CN115649191A - Vehicle lane change decision-making method and device, computer equipment and storage medium - Google Patents
Vehicle lane change decision-making method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115649191A CN115649191A CN202211245190.4A CN202211245190A CN115649191A CN 115649191 A CN115649191 A CN 115649191A CN 202211245190 A CN202211245190 A CN 202211245190A CN 115649191 A CN115649191 A CN 115649191A
- Authority
- CN
- China
- Prior art keywords
- lane
- track
- vehicle
- determining
- lane change
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The application relates to a vehicle lane change decision-making method, a vehicle lane change decision-making device, computer equipment and a storage medium. The method comprises the following steps: acquiring surrounding environment information of a vehicle; determining a track evaluation result of switching to a target lane based on the surrounding environment information; and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information. By the method, the target lane is subjected to the track evaluation and the lane change requirements from various sources are comprehensively considered, the optimal track result with higher safety can be output according to the real-time traffic condition, the safety, the reasonability and the real-time performance of the track result generated by the lane change intention decision and the lane change implementation decision are improved, and the adverse influence of lane change on traffic is reduced.
Description
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to a vehicle lane change decision method, an apparatus, a computer device, and a storage medium.
Background
With the concept of automatic driving, the core of the development of the whole field is an automatic driving system, which is known as a function of sensing the road environment through an on-vehicle sensing system, and controlling the steering, lane changing track and speed of a vehicle according to the road, vehicle position and obstacle information obtained by sensing, so that the vehicle can safely and reliably run on the road and reach a predetermined place.
The channel change decision in the Baidu Apollo platform in the current-stage automatic driving research and application is mainstream, the generation of the channel change intention in the decision scheme is basically obtained by analyzing high-precision map navigation information, a series of tracks are generated by sampling the end state, then the track evaluation is carried out, the decision algorithm is more like a track selector, and the track with the most front ranking is selected through different evaluation functions.
In the conventional technical scheme for the track change decision, the track change track is selected after being successfully calculated, and the comprehensive evaluation is lacked, so that the output track is not high in safety and poor in real-time performance.
Disclosure of Invention
In view of the above, it is necessary to provide a vehicle lane change decision method, device, computer device, and storage medium for solving the above technical problems.
In a first aspect, the present application provides a vehicle lane change decision method, including:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result for switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
In one embodiment, the obtaining the surrounding environment information of the vehicle includes:
at least one of road information, vehicle travel information, and peripheral obstacle information is acquired.
In one embodiment, the determining a result of trajectory evaluation for switching to a target lane based on the surrounding environment information previously includes:
determining a lane change demand and a target lane based on at least one of a user lane change instruction, preset navigation information and a vehicle driving state.
In one embodiment, the determining the lane change requirement and the target lane based on the vehicle driving state comprises:
acquiring the running speed of the vehicle;
if the vehicle running speed is less than a preset threshold value, estimating lane changing driving expectation of the left and right adjacent lanes;
the target lane is determined based on the evaluation result.
In one embodiment, the determining a result of the trajectory evaluation for switching to the target lane based on the surrounding environment information includes:
determining a plurality of candidate trajectories based on the target lane;
determining track stability based on the number of times each candidate track is determined as an optimal track within a preset time period;
determining lane changing efficiency of each candidate track based on the predicted lane changing time;
determining the influence degree of each candidate track based on the road occupation area of the target lane in the lane changing process;
determining the risk degree of each candidate track based on the collision probability with the front vehicle in the lane changing process;
and determining a track evaluation result of each candidate track based on track stability, lane changing efficiency, influence degree and risk degree.
In one embodiment, the determining the trajectory evaluation result of each candidate trajectory based on trajectory stability, lane change efficiency, influence degree and risk degree further includes:
carrying out weighted summation on the track stability, the lane changing efficiency, the influence degree and the risk degree to obtain an evaluation value of each candidate track;
determining an optimum trajectory as the trajectory evaluation result based on the evaluation value.
In one embodiment, the determining a lane change decision result based on the trajectory evaluation result, the user instruction, and the preset navigation information includes:
and if any one of the track evaluation result, the user instruction and the preset navigation information does not accord with a preset condition, the lane change decision result is that the lane is not changed.
