Method, system and device for lane changing control in automatic driving, storage medium and vehicle

By obtaining the position information of the bicycle in the autonomous driving system to determine the cancellation level of lane change and intelligent jump status, the problem of difficulty in capturing lane change timing and heading angle fluctuations in large traffic density sections is solved, and the success rate and comfort of lane change are improved .

CN119058675AActive Publication Date: 2024-12-03GUANGZHOU AUTOMOBILE GROUP CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202310627167.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03
Estimated Expiration
2043-05-30

AI Technical Summary

Technical Problem

The existing autonomous driving system is difficult to capture the lane change opportunity in a large traffic density section, resulting in a low success rate of lane change, and the heading angle of the vehicle fluctuates greatly when lane change is cancelled, resulting in panic takeover.

Method used

During the lane change execution, the lateral offset and angle radian value of the bicycle and the original lane virtual reference line are obtained, the lane change cancellation level is judged, and the level is jumped to the corresponding target state according to the level, and the bicycle is controlled to reach the target position to control the bicycle to reach the target position , to intelligently determine the subsequent state and avoid mechanical state jumps.

Benefits of technology

It improves the success rate and comfort of the lane change of the autonomous driving system, reduces the degree of steering wheel return and heading angle fluctuations, is more in line with human driving habits, and can effectively seize the fleeting lane change opportunity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119058675A_ABST
    Figure CN119058675A_ABST
Patent Text Reader

Abstract

The invention discloses a method for controlling lane changing in automatic driving, which comprises the following steps of: in a lane changing execution process, if a lane changing cancelling command is received, acquiring current position information of a vehicle; according to the vehicle position information, the current lane changing cancelling grade is judged; according to the current lane changing cancel grade, a target state and a target pose, corresponding to the current lane changing cancel grade, of the vehicle are obtained, a vehicle decision state machine jumps to the target state, and the vehicle is controlled to reach the target pose. The invention further discloses a corresponding system and device, a storage medium and a vehicle. By implementing the method, the lane changing success rate, comfort and safety of the automatic driving system can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a method, system, device, storage medium and vehicle for lane change control in automatic driving. Background Art

[0002] In the current mainstream autonomous driving systems, decision-making, planning and control generally adopt tracking-based solutions. Such solutions are based on the navigation route given by the user-set navigation, downstream decision-making, planning and control to perceive or high-precision maps, obtain the lane edge lines of the current and future distance in real time, and based on this lane edge line, generate a virtual reference line for each lane on the navigation route, and implement behavior decisions, path and trajectory planning and control based on these reference lines.

[0003] In the autonomous driving system, human daily driving behaviors are abstracted and summarized into a series of decisions and actions such as lane changing, obstacle avoidance and lane keeping. The decision triggering and action execution process of autonomous driving can be combined and subdivided into five states: propose, prepare, execute, finish and cancel, based on the anthropomorphic thinking process, and lane keeping is used as the default state. The jumps between states can be controlled by setting thresholds and rules and using hierarchical finite state machines to prevent frequent state switching. For the entry and exit process of a single state, the corresponding logic judgment module can be bound for control. Using this method, the decision-making and behavior process of human drivers can be better simulated.

[0004] Safety is of vital importance for lane change decisions and behaviors. To ensure safety, during the lane change process, if a lane change condition is not met, the system will directly make a decision to cancel the lane change. In existing autonomous driving systems, the general solution for the behavior of the vehicle after the lane change is canceled is to directly return the vehicle to the center of the original lane and continue to drive based on the virtual reference line of the original lane. The system will try to initiate a lane change plan after a cooling period. In terms of the state jump of the state machine, after entering the cancel state, it is necessary to first return to the default lane keeping state, and then enter the lane change propose state to find the right time.

[0005] However, the existing lane change decision-making scheme has many shortcomings:

[0006] First, in high-traffic sections and at the end of the navigation lane change, the right time to change lanes is fleeting. The existing solution cannot capture the lane change opportunity in time, and the large fluctuation of the vehicle's heading angle will cause great panic to the driver and passengers. The above jump process takes a long time, and during the jump process, it is likely that the right time to change lanes will appear multiple times. The mechanical jump process will cause the vehicle to miss a lot of lane change opportunities, or even get stuck at the end of the navigation lane change, eventually leading to manual takeover or system exit.

[0007] Secondly, the existing technical solutions do not consider the execution degree of the lane change behavior of the ego vehicle when it enters the lane change cancellation state. If the ego vehicle has already pressed onto the lane edge line at this time, or even a large part of the vehicle body has entered the target lane, according to the existing technical solutions, the ego vehicle needs to return to the center of the original lane, and the heading angle required for the ego vehicle to return to the center of the original lane is very large. Externally, the ego vehicle exhibits irregular serpentine movements on roads with high traffic density, and it is difficult to adjust the appropriate posture for the next lane change opportunity. Internally, the steering wheel is turned back to a large extent, which causes the front of the ego vehicle to suddenly swing back, which can easily cause panic takeover. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a method, system, device, storage medium and vehicle for lane change control in automatic driving, which can improve the lane change success rate, comfort and safety of the automatic driving system.

