform lane change and obstacle avoidance without colliding with the preceding obstacle is: The following formula (19) must be satisfied.

[0145]

[0146] in,

[0147] Substituting formula (20) into formula (19), we can obtain the following formula (21):

[0148]

[0149] Among them, t c is the moment when the vehicle may collide with the obstacle in front during the lane change process; t'0 is the start time of lane change; v'0 is the speed of the vehicle at the start time of lane change; v FC is the speed of the obstacle in front at the start of lane change; a' s (t) is the acceleration of the vehicle during the lane change process; a FC (t) is the acceleration or deceleration of the obstacle in front during the lane change process; d0 is the safe distance that the vehicle needs to maintain between itself and the obstacle in front when braking is completed; d SC is the distance traveled by the vehicle at the time of collision; d LC is the distance to the obstacle ahead at the time of collision.

[0150] like Figure 5 As shown, during the lane changing process, at the start time t'0, the relative distance between the vehicle and the obstacle in front is Assume t c is the moment when the vehicle may collide with the obstacle in front during the lane change process. The lateral displacement of the vehicle when it reaches the collision point is the lateral width H of the obstacle in front. F The shorter the lane change process, the shorter the longitudinal distance traveled by the vehicle. According to the tire side slip characteristics, the maximum tire force F along the y-axis is guaranteed to keep the longitudinal slip rate and side slip angle within the linear range. ymax , the shortest lane-changing time can be calculated using the following formula (22):

[0151]

[0152] Among them, t f is the shortest time of lane changing process; m s is the mass of the vehicle; H R is the lateral distance between the centerline of the current lane and the centerline of the target lane; F ymax To ensure the maximum tire force along the y-axis within the linear range of longitudinal slip rate and slip angle according to the tire cornering characteristics.

[0153] The following formula (23) can be used to calculate the time when the vehicle may collide with the obstacle in front during the lane change process:

[0154]

[0155] Among them, t c is the moment when the vehicle may collide with the obstacle in front; m s is the mass of the vehicle; H F is the lateral width of the obstacle in front; F ymax To ensure the maximum tire force along the y-axis within the linear range of longitudinal slip rate and slip angle according to the tire cornering characteristics.

[0156] The maximum lateral acceleration a of the vehicle is determined by the tire cornering characteristics. ymax Changing lanes is necessary to avoid colliding with the obstacle ahead. Defined as the first lane change obstacle avoidance safety distance threshold In this scenario, the risk of the obstacle in front of the vehicle at the beginning of the lane change is defined as the risk threshold for the vehicle in front of the lane change obstacle avoidance (Risk Threshold for Obstacle Avoidance by Lane Change), denoted as RT LC_F .

[0157] According to the above-mentioned real-time quantitative assessment model of driving risk, RT LC_F The speed of the vehicle at the start of lane change, the speed of the obstacle in front, and the safety distance threshold between the vehicle and the first lane change obstacle avoidance The following formula (24) can be used to calculate the risk threshold of the vehicle ahead during lane change and obstacle avoidance in real time:

[0158]

[0159] Among them, v'0 is the speed of the vehicle at the beginning of lane change; v FC is the speed of the obstacle in front at the start of lane change; m s is the mass of the vehicle; m F is the mass of the obstacle in front; k x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,p is the first transverse gradient adjustment coefficient; r max is the free flow vehicle spacing, which is used to indicate the maximum risk impact range; FS is the vertical coordinate of the obstacle in front of the vehicle in the coordinate system, that is, the horizontal relative distance from the vehicle; r0 is the driver's attention range for the risk.

[0160] In a specific implementation, the following method is used to calculate the risk threshold of the vehicle behind the target lane for lane change obstacle avoidance: the longitudinal relative distance that the vehicle needs to maintain with the vehicle behind the target lane when the vehicle performs lane change obstacle avoidance at the maximum longitudinal acceleration and does not collide with the vehicle behind the target lane is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the second lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the vehicle behind the target lane reaches the second lane change obstacle avoidance safety distance, lane change obstacle avoidance is performed, and the risk of the vehicle behind the target lane to the vehicle is calculated based on the status information of the vehicle at the start of the lane change and the status information of the vehicle behind the target lane, and the calculated risk is used as the risk threshold of the vehicle behind the target lane for lane change obstacle avoidance, wherein the longitudinal direction refers to the extension direction of the current lane.

[0161] In some embodiments, the shortest time for the lane change process can be calculated based on the lateral distance between the center lines of the current lane and the target lane, the mass of the vehicle, and the maximum tire force of the vehicle in the lateral direction; and the longitudinal relative distance that the vehicle needs to maintain with the vehicle behind the target lane is calculated based on the start time of the lane change, the speed of the vehicle, the speed of the vehicle behind the target lane, the shortest time, the acceleration of the vehicle, and the acceleration / deceleration of the vehicle behind the target lane, where the lateral direction refers to the direction perpendicular to the extension direction of the current lane.

[0162] Reference Figure 6 , shows a schematic diagram of the relative positions of the host vehicle and the following vehicle in the target lane during a lane change and obstacle avoidance process in an embodiment of the present invention. If there is a following vehicle in the target lane, and its speed is greater than that of the host vehicle at the start of the lane change, there is a risk of a rear-end collision between the following vehicle and the host vehicle during the lane change. In this scenario, the host vehicle must accelerate during the lane change to avoid the risk of a collision with the following vehicle.

[0163] At the start of lane change, the relative longitudinal distance between the vehicle behind the target lane and the vehicle along the lane direction must satisfy the following formula (25) before the lane change operation can be performed.

[0164]

[0165] in,

[0166] Substituting formula (26) into formula (25) yields the following formula (27).

