Method and apparatus for identifying vehicle lane change intent

Abstract

Methods and apparatuses for identifying a vehicle's lane change intent are provided. A method includes determining a lateral position of a vehicle relative to a current lane for a current time period; when the lateral position of the vehicle is in one of a left side region or a right side region relative to the current lane, determining a probability that the vehicle has an intent to change to a side lane corresponding to the lateral position given a prior probability that the vehicle has the intent to change to the side lane for the current time period and a probability that the vehicle is in the lateral position given the intent of the vehicle to change to the side lane; and determining to change a target lane of the vehicle from the current lane to the side lane based at least in part on the probability that the vehicle has the intent to change to the side lane given the lateral position of the vehicle for the current time period satisfying a lane change condition.

Description

Technical Field

[0001] This disclosure relates to automotive electronics technology, and more specifically, to methods and apparatus for recognizing a vehicle's lane-changing intentions. Background Technology

[0002] Advanced Driver Assistance Systems (ADAS) are a collection of hardware and software units designed to assist drivers. ADAS integrates and analyzes data from the vehicle's own operations, environmental data collected by various sensors, and other data to achieve various safety and adaptive functions. ADAS can warn of dangerous situations and erroneous driving behaviors, and control the vehicle, minimizing human error, improving road safety, and enhancing the driving experience.

[0003] During assisted driving, ADAS can select at least one vehicle associated with the currently targeted lane as the target vehicle for the assisted driving operation. By analyzing information such as the relative distance and speed between the vehicle and the target vehicle, ADAS can control the vehicle's speed and braking, or provide safety warnings or driving assistance to the driver. When the vehicle changes lanes, ADAS needs to identify the vehicle's lane-changing intention early in the lane-changing operation and switch the targeted lane and target vehicle in a timely manner to ensure driving safety and comfort. Therefore, timely and accurate identification of the vehicle's lane-changing intention is one of the important challenges in current assisted driving technologies. Summary of the Invention

[0004] In the Summary section, some selected concepts are presented in a simplified form, which will be further described in the Detailed Description section below. This Summary section is not intended to identify any key or essential features of the claimed subject matter, nor is it intended to help determine the scope of the claimed subject matter.

[0005] According to one aspect of this disclosure, a method for identifying a vehicle's lane-changing intention is provided, the method comprising: determining the lateral position of a vehicle relative to a current lane during a current time period, the lateral position including the vehicle being in one of a central region, a left region, or a right region relative to the current lane; when the lateral position of the vehicle is in one of the left region or the right region relative to the current lane, determining, at least in part, a probability that the vehicle intends to change to the side lane given that it is in the lateral position during the current time period, based on a prior probability that the vehicle intends to change to the side lane corresponding to the lateral position during the current time period and a probability that the vehicle is in the lateral position given that it intends to change to the side lane; and determining to change the vehicle's target lane from the current lane to the side lane, based at least in part on the probability that the vehicle intends to change to the side lane given that it is in the lateral position during the current time period satisfying a lane-changing condition.

[0006] According to one aspect of this disclosure, an assisted driving method is provided, the method comprising: determining a lateral position of a vehicle relative to a current lane during a current time period, the lateral position including the vehicle being in one of a central region, a left region, or a right region relative to the current lane; when the lateral position of the vehicle is in one of the left region or the right region relative to the current lane, determining, at least in part, a probability that the vehicle intends to change to the side lane given that the vehicle is in the lateral position during the current time period, based on a prior probability that the vehicle intends to change to the side lane corresponding to the lateral position during the current time period and a probability that the vehicle is in the lateral position given that the vehicle intends to change to the side lane; and determining to change the vehicle's target lane from the current lane to the side lane, based at least in part on a lane-changing condition satisfied by the probability that the vehicle intends to change to the side lane given that the vehicle is in the lateral position during the current time period.

[0007] According to one aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory coupled to the at least one processor and configured to store instructions, wherein, when executed by the at least one processor, the at least one processor causes the at least one processor to: determine the lateral position of a vehicle relative to a current lane during a current time period, the lateral position including the vehicle being in one of a central region, a left region, or a right region relative to the current lane; when the lateral position of the vehicle is in one of the left region or the right region relative to the current lane, determine, at least in part, a probability that the vehicle intends to change to the side lane given that the vehicle is in the lateral position during the current time period, based on a prior probability that the vehicle intends to change to the side lane corresponding to the lateral position during the current time period and a probability that the vehicle is in the lateral position given that the vehicle intends to change to the side lane; and determine to change the vehicle's target lane from the current lane to the side lane, based at least in part on a lane-changing condition satisfied by the probability that the vehicle intends to change to the side lane given that the vehicle is in the lateral position during the current time period.

