A vehicle lane changing control method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a vehicle lane changing control method, device, electronic equipment and storage medium, the method comprising: calculating an expected position region of a target lane of a self vehicle after performing lane changing according to environmental information and self vehicle state information; calculating an empty period of the expected position region according to state information of at least one other vehicle driving on the target lane; performing lane changing path planning for the self vehicle according to the self vehicle state information, the expected position region and the empty period; and if the lane changing path planning is successful, controlling the self vehicle to perform lane changing according to the planned lane changing path, so that the self vehicle drives into the expected position region in the empty period. Accordingly, the lane changing action of the self vehicle can be adapted to the traffic flow state of the target lane, avoiding low traffic efficiency caused by excessive conservative waiting, reducing the interference of lane changing on the original traffic flow of the target lane, and realizing the cooperative optimization of lane changing safety and traffic efficiency.

Description

TECHNICAL FIELD

[0001] One or more embodiments of the present disclosure relate to the field of autonomous driving, and in particular, to a vehicle lane changing control method and device, an electronic device, and a storage medium. BACKGROUND

[0002] In related technologies, when dealing with the lane changing task in the case of lane merging, the vehicle autonomous driving system usually adopts a passive waiting strategy based on a fixed distance threshold. Specifically, when the distance between the vehicle behind the target lane and the ego vehicle reaches or exceeds the preset fixed threshold, the system will trigger the lane changing operation; otherwise, if the distance is less than the threshold, the autonomous vehicle needs to stay in the original lane until the condition is met. This method is relatively simple to implement and easy to quickly deploy.

[0003] However, this strategy has obvious limitations. Since it only relies on the static distance between the two vehicles at the current time to make decisions, it fails to fully consider the dynamic characteristics of the ego vehicle and the vehicle behind, such as the time required for the ego vehicle to complete lane changing and the speed adjustment that the vehicle behind may make, which makes the ego vehicle at risk of collision with the vehicle behind during the actual lane changing process, and even reduces the efficiency and smoothness of the overall traffic flow due to the overly conservative waiting strategy. SUMMARY

[0004] Therefore, the present disclosure provides a vehicle lane changing control method, which comprises:

[0005] According to the environmental information and the ego vehicle state information, the expected position region of the ego vehicle after executing lane changing is calculated;

[0006] According to the state information of at least one other vehicle driving on the target lane, the vacant period of the expected position region is calculated;

[0007] According to the ego vehicle state information, the expected position region, and the vacant period, the ego vehicle is subjected to lane changing path planning;

[0008] If the lane changing path planning is successful, the ego vehicle is controlled to execute lane changing according to the planned lane changing path, so that the ego vehicle enters the expected position region during the vacant period.

[0009] Optionally, the vacant period is a preset number, and the lane changing path planning of the ego vehicle according to the ego vehicle state information, the expected position region, and the vacant period comprises:

[0010] According to the ego vehicle state information, the expected position region, and the first vacant period in the plurality of vacant periods, the ego vehicle is subjected to lane changing path planning;

[0011] After the lane-changing path planning for the ego vehicle, the method further comprises:

[0012] If the lane-changing path planning fails, the ego vehicle is planned according to the ego vehicle state information, the expected position region, and a next-order vacant time period determined in sequence among a plurality of vacant time periods.

[0013] The above steps are repeatedly executed until the lane-changing path planning succeeds.

[0014] Optionally, the calculation of the vacant time period of the expected position region according to the state information of at least one other vehicle driving on the target lane comprises:

[0015] According to the state information of at least one other vehicle driving on the target lane, the head position and the tail position of the other vehicle in the current time and the future time period are determined.

[0016] According to the head position and the tail position of the other vehicle in the current time, it is determined whether the expected position region is vacant.

[0017] If the expected position region is vacant, the current time is collected as the start time of the vacant time period.

[0018] According to the head position of the other vehicle in the future time period, the time when the head position of the other vehicle reaches the lower boundary of the expected position region is determined as the end time of the vacant time period.

[0019] Optionally, the method further comprises:

[0020] If the expected position region is not vacant, a plurality of groups of adjacent vehicles are determined according to the state information of the other vehicle.

[0021] The time when the tail of the previous vehicle of the adjacent vehicle reaches the upper boundary of the expected position region and the head of the next vehicle of the adjacent vehicle does not reach the lower boundary of the expected position region is taken as the start time of the vacant time period.

[0022] The time when the head of the next vehicle of the adjacent vehicle reaches the lower boundary of the expected position region and the tail of the previous vehicle of the adjacent vehicle has reached or exceeded the upper boundary of the expected position region is taken as the end time of the vacant time period.

[0023] Optionally, the method further comprises:

[0024] If the expected position region is not vacant, the inter-vehicle distance between the other vehicles in the current time is determined according to the head position and the tail position of the other vehicle in the current time.

[0025] if there is a vehicle group in the other vehicles, the inter-vehicle distance between the vehicles included in the vehicle group is less than the length of the expected position region in the target lane direction, the vehicle group is processed as a whole vehicle;

[0026] determining a plurality of groups of adjacent vehicles in the other vehicles, comprising:

[0027] determining a plurality of groups of adjacent vehicles in the processed other vehicles.

[0028] Optionally, the environment information includes the center line position of the target lane and driving scene information, and the ego vehicle state information includes the length and width of the ego vehicle, the position point of the ego vehicle and the speed of the ego vehicle; and the calculation of the expected position region of the ego vehicle in the target lane after performing the lane change according to the environment information and the ego vehicle state information comprises:

[0029] determining a corresponding position point in the center line position that is in the same driving position as the position point of the ego vehicle;

[0030] predicting the time length required for the ego vehicle to complete the lane change to the target lane according to the driving scene information;

[0031] calculating a center point of the expected position region according to the corresponding position point, the speed and the predicted time length;

[0032] determining the expected position region of the ego vehicle in the target lane after performing the lane change according to the length and width of the ego vehicle and the center point.

[0033] Optionally, the planned lane change path includes a plurality of trajectory points, each trajectory point including the position and direction of the ego vehicle at a certain time in the current time and the future time period, and after the lane change path planning for the ego vehicle, the method further comprises:

[0034] obtaining other vehicle state information of the target lane to calculate the position of the other vehicles at the same time according to the time of the plurality of trajectory points;

[0035] if the distance between the position of any trajectory point in the plurality of trajectory points and the position of the other vehicles is less than a preset safety distance threshold, or the direction of the last trajectory point included in the planned lane change path is inconsistent with the driving direction of the target lane, it is determined that the lane change path planning fails;

[0036] otherwise, it is determined that the lane change path planning succeeds.