In a second aspect, the application further provides a vehicle lane change decision device. The device comprises:
the acquisition module is used for acquiring surrounding environment information of the vehicle;
the evaluation module is used for determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and the decision-making module is used for determining a channel-changing decision-making result based on the track evaluation result, the user instruction and preset navigation information.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
The vehicle lane change decision method, the device, the computer equipment and the storage medium acquire the surrounding environment information of the vehicle; determining a track evaluation result of switching to a target lane based on the surrounding environment information; and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information. The optimal track result with higher safety can be output according to the real-time traffic condition, and the safety, the reasonability and the real-time performance of the final lane changing track are improved.
Drawings
FIG. 1 is a diagram of an exemplary implementation of a lane change decision method for a vehicle;
FIG. 2 is a schematic flow chart of a vehicle lane change decision method according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a lane change requirement and target lane determination of a vehicle lane change decision method in one embodiment of the invention;
FIG. 4 is a flow chart illustrating trajectory stability assessment in one embodiment of the present invention;
FIG. 5 is a schematic flow chart of a lane change decision result implementation of a vehicle lane change decision method according to an embodiment of the present invention;
FIG. 6 is a block diagram of a lane-change decision device for a vehicle according to an embodiment of the present invention;
fig. 7 is an internal structural diagram of a computer device in one embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The automatic driving system senses the road environment through a vehicle-mounted sensing system, and controls the steering, lane changing track and speed of the vehicle according to the road, vehicle position and obstacle information obtained by sensing, so that the vehicle can safely and reliably run on the road and reach a preset place.
The channel change decision in the Baidu Apollo platform in the current-stage automatic driving research and application is mainstream, the generation of the channel change intention in the decision scheme is basically obtained by analyzing high-precision map navigation information, a series of tracks are generated by sampling the end state, then the track evaluation is carried out, the decision algorithm is more like a track selector, and the track with the most front ranking is selected through different evaluation functions.
The vehicle lane change decision method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. A user makes a current behavior on the terminal 102, the terminal 102 transmits current behavior data to the server 104, and the server 104 acquires surrounding environment information of a vehicle; determining a track evaluation result for switching to a target lane based on the surrounding environment information; and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a vehicle lane change decision method is provided, and this embodiment is exemplified by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented by interaction between the terminal and the server.
In this embodiment, the method includes the steps of:
in step S201, the surrounding environment information of the vehicle is acquired.
The surrounding environment information of the vehicle is environment information that affects decisions such as traveling, lane change, turning, and the like of the target vehicle during automatic driving.
Specifically, the vehicle generates various data during traveling, which may include data of the host vehicle itself and data of obstacles around the host vehicle during traveling. Alternatively, data of the obstacle of the host vehicle itself and surrounding obstacles during driving can be acquired by sensors such as a GPS, an IMU, a camera, and a laser radar, and then information such as the type, position, and speed of the obstacle can be identified from the data by techniques such as artificial intelligence.
Step S202, determining the track evaluation result of switching to the target lane based on the surrounding environment information.
Specifically, after the vehicle surrounding environment information is determined, if lane changing is to be performed at present, a plurality of tracks are available for selection, a lane changing result according to each track can be predicted according to the environment information to judge feasibility of each track, and further track scoring estimation is performed on a track cluster under the scene in a preset time period to determine performability of each target lane.
Step S203, determining a lane change decision result based on the track evaluation result, the user instruction and the preset navigation information.
It can be understood that if the final lane change result is determined based on only one of the trajectory evaluation result, the user instruction and the preset navigation information, the determination is very comprehensive and the output result does not necessarily meet the requirement of real-time lane change, and the trajectory evaluation result, the real-time user instruction and the preset navigation information are analyzed in combination, so that the real-time situation before the final lane change is implemented can be comprehensively considered, and the accuracy of the final output lane change decision result is improved.
According to the vehicle lane change decision method, the peripheral environment information of a vehicle is obtained, a track evaluation result of switching to a target lane is determined based on the peripheral environment information, the track evaluation result is the evaluation of a target lane track cluster generated in a preset time period, the track evaluation result is combined and analyzed with a lane change requirement with a target track generated based on a real-time user instruction and real-time preset navigation information, a lane change decision result is finally output, an optimal track result with higher safety can be output according to the real-time traffic condition, and the safety, the reasonability and the real-time performance of the final lane change track are improved.
