Obstacle lane changing intention analysis method in automatic driving

Abstract

The invention relates to an obstacle lane changing intention analysis method in automatic driving, and the method comprises the steps: S1, starting an intention analysis module based on the current driving information of a vehicle, and carrying out the screening of obstacles in front of the side of the vehicle; s2, detecting and identifying whether a vehicle obstacle exists in front of the side of the vehicle or not; s3, if the vehicle obstacle exists in front of the side of the vehicle, a target vehicle is determined; based on the driving information of the target vehicle and the driving condition of the lane where the target vehicle is located, whether the target vehicle has a lane changing intention or not is judged and predicted by combining the driving condition of the lane where the vehicle is located. Through the steps, lane changing intention analysis of the prediction module under the condition that the target vehicle does not give a prompt is complemented, prediction and operation are carried out in advance, and the automatic driving vehicle can run more safely and comfortably.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular to a method for analyzing obstacle lane change intention in autonomous driving. Background Art

[0002] As cars become increasingly intelligent, more and more autopilot functions are installed on various models at home and abroad. The prediction module is an indispensable function in the field of autopilot. It enables autopilot vehicles to make advance judgments about the environment based on the prediction results, ensuring the comfortable and safe operation of the vehicle. However, the general prediction module only predicts the obstacle's driving trajectory, that is, predicts the obstacle's driving trajectory in the next few seconds. This prediction is limited by the prediction module's algorithm, and its path may not be accurate. For the decision-making module of the autopilot vehicle, using only the obstacle prediction trajectory as the basis for decision-making may be insufficient, such as the delay in the speed reduction decision leading to sudden braking or collision of the vehicle.

[0003] Therefore, there is an urgent need to provide a method for analyzing obstacle lane change intention in autonomous driving to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings and defects of the prior art and provide a method for analyzing the lane change intention of an obstacle in autonomous driving, which complements the lane change intention analysis of the prediction module when the target vehicle does not give a prompt, and makes predictions and operations in advance, so that the autonomous driving vehicle can drive more safely and comfortably.

[0005] The objective of the present invention is achieved through the following technical solutions:

[0006] A method for analyzing obstacle lane change intention in autonomous driving, characterized by comprising:

[0007] S1: Based on the current driving information of the vehicle, the intention analysis module is started to screen obstacles in front of the vehicle;

[0008] S2: Detect and identify whether there is a vehicle obstacle in front of the vehicle;

[0009] S3: If there is a vehicle obstacle in front of the vehicle, determine the target vehicle; based on the driving information of the target vehicle and the driving condition of the lane where the vehicle is located, combined with the driving condition of the lane where the vehicle is located, judge and predict whether the target vehicle has the intention to change lanes.

[0010] Optionally, the specific steps of obstacle screening in S1 include:

[0011] S11: Static obstacle filtering, filtering static obstacles in front of the vehicle;

[0012] S12: Non-motor vehicle obstacle filtering, filtering pedestrians and other non-motor vehicle type dynamic obstacles;

[0013] S13: Motor vehicle obstacle filtering, including motor vehicle obstacles that are too far away in the longitudinal direction, motor vehicle obstacles that are traveling in the opposite direction of the vehicle, motor vehicle obstacles whose front ends lag behind the vehicle by at least half a body length, and motor vehicle obstacles located in the lane of the vehicle.

[0014] Optionally, it also includes:

[0015] S4: Determine whether the target vehicle is overtaking in the opposite lane;

[0016] S41: Determine the lane where the target vehicle is located. If the lane is not adjacent to the host vehicle, determine that the target vehicle is an unrelated vehicle.

[0017] S42: If the lane where the target vehicle is located is an adjacent lane to the lane of the own vehicle, determine whether the target vehicle is in an opposite lane;

[0018] S43: If the target vehicle is in an adjacent opposite lane, determine whether the target vehicle is traveling in the same direction as the host vehicle; if so, the target vehicle has an intention to change lanes.