[0008] According to one aspect of this disclosure, a computer program product is provided, comprising instructions that, when executed by at least one processor, cause the at least one processor to: determine the lateral position of a vehicle relative to a current lane during a current time period, the lateral position including the vehicle being in one of a central region, a left region, or a right region relative to the current lane; when the lateral position of the vehicle is in one of the left region or the right region relative to the current lane, determine, at least in part, a probability that the vehicle intends to change to the side lane given that it is in the lateral position during the current time period, based on a prior probability that the vehicle intends to change to the side lane corresponding to the lateral position during the current time period and a probability that the vehicle is in the lateral position given that it intends to change to the side lane; and determine to change the vehicle's target lane from the current lane to the side lane, based at least in part on a lane-changing condition satisfied by the probability that the vehicle intends to change to the side lane given that it is in the lateral position during the current time period. Attached Figure Description

[0009] The above and other objects, features and advantages of the embodiments of this disclosure will become more apparent from the more detailed description of the embodiments in conjunction with the accompanying drawings, in which the same reference numerals generally represent the same elements.

[0010] Figure 1 A schematic diagram illustrating exemplary vehicle driving scenarios based on some implementations of this disclosure is shown;

[0011] Figure 2 A schematic diagram of one implementation of the lane change intention calculation process according to the present disclosure is shown;

[0012] Figure 3 A flowchart is shown of an exemplary method for recognizing a vehicle's lane-changing intention, implemented according to this disclosure;

[0013] Figure 4 A block diagram of an exemplary device for recognizing a vehicle's lane-changing intention, according to the present disclosure, is shown.

[0014] Figure 5 A block diagram of an exemplary apparatus for recognizing a vehicle's lane-changing intention, according to another implementation of the present disclosure, is shown. Detailed Implementation

[0015] In the following description, numerous specific details are set forth for illustrative purposes. However, it should be understood that implementation of this disclosure can be carried out without these specific details. In other instances, well-known circuits, structures, and techniques have not been shown in detail so as not to affect the understanding of the description.

[0016] Throughout this specification, references to "an implementation," "implementation," "exemplary implementation," "some implementations," "various implementations," etc., indicate that the implementation of the content described in this disclosure may include specific features, structures, or characteristics. However, it is not implied that every implementation must include these specific features, structures, or characteristics. Furthermore, some implementations may have some, all, or none of the features described for other implementations.

[0017] In a manner most conducive to understanding the claimed subject matter, various operations may be described as a series of discrete actions or operations in sequence. However, the order in which they are described should not be construed as implying that these operations are necessarily order-dependent. In particular, these operations may be performed in a manner other than that presented. In other implementations, various additional operations may be performed, and / or various operations already described may be omitted.

[0018] In the specification and claims, the phrase "A and / or B" may appear to mean one of the following: (A), (B), (A and B). Similarly, the phrase "A, B and / or C" may appear to mean one of the following: (A), (B), (C), (A and B), (A and C), (B and C), (A and B and C).

[0019] In the specification and claims, the terms “coupled” and “connected” and their derivatives may be used. It is important to understand that these terms are not intended to be synonyms. Rather, in a particular implementation, “connected” is used to indicate that two or more components are in direct physical or electrical contact with each other, while “coupled” is used to indicate that two or more components cooperate or interact with each other, but they may or may not be in direct physical or electrical contact.

[0020] Advanced Driver Assistance Systems (ADAS) assist the vehicle's driving operations or driver behavior by comprehensively calculating and analyzing vehicle driving data and environmental data collected by sensors installed on the vehicle. ADAS includes systems such as Adaptive Cruise Control (ACC), Traffic Jam Assist (TJA), Intelligent Cruise Control (ICC), Lane Change Assist (LCA), and Automatic Lane Change Assist (ALC). A significant challenge in assisted driving is recognizing the vehicle's lane-changing intentions. The following describes a concept for a method based on this disclosure for recognizing a vehicle's lane-changing intentions, using an ACC system as an example.

[0021] The Adaptive Cruise Control (ACC) system is an intelligent driver assistance system developed from the Cruise Control System (CCS). Its main functions include cruise control, following lane control, stop-start function control, and forward collision warning control. When one or more of these functions are activated, the ACC system needs to identify the vehicle's current lane and whether there are vehicles ahead in that lane. If there are vehicles ahead, the nearest vehicle is selected as the target vehicle for calculations related to the various ACC functions. Therefore, when changing lanes, the ACC system needs to identify the vehicle's lane-changing intention early in the process and switch the lane from the current lane to the target lane to further identify the target vehicle. If the lane-changing intention cannot be identified in a timely manner, the lane switching will be delayed. Delayed lane switching may lead to undesirable consequences such as delayed braking or the need for frequent manual intervention by the driver.

[0022] Conventional lane-changing algorithms primarily determine the probability of a vehicle's specific lane-changing intention based on inputs such as the vehicle's turn signal status and its lateral velocity relative to the lane boundary. Therefore, if the driver does not activate the corresponding turn signal during a lane change and the vehicle's lateral velocity relative to the lane boundary is low, the lane-changing intention is difficult to identify, leading to delayed lane-keeping. This disclosure provides a method for timely and accurate identification of a vehicle's lane-changing intention.