[0037] The present disclosure also provides a vehicle lane change control device, the device comprising:

[0038] The first calculation unit is configured to calculate an expected position region of the ego vehicle in the target lane after the ego vehicle performs the lane change according to the environment information and the ego vehicle state information;

[0039] The second calculation unit is configured to calculate an empty period of the expected position region according to state information of at least one other vehicle traveling on the target lane;

[0040] The planning unit is configured to perform lane change path planning for the ego vehicle according to the ego vehicle state information, the expected position region, and the empty period.

[0041] The control unit is configured to control the ego vehicle to perform the lane change according to the planned lane change path to make the ego vehicle enter the expected position region in the empty period if the lane change path planning is successful.

[0042] The present disclosure also provides an electronic device, which comprises a communication interface, a processor, a memory, and a bus, the communication interface, the processor, and the memory are connected to each other through the bus;

[0043] The memory stores machine readable instructions, and the processor executes the above method by invoking the machine readable instructions.

[0044] The present disclosure also provides a machine readable storage medium, which stores machine readable instructions, and the machine readable instructions realize the above method when invoked and executed by a processor.

[0045] Therefore, in the technical solution of the present disclosure, the expected position region of the ego vehicle in the target lane after the ego vehicle performs the lane change is calculated according to the environment information and the ego vehicle state information, and the empty period in which no other vehicle enters the expected position region is calculated based on the state information of other vehicles traveling on the target lane, thereby realizing dynamic forward-looking judgment of the lane change opportunity. Finally, the lane change path planning is performed in combination with the ego vehicle state information, the expected position region, and the empty period, so that the ego vehicle can enter the expected position region in the empty period, and the ego vehicle is controlled to perform the lane change after the lane change path planning is successful.

[0046] Through the above method, on the one hand, the empty period of the expected position region is calculated based on the state information of other vehicles traveling on the target lane, thereby avoiding conflicts in the middle of the lane change caused by single static distance judgment and improving the safety and accuracy of the lane change decision. On the other hand, the lane change path planning is performed according to the ego vehicle state information, the expected position region, and the empty period, so that the lane change action of the ego vehicle can adapt to the traffic flow state of the target lane, thereby avoiding low traffic efficiency caused by excessive conservative waiting, reducing the interference of the lane change on the original traffic flow of the target lane, and realizing the cooperative optimization of the safety and traffic efficiency of the lane change. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0048] Figure 1 FIG. 1 is a schematic diagram of a lane merging scenario according to an example embodiment;

[0049] Figure 2 FIG. 2 is a flowchart of a vehicle lane change control method according to an example embodiment;

[0050] Figure 3 FIG. 3 is a schematic diagram of a vacant period calculation scenario according to an example embodiment;

[0051] Figure 4 FIG. 4 is a schematic diagram of another vacant period calculation scenario according to an example embodiment;

[0052] Figure 5 FIG. 5 is a schematic diagram of yet another vacant period calculation scenario according to an example embodiment;

[0053] Figure 6 FIG. 6 is a schematic diagram of a prospective position region determination method according to an example embodiment;

[0054] Figure 7 FIG. 7 is a flowchart of another vehicle lane change control method according to an example embodiment;

[0055] Figure 8 FIG. 8 is a hardware structure diagram of an electronic device according to an example embodiment;

[0056] Figure 9 FIG. 9 is a block diagram of a vehicle lane change control device according to an example embodiment. DETAILED DESCRIPTION

[0057] In order to make the technical solutions in the present disclosure better understood, the technical solutions in the present disclosure will be described clearly and completely in the following with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some embodiments of the present disclosure, but not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present disclosure.

[0058] It should be noted that the steps of the respective methods are not necessarily performed in the order shown and described in the present disclosure in other embodiments. In some other embodiments, the steps included in the methods thereof can be more or less than described in the present disclosure. In addition, a single step described in the present disclosure can be broken down into multiple steps for description in other embodiments; and multiple steps described in the present disclosure can be combined into a single step for description in other embodiments.

[0059] In the related art, the vehicle automatic driving system usually adopts a passive waiting strategy based on a fixed distance threshold when processing the lane change task in the lane merging situation. Specifically, the system will trigger the lane change operation only when the distance between the rear vehicle of the target lane and the ego vehicle reaches or exceeds the preset fixed threshold; otherwise, if the distance is less than the threshold, the autonomous vehicle needs to stay in the original lane until the condition is met. This method is relatively simple to implement and easy to quickly deploy and apply.

[0060] Please refer to Figure 1 , Figure 1 is a schematic diagram of a lane merging scenario shown by an exemplary embodiment. As Figure 1 shown, the current lane in which the ego vehicle travels is about to end, and the ego vehicle needs to change lanes to the right from the current lane to the target lane to avoid collision. In the related art, the vehicle automatic driving system usually adopts a passive waiting strategy based on a fixed distance threshold to process such a lane change task. The system will trigger the lane change operation only when the distance between the rear vehicle of the target lane and the ego vehicle reaches or exceeds the preset fixed threshold; otherwise, it stays in the original lane until the condition is met.

[0061] However, this strategy has obvious limitations. Since it only relies on the static distance between the two vehicles at the current time to make decisions, it fails to fully consider the dynamic characteristics of the ego vehicle and the rear vehicle, such as the time required for the ego vehicle to complete the lane change, the speed adjustment that the rear vehicle may make, etc., which makes the ego vehicle have a risk of collision with the rear vehicle during the actual lane change process, and even reduces the overall traffic flow efficiency and smoothness due to the overly conservative waiting strategy.

[0062] In view of this, the present disclosure aims to provide a technical solution that is adapted to the actual vehicle traffic situation and takes into account both the safety of lane changing and the efficiency of traffic.

[0063] The technical scheme firstly calculates an expected position region of the ego vehicle after executing lane changing according to the environmental information and the ego vehicle state information; then, calculates an empty period of the expected position region according to the state information of at least one other vehicle driving on the target lane; further, performs lane changing path planning on the ego vehicle according to the ego vehicle state information, the expected position region and the empty period; and finally, controls the ego vehicle to execute lane changing according to the planned lane changing path, so that the ego vehicle drives into the expected position region in the empty period.

[0064] For example, in a lane merging area of an expressway approaching an exit ramp, an autonomous vehicle needs to change lanes to the right into a target lane due to lane narrowing. At this time, an autonomous driving control unit (hereinafter referred to as: control unit) starts a lane changing decision-making process. First, the control unit obtains the lane line position, curvature and other environmental information of the current lane and the target lane through sensor data such as cameras, lidar, etc., as well as the ego vehicle state information, including the current vehicle speed of 80 km / h, the acceleration of -1 m / s², the vehicle body length of 4.8 meters, the lateral offset, etc., and calculates the expected position region that the ego vehicle should enter after completing the lane changing action, i.e., a rectangular space extending 80 meters forward from 60 meters in front of the ego vehicle on the target lane and covering the entire lane width laterally, based on the predefined time required for lane changing. This region ensures that the vehicle can smoothly drive in the center after lane changing is completed.

