An obstacle avoidance path planning method and system for an unmanned vehicle

Abstract

This invention discloses an obstacle avoidance path planning method for autonomous vehicles, relating to the field of autonomous vehicle technology, to address the problem that current autonomous vehicles cannot smoothly avoid obstacles encountered ahead. The method includes real-time detection of the vehicle's current lane and the movement of obstacles in adjacent lanes; when an obstacle is detected ahead of the current lane, determining whether avoidance is necessary; determining an appropriate motion path planning strategy; planning a smooth obstacle avoidance path based on the current vehicle's path and the paths of obstacles in the preceding and adjacent lanes; and implementing obstacle avoidance maneuvers by changing lanes, decelerating, braking, or bypassing the obstacle according to the planned path. This invention also discloses an obstacle avoidance path planning system for autonomous vehicles. This invention can adapt to various road traffic conditions, smoothly and safely bypassing obstacles in front of the autonomous vehicle, improving passenger comfort.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle technology, and in particular to an obstacle avoidance path planning method and system for autonomous vehicles. Background Technology

[0002] In the current technology, the obstacle avoidance strategies of autonomous vehicles are not very perfect. Most control schemes are simply to avoid or brake, without considering the road conditions of adjacent lanes. This makes them very easy to be rear-ended by vehicles behind, which can lead to danger. Some vehicles may also make meaningless lane changes, causing serious discomfort to passengers and even causing danger.

[0003] The application number CN201611246679.8 describes a driving device and strategy for unmanned vehicles in foggy and dusty weather. It proposes a solution for how unmanned vehicles can plan driving routes in severe weather. The solution analyzes the current weather conditions based on the collected information, then determines whether the information collected by the vehicle identification device is usable, and then formulates the corresponding specific driving strategy.

[0004] The aforementioned patent proposes driving strategies in adverse environments, enabling driving even when the driver's visibility is poor. However, it does not address solutions for obstacles in the lane. Therefore, in-depth research is urgently needed on how to enable autonomous vehicles to comprehensively consider road traffic conditions and smoothly navigate around obstacles. Summary of the Invention

[0005] This invention provides a method and system for obstacle avoidance path planning for autonomous vehicles, which solves the problem that current autonomous vehicles cannot smoothly avoid obstacles when they encounter them in front of them.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] An obstacle avoidance path planning method for autonomous vehicles includes the following steps:

[0008] S100 can detect the current lane of the vehicle and the movement of obstacles in the adjacent lanes on both sides in real time.

[0009] S200: When an obstacle is detected in front of the current lane, the distance and speed difference between the vehicle and the obstacle are obtained to determine whether it is necessary to avoid it.

[0010] S300 determines an appropriate motion path planning strategy when avoidance is required;

[0011] The S400 plans a smooth obstacle avoidance path based on the current vehicle's driving path and the driving paths of obstacles in front and in adjacent lanes on both sides.

[0012] The S500 can perform obstacle avoidance operations by changing lanes, slowing down and braking, or going around obstacles according to the planned obstacle avoidance path.

[0013] This invention detects the road traffic conditions of an autonomous vehicle in its current lane and the two adjacent lanes. When an obstacle is detected in front of the vehicle in the current lane, the invention plans a relatively smooth driving path by combining the obstacle and the traffic conditions of the adjacent lanes, and achieves this by changing lanes, slowing down and braking, or going around the obstacle.

[0014] Furthermore, in step S200, when an obstacle is detected in front of the current lane, it is also necessary to confirm the type of obstacle.

[0015] By identifying the type of obstacle ahead, it can be ensured that autonomous vehicles will not decelerate, brake, or change lanes in a way that violates common sense, thereby reducing dangerous driving behavior and improving passenger comfort.

[0016] Further, the steps for determining the type of obstacle include:

[0017] S201, when an obstacle vehicle is detected directly in front of the current lane, or when an adjacent lane on one side is driving over the lane line of this vehicle and encroaching on the area of ​​this vehicle's lane for more than a predetermined threshold, and at this time there is no obstacle vehicle in front of the other adjacent lane and no vehicle behind with a speed exceeding a predetermined value, the type of obstacle in front is determined to be a lane-changing obstacle.

[0018] S202, when an obstacle vehicle is detected directly in front of the current lane, and there are also obstacle vehicles in front of and behind the adjacent lanes at a speed exceeding a predetermined value, the type of obstacle ahead is determined to be a brakeable obstacle.

[0019] S203, when it is detected that the vehicle is traveling in an adjacent lane on one side and the area of ​​the vehicle's lane encroaching on the lane is greater than a predetermined threshold, and at this time there is an obstacle vehicle in front of the other lane or a vehicle behind with a speed exceeding a predetermined value, the type of obstacle in front is determined to be a braking obstacle.

[0020] S204, when it is detected that the vehicle is traveling in an adjacent lane on one side and the area of ​​the vehicle encroaching on the lane of the vehicle is less than a predetermined threshold, the type of obstacle ahead is determined to be an obstacle that should be bypassed.