[0167]

[0168] in, is the longitudinal relative distance between the vehicle and the vehicle behind the target lane when there is no collision between the vehicle and the vehicle behind the target lane; t fis the shortest time of the lane changing process; v'0 is the speed of the vehicle at the beginning of the lane changing; v LR0 is the speed of the vehicle behind in the target lane at the start of lane change; a' s (t) is the acceleration of the vehicle during the lane change process; a LR (t) is the acceleration or deceleration of the vehicle behind the target lane during the lane change process. d0 is the safe distance that the vehicle needs to maintain with the vehicle behind the target lane when the lane change is completed; d S The distance traveled by the vehicle at the time of lane change completion; d LR is the distance traveled by the following vehicle in the target lane at the time the lane change is completed; t'0 is the time when the lane change starts.

[0169] Specifically, the vehicle has a maximum longitudinal acceleration a xmax The longitudinal relative distance when executing lane change obstacle avoidance to avoid collision with the following vehicle in the target lane is used as the second lane change obstacle avoidance safety distance threshold. In this scenario, lane change and obstacle avoidance are performed. At the start of lane change, the risk of the vehicle behind the target lane to the vehicle is the risk threshold of the vehicle behind the target lane, which can be recorded as RT. LC_LR .

[0170] According to the above-mentioned real-time quantitative assessment model of driving risk, RT LC_LR The speed of the vehicle at the start of the lane change, the speed of the vehicle behind in the target lane, and the second lane change obstacle avoidance safety distance threshold Related. RT LC_LR The real-time calculation formula is as follows (28):

[0171]

[0172] Among them, v'0 is the speed of the vehicle at the beginning of lane change; v LR0 is the speed of the vehicle behind in the target lane at the start of lane change; m LR is the mass of the following vehicle in the target lane; y LRS is the vertical coordinate of the vehicle behind the target lane in the coordinate system of the vehicle; m s is the mass of the vehicle; k x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,p is the first transverse gradient adjustment coefficient; r max is the free-flow vehicle distance, which is used to indicate the maximum risk impact range. is the longitudinal relative distance between the vehicle and the following vehicle in the target lane; r0 is the driver's risk focus range.

[0173] In a specific implementation, the risk threshold of the vehicle in front of the target lane for lane change and obstacle avoidance can be calculated in the following manner: when the speed of the vehicle in front of the target lane is greater than the speed of the obstacle ahead and less than the speed of the vehicle, the longitudinal relative distance that the vehicle and the vehicle in front of the target lane need to maintain when the vehicle performs lane change and obstacle avoidance at the maximum longitudinal deceleration and does not collide with the vehicle in front of the target lane is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the third lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the vehicle in front of the target lane reaches the third lane change obstacle avoidance safety distance threshold, lane change and obstacle avoidance are performed, and based on the status information of the vehicle and the status information of the vehicle in front of the target lane at the start time of the lane change, the risk of the vehicle in front of the target lane to the vehicle at the start time of the lane change and obstacle avoidance is calculated, and the calculated risk is used as the risk threshold of the vehicle in front of the target lane for lane change and obstacle avoidance, wherein the longitudinal direction refers to the extension direction of the current lane.

[0174] In some embodiments, the shortest time of the lane change process is calculated based on the lateral distance between the center lines of the current lane and the target lane, the mass of the vehicle, and the maximum tire force of the vehicle in the lateral direction; and the longitudinal relative distance that the vehicle needs to maintain with the vehicle in front of the target lane is calculated based on the start time of lane change obstacle avoidance, the speed of the vehicle, the speed of the vehicle in front of the target lane, the shortest time, the deceleration of the vehicle, and the acceleration / deceleration of the vehicle in front of the target lane, wherein the lateral direction refers to the direction perpendicular to the extension direction of the current lane.

[0175] The vehicle has a maximum longitudinal deceleration a smax The minimum longitudinal relative distance when executing lane change and avoiding obstacle and not colliding with the preceding vehicle in the target lane Defined as the third lane change obstacle avoidance safety distance threshold. In this scenario, when changing lanes, the risk of the vehicle behind the target lane to the vehicle at the beginning of the lane change is used as the risk threshold of the vehicle in front of the target lane for lane change obstacle avoidance, recorded as RT LC_LF .

[0176] Reference Figure 7 , shows a schematic diagram of the relative positions of the host vehicle and the preceding vehicle in the target lane during a lane change and obstacle avoidance process in an embodiment of the present invention. If there is a preceding vehicle in the target lane, and its speed is greater than that of the preceding vehicle in the current lane, and if the preceding vehicle in the target lane is slower than the host vehicle's speed at the start of the lane change, a rear-end collision between the host vehicle and the preceding vehicle in the target lane is possible during the lane change. In this scenario, the host vehicle must decelerate during the lane change to avoid the risk of a collision with the following vehicle in the target lane.

[0177] At the start of lane change, the longitudinal relative distance between the preceding vehicle in the target lane and the vehicle along the lane direction The following formula (29) must be satisfied before lane changing can be performed.

[0178]

[0179] Among them, v'0 is the speed of the vehicle at the beginning of lane change; v LF0 is the speed of the preceding vehicle in the target lane at the start of lane change; a LF (t) is the acceleration or deceleration of the preceding vehicle during the lane change process; a' s (t) is the deceleration of the vehicle during the lane change process; t'0 is the start time of the lane change; t f is the shortest time of lane changing process; d S is the distance traveled by the vehicle when the lane change is completed; d LF is the distance traveled by the preceding vehicle in the target lane when the lane change is completed; t'0 is the start time of the lane change; and d0 is the safe distance that the vehicle must maintain between itself and the preceding vehicle in the target lane when the lane change is completed.

