Vehicle detour methods, devices, electronic equipment, vehicles and storage media

Abstract

This application discloses a vehicle detour method, device, electronic device, vehicle, and storage medium. Specifically, it includes: acquiring a reference trajectory of the current vehicle, a map of the current area, and obstacle information within a preset range of the current area obtained through the vehicle's perception system; determining the obstacle sequence in the current area based on the reference trajectory and obstacle information; determining whether the current vehicle meets the conditions for prohibiting detour based on the reference trajectory, the map of the current area, and the obstacle sequence; if the current vehicle does not meet the conditions for prohibiting detour, determining the detour direction of the current vehicle based on the map of the current area and the obstacle sequence, and performing detour movement in the detour direction. The method determines a detour decision based on the determination of the prohibition conditions based on the reference trajectory, the map of the current area, and obstacle information; and determines the detour direction based on the obstacles, improving the rationality of the detour decision. This reduces the detour trajectory planning time, further improving the efficiency of detour planning while ensuring safety.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle detour method, apparatus, electronic device, vehicle, and storage medium. Background Technology

[0002] With the hardware upgrades of various sensors and the development of automation technologies such as artificial intelligence, more and more vehicles are adopting driver assistance technologies or even autonomous driving technologies. In autonomous driving scenarios, obstacles such as other vehicles and pedestrians encountered during the vehicle's autonomous navigation have become a critical issue that urgently needs to be addressed.

[0003] Currently, in autonomous driving scenarios, to address potential obstacles in the middle of the lane, personnel use sensor technology to acquire information about obstacles within a certain range around the vehicle, plan multiple candidate trajectories, and determine the probability of successful detour along different trajectories before selecting a route. However, this method does not consider the rationality of the vehicle's driving process, resulting in lower safety in actual use and reduced efficiency in detour planning. Summary of the Invention

[0004] This application provides a vehicle detour method, apparatus, electronic device, vehicle, and storage medium to improve the rationality and safety of detour decisions and increase the efficiency of detour planning.

[0005] According to one aspect of this application, a vehicle detour method is provided, the method comprising:

[0006] Acquire the current vehicle's reference trajectory, the map of the area it is in, and obstacle information within a preset range of the area obtained through the current vehicle's perception system;

[0007] Based on the reference trajectory and obstacle information, determine the sequence of obstacles in the area;

[0008] Based on the reference trajectory, the map of the area, and the sequence of obstacles, determine whether the current vehicle meets the conditions for prohibiting detours;

[0009] If the current vehicle does not meet the conditions for prohibiting detours, the detour direction of the current vehicle is determined according to the map of the area and the sequence of obstacles, and the vehicle detours in the detour direction.

[0010] According to another aspect of this application, a vehicle bypass device is provided, comprising:

[0011] The information acquisition module is used to acquire the current vehicle's reference trajectory, the map of the area, and obstacle information within a preset range of the area obtained through the current vehicle's perception system.

[0012] The sequence determination module is used to determine the sequence of obstacles in the area based on the reference trajectory and obstacle information;

[0013] The detour judgment module is used to determine whether the current vehicle meets the conditions for prohibiting detours based on the reference trajectory, the map of the area, and the sequence of obstacles.

[0014] The direction determination module is used to determine the detour direction of the current vehicle based on the map of the area and the sequence of obstacles if the current vehicle does not meet the conditions for prohibiting detours, and then detour in the detour direction.

[0015] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and,

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle detour method described in any embodiment of this application.

[0019] According to another aspect of this application, a vehicle is provided which is equipped with an electronic device as provided in the embodiments of this application.

[0020] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle detour method described in any embodiment of this application.

[0021] The technical solution of this application embodiment not only determines the detour decision based on the judgment of the detour prohibition conditions according to the reference trajectory, the local area map and obstacle information, but also determines the detour direction based on the obstacle information, thereby improving the rationality of the detour decision and reducing the trajectory planning time of the detour movement. While ensuring the safety of vehicle detour, it can further improve the efficiency of detour planning.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a vehicle detour method according to Embodiment 1 of this application;

[0025] Figure 2 This is a flowchart of a vehicle detour method applicable to Embodiment 2 of this application;

[0026] Figure 3A This is a schematic diagram of a detour direction determination provided in Embodiment 3 of this application;

[0027] Figure 3B This is a schematic diagram of a detour direction determination provided in Embodiment 3 of this application;

[0028] Figure 3C This is a schematic diagram of a detour direction determination provided in Embodiment 3 of this application;

[0029] Figure 4 This is a structural schematic diagram of a vehicle bypass device according to Embodiment 4 of this application;

[0030] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the vehicle detour method of the embodiments of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This application provides a flowchart of a vehicle detour method according to Embodiment 1. This embodiment is applicable to situations where an autonomous vehicle detours around an obstacle (vehicle) in its current lane to overtake and return to the current lane. This method can be executed by a vehicle detour device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0035] S110. Obtain the reference trajectory of the current vehicle, the map of the area, and obstacle information within a preset range of the area obtained through the current vehicle's perception system.