[0009] In order to solve the above technical problems, as one aspect of the present invention, a method for lane change control in automatic driving is provided, which at least comprises the following steps:

[0010] During the lane change execution process, if a lane change cancellation command is received, the current vehicle position information is obtained, and the vehicle position information at least includes: a lateral offset δl of the vehicle relative to the original lane virtual reference line and an angular value δθ between the vehicle and the original lane virtual reference line;

[0011] Determining a current lane change cancellation level according to the vehicle position information;

[0012] According to the current lane change cancellation level, the target state and target posture of the vehicle corresponding to the current lane change cancellation level are obtained, the vehicle decision state machine is jumped to the target state, and the vehicle is controlled to reach the target posture; wherein each lane change cancellation level corresponds to a target state, and the target state includes: lane keeping, lane change proposal, lane change preparation or target lane keeping.

[0013] Wherein, judging the current lane change cancellation level according to the lateral offset δl and the angle radian value δθ further includes:

[0014] When the δl is less than or equal to the first offset threshold, and the δθ is less than or equal to the first radian threshold, it is determined that the current lane change cancellation level is the first level;

[0015] When the δl is less than or equal to the second offset threshold, and the δθ is greater than the first radian value threshold, it is determined that the current lane change cancellation level is the second level;

[0016] When the δθ is greater than the second offset threshold, and the δθ is less than or equal to the first radian value threshold, it is determined that the current lane change cancellation level is the third level;

[0017] When the δl is greater than the second offset threshold, and the δθ is greater than the first radian threshold, it is determined that the current lane change cancellation level is the fourth level;

[0018] The second offset threshold is greater than the first offset threshold.

[0019] Wherein, according to the current lane change cancellation level, obtaining a target state and a target posture of the vehicle corresponding to the current lane change cancellation level, jumping the vehicle decision state machine to the target state, and controlling the vehicle to reach the target posture further includes:

[0020] When the current lane change cancellation level is the first level, the target state is lane keeping, and the state is jumped to the lane keeping state, and the target posture is: δl=0 and δθ=0;

[0021] When the current lane change cancellation level is the second level, the target state is lane change lift, and the state is jumped to the lane change lift state, and the vehicle head is straightened in the lane without continuing to enter the target lane. The target posture is: δθ=0;

[0022] When the current lane change cancellation level is the third level, the target state is lane change preparation. The state is jumped to the lane change preparation state, and the vehicle continues to enter the target lane. The vehicle head is straightened in the target lane. The target posture is: δl is greater than half the lane width, and δθ = 0;

[0023] When the current lane change cancellation level is the fourth level, the target state is target lane keeping. The state is jumped to target lane keeping, and the current posture is maintained. When a suitable space appears, it sticks to the virtual reference line of the target lane. The target posture is: δθ=0.

[0024] Among them, further include:

[0025] After the vehicle jumps into the target state, the judgment logic corresponding to the target state is triggered to perform subsequent control.

[0026] Wherein, when the vehicle jumps into the target state and triggers the judgment logic corresponding to the target state for subsequent control, it further includes:

[0027] When the vehicle enters the lane keeping state or the target lane keeping state, the longitudinal speed decision module of the vehicle is triggered, and then the vehicle determines whether to accelerate or decelerate by judging the movement of the front and rear vehicles in the lane.

[0028] When the vehicle enters the lane change proposal state, it determines whether the driving environment continues to meet the necessity and legality of lane change. If it continues to meet the requirements, it enters the next lane change preparation state; if not, it returns to the lane keeping state.

[0029] When the vehicle enters the lane change preparation state, the decision system determines whether there is a suitable lane change timing and duration in each frame. If so, it enters the lane change execution state and performs the lane change operation; and after the vehicle is close to the virtual reference line of the target lane, it enters the lane change completion state and then jumps to the lane keeping state.

[0030] Accordingly, another aspect of the present invention further provides a system for performing lane change control in automatic driving, which at least comprises:

[0031] A lane change position information acquisition unit is used to acquire the current vehicle position information if a lane change cancellation command is received during the lane change execution process, wherein the vehicle position information at least includes: a lateral offset δl of the vehicle relative to the original lane virtual reference line and an angular value δθ between the vehicle and the original lane virtual reference line;

[0032] a cancellation level determination unit, configured to determine a current lane change cancellation level according to the vehicle position information;

[0033] The target state switching unit is used to obtain the target state and target posture of the vehicle corresponding to the current lane change cancellation level according to the current lane change cancellation level, jump the vehicle decision state machine to the target state, and control the vehicle to reach the target posture; each lane change cancellation level corresponds to a target state, and the target state includes: lane keeping, lane change proposal, lane change preparation or target lane keeping.

[0034] Wherein, the cancellation level determination unit further comprises:

[0035] A first level determination unit, configured to determine that the current lane change cancellation level is the first level when the δl is less than or equal to a first offset threshold and the δθ is less than or equal to a first radian value threshold;

[0036] A second level determination unit, configured to determine that the current lane change cancellation level is the second level when the δl is less than or equal to a second offset threshold and the δθ is greater than a first radian value threshold;

[0037] A third level determination unit, configured to determine that the current lane change cancellation level is the third level when the δl is greater than the second offset threshold and the δθ is less than or equal to the first radian value threshold;

[0038] a fourth level determination unit, configured to determine that the current lane change cancellation level is the fourth level when the δl is greater than the second offset threshold and the δθ is greater than the first radian value threshold;

[0039] The second offset threshold is greater than the first offset threshold.