[0065] Subsequently, the control unit obtains the real-time motion state of other vehicles driving on the target lane, such as a vehicle driving at a speed of 73 km / h on the target lane 80 meters behind the ego vehicle, whose vehicle head is expected to enter the above-mentioned expected position region 3.2 seconds after the current time and completely pass through the region 6.0 seconds after the current time. Based on this motion trajectory, the control unit can determine that the expected position region will be in an empty state without vehicle occupation 6.0 seconds after the current time, until the next vehicle (further away) enters the lower boundary of the expected position region 10.5 seconds, thus determining an empty period from 6.0 seconds to 10.5 seconds.

[0066] On this basis, the control unit performs lane changing path planning in combination with the ego vehicle state information, the spatial boundary of the expected position region and the time window of the empty period from 6.0 to 10.5 seconds. The control unit generates a lane changing trajectory starting at 6.2 seconds and completing at 7.8 seconds using a planning algorithm.

[0067] Finally, when the planned lane-changing path passes the safety and feasibility verification, the control unit issues steering, throttle and brake instructions to the vehicle execution layer, drives the ego vehicle to execute the planned lane-changing path, so that the ego vehicle smoothly cuts into the target lane at 7.8 seconds, and the whole vehicle completely enters the expected position area, and the heading angle is aligned with the lane line, so that the ego vehicle completes the lane-changing process smoothly and accurately.

[0068] It can be seen that, in the technical solution of the present disclosure, the expected position area of the ego vehicle in the target lane after lane-changing is calculated according to the environmental information and the ego vehicle state information, and the empty period in which no other vehicle enters the expected position area is calculated based on the state information of other vehicles on the target lane, so as to realize dynamic forward-looking judgment of the lane-changing opportunity. Finally, the ego vehicle state information, the expected position area and the empty period are combined to plan a lane-changing path, so that the ego vehicle can enter the expected position area during the empty period, and the ego vehicle is controlled to execute lane-changing after the lane-changing path is successfully planned.

[0069] Through the above method, the technical solution of the present disclosure calculates the empty period of the expected position area through the state information of other vehicles on the target lane, avoids conflicts during lane-changing caused by single static distance judgment, and improves the safety and accuracy of lane-changing decision. On the other hand, the ego vehicle state information, the expected position area and the empty period are used to plan a lane-changing path, so that the ego vehicle lane-changing action can adapt to the traffic flow state of the target lane, which not only avoids the low traffic efficiency caused by excessive conservative waiting, but also reduces the interference of lane-changing on the original traffic flow of the target lane, and realizes the cooperative optimization of lane-changing safety and traffic efficiency.

[0070] The present disclosure will be described below through specific embodiments in combination with specific application scenarios.

[0071] Please refer to Figure 2 , Figure 2 is a flowchart of a vehicle lane-changing control method according to an exemplary embodiment. The method can perform the following steps:

[0072] Step 202: Calculate the expected position area of the ego vehicle in the target lane after lane-changing according to the environmental information and the ego vehicle state information.

[0073] For example, in the lane merging area of an expressway approaching an exit ramp, an autonomous vehicle needs to change lanes to the right into the target lane due to lane narrowing. At this time, the autonomous driving control unit (hereinafter referred to as: control unit) starts the lane change decision-making process. First, the control unit obtains the lane line position, curvature, etc. of the current lane and the target lane, as well as the vehicle state information, including the current speed of 80 km / h, the acceleration of -1 m / s2, the vehicle body length of 4.8 meters, the lateral offset, etc., through sensor data such as cameras, lidar, etc., combined with the predefined time required for lane change, to calculate the expected position area that the vehicle should enter after completing the lane change action, i.e. a rectangular space on the target lane extending 80 meters forward from 60 meters in front of the vehicle, covering the entire lane width laterally, which ensures that the vehicle can drive smoothly in the center after completing the lane change.

[0074] Among them, the environmental information refers to the external road environment data perceived by the autonomous vehicle through the vehicle-mounted sensor system, mainly including lane line geometry, lane width, road curvature, lane center line, etc. The vehicle state information refers to the kinematics and dynamics parameters of the vehicle itself, including real-time speed, acceleration, heading angle, vehicle size and current position, etc., which are generally obtained through an inertial navigation system. The expected position area is calculated based on the above information and combined with the lane change behavior model, and its length is usually determined by the current speed of the vehicle and the time required for lane change (e.g. 2-4 seconds), and the lateral direction covers the width of the target lane to ensure that the vehicle completely enters the target lane and drives in the center after completing the lane change, avoiding crossing the line or deviating.

[0075] Step 204: Calculate the empty period of the expected position area according to the state information of at least one other vehicle driving on the target lane.

[0076] For example, the control unit obtains the real-time motion state of the other vehicle driving on the target lane, such as a vehicle on the target lane 80 meters behind the vehicle driving at a constant speed of 73 km / h, whose vehicle head is expected to enter the above-mentioned expected position area in the 3.2 seconds after the current time, and completely pass through the area in the 6.0 seconds after the current time. Based on this motion trajectory, the control unit can determine that the expected position area will be in an empty state without vehicle occupation from the 6.0 seconds after the current time to the 10.5 seconds when the next vehicle (further away) enters the lower boundary of the expected position area, so an empty period from the 6.0 seconds to the 10.5 seconds is determined.

[0077] The state information of other vehicles refers to the motion state data of other vehicles on the target lane, including position, speed, acceleration, heading angle, vehicle length, etc., which is usually detected and tracked by vehicle-mounted sensors such as radar and camera, and combined with multi-target filtering algorithm to realize trajectory prediction. The open period refers to a time period in which the expected position region is not occupied by any other vehicle in the time dimension, i.e. from the moment when the previous vehicle completely leaves the region to the moment when the next vehicle is about to enter the region. The calculation of this period depends on the accurate deduction of the future motion trajectory of the vehicle on the target lane.

[0078] Step 206: According to the self-vehicle state information, the expected position region and the open period, the self-vehicle is path planned for lane change.

[0079] For example, the control unit combines the self-vehicle state information (including current speed, acceleration, heading angle, position coordinates, etc.), the spatial boundary of the expected position region, and the time window of the open period of 6.0 to 10.5 seconds to perform path planning for lane change. The control unit generates a lane change trajectory that starts at 6.2 seconds and completes at 7.8 seconds.

