CN112455445A - Automatic driving lane change decision method and device and vehicle - Google Patents

Automatic driving lane change decision method and device and vehicle Download PDF

Info

Publication number
CN112455445A
CN112455445A CN202011414439.0A CN202011414439A CN112455445A CN 112455445 A CN112455445 A CN 112455445A CN 202011414439 A CN202011414439 A CN 202011414439A CN 112455445 A CN112455445 A CN 112455445A
Authority
CN
China
Prior art keywords
lane
current
track
feasible
map
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
Application number
CN202011414439.0A
Other languages
Chinese (zh)
Inventor
薛兵
徐传骆
韩志华
张旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Zhitu Technology Co Ltd
Original Assignee
Suzhou Zhitu Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Zhitu Technology Co Ltd filed Critical Suzhou Zhitu Technology Co Ltd
Priority to CN202011414439.0A priority Critical patent/CN112455445A/en
Publication of CN112455445A publication Critical patent/CN112455445A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a lane change decision-making method, a lane change decision-making device and a vehicle for automatic driving.A feasible lane sequence comprising a current lane and a target lane is constructed based on the current lane where the current vehicle is located and an adjacent lane of the current lane; generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information of the current lane and the target lane; determining a lane change track corresponding to the current feasible lane sequence according to ST (maximum likelihood) images of a current lane and a target lane in the current feasible lane sequence aiming at each feasible lane sequence; and selecting the lane change track with the minimum cost from the lane change tracks corresponding to each feasible lane sequence according to the cost function as a lane change decision result. The method searches the lane change track of the feasible lane sequence through the ST map of the current lane of the current vehicle and the ST map of the target lane, and the lane change track obtained by the method is smooth and safe, so that the reasonability of the lane change decision and the lane change opportunity is ensured.