[0040] Wherein, the target state switching unit further comprises:

[0041] A first switching processing unit is used for, when the current lane change cancellation level is the first level, the target state is lane keeping, jumping the state to the lane keeping state, and the target posture is: δl=0 and δθ=0;

[0042] The second switching processing unit is used for, when the current lane change cancellation level is the second level, the target state is lane change lifting, jumping the state to the lane change lifting state, not continuing to enter the target lane, and straightening the front of the vehicle on the spot in the lane, and the target posture is: δθ=0;

[0043] The third switching processing unit is used for, when the current lane change cancellation level is the third level, the target state is lane change preparation, jumping the state to the lane change preparation state, continuing to enter the target lane, and straightening the front of the vehicle in the target lane, and the target posture is: δl is greater than half the lane width, and δθ=0;

[0044] The third switching processing unit is used to jump the state to the target lane keeping when the current lane change cancellation level is the fourth level, and keep the current posture. When a suitable space appears, the virtual reference line of the target lane is attached, and the target posture is: δθ=0.

[0045] Among them, further include:

[0046] A post-switching processing unit is used to trigger the judgment logic corresponding to the target state for subsequent control after the vehicle jumps into the target state;

[0047] The post-switching processing unit further comprises:

[0048] The lane keeping processing unit is used to trigger the longitudinal speed decision module of the ego vehicle when the ego vehicle enters the ego lane keeping or target lane keeping state, and then determine whether to accelerate or decelerate by judging the movement of the front and rear vehicles in the lane;

[0049] The lane change proposal processing unit is used to determine whether the driving environment continues to meet the necessity and legality of lane change when the vehicle enters the lane change proposal state. If it continues to meet the necessity and legality, it will enter the next lane change preparation state; if it does not meet the necessity and legality, it will return to the lane keeping state;

[0050] The lane change preparation processing unit is used to determine whether there is a suitable lane change opportunity and duration in each frame when the vehicle enters the lane change preparation state. If the conditions are met, the system enters the lane change execution state and performs the lane change operation. The system enters the lane change completion state after the vehicle is close to the virtual reference line of the target lane, and then jumps to the lane keeping state.

[0051] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned method are implemented.

[0052] According to another aspect of the present invention, a computing device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the aforementioned method when executing the computer program.

[0053] Another aspect of the present invention further provides a vehicle, on which at least a lane change decision device is provided, and the lane change decision device is deployed with the system as described above.

[0054] The implementation of the embodiments of the present invention has the following beneficial effects:

[0055] The present invention provides a method, system, device, storage medium and vehicle for lane change control in automatic driving. In an embodiment of the present invention, during the lane change process, when the lane change state of the self-vehicle is converted from lane change execution to lane change cancellation, the current position information of the self-vehicle is first obtained: the angle between the self-vehicle and the virtual reference line of the original lane and the lateral offset of the self-vehicle relative to the virtual reference line of the original lane, to judge the execution degree of the lane change behavior of the self-vehicle, determine the current lane change cancellation level, and intelligently decide to enter one of the three states of lane keeping, lane change proposal or lane change preparation according to the lane change cancellation level, and then execute the normal jump process of the state machine based on the judgment rule in the state.

[0056] In this embodiment, based on different cancellation levels, the state machine will intelligently jump into different states, thereby triggering the corresponding judgment logic in advance, making the decision of the autonomous driving system more flexible.

[0057] In this embodiment, when the state machine switches to the lane change proposal or lane change preparation state, compared with the prior art, its lane change-related judgment logic will be triggered in advance, so that the autonomous driving system will not miss the fleeting lane change opportunity and lane change space.

[0058] In this embodiment, when the state machine switches to the lane change preparation state, the vehicle will not return to the center of the original lane, but will straighten the front of the vehicle on the spot and directly look for the next lane change space. By adopting this kind of intelligent jump method, the mechanical state jump in the original solution can be avoided, so as to trigger the judgment logic module such as finding the lane change space as soon as possible, ensuring that the autonomous driving system can effectively seize the fleeting opportunity to change lanes.

[0059] At the same time, by implementing the embodiments of the present invention, the steering wheel return degree when the lane change is canceled can be reduced, the fluctuation degree of the vehicle heading angle when the cancellation state occurs can be reduced, and the driving comfort of lane change can be improved. It can also reduce the control tracking pressure of the downstream control end in such scenarios, making the lane change decision and behavior of the automatic driving system more decisive, efficient, smooth, and comfortable, and more in line with human driving habits under high traffic density. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0061] Figure 1 A schematic diagram of the main process of an embodiment of a method for lane change control in automatic driving provided by the present invention;

[0062] Figure 2 A more detailed schematic diagram of the application principle of the present invention;

[0063] Figure 3 A schematic diagram of the vehicle position information involved in the present invention;

