Control method and device for automatic lane changing function
Through the method of evaluating and selecting target gaps, the decision-making problem of automatic lane change in the case of high traffic flow and fast environmental changes is solved, and the success rate and decision-making accuracy of automatic lane change are improved.
Patent Information
- Application Number
- CN202311687257.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-08
- Publication Date
- 2025-06-10
AI Technical Summary
The prior art is difficult to make effective decisions and realize automatic lane change in the case of huge traffic flow, especially in environments where environmental models are rapidly changing.
By evaluating the effectiveness of multiple potential gaps on the target lane and evaluating lane change costs based on factors such as arrival time, the target gap is determined, making the automatic lane change function more comprehensive, accurate and reasonable decision-making.
It improves the success rate of the automatic lane change function during autonomous driving, and enhances the lane change decision-making ability in the case of high traffic flow and fast environmental changes.
Smart Images
Figure CN120116936A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of control of an automatic lane change function, and more specifically, to a control method and device for an automatic lane change function, a computer storage medium, a computer program product, and an advanced driver assistance system (ADAS). Background Art
[0002] For the automatic lane change function, there is currently no mature technical solution to determine the target gap. Since the environmental model changes every second, it is difficult for the autonomous vehicle to make a decision on the target gap in order to change lanes.
[0003] The existing scheme only evaluates a single gap near the ego vehicle and waits for the right time to change lanes, but it will be difficult for the ego vehicle to change lanes in heavy traffic. Summary of the invention
[0004] According to one aspect of the present application, a control method for an automatic lane change function is provided, the method comprising: evaluating the effectiveness of multiple potential gaps on a target lane; when a first potential gap among the multiple potential gaps is valid, evaluating the lane change cost of the first potential gap at least based on an arrival time, wherein the arrival time is the time taken for the vehicle to reach the center point of the first potential gap; and determining a target gap from the multiple potential gaps based on the evaluated lane change costs, so that the automatic lane change function controls the vehicle to change lanes based on the target gap.
[0005] As a supplement or alternative to the above solution, in the above method, evaluating the effectiveness of multiple potential gaps on the target lane includes: evaluating the effectiveness of the multiple potential gaps according to the gap length gap_length, the space of the leading obstacle in front of the vehicle lead_obs_space, and the arrival time arrival_time.
[0006] As a supplement or alternative to the above scheme, in the above method, when the gap length gap_length is greater than the minimum safety distance threshold min_safe_size, the space lead_obs_space of the leading obstacle in front of the vehicle is greater than the preset minimum space threshold min_lc_space, and the arrival time arrival_time is less than the first time threshold time_threshold, the gap is determined to be valid.
[0007] As a supplement or alternative to the above scheme, in the above method, when a first potential gap among the multiple potential gaps is valid, evaluating the lane change cost of the first potential gap at least based on the arrival time includes: evaluating the lane change cost of the first potential gap based on the gap space, speed efficiency, arrival time and impact on other vehicles.
[0008] As a supplement or replacement to the above solution, in the above method, determining a target gap from the multiple potential gaps according to the evaluated lane change cost includes: determining the gap corresponding to the lowest value in the evaluated lane change costs as the target gap.
[0009] As a supplement or replacement to the above solution, the above method further includes: determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost.
[0010] As a supplement or replacement to the above solution, in the above method, determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost includes: checking whether a first target gap already exists in the automatic lane change function; when the first target gap exists, determining whether the duration of the first target gap is greater than a second time threshold T; and only when the duration is greater than the second time threshold T and the lane change cost of a second gap is less than the difference between the lane change cost of the first target gap and a dynamic threshold ∈, determining the second gap as the new target gap.