Description

Automatic driving lane change decision method and device and vehicle
Technical Field
The invention relates to the technical field of automatic driving, in particular to a lane change decision method and device for automatic driving and a vehicle.
Background
Decision planning is the brain of an automatic driving system, the essence of a decision planning problem is a search problem in a time domain and a space domain, and the complexity of direct solving is too high to meet the requirement of operation real-time performance. The lane change decision is an important component of decision planning of an automatic driving system, and in a freset coordinate system, a lateral dimension is directly introduced into a search problem by the lane change requirement of an automatic driving vehicle, so that the generation of a lane change track is one of keys of a decision planning algorithm. The lane change decision requires considering the obstacle information of the current lane and the target lane, and considering the reasonability of the lane change track and the lane change time under partial scenes, for example, if the speed of the target lane is too high, the unreasonable lane change track can influence the normal traffic flow although the requirement of collision time is met.
In the related art, two lane change decision algorithms are provided, one is to calculate a lane change profit value when a vehicle has a change motivation, and then output a lane change decision result based on the lane change profit value, but in the method, only the instantaneous vehicle speed of a target lane is considered when the lane change profit value is calculated, and an unreasonable lane change decision is easily generated. The second method is that firstly, the current running environment information of the intelligent vehicle is determined, then a first lane change decision is generated based on a first decision rule and the environment information, and then a second lane change decision is generated based on the first lane change decision and a second decision rule.
Disclosure of Invention
The invention aims to provide a lane change decision method and device for automatic driving and a vehicle, so as to improve the reasonability of lane change decision and lane change time of the automatic driving vehicle.
In a first aspect, the present invention provides a lane change decision method for automatic driving, including: constructing a feasible lane sequence of the current vehicle based on the current lane where the current vehicle is located and the adjacent lane of the current lane; the feasible lane sequence comprises a current lane and a target lane, wherein the target lane is any one of the current lane and an adjacent lane; generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; the ST map is used for indicating the relation between the travel distance of the current vehicle and the time; for each feasible lane sequence, determining a lane change track corresponding to the current feasible lane sequence according to an ST graph of a current lane and an ST graph of a target lane in the current feasible lane sequence; and selecting the lane change track with the minimum cost from the lane change tracks corresponding to each feasible lane sequence as a lane change decision result according to a preset cost function.
In an optional embodiment, the step of determining the lane change trajectory corresponding to the current feasible lane sequence according to the ST map of the current lane and the ST map of the target lane in the current feasible lane sequence includes: in the current feasible lane sequence, searching a first track meeting a preset condition in a current lane according to an ST (test sequence) diagram of the current lane and a driving area of an obstacle of the current lane; determining the last track point in the first track as an initial track point in the target lane; searching a second track meeting a preset condition in the target lane based on the initial track point, the ST map of the target lane and the driving area of the obstacle of the target lane; and combining the first track and the second track to obtain a lane change track corresponding to the current feasible lane sequence.
In an optional embodiment, the step of searching for the first trajectory satisfying the preset condition in the current lane according to the ST map of the current lane and the driving area of the obstacle in the current lane includes: dividing the ST map of the current lane into a plurality of connected domains according to the boundary of the driving region of the obstacle in the current lane in the ST map of the current lane; determining each connected domain outside the driving region of the obstacle as a drivable region of the current vehicle; determining an optional area path of the current vehicle based on the drivable area of the current vehicle; selecting an optimal path from the selectable area paths based on a preset selection rule; searching candidate track points meeting preset conditions from the optimal path; and combining the alternative track points into a first track.
In an alternative embodiment, the step of dividing the ST map of the current lane into a plurality of connected regions according to the boundary of the driving region of the obstacle in the current lane in the ST map of the current lane includes: determining an area below an ST line in an ST image of a current lane as a drivable area of a current vehicle; the travelable region of the current vehicle is divided into a plurality of connected regions according to the boundary of the travel region of the obstacle in the current lane.
In an optional embodiment, the step of selecting an optimal path from the selectable area paths based on a preset selection rule includes: calculating the cost of each optional regional path based on a preset cost calculation rule; and determining the selectable regional path with the minimum cost as the optimal path.
In an optional embodiment, the step of searching for candidate track points that satisfy the preset condition from the optimal path includes: searching a track meeting a preset condition under the optimal path by using a depth-first search algorithm; the preset conditions comprise vehicle dynamics, traffic laws and regulations, driving efficiency and no-collision conditions; and sampling the tracks meeting the preset conditions to obtain a plurality of alternative track points meeting the safe distance and the safe collision time of the forward obstacle and the backward obstacle of the current lane.
In an optional embodiment, the step of searching for candidate track points that satisfy the preset condition from the optimal path includes: determining a soft deceleration track of the current vehicle according to preset deceleration parameters; and sampling the soft deceleration track to obtain a plurality of alternative track points which meet the safe distance and safe collision time of the forward obstacle and the backward obstacle of the current lane.
In an alternative embodiment, the preset cost function is determined by: and constructing a cost function according to the stability, the smoothness and the collision risk of the current vehicle.
In a second aspect, the present invention provides an automatic driving lane change decision device, comprising: the lane sequence construction module is used for constructing a feasible lane sequence of the current vehicle based on the current lane where the current vehicle is located and the adjacent lane of the current lane; the feasible lane sequence comprises a current lane and a target lane, wherein the target lane is any one of the current lane and an adjacent lane; the system comprises an ST map determining module, a driving state determining module and a driving state determining module, wherein the ST map determining module is used for generating an ST map of a current lane and an ST map of a target lane according to the driving state of a current vehicle and the obstacle information on the current lane and the target lane; the ST map is used for indicating the relation between the travel distance of the current vehicle and the time; the lane change track determining module is used for determining a lane change track corresponding to the current feasible lane sequence according to the ST image of the current lane and the ST image of the target lane in the current feasible lane sequence aiming at each feasible lane sequence; and the result determining module is used for selecting the lane change track with the minimum cost from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function as a lane change decision result.