[0064] Figure 4 A schematic diagram of the corresponding relationship between the vehicle position information corresponding to the four lane change cancellation levels involved in the present invention;

[0065] Figure 5 A schematic diagram of a processing process after switching to a lane keeping state according to the present invention;

[0066] Figure 6 A schematic diagram of a processing process after switching to a lane change proposal state according to the present invention;

[0067] Figure 7 A schematic diagram of a processing process after switching to a lane change preparation state according to the present invention;

[0068] Figure 8A schematic structural diagram of an embodiment of a system for lane change control in automatic driving provided by the present invention;

[0069] Fig. 9 for Figure 8 A schematic diagram of the structure in which the level determination unit is cancelled;

[0070] Fig.10 for Figure 8 A schematic diagram of the structure of the target state switching unit;

[0071] Fig.11 for Figure 8 Schematic diagram of the structure of the post-switching processing unit. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0073] like Figure 1 FIG. 1 is a schematic diagram showing a main process of an embodiment of a method for lane change control in an automatic driving according to the present invention; and FIG. Figures 2 to 7 As shown, in this embodiment, the method for performing lane change control in the automatic driving includes at least the following steps:

[0074] Step S10, during the lane change execution process, if a lane change cancellation command is received, obtain the current vehicle position information, the vehicle position information at least including: the lateral offset δl of the vehicle relative to the original lane virtual reference line and the radian value δθ of the angle between the vehicle and the original lane virtual reference line;

[0075] It is understandable that in the autonomous driving system, the state machine pre-state of the lane change decision is the lane change execution state. During the lane change execution process, the traffic conditions on the current target lane, the predicted motion trajectory of the surrounding dynamic objects, and the results of the downstream motion planning are comprehensively considered to judge the lane change safety in real time. When the lane change safety conditions are not met, the lane change cancel state is entered. At this time, the decision module of the autonomous driving system needs to record the lateral offset δl of the vehicle relative to the original lane virtual reference line (such as the center line of the original lane) and the radian value δθ of the angle between the vehicle and the original lane virtual reference line, such as Figure 3 As shown, a schematic diagram of the lateral offset δl and the angle radian value δθ during the lane change process is shown, wherein the lateral offset δl may be the distance between the center point O of the vehicle and the virtual reference line of the original lane;

[0076] Step S11, judging the current lane change cancellation level according to the vehicle position information to determine the degree of execution of the current lane change decision;

[0077] In a specific example, the step S11 further includes:

[0078] When the δl is less than or equal to the first offset threshold, and the δθ is less than or equal to the first radian threshold, it is determined that the current lane change cancellation level is the first level; in this case, both δl and δθ are very small, indicating that the lane change action has not actually started at this time;

[0079] When δl is less than or equal to the second offset threshold, and δθ is greater than the first radian value threshold, it is determined that the current lane change cancellation level is the second level; in this case, δθ is large and δl is small, indicating that the swing amplitude of the vehicle head is large, but the vehicle speed is slow, the forward distance is short, and the lane change action is only performed to a small extent;

[0080] When δl is greater than the second offset threshold, and δθ is less than or equal to the first radian value threshold, it is determined that the current lane change cancellation level is the third level; in this case, δθ is small and δl is large, indicating that the vehicle speed is fast at this time, and a small steering wheel angle can make the vehicle quickly deviate from the original reference line, and the lane change action is executed to a greater extent;

[0081] When the δl is greater than the second offset threshold and the δθ is greater than the first radian value threshold, it is determined that the current lane change cancellation level is the fourth level; in this case, both δl and δθ are large, indicating that the lane change action has been deeply executed at this time.

[0082] The second offset threshold is greater than the first offset threshold; in a specific example, the first offset threshold is 0.3 m, the second offset threshold is 0.6 m, and the first arc value threshold is 0.06 degrees.

[0083] Step S12, according to the current lane change cancellation level, obtaining the target state of the ego vehicle corresponding to the current lane change cancellation level and the target posture that needs to be adjusted, jumping the vehicle decision state machine to the target state, and controlling the ego vehicle to reach the target posture; wherein each lane change cancellation level corresponds to a target state, and the target state includes: ego lane keeping, propose, ready or target lane keeping.

[0084] In a specific example, the step S12 further includes:

[0085] When the current lane change cancellation level is the first level, the target state is self-lane keeping, and the state is jumped to the self-lane keeping state, and the tracking forward is performed based on the virtual reference line of the original lane, and the target posture is: δl=0 and δθ=0;

[0086] When the current lane change cancellation level is the second level, the target state is lane change lift, and the state is jumped to the lane change lift state, and the vehicle head is straightened in the lane without continuing to enter the target lane. The target posture is: δθ=0;

[0087] When the current lane change cancellation level is the third level, the target state is lane change preparation. The state is jumped to the lane change preparation state, and the vehicle continues to enter the target lane. The vehicle head is straightened in the target lane. The target posture is: δl is greater than half the lane width, and δθ = 0;

[0088] When the current lane change cancellation level is the fourth level, the target state is target lane keeping. The state is jumped to target lane keeping, and the current posture is maintained. When a suitable space appears, it sticks to the virtual reference line of the target lane. The target posture is: δθ=0.