[0036] In this context, the current vehicle can be a vehicle already traveling in the lane. In an autonomous driving scenario, the current vehicle is in autonomous driving and / or automatic cruise control mode. When overtaking or detouring is required, the vehicle can automatically assess road conditions and detour. The embodiments of this application illustrate the determination of the detour direction based on this scenario. It should be noted beforehand that the term "detour" in the embodiments of this application refers to the vehicle bypassing an obstacle ahead and returning to the lane corresponding to its original reference trajectory, and does not imply taking a detour or similar detour.

[0037] The reference trajectory of the current vehicle can be a pre-set driving route in the autonomous driving scenario, which may include, but is not limited to, the planned path and lane between the origin and destination. Since the reference trajectory is predetermined during autonomous driving, it can be directly obtained here. The local area map can be map information of a certain range where the current vehicle is currently driving. The local area map can be obtained through real-time positioning information and related navigation information, which is not limited in this embodiment. The current vehicle's perception system can be composed of a series of sensors and processors for perceiving road condition information. Through the perception system, obstacle information within a preset range in the current map area can be obtained. Of course, these obstacles can include dynamic obstacles and static obstacles. It should be explained that the distinction between dynamic and static obstacles depends on the selected reference frame and is not an absolute definition. For example, other vehicles traveling at the same speed as the current vehicle in the lane ahead of the current vehicle are considered dynamic obstacles relative to the world reference frame, but are static obstacles (relatively stationary) relative to the current vehicle's reference frame.

[0038] S120. Based on the reference trajectory and obstacle information, determine the sequence of obstacles in the area.

[0039] An obstacle sequence can be a series of closely spaced obstacles. It's understandable that it's dangerous for a vehicle to weave between nearby obstacles (such as other vehicles) while returning to its original lane. Therefore, the system first determines if there are consecutive, closely spaced obstacles in the obstacle information ahead of the lane based on the reference trajectory, and defines these consecutive obstacles as an obstacle sequence. Of course, an obstacle sequence can include at least one obstacle.

[0040] In one optional implementation, the obstacle sequence may include a forward obstacle sequence in the current vehicle's direction of travel. Determining the obstacle sequence in the area based on the reference trajectory and obstacle information may include: determining the reference driving lane of the current vehicle based on the reference trajectory; and sorting the distances between each obstacle and the current vehicle in the direction of travel from largest to smallest to obtain the forward obstacle sequence.

[0041] It is understandable that when a vehicle changes lanes to detour, it must avoid a series of obstacles ahead of its current lane. Therefore, based on the reference trajectory, the corresponding lane on the map, i.e., the reference operating lane, can be determined using high-precision map information. By sorting the obstacles within a certain preset range determined by the perception system according to their distance from the current vehicle in the direction of travel and within the reference operating lane, from farthest to closest, a forward obstacle sequence can be obtained.

[0042] The above implementation provides a way to determine the sequence of forward obstacles for vehicle detours, effectively helping the current vehicle to identify multiple consecutive obstacles in front of the reference operating lane, thereby helping the vehicle to bypass these consecutive obstacles and return to the reference operating lane, which helps to improve the safety and efficiency of vehicle detours.

[0043] Based on this, the method may include: if the distance between two adjacent obstacles exceeds a preset length threshold, then assign the two obstacles to different obstacle sequences respectively.

[0044] The preset length threshold can be the allowable distance between obstacles. Understandably, if two obstacles (such as other vehicles in motion) are far apart in the same lane, they can be assigned to two different obstacle sequences. This allows the vehicle to first bypass the closer obstacle sequence, then re-evaluate the obstacle sequence and bypass the more distant one, further ensuring the safety and rationality of the vehicle's detour.

[0045] S130. Based on the reference trajectory, the map of the area, and the sequence of obstacles, determine whether the current vehicle meets the conditions for prohibiting detours.