[0019] Optionally, it also includes:

[0020] S5: A static obstacle A is detected in front of the lane where the vehicle is located;

[0021] S51: Detect whether there is no obstacle in front of the target vehicle. If there is no obstacle, the lane change intention analysis result is negative, and the target vehicle will not tend to change lanes;

[0022] S52: If there is a static obstacle B in front of the target vehicle, and the distance between the static obstacle B and the target vehicle is smaller than the distance between the vehicle and the static obstacle A, the target vehicle has an intention to change lanes;

[0023] S53: If there is a dynamic obstacle in front of the target vehicle, identify the speed of the dynamic obstacle; if the speed of the dynamic obstacle is greater than the speed of the target vehicle, determine that the target vehicle has no intention to change lanes;

[0024] S54: If the speed of the dynamic obstacle is less than the speed of the target vehicle, and the distance between the host vehicle and the static obstacle A is far, the target vehicle has an intention to change lanes.

[0025] Optionally, it also includes:

[0026] S61: It is detected that there is a dynamic obstacle A in front of the vehicle, and the speed of the dynamic obstacle A is greater than that of the target vehicle;

[0027] S611: If there is a dynamic obstacle B in front of the target vehicle, determine whether the speed of the dynamic obstacle B is greater than the speed of the target vehicle; if the speed of the dynamic obstacle B is greater than the speed of the target vehicle, the target vehicle has no intention to change lanes; if the speed of the dynamic obstacle B is less than the speed of the target vehicle, the target vehicle has an intention to change lanes;

[0028] S612: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes;

[0029] S613: If there is no obstacle in front of the target vehicle, the target vehicle has no intention to change lanes.

[0030] Optionally, it also includes:

[0031] S62: It is detected that there is a dynamic obstacle A in front of the vehicle, and the speed of the dynamic obstacle A is lower than that of the target vehicle;

[0032] S621: If there is a dynamic obstacle B in front of the target vehicle, determine whether the speed of the dynamic obstacle B is greater than the speed of the target vehicle; if the speed of the dynamic obstacle B is greater than the speed of the target vehicle, the target vehicle has no intention to change lanes;

[0033] S622: If the speed of the dynamic obstacle B is less than the speed of the target vehicle, and the longitudinal distance between the target vehicle and the dynamic obstacle A is much greater than the longitudinal distance between the target vehicle and the dynamic obstacle B, then the target vehicle has an intention to change lanes;

[0034] S623: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes;

[0035] S624: If there is no obstacle in front of the target vehicle, the target vehicle has no intention to change lanes.

[0036] Optionally, it also includes:

[0037] S7: It is detected that there is no obstacle in front of the lane where the vehicle is located;

[0038] S71: If there is no obstacle in front of the target vehicle and the speed of the target vehicle is less than the speed of the host vehicle, the target vehicle has no intention to change lanes;

[0039] S72: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes;

[0040] S73: If there is a dynamic obstacle in front of the target vehicle, check whether the speed of the dynamic obstacle is greater than that of the target vehicle; if the speed of the dynamic obstacle is greater than that of the target vehicle, the target vehicle has no intention of changing lanes; if the speed of the dynamic obstacle is less than that of the target vehicle and the target vehicle has no signs of deceleration, the target vehicle has an intention of changing lanes.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] In the present invention, firstly, based on the current driving information of the vehicle, the intention analysis module is started to screen obstacles in front of the side of the vehicle, wherein the obstacle screening is to screen out irrelevant obstacle information, such as pedestrians or other non-motor vehicle obstacles; after the irrelevant obstacle screening is completed, it is detected and identified whether there is a vehicle obstacle in front of the side of the vehicle, and if there is a vehicle obstacle, the target vehicle is determined; based on the driving information of the target vehicle and the driving conditions of the lane where it is located, combined with the driving conditions of the lane where the vehicle is located, it is judged and predicted whether the target vehicle has the intention to change lanes, so as to prevent the target vehicle in the adjacent lane from forcibly changing lanes without any warning, causing the vehicle to brake suddenly or collide; through the above steps, the prediction module is supplemented with the analysis of the lane change intention when the target vehicle does not give a prompt, and prediction and operation are performed in advance, so that the autonomous driving vehicle can drive more safely and comfortably. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a structural flow chart of the present invention.

