CN115158319A

CN115158319A - Vehicle lane changing method, device, electronic equipment and storage medium

Info

Publication number: CN115158319A
Application number: CN202210869635.XA
Authority: CN
Inventors: 陈鹏旭
Original assignee: Apollo Intelligent Technology Beijing Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2022-07-22
Filing date: 2022-07-22
Publication date: 2022-10-11

Abstract

The disclosure provides a vehicle lane changing method, a vehicle lane changing device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the fields of automatic driving and intelligent transportation. The specific implementation scheme is as follows: acquiring the current running state of the current vehicle at the current moment, and predicting at least one predicted running state of the current vehicle at the future moment; predicting a predicted environmental state of a lane change space on the target lane at the future time; combining the current driving state, each predicted driving state and the predicted environment state to obtain a state combination, and screening to obtain a target combination; instructing the current vehicle to change to travel on the target lane. The embodiment of the disclosure can timely change the lane of the vehicle and improve the lane change safety of the vehicle.

Description

Vehicle lane changing method, device, electronic equipment and storage medium

Technical Field

The disclosure relates to the field of artificial intelligence, in particular to the field of automatic driving and intelligent transportation, and in particular relates to a vehicle lane changing method and device, electronic equipment and a storage medium.

Background

With the increasing living standard and the development of vehicle assembly technology, vehicles such as cars, high chassis off-road vehicles and commercial vehicles have become more and more popular and become important transportation means in people's lives.

Due to the diversity and complexity of the actual driving road environment in real life, traffic accidents are easily caused by the lane change of vehicles.

Disclosure of Invention

The disclosure provides a vehicle lane change method, a vehicle lane change device, an electronic device and a storage medium.

According to an aspect of the present disclosure, there is provided a lane change method for a vehicle, including:

acquiring the current running state of the current vehicle at the current moment, and predicting at least one predicted running state of the current vehicle at the future moment;

predicting a predicted environmental state of a lane change space on the target lane at the future time;

combining the current driving state, each predicted driving state and the predicted environment state to obtain a state combination, and screening to obtain a target combination;

and indicating the current vehicle to run in the predicted running state in the target combination at the future time, and running along a lane change route corresponding to the predicted environment state in the target combination to change to the target lane for running.

According to an aspect of the present disclosure, there is provided a vehicle lane-changing device including:

the driving state prediction module is used for acquiring the current driving state of the current vehicle at the current moment and predicting at least one predicted driving state of the current vehicle at the future moment;

the lane change environmental state prediction module is used for predicting the predicted environmental state of the lane change space on the target lane at the future moment;

the state combination screening module is used for combining the current driving state, each predicted driving state and the predicted environment state to obtain a state combination and screening to obtain a target combination;

and the lane change driving module is used for indicating the current vehicle to drive in the predicted driving state in the target combination at the future time, driving along a lane change route corresponding to the predicted environment state in the target combination and converting the lane change route to the target lane for driving.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a vehicle lane-change method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to execute a vehicle lane-changing method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the vehicle lane change method of any of the embodiments of the present disclosure.

The embodiment of the disclosure can timely change the lane of the vehicle and improve the lane change safety of the vehicle.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic illustration of a vehicle lane-change method disclosed in accordance with an embodiment of the present disclosure;

FIG. 2 is a view of a vehicle traveling according to an embodiment of the present disclosure;

FIG. 3 is a flow chart of another vehicle lane-change method disclosed in accordance with an embodiment of the present disclosure;

FIG. 4 is a flow chart of another vehicle lane-change method disclosed in accordance with an embodiment of the present disclosure;

FIG. 5 is a view of another vehicle driving scenario disclosed in accordance with an embodiment of the present disclosure;

FIG. 6 is a flow chart of another vehicle lane-change method disclosed in accordance with an embodiment of the present disclosure;

FIG. 7 is a view of another vehicle driving scenario disclosed in accordance with an embodiment of the present disclosure;

FIG. 8 is a block diagram of a vehicle lane-change device disclosed in accordance with an embodiment of the present disclosure;

FIG. 9 is a block diagram of an electronic device for implementing a vehicle lane-change method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a flowchart of a lane change method for a vehicle according to an embodiment of the disclosure, which may be applied to a case of indicating a lane change of a vehicle. The method of this embodiment may be executed by a vehicle lane changing apparatus, which may be implemented in a software and/or hardware manner, and is specifically configured in an electronic device with certain data operation capability, where the electronic device may be a client device or a server device, and the client device may be, for example, a mobile phone, a tablet computer, a vehicle-mounted terminal, a desktop computer, and the like.

S101, acquiring the current running state of the current vehicle at the current moment, and predicting at least one predicted running state of the current vehicle at a future moment.

The current vehicle is a vehicle to be lane-changed, and the current vehicle runs on the current lane and needs to be changed to the target lane. The electronic device may be a device configured in the current vehicle, for example, a vehicle-mounted terminal, and may also be a device that is in communication connection with the current vehicle, for example, a mobile phone or a server. It should be noted that the current driving state of the current vehicle obtained by the non-vehicle-mounted terminal such as the mobile phone and the server is authorized by the user of the current vehicle, and both the current driving state and the authorized state meet the regulations of related laws and regulations, and do not violate the good customs of the public order.

The current time may refer to a time at which the current vehicle has determined that a change from the current lane to the target lane is required and a time thereafter. That is, from the current time, the current vehicle begins to plan how to change from the current lane to the target lane. The current running state refers to a running state of the current vehicle at the current time. The driving state may refer to driving data of the vehicle during driving, and may include at least one of the following: speed, acceleration, position, time of day, etc. Specifically, the current vehicle is in the current driving state and still drives on the current lane, that is, the current vehicle continues to drive on the current lane without performing operation behaviors such as lane changing and the like in the process from the current time to the future time.

The future time is a time after the current time, and illustratively, the current time is 9 points, and the future time may be 9 points and 5 seconds. The predicted travel state refers to a travel state of the current vehicle at a future time.

The predicted travel state at the future time can be predicted from the current travel state at the current time, and the time period from the current time to the future time and the current travel state can be determined, so that the predicted travel state at the future time can be deduced. Illustratively, the time period is 5, and the current driving state is position a and speed 3. For example, when the vehicle is traveling at a constant speed, the predicted traveling state is speed 3 and position a +3*5. For example, in the case of the constant speed running, the running state is predicted to be speed 4 and position a + (3+4) × 5/2. In another example, even deceleration running predicts that the running state is deceleration 0.2 and position A +3*5- (0.2 x 5^ 2)/2. The type of travel (constant speed, uniform speed change, uniform deceleration, etc.) and the speed of the predicted travel state can be randomly selected. In addition, other cases are also possible, and are not specifically limited herein.

And S102, predicting the predicted environment state of the lane change space on the target lane at the future moment.

The target lane is the lane in which the current vehicle is about to travel. The lane change space is a space in which a current vehicle can travel on the target lane. May be determined based on the vehicle traveling in the target lane.

Optionally, the predicting the predicted environmental state of the lane change space on the target lane at the future time includes: acquiring the running state of the obstacle vehicle on the target lane at the current moment; determining a space between two adjacent obstacle vehicles as a lane change space; and predicting the predicted environment state of the lane-changing space at the future moment according to the running states of two adjacent obstacle vehicles at the current moment.

The obstacle vehicle is a vehicle that affects a current vehicle to change to a target lane on which the obstacle vehicle is traveling. The lane change space refers to a space determination between two obstacle vehicles traveling adjacently on the target lane. Generally, a vehicle located in front of a current vehicle in two obstacle vehicles is used as a front vehicle, a vehicle located behind the current vehicle in the two obstacle vehicles is used as a rear vehicle, a space between a tail of the front vehicle and a head of the rear vehicle can be determined as a lane change space, and any obstacle, such as an obstacle vehicle, does not exist in the lane change space. The driving state of the obstacle vehicle can be acquired by a sensor arranged on the current vehicle, and can also be extracted from data provided by authorization of the obstacle vehicle. The predicted environmental state of the lane change space refers to an environmental state of the lane change space at a future time. The predicted environment state may refer to a region range, a movement state, a positional relationship, and the like of the lane change space at a future time. The predicted environment state may include a regional range and a position of the lane change space at a future time, a driving state of the obstacle vehicle that determines the lane change space, a relative relationship state between the obstacle vehicles that determines the lane change space, and a relative positional relationship between the lane change space and the current lane, and the like, wherein the relative relationship state may include at least one of: relative position, relative distance, relative velocity, etc. The relative positional relationship may be that the lane change space is located in a left lane of the current lane or that the lane change space is located in a right lane of the current lane.