[0089] In a specific example, the method further comprises:

[0090] Step S13, after the vehicle jumps into the target state, triggering the judgment logic corresponding to the target state to perform subsequent control. Wherein, step S13 further includes:

[0091] Step S130, when the ego vehicle enters the ego lane keeping or target lane keeping state, the longitudinal speed decision module of the ego vehicle is triggered, and then the movement of the front and rear vehicles in the lane is judged to determine whether to accelerate or decelerate at present;

[0092] Specifically, when the ego vehicle enters ego lane keeping, it follows the virtual reference line of the original lane; and when the ego vehicle enters the target lane keeping state, it maintains the current position, blocks the original lane change space, and looks for an opportunity to stick to the virtual reference line of the target lane. The state machine jump diagram of this situation can be seen in Figure 5 As shown;

[0093] Step S131, when the vehicle enters the lane change propose state, it determines whether the driving environment continues to meet the necessity and legality of lane change. If it continues to meet the requirements, it enters the next lane change ready state, executes the logic of finding lane change space, and waits for an opportunity to perform lane change operations. If it does not meet the requirements, it returns to the lane keeping state, that is, the vehicle behaves as if it is close to the lane edge or pressing the lane edge for a period of time, and then returns to the center of the original lane. The state machine jump diagram of this situation can be seen in Figure 6 As shown;

[0094] In a specific example, the following factors should be considered when determining the necessity and legality of lane change:

[0095] Necessity of lane change: In the case of navigation lane change, it is necessary to consider the distance to the next intersection, whether there is a sensed lane line, whether the attributes of the current lane and the target lane meet the requirements of straight driving, left turn, right turn or U-turn, etc.; for overtaking lane change, it is necessary to consider the relative speed and distance to the vehicle in front, as well as the traffic speed of the own lane and the traffic speed of the adjacent lane, etc.

[0096] For the legality of lane change, factors such as speed limit information, lane edge information (such as dotted line or solid line) and road rights need to be considered.

[0097] Step S132, when the vehicle enters the lane change ready state, since the vehicle has already entered the target lane, returning to the original lane to perform lane keeping will cause a large swing of the vehicle head. Therefore, the vehicle will temporarily keep the vehicle head on the spot and keep moving forward in the target lane, pressing the lane edge.

[0098] The decision system directly triggers the logic of finding a suitable lane change space, that is, it determines whether there is a suitable lane change opportunity and duration in each frame. If it is satisfied, it means that it is safe to perform the lane change at this time, so it will enter the lane change execution state and perform the lane change operation. Specifically, in this state, the ego vehicle will turn the steering wheel to deviate from the original lane according to the locked lane change space, and accelerate and decelerate according to the relative speed with the front and rear vehicles. This state will continue until the ego vehicle completely enters the target lane and is close to the virtual reference line of the target lane. It is understandable that since part of the right of way in the target lane has been occupied at this time, the rear vehicle will give up space for the ego vehicle to use, which can also increase the probability of a suitable lane change space. And the ego vehicle is always looking for a suitable lane change space, so it will increase the success rate of lane change.

[0099] When the ego vehicle is close to the virtual reference line of the target lane, it means that the lane change action is about to be completed and the lane change is completed. This state will not last for a long time. When the direction of the ego vehicle is consistent with the direction of the target lane, it means that the lane change behavior is completely completed and the ego vehicle is in the lane keeping state. The state machine state jumps to "lane keeping". The state machine jump diagram for this situation can be seen in Figure 7 shown.

[0100] In a specific example, the following conditions are generally considered to determine whether there is a suitable time to change lanes: whether there is a suitable lane-changing space in the target lane, the gap between the vehicle in front and behind relative to the vehicle at present, and the gap between the vehicle in front and behind relative to the vehicle two seconds in the future, calculated using relative speed and fixed time interval; suitable gap, longitudinal distance greater than the length of the vehicle, etc.

[0101] In a specific example, the lane change opportunity duration can be set to 10 frames; the "lane change preparation" state timeout is set to 8 seconds; the "lane change completion" judgment condition is set to: δl is less than 0.2m, and δθ is less than 0.02; the traffic density is the value obtained by dividing the number of vehicles within a distance by the distance.

[0102] It is understandable that the present invention combines the vehicle's own position information (i.e., posture) after the lane change is canceled, and subdivides the lane change cancellation state into four levels according to the execution degree of the lane change of the vehicle. Based on different cancellation levels, the state machine will intelligently jump into different states, and then trigger the corresponding judgment logic in advance, making the decision of the autonomous driving system more flexible and efficient. In particular, the state machine will jump directly to the ready state, in which the autonomous driving decision module will directly start looking for the right time to change lanes. This type of jump can avoid missing the right time to change lanes and improve the success rate of lane changes.