[0044] Figure 2 The flowchart of the present invention is to screen whether the target vehicle is overtaking in the opposite direction.

[0045] Figure 3 This is a flow chart when there is a static obstacle A in front of the vehicle in the present invention.

[0046] Figure 4 It is a flow chart when there is no obstacle in front of the vehicle in the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described in detail below in conjunction with embodiments and drawings, but the embodiments of the present invention are not limited thereto.

[0048] The technical solution of the present invention proposes a method for analyzing obstacle lane change intention in autonomous driving.

[0049] Reference Figures 1 to 4 , in this embodiment, includes:

[0050] S1: Based on the current driving information of the vehicle, the intention analysis module is started to screen obstacles in front of the vehicle;

[0051] S2: Detect and identify whether there is a vehicle obstacle in front of the vehicle;

[0052] S3: If there is a vehicle obstacle in front of the vehicle, determine the target vehicle; based on the driving information of the target vehicle and the driving condition of the lane where the vehicle is located, combined with the driving condition of the lane where the vehicle is located, judge and predict whether the target vehicle has the intention to change lanes.

[0053] Optionally, refer to Figure 1 In this embodiment, the prediction module makes an advance judgment of the environment in which the vehicle is located based on the prediction results. First, based on the current driving information of the vehicle, the intention analysis module is started to screen obstacles in front of the side of the vehicle, wherein the obstacle screening is to screen out irrelevant obstacle information, such as pedestrians or other non-motor vehicle obstacles, to prevent the intention analysis module of the vehicle from being affected; after the irrelevant obstacle screening is completed, it is detected and identified whether there is a vehicle obstacle in front of the side of the vehicle. If there is a vehicle obstacle, the target vehicle is determined; based on the driving information of the target vehicle and the driving condition of the lane where the vehicle is located, combined with the driving condition of the lane where the vehicle is located, the target vehicle is determined; The driving condition is composed of information such as the front and rear vehicles, the vehicle speed and the obstacles ahead, so as to prevent the target vehicle in the adjacent lane from forcibly changing lanes without any warning, causing the vehicle to brake suddenly or collide. After the target vehicle is detected and identified in S2, it is necessary to detect whether the target vehicle has turned on the turn signal, and it can also predict in advance whether the target vehicle has the intention to change lanes. Through the above steps, the prediction module is supplemented for the analysis of the lane change intention when the target vehicle does not give a prompt, and the prediction and operation are performed in advance, so that the autonomous driving vehicle can drive more safely and comfortably.

[0054] In this embodiment, the specific steps of obstacle screening in step S1 include:

[0055] S11: Static obstacle filtering, filtering static obstacles in front of the vehicle; static obstacles do not have the intention of changing lanes, so they are screened and filtered.

[0056] S12: Non-motor vehicle obstacle filtering, filtering pedestrians and other non-motor vehicle type dynamic obstacles; during driving, if there are pedestrians or non-motor vehicle type dynamic obstacles, the vehicle will give priority to slowing down and avoiding them, so non-motor vehicle obstacles are also screened and filtered.

[0057] S13: Motor vehicle obstacle filtering, including motor vehicle obstacles that are too far away in the longitudinal direction, motor vehicle obstacles traveling in the opposite direction to the vehicle, motor vehicle obstacles whose front end lags behind the vehicle by at least half a body length, and moving vehicle obstacles located in the lane of the vehicle; among them, motor vehicle obstacles that are too far away in the longitudinal direction can be ignored, and even if there is an intention to change lanes, the vehicle can respond in time. The judgment standard of the motor vehicle obstacle is based on time multiplied by the current vehicle speed. The specified time is 5 seconds, and the distance reached within 5 seconds at the current vehicle speed is the effective longitudinal judgment range; motor vehicle obstacles that are traveling in the opposite direction to the vehicle can be ignored, and there is no possibility of changing lanes; motor vehicle obstacles whose front end lags behind the vehicle by at least half a body length cannot change lanes, and even if the obstacle changes lanes, it needs to exceed the vehicle before changing lanes, so it is not considered for filtering; and the lane change of moving vehicle obstacles in the lane of the vehicle will not affect the driving of the vehicle.