[0180] The maximum longitudinal deceleration a of the vehicle is determined by the road adhesion coefficient. smax Slow down to avoid collision with the car in front Defined as the third lane change obstacle avoidance safety distance threshold In this scenario, the risk of the vehicle in front of the target lane to the vehicle at the start of lane change is defined as the risk threshold of the vehicle in front of the target lane for lane change obstacle avoidance, denoted as RT LC_LF .

[0181] According to the above-mentioned real-time quantitative assessment model of driving risk, RT LC_LF The speed of the vehicle at the start of lane change, the speed of the preceding vehicle in the target lane, and the third lane change obstacle avoidance safety distance threshold Related. RT LC_LF The real-time calculation formula is shown in formula (30):

[0182]

[0183] Among them, RT LC_LF is the risk threshold of the vehicle ahead in the target lane for lane change avoidance; v'0 is the speed of the vehicle at the start of lane change; v LF0 is the speed of the preceding vehicle in the target lane at the start of lane change; m s is the mass of the vehicle; k x,0 and k x,p are the first longitudinal gradient adjustment coefficients; k y,p is the first transverse gradient adjustment coefficient; r max is the free flow vehicle spacing, used to indicate the maximum risk impact range. m LF is the mass of the preceding vehicle in the target lane; y LFS is the vertical coordinate of the preceding vehicle in the target lane in the coordinate system of the vehicle; r0 is the driver's risk focus range.

[0184] Further, refer to Figure 8, a specific implementation of step S14 in an embodiment of the present invention is given, and step S14 may include the following steps:

[0185] Step S141 , determining whether the risk posed by the obstacle ahead to the vehicle is greater than a first critical risk threshold.

[0186] When the judgment result is yes, execute step S142; when the judgment result is no, execute step S144.

[0187] In a specific implementation, the first critical risk threshold is related to the braking obstacle avoidance risk threshold and is less than the braking obstacle avoidance risk threshold. A first critical risk coefficient K1 can be configured, and the product of the first critical risk coefficient and the braking obstacle avoidance risk threshold is used as the first critical risk threshold. Where 0 < K1 < 1.

[0188] In specific implementations, the first critical risk coefficient is used to characterize different drivers' psychological acceptance of driving risk. A higher acceptance of driving risk, i.e., a greater acceptable driving risk, corresponds to a higher first critical risk coefficient. Correspondingly, a lower acceptance of driving risk, i.e., a lower acceptable driving risk, corresponds to a lower first critical risk coefficient. The specific value of the first critical risk coefficient can be determined through analysis of natural driving data.

[0189] In some embodiments, in order to further improve the determined first critical risk coefficient to be more consistent with the driving risk acceptance level of the actual vehicle driver, the first critical risk coefficient can be determined by the driver driving the vehicle based on the obtained driving data.

[0190] Step S142: Determine the type of the front obstacle based on the motion information of the front obstacle.

[0191] Step S143 : determining an obstacle avoidance strategy based on the type of the obstacle ahead, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the relationship between the lane change obstacle avoidance risk threshold.

[0192] Step S144, maintain the current state and continue driving.

[0193] Further, refer to Figure 9 , a specific implementation of step S143 in an embodiment of the present invention is given, and step S143 may include the following steps:

[0194] Step S1431: Determine whether the obstacle ahead is a dynamic obstacle.

[0195] In specific implementations, obstacle types include dynamic obstacles and static obstacles. The obstacle type can be determined based on the obstacle's speed. When the obstacle's speed is 0, the obstacle is a static obstacle. When the obstacle's speed is greater than zero, the obstacle is a dynamic obstacle.

[0196] When the judgment result is yes, that is, the type of obstacle is a dynamic obstacle, step S1432 is executed. When the judgment result is no, that is, the type of obstacle is a static obstacle, step S1436 is executed.

[0197] Step S1432: Determine whether the risk posed by the obstacle ahead to the vehicle is greater than a second critical risk threshold.

[0198] When the judgment result is no, execute step S1433; when the judgment result is yes, execute step S1434.

[0199] In a specific implementation, the second critical risk threshold is related to the braking obstacle avoidance risk threshold, and is between the first critical risk threshold and the braking obstacle avoidance risk threshold. A second critical risk coefficient K2 can be configured, and the product of the second critical risk coefficient and the braking obstacle avoidance risk threshold is used as the second critical risk threshold. Among them, 0<K1<K2<1. The second critical risk threshold is used to reflect the driving style types of different drivers. Drivers with different driving style types can accept different levels of risk. For example, the second critical risk coefficient corresponding to a driver with a cautious driving style type is smaller than the second critical risk coefficient corresponding to a driver with an aggressive driving style type. The specific value of the second critical risk coefficient can be obtained through analysis of natural driving data.

[0200] In some embodiments, in order to further improve the determined second critical risk coefficient to be more consistent with the driving style type of the actual vehicle driver, the second critical risk coefficient can be determined based on the driving data obtained by the driver driving the vehicle.

[0201] In step S1433, if the risk posed by the obstacle ahead to the vehicle is not greater than the second critical risk threshold, a deceleration is determined based on the vehicle status information and the obstacle status information ahead, and the vehicle is controlled to decelerate and then cruise after the vehicle is followed according to the determined deceleration.

[0202] Step S1434: Determine whether the risk posed by the front obstacle to the vehicle is greater than the braking obstacle avoidance risk threshold.

[0203] When the judgment result is no, execute step S1435; when the judgment result is yes, execute step S1436.

[0204] Step S1435: If the risk posed by the front obstacle to the vehicle is not greater than the braking obstacle avoidance risk threshold, a deceleration is determined based on the vehicle status information and the status information of the front obstacle, and the vehicle is controlled to decelerate until it stops according to the determined deceleration.

[0205] Step S1436, determine whether the lane change condition is met.

[0206] In a specific implementation, whether the lane changing condition is met is determined based on the risk posed to the vehicle by traffic participants in adjacent lanes, the risk posed by the obstacle ahead, and the lane changing obstacle avoidance risk threshold.