The predicted environmental state of the lane change space at the future time is predicted according to the driving state of the obstacle vehicle on the target lane at the current time, and may be: and determining a plurality of pairs of two adjacent obstacle vehicles according to the obstacle vehicles on the target lane at the current moment, determining the current environment state of the lane changing space on the target lane for each pair, and determining the predicted environment state according to the current environment state. The current environment state refers to an environment state of the lane change space at the current moment, and the specific content of the current environment state can refer to the predicted environment state. Alternatively, the driving state of the obstacle vehicle at the future time may be determined based on the driving state of the obstacle vehicle at the present time, and a plurality of pairs of adjacent two obstacle vehicles at the future time may be determined, and for each pair of obstacle vehicles, a lane change space on the target lane may be determined, and the predicted environmental state of the lane change space may be determined based on the driving states of the pair of obstacle vehicles at the future time.

For example, the driving state of the obstacle vehicle on the target lane at the current time is: the front vehicle of the two adjacent obstacle vehicles has a speed of 10 and a position of B, and the rear vehicle has a speed of 5 and a position of C. The current environmental state of the lane-changing space determined by the two adjacent obstacle vehicles is as follows: the front vehicle speed 10, the front vehicle position B, the rear vehicle speed 5, the rear vehicle position C and the distance between the two vehicles are the distance between B and C. For example, the constant speed of the front vehicle and the rear vehicle is predicted, the time length between the current time and the future time is 5, and correspondingly, the driving state of the obstacle vehicle at the future time is as follows: the front vehicle has a speed of 10 and a position of B +50, the rear vehicle has a speed of 5 and a position of C +25. The predicted environmental state is: the front vehicle speed 10, the front vehicle position B +50, the rear vehicle speed 5, the rear vehicle position C +25 and the distance between the two vehicles are the distances between B +50 and C +25. As shown in fig. 2, at the present time, the unframed present vehicle 11 is traveling in the present lane, and there is a vehicle 21 ahead of the present lane, and at the same time, there are an obstacle vehicle 31, an obstacle vehicle 41, and an obstacle vehicle 51 in the target lane. Wherein the space between the adjacent obstacle vehicle 31 and obstacle vehicle 41 serves as a lane change space, and the space between the adjacent obstacle vehicle 41 and obstacle vehicle 51 serves as a lane change space. In fact, at the present time, the unblinded current vehicle 11 travels in the present traveling state, and at the future time, the current vehicle 11, which is outlined by a broken line, travels in the predicted traveling state.

It should be noted that, if there is only one obstacle vehicle on the target lane, it is possible to determine that the distance between the two vehicles is infinite in the predicted environmental state of the lane change space, and the position of the non-existing obstacle vehicle is infinite. For example, the predicted environment state may include end points of the lane change space, where one end point represents an obstacle vehicle, and the end points further record the position, speed, acceleration, and the like of the obstacle vehicle, and if there is no obstacle vehicle at one end, record the corresponding end point as a no-vehicle state.

Wherein, S101 and S102 may be sequentially exchanged. In fact, it may be detected whether the current vehicle can change to the target lane at the current time based on the current driving state of the current vehicle at the previous time and the driving state of the obstacle vehicle on the target lane. In the case of a lane change disabled situation, at least one predicted traveling state of the current vehicle at a future time and a predicted environmental state of a lane change space on the target lane at the future time are predicted. In the case of lane change, a lane change route is determined based on the current driving state of the current vehicle at the previous time and the driving state of the obstacle vehicle in the target lane, and the vehicle is instructed to change from the current lane to the target lane along the lane change route.

The lane change space is determined by combining the driving states of the obstacle vehicles on the target lane at the current moment, the lane change space at the future moment is predicted, the predicted environment state of the lane change space is determined, the space range of the lane change can be increased, the lane change possibility is increased, and the lane change success rate is improved.

S103, combining the current running state, each predicted running state and the predicted environment state to obtain a state combination, and screening to obtain a target combination.

As in the foregoing example, there are a plurality of predicted travel states. For example, a predicted travel state may be obtained by assuming constant-speed travel based on the current travel state so that the speed in the predicted travel state at the future time is the same as the speed in the current travel state and determining other travel states at the future time, or a predicted travel state may be obtained by assuming uniform-acceleration travel based on the current travel state so that the acceleration in the predicted travel state at the future time is the same as the acceleration in the current travel state and determining other travel states at the future time based on the acceleration. Furthermore, a predicted travel state can be obtained by determining other travel states at a future time based on the current travel state assuming that a certain position, i.e., a position where the predicted travel state is known, can be reached at the future time. In summary, at least one condition prediction may be made based on the current driving state, and at least one predicted driving state may be derived.

In addition, a plurality of obstacle vehicles exist on the target lane, and a plurality of lane change spaces can be determined. Meanwhile, as described in the previous example, at least one predicted environmental state may exist per lane change space.

The current driving state may be combined with any one of the predicted driving states and any one of the predicted environmental states to form a state combination. The current driving state is the same in each state combination.

And screening the state combinations to obtain target combinations, wherein the target combinations are used for determining that the current vehicle is converted into the target combinations from the current driving state to predict the driving state, and converting into the lane changing space of the predicted environment state in the target combinations to realize the driving conversion from the current lane to the target lane.

The status combinations may be selected according to the feasibility of the status combination, according to the driving cost, according to the driving stability, or according to a combination of at least two of the foregoing.

And S104, indicating the current vehicle to run in the predicted running state in the target combination at the future time, running along the lane change route corresponding to the predicted environment state in the target combination, and changing to the target lane to run.

The predicted travel state in the target combination may refer to a travel state that the current vehicle reaches at a future time, for controlling the current vehicle to reach the predicted travel state at the future time from the current travel state. The predicted environment state in the target combination may be an environment state of a lane-changing space formed by an obstacle vehicle influencing the current vehicle to change to the target lane at a future time, and is used to instruct the current vehicle to enter the lane-changing space corresponding to the predicted environment state by using the predicted driving state as an initial state, so as to instruct the current vehicle to change to the target lane for driving. The lane change route refers to a route from a predicted driving state to a lane change space in a predicted environment state. For example, the starting point of the lane-changing route may be a position in the predicted driving state, and the ending point of the lane-changing route may be the center of the lane-changing space in the predicted environmental state, for example, the lane-changing space is a rectangular parallelepiped, the center of the lane-changing space is a central symmetrical point of the rectangular parallelepiped, and route planning is performed according to the starting point and the ending point to form the lane-changing route.

In the prior art, when an automatic driving vehicle runs on a general road, a situation that a lane change is required often occurs, but an obstacle on a target lane may cause the lane change not to satisfy a condition. For example, when the host vehicle has an obstacle laterally arranged side by side, it is difficult to succeed in directly making a lane change.

According to the technical scheme, the current driving state of the current vehicle at the current moment and the driving state of an obstacle vehicle on a target lane are obtained, the predicted driving state of the current vehicle at the future moment and the predicted environment state of a lane change space on the target lane are predicted, the current driving state is combined into a plurality of state combinations, the state combinations are screened to obtain target combinations, the current vehicle is indicated to drive to reach the predicted driving state in the target combinations, the predicted driving state in the target combinations is taken as a starting point, the vehicle drives along a lane change route corresponding to the predicted environment state in the target combinations, the vehicle accurately changes to the target lane in time, the vehicle can continue to drive under the condition that the lane change of the target lane is influenced, the lane change is carried out at a certain moment in the future, the condition that the lane change fails due to the fact that the lane change cannot be carried out at the moment can be avoided, the lane change success rate is improved, and the lane change safety is improved.

Fig. 3 is a flowchart of another vehicle lane change method disclosed according to an embodiment of the present disclosure, which is further optimized and expanded based on the above technical solution, and can be combined with the above various alternative embodiments. The at least one predicted driving state of the current vehicle at the predicted future time is embodied as: acquiring the driving performance range of the current vehicle; determining the driving position range of the current vehicle at the future moment according to the driving performance range of the current vehicle and the current driving state; sampling in the driving position range and sampling in the driving performance range, and combining to determine at least one predicted driving state.