[0023] The following is a reference. Figure 1 The diagram 100 illustrates an exemplary vehicle driving scenario according to some implementations of the present disclosure.

[0024] It should be understood that, for the purpose of clear illustration, Figure 1 The objects in the drawing are not drawn to scale. Figure 1 The diagram shows three lanes. Vehicle 101, equipped with ACC (Adaptive Cruise Control), is currently traveling in lane 110, with another vehicle 111 traveling directly in front of vehicle 101. Lane 120 is the left-adjacent lane to the current lane, and vehicle 121 is traveling in lane 120, positioned longitudinally in front of vehicle 101. Lane 130 is the right-adjacent lane to the current lane.

[0025] The current ACC system uses lane 110, where vehicle 101 is currently traveling, as the aiming lane, and vehicle 111 as the target vehicle.

[0026] Taking a vehicle changing lanes to the left as an example, when a vehicle changes lanes, the ACC system needs to identify the vehicle's lane-changing intention early in the process and promptly switch the target lane to lane 120, thus enabling it to promptly identify vehicle 121 as the target vehicle. After re-identifying the target vehicle, the ACC system can calculate the target speed and acceleration required for vehicle 101 to follow vehicle 121 based on information such as the relative distance and speed between vehicle 101 and vehicle 121, and automatically adjust the throttle opening and braking pressure to make vehicle 101 follow vehicle 121.

[0027] In one implementation, the lane-changing intention of vehicle 101 can include three types: changing to the left lane 120, changing to the right lane 130, and remaining in the current lane 110. At any given time, the sum of the probabilities of these three lane-changing intentions is 1. According to some implementations of this disclosure, whether to switch lanes can be determined at least in part based on the probability that the vehicle has one or more of the three lane-changing intentions when it is in a lateral position relative to the current lane 110.

[0028] For ease of discussion, the lateral position of vehicle 101 relative to the current lane 110 can be described as the region in which the vehicle is located relative to the current lane 110. In one implementation, the current lane can be divided into three regions: the left region, the middle region, and the right region.

[0029] Figure 1 The diagram schematically shows the left edge line 111-a and the right edge line 111-b of lane 110. Furthermore, Figure 1 The boundary lines 112-a and 112-b of the middle section of lane 110, the boundary line 121 of the area of ​​the left adjacent lane 120 immediately adjacent to the current lane, and the boundary line 131 of the area of ​​the right adjacent lane 130 immediately adjacent to the current lane are schematically shown.

[0030] In one implementation, the area between boundary lines 112-a and 112-b can be the middle area, the area between the left edge line 111-a and boundary line 112-a of lane 110 can be the left-side area, and the area between the right edge line 111-b and boundary line 112-b of lane 110 can be the right-side area. For example, the middle area can be the middle two-thirds of the lane; the left-side area can be the left one-sixth of the current lane; and the right-side area can be the right one-sixth of the current lane.

[0031] In another implementation, the area between boundary lines 112-a and 112-b is the middle area; the area between boundary line 121 and boundary line 112-a of the area of ​​the left adjacent lane 120 immediately adjacent to the current lane is the left area; and the area between boundary line 131 and boundary line 112-b of the area of ​​the right adjacent lane 130 immediately adjacent to the current lane is the right area. In this implementation, for example, the middle area could be the middle two-thirds of the current lane; the left area could be the left one-sixth of the current lane and the right one-sixth of the area of ​​the left adjacent lane; and the right area could be the right one-sixth of the current lane and the left one-sixth of the area of ​​the right adjacent lane.

[0032] It should be noted that other methods are also feasible for determining the division of regions, and are not limited to the specific example given above.

[0033] Figure 2 A schematic diagram 200 illustrates a lane change intention calculation process according to one embodiment of the present disclosure.

[0034] According to one implementation of this disclosure, when the lateral position of the vehicle is in either the left or right region relative to the current lane, the probability that the vehicle has the intention to change to the lane corresponding to the current lateral position can be calculated, and the lane to be aimed can be determined at least in part based on the calculated lane change intention probability.

[0035] In one implementation, Bayes' theorem can be used to calculate the probability that a vehicle, given its current lateral position, intends to change lanes to the side corresponding to that lateral position during the current time period.