[0080] The path planning for lane change refers to a process of generating a motion trajectory that meets safety and dynamic feasibility for an autonomous vehicle given the initial state, target spatial region and time constraints. The trajectory includes longitudinal (along the lane direction) speed and acceleration planning, as well as lateral (across the lane direction) displacement, speed, acceleration and heading angle change curve, ensuring that the vehicle smoothly and accurately completes lane switching within the specified time. The self-vehicle state information serves as the initial condition for path planning, ensuring that the planning starting point is consistent with the actual state of the self-vehicle; the expected position region defines the spatial constraint of the path endpoint, i.e. after lane change is completed, the vehicle as a whole should fall completely within the region and maintain central driving; the open period provides a time window constraint, requiring the end time of the lane change action to fall within this period to avoid conflicts with other vehicles on the target lane. In terms of technical means, path planning can be implemented using optimization-based or sampling-based algorithms, which are not limited by the present disclosure.

[0081] Step 208: If the path planning for lane change is successful, the self-vehicle is controlled to perform lane change according to the planned lane change path, so that the self-vehicle enters the expected position region during the open period.

[0082] For example, when the planned lane change path passes the safety and feasibility verification, the control unit issues steering, throttle and brake instructions to the vehicle execution layer to drive the self-vehicle to execute the planned lane change path, so that the self-vehicle smoothly cuts into the target lane at 7.8 seconds, the whole vehicle completely enters the expected position region, and the heading angle is aligned with the lane line, thereby smoothly and accurately completing the self-vehicle lane change process.

[0083] wherein, the success of the lane-changing path planning refers to that the generated lane-changing trajectory satisfies multiple constraint conditions such as safety, reachability and driving compliance in the time-space dimension. Specifically, the planned lane-changing path is composed of a series of trajectory points distributed in time sequence, each trajectory point contains the expected position (such as x, y coordinates in the Cartesian coordinate system) and the driving direction (i.e. the heading angle) of the ego vehicle at a future time. After the path is generated, the control unit needs to further verify whether it satisfies the above constraint conditions. Only when all trajectory points satisfy the above constraint conditions, it is determined that the path planning is successful. In terms of technical means, this verification process is usually realized through time-space alignment and collision envelope detection, which is not limited in the present disclosure.

[0084] In an embodiment shown, the number of the empty time periods is preset, and the lane-changing path planning for the ego vehicle according to the ego vehicle state information, the expected position region and the empty time periods comprises: performing the lane-changing path planning for the ego vehicle according to the ego vehicle state information, the expected position region and the empty time period located at the first order among the plurality of empty time periods; after the lane-changing path planning for the ego vehicle, the method further comprises: if the lane-changing path planning fails, performing the lane-changing path planning for the ego vehicle according to the ego vehicle state information, the expected position region and the empty time period located at the next order determined in sequence among the plurality of empty time periods; repeating the above steps until the lane-changing path planning is successful.

[0085] For example, in the lane merging area of the highway approaching the exit ramp, the autonomous vehicle needs to change lanes to the right into the target lane due to the narrowing of the lane. After analyzing the traffic of the target lane, the control unit identifies that there are three empty time periods available for lane changing in the future: empty time period A (6.0-8.5 seconds), empty time period B (10.2-13.0 seconds), and empty time period C (15.8-18.4 seconds). The control unit first performs lane-changing path planning based on the current state information of the ego vehicle (speed 80 km / h, acceleration -0.3 m / s²), the expected position region (a rectangular space 60-140 meters ahead of the target lane), and the earliest appearing empty time period A. The planning algorithm generates a lateral cut trajectory starting at 6.2 seconds and completing at 7.8 seconds, and performs safety verification. However, since the ego vehicle is not heading in the same direction as the target lane at the end of the trajectory, the control unit determines that the current path planning fails. At this time, the control unit automatically switches to the next available empty time period B and re-plans the lane-changing path based on the updated ego vehicle state information. After verification, the path satisfies the safety verification, confirming the success of the planning, and the control unit controls the vehicle to perform lane-changing according to the planned path.

[0086] The empty time period can be sorted in chronological order, and the earliest appearing time period is selected as the priority to improve the efficiency of lane changing and avoid missing the lane merging opportunity due to excessive waiting. The path planning failure determination conditions include, but are not limited to, the deviation of the vehicle heading angle from the target lane direction exceeding a threshold at the end of the trajectory, the distance between the vehicle and other vehicles in the lane changing process being less than a safety threshold, and the lateral acceleration exceeding a vehicle comfort threshold. When switching to the next empty time period, the control unit can obtain the state information of the vehicle and other vehicles in the target lane collected by the sensor, to ensure that the path planning matches the current traffic environment. To save computing resources, only the motion state of the other vehicles behind the vehicle in the target lane can be calculated.

[0087] In one embodiment shown, the calculation of the empty time period of the expected position region according to the state information of at least one other vehicle driving on the target lane includes: determining the head position and tail position of the other vehicle within the current time and future period according to the state information of at least one other vehicle driving on the target lane; determining whether the expected position region is empty according to the head position and tail position of the other vehicle at the current time; if the expected position region is empty, collecting the current time as the start time of the empty time period; determining the time when the head position of the other vehicle reaches the lower boundary of the expected position region according to the head position of the other vehicle within the future period, and taking it as the end time of the empty time period.

[0088] For example, please refer to Figure 3 , Figure 3 is an example of an embodiment showing a schematic diagram of an empty time period calculation. As Figure 3As shown, the ego vehicle plans to change lanes from the current lane to the right target lane, and first performs a lane change preparation, such as deceleration, adjustment of the heading angle, etc. There are other vehicles driving on the target lane, which are marked as vehicle 1, vehicle 2 and vehicle 3. First, the control unit obtains the state information of the other vehicles on the target lane collected by the perception module (laser radar, millimeter wave radar and camera fusion perception system), including position, speed, acceleration and vehicle size, etc. According to this information, the control unit calculates the head and tail positions of each vehicle at the current time and in the future period. For example, the head position of vehicle 1 is 147 meters in front of the ego vehicle, and the tail position is 142 meters in front of the ego vehicle at the current time. The head position of vehicle 2 is 40 meters in front of the ego vehicle, and the tail position is 35 meters in front of the ego vehicle at the current time. Accordingly, the control unit can determine that the current expected position area (a rectangular space of 60-140 meters in front of the target lane) is empty, and then take the current time as the start time of the empty period. Next, according to the head and tail positions of each vehicle in the future period, it is determined that the head position of vehicle 2 will reach the lower boundary of the expected position area 3 seconds after the current time, and the time point 3 seconds after the current time is the end time of the empty period.

[0089] In the above embodiment, the perception module defines the expected position area as a rectangular area composed of discrete coordinate points, and clearly defines the upper boundary, lower boundary longitudinal coordinate (longitudinal direction is the driving direction of the target lane) and left boundary, right boundary lateral coordinate of the area, forming a closed space boundary range. The perception module tracks dynamic targets within a certain range of the target lane in real time through multiple sensors, collects real-time state information (such as position, speed, etc.) of each vehicle, and then compares the longitudinal coordinates of the dynamic targets with the upper boundary and lower boundary longitudinal coordinates of the expected position area to determine whether the target is in the expected position area. The perception module can set a dynamic flag for each dynamic target, which is 1 if it is in the expected position area and 0 if it is not in the expected position area. If all target flags within the field of view obtained by the perception module through multiple sensors are 0, it indicates that the expected position area is empty.