S301, acquiring the current running state of the current vehicle at the current moment.

And S302, acquiring the running performance range of the current vehicle.

The driving performance range may refer to a numerical range of driving performance that can be achieved by the current vehicle. The driving performance may refer to a real-time operation parameter during the current vehicle driving. The driving performance may include the speed and/or acceleration of the vehicle, etc. The driving performance range may be determined based on information such as an attribute of the vehicle, a driving manner of the vehicle set by a user, and a constraint condition for driving the vehicle. The attribute information of the vehicle refers to the performance of the vehicle itself, for example, the maximum speed can reach 200, and the driving performance range of the vehicle can be 0-200. The vehicle driving manner set by the user may be a vehicle driving manner determined based on a user demand, for example, the vehicle driving manner is a sport type, and the corresponding driving performance range may be a speed of 0 to 120, or, for example, the vehicle driving manner is a stable type, and the corresponding driving performance range may be a speed of 0 to 80. The constraint condition may be a performance range determined based on information such as safety and user experience of the vehicle, for example, a driving performance range of acceleration is (-20) -20.

And S303, determining the driving position range of the current vehicle at a future moment according to the driving performance range of the current vehicle and the current driving state.

The travel position range may refer to a range of predicted positions of the current vehicle at a future time. The driving performance range is a range that defines the achievable driving performance of the present vehicle during the course from the present time to the future time. That is, the variation range of the current running state is the running performance range constraint. The current running state is constrained to vary within the range of the running performance from the current time until the future time, whereby based on the current running state and the range of the running performance, the maximum distance and the minimum distance traveled by the current vehicle can be determined, thereby determining the range of the running position of the current vehicle at the future time. It should be noted that the driving position may be directly represented by the distance traveled by the current vehicle from the current time to the future time.

For example, the driving position range may be determined by calculating the driving position based on the current driving state and the extreme value or the end value of the driving performance range and filtering out the extreme value or the end value of the driving position range.

S304, sampling in the driving position range and sampling in the driving performance range, and combining to determine at least one predicted driving state.

The sampling in the driving position range and the sampling in the driving performance range can be randomly combined to form at least one predicted driving state. Illustratively, the travel position ranges from 10-60, and 10, 30, and 50 may be sampled. The driving performance range includes speed: 5-9, samples may result in 5 and 9, accelerations include (-3) -3, samples may result in-2, 0, 1, and 2. The predicted travel states formed by the combination may include: travel position 10, speed 5, acceleration-2. As another example, the predicted travel states formed by the combination may include: travel position 30, speed 5, acceleration-2.

In addition, the predicted driving states can be screened, and actually, some predicted driving states formed by combination cannot be converted from the current driving state. These infeasible predicted travel states may be eliminated.

Specifically, the driving position, speed and acceleration in a predicted driving state, the time and the current position in the current driving state may be obtained, and a fifth-order polynomial may be obtained, so that a plurality of times in the driving process from the current time to the future time and corresponding driving positions, speeds and accelerations may be calculated, and a driving route corresponding to the predicted driving state may be determined. The predicted driving state corresponding to the driving route may be screened based on whether the speed and acceleration of the driving route at each time point belong to the driving performance range and whether the driving route will collide with the preceding vehicle or the following vehicle of the current lane at each time point. For example, a driving route with at least one condition that the speed does not belong to the driving performance range, the acceleration does not belong to the driving performance range, and the vehicle can collide with the current lane is obtained, and the corresponding predicted driving state is removed.

And S305, predicting the predicted environment state of the lane change space on the target lane at the future moment.

S306, combining the current running state, each predicted running state and the predicted environment state to obtain a state combination, and screening to obtain a target combination.

Optionally, the screening to obtain a target combination includes: for each state combination, detecting the trafficability of the current vehicle to change lane to the lane change space according to the predicted running state of the current vehicle and the predicted environment state of the lane change space; and screening each state combination according to the trafficability detection result to obtain a target combination.

The trafficability detection result may be a detection result of whether the current vehicle can shift from the current lane to the lane change space on the target lane in the predicted travel state. The trafficability detection result includes trafficability and non-trafficability. The state combinations are screened to obtain target combinations, and the state combinations which can be passed can be determined as the target combinations, and the state combinations which can not be passed can be removed.

The result of the trafficability detection may be determined by detecting safety of whether the current vehicle of the predicted traveling state can travel to the lane change space. In a specific example, for a state combination, calculating the safe longitudinal distance between the current vehicle and the front vehicle in the lane change space and the safe longitudinal distance between the current vehicle and the rear vehicle in the lane change space, accumulating and summing the safe longitudinal distances, comparing the sum of the safe longitudinal distances with the relative distance between the front vehicle and the rear vehicle in the predicted environmental state, and determining the trafficability detection result of the state combination according to the comparison result. Determining the trafficability detection result of the state combination as trafficable under the condition that the relative distance is greater than or equal to the sum of the safe longitudinal distances; and determining that the traffic detection result of the state combination is not passable under the condition that the relative distance is less than the sum of the safe longitudinal distances.

Illustratively, the safe longitudinal distance sum S1 is calculated based on the following formula:

S1＝(v_dst-v_obst)*t_dst_thr+max(t_thw*v+v_diff*t_ttc,0.0)

the minimum speed of the front vehicle of the target lane is v _ dst _ min, the minimum speed of all the front vehicles in each state combination can be counted, the preset running speed of the current vehicle on the target lane is v _ dst _ cruise, and the minimum speed of the front vehicle and the preset running speed is v _ dst _ cruise; v _ obst is the speed of the vehicle in front of the current lane, and t _ dst _ thr, t _ thw and t _ ttc are set time parameters; the driving style selected manually by t _ dst _ thr is related, and t _ thw is the time when the front vehicle brakes suddenly and collides with the current vehicle; t _ ttc is the time when the vehicle runs at the current speed without sudden braking and the preceding vehicle collides with the current vehicle; thw and ttc are determined according to the speed limit, the reaction time, the driving style and the like of the traffic rule; the vehicle speed control method comprises the following steps of obtaining a front vehicle speed v _ front, a front vehicle relative speed v _ diff = v-v _ front, a rear vehicle speed v _ back and a rear vehicle relative speed v _ diff = v _ back-v.

The distance in the predicted environmental state is calculated based on the following formula:

d_dst+v_front*(t-t0)+0.5*a_front*(t-t0)^2-v_back(t-t0)-0.5*a_back*(t-t0)^2

wherein t0 is the current time, t is the future time, a _ front vehicle acceleration and a _ back rear vehicle acceleration. d _ dst is the longitudinal distance of the current environment state of the lane change space at the current moment, and is obtained by detecting the distance between the front vehicle position and the rear vehicle position. The longitudinal distance is a direction parallel to the lane, and the transverse distance is a direction perpendicular to the lane.

And the state combination is screened through the trafficability detection result, so that the target combination for detecting the lane change is realized, the lane change accuracy is improved, and the lane change safety is improved.

Optionally, the screening, according to the trafficability detection result, each state combination to obtain a target combination includes: screening each state combination according to the trafficability detection result to obtain an alternative combination; for each of the alternative combinations, determining a planned route from the current travel state to the predicted environmental state based on the current travel state, the predicted travel state, and the predicted environmental state; for each alternative combination, calculating the weight of the alternative combination according to the planned route and the predicted environmental state; and screening each alternative combination according to the weight of each alternative combination to obtain a target combination.

The alternative combination may be a state combination of variable lanes. And further screening the alternative combinations according to the weight, and actually screening the optimal target combination. The candidate combinations are usually screened according to the weight for screening out the target combination which is safest and most stable to drive. The planned route refers to a route determined by taking a current position in a current driving state as a starting point and a driving position in a predicted driving state as an end point, and determines driving states, such as speed, acceleration, driving position and the like, of each position point on the route based on the current driving state as an initial state and the predicted driving state as an end state.