[0011] According to another aspect of the present application, there is provided a control device for an automatic lane change function, the device including: a first evaluation device for evaluating the effectiveness of multiple potential gaps on a target lane; a second evaluation device for evaluating the lane change cost of a first potential gap among the multiple potential gaps at least according to the arrival time, where the arrival time is the time taken for the vehicle to reach the center point of the first potential gap; and a first determination device for determining a target gap from the multiple potential gaps according to the evaluated lane change cost, such that the automatic lane change function controls the vehicle to change lanes based on the target gap.
[0012] As a supplement or replacement to the above solution, in the above device, the first evaluation device is configured to evaluate the effectiveness of the multiple potential gaps according to a gap length gap_length, a space lead_obs_space of a leading obstacle in front of the vehicle itself, and an arrival time arrival_time.
[0013] As a supplement or replacement to the above solution, in the above device, the second evaluation device is configured to: evaluate the lane change cost of the first potential gap according to a gap space, a speed efficiency, an arrival time, and an impact on other vehicles.
[0014] As a supplement or replacement to the above solution, the above device further includes: a second determination device for determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost.
[0015] As a supplement or replacement to the above solution, in the above device, the second determination device is configured to: check whether there is a first target gap in the automatic lane change function; when the first target gap exists, determine whether the duration of the first target gap is greater than a second time threshold T; and only when the duration is greater than the second time threshold T and the lane change cost of the second gap is less than the difference between the lane change cost of the first target gap and the dynamic threshold ∈, determine the second gap as the new target gap.
[0016] According to another aspect of the present application, there is provided a computer storage medium, the medium including instructions that, when running, execute the method as described above.
[0017] According to another aspect of the present application, there is provided a computer program product, including a computer program that, when executed by a processor, implements the method as described above.
[0018] According to another aspect of the present application, there is provided an advanced driver assistance system ADAS, the advanced driver assistance system ADAS including the device as described above.
[0019] The control solution for the automatic lane change function in the embodiments of the present application evaluates the effectiveness of multiple potential gaps on the target lane, and when the first potential gap among the multiple potential gaps is effective, evaluates the lane change cost of the first potential gap at least according to the arrival time, and finally determines the target gap from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to change lanes based on the determined target gap. The control solution for the automatic lane change function makes more comprehensive, accurate and reasonable decisions on the target gap for the automatic lane change function, and increases the success rate of lane change during the automatic driving process. In one embodiment, it is determined whether to change the target gap according to the duration of the target gap and the evaluated lane change cost, which can help maintain the stability of the target gap. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] From the following detailed description in conjunction with the drawings, the above and other objects and advantages of the present application will become more completely clear, wherein the same or similar elements are denoted by the same reference numerals.
[0021] Figure 1 A flowchart showing the control method for the automatic lane change function according to an embodiment of the present application is shown;
[0022] Figure 2 A structural diagram showing the control device for the automatic lane change function according to an embodiment of the present application is shown; and
[0023] Figure 3A schematic diagram of a lane change scenario using the automatic lane change function according to an embodiment of the present application is shown. Detailed implementation manners
[0024] Hereinafter, a control scheme for the automatic lane change function according to each exemplary embodiment of the present application will be described in detail with reference to the accompanying drawings.
[0025] Figure 1 A flowchart of a control method 1000 for the automatic lane change function according to an embodiment of the present application is shown. As Figure 1 shown, the control method 1000 for the automatic lane change function includes the following steps:
[0026] In step S110, the effectiveness of multiple potential gaps on the target lane is evaluated;
[0027] In step S120, when the first potential gap among the multiple potential gaps is effective, the lane change cost of the first potential gap is evaluated at least based on the arrival time, where the arrival time is the time taken for the vehicle to reach the center point of the first potential gap; and
[0028] In step S130, a target gap is determined from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to change lanes based on the target gap.
[0029] In the context of the present application, the term "automatic lane change function" is also referred to as a lane change assist function or a Lanechangefunction, and this function is located in a driving assistance system (such as ADAS). In one or more embodiments, the "automatic lane change function" is used to assist the driver in driving the vehicle into an adjacent lane. The term "target lane" refers to the lane that the automatic lane change function intends to drive the vehicle into, for example, the target lane is an adjacent lane to the lane where the vehicle is located. The term "potential gap" is formed by the gap between a leading obstacle ahead on the target lane (such as the vehicle ahead on the target lane) and a trailing obstacle (such as the vehicle behind on the target lane).
[0030] Refer to Figure 3 which shows a schematic diagram of a lane change scenario using the automatic lane change function according to an embodiment of the present application. As Figure 3As shown, the vehicle 310 and the guiding vehicle 350 (i.e., the leading obstacle in front of the host vehicle) are traveling on the left lane 3100, while other vehicles 320 and 330 are traveling on the right lane 3200. At a certain moment, the automatic lane-changing function on the vehicle 310 intends to change lanes to the right. At this time, the gap formed between the vehicle 320 in front (i.e., the leading obstacle in the target lane) and the vehicle 330 behind (i.e., the trailing obstacle in the target lane) on the right lane 3200 is the potential gap. In one embodiment, after evaluating the effectiveness and lane-changing cost of multiple potential gaps from multiple aspects or angles, a suitable target gap is selected for the automatic lane-changing function to form the target trajectory 340.
[0031] In step S110, the effectiveness of multiple potential gaps in the target lane is evaluated. In one embodiment, step S110 includes: evaluating the effectiveness of the multiple potential gaps according to three conditional factors, namely the gap length gap_length, the space lead_obs_space of the leading obstacle in front of the host vehicle, and the arrival time arrival_time. For example, when the gap length gap_length is greater than the minimum safety distance threshold min_safe_size, the space lead_obs_space of the leading obstacle in front of the host vehicle is greater than the preset minimum space threshold min_lc_space, and the arrival time arrival_time is less than the first time threshold time_threshold, it is determined that the gap is valid.
[0032] For example, the gap length gap_length can be determined according to the following formula:
[0033] gap_length = front_obs.start_s – rear_obs.end_s + gap_valid_time * (front_obs.v – rear_obs.v),
[0034] where front_obs.start_s represents the tail coordinate of the vehicle in front (the leading obstacle in front, such as Figure 3 320 in the figure) in the SL coordinate system, rear_obs.end_s represents the head coordinate of the vehicle behind (the trailing obstacle behind, such as Figure 3 330 in the figure) in the SL coordinate system, gap_valid_time represents the predicted time when the gap is valid, and front_obs.v and rear_obs.v respectively represent the longitudinal speeds of the vehicle in front (the leading obstacle in front, such as Figure 3 320 in the figure) and the vehicle behind (the trailing obstacle behind, such as Figure 3 330 in the figure).
[0035] As can be seen from the above formula, when evaluating the effectiveness of a potential gap using the gap length gap_length, predictive information (such as the predicted time gap_valid_time for the gap to be valid) is adopted, fully considering the temporal variability of the gap length, making the finally obtained gap length more accurate.
[0036] In one embodiment, the minimum safe distance threshold min_safe_size is determined according to the following formula:
[0037] min_safe_size = min_safe_front + min_safe_rear + ego_length,
[0038] where min_safe_front is the minimum safe distance to the vehicle in front, min_safe_rear is the minimum safe distance to the vehicle behind, and ego_length is the body length of the vehicle itself. In one embodiment, the minimum safe distance min_safe_front to the vehicle in front and the minimum safe distance min_safe_rear to the vehicle behind can be determined according to the following formula:
[0039] min_safe_front = max(0, v_ego_gap - front_obs.v) 2 / (2 * a soft_max ) + safety_dist; and
[0040] min_safe_rear = max(0, rear_obs.v - v_ego_gap) 2 / (2 * a soft_max ) + safety_dist,
[0041] where front_obs.v and rear_obs.v respectively represent the longitudinal speeds of the vehicle in front (the obstacle in front, such as Figure 3 320 in Figure 3 ) and the vehicle behind (the obstacle behind, such as soft_max 330 in
[0042] v_ego_gap represents the driving speed allowed after the vehicle enters the gap, and this allowed driving speed is restricted by the obstacle speed and the map speed limit. a
[0043] Among them, safe_buffer is a fixed parameter, and t_reaction represents the reaction time.
[0044] In one embodiment, when the calculated gap length gap_length is less than or equal to the minimum safety distance threshold min_safe_size, it can be determined that the potential gap corresponding to the gap length gap_length is invalid (for example, it does not fall within the consideration range of the target gap).
[0045] In addition to the gap length gap_length, in one embodiment, the space of the leading obstacle in front of the host vehicle lead_obs_space also needs to be considered when evaluating the effectiveness of the potential gap. The space of the leading obstacle in front of the host vehicle lead_obs_space can be determined according to the following formula:
[0046] lead_obs_space = (gap_lc_time + t_buffer) * (lead_obs.v - rear_obs.v) + lead_obs.start_s - rear_obs.end_s,
[0047] Among them, gap_lc_time represents the expected lane change time for a gap, t_buffer represents the time buffer, which is an adjustable parameter (can be positive, negative, or zero), lead_obs.v and rear_obs.v respectively represent the longitudinal speeds of the leading obstacle in front of the host vehicle (such as the vehicle in front in the current lane, as shown by 350 in Figure 3 ), and the rear obstacle of the gap (such as the vehicle behind in the target lane, as shown by 330 in Figure 3 ), lead_obs.start_s and rear_obs.end_s respectively represent the tail coordinates of the leading obstacle in front of the host vehicle (such as the vehicle in front in the current lane, as shown by 350 in Figure 3 ), and the head coordinates of the rear obstacle of the gap (such as the vehicle behind in the target lane, as shown by 330 in Figure 3 ).
[0048] In one embodiment, when the calculated space of the leading obstacle in front of the host vehicle lead_obs_space is less than or equal to the preset minimum (lane change) space threshold min_lc_space, it can be determined that the potential gap corresponding to the space of the leading obstacle in front of the host vehicle lead_obs_space is invalid (for example, it does not fall within the consideration range of the target gap). That is to say, the leading obstacle in front of the host vehicle should leave enough space for the vehicle to change lanes, otherwise this gap will not be considered as the target gap.
[0049] In addition to the gap length "gap_length" and the leading obstacle space "lead_obs_space" in front of the host vehicle, in one embodiment, the arrival time "arrival_time" is also considered when evaluating the effectiveness of a potential gap. In the context of the present application, the term "arrival time" refers to the time it takes for the host vehicle to reach the center point of a certain gap. Taking a certain potential gap in front of the host vehicle as an example, the host vehicle needs to accelerate to the speed limit value and then catch up with the center point of the gap. Therefore, the time ("arrival time") it takes for the host vehicle to catch up with a certain gap can be estimated by the following formula, so as to evaluate the ability of the host vehicle to catch up with the gap:
[0050] v limit = min(rear obs .v + 3, map_v_limit)
[0051] t 1 = (v limit - v ego ) / a max
[0052]
[0053]
[0054]
[0055] v delta = v limit - v rear
[0056]
[0057] In the above formula, arrival_time represents the arrival time, v limit represents the speed limit value, which is restricted by the longitudinal speed rear obs .v of the obstacle behind the gap and the map speed limit map_v_limit. t 1 represents the acceleration time for the host vehicle to reach the speed limit value v limit , v ego represents the longitudinal speed of the host vehicle, a max represents the maximum acceleration of the host vehicle, represents the S coordinate position of the host vehicle when accelerating to the speed limit value v limit in the SL coordinate system, S ego represents the current S coordinate position of the host vehicle in the SL coordinate system, represents the S coordinate position of the center point of the gap in the SL coordinate system when the host vehicle accelerates to the speed limit value v limit , S rearRepresents the head coordinate of the obstacle at the rear end of the (current) gap (such as the vehicle behind) in the SL coordinate system, S front Represents the tail coordinate of the (current) obstacle in front (such as the vehicle in front) in the SL coordinate system, v rear Represents the longitudinal speed of the obstacle at the rear end of the (current) gap (such as the vehicle behind), S delta Represents the distance between the vehicle and the center point of the gap, v delta Represents the speed difference between the vehicle and the obstacle at the rear end of the gap (such as the vehicle behind).
[0058] In one embodiment, when the calculated arrival time arrival_time is greater than or equal to the first time threshold time_threshold, it can be determined that the potential gap corresponding to the arrival time arrival_time is invalid (for example, not within the consideration range of the target gap). That is to say, the arrival time arrival_time has exceeded the maximum waiting time required (or defined) by the system, so the gap corresponding to the arrival time will not be considered as the target gap.
[0059] In step S120, when the first potential gap among the multiple potential gaps is valid, the lane-changing cost of the first potential gap is evaluated at least based on the arrival time. In one embodiment, step S120 includes: evaluating the lane-changing cost of the first potential gap based on the gap space, speed efficiency, arrival time, and the impact on other vehicles (four aspects). Evaluating the lane-changing cost from these four aspects can help select the best target gap and thus improve the lane-changing success rate of the automatic lane-changing function.
[0060] In one embodiment, the lane-changing cost Cost related to the gap space space Can be determined according to the following formula:
[0061]
[0062] Where gap_length represents the gap length and can be determined according to the following formula:
[0063] gap_length = front_obs.start_s – rear_obs.end_s + gap_valid_time * (front_obs.v – rear_obs.v),
[0064] In the above formula, front_obs.start_s represents the tail coordinate of the vehicle in front (the obstacle in front, such as Figure 3 320 in) in the SL coordinate system, and rear_obs.end_s represents the rear vehicle (the obstacle behind, such as Figure 3The head coordinates of the 330) in it, gap_valid_time represents the predicted time when the gap is valid, front_obs.v and rear_obs.v respectively represent the longitudinal speeds of the vehicle in front (the obstacle in front, such as Figure 3 the 320) in it and the vehicle behind (the obstacle behind, such as Figure 3 the 330) in it.
[0065] Similarly, min_safe_size represents the minimum safe distance threshold, which can be determined according to the following formula:
[0066] min_safe_size = min_safe_front + min_safe_rear + ego_length,
[0067] In the above formula, min_safe_front is the minimum safe distance of the vehicle in front, min_safe_rear is the minimum safe distance of the vehicle behind, and ego_length is the body length of the vehicle itself. In addition, the parameter MaxSpaceCost is a fixed value, representing the lane-changing cost related to the maximum gap space.
[0068] In one embodiment, the lane-changing cost Cost related to speed efficiency speed may depend on the obstacle speed and the map speed limit, and can be determined according to the following formula, for example:
[0069]
[0070] where, v_ego_gap represents the driving speed allowed after the vehicle enters the gap, and the allowed driving speed is limited by the obstacle speed and the map speed limit. map_v_limit represents the map speed limit, and MaxSpeedCost is a fixed value, representing the maximum lane-changing cost related to speed efficiency.
[0071] In one embodiment, the lane-changing cost Cost related to arrival time time may depend on the relative distance and speed, and can be determined according to the following formula, for example:
[0072]
[0073] where, arrival_time represents the arrival time, and ego s represents the S coordinate position of the vehicle itself in the SL coordinate system, represents the S coordinate position of the center point of the gap in the SL coordinate system, MaxDistRange represents the effective observation range of the obstacle, that is, the farthest observation distance, and MaxDistCost is a fixed parameter value.
[0074] In one embodiment, the lane change cost Cost related to the impact on other vehicles other is a factor for attempting to minimize the impact on other vehicles, especially when we perform a lane change operation. Here, we assume that other vehicles will use acceleration (deceleration) to avoid collisions. For example, the lane change cost Cost related to the impact on other vehicles can be calculated through a Sigmoid function other , as follows:
[0075]
[0076] where a max represents the maximum acceleration (deceleration) (of other vehicles), C is a constant, and cost max is a fixed value representing the maximum lane change cost related to the impact on other vehicles.
[0077] In one embodiment, the maximum acceleration (deceleration) a max can be determined by the following formula:
[0078]
[0079] where s(t end ) represents the S coordinate position of the lane change target point in the SL coordinate system, S vehicle (t 0 ) represents the S coordinate position of the affected vehicle, s safety represents the safety distance, t 0 and t end respectively represent the time points when the lane change starts and ends, and v 0 represents the longitudinal speed of the affected vehicle at the start of the lane change.
[0080] In one embodiment, the evaluated lane change cost Cost total can be determined by the following formula:
[0081] Cost total = Cost space + Cost speed + Cost time + Cost other .
[0082] In step S130, a target gap is determined from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to perform a lane change based on the target gap. In one embodiment, step S130 may include: determining the gap corresponding to the lowest value in the evaluated lane change cost as the target gap.
[0083] In one embodiment, although Figure 1 Not shown in the figure, the above method 1000 may further include: determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost. That is to say, changing the target gap will be judged from two dimensions: the duration of the previously determined target gap and the lane change cost. This can ensure the stability of the decision-making.
[0084] In one embodiment, determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost includes: checking whether there is a first target gap in the automatic lane change function; when the first target gap exists, judging whether the duration of the first target gap is greater than a second time threshold T; and only when the duration is greater than the second time threshold T and the lane change cost of the second gap is less than the difference between the lane change cost of the first target gap and a dynamic threshold ∈ (greater than 0) (that is, the lane change cost of the second gap is much smaller than that of the first target gap, and the duration of the first target gap is already greater than T), determining the second gap as the new target gap. In this way, the stability of the target gap decision-making can be ensured to a certain extent.
[0085] In addition, those skilled in the art can easily understand that the control method 1000 for the automatic lane change function provided by one or more of the above embodiments of the present application can be implemented by a computer program. For example, the computer program is included in a computer program product, and when the computer program is executed by a processor, it implements the control method 1000 for the automatic lane change function of one or more embodiments of the present application. Another example is that when a computer storage medium (such as a USB flash drive) storing the computer program is connected to a computer, running the computer program can execute the control method 1000 for the automatic lane change function of one or more embodiments of the present application.
[0086] Figure 2 shows a schematic structural diagram of a control device 2000 for an automatic lane change function according to an embodiment of the present application. As Figure 2 shown, the control device 2000 for the automatic lane change function includes: a first evaluation device 210, a second evaluation device 220, and a first determination device 230. Among them, the first evaluation device 210 is used to evaluate the effectiveness of multiple potential gaps on the target lane; the second evaluation device 220 is used to evaluate the lane change cost of the first potential gap at least according to the arrival time when the first potential gap among the multiple potential gaps is effective, where the arrival time is the time taken for the vehicle to reach the center point of the first potential gap; and the first determination device 230 is used to determine a target gap from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to change lanes based on the target gap.
[0087] In the context of the present application, the term "automatic lane change function" is also referred to as lane change assist function or Lane change function, and this function is located in a driving assistance system (such as ADAS). In one or more embodiments, the "automatic lane change function" is used to assist the driver in driving the vehicle into an adjacent lane. The term "target lane" refers to the lane that the automatic lane change function intends to drive the vehicle into, for example, the target lane is an adjacent lane to the lane where the vehicle is located. The term "potential gap" is constituted by the gap formed between the leading obstacle ahead on the target lane (such as the vehicle ahead on the target lane) and the obstacle behind (such as the vehicle behind on the target lane).
[0088] In one embodiment, the first evaluation device 210 is configured to evaluate the effectiveness of the plurality of potential gaps according to the gap length gap_length, the space lead_obs_space of the leading obstacle in front of the host vehicle, and the arrival time arrival_time. For example, the first evaluation device 210 is configured to determine that the gap is valid when the gap length gap_length is greater than the minimum safety distance threshold min_safe_size, the space lead_obs_space of the leading obstacle in front of the host vehicle is greater than the preset minimum space threshold min_lc_space, and the arrival time arrival_time is less than the first time threshold time_threshold.
[0089] In one embodiment, the second evaluation device 220 is configured to: evaluate the lane change cost of the first potential gap according to the gap space, speed efficiency, arrival time, and the impact on other vehicles.
[0090] In one embodiment, the first determination device 230 is configured to: determine the gap corresponding to the lowest value among the evaluated lane change costs as the target gap.
[0091] Although Figure 2 not shown in the figure, in one embodiment, the above device 2000 may further include: a second determination device for determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost. In one implementation, the second determination device is configured to: check whether there is a first target gap in the automatic lane change function; when the first target gap exists, determine whether the duration of the first target gap is greater than the second time threshold T; and only when the duration is greater than the second time threshold T and the lane change cost of the second gap is less than the difference between the lane change cost of the first target gap and the dynamic threshold ∈, determine the second gap as the new target gap.
[0092] In one embodiment, the above control device 2000 for the automatic lane change function may be integrated into various advanced driver assistance systems (ADAS). In one embodiment, the advanced driver assistance system (ADAS) may be installed in a vehicle.
[0093] "Advanced driver assistance system", also known as ADAS or advanced driving assistance system. It uses a variety of sensors installed on the vehicle (e.g., millimeter-wave radar, lidar, mono / stereo cameras, and satellite navigation) to sense the surrounding environment at any time during vehicle driving, collect data, identify, detect, and track static and dynamic objects, and combine navigation map data for system operation and analysis, so as to pre-warn the driver of possible dangers and effectively improve the comfort and safety of vehicle driving. In one embodiment, in addition to the automatic lane change function, the advanced driver assistance system may further include a navigation and real-time traffic system (TMC), an intelligent speed adaptation (ISA) system (Intelligent speed adaptation or intelligent speed advice), a vehicular communication system, an adaptive cruise control (ACC), a lane departure warning system (LDWS), a lane keep assistance system, a collision avoidance or pre-crash system, a night vision system, an adaptive light control system, a pedestrian protection system, an automatic parking system, a traffic sign recognition system, a blind spot detection system, a driver drowsiness detection system, a hill descent control system, and an electric vehicle warning sounds system, etc.
[0094] In summary, the control scheme for the automatic lane change function in the embodiments of the present application evaluates the effectiveness of multiple potential gaps on the target lane, and when the first potential gap among the multiple potential gaps is effective, evaluates the lane change cost of the first potential gap at least based on the arrival time. Finally, the target gap is determined from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to change lanes based on the determined target gap. The control scheme for the automatic lane change function makes a more comprehensive, accurate and reasonable decision on the target gap for the automatic lane change function, and increases the success rate of lane change during the automatic driving process. In one embodiment, a hysteresis system is used to change the target gap, that is, whether to change the target gap is determined according to the duration of the target gap and the evaluated lane change cost. This can help maintain the stability of the target gap.
[0095] The above examples mainly illustrate the control scheme for the automatic lane change function in the embodiments of the present application. Although only some of the embodiments of the present application are described, those of ordinary skill in the art should understand that the present application can be implemented in many other forms without departing from its gist and scope. Therefore, the examples and embodiments shown are regarded as illustrative rather than restrictive, and the present application may cover various modifications and substitutions without departing from the spirit and scope of the present application as defined by the various claims.