In a third aspect, the invention provides a vehicle comprising a vehicle body and an autonomous driving lane change decision device as described in the previous embodiments.
The embodiment of the invention has the following beneficial effects:
the invention provides an automatic driving lane change decision method, a device and a vehicle.A plurality of feasible lane sequences comprising a current lane and a target lane are constructed based on the current lane where the current vehicle is located and the adjacent lane of the current lane; generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; for each feasible lane sequence, determining a lane change track corresponding to the current feasible lane sequence according to an ST graph of a current lane and an ST graph of a target lane in the current feasible lane sequence; and then selecting the lane change track with the minimum cost as a lane change decision result from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function. The method searches the lane change track of the feasible lane sequence through the ST map of the current lane of the current vehicle and the ST map of the target lane, and the lane change track obtained by the method is smooth and safe, so that the reasonability of the lane change decision and the lane change opportunity is ensured.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention as set forth above.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a lane change decision method for automatic driving according to an embodiment of the present invention;
FIG. 2 is a flow chart of another automatic lane change decision method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a vehicle according to an embodiment of the present invention;
fig. 4 is an ST diagram of a current lane LaneA according to an embodiment of the present invention;
FIG. 5 is an ST diagram of a target lane provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an automatic driving lane change decision device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Two lane change decision algorithms are provided in the related art, one is an intelligent vehicle lane change decision method, which comprises the following steps: firstly, determining the current running environment information of the intelligent vehicle, and updating vehicle parameters; further judging whether the intelligent vehicle has a lane change motivation, and if so, entering the step 1; if the judgment is no, entering the step 2; step 1, calculating a lane change income value; and 2, outputting a channel changing decision result, wherein the channel changing decision result comprises no channel changing, left channel changing and right channel changing. In the method, only the instantaneous speed of the target lane is considered when the lane change income value is calculated in the step 1, and a prediction result is not used, so that an unreasonable lane change decision is easily generated.
A second method, comprising: firstly, determining current running environment information of the intelligent vehicle, wherein the environment information comprises track information and lane information; generating a first lane change decision based on the first decision rule and the environmental information; and generating a second channel changing decision based on the first channel changing decision and a second decision rule. The method uses a state machine to give a channel change decision, and cannot provide necessary channel change information, such as channel change time and the like, so that the subsequent track generation has great difficulty.
Based on this, the lane change decision algorithm in the related art has the problem that the vehicle lane change decision and the lane change are unreasonable in practice, so the embodiment of the invention provides a lane change decision method, a lane change decision device and a vehicle for automatic driving. In order to facilitate understanding of the embodiment of the present invention, a detailed description is first given to a lane change decision method for automatic driving provided by the embodiment of the present invention, as shown in fig. 1, the method includes the following specific steps:
step S102, constructing a feasible lane sequence of the current vehicle based on the current lane where the current vehicle is located and the adjacent lane of the current lane; the feasible lane sequence comprises a current lane and a target lane, wherein the target lane is any one of the current lane and an adjacent lane.
The current vehicle is a vehicle for a user to ride, and the vehicle can change lanes according to requirements. The travelable lane sequence of the current vehicle may include three types: the first is to keep the current lane running, namely the target lane is the current lane; the second is to change the lane from the current lane to the adjacent lane on the left of the current lane, namely the target lane is the adjacent lane on the left; the third is to change the lane from the current lane to the adjacent lane on the right side of the current lane, i.e. the target lane is the adjacent lane on the right side.
Step S104, generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; the ST map is used to indicate the relationship between the travel distance of the current vehicle and the time.
The running state of the current vehicle may include a current running speed, acceleration, deceleration, and the like of the current vehicle, the obstacle may be a vehicle other than the current vehicle that runs on a lane, and the obstacle information may include a running state of the obstacle. The ST diagram may be understood as a route-time diagram in which the current travel distance of the vehicle in the current lane or the target lane is plotted over time.
And step S106, determining a lane change track corresponding to the current feasible lane sequence according to the ST graph of the current lane and the ST graph of the target lane in the current feasible lane sequence aiming at each feasible lane sequence.
Because each feasible lane sequence comprises the current lane and the target lane and only the target lane contained in each feasible lane sequence is different, each feasible lane sequence can be used as the current lane sequence, and the lane change track corresponding to the current feasible lane sequence can be obtained according to the ST diagram of the current lane and the ST diagram of the target lane.
In the concrete implementation, on the basis of an ST diagram of a current lane and an ST diagram of a target lane, an optimal track on the current lane is searched, track point sampling is carried out on the track, the optimal track is searched on the target lane by taking the optimal track as an initial track point of the target lane, the optimal track on the current lane is combined with the optimal track on the target lane, a lane change track corresponding to a current feasible lane sequence can be obtained, and the lane change track obtained in the mode is smooth and safe, so that the reasonability of a lane change decision and the lane change time is ensured.
And S108, selecting the lane change track with the minimum cost from the lane change tracks corresponding to each feasible lane sequence as a lane change decision result according to a preset cost function.
The preset cost function can be set by a user in advance, and can also be constructed by the user according to the driving stability, smoothness, collision risk and the like of the current vehicle. During specific implementation, the cost of the lane change track corresponding to each feasible lane sequence is calculated according to a preset cost function, and the lane change track with the minimum cost is determined as a final lane change track, which is also a lane change decision result.
The embodiment of the invention provides an automatic driving lane change decision method, which comprises the steps of firstly constructing a plurality of feasible lane sequences comprising a current lane and a target lane based on the current lane where a current vehicle is located and an adjacent lane of the current lane; generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; for each feasible lane sequence, determining a lane change track corresponding to the current feasible lane sequence according to an ST graph of a current lane and an ST graph of a target lane in the current feasible lane sequence; and then selecting the lane change track with the minimum cost as a lane change decision result from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function. The method searches the lane change track of the feasible lane sequence through the ST map of the current lane of the current vehicle and the ST map of the target lane, and the lane change track obtained by the method is smooth and safe, so that the reasonability of the lane change decision and the lane change opportunity is ensured.