For each alternative combination, a planned route may be determined based on the current driving state and the predicted driving state. And determining the lane change route according to the predicted driving state and the predicted environment state. The lane change course refers to a course that travels from a current lane to a lane change space in a predicted environment state in a predicted travel state. And carrying out statistics on the weight of the planned route and the weight of the lane change space in the prediction environment state, carrying out weighted summation, and calculating to obtain the weight of the alternative combination. Or counting the weight of the planned route and the lane change route, and counting the weight of the lane change space in the prediction environment state, carrying out weighted summation, and calculating to obtain the weight of the alternative combination. The weight of the statistically planned route and the lane change route may be calculated by counting the travel cost of the route.

Specifically, the weight of the actual route is used for describing the stability and complexity of the vehicle running, and the weight of the space is used for describing the lane change safety of the driving into the lane change space. The calculated weights of the alternative combinations are thus used to describe driving stability, driving complexity and lane change safety in the lane change mode of the alternative combinations. Generally, the higher the complexity of a driving route, the more frequent the state change, the larger the variation, the higher the driving cost and the larger the weight; the lower the complexity of the travel route, the less the state change, the smaller the amount of change, the lower the travel cost, and the smaller the weight. The weight of the statistical lane change space can be calculated by the safety of the statistical lane change space. Generally, the larger the longitudinal distance of a lane change space is, the farther a front obstacle vehicle and a rear obstacle vehicle are, the closer the distance between the lane change space and a current lane is, the higher the safety is, and the smaller the weight is; the smaller the longitudinal distance of the lane change space is, the closer the front and rear obstacle vehicles are, the farther the distance between the lane change space and the current lane is, the lower the safety is, and the larger the weight is.

For example, the weights of the planned route and the lane-change route may be determined by weighted summation of at least one of the travel time length of the route, the acceleration of the route, and the acceleration integral value. The weight of the lane change space in the prediction environment state can be determined by weighted summation according to at least one item of longitudinal distance between the front vehicle and the rear vehicle, speed difference between the front vehicle and the rear vehicle, distance between the space and the current vehicle and the like.

Indeed, the above example indicates that the greater the weight, the less safe the ride and the more difficult the ride; the lower the weight, the safer and simpler the ride. In addition, the weight may be set to be small, and the driving is safer, and may be specifically set as needed, which is not particularly limited.

According to the weights of the candidate combinations, the candidate combination with low driving cost and high safety is screened out, for example, the candidate combination with the lowest driving cost and the highest safety can be selected as the target combination, and the target combination can be determined. If there are more than one, one of the numbers can be randomly selected to be determined as the target combination. If the target combination is empty, the driving performance range and the driving position range can be sampled again, namely the predicted driving state is determined again, the alternative combination is correspondingly determined again, and the target combination is obtained through screening. If the target combination is empty for multiple resampling and screening, the future time may be adjusted and may be delayed, for example, from 3 seconds to 5 seconds.

Through the alternative combination screened according to the trafficability detection result, a more stable and safe driving route is screened out according to the planned route and the predicted environment state, the lane-changing driving mode is simplified, and the lane-changing safety is improved.

And S307, indicating the current vehicle to run in the predicted running state in the target combination at the future time, running along the lane change route corresponding to the predicted environment state in the target combination, and changing to the target lane for running.

Optionally, the current vehicle is an autonomous vehicle.

The disclosed embodiments are applied to an autonomous vehicle. Instructing the current vehicle to travel at a future time in the predicted travel state in the target combination and to travel along the lane change route corresponding to the predicted environmental state in the target combination to change to the target lane may include controlling the current vehicle to travel at the future time in the predicted travel state in the target combination and to travel along the lane change route corresponding to the predicted environmental state in the target combination to change to the target lane.

The method comprises the steps of detecting the future time of lane changing of an automatic driving vehicle, determining the predicted driving state corresponding to the future time, controlling the current vehicle to reach the predicted driving state, driving into a lane changing space under the condition that the predicted environmental state is feasible based on the predicted environmental state of the lane changing space determined by the predicted surrounding vehicles, increasing the possibility of the current vehicle changing the lane in the future, improving the lane changing success rate, and improving lane changing safety and driving safety.

According to the technical scheme, the driving position range of the current vehicle at the future moment is calculated by acquiring the driving performance range of the current vehicle and combining the current driving state, the driving position range and the driving performance range are respectively sampled, and the sampling results are combined to form a plurality of predicted driving states, so that the driving flexibility and diversity of the vehicle can be improved, the driving state of the current vehicle at the future moment is increased, the possibility of lane change at the future moment is increased, the success rate of lane change at the future moment is improved, and the rapid lane change is realized.

Fig. 4 is a flowchart of another vehicle lane change method disclosed according to an embodiment of the present disclosure, which is further optimized and expanded based on the above technical solution, and can be combined with the above various alternative embodiments. The driving along the lane change route corresponding to the predicted environment state in the target combination is changed to the driving on the target lane, and the method is embodied as follows: acquiring a dangerous area of a target vehicle associated with the predicted environment state in the target combination on a target lane; determining a buffer area and the weight of a position point included in the buffer area according to the dangerous area; determining a lane change terminal according to the predicted environment state in the target combination; generating a lane change route corresponding to the predicted environmental state in the target combination by taking a position corresponding to the predicted driving state in the target combination as a starting point, taking the lane change terminal point as a terminal point and according to the weight of a position point included in a buffer area on the target lane; instructing the current vehicle to travel along the lane change route to the target lane.

S401, the current running state of the current vehicle at the current moment is obtained, and at least one predicted running state of the current vehicle at the future moment is predicted.

S402, predicting the predicted environment state of the lane change space on the target lane at the future moment.

And S403, combining the current running state, each predicted running state and the predicted environment state to obtain a state combination, and screening to obtain a target combination.

And S404, indicating the current vehicle to run in the predicted running state in the target combination at the future time.

S405, acquiring a dangerous area of the target vehicle associated with the predicted environment state in the target combination on the target lane.

And under the condition that the current vehicle changes the lane to the position corresponding to the predicted running state in the target combination, detecting the obstacle vehicle related to the predicted environment state on the target lane in real time. The detection is performed in order to perform real-time route planning in real time, so as to ensure the accuracy of the route and improve the lane change safety.

The target vehicle associated with the predicted environmental state in the target combination means two obstacle vehicles forming a lane change space in the predicted environmental state. The dangerous area refers to an area where the vehicle cannot pass around the obstacle, and if the current vehicle travels to the dangerous area, the current vehicle collides with the obstacle, resulting in an accident.

Wherein the danger zone can be detected by the length of the collision. For example, according to the foregoing example, the sum of the safe longitudinal distances may be calculated, and the safe region may be determined in the lane change space under the predicted environmental condition, where the longitudinal distance of the safe region is equal to the sum of the safe longitudinal distances. And determining other regions in the lane change space in the predicted environmental state outside the safe region as dangerous regions.

S406, determining a buffer area and the weight of the position point included in the buffer area according to the dangerous area.

The buffer area refers to an area where the current vehicle can pass but needs to leave in time. The danger zone is at a greater risk level than the buffer zone. In practice, the lane change space may be divided into three regions: safe area, buffer area and danger area. The safe area is an area where the vehicle can currently pass through, and is also the safest area. The dangerous area is an area where the vehicle is currently impassable, and is also the most dangerous area. The buffer area refers to an area between the safe area and the dangerous area. In fact, in some limit situations, the vehicle in front of the current lane and the target vehicle are both close to the current vehicle, and when the vehicle needs to change lanes at the moment, the planned trajectory of the vehicle may intersect the buffer area, but the planned trajectory is close to the edge of the buffer area as much as possible, the intersection with the buffer area is as small as possible, and the vehicle can leave the buffer area in time in the case of being capable of leaving. The weight of a location point comprised by the buffer area is used to describe the risk level of the location point. Generally, the closer the position point is to the target vehicle, the more dangerous the position point is, and the less the vehicle is recommended to pass; the farther the location point is from the target vehicle, the safer the location point is, the more the vehicle is recommended to pass, and the weight is set accordingly. For example, the weight of the location points included in the buffer area may be set to be the same value, 0 or the highest value, or the weight of the location points included in the buffer area may be set to be proportional to the distance of the target vehicle, for example, inversely proportional, and the closer the distance, the greater the weight, the more dangerous; the further away the distance, the smaller the weight, the safer. As shown in fig. 5, a region 61 (hatched region) is a dangerous region, and a region 62 (vertical region) is a buffer region. The buffer area 62 is located outside the dangerous area 61, and the areas outside the buffer area 62 and the dangerous area 61 are safe areas. The buffer area 62 may be passed by the front vehicle 11 when changing to the target lane.