[0103] At the same time, in an embodiment of the present invention, based on the four levels of lane change cancellation status, combined with the target posture information, the posture of the vehicle can be intelligently adjusted to avoid a large swing back of the front of the vehicle. When the lane change is canceled, when the vehicle is already driving on the lane edge, in this embodiment, the vehicle will be allowed to straighten the front of the vehicle on the spot, thereby showing the following vehicle that it has not given up the lane change. If the vehicle has almost completely entered the target lane at this time, in this embodiment, the vehicle will continue to maintain this posture, which is specifically manifested in that the front of the vehicle directly enters the fleeting lane change space, thereby showing the following vehicle that it is still executing the lane change. Therefore, in this solution, when the lane change is canceled, the swing amplitude of the front of the vehicle will first be greatly reduced, which can improve the driving comfort, and at the same time it can occupy a certain degree of road rights, thereby helping to improve the success rate of capturing the lane change space and opportunity.

[0104] In this embodiment, by utilizing the posture of the ego vehicle after the lane change is canceled, the state that the state machine enters next is intelligently selected, and then the lane change timing judgment module is triggered in time to seize the appropriate lane change opportunity as soon as possible. At the same time, the ego vehicle can quickly adjust to the appropriate posture, reducing the degree of ego vehicle swing back, making the lane change decision and behavior of the automatic driving system more decisive, efficient, smooth, and comfortable, which is more in line with human driving habits under high traffic density.

[0105] like Figure 8 FIG. 1 is a schematic diagram showing a structure of an embodiment of a system for lane change control in an automatic driving system provided by the present invention. Figures 9 to 11 As shown, in this embodiment, the system at least includes:

[0106] The lane change position information acquisition unit 10 is used to acquire the current vehicle position information if a lane change cancellation command is received during the lane change execution process, wherein the vehicle position information at least includes: a lateral offset δl of the vehicle relative to the original lane virtual reference line and an angular value δθ between the vehicle and the original lane virtual reference line;

[0107] a cancellation level determination unit 11, configured to determine a current lane change cancellation level according to the vehicle position information;

[0108] a target state switching unit 12, configured to obtain a target state and a target posture of the vehicle corresponding to the current lane change cancellation level according to the current lane change cancellation level, jump the vehicle decision state machine to the target state, and control the vehicle to reach the target posture; wherein each lane change cancellation level corresponds to a target state, and the target state includes: lane keeping, lane change proposal, lane change preparation, or target lane keeping;

[0109] The post-switching processing unit 13 is used to trigger the judgment logic corresponding to the target state to perform subsequent control after the vehicle jumps into the target state.

[0110] like Fig. 9 As shown, in a specific example, the cancellation level determination unit 11 further includes:

[0111] A first level determination unit 110, configured to determine that the current lane change cancellation level is the first level when the δl is less than or equal to a first offset threshold and the δθ is less than or equal to a first radian threshold;

[0112] A second level determination unit 111, configured to determine that the current lane change cancellation level is the second level when the δl is less than or equal to the second offset threshold and the δθ is greater than the first radian value threshold;

[0113] A third level determination unit 112, configured to determine that the current lane change cancellation level is the third level when the δl is greater than the second offset threshold and the δθ is less than or equal to the first radian value threshold;

[0114] a fourth level determination unit 113, configured to determine that the current lane change cancellation level is the fourth level when the δl is greater than the second offset threshold and the δθ is greater than the first radian value threshold;

[0115] The second offset threshold is greater than the first offset threshold.

[0116] like Fig.10 As shown, in a specific example, the target state switching unit 12 further includes:

[0117] The first switching processing unit 120 is used for switching the state to the lane keeping state when the current lane change cancellation level is the first level and the target state is lane keeping, and the target posture is: δl=0 and δθ=0;

[0118] The second switching processing unit 121 is used for, when the current lane change cancellation level is the second level, the target state is lane change lifting, jumping the state to the lane change lifting state, not continuing to enter the target lane, and straightening the front of the vehicle on the spot in the lane, and the target posture is: δθ=0;

[0119] The third switching processing unit 122 is used for, when the current lane change cancellation level is the third level, the target state is lane change preparation, jumping the state to the lane change preparation state, continuing to enter the target lane, and straightening the front of the vehicle in the target lane, and the target posture is: δl is greater than half the lane width, and δθ=0;

[0120] The third switching processing unit 123 is used to jump the state to the target lane keeping when the current lane change cancellation level is the fourth level, and its target state is the target lane keeping, and maintain the current posture. When a suitable space appears, it sticks to the virtual reference line of the target lane, and the target posture is: δθ=0.

[0121] like Fig.11 As shown, in a specific example, the post-switching processing unit 13 further includes:

[0122] The lane keeping processing unit 130 is used to trigger the longitudinal speed decision module of the vehicle when the vehicle enters the lane keeping state or the target lane keeping state, and then determine whether to accelerate or decelerate by judging the movement of the front and rear vehicles in the lane;

[0123] The lane change proposal processing unit 131 is used to determine whether the driving environment continues to meet the necessity and legality of lane change when the vehicle enters the lane change proposal state, and if so, enter the next lane change preparation state; if not, return to the lane keeping state;

[0124] The lane change preparation processing unit 132 is used for when the vehicle enters the lane change preparation state, the decision system determines whether there is a suitable lane change opportunity and duration in each frame, and if satisfied, enters the lane change execution state and performs the lane change operation; and enters the lane change completion state after the vehicle has approached the virtual reference line of the target lane, and then jumps to the lane keeping state.