The embodiment of the invention also provides another lane change decision method for automatic driving, which is realized on the basis of the method of the embodiment; the method mainly describes a specific process of determining a lane change trajectory corresponding to a current feasible lane sequence according to an ST map of a current lane in the current feasible lane sequence and an ST map of a target lane (realized by the following steps S206-S212), as shown in fig. 2, the method includes the following specific steps:
step S202, constructing a feasible lane sequence of the current vehicle based on the current lane where the current vehicle is located and the adjacent lane of the current lane; the feasible lane sequence comprises a current lane and a target lane, wherein the target lane is any one of the current lane and an adjacent lane.
As shown in fig. 3, which is a schematic diagram of a vehicle driving, a current lane where a current vehicle ego is currently located is LaneA, an obstacle ObsA invades the current lane, and an obstacle ObsB and an obstacle ObsC exist on an adjacent lane LaneB, so that the current vehicle has three possible lane sequences, which are: LaneA, LaneA-LaneB and LaneA-LaneC, that is, the target lanes in these three cases correspond to LaneA, LaneB and LaneC, respectively. The target lane in the schematic diagram shown in fig. 3 is LaneB.
Step S204, generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; the ST map is used to indicate the relationship between the travel distance of the current vehicle and the time.
And step S206, aiming at each feasible lane sequence, searching a first track meeting preset conditions in the current lane according to the ST diagram of the current lane and the driving area of the obstacle of the current lane in the current feasible lane sequence.
The obstacle can be located in front of or behind a current lane where the current vehicle is located, as time goes on, an area where the current vehicle passes on the current lane is overlapped with an area where the obstacle passes on the current lane, the overlapped area in an ST image of the current lane is removed, a travelable area of the current vehicle can be obtained, a first track meeting preset conditions is searched for on the travelable area, and the first track is the optimal track on the current lane. The preset conditions may be set according to user requirements, for example, the preset conditions are conditions of meeting vehicle dynamics, traffic regulations, driving efficiency, no collision and the like, or meeting the safety distance and the safety collision time of the forward obstacle and the backward obstacle of the current lane.
In a specific implementation, the step S206 may be determined by the following steps 10-13:
step 10, dividing the ST map of the current lane into a plurality of connected domains according to the boundary of the driving region of the obstacle in the current lane in the ST map of the current lane; and determining each connected domain outside the driving area of the obstacle as the driving area of the current vehicle.
In specific implementation, determining an area below an ST line in an ST image of a current lane as a travelable area of a current vehicle; the travelable region of the current vehicle is divided into a plurality of connected regions according to the boundary of the travel region of the obstacle in the current lane. As shown in fig. 4, which is an ST diagram of the current lane LaneA in fig. 3, the driving area of the obstacle ObsA in the current lane is a diamond area in fig. 4, and the drivable area of the current vehicle can be divided into three connected domains according to the boundary of the diamond area: AreaA, AreaB, and AreaC.
And step 11, determining the selectable area path of the current vehicle based on the drivable area of the current vehicle.
The selectable area path of the current vehicle may include one or more travelable areas, and the travelable areas may be interconnected. For example, the current vehicle area-selectable path in FIG. 4 includes area-area B and area-area C.
And 12, selecting an optimal path from the selectable area paths based on a preset selection rule.
The selection rule is set according to the user requirement, and the selection rule may be to select the selectable area path with the minimum cost, or may be to select the selectable area path with the shortest time, and the like. In specific implementation, the cost of each optional area path can be calculated based on a preset cost calculation rule; and determining the selectable regional path with the minimum cost as the optimal path. The cost calculation rule can be set according to the requirements of users.
In the concrete implementation, an ST map of a current lane is constructed according to the driving state of a current vehicle and obstacle information, due to the existence of dynamic obstacles, most of feasible regions in the ST map are non-convex spaces, the non-convex spaces are rasterized by obstacle boundaries in the ST map, an acyclic graph is constructed, feasible ST paths with minimum cost (equivalent to the selectable region paths) are searched, and the convex feasible spaces are obtained.
Step 13, searching candidate track points meeting preset conditions from the optimal path; and combining the alternative track points into a first track.
In specific implementation, an optimal collision-free motion track can be searched in an optimal path by considering the state of an obstacle, vehicle dynamics, traffic regulations, driving efficiency and the like, wherein the track is a lane keeping motion track; the deceleration track can also be generated by soft deceleration, and then the lane keeping motion track or the candidate track point determined from the deceleration track is obtained. In a specific implementation, the step 13 can be implemented by the following steps 20 to 21:
step 20, searching a track meeting a preset condition under the optimal path by using a depth-first search algorithm; the preset conditions include vehicle dynamics, traffic regulations, driving efficiency, and no-collision conditions. Wherein, the track satisfying the preset condition is equivalent to the lane keeping motion track.
And step 21, sampling the tracks meeting the preset conditions to obtain a plurality of alternative track points meeting the safe distance and the safe collision time of the forward obstacle and the backward obstacle of the current lane. The trace points P1, P2, PK-1、PKTo obtain a plurality of candidate track points.
The soft deceleration trajectory is considered because normal driving does not necessarily search out a proper lane change trajectory point, and therefore, adding an additional soft deceleration trajectory can increase the probability of success of lane change. Thus, the above step 13 can also be realized by the following steps 30 to 31:
and step 30, determining the soft deceleration track of the current vehicle according to the preset deceleration parameters. The lower trace as in fig. 4 is the soft deceleration trajectory.
And step 31, sampling the soft deceleration track to obtain a plurality of alternative track points which meet the safety distance and the safety collision time of the forward obstacle and the backward obstacle of the current lane.
And step S208, determining the last track point in the first track as the initial track point in the target lane.
The last track point in the first track corresponds to the track point P in fig. 4K. The last track point can also be understood as a joint track point of the current track point and the target track point.
And step S210, searching a second track meeting preset conditions in the target lane based on the initial track point, the ST map of the target lane and the driving area of the obstacle of the target lane.