[0046] Among them, the prohibition conditions can be the prohibition conditions that need to be judged before the current vehicle can detour. There can be multiple prohibition conditions. If any one of the prohibition conditions is met, the current vehicle is not allowed to detour. If none of the prohibition conditions are met, it means that the current vehicle can detour here.

[0047] Furthermore, the conditions prohibiting detours include at least one of the following:

[0048] The current vehicle speed exceeds the preset speed threshold;

[0049] The duration of the forward obstacle sequence is less than a preset duration threshold;

[0050] The distance between the forward obstacle sequence and the nearest intersection ahead in the current vehicle's direction of travel is less than a first preset distance threshold;

[0051] The distance between the forward obstacle sequence and the current vehicle's destination is less than a second preset distance threshold;

[0052] The sequence of obstacles ahead is within the solid lane line.

[0053] Understandably, the prohibition on detours applies only to situations where vehicles are not allowed to detour. Specifically, in the first point, if the current vehicle is traveling too fast, it actually indicates that the road conditions are good, and vehicles ahead in the reference lane are also maintaining high speeds. Under these ideal conditions, the current vehicle does not need to detour or overtake.

[0054] Secondly, the preset duration threshold can be a time threshold for the existence of the forward obstacle sequence. If the duration of the obstacle sequence exceeds this threshold, it can be understood that the forward obstacle sequence is stable, and therefore the current vehicle can bypass it by changing lanes, accelerating, or other means. Similarly, if the duration of the forward obstacle sequence is less than this threshold, it means that the forward obstacle sequence is unstable and only exists for a very short time, so the current vehicle does not need to bypass it.

[0055] Thirdly, the first preset distance threshold can be used to determine the distance between the forward obstacle sequence and the nearest intersection ahead of the reference driving lane. If this distance is very small, that is, the forward obstacle sequence is close to the intersection, it is conceivable that if the forward obstacle sequence is close to the intersection, the current vehicle will not be able to return to the reference driving lane at the intersection after detouring, and therefore cannot perform the detouring movement.

[0056] In the fourth point, the second preset distance threshold can be used to determine whether the current vehicle is close to the destination of the reference trajectory. It should be noted that at the beginning of autonomous driving, the destination is of course already determined. If the current vehicle is less than the second preset distance threshold from the destination, it means that the current vehicle is very close to the destination, and there is no need to perform detour.

[0057] Fifthly, if the sequence of obstacles ahead is within the solid lines of the lane, one cannot bypass it by changing lanes or accelerating; one must strictly abide by traffic rules.

[0058] Of course, it should be added that the aforementioned preset duration threshold, first preset distance threshold, second preset distance threshold, etc., can all be set by relevant technical personnel according to the actual situation and experimental results, and this application embodiment does not limit this.

[0059] The above implementation provides a basis for vehicles in autonomous driving scenarios to determine whether they can detour before detouring. If at least one of the above-mentioned conditions prohibiting detouring is met, the vehicle cannot choose to detour; conversely, if none of the above-mentioned conditions prohibiting detouring are met, the vehicle can choose to detour, thus ensuring the safety of the vehicle when detouring.

[0060] S140. If the current vehicle does not meet the conditions for prohibiting detours, the detour direction of the current vehicle shall be determined according to the map of the area and the sequence of obstacles, and the vehicle shall detour in the detour direction.

[0061] As mentioned above, if a vehicle does not meet the conditions for prohibiting detours, it can choose to detour. In this case, the detour direction needs to be determined based on the map of the area where the vehicle is located and the sequence of obstacles. It's understood that the obstacle sequence includes not only the forward obstacle sequence ahead of the reference lane, but also other obstacle sequences in the adjacent lanes to the left and right of the reference lane, such as other vehicles traveling in those lanes. These other obstacle sequences may affect the vehicle's turning or lane changing. Therefore, the impact of these other obstacle sequences on the vehicle's detour must be considered, and then the direction in which the vehicle is allowed to detour must be determined before controlling the vehicle to detour in that direction.

[0062] The technical solution of this application embodiment not only determines the detour decision based on the judgment of the detour prohibition conditions according to the reference trajectory, the local area map and obstacle information, but also determines the detour direction based on the obstacle information, thereby improving the rationality of the detour decision and reducing the trajectory planning time of the detour movement. While ensuring the safety of vehicle detour, it can further improve the efficiency of detour planning.