[0090] In some embodiments, the process of the ego vehicle preparing for lane change includes combined operations such as deceleration, flashing of turn signal, small adjustment of heading angle, honking, etc. On the one hand, it prepares safety conditions for its own lane change, and on the other hand, it transmits the lane change intention to the vehicles behind the target lane, so that the vehicles behind the target lane accelerate or decelerate to drive, thereby providing favorable conditions for the expected position area to be emptied as soon as possible. During the deceleration process of the ego vehicle preparing for lane change, the ego vehicle control unit can obtain the remaining length of the current lane collected by the perception module. If the remaining length of the current lane is greater than or equal to the reference buffer distance of the current lane, it indicates that the remaining length of the current lane is relatively sufficient, and the ego vehicle can decelerate at an acceleration If the remaining length of the current lane is less than the reference buffer distance of the current lane, it indicates that the remaining length of the current lane is not sufficient, and the ego vehicle needs to decelerate at an acceleration decelerate, wherein As , .

[0091] In the illustrated embodiment, the method further comprises: if the expected position region is not empty, determining a number of adjacent vehicles according to the state information of the other vehicles; taking the time when the tail of the preceding vehicle of the adjacent vehicles reaches the upper boundary of the expected position region and the head of the following vehicle of the adjacent vehicles does not reach the lower boundary of the expected position region as the starting time of the empty period; and taking the time when the head of the following vehicle of the adjacent vehicles reaches the lower boundary of the expected position region and the tail of the preceding vehicle of the adjacent vehicles has reached or exceeded the upper boundary of the expected position region as the ending time of the empty period.

[0092] For example, please refer to Figure 4 , Figure 4 is another schematic diagram of the calculation of the empty period according to an exemplary embodiment. As Figure 4 shown, the perception module (laser radar, millimeter wave radar and camera fusion perception system) of the ego vehicle collects the motion state data of the No. 1 vehicle, the No. 2 vehicle and the No. 3 vehicle in the target lane, and the control unit calculates the head and tail positions of each vehicle at the current time and in the future period according to the data, and determines that the current expected position region (the rectangular space of 60-140 meters in front of the target lane) is not empty. Next, the control unit determines that the tail position of the No. 2 vehicle will reach the upper boundary of the expected position region after 3 seconds from the current time, and the head position of the No. 3 vehicle does not reach the lower boundary of the expected position region at this time, so the time point 3 seconds after the current time is taken as the starting time of the empty period. The control unit determines that the head position of the No. 3 vehicle will reach the lower boundary of the expected position region after 5 seconds from the current time, and the tail position of the No. 2 vehicle has reached or exceeded the upper boundary of the expected position region at this time, so the time point 5 seconds after the current time is taken as the ending time of the empty period.

[0093] In which, for the detection of the vehicle leaving the upper boundary of the expected position region or the vehicle entering the lower boundary of the expected position region: the perception module of the control unit can extract the longitudinal position coordinates of the head and tail of the vehicle (based on the ego vehicle coordinate system) through the target contour recognition algorithm, and determine the longitudinal coordinate threshold of the expected position region based on the boundary parameters of the expected position region. Then, the control unit compares the two, and when it is detected that the longitudinal position coordinate of the tail of the vehicle is about to exceed the upper boundary coordinate threshold of the expected position region, or it is detected that the longitudinal position coordinate of the head of the vehicle touches the lower boundary coordinate threshold of the expected position region, the time stamps of the two time points are recorded.

[0094] In the illustrated embodiment, the method further comprises: if the expected position region is not empty, determining the inter-vehicle distance between the other vehicles at the current time according to the head position and tail position of the other vehicles at the current time; if there is a vehicle group in the other vehicles, the inter-vehicle distance between the vehicles included in the vehicle group is less than the length of the expected position region in the target lane direction, the vehicle group is processed as a whole vehicle; and determining a plurality of groups of adjacent vehicles in the other vehicles, including: determining a plurality of groups of adjacent vehicles in the processed other vehicles.

[0095] For example, please refer to Figure 5 , Figure 5 is a schematic diagram of another case of calculating the empty period shown in an exemplary embodiment. As Figure 5 shown, the perception module of the ego vehicle collects the motion state information of adjacent vehicles (such as vehicle No. 1 and vehicle No. 2, vehicle No. 2 and vehicle No. 3) in the target lane, performs data fusion and space-time synchronization processing through point cloud registration and target tracking algorithm, eliminates sensor noise and time stamp deviation, and obtains the position coordinates (such as x and y coordinates in the coordinate system with the current position of the ego vehicle as the origin) of the adjacent vehicles in the same time dimension. Based on the position coordinates of the adjacent vehicles, the control unit calculates the actual inter-vehicle distance value of the adjacent two vehicles in the target lane through the Euclidean distance formula. If the calculated inter-vehicle distance ≥ the total length of the expected position region in the longitudinal direction, it means that the adjacent two vehicles will not occupy the expected position region at the same time, and the time-space occupation of the vehicles on the expected position region can be analyzed independently; if the inter-vehicle distance < the total length of the safety corridor in the longitudinal direction, it means that the two vehicles will occupy the target corridor at the same time, and they are bound as a whole queue. After being bound as a whole queue, the bound whole queue (such as vehicle No. 2 and vehicle No. 3 in Figure 5 ) and vehicle No. 1 are regarded as adjacent vehicles, and the empty period of the expected position region is calculated.

[0096] Among them, the inter-vehicle distance refers to the longitudinal distance of the adjacent two vehicles in the target lane direction, which is usually represented by the distance between the tail of the front vehicle and the head of the rear vehicle, and is used to evaluate the relative closeness between the vehicles. The vehicle group refers to a group of vehicles driving on the target lane, and the inter-vehicle distance between the vehicles in the group is less than the longitudinal length of the expected position region. Since these vehicles will occupy the expected position region at the same time during the lane changing process, they cannot provide an independent insertion gap for the ego vehicle, so the control unit processes them as a whole, and the front boundary is the head position of the first vehicle in the group, and the rear boundary is the tail position of the last vehicle, and the whole is regarded as a continuous occupation unit to participate in the subsequent empty period calculation.

[0097] In this embodiment, by merging a plurality of closely driving vehicles into a single logical entity, the complexity of traffic flow modeling is simplified, the fragmentation problem caused by individually judging each vehicle in the group is avoided, the calculation resources are saved, and the efficiency is improved.