[0021] Based on the road conditions of the current lane and adjacent lanes, obstacles ahead are classified into three types: obstacles suitable for lane changing, obstacles suitable for braking, and obstacles suitable for bypassing. Then, driving routes are planned for different types of obstacles to enable autonomous vehicles to smoothly avoid obstacles.

[0022] Furthermore, the step of determining the corresponding obstacle avoidance route based on the type of obstacle includes:

[0023] S301, when it is determined that the obstacle ahead is a suitable obstacle for lane changing, the lane changing route to the adjacent lane shall be determined according to the lane changing planning strategy;

[0024] S302, When it is determined that the obstacle ahead is a suitable obstacle for braking, the braking force is determined based on the deceleration braking strategy and the distance and speed to the obstacle ahead;

[0025] S303, when it is determined that the obstacle ahead is a suitable obstacle to bypass, the optimal bypass route is determined according to the obstacle bypass strategy.

[0026] Once the autonomous vehicle identifies the type of obstacle ahead, it plans different avoidance methods based on the type of obstacle to avoid unnecessary driving maneuvers that could affect the driving comfort of the autonomous vehicle.

[0027] Furthermore, the optimal route planning steps for the obstacle avoidance route are as follows:

[0028] S330: Determine an initial azimuth point directly in front of the current driving trajectory; select multiple candidate azimuth points at small intervals along the vertical direction of the trajectory line at the initial azimuth point; and form multiple smooth obstacle avoidance trajectories based on the current position, current driving direction, and driving direction of each candidate azimuth point.

[0029] S331. Based on three factors—the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance—select the optimal obstacle avoidance trajectory from among multiple obstacle avoidance trajectories.

[0030] The vehicle's computer plans an obstacle avoidance route for the autonomous vehicle based on the traffic conditions of the current lane and adjacent lanes. The planning principle is mainly based on a smooth line composed of a sufficient number of dense points, which allows the autonomous vehicle to avoid or bypass obstacles as it moves along this smooth line.

[0031] Furthermore, the specific steps for selecting an optimal obstacle avoidance trajectory are as follows:

[0032] S3310, obtain the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the vehicle in the adjacent lane;

[0033] S3311, obtain the first instantaneous relative distance between each obstacle avoidance trajectory and the obstacle in front;

[0034] S3312, obtain the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane;

[0035] S3313, Multiply the lateral spacing, the first instantaneous relative distance and the second instantaneous relative distance corresponding to each obstacle avoidance trajectory by their respective pre-weighting factors and sum them up to obtain the total obstacle avoidance parameters;

[0036] S3314, the obstacle-avoidance trajectory with the smallest total obstacle-avoidance parameters is determined as the optimal obstacle-avoidance trajectory.

[0037] Based on the distances between the autonomous vehicle and the obstacles ahead and the vehicles on both sides, and by summing the three numbers using their respective weighting factors, the total obstacle avoidance parameters for the route can be obtained. By comparing the total obstacle avoidance parameters of multiple obstacle avoidance trajectories, the optimal obstacle avoidance trajectory can be determined.

[0038] This invention also discloses an obstacle avoidance path planning system for autonomous vehicles, comprising:

[0039] The real-time traffic condition recognition unit is used to detect and recognize the traffic conditions of the lane where the car is currently located and the adjacent lanes on both sides in real time; that is, to recognize the surrounding situation of the current driverless car in real time.

[0040] The obstacle type recognition unit is used to detect the type of obstacle in front of the current lane, including: obstacles suitable for lane changing, obstacles suitable for braking, and obstacles suitable for bypassing; detecting obstacles in front of the lane facilitates obstacle avoidance operations for the current autonomous vehicle.

[0041] The strategy determination unit determines the corresponding motion path planning strategy based on the obstacle type, including lane changing strategy, deceleration strategy and obstacle avoidance strategy; and plans the corresponding obstacle avoidance strategy based on the obstacle type identified by the obstacle type identification unit.

[0042] The execution unit is used to execute the motion path planning strategy determined by the strategy determination unit, which is achieved by changing lanes, decelerating and braking, or bypassing obstacles. According to the obstacle avoidance strategy determined by the strategy determination unit, the execution unit performs the corresponding obstacle avoidance operation.

[0043] Furthermore, the strategy determination unit includes:

[0044] The lane change strategy determination unit is used to determine the lane change route on the side where there are no vehicles in the adjacent lanes when the obstacle ahead is a suitable lane change obstacle; when the obstacle ahead is identified as a suitable lane change obstacle, the lane change strategy determination unit determines the next lane change route.

[0045] The deceleration strategy determination unit is used to determine the braking force based on the deceleration braking strategy and the distance to the obstacle when the obstacle in front is a suitable braking obstacle; when the obstacle in front is identified as a suitable braking obstacle, the deceleration strategy determination unit determines the next braking force to ensure that the vehicle will not collide with the obstacle in front.