[0036] The following describes the process of estimating a vehicle's lane-changing intention, taking the example of a vehicle traveling to the left of its current lane and considering the probability of the vehicle's intention to change lanes to the left. In one implementation, the probability (210) that the vehicle intends to change lanes to the left in the current time period when it is traveling to the left of its current lane can be calculated by the following formula: p(intention_to_change_left|in_left_area)=p(intentionK1)×p(transform_left)×p(in_left_area|intention_to_change_left) formula (1)

[0037] Here, p(intentionK1)(220) represents the probability that a vehicle had one of three lane-changing intentions in the previous time period. Specifically, p(intentionK1)(220) can include the probability p(change left laneK1) that a vehicle had the intention to change to the left lane, the probability p(change right laneK1) that a vehicle had the intention to change to the right lane, and the probability p(keep laneK1) that a vehicle had the intention to stay in the current lane. In one implementation, p(intentionK1)(220) can be obtained by storing the probabilities of the three lane-changing intentions of a vehicle in the previous time period and feeding them back into the input of the lane-changing intention calculation process in the current time period.

[0038] p(transform_left)(230) is the probability that a vehicle in the current time period intends to change to the left lane, given that the vehicle in the previous time period had three different lane-changing intentions. In one example, p(transform_left)(230) may include the probability that a vehicle in the current time period intends to change to the left lane given that the vehicle in the previous time period intended to change to the left lane (e.g., 0.9); the probability that a vehicle in the current time period intends to change to the left lane given that the vehicle in the previous time period intended to change to the right lane (e.g., 0.005); and the probability that a vehicle in the current time period intends to change to the left lane given that the vehicle in the previous time period intended to stay in the current lane (e.g., 0.005). In one implementation, p(transform_left)(230) may be pre-configurable.

[0039] p(in_left_area|intention_to_change_left)(240) is the probability that the vehicle is in the left area given that it intends to change to the left lane. In one implementation, the probability that the vehicle is in the left area given that it intends to change to the left lane can be preconfigured.

[0040] The product of p(intentionK1)(220) and p(transform_left)(230) can be called the prior probability prior_left(250) that the vehicle intends to change to the left lane in the current time period. prior_left(250) can be calculated by the following formula: prior_left=p(intentionK1)*p(transform_left) formula (2)

[0041] For example, substituting the values ​​of p(intentionK1) and p(transform_left) into formula (2), prior_left(250) can be: prior_left=p(change left laneK1)*0.9+p(change right laneK1)*0.005+p(keep laneK1)*0.005

[0042] Therefore, substituting formula (2) into formula (1), the probability (210) that the vehicle intends to change to the left lane in the current time period when it is traveling in the area to the left of the current lane can be calculated by the following formula: p(intention_to_change_left|in_left_area)=prior_left×p(in_left_area|intention_to_change_left) Formula (3)

[0043] Based on the same principle, the probability (260) that a vehicle intends to change lanes to the right when it is traveling in the area to the right of its current lane can be calculated by the following formula: p(intention_to_change_right|in_right_area)=p(intentionK1)×p(transform_right)×p(in_right_area|intention_to_change_right) Formula (4)

[0044] Wherein, p(intentionK1)(220) is the probability that the vehicle has three lane-changing intentions in the previous period, which is the same as p(intentionK1)(220) described in the above formula (1).

[0045] Among them, p(transform_right)(270) is similar to p(transform_left)(230) described in the above formula (1), which is the probability that a vehicle in the current time period has the intention to change to the right lane under the premise that the vehicle has three lane-changing intentions in the previous time period.

[0046] Here, p(in_right_area|intention_to_change_right)(280) is similar to p(in_left_area|intention_to_change_left)(240) described in formula (1) above, and represents the probability that the vehicle is in the right-hand area given that the vehicle intends to change to the right lane. In one implementation, the probability that the vehicle is in the right-hand area given that the vehicle intends to change to the right lane can be preconfigured.

[0047] The product of p(intentionK1)(220) and p(transform_right)(270) can be called the prior probability prior_right(290) that the vehicle intends to change to the right lane in the current time period. prior_right(290) can be calculated as follows: prior_right=p(intentionK1)*p(transform_right) Formula (5)

[0048] Therefore, substituting formula (5) into formula (4), the probability (260) that the vehicle intends to change to the right lane in the current time period when it is traveling in the right area relative to the current lane can be calculated by the following formula: p(intention_to_change_right|in_right_area)=prior_right×p(in_right_area|intention_to_change_right) Formula (6)

[0049] The following is for reference. Figure 3 The present disclosure describes a method 300 for identifying a vehicle's lane-changing intention.

[0050] The method begins at step 310, in which the lateral position of the vehicle relative to the current lane is determined for the current time period. For example, the lateral position of the vehicle includes the vehicle being in one of the center, left, or right regions relative to the current lane.

[0051] In one implementation, the lateral position of the vehicle can be determined based on which of the three regions relative to the current lane the rear axle center is located in.

[0052] For example, when the rear axle center of the vehicle is located in the middle two-thirds of the current lane, the vehicle can be determined to be in the center area relative to the current lane. When the rear axle center of the vehicle is located in the left one-sixth of the current lane, the vehicle can be determined to be in the left area relative to the current lane. When the rear axle center of the vehicle is located in the right one-sixth of the current lane, the vehicle can be determined to be in the right area relative to the current lane.