[0207] In a specific implementation, the lane change conditions include: the risk posed by the obstacle ahead to the host vehicle is no greater than the lane change obstacle avoidance leading vehicle risk threshold, the risk posed by the following vehicle in the target lane to the host vehicle is no greater than the lane change obstacle avoidance target lane trailing vehicle risk threshold, and the risk posed by the preceding vehicle in the target lane to the host vehicle is no greater than the lane change obstacle avoidance target lane leading vehicle risk threshold. The lane change obstacle avoidance risk thresholds include: the lane change obstacle avoidance leading vehicle risk threshold, the lane change obstacle avoidance target lane trailing vehicle risk threshold, and the lane change obstacle avoidance target lane leading vehicle risk threshold.

[0208] When the judgment result is yes, execute step S1437; when the judgment result is no, execute step S1438.

[0209] Step S1437, execute lane change to avoid obstacles.

[0210] Step S1438: Control the vehicle to decelerate at the maximum deceleration until it stops.

[0211] In order to facilitate those skilled in the art to better understand and implement the embodiments of the present invention, a non-limiting embodiment of the intelligent vehicle active obstacle avoidance control method provided by the embodiment of the present invention is described below through a non-limiting embodiment.

[0212] Reference Figure 10 , a flow chart of an active obstacle avoidance control method for an intelligent vehicle in an embodiment of the present invention is given, which may specifically include the following steps:

[0213] Step S101: collecting status information of the vehicle and traffic participants around the vehicle.

[0214] Step S102 : Calculate the risk posed by the traffic participants to the vehicle based on the status information of the vehicle and the traffic participants around the vehicle.

[0215] In specific implementations, the risk posed by traffic participants to the vehicle primarily refers to driving risk. The established real-time driving risk quantitative assessment model can be used to estimate the quantitative risk value posed by each traffic participant to the vehicle. Based on the quantitative risk value posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold, the vehicle's active obstacle avoidance behavior decision is executed. The specific obstacle avoidance decision process may include steps S103 to S111.

[0216] The specific method for calculating the risk posed by traffic participants to the vehicle can be referred to the description in the above-mentioned embodiment and will not be elaborated here.

[0217] Step S103: Determine the risk F posed by the traffic participants in the front lane to the vehicle. F_S Does F satisfy F_S ≤K1*RT B_F .

[0218] According to the risk F caused by the traffic participants in the current lane ahead of the vehicle F_S , judge whether there is an obstacle in front of the current lane. When the risk of the vehicle being affected by the traffic participants in front of the current lane is greater than zero, it is judged that there is an obstacle in front of the current lane. F_S =0, it indicates that there is no obstacle in front of the current lane.

[0219] When there is an obstacle ahead, an obstacle avoidance strategy is determined based on the relationship between the risk posed by the traffic participant ahead of the current lane and the first critical risk threshold. The obstacle ahead can be a vehicle, object, pedestrian, cyclist, etc.

[0220] When the judgment result is yes, execute step S104; when the judgment result is no, execute step S105.

[0221] Among them, K1 is the first critical risk coefficient, and 0<K1<1, RT B_F is the braking obstacle avoidance risk threshold, K1*RT B_F is the first critical risk threshold.

[0222] Step S104: maintain the current state and continue driving.

[0223] Step S105: Determine the speed v of the obstacle ahead F Does it satisfy v F =0.

[0224] If there is an obstacle in front of the current lane, the type of the obstacle is further determined. The type of obstacle can be determined based on the speed of the obstacle.

[0225] When the judgment result is yes, that is, the speed v of the obstacle in front F Satisfy v F =0, it is determined that the type of the obstacle ahead is a static obstacle, and step S106 is executed.

[0226] When the judgment result is no, that is, the speed v of the obstacle in front F If it is not equal to zero, it is determined that the type of the obstacle ahead is a dynamic obstacle, and step S108 is executed.

[0227] Step S106, determine whether F is satisfied F_S ≤RT LC_F And F LR_S ≤RT LC_LR And F LF_S ≤RT LC_LF .

[0228] Determine the risk F posed by the obstacle in front of the current lane to the vehicle F_S Is it not greater than the braking obstacle avoidance risk threshold RT? B_F , that is, whether F is satisfied F_S ≤RT LC_F When there is a vehicle behind the target lane, the risk F generated by the vehicle behind the target lane is determined. LR_S Does F satisfy LR_S ≤RT LC_LR When there is a preceding vehicle in the target lane, the risk F generated by the preceding vehicle in the target lane to the vehicle is determined. LF_S Does F satisfy LF_S ≤RT LC_LF , where RT LC_F is the risk threshold of the vehicle ahead in the current lane for lane change and obstacle avoidance, RT LC_LR is the risk threshold of the vehicle behind the target lane in lane change and obstacle avoidance, RT LC_LF is the risk threshold of the vehicle ahead in the target lane for lane change and obstacle avoidance.

[0229] When the judgment result is yes, that is, F F_S ≤RT LC_F And F LR_S ≤RT LC_LR And F LF_S ≤RT LC_LF , it is determined that the lane change condition is met, and step S107 is executed.

[0230] When the judgment result is no, that is, F is not satisfied F_S ≤RT LC_F 、F LR_S ≤RT LC_LR and F LF_S ≤RT LC_LF When any of the conditions are met, it is determined that the lane changing condition is not met, and step S111 is executed.

[0231] In particular, when there is no following vehicle behind the target lane, it is determined that F LR_S ≤RT LC_LR When there is no preceding vehicle in the target lane, it is determined that F LF_S ≤RT LC_LF .

[0232] Step S108, determine F F_S Does F satisfy F_S ≤K2*RT B_F .