[0063] Example 2

[0064] Figure 2 This is a flowchart of a vehicle detour method provided in Embodiment 2 of this application. This embodiment further refines the determination of the vehicle detour direction based on the above-described embodiments. The obstacle sequence includes the obstacle sequence of adjacent lanes of the current vehicle's driving lane. For example... Figure 2 As shown, the method includes:

[0065] S210. Obtain the reference trajectory of the current vehicle, the map of the area, and obstacle information within a preset range of the area obtained through the current vehicle's perception system.

[0066] S220. Based on the reference trajectory and obstacle information, determine the sequence of obstacles in the area.

[0067] S230. Based on the reference trajectory, the map of the area, and the sequence of obstacles, determine whether the current vehicle meets the conditions for prohibiting detours.

[0068] S240. If the current vehicle does not meet the conditions for prohibiting detours, determine the stop line at the intersection ahead of the current vehicle's direction of travel based on the map of the area.

[0069] If the current vehicle does not meet any of the conditions prohibiting detours, it means that the current vehicle can make a detour decision. At this time, based on the local map and the current location of the vehicle (e.g., through navigation and maps), the nearest intersection ahead of the current vehicle is first determined, and the location of the stop line at that intersection is determined.

[0070] S250. Based on the stop line at the intersection, determine whether the downstream permissible direction of traffic for adjacent lanes includes straight-ahead traffic.

[0071] The adjacent lanes can be the lanes immediately to the left or right of the reference operating lane. The downstream permitted direction of travel can be the permitted direction of travel for the adjacent lane after passing through the intersection. It's understandable that different lanes at an intersection may have different permitted directions of travel; some may only allow straight ahead, some may allow right turns and straight ahead, some may allow left turns and straight ahead, and some may only allow left turns, etc. When the downstream permitted direction of an adjacent lane includes straight ahead, the current vehicle can use the adjacent lane to go straight past the sequence of obstacles ahead, thereby returning to the reference operating lane and achieving the detour. Therefore, determining the permitted direction of travel for the adjacent lane after the intersection is quite important.

[0072] S260. If the downstream permissible direction of traffic in an adjacent lane includes straight-ahead travel, then the detour direction shall be determined based on the sequence of obstacles in the adjacent lane.

[0073] If the downstream permissible direction of travel in an adjacent lane includes a "straight" direction, then the decision to detour via the left or right lane is made based on the adjacent lane obstacle sequence. It's important to note that the adjacent lane obstacle sequence can be any sequence of obstacles within adjacent lanes. Both the left and right adjacent lanes may contain adjacent lane obstacle sequences. Furthermore, the adjacent lane obstacle sequence differs from the obstacle sequence in the reference operating lane, which only contains the forward obstacle sequence (i.e., the obstacle sequence directly in front of the current vehicle). Adjacent lanes, however, may contain obstacle sequences located in front of or behind the current vehicle. It's understandable that other vehicles in adjacent lanes may have speeds slower than the current vehicle (vehicles in front of the current vehicle) or faster than the current vehicle (vehicles behind the current vehicle).

[0074] It's easy to imagine that if a vehicle in the adjacent lane corresponding to the detour direction is traveling slower than the current vehicle, or if a vehicle behind is traveling faster than the current vehicle, a collision and traffic accident are inevitable. Therefore, judging the state of these adjacent lane obstacle sequences helps vehicles determine their detour direction. This further ensures the safety of lane changes and detours before the detour begins.

[0075] In one optional implementation, the adjacent lane obstacle sequence includes an adjacent lane forward obstacle sequence and an adjacent lane rear obstacle sequence; determining the detour direction based on the adjacent lane obstacle sequence may include: calculating the simulated collision time between the adjacent lane forward obstacle sequence and adjacent lane rear obstacle sequence corresponding to the left and right adjacent lanes and the current vehicle, respectively; determining the combined collision time of the left adjacent lane and the combined collision time of the right adjacent lane based on each simulated collision time and a preset collision time weight; and taking the direction of the adjacent lane corresponding to the larger combined collision time as the detour direction.

[0076] For adjacent lanes on both the left and right, obstacle sequences may occur in both the forward and backward directions, i.e., obstacle sequences ahead and behind in the adjacent lane. The simulated collision time is the estimated duration of a potential collision with either the preceding or following obstacle sequence when the vehicle is changing lanes on the left or right. Preset collision time weights differentiate the importance of the preceding and following obstacle sequences within the same adjacent lane compared to the simulated collision time of the current vehicle. Furthermore, the calculation of the simulated collision time considers the speed of the current vehicle, the speed of the obstacle sequence, the rate of change of the current vehicle's acceleration, and the current vehicle's maximum acceleration; the calculation method for the simulated collision time follows Newton's laws of motion. Of course, these collision time weights can be set by technical personnel based on extensive experimental results. The comprehensive collision time is the combined time within a single adjacent lane when the current vehicle is changing lanes and may collide with obstacles ahead or behind.