In a specific implementation, the second track meeting the preset condition is searched in the target lane in the same way as the first track meeting the preset condition is searched in the current lane. For example, assuming that LaneB in fig. 3 is a target lane, an ST map of the target lane as shown in fig. 5 can be obtained, and according to fig. 3, two obstacles ObsB and ObsC exist in the target lane LaneB, so that a quadrilateral region in fig. 5 represents a travelable region corresponding to the obstacle ObsC, and a lower triangular region represents a travelable region corresponding to the obstacle ObsB, and according to a boundary of the travelable regions of the two obstacles, the travelable region of the current vehicle in the target lane can be divided into two connected regions: area and area. Since area and area are not communicated with each other, only one area path of the current vehicle on the current lane is area. And then, with the initial track point in the target lane as a starting point, searching for the moving track point in an area space by using a depth-first search algorithm to respectively obtain lane keeping tracks meeting the conditions of vehicle dynamics, traffic regulations, driving efficiency, no collision and the like, and determining a soft deceleration track according to preset deceleration parameters. And sampling the lane keeping track and the soft deceleration track to obtain alternative track changing track points which meet the safety distance and the safety collision time of the forward obstacle and the backward obstacle of the target lane. In specific implementation, if the search is successful by using the depth-first search algorithm, the traversal of the alternative lane change points is stopped, and a second track consisting of the alternative lane change points can be obtained.
And step S212, combining the first track and the second track to obtain a lane change track corresponding to the current feasible lane sequence.
And combining the first track of the current lane and the second track of the target lane to obtain a lane change track corresponding to the current feasible lane sequence, wherein the lane change track can also be called a lane change longitudinal motion track. The lane-changing longitudinal motion trail of other feasible lane sequences can be obtained in the same way.
And step S214, selecting the lane change track with the minimum cost from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function as a lane change decision result.
The preset cost function may be determined by: and constructing a cost function according to the stability, the smoothness and the collision risk of the current vehicle. Namely, the stability, the smoothness, the collision risk and the like of the current vehicle are considered, a cost function is constructed, a lane change decision result is obtained, and information such as lane change points is provided for the subsequent track generation.
The lane change decision method for automatic driving considers the safety of the motion tracks on the lane and the target lane based on the searched lane change decision; and the track changing points are searched through sampling, so that the smoothness of the track changing track and the reasonability of the track changing decision are ensured. Meanwhile, the mode considers the barrier predicted track of the current lane and the target lane, and ensures the safety of lane changing track; and the track changing points are obtained by sampling the track points of the current lane, and are used as initial points of the target lane, so that the smoothness and the reasonability of the track changing track are ensured, the safety of the track of the target lane is checked, the redundancy of the track changing decision is increased, and the success rate of the track changing is improved.
Corresponding to the above method embodiment, an embodiment of the present invention provides an automatic driving lane change decision apparatus, as shown in fig. 6, the apparatus includes:
a lane sequence constructing module 60, configured to construct a feasible lane sequence of the current vehicle based on a current lane where the current vehicle is located and an adjacent lane of the current lane; the feasible lane sequence comprises a current lane and a target lane, wherein the target lane is any one of the current lane and an adjacent lane.
An ST map determining module 61, configured to generate an ST map of the current lane and an ST map of the target lane according to a driving state of the current vehicle and obstacle information on the current lane and the target lane; the ST map is used to indicate the relationship between the travel distance of the current vehicle and the time.
And a lane change trajectory determination module 62, configured to determine, for each feasible lane sequence, a lane change trajectory corresponding to the current feasible lane sequence according to the ST map of the current lane in the current feasible lane sequence and the ST map of the target lane.
And the result determining module 63 is configured to select, according to a preset cost function, a lane change trajectory with the smallest cost from the lane change trajectories corresponding to each feasible lane sequence as a lane change decision result.
The automatic driving lane change decision device firstly constructs a plurality of feasible lane sequences including a current lane and a target lane based on the current lane where a current vehicle is located and an adjacent lane of the current lane; generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; for each feasible lane sequence, determining a lane change track corresponding to the current feasible lane sequence according to an ST graph of a current lane and an ST graph of a target lane in the current feasible lane sequence; and then selecting the lane change track with the minimum cost as a lane change decision result from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function. The method searches the lane change track of the feasible lane sequence through the ST map of the current lane of the current vehicle and the ST map of the target lane, and the lane change track obtained by the method is smooth and safe, so that the reasonability of the lane change decision and the lane change opportunity is ensured.
Further, the lane change trajectory determination module 62 is configured to: in the current feasible lane sequence, searching a first track meeting a preset condition in a current lane according to an ST (test sequence) diagram of the current lane and a driving area of an obstacle of the current lane; determining the last track point in the first track as an initial track point in the target lane; searching a second track meeting a preset condition in the target lane based on the initial track point, the ST map of the target lane and the driving area of the obstacle of the target lane; and combining the first track and the second track to obtain a lane change track corresponding to the current feasible lane sequence.
Specifically, the lane change trajectory determination module 62 includes: the system comprises a dividing module, a judging module and a judging module, wherein the dividing module is used for dividing an ST map of a current lane into a plurality of connected domains according to the boundary of a driving area of an obstacle in the current lane in the ST map of the current lane; determining each connected domain outside the driving region of the obstacle as a drivable region of the current vehicle; the route determination module is used for determining a selectable area route of the current vehicle based on the drivable area of the current vehicle; the route selection module is used for selecting an optimal route from the selectable area routes based on a preset selection rule; the track determining module is used for searching candidate track points meeting preset conditions from the optimal path; and combining the alternative track points into a first track.
Further, the dividing module is further configured to: determining an area below an ST line in an ST image of a current lane as a drivable area of a current vehicle; the travelable region of the current vehicle is divided into a plurality of connected regions according to the boundary of the travel region of the obstacle in the current lane.
Further, the path determining module is further configured to: calculating the cost of each optional regional path based on a preset cost calculation rule; and determining the selectable regional path with the minimum cost as the optimal path.