[0233] In the case where F F_S ≤K1*RT B_F The traffic participant in front of the current lane is determined to be a front obstacle, and the type of the front obstacle is a dynamic obstacle. F_S Is it less than or equal to the second critical risk threshold, that is, whether it satisfies F F_S ≤K2*RT B_F Among them, K2 is the second critical risk factor, K2*RT B_F is the second critical risk threshold, 0<K1<K2<1.

[0234] When the judgment result is yes, that is, F F_S ≤K2*RT B_F , execute step S109. When the judgment result is no, that is, F F_S >K2*RT B_F , execute step S110.

[0235] Step S109: decelerate and avoid obstacles.

[0236] If F F_S ≤K2*RT B_F At this time, according to the relative speed between the vehicle and the obstacle in front, choose the appropriate deceleration to achieve cruise control.

[0237] Furthermore, the deceleration during obstacle avoidance can be determined based on the speed of the obstacle ahead and its relative distance to the vehicle, as well as the vehicle's speed, and only needs to ensure that the vehicle does not collide with the obstacle ahead.

[0238] Step S110, determine whether F is satisfied F_S ≤RT B_F .

[0239] If F F_S >K2*RT B_F At this time, it is impossible to avoid obstacles by normal braking and deceleration with appropriate deceleration. The driving risk F caused by the obstacle in front of the vehicle can be F_Sand the braking obstacle avoidance risk threshold RT B_F The relationship between them is used to determine whether obstacle avoidance can be achieved by emergency braking.

[0240] If F F_S ≤RT B_F At this time, the vehicle can avoid the obstacle by braking at an appropriate deceleration until the vehicle stops, and then execute step S111.

[0241] If F F_S >RT B_F At this time, the vehicle cannot avoid the obstacle by braking to a stop at an appropriate deceleration, and step S106 is executed.

[0242] That is, when the judgment result is yes, step S111 is executed. When the judgment result is no, step S106 is executed.

[0243] Step S111, brake and stop to avoid obstacles.

[0244] In practice, when braking to avoid an obstacle, the vehicle brakes to a stop using an appropriate deceleration rate to avoid the obstacle. The deceleration rate can be determined based on the vehicle's speed, the speed of the obstacle ahead, and the relative distance between the vehicle and the obstacle.

[0245] In particular, if F F_S =RT B_F , then the vehicle needs to have a maximum longitudinal deceleration a determined by the road adhesion coefficient smax Slow down until you stop.

[0246] It should be noted that the lane changing and obstacle avoidance solutions in the above embodiments are mainly illustrated using the front vehicle in the target lane and the rear vehicle in the target lane as examples. In actual traffic scenarios, traffic participants may also include pedestrians, cyclists, temporary construction equipment and other obstacles in addition to vehicles. The specific implementation solution can refer to the description in the above embodiments when there is a vehicle in the target lane, and examples will not be given one by one here.

[0247] The active obstacle avoidance control method for intelligent vehicles provided by the embodiment of the present invention calculates the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold for different obstacle avoidance scenarios, formulates triggering rules for different collision avoidance behaviors, and uses the driving risk quantification assessment method to establish active obstacle avoidance behaviors such as braking obstacle avoidance, lane change obstacle avoidance, and vehicle-following cruise for intelligent vehicles, providing a theoretical judgment basis for subsequent obstacle avoidance decisions. It can achieve the optimal collision avoidance decision based on the status information of the vehicle and surrounding traffic participants in different scenarios, and can meet the requirements for active obstacle avoidance behavior decisions of intelligent vehicles in complex road traffic scenarios, with strong scenario adaptability. In addition, the active obstacle avoidance control method for intelligent vehicles provided by the embodiment of the present invention is not only applicable to a single intelligent vehicle, but can also be adaptively expanded to multi-vehicle collaborative obstacle avoidance behavior decision-making for intelligent connected vehicles, forming a multi-vehicle collaborative obstacle avoidance behavior decision-making system.

[0248] The embodiment of the present invention also provides an intelligent vehicle active obstacle avoidance control device, referring to Figure 11 , a schematic structural diagram of an intelligent vehicle active obstacle avoidance control device according to an embodiment of the present invention is provided. The intelligent vehicle active obstacle avoidance control device 100 may include:

[0249] An acquisition unit 10 is configured to acquire status information of the vehicle and status information of traffic participants around the vehicle, wherein the status information includes position information and motion information;

[0250] An estimation unit 20, configured to estimate the risk posed by each traffic participant to the vehicle based on the vehicle's status information and the status information of each traffic participant;

[0251] A judgment unit 30 is configured to judge whether there is an obstacle ahead of the current lane within a preset driving risk range based on the risk posed by each traffic participant to the vehicle, where the current lane refers to the lane in which the vehicle is currently located;

[0252] The obstacle avoidance strategy determination unit 40 is used to determine the obstacle avoidance strategy when there is the obstacle ahead, based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold, and to perform obstacle avoidance operations corresponding to the determined obstacle avoidance strategy, wherein the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold are both related to the status information of the vehicle and each traffic participant.

[0253] In a specific implementation, the specific working principle and workflow of the intelligent vehicle active obstacle avoidance control device 100 can be found in the description of the intelligent vehicle active obstacle avoidance control method provided in any of the above embodiments of the present invention, and will not be repeated here.

[0254] An embodiment of the present invention also provides a storage medium, which is a non-volatile storage medium or a non-transient storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the description of the intelligent vehicle active obstacle avoidance control method provided in any of the above embodiments of the present invention.

[0255] An embodiment of the present invention also provides a terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor runs the computer program, it executes the description of the intelligent vehicle active obstacle avoidance control method provided in any of the above embodiments of the present invention.