[0046] The obstacle avoidance strategy determination unit is used to plan the optimal obstacle avoidance route according to the obstacle avoidance planning strategy when the obstacle in front is an obstacle that should be avoided. When the obstacle in front is identified as an obstacle that should be avoided, the obstacle avoidance strategy determination unit determines the next optimal obstacle avoidance route, thereby reducing the invalid obstacle avoidance actions of the current autonomous vehicle and improving the riding experience.

[0047] Furthermore, the obstacle avoidance strategy determination unit includes:

[0048] The obstacle avoidance trajectory acquisition unit is used to determine an initial azimuth point directly in front of the current driving trajectory, select multiple candidate azimuth points at small intervals along the vertical direction of the trajectory line at the initial azimuth point, and then form multiple smooth obstacle avoidance trajectories based on the current position, the current driving direction, and the driving direction of each candidate azimuth point; select multiple candidate azimuth points on the simulated obstacle avoidance route, and form a smooth driving route from the multiple candidate azimuth points to ensure that the vehicle can smoothly bypass the obstacle in front.

[0049] The obstacle avoidance trajectory determination unit is used to select the optimal obstacle avoidance trajectory from multiple obstacle avoidance trajectories based on three factors: the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance. The optimal obstacle avoidance trajectory is obtained by precise numerical calculation and comparison.

[0050] Furthermore, the obstacle avoidance trajectory determination unit includes:

[0051] The lateral spacing acquisition unit is used to acquire the lateral spacing between each obstacle avoidance trajectory and the obstacle in front or the obstacle vehicle in the adjacent lane; and to acquire the lateral spacing between the autonomous vehicle and the obstacle in front and the current autonomous vehicle and the obstacle vehicle in the adjacent lane on the planned obstacle avoidance trajectory.

[0052] The first instantaneous relative distance acquisition unit is used to acquire the first instantaneous relative distance between each obstacle avoidance trajectory and the obstacle in front; and to acquire the first instantaneous relative distance between the current autonomous vehicle and the obstacle in front on the planned obstacle avoidance trajectory.

[0053] The second instantaneous relative distance acquisition unit is used to acquire the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane; and to acquire the second instantaneous relative distance between the current autonomous vehicle and the obstacle vehicle in the adjacent lane on the planned obstacle avoidance trajectory.

[0054] The weighted calculation unit multiplies the lateral spacing, first instantaneous relative distance, and second instantaneous relative distance corresponding to each obstacle avoidance trajectory by their respective pre-weighting factors and sums them to obtain the total obstacle avoidance parameters; it is used to multiply the acquired data by their respective weighting factors and add them together to obtain the final total obstacle avoidance parameters.

[0055] The optimal obstacle avoidance trajectory determination unit determines the obstacle avoidance trajectory with the smallest total obstacle avoidance parameters. It compares the total obstacle avoidance coefficients of multiple obstacle avoidance trajectories calculated by the weighted calculation unit to determine the optimal obstacle avoidance trajectory. The vehicle computer then inputs the result to the execution unit to control the autonomous vehicle to avoid obstacles. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating an obstacle avoidance path planning method for an unmanned vehicle provided by the present invention.

[0057] Figure 2 This is a preferred embodiment of step S200 of the obstacle avoidance path planning method for an unmanned vehicle provided by the present invention;

[0058] Figure 3 This is a preferred embodiment of step S300 of the obstacle avoidance path planning method for an unmanned vehicle provided by the present invention;

[0059] Figure 4 This is a schematic diagram of the first traffic condition in an obstacle avoidance path planning method for an unmanned vehicle provided by the present invention.

[0060] Figure 5 This is a schematic diagram of a second traffic situation in an obstacle avoidance path planning method for unmanned vehicles provided by the present invention.

[0061] Figure 6 This is a schematic diagram of a third traffic condition in an obstacle avoidance path planning method for unmanned vehicles provided by the present invention.

[0062] Figure 7 This is a schematic diagram of the fourth traffic condition in the obstacle avoidance path planning method for unmanned vehicles provided by the present invention;

[0063] Figure 8 This is a schematic diagram of the fifth traffic condition in the obstacle avoidance path planning method for unmanned vehicles provided by the present invention;

[0064] Figure 9 A schematic diagram illustrating the path planning principle of an obstacle avoidance path planning method for unmanned vehicles provided by the present invention;

[0065] Figure 10 This is a schematic diagram of the structure of an obstacle avoidance path planning system for an unmanned vehicle provided by the present invention;

[0066] Figure 11 This invention provides a schematic diagram of the structure of a strategy determination unit in an obstacle avoidance path planning system for unmanned vehicles.