Illustratively, determining the buffer area according to the danger area includes: and expanding outwards outside the dangerous area, and determining the expanded area as a buffer area.

And expanding the area with the preset area size outwards, and determining the area with the preset area size as a buffer area. The area size can be obtained according to the statistics of relevant experiments of safe collision lane change. For example, the zone longitudinal dimension is half of the target vehicle body.

As another example, determining a buffer region based on the hazardous area includes: and adjusting the collision duration of the determined dangerous area, and determining the area as the dangerous area based on the difference set between the area determined by the adjusted collision duration and the dangerous area.

According to the previous example, the sum of the first safe longitudinal distances is calculated according to the first collision duration (t _ thw and t _ ttc), the dangerous area is determined, the first collision duration is reduced to obtain the second collision duration, the sum of the second safe longitudinal distances is calculated to obtain the alternative area, and the difference set between the dangerous area and the alternative area is calculated to obtain the buffer area.

In fact, the buffer setting is mainly related to the error of the current vehicle sensing system, the current vehicle sensing system needs to provide an error model of the current vehicle under each condition, and the buffer setting is generally the maximum value of the sensing error. The zone size and the second collision duration (or the difference between the second collision duration and the first collision duration) are set according to the maximum value of the perceived error.

S407, determining a lane change terminal according to the predicted environment state in the target combination.

And selecting a position point in the lane change space under the prediction environment state, and determining the position point as a lane change terminal point. Illustratively, the lane change space is a cuboid, and a central symmetry point can be selected to be determined as a lane change end point. The center of gravity may also be selected to be determined as the lane change endpoint.

And S408, taking the position corresponding to the predicted driving state in the target combination as a starting point, taking the lane-changing terminal point as an end point, and generating a lane-changing route corresponding to the predicted environment state in the target combination according to the weight of the position point included in the buffer area on the target lane.

The lane-changing route can be planned according to the route starting point and the route emphasis point. The buffer area includes a weight of a location point for limiting a range in which the location point on the lane change route is located. For example, the location point on the lane change route may not be in the danger zone, but may be in the safety zone. For the buffer area, the position point on the lane change route is preferentially not in the buffer area, and in the case of having to pass through the buffer area, is preferentially in a safer position in the buffer area.

Optionally, the generating a lane change route corresponding to the predicted environmental state in the target combination by using the position corresponding to the predicted driving state in the target combination as a starting point, using the lane change end point as an end point, and according to the weight of the position point included in the buffer area on the target lane, includes: generating at least one alternative route by taking a position corresponding to a predicted driving state in the target combination as a starting point, taking the lane change terminal point as a terminal point and according to the dangerous area, wherein the distance between a position point in the buffer area and the target vehicle corresponds to the weight of the position point; determining the safety detection result of the alternative route according to the track points included by the alternative route and the weight of the position points in the buffer area; and screening to obtain the lane change routes according to the safety detection results of the alternative routes.

The alternative route is a route which is not intersected with the dangerous area, is obtained by planning by taking a position corresponding to the predicted driving state as a starting point and taking a lane-changing terminal point as a terminal point. There is at least one location point that is different for different alternative routes. The alternative route does not intersect the hazardous area. In fact, two target vehicles exist in the lane change space, and the distance between the position point and the target vehicle in the buffer area corresponds to the weight of the position point, which means the distance between the position point and the nearest target vehicle in the buffer area, and corresponds to the weight of the position point. The safety detection result is used for describing the safety of the alternative route.

According to the track points included by the alternative route and the weights of the position points in the buffer area, the weights of the track points included by the alternative route can be determined. And accumulating the weights of the track points included by the alternative route, so that the safety detection result of the alternative route can be calculated. And screening the alternative route corresponding to the safety detection result with the lowest risk and the highest safety, and determining the alternative route as the lane change route.

In a specific example, the buffer area includes location points whose weights are inversely proportional to distances of 1, 2, and 3, and correspondingly, the location points have weights of 10, 9, and 8. The track point of the three position points included in alternative route a is correspondingly the sum of the weights of the track points, i.e. the safety detection result, 10+9+8=27, and the safety detection result of alternative route B is 13. And selecting the alternative route B with the highest safety, namely the lowest numerical value safety detection result from the alternative route A and the alternative route B to be determined as the lane change route.

The method comprises the steps of generating a plurality of alternative routes, determining the weight of a position point in a buffer area in the alternative routes based on the weight of the position point in the buffer area, determining the safety detection result of the alternative routes, screening the alternative routes according to the safety detection result, reducing the probability of passing through the buffer area, and improving the safety of the lane-changing route.

Optionally, the generating a lane change route corresponding to the predicted environmental state in the target combination by using the position corresponding to the predicted driving state in the target combination as a starting point, using the lane change end point as an end point, and according to the weight of the position point included in the buffer area on the target lane, includes: determining the passing type of a buffer area according to the weight of the position point included in the buffer area on the target lane; sequentially determining track points passed by a lane change route by taking the position corresponding to the predicted driving state in the target combination as a starting point, taking the lane change end point as an end point and according to the passing type of the buffer area, wherein the positions of the track points correspond to the passing type of the buffer area; and forming the lane changing route according to the track points passed by the lane changing route.

The traffic type may include passable and non-passable. The positions of the track points correspond to the passing types of the buffer area, namely the buffer area can pass through, and the positions of the track points can be located in the buffer area; the buffer area is not accessible, and the positions of the track points cannot be located in the buffer area. Determining the traffic type of the buffer area according to the weight can be: counting the sum of the weights, and determining the passing type according to the comparison result between the weights and the first threshold value; or counting the number of the position points larger than the second threshold value, and determining the passing type according to the comparison result between the number and the third threshold value; alternatively, the traffic type is determined directly from the value of the weight of the location point comprised by the buffer area.

In a specific example, whether an alternative route that does not pass through a buffer area can be generated is detected, and in the case that an alternative route that does not pass through a buffer area can be generated, weights of location points included in the buffer area may be set to be 0; in the case where only an alternative route passing through the buffer area can be generated, the weights of the position points included in the buffer area may be set to be all 1. Under the condition that the weight is 0, determining that the passing type is passable; in the case where the weight is 1, it is determined that the traffic type is not traffic.

And planning the next track point by taking the position corresponding to the predicted driving state in the target combination as a starting point, and continuing to plan the next track point according to the next track point until the track change end point is planned. In the planning process, a plurality of selectable positions of the next track point can be provided, wherein one selectable position is located in the buffer area, and the other selectable position is located outside the buffer area. And determining which positions are selectable according to the passing type of the buffer area, selecting one position from the selectable positions, and determining the position of the next track point, thereby determining the next track point. Illustratively, the buffer area is accessible, one selected from three positions, the buffer area is not accessible, and one selected from two positions located outside the buffer area. And connecting the track points passed by the lane changing route to form the lane changing route.

The passing type of the buffer area is determined according to the weight of the position points, so that whether the positions of the track points are in the buffer area or not is restrained in the process of planning the track points one by one, a lane changing route which accords with the passing type of the buffer area is planned, and the driving safety of the lane changing route is improved.

S409, indicating the current vehicle to change to the target lane to travel along the lane change route.

In addition, in some cases, in order to save computing resources and ensure the stability of route planning, historical computing results are multiplexed. If the obstacle collision happens on the historical route, the planning needs to be carried out again, otherwise, the driving is continued by using the historical result. When the result is planned, the route can be planned by utilizing the method, and when whether the route collides with the target vehicle or not is judged, the buffer area is set to be a passing area, so that the processing capacity of sensing errors can be realized.

According to the technical scheme of the disclosure, the buffer area of the target vehicle on the target lane and the weight of the position point of the buffer area are detected, the route is determined according to the weight during route planning, lane changing can be prioritized, the situations that the route planning is unstable and fails due to sensing errors are processed under the condition that the safety is ensured, the target vehicle is far away during lane changing, the safety of the route can be improved, and therefore lane changing safety is improved.