Claims
1. A control method for an automatic lane change function, characterized in that, the method includes: evaluating the effectiveness of multiple potential gaps on the target lane; when the first potential gap among the multiple potential gaps is effective, evaluating the lane change cost of the first potential gap at least based on the arrival time, where the arrival time is the time taken for the vehicle to reach the center point of the first potential gap; and determining a target gap from the multiple potential gaps according to the evaluated lane change cost, so that the automatic lane change function controls the vehicle to change lanes based on the target gap.
2. The method according to claim 1, wherein, evaluating the effectiveness of multiple potential gaps on the target lane includes: evaluating the effectiveness of the multiple potential gaps according to the gap length gap_length, the space lead_obs_space of the leading obstacle in front of the vehicle, and the arrival time arrival_time.
3. The method according to claim 2, wherein, when the gap length gap_length is greater than the minimum safety distance threshold min_safe_size, the space lead_obs_space of the leading obstacle in front of the vehicle is greater than the preset minimum space threshold min_lc_space, and the arrival time arrival_time is less than the first time threshold time_threshold, it is determined that the gap is effective.
4. The method according to claim 1, wherein, when the first potential gap among the multiple potential gaps is effective, evaluating the lane change cost of the first potential gap at least based on the arrival time includes: evaluating the lane change cost of the first potential gap according to the gap space, speed efficiency, arrival time, and the impact on other vehicles.
5. The method according to claim 1, wherein, determining a target gap from the multiple potential gaps according to the evaluated lane change cost includes: determining the gap corresponding to the lowest value in the evaluated lane change costs as the target gap.
6. The method according to claim 1, further includes: determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost.
7. The method according to claim 6, wherein, determining whether to change the target gap according to the duration of the target gap and the evaluated lane change cost includes: checking whether there is a first target gap in the automatic lane change function; when the first target gap exists, judging whether the duration of the first target gap is greater than the second time threshold T; and only when the duration is greater than the second time threshold T and the lane change cost of the second gap is less than the difference between the lane change cost of the first target gap and the dynamic threshold ∈, determining the second gap as the new target gap.
8. A control device for an automatic lane change function, characterized in that, the device includes: a first evaluation device for evaluating the effectiveness of multiple potential gaps on the target lane; A second evaluation device, configured to evaluate the lane-changing cost of the first potential gap based at least on the arrival time when the first potential gap among the multiple potential gaps is valid, where the arrival time is the time taken for the host vehicle to reach the center point of the first potential gap; and A first determination device, configured to determine a target gap from the multiple potential gaps according to the evaluated lane-changing cost, such that the automatic lane-changing function controls the host vehicle to change lanes based on the target gap.
9. The device according to claim 8, wherein, the first evaluation device is configured to evaluate the effectiveness of the multiple potential gaps according to the gap length gap_length, the space lead_obs_space of the leading obstacle in front of the host vehicle, and the arrival time arrival_time.
10. The device according to claim 8, wherein, the second evaluation device is configured to: evaluate the lane-changing cost of the first potential gap according to the gap space, speed efficiency, arrival time, and the impact on other vehicles.
11. The device according to claim 8, further comprises: A second determination device, configured to determine whether to change the target gap according to the duration of the target gap and the evaluated lane-changing cost.
12. The device according to claim 11, wherein, the second determination device is configured to: check whether there is a first target gap in the automatic lane-changing function; when the first target gap exists, determine whether the duration of the first target gap is greater than a second time threshold T; and only when the duration is greater than the second time threshold T and the lane-changing cost of the second gap is less than the difference between the lane-changing cost of the first target gap and the dynamic threshold ∈, determine the second gap as the new target gap.
13. A computer storage medium, characterized in that the medium includes instructions that, when running, execute the method according to any one of claims 1 to 7.
14. A computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, it implements the method according to any one of claims 1 to 7.
15. An advanced driving assistance system ADAS, characterized in that the advanced driving assistance system ADAS includes the device according to any one of claims 8 to 12.