[0053] In one implementation, the left and right regions can be widened to the left and right adjacent lanes of the current lane, respectively. For example, the vehicle is determined to be in the left region when its rear axle center is located in the left one-sixth of the current lane, and also when its rear axle center is located in the right one-sixth of the current lane's left adjacent lane. Similarly, the vehicle is determined to be in the right region when its rear axle center is located in the right one-sixth of the current lane, and also when its rear axle center is located in the left one-sixth of the current lane's right adjacent lane.

[0054] By widening the left and right lane regions to the adjacent lanes on the left and right, respectively, the accuracy and consistency of lane-change intention recognition can be improved. For example, without widening the left lane region to the left lane, when a vehicle changes lanes to the left, it is assumed to be in the left lane region relative to the current lane when the vehicle's rear axle center moves to the area one-sixth of the way to the left of the current lane. However, when the vehicle's rear axle center moves across the left edge line and enters the left lane, the capture of the vehicle's position in the left lane region at that moment may be lost, resulting in inaccurate or abrupt results in determining the vehicle's lane-change intention.

[0055] Those skilled in the art will understand that the above-described division of areas is merely an example and not a limitation.

[0056] In another implementation, for example, the lateral position of the vehicle can be determined based on which of three regions relative to the current lane a straight line parallel to the lane passing through any point on the vehicle's profile lies within. In yet another implementation, for example, the lateral position of the vehicle can be determined based on which of three regions relative to the current lane a straight line parallel to the lane passing through any point on the vehicle lies within.

[0057] Next, method 300 proceeds to step 320, in which, when the vehicle's lateral position is either in the left or right region relative to the current lane, it is based at least in part on the prior probability that the vehicle has the intention to change lanes to the side corresponding to the lateral position during the current time period (e.g., prior_left(250) in formula (3), prior_right(290) in formula (6)) and the probability that the vehicle is in the lateral position given that the vehicle has the intention to change lanes to the side (e.g., p(in_left_area|intention_to_c) in formula (3)). The probability that a vehicle has the intention to change to the lane on the side given that the vehicle is in the lateral position at the current time (e.g., p(in_right_area|intention_to_change_right) in Formula (3) and p(intention_to_change_right|in_right_area) in Formula (6) is determined by p(intention_to_change_left|in_left_area) in Formula (3) and p(intention_to_change_right|in_right_area) in Formula (6).

[0058] In one implementation, the three lane-changing intentions include the intention of the vehicle to change to the lane corresponding to its lateral position, the intention of the vehicle to change to the lane opposite to said lane, and the intention of the vehicle to remain in the current lane. As described with reference to Equations (1) and (3), the prior probability is determined at least in part based on the probability p(intentionK1) of the vehicle having the three lane-changing intentions in the previous time period (e.g., p(intentionK1)(220) in Equations (1) and (3)) and the probability p(transform) of the vehicle having the intention to change to the lane corresponding to its lateral position in the current time period given that the vehicle had the three lane-changing intentions in the previous time period (e.g., p(transform_left)(230) in Equation (1) and p(transform_right)(270) in Equation (4)).

[0059] In one implementation, the probability that a vehicle intends to change lanes to the side corresponding to the lateral position when it is in the current time period can be determined by the following formula: p(intention_to_change_lane|in_lane_changing_area)=prior p(in_lane_changing_area|intention_to_change_lane) Formula (7)

[0060] Understandably, as an example, when the vehicle's lateral position is in the left area relative to the current lane, the prior probability of the vehicle having the intention to change to the left lane in the current time period, prior_left (250), can be used as prior, and the probability of the vehicle being in the left area given that the vehicle has the intention to change to the left lane, p(in_left_area|intention_to_change_left) (240), can be used as p(in_lane_changing_area|intention_to_change_lane) to be substituted into formula (7) to calculate the probability of the vehicle having the intention to change to the left lane given that the vehicle is in the left area in the current time period, p(intention_to_change_lane|in_lane_changing_area).

[0061] In another example, when the vehicle's lateral position is that the vehicle is in the right area relative to the current lane, the prior probability prior_right (290) of the vehicle's intention to change to the right lane in the current time period can be used as prior, and the probability p(in_right_area|intention_to_change_right) (280) of the vehicle being in the right area given that the vehicle has the intention to change to the right lane can be used as p(in_lane_changing_area|intention_to_change_lane) to be substituted into formula (7) to calculate the probability p(intention_to_change_lane|in_lane_changing_area) of the vehicle having the intention to change to the right lane given that the vehicle is in the right area in the current time period.

[0062] In one implementation, the probability p(in_lane_changing_area|intention_to_change_lane) that the vehicle is in the lateral position given its intention to change lanes to the side corresponding to the lateral position is determined at least in part based on the vehicle's lateral position in the current time period. For example, in one implementation, the probability p(in_lane_changing_area|intention_to_change_lane) that the vehicle is in the lateral position given its intention to change lanes to the side corresponding to the lateral position can be preconfigurable.