Fig. 6 is a flowchart of another vehicle lane change method disclosed according to an embodiment of the present disclosure, which is further optimized and expanded based on the above technical solution, and can be combined with the above various alternative embodiments. Before the current driving state of the current vehicle at the current moment is obtained, the following optimization steps can be performed: detecting an obstacle of the current vehicle on a current lane; detecting a driving state of an associated vehicle on a lane adjacent to the current lane in the presence of a current obstacle affecting traffic efficiency of the current vehicle; detecting adjacent lanes of the lane-changing according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle; and determining a target lane according to the adjacent lanes of the variable lane.

And S601, detecting the obstacle of the current vehicle on the current lane.

Obstacles include moving objects and stationary objects. An obstacle mainly refers to an object in front of the current lane. Whether an obstacle exists in front of the current lane can be detected through an image acquisition device of the current vehicle, or whether an obstacle exists in front of the current lane can be acquired through a navigation application.

S602, under the condition that a current obstacle influencing the passing efficiency of the current vehicle exists, detecting the running state of the related vehicle on the adjacent lane of the current lane.

The traffic efficiency is used to determine whether the current vehicle is able to continue traveling at the current speed. It is understood that the traffic efficiency is influenced by the traffic condition of congestion and/or the traffic scene of the traffic speed pressed by the vehicle in front of the current lane. The current obstacle refers to an obstacle that affects the passing efficiency of the current vehicle. Illustratively, the current obstacle is a fixed obstacle, such as a warning sign. As another example, the current obstacle is a preceding vehicle that travels at a decelerated speed. The adjacent lanes of the current lane refer to the left and right lanes of the current vehicle. The associated vehicle refers to a vehicle traveling on an adjacent lane.

Specifically, it is possible to detect whether there is a current obstacle affecting the traffic efficiency of the current vehicle, based on the running state of the vehicle ahead of the current lane and the current running state. Illustratively, 1, detecting whether the speed of a vehicle in front of a current lane is lower than the difference between a speed limit and a longitudinal speed threshold, wherein the speed limit is determined by policies (such as intersection rules), vehicle properties, safety, experience feeling and the like, and the longitudinal speed threshold can be 10km/h. (ii) a 2. Detecting whether the acceleration of a vehicle in front of a current lane is smaller than a first acceleration threshold value; 3. detecting whether the transverse speed of a vehicle in front of a current lane is greater than a transverse speed threshold value; 4. at 1-3, and the duration is greater than the duration threshold, it is determined that there is a current obstacle affecting traffic efficiency.

S603, detecting adjacent lanes of the variable lane according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle.

The adjacent lane of the lane change means an adjacent lane which is clear and has a space of the lane change. And detecting whether the adjacent lane is a lane-changeable space according to the driving state of the associated vehicle and the current driving state, thereby detecting the adjacent lane of the lane-changeable space.

Optionally, the detecting an adjacent lane of a lane-change lane according to the driving state of the associated vehicle at the current time and the current driving state of the current vehicle includes: detecting an adjacent lane with unobstructed traffic according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle; detecting a longitudinal distance between at least one pair of adjacent associated vehicles on an unobstructed adjacent lane of traffic in the presence of the unobstructed adjacent lane of traffic; and detecting adjacent lanes of the variable lane in the adjacent lanes with unobstructed traffic according to the longitudinal distance between each pair of adjacent associated vehicles.

Traffic unobstructed is used to describe whether there are obstacles in front of adjacent lanes that affect traffic efficiency. Whether the adjacent lanes have smooth traffic can be detected by detecting the associated vehicle positioned in front of the current vehicle on the target lane and based on the running state of the associated vehicle in front, the running state of the vehicle in front of the current lane and the current running state. Specifically, 5, the minimum speed in at least one associated vehicle in front of the current vehicle in the target lane is detected, the preset cruising speed of the current vehicle in the target lane is detected, and the minimum speed is determined from the minimum speed and the preset cruising speed. The running speed of the vehicle in front of the current lane is acquired. It is detected whether the minimum speed is greater than the sum of the travel speed of the vehicle in front of the current lane and a longitudinal speed threshold. 6. Whether the acceleration of the nearest associated vehicle ahead of the current vehicle of the target lane is greater than a second acceleration threshold. 7. Calculating the product of the difference between the minimum driving speed of the target lane and the speed of the vehicle in front of the current lane and a preset time length (such as the previous example t _ dst _ thr), calculating the difference between the product and the longitudinal distance between the vehicle in front of the current lane and the current vehicle, and detecting whether the longitudinal distance between the nearest vehicle in front of the target lane and the current vehicle is greater than the difference of the longitudinal distances, namely detecting based on the following formula:

d_dst>d_obst–(v_dst–v_obst)*t_dst_thr

and in the case that all the results are 5-7, determining that the traffic is smooth.

Whether the multiple adjacent lanes are smooth or not can be judged at the same time, or the adjacent lanes are judged one by one according to priority, for example, a left lane is judged preferentially, and then a right lane is judged.

The target lane of the lane-changing is actually a space on the target lane where the lane-changing is possible. That is, the longitudinal distance between adjacent associated vehicles on the lane of lane-changing target is enough to change lane. The longitudinal distance between at least one pair of adjacent associated vehicles on the adjacent lanes can be detected, and the longitudinal distance of the lane-changing can be detected according to the longitudinal distances, so that whether the adjacent lanes are lane-changing can be detected.

Detecting whether the longitudinal distance between adjacent associated vehicles is greater than a preset longitudinal distance threshold, for example, calculating the longitudinal distance threshold D based on the following formula:

D＝d_min+max(t_thw*v+v_diff*t_ttc,0.0)

and acquiring adjacent lanes with longitudinal distances larger than a preset longitudinal distance threshold, and determining a target lane from the adjacent lanes. And under the condition that the adjacent lanes with the longitudinal distance larger than the preset longitudinal distance threshold value comprise a left lane, determining that the left lane of the current lane is the target lane. And under the condition that the adjacent lanes with the longitudinal distance larger than the preset longitudinal distance threshold value only comprise the right lane and are not close to the junction position point, determining that the right lane of the current lane is the target lane. And determining that the target lane is empty when the adjacent lanes with the longitudinal distance larger than the preset longitudinal distance threshold value only comprise the right lane and are close to the junction position point.

The lane changing method has the advantages that the smooth traffic is detected, the adjacent lane of the lane changing is detected, the lane changing method is determined to be the target lane, the lane changing passing efficiency and the lane changing success rate can be improved, and accordingly the driving efficiency is improved.

In a specific example, as shown in fig. 7, when the current vehicle 11 is traveling in the current lane, it is first detected whether the vehicle 21 in front of the current lane affects the traffic efficiency of the current vehicle 11, and in the case of the effect, it is detected whether the left lane is clear, specifically, it is required to detect whether the vehicle 51 and the vehicle 21 affect the traffic efficiency of the current vehicle 11, and in the case of the left lane is clear, it is detected whether there is a lane-changing area of the current vehicle 11 between the vehicle 31 and the vehicle 51.

And S604, determining a target lane according to the adjacent lane of the variable lane.

And determining a target lane according to the type and the number of adjacent lanes of the variable lane. In the case where the number of adjacent lanes of the variable lane is only one, the adjacent lane is determined as the target lane. And under the condition that the number of the adjacent lanes of the variable lane is multiple, selecting the adjacent lane with the high priority according to the type of the adjacent lane, and determining the adjacent lane as the target lane. And under the condition that the current vehicle is adjacent to the merging and merging position, the number of the adjacent vehicles of the variable lane is only one, and the adjacent vehicles are the right lane of the current lane, so that the target lane is determined to be empty.

S605 acquires the current running state of the current vehicle at the current time, and predicts at least one predicted running state of the current vehicle at a future time.

The method includes detecting whether a current vehicle can change to a target lane at a current time, and predicting at least one predicted driving state of the current vehicle at a future time and predicting a predicted environmental state of a lane change space on the target lane at the future time if the lane change cannot be made. In the case of lane change, a lane change route is determined, and the vehicle is instructed to change from the current lane to the target lane along the lane change route.

S606, predicting the predicted environment state of the lane change space on the target lane at the future moment.

And S607, combining the current driving state, each predicted driving state and the predicted environment state to obtain a state combination, and screening to obtain a target combination.

And S608, indicating the current vehicle to run in the predicted running state in the target combination at the future time, running along the lane change route corresponding to the predicted environment state in the target combination, and changing to the target lane to run.