[0058] In this embodiment, refer to Figure 2 , also includes the judgment of whether the target vehicle is overtaking in the opposite direction. First, it is judged whether the target vehicle is in the adjacent lane of the vehicle. If not, it is judged as an unrelated vehicle. If they are adjacent, subsequent judgment is made; if the lane where the target vehicle is located is an adjacent lane to the lane of the vehicle, then it is judged whether the target vehicle is in the opposite lane. After being in the opposite lane, it is judged whether the target vehicle is traveling in the same direction as the vehicle. If the target vehicle is in the adjacent opposite lane and traveling in the same direction as the vehicle, the target vehicle is judged to have the intention to change lanes.

[0059] In this embodiment, refer to Figure 3 , further comprising S5: detecting that there is a static obstacle A in front of the lane where the vehicle is located, and performing subsequent determination and analysis based on this condition;

[0060] S51: Check whether the area in front of the target vehicle is clear. If so, the lane change intention analysis result is negative, and the target vehicle will not tend to change lanes. If there is a static obstacle A in front of the vehicle and there is no obstacle in front of the target, the target vehicle has no intention of changing lanes, and the output lane change intention analysis result is negative.

[0061] S52: If there is a static obstacle B in front of the target vehicle, and the distance between the static obstacle B and the target vehicle is smaller than the distance between the vehicle and the static obstacle A, the target vehicle has the intention to change lanes; since there is a static obstacle in front of the target vehicle, and the distance between the static obstacle B and the target vehicle is smaller than the distance between the vehicle and the static obstacle A, if the target vehicle wants to speed up the journey, it will choose to change lanes to avoid the static obstacle B in front, so the target vehicle has a greater probability of intending to change lanes; on the contrary, if the distance between the static obstacle B and the target vehicle is smaller than the distance between the vehicle and the static obstacle A, the target vehicle will not change lanes.

[0062] S53: If there is a dynamic obstacle in front of the target vehicle, identify the speed of the dynamic obstacle; if the speed of the dynamic obstacle is greater than the speed of the target vehicle, determine that the target vehicle has no intention to change lanes;

[0063] S54: If the speed of the dynamic obstacle is less than the speed of the target vehicle, and the distance between the vehicle and the static obstacle A is far, the target vehicle has the intention to change lanes; if the speed of the dynamic obstacle is less than the target vehicle, there is a possibility that the target vehicle will change lanes and overtake, so it is judged that the target vehicle has the intention to change lanes.

[0064] In this embodiment, the following steps are also included: S61: If a dynamic obstacle A is detected in front of the vehicle, the speed of the dynamic obstacle is judged and compared. If the speed of the dynamic obstacle A is greater than that of the target vehicle, the subsequent steps are judged; S61: If a dynamic obstacle B is detected in front of the target vehicle, the speed of the target vehicle is compared with that of the dynamic obstacle B. If the speed of the dynamic obstacle B is greater than that of the target vehicle, the target vehicle will not be congested if it follows the dynamic obstacle B, so there is no intention to change lanes; if the speed of the dynamic obstacle B is less than that of the target vehicle, the target vehicle will usually choose to change lanes and overtake if it wants to speed up, so the target vehicle has the intention to change lanes. S612: If a static obstacle is present in front of the target vehicle, since the static obstacle will affect the continued driving of the target vehicle, the target vehicle has the intention to change lanes; if there is no obstacle in front of the target vehicle, and there is a dynamic obstacle A in front of the vehicle, the lane where the target vehicle is located is unobstructed, so the target vehicle has no intention to change lanes.