Further, the trajectory determination module is further configured to: searching a track meeting a preset condition under the optimal path by using a depth-first search algorithm; the preset conditions comprise vehicle dynamics, traffic laws and regulations, driving efficiency and no-collision conditions; and sampling the tracks meeting the preset conditions to obtain a plurality of alternative track points meeting the safe distance and the safe collision time of the forward obstacle and the backward obstacle of the current lane.
Further, the trajectory determination module is further configured to: determining a soft deceleration track of the current vehicle according to preset deceleration parameters; and sampling the soft deceleration track to obtain a plurality of alternative track points which meet the safe distance and safe collision time of the forward obstacle and the backward obstacle of the current lane.
Further, the apparatus further includes a cost function determining module, configured to: and constructing a cost function according to the stability, the smoothness and the collision risk of the current vehicle.
The implementation principle and the generated technical effect of the automatic driving lane change decision device provided by the embodiment of the invention are the same as those of the data backup method embodiment, and for the sake of brief description, the corresponding contents in the method embodiment can be referred to where the device embodiment is not mentioned.
As shown in fig. 7, the vehicle includes a vehicle body 70 and an automatic driving lane change decision device 71, and specific implementation may refer to the method embodiment, and details are not described herein.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A lane change decision method for autonomous driving, the method comprising:
constructing a feasible lane sequence of a current vehicle based on a current lane where the current vehicle is located and a neighboring lane of the current lane; the feasible lane sequence comprises the current lane and a target lane, and the target lane is any one of the current lane and the adjacent lane;
generating an ST map of the current lane and an ST map of the target lane according to the driving state of the current vehicle and the obstacle information on the current lane and the target lane; the ST map is used for indicating the relation between the driving distance of the current vehicle and the time;
for each feasible lane sequence, determining a lane change track corresponding to the current feasible lane sequence according to the ST graph of the current lane and the ST graph of the target lane in the current feasible lane sequence;
and selecting the lane change track with the minimum cost as a lane change decision result from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function.
2. The method according to claim 1, wherein the step of determining the lane change trajectory corresponding to the current feasible lane sequence according to the ST map of the current lane and the ST map of the target lane in the current feasible lane sequence comprises:
in a current feasible lane sequence, searching a first track meeting a preset condition in a current lane according to an ST diagram of the current lane and a driving area of an obstacle of the current lane;
determining the last track point in the first track as an initial track point in the target lane;
searching a second track meeting the preset condition in the target lane based on the initial track point, the ST map of the target lane and the driving area of the obstacle of the target lane;
and combining the first track and the second track to obtain a lane change track corresponding to the current feasible lane sequence.
3. The method according to claim 2, wherein the step of searching for a first trajectory satisfying a preset condition in the current lane according to the ST map of the current lane and a driving area of an obstacle of the current lane comprises:
dividing the ST map of the current lane into a plurality of connected domains according to the boundary of the driving region of the obstacle in the current lane in the ST map of the current lane; determining each connected domain outside the driving area of the obstacle as a drivable area of the current vehicle;
determining a selectable area path of the current vehicle based on a drivable area of the current vehicle;
based on a preset selection rule, selecting an optimal path from the selectable area paths;
searching candidate track points meeting the preset conditions from the optimal path; and combining the alternative track points into the first track.
4. The method according to claim 3, wherein the step of dividing the ST map of the current lane into a plurality of connected components according to a boundary of a driving area of an obstacle in the current lane in the ST map of the current lane comprises:
determining an area below an ST line in an ST diagram of the current lane as a drivable area of the current vehicle;
and dividing the travelable region of the current vehicle into a plurality of connected regions according to the boundary of the traveling region of the obstacle in the current lane.
5. The method according to claim 3, wherein the step of selecting the optimal path from the selectable area paths based on a preset selection rule comprises:
calculating the cost of each selectable regional path based on a preset cost calculation rule;
and determining the selectable area path with the minimum cost as the optimal path.
6. The method according to claim 3, wherein the step of searching for the candidate track points satisfying the preset condition from the optimal path comprises:
searching a track meeting the preset condition under the optimal path by using a depth-first search algorithm; the preset conditions comprise vehicle dynamics, traffic laws and regulations, driving efficiency and no-collision conditions;
and sampling the tracks meeting the preset conditions to obtain a plurality of alternative track points meeting the safe distance and the safe collision time of the forward obstacle and the backward obstacle of the current lane.
7. The method according to claim 3, wherein the step of searching for the candidate track points satisfying the preset condition from the optimal path comprises:
determining a soft deceleration track of the current vehicle according to preset deceleration parameters;
and sampling the soft deceleration track to obtain a plurality of alternative track points which meet the safe distance and safe collision time of the forward obstacle and the backward obstacle of the current lane.
8. The method of claim 1, wherein the predetermined cost function is determined by:
and constructing the cost function according to the stability, the smoothness and the collision risk of the current vehicle.
9. An autonomous lane change decision device, the device comprising:
the lane sequence construction module is used for constructing a feasible lane sequence of the current vehicle based on the current lane where the current vehicle is located and the adjacent lane of the current lane; the feasible lane sequence comprises the current lane and a target lane, and the target lane is any one of the current lane and the adjacent lane;
an ST map determining module, configured to generate an ST map of the current lane and an ST map of the target lane according to a driving state of the current vehicle and obstacle information on the current lane and the target lane; the ST map is used for indicating the relation between the driving distance of the current vehicle and the time;
a lane change track determining module, configured to determine, for each feasible lane sequence, a lane change track corresponding to the current feasible lane sequence according to the ST map of the current lane and the ST map of the target lane in the current feasible lane sequence;
and the result determining module is used for selecting the lane change track with the minimum cost as a lane change decision result from the lane change tracks corresponding to each feasible lane sequence according to a preset cost function.
10. A vehicle comprising a vehicle body and the autonomous driving lane change decision device of claim 9.
CN202011414439.0A 2020-12-04 2020-12-04 Automatic driving lane change decision method and device and vehicle Pending CN112455445A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011414439.0A CN112455445A (en) 2020-12-04 2020-12-04 Automatic driving lane change decision method and device and vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011414439.0A CN112455445A (en) 2020-12-04 2020-12-04 Automatic driving lane change decision method and device and vehicle