[0098] In an embodiment shown, the environment information comprises a centerline position of the target lane and driving scene information, and the ego vehicle state information comprises length and width of the ego vehicle, a position point and a speed; and the method of calculating the expected position region of the ego vehicle after performing lane changing to the target lane based on the environment information and ego vehicle state information comprises: determining a corresponding position point in the centerline position which is in the same driving position as the position point of the ego vehicle; predicting a time length required for the ego vehicle to complete lane changing to the target lane based on the driving scene information; calculating a center point of the expected position region based on the corresponding position point, the speed and the predicted time length; and determining the expected position region of the ego vehicle after performing lane changing to the target lane based on the length and width of the ego vehicle and the center point.

[0099] For example, referring to Figure 6 , Figure 6 is a schematic diagram of an example embodiment of a method of determining an expected position region. As shown in Figure 6 , the ego vehicle is driving on a current lane and plans to change lanes to a target lane on the right side. After the ego vehicle completes lane changing preparation, the control unit obtains the centerline position of the target lane collected by the perception module as 20 meters to the right of the ego vehicle position point, the driving scene as a highway, the length of the ego vehicle as 5.0 meters and the width as 1.8 meters, and the current position point and speed of the ego vehicle. Then, the control unit determines a position point which is in the same driving position as the current position point of the ego vehicle (not shown in the figure) based on the centerline position of the target lane. Then, the control unit determines the time length required for the ego vehicle to complete lane changing to the target lane as 2 seconds based on the relationship between the driving scene and the time length required for completing lane changing which is pre-stored according to the driving scene of the highway. Next, the control unit calculates the center point of the expected position region of the ego vehicle after changing lanes to the target lane based on the speed of the ego vehicle and the time length required for lane changing, and the calculation formula is . The center point is also the end point of the lane changing path planning of the ego vehicle. Finally, the control unit obtains the expected position region (i.e. the dashed box shown in the figure) which covers the area of the plane where the length and width of the ego vehicle are located based on the center point , and the region covers the space range that the ego vehicle may occupy after completing lane changing, which is used for subsequent empty period calculation and lane changing trajectory calculation.

[0100] The expected location area has a length that is a preset multiple of the vehicle's length, and a width that is a preset multiple of the vehicle's width or equal to the width of the target lane. Driving scenario information refers to the road type and traffic environment characteristics of the vehicle, such as highway, urban arterial road, ramp, rainy weather, and nighttime. The vehicle's lane-changing behavior pattern and the time required for lane changes differ under different driving scenarios. The control unit can pre-store the relationship between the time required for the vehicle to complete a lane change and the scenario, such as 2 seconds for a lane change in a highway scenario and 3 seconds for a lane change in an urban arterial road scenario.

[0101] In one embodiment, the planned lane-change path includes several trajectory points, each trajectory point containing the position and direction of the vehicle at the current time and at a certain time in the future. After planning the lane-change path for the vehicle, the method further includes: calculating the positions of the other vehicles at the same time based on the status information of the other vehicles and the times of the several trajectory points; if the distance between the position of any trajectory point and the position of the other vehicles is less than a preset safe distance threshold, or the direction of the last trajectory point included in the planned lane-change path is inconsistent with the driving direction of the target lane, then the lane-change path planning is determined to have failed; otherwise, the lane-change path planning is determined to have succeeded.

[0102] For example, such as Figure 6 As shown, the vehicle plans to change lanes to the right from its current lane to enter the target lane. After completing the lane change path planning, the control unit generates a lane change path containing multiple trajectory points. Each trajectory point corresponds to a timestamp. For example, there are 9 trajectory points at 6.2 seconds, 6.4 seconds, 6.6 seconds... up to 7.8 seconds in the lane change path. Each trajectory point contains the vehicle's expected position (x, y coordinates) and driving direction (heading angle) at that moment. ). Based on the acquired state information of other vehicles on the target lane, the control unit predicts the positions of other vehicles at the corresponding 9 time points through a motion model, and calculates the distance between the expected position of each trajectory point and the position of other vehicles at the corresponding time. If the distance between the position of the trajectory point at 6.6 seconds and the position of other vehicles at 6.6 seconds is 0.5 meters, which is less than the safety distance threshold of 1 meter, the control unit determines that the lane changing path has a collision risk. In addition, the control unit also detects whether the heading angle of the last trajectory point at 7.8 seconds of the lane changing path is consistent with the driving direction (usually the center line direction) of the target lane. If the detected heading angle deviation reaches 8°, which exceeds the allowed deviation of ±5°, it is also determined that the lane changing path does not meet the driving compliance. When any of the above conditions is triggered, the control unit finally determines that the current lane changing path planning fails, and triggers the re-planning process to try to generate a new lane changing path using the next available time period. Only when all trajectory points meet the safety distance and the direction of the end trajectory point is consistent with the driving direction of the target lane, the lane changing path planning is confirmed to be successful.

[0103] In the lane changing path planning, the trajectory point is a key node describing the future position and direction of the ego vehicle. The generation of the trajectory point usually relies on model-based predictive control, fast random search tree or optimization method. The heading angle refers to the included angle between the current driving direction of the vehicle and the center line direction of the target lane. Setting the allowed deviation range of the heading angle can ensure that the ego vehicle maintains the correct driving direction after entering the target lane, which meets the requirements of traffic rules.

[0104] In order to help those skilled in the art better understand the technical solutions of the present disclosure, the following will be introduced from the perspective of the complete process of the present disclosure. Please refer to Figure 7 , Figure 7 is a flowchart of another vehicle lane changing control method shown in an exemplary embodiment. As Figure 7As shown, the control unit of the ego vehicle first acquires environmental information, ego vehicle state information, and state information of other vehicles driving on the target lane, including but not limited to driving scenarios, lane line positions, ego vehicle speed and position, other vehicle speed and position on the target lane, etc. When it is determined according to the environmental information that the ego vehicle needs to change lanes, the control unit controls the ego vehicle to perform actions such as deceleration, turn on the turn signal, fine-tune the heading, honk, etc. to stimulate the rear vehicle on the target lane to pass quickly or decelerate appropriately, creating conditions for the ego vehicle to change lanes. Then, the control unit predicts the expected position region of the ego vehicle on the target lane after performing lane change based on the collected environmental information and ego vehicle state information using a motion model; and predicts the expected positions of other vehicles on the target lane at future time points based on the state information of other vehicles driving on the target lane, and further determines the vacant time periods of the expected position region on the target lane, marked as {1, 2,..., N}, each time period corresponding to a possible lane change opportunity. When calculating the vacant time periods, the vehicle group between the adjacent two vehicles on the target lane whose distance is less than the length of the expected position region can be regarded as a whole to reduce the calculation amount. Next, the control unit sets an interval counter i, which is initialized as follows: i = 0, and performs lane change path planning based on the i-th vacant time period, the expected position region, and the ego vehicle state information. If the planning is successful, the ego vehicle is controlled to perform lane change according to the planned path. If the planning fails, the counter i is incremented to point to the next vacant time period, and then the lane change path planning is performed again based on the next vacant time period. This cycle continues until the lane change path planning is successful. If the lane change path planning is not successful for the N vacant time periods, the driver is prompted to take over the vehicle and manually control the ego vehicle to change lanes.