[0077] Then, calculate the simulated collision time when the current vehicle changes lanes around an obstacle sequence in the adjacent lane ahead, and the simulated collision time when the current vehicle changes lanes around an obstacle sequence in the adjacent lane behind. Then, taking the left adjacent lane as an example, calculate the overall collision time based on the simulated collision times of the current vehicle with the obstacle sequence ahead, the simulated collision time of the current vehicle with the obstacle sequence behind, and the collision time weights. It is important to note that within the same adjacent lane, the sum of the collision time weights for simulated collisions with obstacles in the adjacent lane ahead and with obstacles in the adjacent lane behind is 1.

[0078] By comparing the combined collision times of the left and right adjacent lanes, the lane with the larger combined collision time is chosen as the current vehicle's detour direction. It's understood that a longer combined collision time means more time for the vehicle to detour, allowing sufficient time to adjust its direction and speed. This method, after assessing detour conditions, further determines the specific detour direction without requiring path planning. It uses readily available information such as the vehicle's current speed, distance to the obstacle sequence, relative distance to obstacles in adjacent lanes, obstacle speeds, the vehicle's rate of acceleration change, and maximum acceleration to perform a relatively simple calculation of the combined collision time. This saves the computational resources and time consumed by complex path planning algorithms, ensuring detour safety while improving the efficiency of detour decision-making.

[0079] In the technical solution of this application embodiment, by determining the downstream permitted traffic direction of the intersection, it is determined whether the current vehicle can take a detour strategy. If straight-going is permitted, it can help the vehicle to detour. This can further ensure that the vehicle will not violate traffic regulations or other problems during the lane change and detour, and further improve the rationality and safety of the detour movement.

[0080] Example 3

[0081] This application embodiment is a preferred embodiment provided based on the foregoing implementation methods. This embodiment can be applied to autonomous driving scenarios, where the vehicle judges obstacles ahead and overtakes or detours them. This embodiment utilizes a high-precision map to assist the vehicle in determining detour routes. The information in the high-precision map includes, but is not limited to, lane center lines, lane boundaries, lane boundary types (such as solid lines, dashed lines, double solid lines, etc.), lane turning types (such as straight, left turn, right turn, etc.), and intersection information (including stop line location information, etc.). This preferred embodiment is detailed below:

[0082] First, based on the current vehicle position and information about obstacles ahead, determine whether there is a sequence of obstacles that the vehicle needs to bypass. This sequence can include at least one obstacle, such as another vehicle traveling in front of the current vehicle. The method for filtering the obstacle sequence is as follows:

[0083] The algorithm iterates through all obstacles, determines the lane width of the current vehicle's reference trajectory based on a high-precision map, and filters out stationary obstacles located in the lane ahead of the current vehicle. All obstacles meeting this condition are stored in an array. The obstacles in the filtered array are sorted in ascending order of their distance from the current vehicle, resulting in an ordered obstacle array. The algorithm iterates through this ordered obstacle array, comparing the distances between adjacent obstacles. If the distance exceeds a certain threshold, the obstacle behind that obstacle is removed from the obstacle array, resulting in the final obstacle sequence.

[0084] Secondly, combining the acquired obstacle sequence and high-precision map information, we confirm whether the obstacles can be bypassed. The logic for determining whether an obstacle has basic bypass conditions is as follows:

[0085] (1) Whether the current vehicle speed is within a certain threshold range. If it exceeds the threshold, detour is not allowed.

[0086] (2) Whether the obstacle closest to the current vehicle in the obstacle sequence is stably present, that is, whether the obstacle is stably present for more than a certain number of detection cycles. If not, detouring is not allowed. Since there is a detection cycle when the current vehicle detects the obstacle sequence, if the obstacle sequence is detected in multiple consecutive detection cycles, it means that the obstacle sequence is stably present in front of the current vehicle, and detouring is allowed; if the obstacle sequence is not stably present in front of the current vehicle, detouring is not allowed.

[0087] (3) Whether the sequence of obstacles is close to the intersection. If it is within a certain range of the intersection, detour is not allowed.

[0088] (4) Whether the obstacle sequence is close to the destination endpoint. If it is within a certain distance from the destination endpoint, detouring is not allowed.

[0089] (5) Whether the obstacle sequence is within the solid line lane. If the obstacle sequence is within the solid line lane, detour is not allowed.

[0090] Specifically, the method for determining the distance to the intersection in (3) is as follows:

[0091] By combining the current vehicle position and high-precision map information, the position of the nearest intersection stop line in front of the current vehicle is obtained, thus determining the distance between the front position of the last obstacle in the obstacle sequence and the position of the intersection stop line ahead.

[0092] In particular, there are some special cases in condition (3). For some special intersections, such as the exit of a community or park, the stop line of such intersections is generally not set as a solid line. In this case, combined with the high-precision map, starting from the end of the obstacle queue to the stop line of the intersection, lane boundary detection is performed every interval (e.g., 2m). If there is no solid line in the entire distance range, it means that the basic detour conditions are met. However, in order to ensure safety, the number of stable existence period judgment thresholds in condition (2) needs to be increased accordingly.

[0093] Furthermore, the method for determining condition (5) is as follows:

[0094] Iterates through each obstacle from the end of the obstacle queue to the beginning, and uses a high-precision map to check whether the lane boundary type at the center of each obstacle is a solid line. If the lane boundary on both sides of an obstacle is a solid line, detouring is not allowed.

[0095] Finally, when the obstacle sequence can be bypassed, the detour direction is determined. For considerations of detour safety, smoothness, and rationality (i.e., ensuring a smooth return to the current vehicle lane after detour), the current vehicle's detour direction is determined primarily based on the following two conditions:

[0096] ① Determine the detour direction by combining high-precision map information;

[0097] ② Determine the detour direction by combining information on obstacles in the adjacent lanes on the left and right.

[0098] For point ①, starting from the current vehicle position, a certain distance D, such as 100m, is searched forward along the vehicle's direction of travel. If an intersection exists within distance D, the stop line position of the first intersection is detected. Lane information of the left and right adjacent lanes at the 100m mark is obtained (if an intersection exists, the left and right adjacent lane information at the intersection stop line position is obtained). It is then determined whether the downstream adjacent lane of that adjacent lane includes a straight-ahead turn. Considering that using the right-turn lane might prevent the current vehicle from smoothly returning to its original lane after detouring, detouring on the side without a straight-ahead turn attribute is not recommended. For example... Figure 3A As shown, if neither of the adjacent lanes on either side contains straight-ahead lanes, then a detour decision is not recommended; Figure 3B and Figure 3C As shown, select the adjacent lane on the side that includes straight-ahead traffic to detour; if both sides include straight-ahead traffic, then proceed to step ②.

[0099] For point ②, obstacles located in the left and right adjacent lanes, behind the current vehicle and traveling faster than the current vehicle, are selected. These obstacles are then sorted in descending order of their longitudinal distance from the current vehicle. The time-to-collision (TTC) time between the obstacle at the end of the queue (the obstacle closest to the current vehicle) and the current vehicle is calculated.lr and TTC rr Among them, TTC lr To filter out the collision time between the nearest obstacle in the left adjacent lane and the current vehicle, TTC rr The collision time between the current vehicle and the nearest obstacle in the adjacent lane on the right.

[0100] Obstacles located in the left and right adjacent lanes, positioned in front of the current vehicle and traveling slower than it, are selected separately. These obstacles are then sorted into two groups based on their longitudinal distance from the current vehicle, from smallest to largest. The time-to-collision (TTC) time between the head of the queue (the obstacle closest to the current vehicle) and the current vehicle is calculated. lf and TTC rf Among them, TTC lf To filter out the collision time between the nearest obstacle in the left adjacent lane and the current vehicle, TTC rf The collision time between the current vehicle and the nearest obstacle in the adjacent lane to the right;

[0101] Calculate the weighted lane change combined collision time (TTC) total Ultimately, the direction with the larger weighted lane change collision time was selected. Specifically, the weighted lane change collision time on the left was calculated as follows:

[0102] TTC total_l =λTTC lr +(1-λ)TTC lf ;

[0103] The weighted average collision time for right-side lane changes is:

[0104] TTC total_r =λTTC rr +(1-λ)TTC rf ;

[0105] Where λ is the scaling factor for (0,1).

[0106] In addition, TTC lr and TTC rr The calculation comprehensively considers information such as the current vehicle speed, the distance between the current vehicle and the obstacle to be bypassed, the relative distance to obstacles in adjacent lanes, the obstacle speed, the rate of change of the current vehicle's acceleration, and the current vehicle's maximum acceleration. lf and TTC rfThe calculation comprehensively considers information such as the current vehicle speed, the distance between the current vehicle and the obstacle to be bypassed, the relative distance between the current vehicle and obstacles in adjacent lanes, the obstacle speed, the rate of change of the current vehicle's acceleration, and the current vehicle's maximum acceleration. The determination of each speed can be based on the aforementioned readily available conditions, and can be simulated and calculated according to existing physical laws.

[0107] Example 4

[0108] Figure 4 This is a structural schematic diagram of a vehicle bypass device provided in Embodiment 4 of this application. Figure 4 As shown, the device 400 includes:

[0109] The information acquisition module 410 is used to acquire the reference trajectory of the current vehicle, the map of the area, and obstacle information within a preset range of the area obtained by the current vehicle's perception system.

[0110] The sequence determination module 420 is used to determine the sequence of obstacles in the area based on the reference trajectory and obstacle information;

[0111] The detour judgment module 430 is used to determine whether the current vehicle meets the conditions for prohibiting detour based on the reference trajectory, the map of the area, and the sequence of obstacles;

[0112] The direction determination module 440 is used to determine the detour direction of the current vehicle based on the map of the area and the sequence of obstacles if the current vehicle does not meet the conditions for prohibiting detours, and then detour in the detour direction.

[0113] The technical solution of this application embodiment not only determines the detour decision based on the judgment of the detour prohibition conditions according to the reference trajectory, the local area map and obstacle information, but also determines the detour direction based on the obstacle information, thereby improving the rationality of the detour decision and reducing the trajectory planning time of the detour movement. While ensuring the safety of vehicle detour, it can further improve the efficiency of detour planning.

[0114] In one alternative implementation, the sequence determination module 420 may include:

[0115] The reference lane determination unit is used to determine the reference lane of the current vehicle based on the reference trajectory.

[0116] The forward sequence determination unit is used to sort the distances between each obstacle and the current vehicle in the driving direction from largest to smallest to obtain the forward obstacle sequence.

[0117] In one alternative embodiment, the device 400 may include:

[0118] The obstacle sequence allocation module is used to allocate the two obstacles to different obstacle sequences if the distance between two adjacent obstacles exceeds a preset length threshold.

[0119] In one alternative implementation, the detour prohibition condition includes at least one of the following conditions:

[0120] The current vehicle speed exceeds the preset speed threshold;

[0121] The duration of the forward obstacle sequence is less than a preset duration threshold;

[0122] The distance between the forward obstacle sequence and the nearest intersection ahead in the current vehicle's direction of travel is less than a first preset distance threshold;

[0123] The distance between the forward obstacle sequence and the current vehicle's destination is less than a second preset distance threshold;

[0124] The sequence of obstacles ahead is within the solid lane line.

[0125] In one alternative implementation, the obstacle sequence includes a sequence of adjacent lane obstacles in the adjacent lanes of the current vehicle's driving lane, and the direction determination module 440 may include:

[0126] The intersection line determination unit is used to determine the stop line at the intersection ahead of the current vehicle's direction of travel based on the map of the area.

[0127] The direction of travel determination unit is used to determine, based on the stop line at the intersection, whether the downstream permitted direction of travel for adjacent lanes includes straight-ahead travel;

[0128] The detour direction determination unit is used to determine the detour direction based on the obstacle sequence of the adjacent lane if the downstream permissible direction of travel of the adjacent lane includes straight travel.

[0129] In one optional embodiment, the adjacent lane obstacle sequence includes an adjacent lane forward obstacle sequence and an adjacent lane rear obstacle sequence; the detour direction determination unit may include:

[0130] The simulation time determination sub-unit is used to calculate the simulated collision time between the current vehicle and the sequence of obstacles in front of the adjacent lane and the sequence of obstacles behind the adjacent lane corresponding to the left and right adjacent lanes, respectively.

[0131] The integrated time determination subunit is used to determine the integrated collision time of the left adjacent lane and the integrated collision time of the right adjacent lane based on each simulated collision time and a preset collision time weight.

[0132] The detour direction determination subunit is used to determine the direction of the adjacent lane corresponding to the larger overall collision time as the detour direction.

[0133] The vehicle detour device provided in this application embodiment can execute the vehicle detour method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each vehicle detour method.

[0134] Example 5

[0135] Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0136] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle detour methods.

[0139] In addition, this application embodiment also provides a vehicle that can be used in an autonomous driving scenario, and the vehicle may be equipped with the above-mentioned electronic device 10.

[0140] In some embodiments, the vehicle detour method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle detour method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle detour method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0146] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0147] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0148] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for vehicle detour, characterized in that, The method includes: Acquire the current vehicle's reference trajectory, the map of the area it is in, and obstacle information within a preset range of the area obtained through the current vehicle's perception system; Based on the reference trajectory and the obstacle information, determine the sequence of obstacles in the area; Based on the reference trajectory, the map of the area, and the sequence of obstacles, determine whether the current vehicle meets the conditions for prohibiting detours; If the current vehicle does not meet the prohibited detour conditions, the detour direction of the current vehicle is determined according to the map of the area and the obstacle sequence, and the vehicle detours in the detour direction. The obstacle sequence includes the obstacle sequence of adjacent lanes of the current vehicle's driving lane. Determining the detour direction of the current vehicle based on the area map and the obstacle sequence includes: Based on the map of the area, determine the stop line at the intersection ahead of the current vehicle's direction of travel; Based on the stop line at the intersection, determine whether the downstream permissible direction of traffic for the adjacent lane includes straight-ahead travel; If the downstream permissible direction of travel in the adjacent lane includes straight travel, then the detour direction is determined based on the sequence of obstacles in the adjacent lane.

2. The method according to claim 1, characterized in that, The obstacle sequence includes a forward obstacle sequence along the current vehicle's direction of travel. Determining the obstacle sequence in the area based on the reference trajectory and the obstacle information includes: Based on the reference trajectory, determine the reference operating lane of the current vehicle; The forward obstacle sequence is obtained by sorting the distances between each obstacle and the current vehicle in the direction of travel from largest to smallest.

3. The method according to claim 2, characterized in that, The method includes: If the distance between two adjacent obstacles exceeds a preset length threshold, the two obstacles will be assigned to different obstacle sequences.

4. The method according to claim 2, characterized in that, The conditions for prohibiting detours include at least one of the following: The current vehicle speed exceeds a preset speed threshold; The duration of the forward obstacle sequence is less than a preset duration threshold. The distance between the forward obstacle sequence and the nearest intersection ahead of the current vehicle's direction of travel is less than a first preset distance threshold. The distance between the forward obstacle sequence and the destination of the current vehicle is less than a second preset distance threshold; The sequence of forward obstacles is located within the solid line lane.

5. The method according to claim 1, characterized in that, The adjacent lane obstacle sequence includes an adjacent lane forward obstacle sequence and an adjacent lane rear obstacle sequence; determining the detour direction based on the adjacent lane obstacle sequence includes: Calculate the simulated collision time between the current vehicle and the sequence of obstacles in front of and behind the adjacent lanes corresponding to the two adjacent lanes on the left and right, respectively. Based on the simulated collision times and preset collision time weights, the combined collision time of the left adjacent lane and the combined collision time of the right adjacent lane are determined. The direction of the adjacent lane corresponding to the larger overall collision time is taken as the detour direction.

6. A vehicle bypass device, characterized in that, include: The information acquisition module is used to acquire the current vehicle's reference trajectory, the map of the area, and obstacle information within a preset range of the area obtained through the current vehicle's perception system. The sequence determination module is used to determine the sequence of obstacles in the area based on the reference trajectory and the obstacle information. The detour determination module is used to determine whether the current vehicle meets the detour prohibition conditions based on the reference trajectory, the map of the area, and the obstacle sequence; The direction determination module is used to determine the detour direction of the current vehicle based on the map of the area and the obstacle sequence if the current vehicle does not meet the detour prohibition conditions, and to detour in the detour direction. The obstacle sequence includes the adjacent lane obstacle sequence of the current vehicle's driving lane, and the direction determination module includes: The intersection line determination unit is used to determine the intersection stop line ahead of the current vehicle's direction of travel based on the map of the area. The traffic direction determination unit is used to determine, based on the intersection stop line, whether the downstream permissible traffic direction of the adjacent lane includes straight-ahead travel; A detour direction determination unit is used to determine the detour direction based on the obstacle sequence of the adjacent lane if the downstream permissible traffic direction of the adjacent lane includes straight travel.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle detour method according to any one of claims 1-5.

8. A vehicle, characterized in that, The vehicle is equipped with the electronic equipment as described in claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the vehicle detour method of any one of claims 1-5.

Images