According to the technical scheme, under the condition that a current obstacle influencing the current vehicle passing efficiency exists, whether an adjacent lane of a lane-changing area exists or not is detected, a target lane is determined, and the predicted running state and the predicted environment state of the current vehicle are triggered and detected, so that the vehicle enters a lane-changing space at the future moment, the vehicle is changed to the target lane to run, the passing efficiency of the vehicle can be improved, the influence of the congestion condition on the vehicle is reduced, and the running stability of the vehicle is improved.

Fig. 8 is a structural diagram of a vehicle lane change device in an embodiment of the present disclosure, which is applied to a case of indicating a vehicle lane change, according to an embodiment of the present disclosure. The device is realized by software and/or hardware and is specifically configured in electronic equipment with certain data operation capacity.

A lane-changing apparatus 800 for a vehicle shown in fig. 8 includes: an image acquisition module 801, a fusion feature acquisition module 802, an image transformation module 803 and a vehicle lane changing module 804; wherein, the first and the second end of the pipe are connected with each other,

a driving state prediction module 801 configured to obtain a current driving state of a current vehicle at a current time and predict at least one predicted driving state of the current vehicle at a future time;

a lane change environment state prediction module 802, configured to predict a predicted environment state of a lane change space on the target lane at the future time;

a state combination screening module 803, configured to combine the current driving state, each of the predicted driving states, and the predicted environment state to obtain a state combination, and screen to obtain a target combination;

and the lane change driving module 804 is configured to instruct the current vehicle to drive in the predicted driving state in the target combination at the future time, and to drive along a lane change route corresponding to the predicted environmental state in the target combination, so as to change to the target lane for driving.

Further, the driving state prediction module 801 includes: a driving performance range acquisition unit configured to acquire a driving performance range of the current vehicle; a driving position range obtaining unit, configured to determine a driving position range of the current vehicle at a future time according to the driving performance range of the current vehicle and the current driving state; and a predicted travel state acquisition unit for sampling in the travel position range and sampling in the travel performance range, and determining at least one predicted travel state in combination.

Further, the status combination screening module 803 includes: a trafficability detection unit configured to detect trafficability of the current vehicle to change lane to the lane change space according to a predicted running state of the current vehicle and a predicted environmental state of the lane change space for each of the state combinations; and the target combination screening unit is used for screening each state combination according to the trafficability detection result to obtain a target combination.

Further, the target combination screening unit includes: the alternative combination screening subunit is used for screening each state combination according to the trafficability detection result to obtain an alternative combination; a route planning subunit, configured to determine, for each of the candidate combinations, a planned route from the current driving state to the predicted environment state according to the current driving state, the predicted driving state, and the predicted environment state; a planned route subunit, configured to calculate, for each of the candidate combinations, a weight of the candidate combination according to the planned route and the predicted environmental state; and the target combination determining subunit is used for screening each alternative combination according to the weight of each alternative combination to obtain a target combination.

Further, the lane change environment state prediction module includes: the obstacle vehicle driving state acquisition unit is used for acquiring the driving state of the obstacle vehicle on the current target lane; a lane change space detection unit for determining a space between two adjacent obstacle vehicles as a lane change space; and the environment state prediction unit is used for predicting the predicted environment state of the lane change space at the future moment according to the running states of two adjacent obstacle vehicles at the current moment.

Further, the lane-changing driving module 804 includes: a dangerous area detection unit for acquiring a dangerous area of a target vehicle associated with the predicted environmental state in the target combination on a target lane; the buffer area detection unit is used for determining a buffer area and the weight of a position point included in the buffer area according to the dangerous area; the lane change terminal point determining unit is used for determining a lane change terminal point according to the predicted environment state in the target combination; a lane change route generation unit, configured to generate a lane change route corresponding to the predicted environmental state in the target combination, using a position corresponding to the predicted driving state in the target combination as a starting point, using the lane change end point as an end point, and according to a weight of a position point included in a buffer area on the target lane; and the lane change driving indicating unit is used for indicating the current vehicle to change to the target lane to drive along the lane change route.

Further, the lane change route generation unit includes: a candidate route generating subunit, configured to generate at least one candidate route by using a position corresponding to a predicted driving state in the target combination as a starting point, using the lane change destination as a destination, and according to the dangerous area, where a distance between a position point in the buffer area and the target vehicle corresponds to a weight of the position point; the driving cost calculating subunit is configured to determine a safety detection result of the alternative route according to the track points included in the alternative route and the weights of the position points in the buffer area; and the lane change route screening subunit is used for screening to obtain a lane change route according to the safety detection result of each alternative route.

Further, the lane change route generation unit includes: the traffic type detection subunit is used for determining the traffic type of the buffer area according to the weight of the position point included in the buffer area on the target lane; the point-by-point planning subunit is used for sequentially determining track points passed by a lane change route by taking the position corresponding to the predicted driving state in the target combination as a starting point, taking the lane change end point as an end point and according to the passing type of the buffer area, wherein the positions of the track points correspond to the passing type of the buffer area; and the lane changing route determining subunit is used for forming the lane changing route according to the track points passed by the lane changing route.

Further, the vehicle lane-changing device further includes: the obstacle detection module is used for detecting an obstacle of the current vehicle on a current lane; the adjacent lane vehicle detection module is used for detecting the running state of a related vehicle on an adjacent lane of the current lane under the condition that a current obstacle influencing the passing efficiency of the current vehicle exists; the adjacent lane changing detection module is used for detecting an adjacent lane of a variable lane according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle; a target lane detection module for determining a target lane according to adjacent lane of the lane-change

Further, the adjacent lane change detection module includes: the adjacent lane unobstructed detection unit is used for detecting an adjacent lane with unobstructed traffic according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle; the adjacent vehicle longitudinal distance unit is used for detecting the longitudinal distance between at least one pair of adjacent associated vehicles on the adjacent lane with unobstructed traffic under the condition that the adjacent lane with unobstructed traffic exists; and the lane-variable screening unit is used for detecting the lane-variable adjacent lanes in the adjacent lanes with unobstructed traffic according to the longitudinal distance between each pair of adjacent associated vehicles.

Further, the current vehicle comprises an autonomous vehicle.

The vehicle lane changing device can execute the vehicle lane changing method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects for executing the vehicle lane changing method.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 9 illustrates a schematic area diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901, which can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM) 902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.

A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 901 executes the respective methods and processes described above, such as the vehicle lane change method. For example, in some embodiments, the vehicle lane-change method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of the vehicle lane-change method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the vehicle lane change method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or area diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of changing lanes of a vehicle, comprising:

predicting the predicted environment state of the lane change space on the target lane at the future moment;

2. The method of claim 1, wherein the predicting at least one predicted driving state of the current vehicle at a future time comprises:

acquiring the driving performance range of the current vehicle;

determining the driving position range of the current vehicle at a future moment according to the driving performance range of the current vehicle and the current driving state;

sampling in the driving position range and sampling in the driving performance range, and combining to determine at least one predicted driving state.

3. The method of claim 1, wherein the screening results in a combination of targets comprising:

for each state combination, detecting the trafficability of the current vehicle to change lane to the lane change space according to the predicted running state of the current vehicle and the predicted environment state of the lane change space;

and screening each state combination according to the trafficability detection result to obtain a target combination.

4. The method of claim 3, wherein the screening each of the status combinations according to the trafficability detection result to obtain a target combination comprises:

screening each state combination according to the trafficability detection result to obtain an alternative combination;

for each of the alternative combinations, determining a planned route from the current travel state to the predicted environment state based on the current travel state, the predicted travel state, and the predicted environment state;

for each of the alternative combinations, calculating a weight for the alternative combination based on the planned route and the predicted environmental state;

and screening each alternative combination according to the weight of each alternative combination to obtain a target combination.

5. The method of claim 1, wherein said predicting the predicted environmental state of the lane-change space on the target lane at the future time comprises:

acquiring the running state of the obstacle vehicle on the target lane at the current moment;

determining a space between two adjacent obstacle vehicles as a lane change space;

and predicting the predicted environment state of the lane-changing space at the future moment according to the running states of two adjacent obstacle vehicles at the current moment.