[0065] Further, in the present embodiment, it also includes S62: if it is detected that there is a dynamic obstacle A in front of the vehicle, and the speed of the dynamic obstacle A is less than that of the target vehicle, then the subsequent steps are performed; S621: if there is a dynamic obstacle B in front of the target vehicle, the speed of the dynamic obstacle B is compared with that of the dynamic obstacle A. If the speed of the dynamic obstacle B is greater than the speed of the target vehicle, the target vehicle will not be hindered from driving in the lane, so the target vehicle has no intention of changing lanes; if the speed of the dynamic obstacle B is less than the speed of the vehicle, and the longitudinal distance between the target vehicle and the dynamic obstacle is greater than the longitudinal distance between the target vehicle and the dynamic obstacle B, the target vehicle will have a larger driving space after changing lanes, so the target vehicle has an intention of changing lanes; at the same time, if the speed of the dynamic obstacle B is much lower than the dynamic obstacle A, and the speed of the target vehicle is higher than that of the vehicle or the rear of the target vehicle exceeds the front of the vehicle, then the target vehicle has an obvious intention of changing lanes; S623: if there is a static obstacle in front of the target vehicle, then the target vehicle will have an intention of changing lanes because the static obstacle will affect the driving of the target vehicle; if there is no obstacle in front of the target vehicle, then the target vehicle has no intention of changing lanes. The standard for detecting whether there is an obstacle in front of the target vehicle or the vehicle is: to detect the path that can be reached after the target vehicle or the vehicle has traveled at the current speed for a set time. The set time is set to 5 seconds here. In other embodiments, the set time can also be set to more than 5 seconds, which is not limited here.

[0066] In this embodiment, refer to Figure 4 , and further includes the following steps: S7: if it is detected that there is no obstacle in the lane in front of the vehicle, then the obstacle detection is performed in front of the target vehicle; S71: if there is no obstacle in front of the target vehicle and the speed of the target vehicle is less than the speed of the vehicle, then the target vehicle has no intention to change lanes; S72: if there is a static obstacle in front of the target vehicle, then the target vehicle has the intention to change lanes, which can be specifically judged according to whether the target vehicle decelerates. If the target vehicle continues to decelerate, there is no intention to change lanes. If the target vehicle maintains the current speed or accelerates, there is an intention to change lanes. S73: if there is a dynamic obstacle in front of the target vehicle, then it is detected whether the speed of the dynamic obstacle is greater than that of the target vehicle. If the speed of the dynamic obstacle is greater than that of the target vehicle, it will not affect the driving of the target vehicle, that is, the target vehicle has no intention to change lanes; if the speed of the dynamic obstacle is less than that of the target vehicle and the target vehicle has no signs of deceleration, then the target vehicle has the intention to change lanes; of course, the intention analysis module is established on the analysis of the intention to change lanes when the target vehicle does not give a turn signal. If the target vehicle gives a turn signal, the turn signal is used as a benchmark.

[0067] The above-mentioned embodiments only express the implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A method for analyzing obstacle lane change intention in autonomous driving, characterized in that: include: S1: Based on the current driving information of the vehicle, the intention analysis module is started to screen obstacles in front of the vehicle; S2: Detect and identify whether there is a vehicle obstacle in front of the vehicle; S3: If there is a vehicle obstacle in front of the vehicle, determine the target vehicle; based on the driving information of the target vehicle and the driving condition of the lane where the vehicle is located, combined with the driving condition of the lane where the vehicle is located, judge and predict whether the target vehicle has the intention to change lanes.

2. The method for analyzing lane change intention of an obstacle in an automatic driving according to claim 1, characterized in that: The specific steps of obstacle screening in S1 include: S11: Static obstacle filtering, filtering static obstacles in front of the vehicle; S12: Non-motor vehicle obstacle filtering, filtering pedestrians and other non-motor vehicle type dynamic obstacles; S13: Motor vehicle obstacle filtering, including motor vehicle obstacles that are too far away in the longitudinal direction, motor vehicle obstacles that are traveling in the opposite direction of the vehicle, motor vehicle obstacles whose front ends lag behind the vehicle by at least half a body length, and motor vehicle obstacles located in the lane of the vehicle.