In one embodiment, the acquiring the surrounding environment information of the vehicle includes the following steps:
at least one of road information, vehicle travel information, and peripheral obstacle information is acquired.
It can be understood that road information such as the length and width of the lane where the vehicle is located and the adjacent lane in the space-time environment at the current time, the type of lane line, the road speed limit and the like are acquired;
acquiring vehicle running information such as vehicle position, speed, maximum and minimum acceleration and deceleration, user instructions and the like;
peripheral obstacle information such as the position, speed, predicted trajectory, and the like of an obstacle is acquired.
In other embodiments, other environmental information may also be obtained, which only has an influence on the vehicle running, and is not limited specifically here.
According to the embodiment, at least one of the peripheral environment information of the vehicle, such as road information, vehicle driving information and peripheral obstacle information, is acquired, the environment data influencing the lane change decision result is collected in a targeted manner, and the method is favorable for restoring the vehicle driving live environment as truly as possible so as to ensure the accuracy of the track evaluation result.
In one embodiment, the determining a result of the trajectory evaluation for switching to the target lane based on the surrounding environment information previously comprises:
determining a lane change demand and a target lane based on at least one of a user lane change instruction, preset navigation information and a vehicle driving state.
The lane change request generated based on the user lane change instruction and the preset navigation information is an external lane change request in a lane change scene belonging to a vehicle and is classified as an intention of passive lane change; and the lane change request generated based on the vehicle running state is classified as the active lane change intention.
Specifically, the automatic driving is not completely unmanned driving, so the lane change requirement in the driving process comes from two aspects, on one hand, the lane change requirement is automatically generated by the automatic driving system based on the vehicle running state of the current lane, for example, when the current lane is extremely congested, the lane change requirement is generated by the automatic driving system; on the other hand, the lane change command is not generated by the automatic driving system itself, but is from the lane change command of the user, or the lane change requirement is generated by the path planning of the navigation system.
It can be understood that the above embodiments comprehensively consider the lane change requirements in various aspects, and can effectively reduce the lane change decision conflict and improve the security of the lane change decision result.
In another embodiment, the determining the lane change request and the target lane based on the vehicle driving state includes:
acquiring the running speed of the vehicle;
if the vehicle running speed is less than a preset threshold value, estimating lane changing driving expectation of the left and right adjacent lanes;
determining a target lane based on the evaluation result.
Specifically, the running speed of the vehicle in the current lane is obtained, if the running speed of the vehicle is within a preset threshold range, the passing efficiency is in accordance with the expectation, no lane change requirement is generated, and the vehicle continues to run in the current lane; if the vehicle running speed is lower than the preset threshold value, it is indicated that the traffic efficiency of the lane is not high, and then lane-changing driving expectations of the left and right adjacent lanes are evaluated, wherein the lane-changing driving expectations comprise lane collision risks, lane violation risks, obstacle risks and the like. For example, the preset speed threshold is 30-60 km/h, and when the actually acquired vehicle running speed is within the range of 30-60 km/h, the vehicle continues to run in the current lane; and when the running speed of the vehicle is less than 30 kilometers per hour, estimating lane change driving expectation of the left and right adjacent lanes, generating a lane change requirement containing a target lane when the estimated lane has no collision risk, and maintaining the current lane to continue running when the estimated lanes have collision risks and do not generate the lane change requirement. For example, the driving speed may be a real-time speed at the current time, or an average speed within a preset time period, and may be set by a user according to an actual requirement, which is not specifically limited herein.
In other embodiments, the method further comprises the steps of obtaining the passing efficiency of the vehicle, and judging whether to evaluate the lane-changing driving expectation of the left and right adjacent lanes according to whether the passing efficiency meets a preset threshold value. The traffic efficiency refers to the matching degree of a forward space and a preset target speed in the running process of the vehicle. The forward space in the running process of the vehicle refers to the relative distance between the head of the vehicle and the tail of the front vehicle.
Referring to fig. 3, fig. 3 is a schematic flow chart illustrating a lane change requirement and a target lane determination of a vehicle lane change decision method according to an embodiment of the invention.
In this embodiment, the flow of the lane change request and the determination of the target lane includes:
step one, identifying a lane changing request or identifying preset navigation information by a user.