6. The method of claim 1, wherein the driving along the lane-change route corresponding to the predicted environmental state in the target combination to the target lane comprises:

acquiring a dangerous area of a target vehicle associated with the predicted environment state in the target combination on a target lane;

determining a buffer area and the weight of a position point included in the buffer area according to the dangerous area;

determining a lane change terminal according to the predicted environment state in the target combination;

generating a lane change route corresponding to the predicted environmental state in the target combination by taking a position corresponding to the predicted driving state in the target combination as a starting point, taking the lane change terminal point as a terminal point and according to the weight of a position point included in a buffer area on the target lane;

instructing the current vehicle to travel along the lane change route to the target lane.

7. The method according to claim 6, wherein the generating of the lane-change route corresponding to the predicted environmental state in the target combination with the position corresponding to the predicted driving state in the target combination as a starting point, the lane-change end point as an end point, and the weight of the position point included in the buffer area on the target lane as a basis comprises:

generating at least one alternative route by taking a position corresponding to a predicted driving state in the target combination as a starting point, taking the lane change terminal point as a terminal point and according to the dangerous area, wherein the distance between a position point in the buffer area and the target vehicle corresponds to the weight of the position point;

determining the safety detection result of the alternative route according to the track points included by the alternative route and the weight of the position points in the buffer area;

and screening to obtain the lane change route according to the safety detection result of each alternative route.

8. The method according to claim 6, wherein the generating of the lane change route corresponding to the predicted environmental state in the target combination with the position corresponding to the predicted driving state in the target combination as a starting point, the lane change end point as an end point and the weight of the position point included in the buffer area on the target lane comprises:

determining the passing type of a buffer area according to the weight of the position point included in the buffer area on the target lane;

sequentially determining track points passed by a lane change route by taking the position corresponding to the predicted driving state in the target combination as a starting point, taking the lane change end point as an end point and according to the passing type of the buffer area, wherein the positions of the track points correspond to the passing type of the buffer area;

and forming the lane changing route according to the track points passed by the lane changing route.

9. The method of claim 1, further comprising:

detecting an obstacle of the current vehicle on a current lane;

detecting a driving state of an associated vehicle on a lane adjacent to the current lane in the presence of a current obstacle affecting traffic efficiency of the current vehicle;

detecting adjacent lanes of the lane-changing according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle;

and determining a target lane according to the adjacent lanes of the variable lane.

10. The method according to claim 9, wherein the detecting of the adjacent lane of the variable lane according to the traveling state of the associated vehicle at the present time and the present traveling state of the present vehicle includes:

detecting an adjacent lane with unobstructed traffic according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle;

detecting a longitudinal distance between at least one pair of adjacent associated vehicles on an unobstructed adjacent lane of traffic in the presence of the unobstructed adjacent lane of traffic;

and detecting adjacent lanes of the variable lane in the adjacent lanes with unobstructed traffic according to the longitudinal distance between each pair of adjacent associated vehicles.

11. The method of claim 1, wherein the current vehicle is an autonomous vehicle.

12. A vehicle lane-change device comprising:

and the lane change driving module is used for indicating the current vehicle to drive in the predicted driving state in the target combination at the future time, drive along a lane change route corresponding to the predicted environment state in the target combination and change to the target lane for driving.

13. The apparatus of claim 12, wherein the driving condition prediction module comprises:

a driving performance range acquisition unit configured to acquire a driving performance range of the current vehicle;

a driving position range obtaining unit, configured to determine a driving position range of the current vehicle at a future time according to the driving performance range of the current vehicle and the current driving state;

a predicted travel state acquisition unit for sampling in the travel position range and sampling in the travel performance range, and determining at least one predicted travel state in combination.

14. The apparatus of claim 12, wherein the status combination filtering module comprises:

a trafficability detection unit configured to detect trafficability of the current vehicle to change lane to the lane change space according to a predicted running state of the current vehicle and a predicted environmental state of the lane change space for each of the state combinations;

and the target combination screening unit is used for screening each state combination according to the trafficability detection result to obtain a target combination.

15. The apparatus of claim 14, wherein the target combination filtering unit comprises:

the alternative combination screening subunit is used for screening each state combination according to the trafficability detection result to obtain an alternative combination;

a route planning subunit, configured to determine, for each of the candidate combinations, a planned route from the current driving state to the predicted environment state according to the current driving state, the predicted driving state, and the predicted environment state;

a planned route subunit, configured to calculate, for each of the candidate combinations, a weight of the candidate combination according to the planned route and the predicted environmental state;

and the target combination determining subunit is used for screening each alternative combination according to the weight of each alternative combination to obtain a target combination.

16. The apparatus of claim 12, wherein the lane-change environmental state prediction module comprises:

the obstacle vehicle driving state acquisition unit is used for acquiring the driving state of the obstacle vehicle on the current target lane;

a lane change space detection unit for determining a space between two adjacent obstacle vehicles as a lane change space;

and the environment state prediction unit is used for predicting the predicted environment state of the lane change space at the future moment according to the running states of two adjacent obstacle vehicles at the current moment.

17. The apparatus of claim 12, wherein the lane-change traveling module comprises:

a dangerous area detection unit for acquiring a dangerous area of a target vehicle associated with the predicted environmental state in the target combination on a target lane;

the buffer area detection unit is used for determining a buffer area and the weight of a position point included in the buffer area according to the dangerous area;

the lane change terminal point determining unit is used for determining a lane change terminal point according to the predicted environment state in the target combination;

a lane change route generation unit, configured to generate a lane change route corresponding to the predicted environmental state in the target combination, with a position corresponding to the predicted driving state in the target combination as a start point, with the lane change end point as an end point, and according to a weight of a position point included in a buffer area on the target lane;

and the lane change driving indicating unit is used for indicating the current vehicle to change to the target lane to drive along the lane change route.

18. The apparatus of claim 17, wherein the lane change route generation unit comprises:

a candidate route generating subunit, configured to generate at least one candidate route by using a position corresponding to a predicted driving state in the target combination as a starting point, using the lane change destination as a destination, and according to the dangerous area, where a distance between a position point in the buffer area and the target vehicle corresponds to a weight of the position point;

the driving cost calculating subunit is configured to determine a safety detection result of the alternative route according to the track points included in the alternative route and the weights of the position points in the buffer area;

and the lane change route screening subunit is used for screening the lane change routes according to the safety detection results of the alternative routes.

19. The apparatus of claim 17, wherein the lane change route generation unit comprises:

the traffic type detection subunit is used for determining the traffic type of the buffer area according to the weight of the position point included in the buffer area on the target lane;

the point-by-point planning subunit is used for sequentially determining track points passed by a track changing route by taking the position corresponding to the predicted driving state in the target combination as a starting point, taking the lane changing end point as an end point and according to the passing type of the buffer area, wherein the positions of the track points correspond to the passing type of the buffer area;

and the lane changing route determining subunit is used for forming the lane changing route according to the track points passed by the lane changing route.

20. The apparatus of claim 12, further comprising:

the obstacle detection module is used for detecting an obstacle of the current vehicle on a current lane;

the adjacent lane vehicle detection module is used for detecting the running state of a related vehicle on an adjacent lane of the current lane under the condition that a current obstacle influencing the passing efficiency of the current vehicle exists;

the adjacent lane changing detection module is used for detecting an adjacent lane of a variable lane according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle;

and the target lane detection module is used for determining a target lane according to adjacent lanes of the lane-changing.

21. The apparatus of claim 20, wherein the adjacent lane change detection module comprises:

the adjacent lane smooth detection unit is used for detecting an adjacent lane with smooth traffic according to the running state of the associated vehicle at the current moment and the current running state of the current vehicle;

the adjacent vehicle longitudinal distance unit is used for detecting the longitudinal distance between at least one pair of adjacent associated vehicles on the adjacent lane with unobstructed traffic under the condition that the adjacent lane with unobstructed traffic exists;

and the lane-variable screening unit is used for detecting the lane-variable adjacent lanes in the adjacent lanes with unobstructed traffic according to the longitudinal distance between each pair of adjacent associated vehicles.

22. The apparatus of claim 12, wherein the current vehicle comprises an autonomous vehicle.

23. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle lane-change method of any one of claims 1-11.

24. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the vehicle lane-change method according to any one of claims 1-11.

25. A computer program product comprising a computer program which, when executed by a processor, implements a vehicle lane change method according to any one of claims 1-11.