[0125] In another aspect of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the above-mentioned Figures 1 to 7 For more details, please refer to and combine the above Figures 1 to 7 The description is not repeated here.

[0126] In another aspect of the present invention, a computing device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the aforementioned Figures 1 to 7 For more details, please refer to and combine the above Figures 1 to 7 The description is not repeated here.

[0127] Another aspect of the present invention further provides a vehicle, on which at least a lane change decision device is provided, wherein the lane change decision device is deployed with the aforementioned Figures 8 to 11 For more details, please refer to and combine the above Figures 8 to 11 The description is not repeated here.

[0128] The implementation of the embodiments of the present invention has the following beneficial effects:

[0129] The present invention provides a method, system, device, storage medium and vehicle for lane change control in automatic driving. In an embodiment of the present invention, during the lane change process, when the lane change state of the self-vehicle is converted from lane change execution to lane change cancellation, the current position information of the self-vehicle is first obtained: the angle between the self-vehicle and the virtual reference line of the original lane and the lateral offset of the self-vehicle relative to the virtual reference line of the original lane, to judge the execution degree of the lane change behavior of the self-vehicle, determine the current lane change cancellation level, and intelligently decide to enter one of the three states of lane keeping, lane change proposal or lane change preparation according to the lane change cancellation level, and then execute the normal jump process of the state machine based on the judgment rule in the state.

[0130] In this embodiment, based on different cancellation levels, the state machine will intelligently jump into different states, thereby triggering the corresponding judgment logic in advance, making the decision of the autonomous driving system more flexible.

[0131] In this embodiment, when the state machine switches to the lane change proposal or lane change preparation state, compared with the prior art, its lane change-related judgment logic will be triggered in advance, so that the autonomous driving system will not miss the fleeting lane change opportunity and lane change space.

[0132] In this embodiment, when the state machine switches to the lane change preparation state, the vehicle will not return to the center of the original lane, but will straighten the front of the vehicle on the spot and directly look for the next lane change space. By adopting this kind of intelligent jump method, the mechanical state jump in the original solution can be avoided, so as to trigger the judgment logic module such as finding the lane change space as soon as possible, ensuring that the autonomous driving system can effectively seize the fleeting opportunity to change lanes.

[0133] At the same time, by implementing the embodiments of the present invention, the steering wheel return degree when the lane change is canceled can be reduced, the fluctuation degree of the vehicle heading angle when the cancellation state occurs can be reduced, and the driving comfort of lane change can be improved. It can also reduce the control tracking pressure of the downstream control end in such scenarios, making the lane change decision and behavior of the automatic driving system more decisive, efficient, smooth, and comfortable, and more in line with human driving habits under high traffic density.

[0134] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] The above disclosure is only a preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for lane change control in automatic driving, characterized in that: At least the following steps are included: During the lane change execution process, if a lane change cancellation command is received, the current vehicle position information is obtained, and the vehicle position information at least includes: a lateral offset δl of the vehicle relative to the original lane virtual reference line and an angular value δθ between the vehicle and the original lane virtual reference line; Determining a current lane change cancellation level according to the vehicle position information; According to the current lane change cancellation level, the target state and target posture of the self-vehicle corresponding to the current lane change cancellation level are obtained, the vehicle decision state machine is jumped to the target state, and the self-vehicle is controlled to reach the target posture; wherein each lane change cancellation level corresponds to a target state, and the target state includes: self-lane keeping, lane change proposal, lane change preparation or target lane keeping.

2. The method according to claim 1, characterized in that The determining, according to the vehicle position information, the current lane change cancellation level further includes: When the δl is less than or equal to the first offset threshold, and the δθ is less than or equal to the first radian threshold, it is determined that the current lane change cancellation level is the first level; When the δl is less than or equal to the second offset threshold, and the δθ is greater than the first radian value threshold, it is determined that the current lane change cancellation level is the second level; When the δl is greater than the second offset threshold, and the δθ is less than or equal to the first radian value threshold, it is determined that the current lane change cancellation level is the third level; When the δl is greater than the second offset threshold, and the δθ is greater than the first radian threshold, it is determined that the current lane change cancellation level is the fourth level; The second offset threshold is greater than the first offset threshold.

3. The method according to claim 2, characterized in that According to the current lane change cancellation level, obtaining a target state and a target posture of the vehicle corresponding to the current lane change cancellation level, jumping the vehicle decision state machine to the target state, and controlling the vehicle to reach the target posture, further comprising: When the current lane change cancellation level is the first level, the state is switched to the lane keeping state, and the target posture is: δl=0 and δθ=0; When the current lane change cancellation level is the second level, the state is jumped to the lane change lifting state, and the vehicle head is straightened in the lane without continuing to enter the target lane. The target posture is: δθ=0; When the current lane change cancellation level is the third level, the state is jumped to the lane change preparation state, and the vehicle continues to enter the target lane and straighten the front of the vehicle in the target lane. The target posture is: δl is greater than half the lane width, and δθ=0; When the current lane change cancellation level is the fourth level, the state is jumped to the target lane keeping, the current posture is maintained, and when a suitable space appears, it is attached to the virtual reference line of the target lane, and its target posture is: δθ=0.