In this embodiment, the first step specifically includes identifying and confirming the lane change request or the preset navigation information of the user based on the acquired vehicle surrounding environment information, and when the lane change request or the preset navigation information of the user is identified, verifying that "condition 1, the target lane change lane exists and the lane change is allowed by the type of the road boundary", passing the verification, and entering the fourth step.
It can be understood that, in the condition 1, the existence of the target lane change lane means that the target lane change lane can pass, and the conditions of traffic control, road repair and the like which cannot pass do not exist; the road sideline type allowed lane change means that the broken line of the road sideline can change lanes, and the solid line can not change lanes.
And step two, judging the running state of the vehicle.
In the embodiment, the second step specifically includes acquiring the running speed of the vehicle in the current lane, and checking a condition 2, wherein the running speed of the vehicle is within a preset threshold range, which represents that the traffic efficiency is in accordance with the expectation, and if the checking is passed, the lane change requirement is not generated, and the vehicle continues to run in the current lane; if the vehicle running speed is less than the preset threshold value, the passing efficiency of the current lane is not high, and then the adjacent lane passing evaluation is carried out in the third step.
In an understandable condition 2, the judgment of the traffic efficiency of the lane is based on the vehicle running speed, and the longer the distance of the vehicle running in the current lane in unit time is, the higher the traffic efficiency of the lane is; the traffic efficiency can also be judged based on the matching degree of the forward space and the preset target speed in the running process of the vehicle.
And step three, evaluating the trafficability of the adjacent lane.
In this embodiment, the third step specifically includes evaluating lane change driving expectations of left and right adjacent lanes of the current driving lane to obtain an optimal lane change direction, and obtaining an adjacent lane trafficability evaluation result.
The result of the evaluation of the trafficability of the adjacent lane is the prediction of the driving condition from the lane change to the adjacent lane. Illustratively, the driving situation of the lane change to the left adjacent lane and the right adjacent lane is predicted, and the lane change feasibility is judged based on the prediction result. If the prediction result is that the lane changing to the left adjacent lane cannot normally run, the left adjacent lane is not suitable for lane changing, the lane changing to the right adjacent lane can normally run, the right adjacent lane is suitable for lane changing, and finally the lane changing direction is selected as the right side.
And step four, recommending the target lane.
In this embodiment, the fourth step specifically includes verifying "condition 3, that the adjacent lane assessment lane is passable" based on the lane change instruction of the user in the first step, the lane change request obtained by the preset navigation information, and the adjacent lane trafficability assessment result obtained in the third step, and generating a lane change request including the target lane if condition 3 is satisfied; if the verification is not passed, no lane change request is generated, and the current lane driving is continuously maintained.
It can be understood that, in condition 3, the adjacent lane evaluation lane can pass, which means that the lane has no collision risk, no lane changing violation risk, no obstacle risk, and the like.
In another embodiment, the determining a result of the trajectory evaluation of the switch to the target lane based on the surrounding environment information includes:
determining a plurality of candidate trajectories based on the target lane;
determining track stability based on the number of times each candidate track is determined as an optimal track within a preset time period;
determining lane changing efficiency of each candidate track based on the predicted lane changing time;
determining the influence degree of each candidate track based on the road occupation area of the target lane in the lane changing process;
determining the risk degree of each candidate track based on the collision probability with the front vehicle in the lane changing process;
and determining a track evaluation result of each candidate track based on track stability, lane changing efficiency, influence degree and risk degree.
Wherein, the track stability refers to the trafficability of the candidate track in a continuous period of time.
Referring to fig. 4, specifically, determining the trajectory stability based on the number of times that each candidate trajectory is determined as the optimal trajectory within the preset time period includes the following steps:
it can be understood that a plurality of moments exist in the preset time period, each moment has an optimal trajectory, and for the estimated trajectory, the more times the estimated trajectory becomes the optimal trajectory in the preset time period, the better the estimated trajectory stability is.
Step 1, calculating the current k i And (4) integrating all lane changing tracks and the track of the current driving lane at the moment.
Step 2, obtaining the optimal track L of the current time based on the related indexes m 。
The relevant indexes comprise lane change efficiency, influence on a target lane and lane change risk degree indexes.
Step 3, cutting off the current k i At the moment, the track change of the step 1 and the step 2 is obtainedTrace the time number K of the calculation.
Acquiring the time number K of track change calculation in the steps 1 and 2, wherein the time number K includes the current K i At any moment, step 3 can effectively count the current k of the cutoff i The time, the cumulative number of times the track change calculation has been performed.