[0256] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even when only a single embodiment is described with respect to specific features. The feature examples provided in the present disclosure are intended to be illustrative, not limiting, unless otherwise stated. In specific implementations, the technical features of one or more dependent claims may be combined with the technical features of the independent claims, depending on actual needs and where technically feasible, and the technical features from the corresponding independent claims may be combined in any appropriate manner rather than solely through the specific combinations listed in the claims.

[0257] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in any computer-readable storage medium, which may include: ROM, RAM, disk or CD, etc.

[0258] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. An active obstacle avoidance control method for an intelligent vehicle, characterized in that: include: Acquire status information of the vehicle and status information of each traffic participant around the vehicle, wherein the status information includes position information and motion information; estimating the risk posed by each traffic participant to the vehicle based on the vehicle's status information and the status information of each traffic participant; Based on the risk posed by each traffic participant to the vehicle, determine whether there is an obstacle ahead of the current lane within the preset driving risk range, where the current lane refers to the lane where the vehicle is currently located; When the obstacle ahead exists, an obstacle avoidance strategy is determined based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold, and an obstacle avoidance operation corresponding to the determined obstacle avoidance strategy is performed, wherein the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are both related to the status information of the vehicle and each traffic participant, and the braking obstacle avoidance risk threshold is calculated based on the status information of the vehicle and each traffic participant, and the lane-changing obstacle avoidance risk threshold is calculated based on the status information of the vehicle and each traffic participant; The estimating the risk posed by each traffic participant to the vehicle based on the vehicle's state information and the state information of each traffic participant includes: estimating the risk posed by each traffic participant to the vehicle using an equivalent dynamics model based on the vehicle's state information and the state information of each traffic participant; When the obstacle ahead exists, determining an obstacle avoidance strategy based on the relationship between the risk posed to the vehicle by each traffic participant and the braking obstacle avoidance risk threshold and the lane change obstacle avoidance risk threshold includes: determining whether a risk posed by the front obstacle to the vehicle is greater than a first critical risk threshold, where the first critical risk threshold is related to the braking obstacle avoidance risk threshold and is less than the braking obstacle avoidance risk threshold; If the risk posed by the front obstacle to the vehicle is greater than the first critical risk threshold, determining the type of the front obstacle according to the motion state of the front obstacle, where the types of the front obstacle include: static obstacles and dynamic obstacles; Determining an obstacle avoidance strategy based on the relationship between the type of the obstacle ahead, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold; determining the obstacle avoidance strategy based on the relationship between the type of the obstacle ahead, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold includes: When the type of the front obstacle is a dynamic obstacle, determining whether the risk posed by the front obstacle to the host vehicle is greater than a second critical risk threshold, where the second critical risk threshold is related to the braking obstacle avoidance risk threshold and is between the first critical risk threshold and the braking obstacle avoidance risk threshold; If the risk posed by the front obstacle to the host vehicle is not greater than the second critical risk threshold, a deceleration is determined based on the status information of the host vehicle and the status information of the front obstacle, and the host vehicle is controlled to decelerate and then cruise after the vehicle according to the determined deceleration.

2. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: The equivalent dynamics model is used to estimate the risk posed by each traffic participant to the vehicle, including: Based on the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle, the equivalent force generated by each traffic participant on the vehicle is estimated, and the estimated equivalent force is used as the risk generated by each traffic participant on the vehicle.

3. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: The equivalent dynamics model is used to estimate the risk posed by each traffic participant to the vehicle, including: Based on the risk focus range, the speed of each traffic participant, the speed of the vehicle, and the relative distance between each traffic participant and the vehicle, the equivalent force exerted by each traffic participant on the vehicle is estimated, and the estimated equivalent force is used as the risk exerted by each traffic participant on the vehicle.

4. The intelligent vehicle active obstacle avoidance control method according to claim 2 or 3, characterized in that: The relative distance between each traffic participant and the vehicle is the relative distance after the actual relative distance between each traffic participant and the vehicle is adjusted using a first gradient adjustment coefficient. The first gradient adjustment coefficient is used to adjust the driving risk range. The first gradient adjustment coefficient is related to the relative distance between the vehicle and each traffic participant, the speed of the vehicle, and the speed of each traffic participant.

5. The intelligent vehicle active obstacle avoidance control method according to claim 4, characterized in that: The relative distance between each traffic participant and the vehicle is the relative distance after the actual relative distance between each traffic participant and the vehicle is adjusted using the first gradient adjustment coefficient and the second gradient adjustment coefficient. The second gradient adjustment coefficient is used to adjust the driving risk range. The second gradient adjustment coefficient is related to the lane line width and / or the length of the vehicle.

6. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: The braking obstacle avoidance risk threshold is calculated as follows: When the speed of the obstacle ahead is less than the speed of the vehicle, the vehicle calculates the longitudinal relative distance between the vehicle and the obstacle ahead when braking at the maximum deceleration without colliding with the obstacle ahead. The minimum longitudinal relative distance required is used as the braking obstacle avoidance safety distance threshold. If the relative longitudinal distance between the host vehicle and the obstacle ahead reaches the braking obstacle avoidance safety distance threshold, braking obstacle avoidance is performed. Based on the state information of the obstacle ahead and the state information of the host vehicle at the time of braking start, the risk posed by the obstacle ahead to the host vehicle at the time of braking start is calculated, and the calculated risk is used as the braking obstacle avoidance risk threshold, where the longitudinal direction refers to the extension direction of the current lane.

7. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: The lane change obstacle avoidance risk thresholds include at least: a lane change obstacle avoidance leading vehicle risk threshold, a lane change obstacle avoidance target lane rear vehicle risk threshold, and a lane change obstacle avoidance target lane leading vehicle risk threshold; The lane change obstacle avoidance leading vehicle risk threshold is calculated in the following manner: the longitudinal relative distance that the host vehicle needs to maintain with the leading obstacle when the host vehicle accelerates at the maximum lateral acceleration to perform lane change obstacle avoidance and does not collide with the leading obstacle is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the first lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the host vehicle and the leading obstacle reaches the first lane change obstacle avoidance safety distance threshold, the lane change obstacle avoidance is performed, and the risk of the leading obstacle to the host vehicle at the start of the lane change is calculated based on the state information of the leading obstacle and the state information of the host vehicle at the start of the lane change, and the calculated risk is used as the lane change obstacle avoidance leading vehicle risk threshold, wherein the longitudinal direction refers to the extension direction of the current lane, and the risk of the leading obstacle to the host vehicle is equivalently quantified as an equivalent force on the host vehicle; The lane change obstacle avoidance target lane rear vehicle risk threshold is calculated in the following manner: the longitudinal relative distance that the vehicle needs to maintain with the vehicle behind the target lane when the vehicle performs lane change obstacle avoidance at the maximum longitudinal acceleration and does not collide with the vehicle behind the target lane is calculated, and the minimum longitudinal relative distance that needs to be maintained is used as the second lane change obstacle avoidance safety distance threshold; if the longitudinal relative distance between the vehicle and the vehicle behind the target lane reaches the second lane change obstacle avoidance safety distance, the lane change obstacle avoidance is performed, and the risk of the vehicle behind the target lane to the vehicle is calculated based on the state information of the vehicle at the start of the lane change and the state information of the vehicle behind the target lane, and the calculated risk is used as the lane change obstacle avoidance target lane rear vehicle risk threshold, wherein the longitudinal direction refers to the extension direction of the current lane, and the risk of the vehicle behind the target lane to the vehicle is equivalently quantified as an equivalent force on the vehicle; The lane change obstacle avoidance target lane leading vehicle risk threshold is calculated as follows: when the speed of the leading vehicle in the target lane is greater than the speed of the obstacle ahead and less than the speed of the host vehicle, the longitudinal relative distance that the host vehicle needs to maintain with the leading vehicle in the target lane when performing lane change obstacle avoidance at the maximum longitudinal deceleration and avoiding collision with the leading vehicle in the target lane is calculated. The minimum longitudinal relative distance that needs to be maintained is used as the third lane change obstacle avoidance safety distance threshold. If the longitudinal relative distance between the host vehicle and the leading vehicle in the target lane reaches the third lane change obstacle avoidance safety distance threshold, the lane change obstacle avoidance is performed. Based on the status information of the host vehicle and the status information of the leading vehicle in the target lane at the start of the lane change, the risk of the leading vehicle in the target lane to the host vehicle at the start of the lane change obstacle avoidance is calculated. The calculated risk is used as the lane change obstacle avoidance target lane leading vehicle risk threshold, where the longitudinal direction refers to the extension direction of the current lane, and the risk of the leading vehicle in the target lane to the host vehicle is equivalently quantified as an equivalent force on the host vehicle.

8. The intelligent vehicle active obstacle avoidance control method according to claim 7, characterized in that: The calculating of the longitudinal relative distance that the vehicle needs to maintain from the obstacle ahead when the vehicle accelerates at the maximum lateral acceleration to perform lane change and avoid collision with the obstacle ahead includes: Calculating the collision moment between the vehicle and the front obstacle during the lane change process based on the vehicle's lateral displacement, the vehicle's mass, and the maximum tire force in the lateral direction, where the lateral displacement is the lateral displacement of the vehicle when the vehicle collides with the front obstacle; Based on the lane change start time, the vehicle's speed, the speed of the obstacle ahead, the vehicle's acceleration, the acceleration / deceleration of the obstacle ahead, and the collision time, the longitudinal relative distance that the vehicle needs to maintain between the vehicle and the obstacle ahead is calculated, where the lateral distance refers to a direction perpendicular to the extension direction of the current lane.

9. The intelligent vehicle active obstacle avoidance control method according to claim 7, characterized in that: The calculation of the longitudinal relative distance that the host vehicle needs to maintain with the vehicle behind the target lane when the host vehicle performs lane change obstacle avoidance at the maximum longitudinal acceleration and does not collide with the vehicle behind the target lane includes: Calculating a minimum lane change time based on a lateral distance between the centerlines of the current lane and the target lane, the mass of the vehicle, and a maximum lateral tire force of the vehicle; Based on the lane change start time, the speed of the vehicle, the speed of the vehicle behind the target lane, the shortest time, the acceleration of the vehicle, and the acceleration / deceleration of the vehicle behind the target lane, the longitudinal relative distance that the vehicle must maintain between the vehicle and the vehicle behind the target lane is calculated, where the lateral distance refers to a direction perpendicular to the extension direction of the current lane.

10. The intelligent vehicle active obstacle avoidance control method according to claim 7, characterized in that: The calculating of the longitudinal relative distance that the host vehicle needs to maintain from the preceding vehicle in the target lane when the host vehicle performs lane change obstacle avoidance at the maximum longitudinal deceleration and does not collide with the preceding vehicle in the target lane includes: Calculating a minimum lane change time based on a lateral distance between the centerlines of the current lane and the target lane, the mass of the vehicle, and a maximum lateral tire force of the vehicle; Based on the start time of lane change obstacle avoidance, the speed of the vehicle, the speed of the vehicle ahead in the target lane, the shortest time, the deceleration of the vehicle ahead, and the acceleration / deceleration of the vehicle ahead in the target lane, the longitudinal relative distance that the vehicle ahead must maintain between the vehicle ahead and the vehicle ahead in the target lane is calculated, where the lateral distance refers to a direction perpendicular to the extension direction of the current lane.

11. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: Also includes: If the risk posed by the obstacle ahead to the vehicle is greater than the second critical risk threshold, determining whether the risk posed by the obstacle ahead to the vehicle is greater than the braking obstacle avoidance risk threshold; If the risk posed by the obstacle ahead to the vehicle is not greater than the braking obstacle avoidance risk threshold, a deceleration is determined based on the vehicle's status information and the obstacle ahead status information, and the vehicle is controlled to decelerate until it stops according to the determined deceleration.

12. The intelligent vehicle active obstacle avoidance control method according to claim 11, characterized in that: Also includes: If the risk posed by the obstacle ahead to the vehicle is greater than the braking obstacle avoidance risk threshold, determine whether the lane change condition is met based on the risk posed to the vehicle by traffic participants in the adjacent lane, the risk of the obstacle ahead, and the lane change obstacle avoidance risk threshold; If the lane change conditions are met, execute lane change and obstacle avoidance; If the lane changing condition is not met, the vehicle is controlled to decelerate at the maximum deceleration until it stops.

13. The intelligent vehicle active obstacle avoidance control method according to claim 1, characterized in that: The determining of the obstacle avoidance strategy according to the type of the obstacle ahead, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the relationship between the lane change obstacle avoidance risk threshold includes: When the type of the obstacle ahead is a static obstacle, determining whether the lane change condition is met based on the risk posed to the vehicle by traffic participants in the adjacent lane, the risk posed by the obstacle ahead, and the lane change obstacle avoidance risk threshold; If the lane change conditions are met, execute lane change and obstacle avoidance; If the lane changing condition is not met, a deceleration is determined based on the status information of the vehicle and the status information of the obstacle ahead, and the vehicle is controlled to decelerate until it stops according to the determined deceleration.

14. The intelligent vehicle active obstacle avoidance control method according to claim 12 or 13, characterized in that: The lane change obstacle avoidance risk threshold includes: a lane change obstacle avoidance leading vehicle risk threshold, a lane change obstacle avoidance target lane rear vehicle risk threshold, and a lane change obstacle avoidance target lane leading vehicle risk threshold. The lane change conditions include: the risk posed by the front obstacle to the vehicle is not greater than the lane change obstacle avoidance leading vehicle risk threshold, and the risk posed by the rear vehicle in the target lane to the vehicle is not greater than the lane change obstacle avoidance target lane rear vehicle risk threshold, and the risk posed by the front vehicle in the target lane to the vehicle is not greater than the lane change obstacle avoidance target lane leading vehicle risk threshold.

15. An intelligent vehicle active obstacle avoidance control device, characterized in that: include: an acquisition unit, configured to acquire status information of the vehicle and status information of traffic participants around the vehicle, wherein the status information includes position information and motion information; an estimating unit, configured to estimate the risk posed by each traffic participant to the vehicle based on the vehicle's status information and the status information of each traffic participant; a judgment unit, configured to judge whether there is an obstacle ahead of the current lane within a preset driving risk range based on the risk posed to the vehicle by each traffic participant, where the current lane refers to the lane in which the vehicle is currently located; an obstacle avoidance strategy determination unit, configured to, when the obstacle ahead is present, determine an obstacle avoidance strategy based on a relationship between a risk posed to the host vehicle by each traffic participant and a braking obstacle avoidance risk threshold and a lane-changing obstacle avoidance risk threshold, and execute an obstacle avoidance operation corresponding to the determined obstacle avoidance strategy, wherein the braking obstacle avoidance risk threshold and the lane-changing obstacle avoidance risk threshold are both related to status information of the host vehicle and each traffic participant; the braking obstacle avoidance risk threshold is calculated based on the status information of the host vehicle and the status information of each traffic participant, and the lane-changing obstacle avoidance risk threshold is calculated based on the status information of the host vehicle and the status information of each traffic participant; The estimation unit is configured to estimate the risk posed by each traffic participant to the vehicle using an equivalent dynamics model based on the vehicle's state information and the state information of each traffic participant; The obstacle avoidance strategy determination unit is used to determine whether the risk posed by the front obstacle to the vehicle is greater than a first critical risk threshold, the first critical risk threshold is related to the braking obstacle avoidance risk threshold and is less than the braking obstacle avoidance risk threshold; if the risk posed by the front obstacle to the vehicle is greater than the first critical risk threshold, the type of the front obstacle is determined according to the motion state of the front obstacle, and the types of the front obstacle include: static obstacles and dynamic obstacles; the obstacle avoidance strategy is determined according to the type of the front obstacle, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold; the obstacle avoidance strategy is determined according to the relationship between the front obstacle and the risk posed by each traffic participant to the vehicle The obstacle avoidance strategy is determined based on the relationship between the type of the obstacle ahead, the risk posed by each traffic participant to the vehicle, the braking obstacle avoidance risk threshold, and the lane change obstacle avoidance risk threshold, including: when the type of the obstacle ahead is a dynamic obstacle, judging whether the risk posed by the obstacle ahead to the vehicle is greater than a second critical risk threshold, the second critical risk threshold is related to the braking obstacle avoidance risk threshold and is between the first critical risk threshold and the braking obstacle avoidance risk threshold; if the risk posed by the obstacle ahead to the vehicle is not greater than the second critical risk threshold, determining a deceleration based on the status information of the vehicle ahead and the status information of the obstacle ahead, and controlling the vehicle to decelerate and then cruise after the vehicle according to the determined deceleration.

16. A storage medium, wherein the storage medium is a non-volatile storage medium or a non-transient storage medium, and a computer program is stored thereon, wherein: When the computer program is executed by a processor, the steps of the intelligent vehicle active obstacle avoidance control method according to any one of claims 1 to 14 are executed.

17. A terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor runs the computer program, the steps of the intelligent vehicle active obstacle avoidance control method according to any one of claims 1 to 14 are executed.

Images