[0063] In one example, the probability p(in_lane_changing_area|intention_to_change_lane) that the vehicle is in the lateral position given that the vehicle intends to change to the lane corresponding to the lateral position can be set to be greater than both the probability that the vehicle is in the center area given that the vehicle intends to change to that lane and the probability that the vehicle is in the area opposite to the lateral position given that the vehicle intends to change to that lane.

[0064] In another example, the probability p(in_lane_changing_area|intention_to_change_lane) that the vehicle is in the lateral position given the vehicle's intention to change to the lane corresponding to that lateral position can be set to greater than or equal to two-thirds of the width of the current lane (e.g., Meanwhile, the probability that the vehicle is in the center area given that the vehicle intends to change to that side lane, and the probability that the vehicle is in the area opposite to the lateral position given that the vehicle intends to change to that side lane, are set to zero.

[0065] Next, method 300 proceeds to step 330, in which it is determined, at least in part, that the vehicle’s lane of aiming at the lane is changed from the current lane to the lane on the side of the lane corresponding to the lateral position, based on the probability p(intention_to_change_lane|in_lane_changing_area) that the vehicle has the intention to change to the lane on the side of the lane when the vehicle is in the lateral position at the current time satisfies the lane change condition.

[0066] In one implementation, the lane-changing condition may include a probability p(intention_to_change_lane|in_lane_changing_area) that the vehicle intends to change lanes to the side corresponding to the lateral position given that the vehicle is currently in a lateral position is greater than a lane-changing threshold. For example, the lane-changing threshold may be preconfigurable.

[0067] In another implementation, the lane-changing condition may include: the probability p(intention_to_change_lane|in_lane_changing_area) that the vehicle has the intention to change to the lane corresponding to the lateral position when the vehicle is in the lateral position at the current time is greater than all of the following: the probability that the vehicle has the intention to change to the lane opposite to the lane when the vehicle is in the lateral position at the current time, and the probability that the vehicle has the intention to remain in the current lane when the vehicle is in the lateral position at the current time.

[0068] In one implementation, determining that a vehicle will change lanes to the side corresponding to its lateral position is based at least in part on the probability that the vehicle intends to change lanes to the side given that the vehicle's turn signal is on during the current time period, and / or the probability that the vehicle intends to change lanes to the side given its lateral speed during the current time period.

[0069] For example, when a vehicle's left turn signal is on, the probability that the vehicle intends to change to the left lane given that its left turn signal is on during the current time period can be determined at least in part based on the prior probability that the vehicle intends to change to the left lane during the current time period and the probability that the vehicle's left turn signal is on given that the vehicle intends to change to the left lane. Similarly, in one example, when a vehicle's right turn signal is on, the probability that the vehicle intends to change to the right lane given that its right turn signal is on during the current time period can be determined at least in part based on the prior probability that the vehicle intends to change to the right lane during the current time period and the probability that the vehicle's right turn signal is on given that the vehicle intends to change to the right lane.

[0070] As an example, the probability that a vehicle will change lanes to the side corresponding to its lateral position can be determined at least in part based on the product of: the probability that the vehicle intends to change lanes to the side corresponding to its lateral position when it is in a lateral position at the current time, the probability that the vehicle intends to change lanes to the side when its turn signal is on at the current time, and / or the probability that the vehicle intends to change lanes to the side when it has a lateral speed at the current time.

[0071] The methods for recognizing a vehicle's lane-change intentions according to some implementations of this disclosure can be applied as general driver assistance methods to various ADAS driving assistance functions that require lane changes, including but not limited to adaptive cruise control (ACC), traffic jam assist (TJA), intelligent cruise control (ICC), lane change assist (LCA), automatic lane change assist (ALC), and other driver assistance functions or systems. According to some implementations of this disclosure, after determining the vehicle's lane-change intention, the targeting lane can be switched to a new target lane, and one or more vehicles associated with the new target lane can be identified as target vehicles. After re-determining the target lane and the new target vehicles, the driver assistance system can calculate various information required for implementing driver assistance operations such as following, collision detection, lane keeping, and lane change assist based on information such as relative distance and speed to one or more target vehicles, and perform corresponding operations and / or feedback.

[0072] The above text combines Figure 3 A flowchart illustrating example method 300 according to some implementations of this disclosure is provided. Those skilled in the art will understand that the methods described herein are merely exemplary and not restrictive. Unless otherwise expressly stated, the operations shown are not necessarily to be performed in the order described, and not every operation described herein is necessary for implementing a particular implementation of this disclosure. In other implementations, method 300 may also include other operations described in the specification. Furthermore, it is understood that various operations of the exemplary method 300 can be implemented using software, hardware, firmware, or any combination thereof.