Step 4, judging whether K is satisfied<N, wherein N is a preset number of times; when K is satisfied<N, obtaining a pre-evaluation track L k Is the optimal track L within N moments m Number of times n k (ii) a When K is not satisfied<N, assign K = K +1, and re-perform step 1 loop calculation.
Wherein, step 4 can effectively control the time required to perform the track calculation within a preset range, that is, ensure that the calculated track time segment is always kept at k i Time k to i K before i -N time instants.
Step 5, calculating each pre-evaluation track L k Stability value J of sta The concrete calculation formula is
Wherein the pre-evaluation trajectory L k Is the optimal track L within N moments m Number of times n k N is to be k The pre-evaluation trajectory L can be intuitively reflected through the ratio by dividing the total time number k Stability of (2).
The lane changing efficiency is that the time required from the current lane changing to the specified position of the target lane is calculated based on the preset same distance, and the longer the time is, the lower the lane changing efficiency is.
Specifically, determining the lane change efficiency of each candidate track based on the predicted lane change time comprises the following steps:
J eff representing the lane change efficiency.
Δ t The time required for changing the lane from the current position to the specified position of the target lane when the current evaluation track is at the preset same distance is included.
Carrying out normalization calculation on the time consumption of the evaluation track, the longest time consumption and the shortest time consumption to finally obtain the track changing efficiency J eff 。
The influence degree refers to the influence degree on other vehicles, namely when the vehicles change lanes, the larger the occupied area is, the larger the influence on other vehicles is, for the occupied area condition of the target lane in the whole lane changing process.
Specifically, the step of determining the influence degree of each candidate track based on the road occupation area of the target lane in the lane changing process includes the following steps:
J inf representing the effect on other vehicles.
S k The lane occupation area of the target lane is determined in the whole lane changing process from the current lane changing position to the specified position of the target lane when the same distance is preset in the current evaluation track.
S max And the occupied area of the lane changing track with the largest occupied area from the current lane changing position to the specified position of the target lane is the occupied area of the lane changing track with the largest occupied area from the current lane changing position to the specified position of the target lane based on the preset same distance.
S min And the lane change area is the lane change area of the lane change track with the minimum lane change area from the current lane change position to the specified position of the target lane based on the preset same distance in all the candidate tracks.
The occupied road area of the evaluation track, the maximum occupied road area and the minimum occupied road area are subjected to normalization calculation, and the influence J on other vehicles is finally obtained inf 。
Wherein, the risk degree refers to the risk that the vehicle collides with the front vehicle for the current evaluation track.
Specifically, the step of determining the risk degree of each candidate trajectory based on the collision probability with the preceding vehicle in the lane changing process includes the following steps:
the judgment index of the collision probability is to calculate the time when the vehicle runs at a constant speed and collides with the front vehicle and the time when the maximum acceleration driving and the front vehicle collide with each other according to the current evaluation track, wherein the time ratio is closer to 1, which indicates that the collision probability is higher and further indicates that the collision risk is higher.
J risk Representing an uncertain risk.
And S is the relative distance between the vehicle and the front vehicle in the current evaluation track.
The collision time of the condition with the maximum collision risk of the current evaluation lane
Time to collision with current minimum risk of lane collision assessment
By performing a division, it is possible to derive a value for the risk of uncertainty J risk The evaluation result of (1).
In addition to the lane change influence factors including the trajectory stability, the lane change efficiency, the influence degree and the risk degree, the influence factors further include vehicle oil consumption or power consumption, natural disaster early warning and the like, in other embodiments, other influence factors may also be included, only the vehicle lane change influence needs to be influenced, and the influence factors are not specifically limited herein.
In another embodiment, the determining the trajectory evaluation result of each candidate trajectory based on trajectory stability, lane change efficiency, influence degree and risk degree further includes:
carrying out weighted summation on the track stability, the lane changing efficiency, the influence degree and the risk degree to obtain an evaluation value of each candidate track;
determining an optimum trajectory as the trajectory evaluation result based on the evaluation value.