Publications (1)

Publication Number Publication Date
CN112455445A true CN112455445A (en) 2021-03-09

Family

ID=74800219

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011414439.0A Pending CN112455445A (en) 2020-12-04 2020-12-04 Automatic driving lane change decision method and device and vehicle

Country Status (1)

Country Link
CN (1) CN112455445A (en)

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113022586A (en) * 2021-04-14 2021-06-25 福瑞泰克智能系统有限公司 Vehicle behavior prediction method and device and storage medium
CN113674329A (en) * 2021-08-13 2021-11-19 上海同温层智能科技有限公司 Vehicle driving behavior detection method and system
CN113830108A (en) * 2021-11-10 2021-12-24 苏州挚途科技有限公司 Decision planning method and device for autonomous vehicle
CN113844451A (en) * 2021-09-30 2021-12-28 上海商汤临港智能科技有限公司 Traveling device control method, traveling device control device, electronic device, and storage medium
CN113859267A (en) * 2021-10-27 2021-12-31 广州小鹏自动驾驶科技有限公司 Route decision method and device and vehicle
CN113954838A (en) * 2021-11-24 2022-01-21 上海安亭地平线智能交通技术有限公司 Vehicle lane change control method and device, electronic device and storage medium
CN114019971A (en) * 2021-11-04 2022-02-08 北京三快在线科技有限公司 Unmanned equipment control method and device, storage medium and electronic equipment
CN114179815A (en) * 2021-12-29 2022-03-15 阿波罗智联(北京)科技有限公司 Method and device for determining vehicle driving track, vehicle, electronic equipment and medium
CN114265430A (en) * 2021-12-21 2022-04-01 深圳市镭神智能系统有限公司 Aerocar, control method thereof and computer readable storage medium
CN114264312A (en) * 2021-11-30 2022-04-01 阿波罗智联(北京)科技有限公司 Path planning method and device for automatic driving vehicle and automatic driving vehicle
CN114506342A (en) * 2022-03-03 2022-05-17 东风悦享科技有限公司 Method and system for automatic driving lane change decision and vehicle
CN115083139A (en) * 2021-03-12 2022-09-20 上海交通大学 Multi-vehicle scheduling method
CN115158363A (en) * 2022-08-16 2022-10-11 广州小鹏自动驾驶科技有限公司 Vehicle lane change processing method and vehicle
CN115179949A (en) * 2022-09-13 2022-10-14 毫末智行科技有限公司 Vehicle pressure speed changing control method, device, equipment and storage medium
CN115195743A (en) * 2022-09-16 2022-10-18 毫末智行科技有限公司 Automatic lane changing method, device, equipment and medium for vehicle based on unmanned driving
CN115938106A (en) * 2022-09-02 2023-04-07 吉林大学 Automatic driving decision online verification method based on traffic participant accessibility analysis
CN115973158A (en) * 2023-03-20 2023-04-18 北京集度科技有限公司 Lane changing track planning method, vehicle, electronic equipment and computer program product
CN116564097A (en) * 2023-07-11 2023-08-08 蘑菇车联信息科技有限公司 Intersection passing decision-making method, device and system of vehicle and electronic equipment
CN117261903A (en) * 2023-11-21 2023-12-22 杭州鉴智机器人科技有限公司 Lane changing method and device for automatic driving vehicle
CN117302224A (en) * 2023-11-30 2023-12-29 上海鉴智其迹科技有限公司 Lane changing method, automatic driving method, device and vehicle
CN117601867A (en) * 2024-01-18 2024-02-27 杭州鉴智机器人科技有限公司 Vehicle lane changing method, vehicle lane changing device, storage medium and vehicle control system
CN117681879A (en) * 2024-02-04 2024-03-12 上海鉴智其迹科技有限公司 Vehicle lane changing method and device, electronic equipment and storage medium
WO2024178799A1 (en) * 2023-02-27 2024-09-06 魔门塔(苏州)科技有限公司 Vehicle passing efficiency determination method and apparatus, and vehicle

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109213153A (en) * 2018-08-08 2019-01-15 东风汽车有限公司 Automatic vehicle driving method and electronic equipment
CN109827586A (en) * 2019-02-20 2019-05-31 百度在线网络技术（北京）有限公司 Car speed planing method, device, equipment and computer-readable medium
CN109901575A (en) * 2019-02-20 2019-06-18 百度在线网络技术（北京）有限公司 Vehicle routing plan adjustment method, device, equipment and computer-readable medium
CN110461676A (en) * 2017-03-29 2019-11-15 三菱电机株式会社 The system and method for controlling the transverse movement of vehicle
CN111123952A (en) * 2019-12-31 2020-05-08 华为技术有限公司 Trajectory planning method and device
DE102018132523A1 (en) * 2018-12-17 2020-06-18 Trw Automotive Gmbh Method and system for controlling a motor vehicle
CN111380534A (en) * 2018-12-27 2020-07-07 百度（美国）有限责任公司 ST-map-learning-based decision making for autonomous vehicles