[0073] Figure 4 A block diagram of an implementation of a device 400 for recognizing a vehicle's lane-changing intention is shown, according to the present disclosure. Device 400 may include, for example, a domain controller, a forward-looking camera, a system-on-a-chip (SoC), a microcontroller, etc., for implementing the methods described herein.

[0074] like Figure 4As shown, device 400 may include module 410 for determining the lateral position of a vehicle relative to a current lane during a current time period, the lateral position including the vehicle being in one of the center region, left region, or right region relative to the current lane. Furthermore, device 400 may include module 420 for determining, at least in part, the probability that the vehicle intends to change lanes to the side lane given that it is in the lateral position during the current time period, based on a prior probability that the vehicle intends to change lanes to the side lane corresponding to the lateral position during the current time period, and the probability that the vehicle is in the lateral position given the intention to change lanes to the side lane. Additionally, device 400 may include module 430 for determining to change the vehicle's lane from the current lane to the side lane, based at least in part on the probability that the vehicle intends to change lanes to the side lane given that it is in the lateral position during the current time period, satisfying a lane-changing condition.

[0075] In some implementations, the various modules of device 400 may be combined or separated depending on actual needs. Those skilled in the art will understand that the exemplary device 400 may be implemented using software, hardware, firmware, or any combination thereof.

[0076] Figure 5 A block diagram of an exemplary electronic device 500 for recognizing a vehicle's lane-change intention, according to this disclosure, is shown. The electronic device 500 may include, for example, a domain controller, a forward-looking camera, a system-on-a-chip (SoC), a microcontroller, etc., for implementing the methods described herein. In one example, the electronic device 500 may be implemented in a vehicle including an ADAS system. For example, the electronic device 500 may be implemented in a vehicle's ADAS system to achieve optimized vehicle lane-change intention recognition.

[0077] like Figure 5 As shown, the electronic device 500 may include at least one processor 510. The processor 510 may include any type of general-purpose processing unit, special-purpose processing unit, core, circuitry, controller, etc. Furthermore, the electronic device 500 may also include a memory 520 coupled to the at least one processor. The memory 520 may include any type of medium that can be used to store data. In some implementations, the memory 520 is configured to store instructions that, when executed, cause the at least one processor 510 to perform the operations described herein, for example, in conjunction with... Figure 3 The flowchart of the exemplary method 300 describes various operations.

[0078] Furthermore, in some implementations, the electronic device 500 may also be equipped with a communication interface that supports various types of wired / wireless communication protocols to communicate with a communication network. Examples of communication networks may include, but are not limited to: Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), Public Telephone Network, Internet, Intranet, Internet of Things (IoT), Infrared Network, Bluetooth Network, Near Field Communication (NFC) Network, ZigBee Network, and so on.

[0079] Furthermore, in some implementations, the aforementioned and other components of the electronic device 500, as well as the electronic device 500 and other components of the work vehicle, can communicate with each other via one or more buses / interconnects, which can support any suitable bus / interconnect protocol, including Peripheral Component Interconnect (PCI), Fast PCI, Universal Serial Bus (USB), Serial Attached SCSI (SAS), Serial ATA (SATA), Fibre Channel (FC), System Management Bus (SMBus), Controller Area Network (CAN) bus, or other suitable protocols.

[0080] Those skilled in the art will understand that the above description of the structure of electronic device 500 is merely exemplary and not restrictive, and other structures are also feasible, as long as they can be used to achieve the functions described herein.

[0081] Various implementations of this disclosure may include or operate on multiple components, parts, units, modules, instances, or mechanisms that can be implemented in hardware, software, firmware, or any combination thereof. Examples of hardware may include, but are not limited to: devices, processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field-programmable gate arrays (FPGAs), memory cells, logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. Examples of software may include, but are not limited to: software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application programming interfaces (APIs), instruction sets, computer code, computer code segments, words, values, symbols, or any combination thereof. Determining whether an implementation is to be implemented using hardware, software, and / or firmware can vary depending on a variety of factors, such as desired compute speed, power level, thermal tolerance, processing cycle budget, input data rate, output data rate, memory resources, data bus speed, and other design or performance constraints, as is expected of a given implementation. Some implementations described herein may include an article of writing. The article of writing may include a storage medium. Examples of storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (e.g., computer-readable instructions, data structures, program modules, or other data). Storage media may include, but are not limited to: random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc (CD), digital multi-disc (DVD) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage or other magnetic storage devices, or any other medium capable of storing information. In some implementations, the article of writing may store executable computer program instructions that, when executed by one or more processing units, cause the processing units to perform the operations described herein. Executable computer program instructions may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, etc. Executable computer program instructions can be implemented using any appropriate high-level, low-level, object-oriented, visual, compiled, and / or interpreted programming language.

[0082] The examples described above include those of the disclosed architecture. It is certainly impossible to describe every conceivable combination of components and / or methods, but those skilled in the art will understand that many other combinations and arrangements are also possible. Therefore, this novel architecture is intended to cover all such alternatives, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A method for identifying a vehicle's lane-changing intention, comprising: Determine the lateral position of the vehicle relative to the current lane during the current time period, wherein the lateral position includes the vehicle being located in one of the center, left, or right regions relative to the current lane; When the lateral position of the vehicle is in either the left or right region relative to the current lane, the probability that the vehicle intends to change lanes to the side lane corresponding to the lateral position is determined at least in part based on the prior probability that the vehicle intends to change lanes to the side lane corresponding to the lateral position in the current time period and the probability that the vehicle is in the lateral position given that the vehicle intends to change lanes to the side lane. as well as The determination to change the vehicle's lane from the current lane to the side lane is based at least in part on the probability that the vehicle intends to change lanes to the side lane when the vehicle is in the lateral position during the current time period.

2. The method according to claim 1, wherein, The probability that a vehicle is in the lateral position, assuming the vehicle intends to change lanes to that side, is determined at least in part based on the vehicle's lateral position during the current time period.

3. The method according to claim 1, wherein, The prior probability is determined at least in part based on the probability that the vehicle had one of the three lane-changing intentions in the previous time period and the probability that the vehicle in the current time period had the intention to change to the lane on the previous side, given that the vehicle had the three lane-changing intentions in the previous time period.

4. The method according to claim 3, wherein, The three lane-changing intentions include the intention of the vehicle to change to one lane, the intention of the vehicle to change to the opposite lane from the one lane, and the intention of the vehicle to remain in the current lane.

5. The method according to claim 1, wherein, The probability that the vehicle is in the lateral position is greater than all of the following, provided that the vehicle intends to change lanes to the side of the lane: The probability that the vehicle is in the central area given that the vehicle intends to change lanes to the side, and The probability that the vehicle is in an area opposite to the lateral position, provided that the vehicle intends to change lanes to the side of the lane.

6. The method according to claim 1, wherein, The probability that the vehicle is in the lateral position is greater than or equal to two-thirds of the width of the current lane, provided that the vehicle intends to change lanes to the side of the lane. The probability that the vehicle is in the center area is zero, provided that the vehicle intends to change lanes to that side. The probability that the vehicle is in an area opposite to the lateral position is zero, provided that the vehicle intends to change lanes to that side.

7. The method according to claim 1, wherein, The probability that a vehicle is in the lateral position is preconfigurable, provided that the vehicle intends to change lanes to that side.

8. The method according to claim 1, wherein, The lane change conditions include: When the vehicle is in the lateral position during the current time period, the probability that the vehicle intends to change lanes to that side is greater than the lane change threshold.

9. The method according to claim 1, wherein, The lane change conditions include: Given that the vehicle is in the lateral position during the current time period, the probability that the vehicle intends to change lanes to that side is greater than all of the following: Given that the vehicle is in the lateral position at the current time, there is a probability that the vehicle intends to change lanes to the opposite lane relative to the lane on one side. Given that the vehicle is in the lateral position at the current time, there is a probability that the vehicle intends to remain in the current lane.

10. The method according to claim 1, wherein, Determining the lateral position includes: When the rear axle center of the vehicle is located within the middle two-thirds of the current lane, the vehicle is determined to be located in the central area; When the rear axle center of the vehicle is located in the area one-sixth of the way to the left of the current lane, the vehicle is determined to be in the left-hand area; or When the rear axle center of the vehicle is located in the right-hand area of ​​the current lane, the vehicle is determined to be in the right-hand area.

11. The method of claim 10, further comprising determining that the vehicle is located in the left-hand region when the rear axle center of the vehicle is located in the right-hand one-sixth region of the adjacent lane to the left of the current lane.

12. The method of claim 10, further comprising determining that the vehicle is located in the right-hand region when the rear axle center of the vehicle is located in the left-hand one-sixth region of the adjacent right lane of the current lane.

13. The method of claim 1, wherein determining that the vehicle will change lanes on one side is based at least in part on one or more of the following: Given that the vehicle's turn signal is on during the current time period, there is a probability that the vehicle intends to change lanes to that side. Given the vehicle's lateral speed during the current time period, there is a probability that the vehicle intends to change lanes to that side.

14. A driving assistance method, comprising the method according to any one of claims 1-13.

15. The method according to claim 14, wherein, The method is performed by at least one of the following: Traffic Jam Assist (TJA); Intelligent Navigation Control (ICC); Lane change assist (LCA); or Automatic Lane Change Assist (ALC).

16. An electronic device comprising: At least one processor; as well as A memory coupled to the at least one processor and used to store instructions, wherein, when executed by the at least one processor, the instructions cause the at least one processor to perform the method according to any one of claims 1-13.

17. The electronic device according to claim 16, wherein, The electronic device includes a domain controller or a forward-facing camera.

18. A computer program product comprising instructions that, when executed by at least one processor, cause the at least one processor to perform the method according to any one of claims 1-15.

Images