3. The method for analyzing lane change intention of an obstacle in automatic driving according to claim 2, characterized in that: Also includes: S4: Determine whether the target vehicle is overtaking in the opposite lane; S41: Determine the lane where the target vehicle is located. If the lane is not adjacent to the host vehicle, determine that the target vehicle is an unrelated vehicle. S42: If the lane where the target vehicle is located is an adjacent lane to the lane of the own vehicle, determine whether the target vehicle is in an opposite lane; S43: If the target vehicle is in an adjacent opposite lane, determine whether the target vehicle is traveling in the same direction as the host vehicle; if so, the target vehicle has an intention to change lanes.

4. The method for analyzing lane change intention of an obstacle in automatic driving according to claim 2, characterized in that: Also includes: S5: A static obstacle A is detected in front of the lane where the vehicle is located; S51: Detect whether there is no obstacle in front of the target vehicle. If there is no obstacle, the lane change intention analysis result is negative, and the target vehicle will not tend to change lanes; S52: If there is a static obstacle B in front of the target vehicle, and the distance between the static obstacle B and the target vehicle is smaller than the distance between the vehicle and the static obstacle A, the target vehicle has an intention to change lanes; S53: If there is a dynamic obstacle in front of the target vehicle, identify the speed of the dynamic obstacle; if the speed of the dynamic obstacle is greater than the speed of the target vehicle, determine that the target vehicle has no intention to change lanes; S54: If the speed of the dynamic obstacle is less than the speed of the target vehicle, and the distance between the host vehicle and the static obstacle A is far, the target vehicle has an intention to change lanes.

5. The method for analyzing lane change intention of an obstacle in automatic driving according to claim 2, characterized in that: Also includes: S61: It is detected that there is a dynamic obstacle A in front of the vehicle, and the speed of the dynamic obstacle A is greater than that of the target vehicle; S611: If there is a dynamic obstacle B in front of the target vehicle, determine whether the speed of the dynamic obstacle B is greater than the speed of the target vehicle; If the speed of dynamic obstacle B is greater than the speed of the target vehicle, the target vehicle has no intention to change lanes; If the speed of dynamic obstacle B is less than that of the target vehicle, the target vehicle has the intention to change lanes; S612: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes; S613: If there is no obstacle in front of the target vehicle, the target vehicle has no intention to change lanes.

6. The method for analyzing lane change intention of an obstacle in automatic driving according to claim 5, characterized in that: Also includes: S62: It is detected that there is a dynamic obstacle A in front of the vehicle, and the speed of the dynamic obstacle A is lower than that of the target vehicle; S621: If there is a dynamic obstacle B in front of the target vehicle, determine whether the speed of the dynamic obstacle B is greater than the speed of the target vehicle; If the speed of dynamic obstacle B is greater than the speed of the target vehicle, the target vehicle has no intention to change lanes; S622: If the speed of the dynamic obstacle B is less than the speed of the target vehicle, and the longitudinal distance between the target vehicle and the dynamic obstacle A is much greater than the longitudinal distance between the target vehicle and the dynamic obstacle B, then the target vehicle has an intention to change lanes; S623: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes; S624: If there is no obstacle in front of the target vehicle, the target vehicle has no intention to change lanes.

7. The method for analyzing lane change intention of an obstacle in automatic driving according to claim 1, characterized in that: Also includes: S7: It is detected that there is no obstacle in front of the lane where the vehicle is located; S71: If there is no obstacle in front of the target vehicle and the speed of the target vehicle is less than the speed of the host vehicle, the target vehicle has no intention to change lanes; S72: If there is a static obstacle in front of the target vehicle, the target vehicle has an intention to change lanes; S73: If there is a dynamic obstacle in front of the target vehicle, detect whether the speed of the dynamic obstacle is greater than that of the target vehicle; If the speed of the dynamic obstacle is greater than that of the target vehicle, the target vehicle has no intention to change lanes; If the speed of the dynamic obstacle is lower than that of the target vehicle and the target vehicle shows no signs of deceleration, then the target vehicle intends to change lanes.

Images