Specifically, the calculation process is as follows:
J tra ＝w 1 J sta +w 2 J eff +w 3 J inf +w 4 J risk
wherein J is tra Return value for a lane change trajectory for a vehicle, J sta For evaluation of the stability of the trajectory over a continuous period of time, J eff For evaluation of lane change efficiency of the trajectory to reach the target lane, J inf For the evaluation of the influence of the lane change trajectory on other vehicles in the target lane, J risk For evaluation of track-changing risks of self-vehicles, w 1 、w 2 、w 3 、w 4 Is the weight coefficient of the above 4 indexes and w 1 +w 2 +w 3 +w 4 =1, wherein the weighting factor is customized according to the user's needs.
It can be understood that the track stability, the lane change efficiency, the influence degree and the risk degree are subjected to weighted summation to obtain the evaluation value of each candidate track, ranking is performed based on the evaluation scores, and finally the optimal track can be determined, so that comprehensive evaluation is realized, and the accuracy is high.
In an embodiment, the determining a lane change decision result based on the trajectory evaluation result, the user instruction, and the preset navigation information includes:
and if any one of the track evaluation result, the user instruction and the preset navigation information does not accord with a preset condition, the lane change decision result is that the lane is not changed.
It can be understood that the feedback of the track evaluation result influences the issuance of the user instruction, and therefore any one of the track evaluation result, the user instruction and the preset navigation information does not meet the preset condition, that is, the track evaluation result shows that no suitable track is changed, or the user indicates that the track is not changed, or the navigation information shows that the track is not changed, and the track change decision result is output as the track change decision result.
According to the embodiment, the lane change decision result can be comprehensively evaluated from the three aspects of the track evaluation result, the user instruction and the preset navigation information, the optimal track result with higher safety can be output according to the real-time traffic condition, and the safety, the reasonability and the real-time performance of the final lane change track are improved.
For example, referring to fig. 5, fig. 5 is a schematic flow chart of implementation of a lane change decision result of the vehicle lane change decision method according to the embodiment.
In the embodiment, the lane change decision result of the vehicle lane change decision method is realized based on a HFSM (hybrid frequency modulation) layered finite state mechanism theory, and the state machine comprises four main states in the lane change completion, lane change cancel, lane change failure and lane change process. The main state of the lane changing completion is a state machine default state, and the main state in the lane changing process comprises three sub-states of lane preparation, lane changing execution and waiting confirmation completion.
And the main lane changing state is a state machine default state, checking 'condition A', receiving a lane changing decision result, and starting a lane changing preparation sub-state in the main state in the lane changing process after the condition A is checked and no collision risk exists in a target lane within a certain time.
The lane-switching-ready sub-state not only provides the functions of adjusting the speed of the vehicle, turning on a steering lamp, prompting by voice and the like according to the road condition of the target lane, but also determines whether to start the next lane-switching-executing sub-state according to the track evaluation result of the target lane.
In the lane change preparation sub-state, when a condition D1 is met, the lane change track evaluation result in a continuous period of time is larger than the expected difference or no lane change requirement exists, a lane change cancellation main state is started; when the condition E1 is met and the lane change decision result continuously generates failures within a period of time, exiting the main state in the lane change process and starting the lane change failure main state; when the condition G is met, when the lane change requirement is continuously unchanged and the lane change track evaluation result is consistent with the expected gap, the lane change execution sub-state is started.
Wherein the executing lane changing sub-state is a process of defining the lane changing track actually traveled by the vehicle.
In the execution lane changing sub-state, when the condition D2 is met and the lane changing requirement changes or disappears, a lane changing canceling state is started; and when the condition E2 is met and the generation of the lane change decision result fails, starting a lane change failure state. And when the condition H is met, the vehicle drives to the target lane according to the lane changing decision result, and the sub-state to be confirmed is started.
The sub-state to be confirmed is completed in two stages, stable running of the vehicle in the target lane is completed after the vehicle crosses the sideline in the stage I, and if the condition E3 is met, the vehicle cannot complete running in the target lane due to control and positioning and an actuator or collision risk, a lane change failure main state is started; in the second stage, if the condition B is met and the lane change requirement is issued by a user instruction, waiting for the confirmation of the user, and starting a lane change completion state after the confirmation;
in the lane change canceling master state, the condition C is met, and the time for continuously and stably receiving the lane change request exceeds the threshold value T cancel When the state is not satisfied, the state is still in the current state,
T cancel ＝T intent +T silence
in the formula T cancel Is a time threshold in condition C, T intent A time for determining stability of lane change intention, wherein a lane change request time generated based on the driving state of the vehicle is much longer than a lane change request time, T, generated based on the user lane change instruction and the preset navigation information silence For lane change silent time;
in the main channel change failure state, recording the failure source of the condition E entering the state, if the condition F is met, confirming that the failure source disappears and exceeds T fail And when a lane change request is received, starting a state in the lane change process, wherein T fail Greater than T cancel Otherwise, the state is stopped.