[0067] Figure 12 This is a schematic diagram of the structure of an obstacle avoidance strategy determination unit in an obstacle avoidance path planning system for unmanned vehicles provided by the present invention;

[0068] Figure 13 This is a schematic diagram of the obstacle avoidance trajectory judgment unit in an obstacle avoidance path planning system for unmanned vehicles provided by the present invention.

[0069] Attached reference numerals: 100 - Real-time traffic condition recognition unit; 200 - Obstacle type recognition unit; 300 - Strategy determination unit; 400 - Execution unit;

[0070] 301 - Lane change strategy determination unit; 302 - Deceleration strategy determination unit; 303 - Obstacle avoidance strategy determination unit;

[0071] 330 - Obstacle trajectory acquisition unit; 331 - Obstacle trajectory judgment unit;

[0072] 3310 - Lateral spacing acquisition unit; 3311 - First instantaneous relative distance acquisition unit; 3312 - Second instantaneous relative distance acquisition unit; 3313 - Weighted calculation unit; 3314 - Optimal obstacle avoidance trajectory determination unit. Detailed Implementation

[0073] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0074] In the description of this invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0075] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0076] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. Furthermore, when describing pipelines or channels, the terms "connection" and "linking" used in this application have the meaning of establishing electrical conductivity. The specific meaning needs to be understood in conjunction with the context.

[0077] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0078] In the current technology, the obstacle avoidance strategies of autonomous vehicles are not very perfect. Most control schemes are simply to avoid or brake, without considering the road conditions of adjacent lanes. This makes them very easy to be rear-ended by vehicles behind, which can lead to danger. Some vehicles may also make meaningless lane changes, causing serious discomfort to passengers and even causing danger.

[0079] The aforementioned patent proposes driving strategies in adverse environments, enabling driving even when the driver's visibility is poor. However, it does not address solutions for obstacles in the lane. Therefore, in-depth research is urgently needed on how to enable autonomous vehicles to comprehensively consider road traffic conditions and smoothly navigate around obstacles.

[0080] To address the aforementioned problems, the present invention provides a method and system for obstacle avoidance path planning of unmanned vehicles, with reference to the accompanying drawings.

[0081] like Figure 1 The diagram shown is a flowchart of an obstacle avoidance path planning method for an autonomous vehicle provided by the present invention, which includes the following steps:

[0082] S100 detects in real time the lane the car is currently in and the movement of obstacles in the adjacent lanes on both sides; specifically, it uses lidar installed on the top of the autonomous vehicle or other locations to detect the 360° surroundings of the autonomous vehicle and identify the traffic conditions of the current lane and adjacent lanes.

[0083] In some embodiments of this application, the area 50 meters in front of or behind the current driverless car is designated as the identification zone.

[0084] Step S200: When an obstacle is detected in front of the current lane, the distance and speed difference between the vehicle and the obstacle are obtained to determine whether avoidance is necessary. Specifically, when the autonomous vehicle is driving normally in the current lane, if an obstacle is detected in front, it may be a vehicle that has always been in front, an obstacle that is in front, or a vehicle that has changed lanes from an adjacent lane to the current lane. At this time, the obstacle or obstacle vehicle in front is detected, and the speed difference between the vehicle and the obstacle or obstacle vehicle in front and the distance between the vehicle and the obstacle are analyzed. The vehicle's computer then determines whether avoidance is necessary.

[0085] In some embodiments of this application, when an obstacle is detected in the lane ahead, it is also necessary to confirm the type of obstacle. The step of confirming the type of obstacle includes:

[0086] S201: When an obstacle vehicle is detected directly ahead in the current lane, or when a vehicle in an adjacent lane is driving over the lane line of this vehicle and encroaching on an area of ​​this vehicle's lane exceeding a predetermined threshold, and at this time there are no obstacle vehicles ahead of the other adjacent lane and no vehicles behind exceeding a predetermined speed, the type of obstacle ahead is determined to be a lane-changing obstacle. These two situations can be referenced. Figure 4 and Figure 5 As shown.

[0087] Specifically, "an obstacle vehicle directly in front of the current vehicle" refers to a vehicle in front of the current vehicle whose speed is equal to or less than the current vehicle's speed. For example, the speed of the obstacle vehicle in front is less than the current vehicle's speed, or less than the current vehicle's speed by a certain value. Alternatively, the speed difference can be proportional to the longitudinal distance between the two vehicles (for example, the greater the distance between the vehicle in front and the current vehicle, the greater the permissible speed). "An obstacle vehicle behind the current vehicle in an adjacent lane" refers to a vehicle behind the current vehicle whose speed is equal to or greater than the current vehicle's speed. For example, the speed of the obstacle vehicle behind is greater than the current vehicle's speed, or greater than the current vehicle's speed by a certain value. Alternatively, the speed difference can be proportional to the longitudinal distance between the two vehicles (for example, the greater the distance between the vehicle behind and the current vehicle, the greater the permissible speed).

[0088] S202: When an obstacle vehicle is detected directly ahead in the current lane, and there are also obstacle vehicles ahead in the adjacent lanes on both sides, and vehicles behind exceeding a predetermined speed, the type of obstacle ahead is determined to be a brake-prone obstacle. This situation can be referred to... Figure 6 As shown.

[0089] S203: When it is detected that a vehicle in an adjacent lane is crossing the lane line of this vehicle and encroaching on an area of ​​this vehicle's lane exceeding a predetermined threshold, and at the same time there is an obstacle vehicle in front of this vehicle or a vehicle behind this vehicle with a speed exceeding a predetermined value in the other lane, the type of obstacle ahead is determined to be a braking obstacle. This situation can be referred to... Figure 7 As shown.

[0090] S204: When it is detected that an adjacent lane is crossing the lane line of the vehicle and the area encroaching on the lane is less than a predetermined threshold, the type of obstacle ahead is determined to be an obstacle that should be bypassed. This situation can be referred to... Figure 8 As shown.

[0091] Step S300: When obstacle avoidance is required, determine a suitable motion path planning strategy. Based on the type of obstacle, determine the corresponding motion path planning strategy, specifically as follows:

[0092] S301, when it is determined that the obstacle ahead is a suitable obstacle for lane changing, the lane changing route to the adjacent lane is determined according to the lane changing planning strategy. The lane changing route on the side with no obstacle ahead and no vehicle behind exceeding the predetermined speed is determined according to the lane changing planning strategy. Specifically, a point is determined on the side with no obstacle ahead and no vehicle behind exceeding the predetermined speed. A smooth lane changing route is generated based on the current position, current driving direction, point, and driving direction to the point. For example, the lane changing route can be generated by using the Hermite curve formula.

[0093] S302, when it is determined that the obstacle ahead is a suitable obstacle for braking, the braking force is determined according to the deceleration braking strategy and the distance and speed to the obstacle ahead; specifically, for example, in one embodiment, the correspondence between the braking force and the distance ahead and the current vehicle speed can be predefined, and when braking is required, the corresponding braking force is obtained according to the distance to the obstacle ahead and the current vehicle speed.

[0094] S303, when it is determined that the obstacle ahead is a suitable obstacle to bypass, the optimal bypass route is determined according to the obstacle bypass strategy.

[0095] Step S400: Based on the current vehicle's driving path and the driving paths of obstacles in front and adjacent lanes on both sides, plan a smooth obstacle avoidance path.

[0096] In some embodiments of this application, when the obstacle ahead is a type that should be bypassed, the step of determining the optimal bypass route is as follows:

[0097] S330: Determine an initial azimuth point directly in front of the current driving trajectory. At the initial azimuth point, select multiple candidate azimuth points at small intervals (such as 30cm, 50cm, etc.) along the vertical direction of the trajectory line. Then, based on the current position, the current driving direction, and the driving direction of each candidate azimuth point, form multiple smooth obstacle avoidance trajectories. Specifically, the Hermite curve formula can be used to generate these trajectories.

[0098] S331. Based on three factors—the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance—select the optimal obstacle avoidance trajectory from among multiple obstacle avoidance trajectories.

[0099] Specifically, step S331 includes:

[0100] S3310, obtain the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the vehicle in the adjacent lane;

[0101] S3311, obtain the first instantaneous relative distance between each obstacle avoidance trajectory and the obstacle in front.

[0102] S3312, obtain the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane.

[0103] S3313, the lateral spacing, first instantaneous relative distance and second instantaneous relative distance corresponding to each obstacle avoidance trajectory are multiplied by their respective pre-weighting factors and summed to obtain the total obstacle avoidance parameters; in one embodiment, the weighting factor of the lateral spacing coefficient can be set to the maximum, the weighting factor of the first instantaneous relative distance can be set to the next maximum, and the weighting factor of the second instantaneous relative distance can be set to the minimum.

[0104] S3314, the obstacle avoidance trajectory with the smallest total obstacle avoidance parameters is determined as the optimal obstacle avoidance trajectory. It should be noted that in this invention, by considering the coefficients of three factors and setting corresponding weighting factors, it is necessary to consider both maintaining a sufficiently safe lateral distance from the obstacle in front and the obstacle vehicle on the other side, and avoiding excessive obstacle avoidance amplitude to prevent lateral loss of control or serious impact on the passage of vehicles behind. Thus, the obtained optimal obstacle avoidance trajectory maintains a sufficiently safe lateral distance from both the obstacle in front and the obstacle vehicle on the other side, and only makes a small obstacle avoidance movement based on the initial driving trajectory.

[0105] It should be noted that, in some embodiments, step S3314 further includes:

[0106] Among multiple obstacle avoidance trajectories, some unreasonable obstacle avoidance trajectories can be eliminated based on the lateral distance between the obstacle ahead and the obstacle vehicle in the adjacent lane.

[0107] like Figure 9 As shown, the upper vertex of the initial driving line of the autonomous vehicle is the initial azimuth point, and the multiple smooth dashed curves above the vehicle are obstacle avoidance trajectories, among which a thick dashed line is the calculated and confirmed optimal obstacle avoidance trajectory; the upper vertex of each curve in the obstacle avoidance trajectory cluster is the other azimuth point; the dashed frame above each curve in the obstacle avoidance trajectory cluster is the vehicle's expected position in each obstacle avoidance trajectory, and one thick dashed frame is the vehicle's expected position in the optimal obstacle avoidance trajectory.

[0108] In step S500, obstacle avoidance is achieved by changing lanes, decelerating and braking, or going around obstacles, according to the planned obstacle avoidance path. After the route is planned in step S400, the vehicle's computer controls the autonomous vehicle to perform the corresponding operations.

[0109] This invention also discloses an obstacle avoidance path planning system for autonomous vehicles, such as... Figure 10 As shown, in this embodiment, the system includes:

[0110] The real-time traffic condition recognition unit 100 is used to detect and recognize the traffic conditions of the lane currently occupied by the vehicle and the adjacent lanes on both sides in real time. Specifically, by using a lidar installed on the top of the autonomous vehicle or other locations, it detects the 360° surroundings of the autonomous vehicle and identifies the traffic conditions of the current lane and adjacent lanes.

[0111] The obstacle type recognition unit 200 is used to detect the type of obstacle in front of the current lane, including: obstacle suitable for lane changing, obstacle suitable for braking, and obstacle suitable for bypassing.

[0112] The strategy determination unit 300 determines the corresponding motion path planning strategy according to the type of obstacle. The motion path planning strategy includes lane changing strategy, deceleration strategy and obstacle avoidance strategy.

[0113] The execution unit 400 is used to execute the motion path planning strategy determined by the strategy determination unit 300, which is achieved by changing lanes, decelerating and braking, or bypassing obstacles.

[0114] Furthermore, in some embodiments, the obstacle type recognition unit 200 further includes:

[0115] The first identification unit is used to determine the type of obstacle ahead as a lane-changing obstacle when it detects that there is an obstacle vehicle directly in front of the vehicle in its lane, or that the adjacent lane on one side is driving on the lane line of the vehicle and the area encroaching on the lane of the vehicle is greater than a predetermined threshold, and at this time there is no obstacle vehicle in front of the adjacent lane on one side and no vehicle behind with a speed exceeding a predetermined value.

[0116] The second identification unit is used to determine the type of obstacle ahead as a brakeable obstacle when it detects an obstacle directly in front of the vehicle in its lane, and at the same time there are vehicles in front of or behind the vehicle in the adjacent lanes on both sides with a speed exceeding a predetermined value; or it is used to determine the type of obstacle ahead as a brakeable obstacle when it detects that an adjacent lane on one side is driving over the lane line of the vehicle and encroaching on the area of ​​the vehicle's lane greater than a predetermined threshold, and at the same time there are vehicles in front of or behind the vehicle in the other lane with a speed exceeding a predetermined value.

[0117] The third identification unit is used to determine the type of obstacle ahead as an obstacle that should be bypassed when it detects that the vehicle is traveling in an adjacent lane on one side and the area encroaching on the vehicle's lane is less than a predetermined threshold.

[0118] Among them, such as Figure 11 As shown, the strategy determination unit 300 includes:

[0119] The lane change strategy determination unit 301 is used to determine the lane change route on the side where there are no vehicles in adjacent lanes when the obstacle ahead is a lane change obstacle, according to the lane change planning strategy. Specifically, a point is determined on the side where there are no vehicles ahead and no vehicles behind with a speed exceeding a predetermined value, and a smooth lane change route is generated based on the current position, current driving direction, point, and driving direction to the point.

[0120] The deceleration strategy determination unit 302 is used to determine the braking force based on the deceleration braking strategy and the distance to the obstacle in front when the obstacle in front is a braking obstacle.

[0121] The obstacle avoidance strategy determination unit 303 is used to plan the optimal obstacle avoidance route according to the obstacle avoidance planning strategy when the type of obstacle ahead is an obstacle that should be avoided.

[0122] like Figure 12 As shown, the obstacle avoidance planning strategy determination unit includes:

[0123] The obstacle avoidance trajectory acquisition unit 330 is used to determine an initial azimuth point in front of the current driving trajectory line, select multiple candidate azimuth points at intervals along the vertical direction of the trajectory line at the initial azimuth point, and then generate multiple smooth obstacle avoidance trajectories based on the current position, the current driving direction, each candidate azimuth point, and the driving direction to each candidate azimuth point.

[0124] The obstacle avoidance trajectory determination unit 331 is used to select the optimal obstacle avoidance trajectory from multiple obstacle avoidance trajectories based on three factors: the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance.

[0125] like Figure 13The obstacle avoidance trajectory determination unit 331 includes:

[0126] The lateral spacing acquisition unit 3310 is used to acquire the lateral spacing between each obstacle avoidance trajectory and the obstacle in front or the obstacle vehicle in the adjacent lane.

[0127] The first instantaneous relative distance acquisition unit 3310 is used to acquire the first instantaneous relative distance between each obstacle-avoiding trajectory and the obstacle in front.

[0128] The second instantaneous relative distance acquisition unit 3312 is used to acquire the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane.

[0129] The weighted calculation unit 3313 is used to multiply the lateral spacing, the first instantaneous relative distance and the second instantaneous relative distance corresponding to each obstacle avoidance trajectory by their respective predefined weighting factors and then sum them up to obtain the total coefficient.

[0130] The optimal obstacle avoidance trajectory determination unit 3314 is used to determine the obstacle avoidance trajectory with the smallest total coefficient as the optimal obstacle avoidance trajectory.

[0131] In one embodiment, the obstacle avoidance trajectory determination unit 331 further includes:

[0132] The exclusion unit is used to exclude some non-compliant obstacle avoidance trajectories from the multiple obstacle avoidance trajectories directly based on the lateral distance between the trajectory and the obstacle in front and the obstacle vehicle on the other side.

[0133] For more details, please refer to the aforementioned section. Figures 1 to 9 The description of that will not be elaborated here.

[0134] Implementing this invention has the following beneficial effects:

[0135] First, in the embodiments of the present invention, the surrounding road traffic environment and other vehicle conditions can be comprehensively considered to automatically and safely bypass vehicles and obstacles near the lane. Second, obstacle bypass decision-making is required before the obstacle bypass action is executed to avoid forcibly executing the obstacle bypass action when it is not suitable, which would lead to lateral control overshoot or seriously affect the passage of vehicles behind.

[0136] Meanwhile, in the embodiments of the present invention, during the obstacle avoidance decision-making process, the optimal trajectory calculation algorithm based on coefficient optimization can maintain a sufficiently safe lateral distance from other vehicles and obstacles as much as possible, and can also avoid excessive obstacle avoidance amplitude to prevent lateral control overshoot or serious impact on the passage of vehicles behind.

[0137] In summary, the methods and systems provided in the embodiments of the present invention can significantly improve the safety and comfort of autonomous vehicles.

[0138] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0139] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0140] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for obstacle avoidance path planning for unmanned vehicles, characterized in that, Includes the following steps: S100 can detect the current lane of the vehicle and the movement of obstacles in the adjacent lanes on both sides in real time. S200: When an obstacle is detected in front of the current lane, the distance and speed difference between the vehicle and the obstacle are obtained to determine whether it is necessary to avoid it. S300 determines an appropriate motion path planning strategy when avoidance is required; The S400 plans a smooth obstacle avoidance path based on the current vehicle's driving path and the driving paths of obstacles in front and in adjacent lanes on both sides. The S500 can perform obstacle avoidance operations by changing lanes, slowing down and braking, or going around obstacles according to the planned obstacle avoidance path.

2. The obstacle avoidance path planning method for an unmanned vehicle according to claim 1, characterized in that, In step S200, when an obstacle is detected ahead of the current lane, it is also necessary to confirm the type of obstacle.

3. The obstacle avoidance path planning method for an unmanned vehicle according to claim 2, characterized in that, The step of determining the type of obstacle includes: S201, when an obstacle vehicle is detected directly in front of the current lane, or when an adjacent lane on one side is driving over the lane line of this vehicle and encroaching on the area of ​​this vehicle's lane for more than a predetermined threshold, and at this time there is no obstacle vehicle in front of the other adjacent lane and no vehicle behind with a speed exceeding a predetermined value, the type of obstacle in front is determined to be a lane-changing obstacle. S202, when an obstacle vehicle is detected directly in front of the current lane, and there are also obstacle vehicles in front of and behind the adjacent lanes at a speed exceeding a predetermined value, the type of obstacle ahead is determined to be a brakeable obstacle. S203, when it is detected that the vehicle is traveling in an adjacent lane on one side and the area of ​​the vehicle's lane encroaching on the lane is greater than a predetermined threshold, and at this time there is an obstacle vehicle in front of the other lane or a vehicle behind with a speed exceeding a predetermined value, the type of obstacle in front is determined to be a braking obstacle. S204, when it is detected that the vehicle is traveling in an adjacent lane on one side and the area of ​​the vehicle encroaching on the lane of the vehicle is less than a predetermined threshold, the type of obstacle ahead is determined to be an obstacle that should be bypassed.

4. The obstacle avoidance path planning method for an unmanned vehicle according to claim 3, characterized in that, The steps for determining the corresponding obstacle avoidance route based on the type of obstacle include: S301, when it is determined that the obstacle ahead is a suitable obstacle for lane changing, the lane changing route to the adjacent lane shall be determined according to the lane changing planning strategy; S302, When it is determined that the obstacle ahead is a suitable obstacle for braking, the braking force is determined based on the deceleration braking strategy and the distance and speed to the obstacle ahead; S303, when it is determined that the obstacle ahead is a suitable obstacle to bypass, the optimal bypass route is determined according to the obstacle bypass strategy.

5. The obstacle avoidance path planning method for an unmanned vehicle according to claim 4, characterized in that, The optimal route planning steps for the obstacle avoidance route are as follows: S330: Determine an initial azimuth point directly in front of the current driving trajectory; select multiple candidate azimuth points at small intervals along the vertical direction of the trajectory line at the initial azimuth point; and form multiple smooth obstacle avoidance trajectories based on the current position, current driving direction, and driving direction of each candidate azimuth point. S331. Based on three factors—the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance—select the optimal obstacle avoidance trajectory from among multiple obstacle avoidance trajectories.

6. The obstacle avoidance path planning method for an unmanned vehicle according to claim 5, characterized in that, The specific steps for selecting an optimal obstacle avoidance trajectory are as follows: S3310, obtain the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the vehicle in the adjacent lane; S3311, obtain the first instantaneous relative distance between each obstacle avoidance trajectory and the obstacle in front; S3312, obtain the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane; S3313, Multiply the lateral spacing, the first instantaneous relative distance and the second instantaneous relative distance corresponding to each obstacle avoidance trajectory by their respective pre-weighting factors and sum them up to obtain the total obstacle avoidance parameters; S3314, the obstacle-avoidance trajectory with the smallest total obstacle-avoidance parameters is determined as the optimal obstacle-avoidance trajectory.

7. An obstacle avoidance path planning system for unmanned vehicles, characterized in that, include: The real-time traffic condition recognition unit is used to detect and identify the traffic conditions of the lane in which the vehicle is currently located and the adjacent lanes on both sides in real time. The obstacle type recognition unit is used to detect the type of obstacle in front of the current lane, including: obstacles suitable for lane changing, obstacles suitable for braking, and obstacles suitable for bypassing. The strategy determination unit determines the corresponding motion path planning strategy based on the type of obstacle. The motion path planning strategy includes lane changing strategy, deceleration strategy and obstacle avoidance strategy. The execution unit is used to execute the motion path planning strategy determined by the strategy determination unit, which is achieved by changing lanes, decelerating and braking, or bypassing obstacles.

8. The obstacle avoidance path planning system for an unmanned vehicle according to claim 7, characterized in that, The strategy determination unit includes: The lane change strategy determination unit is used to determine the lane change route on the side where there are no vehicles in the adjacent lanes when the obstacle ahead is a suitable lane change obstacle, according to the lane change planning strategy. The deceleration strategy determination unit is used to determine the braking force based on the deceleration braking strategy and the distance to the obstacle in front when the obstacle ahead is a suitable braking obstacle. The obstacle avoidance strategy determination unit is used to plan the optimal obstacle avoidance route based on the obstacle avoidance planning strategy when the obstacle ahead is an obstacle that should be avoided.

9. The obstacle avoidance path planning system for an unmanned vehicle according to claim 8, characterized in that, The obstacle avoidance strategy determination unit includes: The obstacle avoidance trajectory acquisition unit is used to determine an initial azimuth point directly in front of the current driving trajectory, select multiple candidate azimuth points at small intervals along the vertical direction of the trajectory line at the initial azimuth point, and then form multiple smooth obstacle avoidance trajectories based on the current position, the current driving direction, and the driving direction of each candidate azimuth point. The obstacle avoidance trajectory determination unit is used to select the optimal obstacle avoidance trajectory from multiple obstacle avoidance trajectories based on three factors: the lateral distance between each obstacle avoidance trajectory and the obstacle ahead or the obstacle vehicle in the adjacent lane, the first instantaneous relative distance, and the second instantaneous relative distance.

10. The obstacle avoidance path planning system for an unmanned vehicle according to claim 9, characterized in that, The obstacle avoidance trajectory determination unit includes: The lateral spacing acquisition unit is used to acquire the lateral spacing between each obstacle avoidance trajectory and the obstacle in front or the obstacle vehicle in the adjacent lane; The first instantaneous relative distance acquisition unit is used to acquire the first instantaneous relative distance between each obstacle avoidance trajectory and the obstacle in front; The second instantaneous relative distance acquisition unit is used to acquire the second instantaneous relative distance between each obstacle avoidance trajectory and the obstacle vehicle in the adjacent lane; The weighted calculation unit multiplies the lateral spacing, the first instantaneous relative distance, and the second instantaneous relative distance corresponding to each obstacle avoidance trajectory by their respective pre-weighting factors and then sums them up to obtain the total obstacle avoidance parameters. The optimal obstacle avoidance trajectory determination unit determines the obstacle avoidance trajectory with the smallest total obstacle avoidance parameters as the optimal obstacle avoidance trajectory.

Images