[0105] Through the above process, the technical solution of the present disclosure can intelligently select a suitable lane change opportunity and generate an adaptive lane change path in a complex traffic environment, thereby improving the lane change success rate and safety of an autonomous vehicle.

[0106] Corresponding to the above-mentioned embodiment of the vehicle lane change control method, the present disclosure also provides an embodiment of a vehicle lane change control device.

[0107] Please refer to Figure 8 , Figure 8Figure 1 is an exemplary embodiment illustrating a hardware structure diagram of an electronic device. At the hardware level, the device includes a processor 802, an internal bus 804, a network interface 806, a memory 808, and a non-volatile memory 810, and can also include other required hardware. One or more embodiments of the present disclosure can be implemented in a software manner, such as by the processor 802 reading a corresponding computer program from the non-volatile memory 810 into the memory 808 and then running. Of course, in addition to the software implementation, one or more embodiments of the present disclosure do not exclude other implementation manners, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or a logic device.

[0108] Figure 2 is an exemplary embodiment illustrating a flowchart of a method for controlling a vehicle to change lanes. Figure 9 , Figure 9 Figure 3 is an exemplary embodiment illustrating a block diagram of a vehicle lane change control device. The device 900 includes:

[0109] a first calculation unit 902 configured to calculate an expected position region of a target lane of a host vehicle after the host vehicle performs a lane change according to environmental information and host vehicle state information;

[0110] a second calculation unit 904 configured to calculate an empty period of the expected position region according to state information of at least one other vehicle traveling on the target lane;

[0111] a first planning unit 906 configured to perform lane change path planning for the host vehicle according to the host vehicle state information, the expected position region, and the empty period;

[0112] a control unit 908 configured to control the host vehicle to perform a lane change according to the planned lane change path to cause the host vehicle to enter the expected position region during the empty period if the lane change path planning is successful.

[0113] In some embodiments, the empty period is a preset number, and the lane change path planning for the host vehicle according to the host vehicle state information, the expected position region, and the empty period includes:

[0114] performing lane change path planning for the host vehicle according to the host vehicle state information, the expected position region, and an empty period located at a first rank among a plurality of empty periods;

[0115] After performing the lane change path planning for the host vehicle, the device further includes:

[0116] The second planning unit 910 is configured to perform lane-changing path planning on the ego vehicle according to the ego vehicle state information, the expected position region, and a next-order vacant time period determined in the plurality of vacant time periods, if the lane-changing path planning fails; and repeat the above steps until the lane-changing path planning succeeds.

[0117] In some embodiments, the calculation of the vacant time period of the expected position region according to the state information of at least one other vehicle driving on the target lane comprises:

[0118] determining the head position and the tail position of the other vehicle in the current time and the future time period according to the state information of the at least one other vehicle driving on the target lane;

[0119] determining whether the expected position region is vacant according to the head position and the tail position of the other vehicle in the current time;

[0120] if the expected position region is vacant, collecting the current time as the start time of the vacant time period;

[0121] determining the time when the head position of the other vehicle reaches the lower boundary of the expected position region as the end time of the vacant time period according to the head position of the other vehicle in the future time period.

[0122] In some embodiments, the device further comprises:

[0123] The first determining unit 912 is configured to determine a plurality of groups of adjacent vehicles according to the state information of the other vehicle if the expected position region is not vacant;

[0124] The first recording unit 914 is configured to collect the time when the tail of the previous vehicle of the adjacent vehicle reaches the upper boundary of the expected position region and the head of the next vehicle of the adjacent vehicle does not reach the lower boundary of the expected position region as the start time of the vacant time period;

[0125] The second recording unit 916 is configured to collect the time when the head of the next vehicle of the adjacent vehicle reaches the lower boundary of the expected position region and the tail of the previous vehicle of the adjacent vehicle has reached or exceeded the upper boundary of the expected position region as the end time of the vacant time period.

[0126] In some embodiments, the device further comprises:

[0127] The second determining unit 918 is configured to determine the inter-vehicle distance between the other vehicles in the current time according to the head position and the tail position of the other vehicle in the current time if the expected position region is not vacant;

[0128] The processing unit 920 is configured to process the vehicle group as a whole vehicle if the inter-vehicle distance between the vehicles included in the vehicle group is less than the length of the expected position region in the target lane direction.

[0129] The device further includes a determining unit 910 configured to determine a plurality of groups of adjacent vehicles in the other vehicles, including:

[0130] The device further includes a determining unit 910 configured to determine a plurality of groups of adjacent vehicles in the other vehicles, including:

[0131] In some embodiments, the environment information includes a center line position of the target lane and driving scene information, and the ego vehicle state information includes a length and width of the ego vehicle, a position point and a speed of the ego vehicle; and the calculation of the expected position region of the ego vehicle in the target lane after performing the lane change based on the environment information and the ego vehicle state information includes:

[0132] The determining unit 910 is configured to determine a corresponding position point in the center line position that is at the same driving position as the position point of the ego vehicle.

[0133] The determining unit 910 is configured to predict a time length required for the ego vehicle to complete the lane change to the target lane based on the driving scene information.

[0134] The determining unit 910 is configured to calculate a center point of the expected position region based on the corresponding position point, the speed and the predicted time length.

[0135] The determining unit 910 is configured to determine the expected position region of the ego vehicle in the target lane after performing the lane change based on the length and width of the ego vehicle and the center point.

[0136] In some embodiments, the planned lane change path includes a plurality of trajectory points, each of which includes a position and a direction of the ego vehicle at a current time and at a time in a future time period, and the device further includes:

[0137] The third calculation unit 922 is configured to calculate a position of the other vehicle at the same time based on the state information of the other vehicle and the time of each of the plurality of trajectory points.

[0138] The third determining unit 924 is configured to determine that the lane change path planning fails if a distance between the position of any trajectory point in the plurality of trajectory points and the position of the other vehicle is less than a preset safety distance threshold, or a direction of a last trajectory point included in the planned lane change path is inconsistent with a driving direction of the target lane; otherwise, it is determined that the lane change path planning is successful.

[0139] The functions and roles of the units in the device are implemented in the implementation process of the corresponding steps in the above method, which will not be described here.

[0140] For the apparatus embodiment, since it basically corresponds to the method embodiment, the relevant parts are described in the part of the method embodiment. The apparatus embodiment described above is only illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the present disclosure according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0141] The system, apparatus, module or unit illustrated in the above embodiments can be specifically implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0142] In a typical configuration, the computer includes one or more processors (CPUs), input / output interfaces, network interfaces, and memories.