The condition E includes three sub-conditions of the condition E1, the condition E2, and the condition E3.
T fail ＝T clear +T silence
In the formula T fail Is a time threshold in the condition F, T clear Time to failure source to disappear steadily, T silence To switch to silent time.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a vehicle lane change decision device for realizing the vehicle lane change decision method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so the specific limitations in one or more vehicle lane change decision device embodiments provided below can be referred to the limitations on the vehicle lane change decision method in the above description, and are not described again here.
In one embodiment, as shown in fig. 6, there is provided a vehicle lane change decision device, including: an obtaining module 610, an evaluating module 620, and a decision module 630, wherein:
the acquiring module 610 is configured to acquire surrounding environment information of a vehicle.
The obtaining module 610 is further configured to obtain at least one of road information, vehicle driving information, and peripheral obstacle information.
And an evaluation module 620, configured to determine a track evaluation result for switching to the target lane based on the surrounding environment information.
The evaluation module 620 is further configured to determine a plurality of candidate trajectories based on the target lane; determining track stability based on the number of times each candidate track is determined as an optimal track within a preset time period; determining lane changing efficiency of each candidate track based on the predicted lane changing time; determining the influence degree of each candidate track based on the road occupation area of the target lane in the lane changing process; determining the risk degree of each candidate track based on the collision probability with the front vehicle in the lane changing process; and determining a track evaluation result of each candidate track based on track stability, lane changing efficiency, influence degree and risk degree.
The evaluation module 620 is further configured to perform weighted summation on the trajectory stability, the lane change efficiency, the influence degree, and the risk degree to obtain an evaluation value of each candidate trajectory; determining an optimum trajectory as the trajectory evaluation result based on the evaluation value.
A decision module 630, configured to determine a lane change decision result based on the trajectory evaluation result, the user instruction, and preset navigation information.
The decision module 630 is further configured to determine that the lane change decision result is no lane change if any one of the trajectory evaluation result, the user instruction, and the preset navigation information does not meet a preset condition.
The vehicle lane change decision-making device further comprises: and determining a module.
The determining module is used for determining a lane changing demand and a target lane based on at least one of a user lane changing instruction, preset navigation information and a vehicle driving state.
The determination module is further configured to:
acquiring the running speed of the vehicle;
if the vehicle running speed is less than a preset threshold value, estimating lane changing driving expectation of the left and right adjacent lanes;
determining a target lane based on the evaluation result.
All or part of each module in the vehicle lane change decision device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a vehicle lane change decision method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (10)
1. A vehicle lane change decision method, the method comprising:
acquiring surrounding environment information of a vehicle;
determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and determining a lane change decision result based on the track evaluation result, the user instruction and preset navigation information.
2. The method of claim 1, wherein the obtaining ambient environment information of the vehicle comprises:
at least one of road information, vehicle travel information, and peripheral obstacle information is acquired.
3. The method of claim 1, wherein the determining a trajectory assessment result of switching to a target lane based on the ambient environment information is preceded by:
determining a lane change demand and a target lane based on at least one of a user lane change instruction, preset navigation information and a vehicle driving state.
4. The method of claim 3, wherein determining a lane change requirement and a target lane based on a vehicle driving state comprises:
acquiring the running speed of the vehicle;
if the vehicle running speed is smaller than a preset threshold value, estimating lane changing driving expectation of the left and right adjacent lanes;
determining a target lane based on the evaluation result.
5. The method according to claim 1, wherein the determining a result of the trajectory evaluation for switching to the target lane based on the surrounding environment information includes:
determining a plurality of candidate trajectories based on the target lane;
determining track stability based on the number of times each candidate track is determined as an optimal track within a preset time period;
determining lane changing efficiency of each candidate track based on the predicted lane changing time;
determining the influence degree of each candidate track based on the road occupation area of the target lane in the lane changing process;
determining the risk degree of each candidate track based on the collision probability with the front vehicle in the lane changing process;
and determining a track evaluation result of each candidate track based on track stability, lane changing efficiency, influence degree and risk degree.