4. The method according to claim 3, characterized in that Further including: After the vehicle jumps into the target state, the judgment logic corresponding to the target state is triggered to perform subsequent control.

5. The method according to claim 3, characterized in that When the vehicle jumps into the target state and triggers the judgment logic corresponding to the target state for subsequent control, it further includes: When the vehicle enters the lane keeping state or the target lane keeping state, the longitudinal speed decision module of the vehicle is triggered, and then the vehicle determines whether to accelerate or decelerate by judging the movement of the front and rear vehicles in the lane. When the vehicle enters the lane change proposal state, it determines whether the driving environment continues to meet the necessity and legality of lane change. If it continues to meet the requirements, it enters the next lane change preparation state; if not, it returns to the lane keeping state. When the vehicle enters the lane change preparation state, the decision system determines whether there is a suitable lane change timing and duration in each frame. If so, it enters the lane change execution state and performs the lane change operation; and after the vehicle is close to the virtual reference line of the target lane, it enters the lane change completion state and then jumps to the lane keeping state.

6. A system for lane change control in automatic driving, characterized in that: At least: A lane change position information acquisition unit is used to acquire the current vehicle position information if a lane change cancellation command is received during the lane change execution process, wherein the vehicle position information at least includes: a lateral offset δl of the vehicle relative to the original lane virtual reference line and an angular value δθ between the vehicle and the original lane virtual reference line; a cancellation level determination unit, configured to determine a current lane change cancellation level according to the vehicle position information; The target state switching unit is used to obtain the target state and target posture of the self-vehicle corresponding to the current lane change cancellation level according to the current lane change cancellation level, and jump the vehicle decision state machine to the target state to control the self-vehicle to reach the target posture; wherein each lane change cancellation level corresponds to a target state, and the target state includes: self-lane keeping, lane change proposal, lane change preparation or target lane keeping.

7. The system according to claim 6, characterized in that The cancellation level determination unit further comprises: A first level determination unit, configured to determine that the current lane change cancellation level is the first level when the δl is less than or equal to a first offset threshold and the δθ is less than or equal to a first radian value threshold; A second level determination unit, configured to determine that the current lane change cancellation level is the second level when the δl is less than or equal to a second offset threshold and the δθ is greater than a first radian value threshold; A third level determination unit, configured to determine that the current lane change cancellation level is the third level when the δl is greater than the second offset threshold and the δθ is less than or equal to the first radian value threshold; a fourth level determination unit, configured to determine that the current lane change cancellation level is the fourth level when the δl is greater than the second offset threshold and the δθ is greater than the first radian value threshold; The second offset threshold is greater than the first offset threshold.

8. The system according to claim 7, characterized in that The target state switching unit further comprises: A first switching processing unit is used to jump the state to the lane keeping state when the current lane change cancellation level is the first level, and its target posture is: δl=0 and δθ=0; The second switching processing unit is used to jump the state to the lane change lifting state when the current lane change cancellation level is the second level, and no longer continue to enter the target lane, and straighten the front of the vehicle on the spot in the lane, and its target posture is: δθ=0; The third switching processing unit is used to jump the state to the lane change preparation state when the current lane change cancellation level is the third level, continue to enter the target lane, and straighten the front of the vehicle in the target lane, and its target posture is: δl is greater than half the lane width, and δθ=0; The third switching processing unit is used to jump the state to the target lane keeping when the current lane change cancellation level is the fourth level, maintain the current posture, and when a suitable space appears, stick to the virtual reference line of the target lane, and its target posture is: δθ=0.

9. The system according to claim 8, characterized in that Further including: A post-switching processing unit is used to trigger the judgment logic corresponding to the target state for subsequent control after the vehicle jumps into the target state; The post-switching processing unit further comprises: The lane keeping processing unit is used to trigger the longitudinal speed decision module of the ego vehicle when the ego vehicle enters the ego lane keeping or target lane keeping state, and then determine whether to accelerate or decelerate by judging the movement of the front and rear vehicles in the lane; The lane change proposal processing unit is used to determine whether the driving environment continues to meet the necessity and legality of lane change when the vehicle enters the lane change proposal state. If it continues to meet the necessity and legality, it will enter the next lane change preparation state; if it does not meet the necessity and legality, it will return to the lane keeping state; The lane change preparation processing unit is used to determine whether there is a suitable lane change opportunity and duration in each frame when the vehicle enters the lane change preparation state. If the conditions are met, the system enters the lane change execution state and performs the lane change operation. The system enters the lane change completion state after the vehicle is close to the virtual reference line of the target lane, and then jumps to the lane keeping state.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

11. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

12. A vehicle, comprising at least a lane change decision device, wherein the lane change decision device is configured with a system as claimed in any one of claims 6 to 9.

Citation Information

Patent Citations

  • Driving assist apparatus

    CN109017777A

  • Vehicle lane changing method and device and electronic equipment

    CN113799776A

  • Vehicle lane changing control method and device and electronic equipment

    CN114516331A

  • Vehicle control method and device, vehicle and storage medium

    CN115195741A

  • Vehicle control method and device and electronic equipment

    CN115230705A