[0143] The memory can include non-persistent memory in computer readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or Flash memory. The memory is an example of computer readable media.

[0144] The computer readable media includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, disk storage, quantum memory, graphene-based storage medium or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition in this paper, computer readable media does not include transitory computer readable media, such as modulated data signals and carriers.

[0145] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or rejection.

[0146] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another identical element in the process, method, article or device comprising the element.

[0147] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in which they are recited in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0148] The terms used in one or more embodiments of the present disclosure are merely for the purpose of describing specific embodiments and are not intended to limit one or more embodiments of the present disclosure. The singular forms "a", "an" and "the" used in one or more embodiments of the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein means and includes any or all possible combinations of one or more associated listed items.

[0149] It should be understood that although the terms first, second, third, etc. can be employed in one or more embodiments of the present disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another type of information. For example, without departing from the scope of one or more embodiments of the present disclosure, first information can also be referred to as second information, and similarly, second information can also be referred to as first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0150] The above merely provides the preferred embodiment of one or more embodiments of the present disclosure, and is not intended to limit one or more embodiments of the present disclosure. Any modification, equivalent replacement, improvement, and the like made within the spirit and principle of one or more embodiments of the present disclosure shall fall within the protection scope of one or more embodiments of the present disclosure.

Claims

1. A vehicle lane change control method characterized by, The method comprises: According to the relationship between the time required for the ego vehicle to complete lane changing and the driving scene stored in advance, the time required for the ego vehicle to complete lane changing to the target lane is predicted according to the current driving scene information; According to the center line position of the target lane, the predicted time and the ego vehicle state information, the expected position area of the ego vehicle after executing lane changing in the target lane is calculated; According to the state information of at least one other vehicle driving on the target lane, the empty time period of the expected position area is calculated; According to the ego vehicle state information, the expected position area and the empty time period, the ego vehicle is planned for lane changing path; If the lane changing path planning is successful, the ego vehicle is controlled to execute lane changing according to the planned lane changing path, so that the ego vehicle drives into the expected position area in the empty time period.

2. The method of claim 1, wherein, The empty time period is a preset number, and the ego vehicle is planned for lane changing path according to the ego vehicle state information, the expected position area and the empty time period. According to the ego vehicle state information, the expected position area and the empty time period located in the first order among the plurality of empty time periods, the ego vehicle is planned for lane changing path. After planning the lane changing path for the ego vehicle, the method further comprises: If the lane changing path planning fails, the ego vehicle is planned for lane changing path according to the ego vehicle state information, the expected position area and the empty time period located in the next order sequentially determined among the plurality of empty time periods; The above steps are repeatedly executed until the lane changing path planning is successful.

3. The method of claim 1, wherein, According to the state information of at least one other vehicle driving on the target lane, the head position and the tail position of the other vehicle within the current time and the future time period are determined; According to the head position and the tail position of the other vehicle at the current time, it is determined whether the expected position area is empty; If the expected position area is empty, the current time is collected as the start time of the empty time period; According to the head position of the other vehicle within the future time period, the time when the head position of the other vehicle reaches the lower boundary of the expected position area is determined as the end time of the empty time period. The method further comprises:

4. The method of claim 3, wherein, If the expected position area is not empty, a plurality of groups of adjacent vehicles are determined according to the state information of the other vehicle; The time when the tail of the previous vehicle of the adjacent vehicle reaches the upper boundary of the expected position area and the head of the next vehicle of the adjacent vehicle does not reach the lower boundary of the expected position area is taken as the start time of the empty time period; The time when the head of the next vehicle of the adjacent vehicle reaches the lower boundary of the expected position area and the tail of the previous vehicle of the adjacent vehicle has reached or exceeded the upper boundary of the expected position area is taken as the end time of the empty time period. The method further comprises:

5. The method of claim 4, wherein, If the expected position area is not empty, the distance between the other vehicles at the current time is determined according to the head position and the tail position of the other vehicle at the current time. ​ if there is a vehicle group in the other vehicles, and the distance between the vehicles included in the vehicle group is less than the length of the expected position region in the target lane direction, the vehicle group is processed as a whole vehicle; determining a plurality of groups of adjacent vehicles in the other vehicles, including: determining a plurality of groups of adjacent vehicles in the other vehicles.

6. The method of claim 1, wherein, The self-vehicle state information includes the length and width of the self-vehicle, the position point and the speed; and the calculation of the expected position region of the self-vehicle in the target lane after performing lane changing according to the center line position of the target lane, the prediction time length and the self-vehicle state information includes: determining a corresponding position point in the center line position which is at the same driving position as the position point of the self-vehicle; calculating a center point of the expected position region according to the corresponding position point, the speed and the prediction time length; determining the expected position region of the self-vehicle in the target lane after performing lane changing according to the length and width of the self-vehicle and the center point.

7. The method of claim 1, wherein, The planned lane changing path includes a plurality of trajectory points, each trajectory point including the position and direction of the self-vehicle at a certain time in the current time and the future time period, and after the lane changing path planning for the self-vehicle, the method further includes: calculating the position of the other vehicles at the same time according to the state information of the other vehicles and the time of the plurality of trajectory points; if the distance between the position of any trajectory point in the plurality of trajectory points and the position of the other vehicles is less than a preset safety distance threshold, or the direction of the last trajectory point included in the planned lane changing path is inconsistent with the driving direction of the target lane, it is determined that the lane changing path planning fails; otherwise, it is determined that the lane changing path planning succeeds.

8. A vehicle lane change control device characterized by comprising: The device includes: a prediction unit configured to predict the time length required for the self-vehicle to complete lane changing to the target lane according to the relationship between the time length required for the self-vehicle to complete lane changing and the driving scene and the current driving scene information; a first calculation unit configured to calculate the expected position region of the self-vehicle in the target lane after performing lane changing according to the center line position of the target lane, the prediction time length and the self-vehicle state information; a second calculation unit configured to calculate the empty period of the expected position region according to the state information of at least one other vehicle driving on the target lane; a planning unit configured to perform lane changing path planning for the self-vehicle according to the self-vehicle state information, the expected position region and the empty period; a control unit configured to control the self-vehicle to perform lane changing according to the planned lane changing path if the lane changing path planning succeeds, so that the self-vehicle drives into the expected position region in the empty period.

9. An electronic device, comprising: The device includes a communication interface, a processor, a memory and a bus, and the communication interface, the processor and the memory are connected to each other through the bus; The memory stores machine readable instructions, and the processor executes the method of any one of claims 1 to 7 by invoking the machine readable instructions.

10. A machine-readable storage medium, characterized in that, The machine readable storage medium stores machine readable instructions which, when invoked and executed by the processor, implement the method of any one of claims 1 to 7.

Images