6. The method of claim 5, wherein determining the trajectory assessment result for each of the candidate trajectories based on trajectory stability, lane change efficiency, impact level, and risk level further comprises:
carrying out weighted summation on the track stability, the lane changing efficiency, the influence degree and the risk degree to obtain an evaluation value of each candidate track;
determining an optimum trajectory as the trajectory evaluation result based on the evaluation value.
7. The method of claim 1, wherein determining a lane-change decision result based on the trajectory evaluation result, a user instruction, and preset navigation information comprises:
and if any one of the track evaluation result, the user instruction and the preset navigation information does not accord with a preset condition, the lane change decision result is that the lane is not changed.
8. A vehicle lane change decision-making device, the device comprising:
the acquisition module is used for acquiring surrounding environment information of the vehicle;
the evaluation module is used for determining a track evaluation result of switching to a target lane based on the surrounding environment information;
and the decision-making module is used for determining a channel-changing decision-making result based on the track evaluation result, the user instruction and preset navigation information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211245190.4A CN115649191A (en) | 2022-10-12 | 2022-10-12 | Vehicle lane change decision-making method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211245190.4A CN115649191A (en) | 2022-10-12 | 2022-10-12 | Vehicle lane change decision-making method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115649191A true CN115649191A (en) | 2023-01-31 |
Family
ID=84988042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211245190.4A Pending CN115649191A (en) | 2022-10-12 | 2022-10-12 | Vehicle lane change decision-making method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115649191A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116858259A (en) * | 2023-06-02 | 2023-10-10 | 速度科技股份有限公司 | Intelligent driving path planning system based on vehicle-road cooperation |
-
2022
- 2022-10-12 CN CN202211245190.4A patent/CN115649191A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116858259A (en) * | 2023-06-02 | 2023-10-10 | 速度科技股份有限公司 | Intelligent driving path planning system based on vehicle-road cooperation |
| CN116858259B (en) * | 2023-06-02 | 2024-02-06 | 速度科技股份有限公司 | Intelligent driving path planning system based on vehicle-road cooperation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11887032B2 (en) | Fleet utilization efficiency for on-demand transportation services | |
| US10262471B2 (en) | Autonomous vehicle degradation level monitoring | |
| US10762447B2 (en) | Vehicle selection for on-demand transportation services | |
| EP3356900B1 (en) | Method and system to predict one or more trajectories of a vehicle based on context surrounding the vehicle | |
| US10697789B2 (en) | Individualized risk routing for human drivers | |
| US10884902B2 (en) | Software version verification for autonomous vehicles | |
| US10501091B2 (en) | Software version and mode switching for autonomous vehicles | |
| US11080806B2 (en) | Non-trip risk matching and routing for on-demand transportation services | |
| US11282016B2 (en) | Individualized risk vehicle matching for an on-demand transportation service | |
| US10789835B2 (en) | Fractional risk performance evaluation for autonomous vehicles | |
| US11288612B2 (en) | Generalized risk routing for human drivers | |
| CN111258217B (en) | Real-time object behavior prediction | |
| US9846049B2 (en) | Route prediction | |
| US10489721B2 (en) | Path segment risk regression system for on-demand transportation services | |
| US20180342033A1 (en) | Trip classification system for on-demand transportation services | |
| US20190004517A1 (en) | Method and apparatus for generating automatic driving strategy | |
| EP3631366B1 (en) | Path segment risk regression system for on-demand transportation services | |
| US20180341881A1 (en) | Post-trip optimization for autonomous vehicles | |
| US10002470B2 (en) | Method and apparatus for predictive driving demand modeling | |
| CN115649191A (en) | Vehicle lane change decision-making method and device, computer equipment and storage medium | |
| JP7379424B2 (en) | Situation-specific vehicle power allocation | |
| JP7350814B2 (en) | Wireless energy transfer to transportation vehicles based on route data | |
| Hernandez et al. | Applications of Cloud Computing in Intelligent Vehicles: A Survey | |
| CN111033423A (en) | Method for evaluating a positioning system of an autonomous vehicle | |
| CN114613160A (en) | Lane using method, lane using device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |