Obstacle avoidance method for negative obstacle and related equipment

Abstract

The invention provides an obstacle avoidance method for a negative obstacle and related equipment, and the method comprises the steps: receiving negative obstacle information and environment information in a vehicle driving process, and the negative obstacle information comprises negative obstacle size information and a negative obstacle position; according to the negative obstacle size information, predicting whether the negative obstacle affects the vehicle to pass through the negative obstacle, and obtaining an influence result of the negative obstacle on the vehicle; under the condition that the influence result of the vehicle is that the negative obstacle affects passing of the vehicle, whether the vehicle can bypass the negative obstacle in the driving process is predicted according to the position of the negative obstacle and the environment information, and a bypass prediction result of the vehicle is obtained; and according to the detouring prediction result, generating an obstacle avoidance strategy of the vehicle. According to the invention, the negative obstacle scene in the vehicle driving process can be identified in combination with the negative obstacle information and the environment information, and the obstacle avoidance strategy is provided for the negative obstacle scene.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an obstacle avoidance method and related equipment for negative obstacles. Background Art

[0002] In recent years, many road collapses have occurred on some mountain roads and winding highways, causing damage to people's lives and property. For negative obstacles such as potholes, holes, fracture surfaces, and collapses that often appear on the road, the existing assisted driving function usually implements an avoidance strategy, but for some small potholes that do not affect the ride experience and driving safety, it is too time-consuming and space-consuming to completely avoid them. Therefore, different obstacle avoidance methods need to be provided for different obstacle avoidance scenarios.

[0003] Since the relevant technology cannot give the optimal obstacle avoidance strategy when the current vehicle passes through negative obstacles, it is particularly important to develop a safe obstacle avoidance method for negative obstacles. Summary of the invention

[0004] In view of this, the present application provides an obstacle avoidance method and related equipment for negative obstacles, which can detect negative obstacles in real time and provide obstacle avoidance strategies.

[0005] A first aspect of an embodiment of the present application provides an obstacle avoidance method for negative obstacles, including receiving negative obstacle information and environmental information during vehicle driving, the negative obstacle information including: negative obstacle size information and negative obstacle position; predicting whether the negative obstacle affects the vehicle's passage through the negative obstacle based on the negative obstacle size information, and obtaining the impact result of the negative obstacle on the vehicle; when the impact result of the vehicle is that the negative obstacle affects the vehicle's passage, predicting whether the vehicle can bypass the negative obstacle during driving based on the negative obstacle position and environmental information, and obtaining the vehicle's bypass prediction result; generating the vehicle's obstacle avoidance strategy based on the bypass prediction result.

[0006] Compared with the related art, the embodiment of the present application has at least the following advantages: by receiving negative obstacle information and environmental information during driving, the impact results of negative obstacles on the vehicle during driving are mined, and the impact results include: predicted passing results, impact results and detour prediction results. According to the impact results, multiple negative obstacle scenarios are identified, the negative obstacle scenario categories are refined, and corresponding obstacle avoidance strategies are executed for different negative obstacle scenarios, and different obstacle avoidance strategies are generated, thereby reducing vehicle obstacle avoidance conflicts and completing the smooth passage of the vehicle through the negative obstacles, thereby reducing damage to the vehicle and ensuring the comfort and sense of security of the passengers in the vehicle.

[0007] Optionally, the method further includes: when the impact result is that the negative obstacle does not affect the passage of the vehicle, executing a first obstacle avoidance strategy, the first obstacle avoidance strategy being used to control the vehicle to maintain a current driving state.

[0008] Optionally, the negative obstacle information also includes a negative obstacle category; based on the detour prediction result, a vehicle obstacle avoidance strategy is generated, including: when the detour prediction result is that there is a detour space, a second obstacle avoidance strategy is generated, and the second obstacle avoidance strategy is used to control the vehicle to pass through the detour space; when the detour prediction result is that there is no detour space, determining whether the vehicle can pass through the negative obstacle based on the negative space obstacle category, and generating an obstacle avoidance strategy based on the determination result of whether the vehicle can pass through the negative obstacle.

[0009] Optionally, an obstacle avoidance strategy is generated based on the determination result of whether the vehicle can pass through the negative obstacle, including: when the determination result is that the vehicle can pass through the negative obstacle, generating a third obstacle avoidance strategy, the third obstacle avoidance strategy is used to control the vehicle to slow down and pass through the negative obstacle; when the determination result is that the vehicle cannot pass through the negative obstacle, generating a fourth obstacle avoidance strategy, the fourth obstacle avoidance strategy is used to control the vehicle to stop driving.

[0010] Optionally, based on the negative obstacle size information, predicting whether the negative obstacle affects the vehicle passing through the negative obstacle, and obtaining the impact result of the negative obstacle on the vehicle, including: obtaining the negative obstacle size and the negative obstacle depth based on the negative obstacle size information; predicting whether the negative obstacle affects the vehicle passing through the negative obstacle based on the negative obstacle size, the negative obstacle depth and the tire width, and obtaining the impact result of the negative obstacle on the vehicle.

[0011] Optionally, based on the negative obstacle position and environmental information, it is predicted whether the vehicle can bypass the negative obstacle during driving to obtain a bypass prediction result of the vehicle, including: determining lane line information based on environmental information; determining the positional relationship between the negative obstacle and the lane line based on the negative obstacle position and lane line information; and determining the bypass prediction result based on the positional relationship.

[0012] Optionally, generating a second obstacle avoidance strategy includes: updating the vehicle's driving path according to the vehicle's current motion state and driving path; generating a third obstacle avoidance strategy includes: planning the vehicle's speed curve according to the vehicle's current motion state and driving path; and enabling the vehicle to pass through negative obstacles based on the speed curve and driving path.

[0013] In a second aspect, the present application provides an obstacle avoidance device for negative obstacles, comprising: The first unit is used to receive negative obstacle information and environmental information during the vehicle driving process, wherein the negative obstacle information includes: negative obstacle size information and negative obstacle position; A second unit is used to predict whether the negative obstacle affects the vehicle passing through the negative obstacle according to the negative obstacle size information, and obtain the impact result of the negative obstacle on the vehicle; A third unit is used for predicting whether the vehicle can bypass the negative obstacle during driving according to the position of the negative obstacle and the environmental information when the impact result of the vehicle is that the negative obstacle affects the passing of the vehicle, so as to obtain a bypass prediction result of the vehicle; A determination unit is used to generate an obstacle avoidance strategy for the vehicle according to the detour prediction result.

[0014] In a third aspect, an embodiment of the present application further provides a vehicle, the vehicle comprising a processor and a memory, the memory being used to store instructions, and the processor being used to call the instructions in the memory so that the vehicle executes the obstacle avoidance method for negative obstacles as in the first aspect.

[0015] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, and the computer program is loaded by a processor to execute the obstacle avoidance method for negative obstacles as in the first aspect.

[0016] The technical effects obtained by the above-mentioned second, third and fourth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of the steps of a method for avoiding negative obstacles provided in one embodiment of the present application.

[0018] Figure 2 A flowchart of the steps of a method for avoiding negative obstacles provided in yet another embodiment of the present application.

[0019] Figure 3 A functional module diagram of an obstacle avoidance device for negative obstacles provided in one embodiment of the present application.

[0020] Figure 4 A schematic diagram of the structure of a vehicle provided in one embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific implementations. It should be noted that the implementations of the present application and the features in the implementations can be combined with each other without conflict.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described implementations are only part of the implementations of the present application, rather than all the implementations.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0024] It should be further noted that, in this article, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0025] In this application, "at least one" means one or more, and "more" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0026] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0027] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given by way of example for reference.

[0028] Road potholes or road potholes refer to the phenomenon of potholes caused by improper design, construction, maintenance, inadequate control, and the influence of natural factors such as climate, environment, geology, and hydrology, as well as vehicle operation and vehicle overloading. Road potholes are usually small, deep, and irregular in shape, and are often found on the surface or joints of concrete slabs.

[0029] Extra-wide road potholes are large-area potholes caused by differential settlement of the new and old roadbeds or construction problems during the process of widening the road. These potholes are usually large and deep, which may affect driving safety and road capacity.

[0030] Subsidence, also known as settlement, is a very common road disease. The road surface sinks due to compression of the foundation soil or other reasons. Settlement usually manifests as partial or overall sinking of the road surface, which may be accompanied by cracks, affecting the flatness and comfort of the road.

[0031] Road collapse refers to the collapse of a road in whole or in part due to geological disasters (such as landslides, earthquakes) or serious construction quality problems. Collapse usually refers to large-scale road damage, which may make the road completely impassable and difficult to repair.

[0032] There are two main numerical methods for solving the optimal control problem: indirect method and direct method. The indirect method is to obtain the first-order necessary conditions for optimality based on the maximum principle or dynamic programming, and then use numerical solution to obtain the optimal control and trajectory.

[0033] The embodiments of the present application provide an obstacle avoidance method and related equipment for negative obstacles, which can detect negative obstacles in real time and provide obstacle avoidance strategies for negative obstacles.

[0034] The obstacle avoidance method for negative obstacles of the present application is applied to vehicles, and its specific process is as follows: Figure 1 As shown, the following steps are included: Step 101: receiving negative obstacle information and environment information during vehicle driving, wherein the negative obstacle information includes: negative obstacle size information and negative obstacle position.

[0035] Among them, the negative obstacle size information includes: the size of the negative obstacle and the depth of the negative obstacle. The size of the negative obstacle is the distance between the two longest points in the negative obstacle boundary. The depth of the negative obstacle is the distance from the deepest point of the negative obstacle to the road surface. The position of the negative obstacle can be the relative position to the lane line, or it can be determined by other calibrated road elements.

[0036] Step 102: predict whether the negative obstacle affects the vehicle passing through the negative obstacle based on the negative obstacle size information, and obtain the impact result of the negative obstacle on the vehicle.

[0037] For some negative obstacles, the vehicle can pass through the negative obstacles, but the negative obstacles are likely to affect the stability of the vehicle's driving. For example, when passing through some negative obstacles, the vehicle chassis may be scratched or the vehicle may lose control. This embodiment determines the impact of the negative obstacle on the vehicle, so that subsequent vehicles can adjust the driving path or driving speed according to the impact result, thereby avoiding accidents during the driving process.

[0038] In one embodiment, based on the negative obstacle size information, it is predicted whether the negative obstacle affects the vehicle passing through the negative obstacle, and the impact result of the negative obstacle on the vehicle is obtained, including: obtaining the negative obstacle size and the negative obstacle depth based on the negative obstacle size information; predicting whether the negative obstacle affects the vehicle passing through the negative obstacle based on the negative obstacle size, the negative obstacle depth and the tire width, and obtaining the impact result of the negative obstacle on the vehicle.

[0039] For example, as long as the size of the negative obstacle is smaller than the width of a single tire, it is considered that the impact result is not affecting the passage of the vehicle. In the case where the size of the negative obstacle is larger than the width of a single tire, it is necessary to further determine whether the depth of the negative obstacle affects the passage of the vehicle. When the depth of the negative obstacle is smaller than the preset depth, the impact result is no impact. When the depth of the negative obstacle is greater than the preset depth, it is considered that the impact result is that the vehicle passes.

[0040] Step 103, when the impact result of the vehicle is that the negative obstacle affects the passing of the vehicle, it is predicted whether the vehicle can bypass the negative obstacle during driving according to the position and environmental information of the negative obstacle, and a bypass prediction result of the vehicle is obtained.

[0041] This embodiment determines the obstacle avoidance space based on the position of the negative obstacle and the environmental information. The size and shape of the obstacle avoidance space directly affect whether the vehicle can safely pass through the negative obstacle. If the obstacle avoidance space is insufficient, the vehicle will collide or the chassis will be scratched when forcibly passing through, resulting in a safety accident.

[0042] In one embodiment, based on the negative obstacle position and environmental information, it is predicted whether the vehicle can bypass the negative obstacle during driving to obtain the vehicle bypass prediction result, including: determining lane line information based on the environmental information; determining the positional relationship between the negative obstacle and the lane line based on the negative obstacle position and the lane line information; and determining the bypass prediction result based on the positional relationship.

[0043] This embodiment determines the obstacle avoidance space by the positional relationship of the lane lines. For example, when a negative obstacle runs through all lane lines ahead, it is considered that there is no detour space for the negative obstacle. When the negative obstacle only occupies part of the lane line, it is necessary to further determine whether the remaining space satisfies the obstacle avoidance space. This embodiment obtains the detour result of the vehicle through the obstacle avoidance space, which helps to optimize the acceleration, deceleration and steering of the vehicle, thereby ensuring that the vehicle passes the negative obstacle smoothly.

[0044] Step 104, based on the detour prediction result, generates an obstacle avoidance strategy for the vehicle.

[0045] The obstacle avoidance strategy of this embodiment comprehensively considers the predicted passing results, impact results and detour prediction results, provides vehicle driving safety, effectively avoids collisions and accidents, and ensures the safety of passengers and pedestrians.

[0046] In one embodiment, the impact result includes not affecting the passage of the vehicle. When the impact result is that the negative obstacle does not affect the passage of the vehicle, the first obstacle avoidance strategy is executed, and the first obstacle avoidance strategy is used to control the vehicle to maintain the current driving state.

[0047] The first obstacle avoidance strategy indicates that the negative obstacle has no effect on the vehicle's driving results. In this embodiment, if there is no negative obstacle on the road ahead or the existing negative obstacle does not affect the normal passage of the vehicle, the auxiliary system does not respond. At this time, the decision result is the first obstacle avoidance strategy "maintain the current state".

[0048] In one embodiment, if Figure 2 As shown, step 104 generates an obstacle avoidance strategy for the vehicle according to the impact result and the detour prediction result, including: Step 1041: When the detour prediction result indicates that there is detour space, a second obstacle avoidance strategy is generated, and the second obstacle avoidance strategy is used to control the vehicle to pass through the detour space.

[0049] If there are negative obstacles on the road ahead that affect the normal passage of the vehicle, and the surrounding environment meets the vehicle's detour conditions (including detour within the lane and detour by borrowing another lane), the auxiliary system will respond to the vehicle's detour. At this time, the decision result is the second obstacle avoidance strategy "execute detour decision".

[0050] Step 1042: When the detour prediction result indicates that there is no detour space, determine whether the vehicle can pass through the negative obstacle according to the negative space obstacle category, and generate an obstacle avoidance strategy based on the determination result of whether the vehicle can pass through the negative obstacle.

[0051] In this embodiment, when the impact result is that a negative obstacle affects the passage of the vehicle, priority is given to whether there is space for detour. If there is space for detour, the second obstacle avoidance strategy is used to detour the vehicle. If there is no space for detour, the third obstacle avoidance strategy is used to slow down the vehicle.

[0052] In one embodiment, when the detour prediction result is that there is no detour space, a determination result is judged, and an obstacle avoidance strategy is generated based on the determination result, including: when the determination result is that the vehicle can pass through the negative obstacle, a third obstacle avoidance strategy is generated, and the third obstacle avoidance strategy is used to control the vehicle to slow down and pass through the negative obstacle; when the determination result is that the vehicle cannot pass through the negative obstacle, a fourth obstacle avoidance strategy is generated, and the fourth obstacle avoidance strategy is used to control the vehicle to stop.

[0053] The predicted passing results include passing and not passing. For negative obstacles that cannot be passed, the vehicle has only two results: detour or stop. Therefore, only the impact of the detour space on the obstacle avoidance strategy needs to be considered. For negative obstacles that can be passed, the vehicle needs to consider the stability of driving by combining the impact results and detour prediction results.

[0054] In this embodiment, if there is a negative obstacle on the road ahead that affects the normal passage of the vehicle, and the surrounding environment does not meet the vehicle's detour conditions (including detour within the lane and detour via another lane) but the negative obstacle allows the vehicle to pass, the auxiliary system will respond by decelerating the vehicle. At this time, the decision result is the third obstacle avoidance strategy "execute slow-moving decision".

[0055] In this embodiment, if there is a negative obstacle on the road ahead that affects the normal passage of the vehicle, and the surrounding environment does not meet the vehicle's detour conditions (including detour within the lane and detour by borrowing lanes) and it is impossible to pass, the auxiliary system will respond with a parking request and make a driving takeover request. At this time, the decision result is "brake stop, driving task takeover.

[0056] In this embodiment, the negative obstacle categories include negative obstacles including first category negative obstacles, second category negative obstacles, and third category negative obstacles. The first category negative obstacles include potholes, the second category negative obstacles include extra-wide potholes, and the third category negative obstacles include road collapse and settlement. According to the negative obstacle category, it is predicted whether the vehicle can drive through the negative obstacle to obtain a predicted passing result, including: when the category of the negative obstacle is the third category negative obstacle, the road structure of the road on which the vehicle is driving is detected. When the road structure does not conform to the preset road structure, the prediction result is that the vehicle cannot pass.

[0057] In this embodiment, the preset road structure can be a half-complete road structure. If it is detected that the collapse causes the lane within one-half of the front to disappear, a detour decision is executed. If the collapse occupies more than one-half of the road width in front to disappear, it is considered that the vehicle cannot pass.

[0058] In one embodiment, based on the negative obstacle position and environmental information, it is predicted whether the vehicle can bypass the negative obstacle during driving to obtain the vehicle bypass prediction result, including: determining lane line information based on the environmental information; determining the positional relationship between the negative obstacle and the lane line based on the negative obstacle position and the lane line information; and determining the bypass prediction result based on the positional relationship.

[0059] In one embodiment, generating a second obstacle avoidance strategy includes: updating the vehicle's driving path according to the vehicle's current motion state and driving path; generating a third obstacle avoidance strategy includes: planning the vehicle's speed curve according to the vehicle's current motion state and driving path; and enabling the vehicle to pass through negative obstacles based on the speed curve and the driving path.

[0060] In a specific embodiment, both the second obstacle avoidance strategy and the third strategy adopt optimal trajectory planning, and plan the future path and speed of the vehicle according to the result of the obstacle avoidance decision; if the decision result is the second obstacle avoidance strategy, the auxiliary system plans the optimal obstacle avoidance detour trajectory based on the current vehicle motion state, including a reference path and a speed curve; if the decision result is the third obstacle avoidance strategy, the auxiliary system plans the optimal speed curve based on the current vehicle motion state, and the reference path remains unchanged.

[0061] In this example, both the second obstacle avoidance strategy and the third obstacle avoidance strategy can be solved based on the optimal control problem (OCP). The OCP problem usually includes an objective function that needs to be minimized or maximized, as well as some inequality and equality constraints.

[0062] For example, in the second obstacle avoidance strategy, trajectory (including path and speed) planning is regarded as a constrained optimization problem, which is described by formulas (1) to (3): Formula (1); Formula (2); Formula (3); Among them, in formula (1) is the objective function of OCP, and in formula (2) is the inequality constraint of OCP, and is the equality constraint of OCP.

[0063] For formula (1) to formula (3), the constraint function needs to consider the vehicle kinematic and dynamic constraints, the boundary value constraints of the starting point and the end point, and the safety constraints of avoiding collision with surrounding negative obstacles. Therefore, formula (1) is the objective function constraint, which is the function expression for minimizing or maximizing the objective function. Formula (2) is the boundary condition constraint, and formula (3) is the collision constraint. For the specific formulas of formula (1), formula (2) and formula (3), see formula (4) to formula (9).

[0064] In this embodiment, the vehicle kinematics and dynamics are derived using a two-degree-of-freedom model, and the final two-degree-of-freedom kinematic model of the vehicle is obtained. The vehicle's motion model can be represented by a differential equation of formula (4), which includes: Formula (4); Among them, formula (4) introduces the steering angle and uses the inertial coordinate system to describe the vehicle coordinates. is the yaw rate , which represents the rate of change of the steering angle over time, that is, the change of the steering angle per unit time. is the displacement of the vehicle in the X direction, is the displacement of the vehicle in the Y direction. is the vehicle wheelbase, is the acceleration, is the steering angular velocity, β and ψ are the steering component velocities at different times. For the boundary value constraints of formula (4), the initial state of the vehicle is Known, terminal state It is determined according to the requirements. Generally speaking, it is necessary to ensure that the vehicle reaches the specified position at the final moment, and the state quantities such as lateral velocity, acceleration and yaw angular velocity are all 0, that is, the speed at the final moment is as shown in formula (5): Formula (5); In formula (5), represents the displacement increment of the vehicle in the X direction at each moment, Represents the displacement increment of the vehicle in the Y direction at each moment. and Indicates that when the vehicle is in the final state, the movement is 0. , and It means that the state variables such as lateral velocity, acceleration and yaw rate are all 0.

[0065] According to formula (1) to formula (5), the second obstacle avoidance strategy of negative obstacles under different spatial conditions can be obtained to determine the driving path of the vehicle.

[0066] When executing the third obstacle avoidance strategy, when the vehicle is slowing down, the vehicle determines the longitudinal speed at the end moment according to the passing speed set upstream; when executing the second obstacle avoidance strategy, when the vehicle is avoiding obstacles, the vehicle determines the lateral position at the end moment according to the detour lateral distance set upstream.

[0067] The collision constraint can be simplified by using the single circle method to describe the contour of the vehicle and reduce the nonlinearity of the constraint. For vehicles of different sizes, the outer contour can be represented by the circumscribed circles of the vehicle body with different radii, as shown in the figure. Therefore, the collision constraint can be expressed by formula (6): Formula (6); Formula (6) represents the position coordinates of vehicle 1 ( , ), the position coordinates of vehicle 2 ( , ), the circumscribed circle of vehicle 1 is , the outer circle of vehicle 2 is .

[0068] The setting of the objective function also needs to be confirmed according to the actual scenario. For the second obstacle avoidance strategy "detour decision" scenario, the target expectation is that the vehicle is as close to the expected lateral position as possible at the end of the task. For the second obstacle avoidance strategy "slow down decision" scenario, the target expectation is that the vehicle reaches the expected longitudinal speed as much as possible at the end of the task. The expected conditions are shown in formula (7) and formula (8): Formula (7); Formula (8); in, To ensure that the vehicle is as close as possible to the desired lateral position at the end of the mission The expected conditions, The vehicle should reach the expected longitudinal speed as much as possible at the end of the mission. expected conditions.

[0069] In addition, ensuring the comfort of the occupants during the mission is the primary task besides safety. Therefore, the speed change and steering angular velocity during the process also need to be as small as possible. The expected conditions are shown in formulas (9) and (10): Formula (9); Formula (10); The desired condition for the vehicle to have the smallest possible acceleration during motion is: It is a desired condition that the steering angular velocity is as small as possible during vehicle motion.

[0070] Finally, the objective function formula (1) can be expressed as The complete trajectory planning problem can be summarized as follows: setting the objective function formula (1), setting motion conditions for the objective function, such as vehicle kinematic constraints formulas (4) to (5), boundary condition constraints formulas (7) to (10), and collision constraints such as formula (6).

[0071] In this embodiment, the negative obstacle categories include first category negative obstacles, second category negative obstacles, and third category negative obstacles. The first category negative obstacles include potholes, the second category negative obstacles include extra-wide potholes, and the third category negative obstacles include road collapse and settlement. Usually, the negative obstacle category is determined based on the reflection information of the road image and the laser radar point cloud.

[0072] In a specific embodiment, for the first type of negative obstacle, based on the reflection information of the road image and the laser radar point cloud, if the width of the identified road negative obstacle is less than 1 / 2 of the width of the lane where the current vehicle is located and the distance between the deepest point of the negative obstacle and the horizontal plane of the road is less than 15 cm, it is defined as the first type of negative obstacle, that is, a pothole. For the second type of negative obstacle, if the width of the identified road negative obstacle is greater than 1 / 2 of the width of the lane where the current vehicle is located and the distance between the negative obstacle and the horizontal plane of the road is less than 15 cm, it is defined as the second type of negative obstacle. For the third type of negative obstacle, if the identified lane has a pothole or settlement with a distance greater than 15 cm from the horizontal plane of the road or the radar point cloud does not reflect depth information and the continuous road elements and road structures on the ground suddenly disappear (for example, continuous lane lines, continuous road edge lines, continuous curbs disappear, etc.), it is defined as the third type of negative obstacle.

[0073] For the first and second types of negative obstacles, the vehicle can pass through, but the impact of passing must be considered, and only the impact result and detour prediction result need to be judged. For the third round of negative obstacles, the vehicle needs to further judge whether it will be unable to pass through the negative obstacle.

[0074] In a specific embodiment, performing obstacle avoidance according to obstacle categories includes: For the first type of obstacles, the first type of obstacles are potholes, which are predicted to be passable obstacles. In this embodiment, the negative obstacle size information is obtained as the width of the pothole on the road, and the width of a single tire is used as the threshold. If the width of the pothole is smaller than the width of a single tire, the impact result is judged to not affect the smooth passage of the vehicle, and the corresponding vehicle control strategies are all output as the "first obstacle avoidance strategy". If the width of the pothole is greater than the width of a single tire and the depth is less than 5cm, the impact result is judged to affect the smooth passage of the vehicle, and the detour space of the pothole needs to be determined in one step. Since the detour space of the first type of obstacles is sufficient, the "second obstacle avoidance strategy" can be directly output.

[0075] For the second type of obstacles, in the ultra-wide road pothole scene, the second type of obstacles are potholes, which are predicted to be passable obstacles. If the negative space obstacle only passes through the front lane, there is a detour space. The vehicle control strategy is determined based on its depth. If the pothole depth is greater than 5cm, when there is detour space, the second obstacle avoidance strategy "execute detour decision" is output; when there is no detour space, the third obstacle avoidance strategy "execute slow strategy" is output. If the pothole depth is less than 5cm, the first obstacle avoidance strategy "maintain current state" is output. If the negative space obstacle passes through all lanes ahead, it is determined only based on the depth. If the depth is greater than 5cm, "execute slow decision" is output, and if the pothole is less than 5cm, "maintain current state" is output.

[0076] For the third type of obstacles, such as road collapse scenarios, it is necessary to further determine whether the vehicle is unable to drive through the negative obstacle category. In the road collapse scenario, if the collapse causes the lane within one-half of the front to disappear, a detour decision is executed. If the collapse occupies more than one-half of the road width in front and is judged to be an impassable negative obstacle category, it is necessary to additionally determine whether there is detour space. If there is detour space, the output is "execute detour decision", and if there is no detour space, the output is "brake stop, driving task take over".

[0077] like Figure 3 As shown, the second aspect provides an obstacle avoidance device for negative obstacles, including: a first unit 301, a second unit 302, a third unit 303 and a determination unit 304.

[0078] The first unit 301 is used to receive negative obstacle information and environment information during the driving process of the vehicle, wherein the negative obstacle information includes: negative obstacle size information and negative obstacle position; The second unit 302 is used to predict whether the negative obstacle affects the vehicle passing through the negative obstacle according to the negative obstacle size information, and obtain the impact result of the negative obstacle on the vehicle; The third unit 303 is used to predict whether the vehicle can bypass the negative obstacle during driving according to the position and environment information of the negative obstacle when the impact result of the vehicle is that the negative obstacle affects the vehicle's passing, and obtain a bypass prediction result of the vehicle; The determination unit 304 is used to generate an obstacle avoidance strategy for the vehicle according to the detour prediction result.

[0079] Please refer to Figure 4 , Figure 4 It is a schematic diagram of an embodiment of a vehicle of the present application.

[0080] The vehicle 100 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30. When the processor 30 executes the computer program 40, the steps in the above-mentioned obstacle avoidance method embodiment for negative obstacles are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0081] Exemplarily, the computer program 40 can also be divided into one or more modules / units, one or more modules / units are stored in the memory 20 and executed by the processor 30. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the vehicle 100. For example, it can be divided into the first data unit 301, the second unit 302, the third unit 303 and the determination unit 304 shown.

[0082] Those skilled in the art will appreciate that the schematic diagram is merely an example of the vehicle 100 and does not constitute a limitation on the vehicle 100 , which may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the vehicle 100 may also include input and output devices, network access devices, buses, etc.

[0083] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, a single-chip microcomputer, or the processor 30 may also be any conventional processor, etc.

[0084] The memory 20 can be used to store the computer program 40 and / or the module / unit. The processor 30 realizes various functions of the vehicle 100 by running or executing the computer program and / or the module / unit stored in the memory 20 and calling the data stored in the memory 20. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the vehicle 100, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0085] If the module / unit integrated in the vehicle 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

Claims

1. An obstacle avoidance method for negative obstacles, applied to a vehicle, characterized in that: include: Receiving negative obstacle information and environment information during the driving of the vehicle, wherein the negative obstacle information includes: negative obstacle size information and negative obstacle position; Predicting, based on the negative obstacle size information, whether the negative obstacle affects the vehicle passing through the negative obstacle, and obtaining an impact result of the negative obstacle on the vehicle; In the case where the impact result of the vehicle is that the negative obstacle affects the passing of the vehicle, predicting whether the vehicle can bypass the negative obstacle during driving according to the position of the negative obstacle and the environmental information, and obtaining a bypass prediction result of the vehicle; An obstacle avoidance strategy for the vehicle is generated according to the detour prediction result.

2. The method according to claim 1, characterized in that The method further comprises: When the impact result is that the negative obstacle does not affect the passage of the vehicle, a first obstacle avoidance strategy is executed, where the first obstacle avoidance strategy is used to control the vehicle to maintain a current driving state.

3. The method according to claim 1, characterized in that The negative obstacle information also includes a negative obstacle category; and generating an obstacle avoidance strategy for the vehicle according to the detour prediction result includes: When the detour prediction result indicates that there is a detour space, generating a second obstacle avoidance strategy, wherein the second obstacle avoidance strategy is used to control the vehicle to pass through the detour space; When the detour prediction result is that there is no detour space, whether the vehicle can pass through the negative obstacle is determined according to the negative space obstacle category, and the obstacle avoidance strategy is generated based on the determination result of whether the vehicle can pass through the negative obstacle.

4. The method according to claim 3, characterized in that The generating the obstacle avoidance strategy based on the determination result of whether the vehicle can pass through the negative obstacle comprises: If the determination result is that the vehicle can pass through the negative obstacle, generating a third obstacle avoidance strategy, wherein the third obstacle avoidance strategy is used to control the vehicle to decelerate and pass through the negative obstacle; When the determination result is that the vehicle cannot pass through the negative obstacle, a fourth obstacle avoidance strategy is generated, and the fourth obstacle avoidance strategy is used to control the vehicle to stop traveling.

5. The method according to claim 1, characterized in that The predicting, based on the negative obstacle size information, whether the negative obstacle affects the vehicle passing through the negative obstacle, and obtaining the impact result of the negative obstacle on the vehicle includes: According to the negative obstacle size information, obtaining the negative obstacle size and the negative obstacle depth; According to the size of the negative obstacle, the depth of the negative obstacle and the tire width of the vehicle, it is predicted whether the negative obstacle affects the vehicle passing through the negative obstacle, and the impact result of the negative obstacle on the vehicle is obtained.

6. The method according to claim 1, characterized in that The predicting, based on the negative obstacle position and the environmental information, whether the vehicle can bypass the negative obstacle during driving, and obtaining the bypass prediction result of the vehicle includes: Determine lane line information according to the environmental information; Determining a positional relationship between the negative obstacle and the lane line according to the negative obstacle position and lane line information; The detour prediction result is determined according to the positional relationship.

7. The method according to claim 4, characterized in that The generating of the second obstacle avoidance strategy includes: updating the driving path of the vehicle according to the current motion state and driving path of the vehicle; The generating the third obstacle avoidance strategy comprises: Planning a speed curve of the vehicle according to the current motion state of the vehicle and the driving path; Based on the speed profile and the driving path, the vehicle passes the negative obstacle.

8. An obstacle avoidance device for negative obstacles, characterized in that: include: The first unit is used to receive negative obstacle information and environmental information during the vehicle driving process, wherein the negative obstacle information includes: negative obstacle size information and negative obstacle position; A second unit is used to predict whether the negative obstacle affects the vehicle passing through the negative obstacle according to the negative obstacle size information, and obtain the impact result of the negative obstacle on the vehicle; A third unit is used for predicting whether the vehicle can bypass the negative obstacle during driving according to the position of the negative obstacle and the environmental information when the impact result of the vehicle is that the negative obstacle affects the passing of the vehicle, so as to obtain a bypass prediction result of the vehicle; A determination unit is used to generate an obstacle avoidance strategy for the vehicle according to the detour prediction result.

9. A vehicle, comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the vehicle executes the obstacle avoidance method for negative obstacles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the obstacle avoidance method for negative obstacles according to any one of claims 1 to 7.

Images