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110461676A (en) * 2017-03-29 2019-11-15 三菱电机株式会社 The system and method for controlling the transverse movement of vehicle
CN109213153A (en) * 2018-08-08 2019-01-15 东风汽车有限公司 Automatic vehicle driving method and electronic equipment
DE102018132523A1 (en) * 2018-12-17 2020-06-18 Trw Automotive Gmbh Method and system for controlling a motor vehicle
CN111380534A (en) * 2018-12-27 2020-07-07 百度（美国）有限责任公司 ST-map-learning-based decision making for autonomous vehicles
CN109827586A (en) * 2019-02-20 2019-05-31 百度在线网络技术（北京）有限公司 Car speed planing method, device, equipment and computer-readable medium
CN109901575A (en) * 2019-02-20 2019-06-18 百度在线网络技术（北京）有限公司 Vehicle routing plan adjustment method, device, equipment and computer-readable medium
CN111123952A (en) * 2019-12-31 2020-05-08 华为技术有限公司 Trajectory planning method and device

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115083139A (en) * 2021-03-12 2022-09-20 上海交通大学 Multi-vehicle scheduling method
CN115083139B (en) * 2021-03-12 2023-11-24 上海交通大学 Multi-vehicle scheduling method
CN113022586A (en) * 2021-04-14 2021-06-25 福瑞泰克智能系统有限公司 Vehicle behavior prediction method and device and storage medium
CN113674329A (en) * 2021-08-13 2021-11-19 上海同温层智能科技有限公司 Vehicle driving behavior detection method and system
CN113844451A (en) * 2021-09-30 2021-12-28 上海商汤临港智能科技有限公司 Traveling device control method, traveling device control device, electronic device, and storage medium
CN113844451B (en) * 2021-09-30 2023-12-19 上海商汤临港智能科技有限公司 Driving device control method and device, electronic device and storage medium
CN113859267A (en) * 2021-10-27 2021-12-31 广州小鹏自动驾驶科技有限公司 Route decision method and device and vehicle
CN113859267B (en) * 2021-10-27 2023-08-25 广州小鹏自动驾驶科技有限公司 Path decision method and device and vehicle
CN114019971B (en) * 2021-11-04 2024-03-26 北京三快在线科技有限公司 Unmanned equipment control method and device, storage medium and electronic equipment
CN114019971A (en) * 2021-11-04 2022-02-08 北京三快在线科技有限公司 Unmanned equipment control method and device, storage medium and electronic equipment
CN113830108A (en) * 2021-11-10 2021-12-24 苏州挚途科技有限公司 Decision planning method and device for autonomous vehicle
CN113954838A (en) * 2021-11-24 2022-01-21 上海安亭地平线智能交通技术有限公司 Vehicle lane change control method and device, electronic device and storage medium
CN113954838B (en) * 2021-11-24 2023-04-07 上海安亭地平线智能交通技术有限公司 Vehicle lane change control method and device, electronic device and storage medium
CN114264312A (en) * 2021-11-30 2022-04-01 阿波罗智联(北京)科技有限公司 Path planning method and device for automatic driving vehicle and automatic driving vehicle
CN114265430A (en) * 2021-12-21 2022-04-01 深圳市镭神智能系统有限公司 Aerocar, control method thereof and computer readable storage medium
CN114179815A (en) * 2021-12-29 2022-03-15 阿波罗智联(北京)科技有限公司 Method and device for determining vehicle driving track, vehicle, electronic equipment and medium
CN114179815B (en) * 2021-12-29 2023-08-18 阿波罗智联(北京)科技有限公司 Method and device for determining vehicle driving track, vehicle, electronic equipment and medium
CN114506342B (en) * 2022-03-03 2023-12-05 东风悦享科技有限公司 Automatic driving lane change decision method, system and vehicle
CN114506342A (en) * 2022-03-03 2022-05-17 东风悦享科技有限公司 Method and system for automatic driving lane change decision and vehicle
CN115158363B (en) * 2022-08-16 2024-03-08 广州小鹏自动驾驶科技有限公司 Vehicle lane change processing method and vehicle
CN115158363A (en) * 2022-08-16 2022-10-11 广州小鹏自动驾驶科技有限公司 Vehicle lane change processing method and vehicle
CN115938106A (en) * 2022-09-02 2023-04-07 吉林大学 Automatic driving decision online verification method based on traffic participant accessibility analysis
CN115938106B (en) * 2022-09-02 2024-07-09 吉林大学 Automatic driving decision online verification method based on traffic participant accessibility analysis
CN115179949B (en) * 2022-09-13 2022-11-29 毫末智行科技有限公司 Vehicle speed-changing control method, device, equipment and storage medium
CN115179949A (en) * 2022-09-13 2022-10-14 毫末智行科技有限公司 Vehicle pressure speed changing control method, device, equipment and storage medium
CN115195743A (en) * 2022-09-16 2022-10-18 毫末智行科技有限公司 Automatic lane changing method, device, equipment and medium for vehicle based on unmanned driving
WO2024178799A1 (en) * 2023-02-27 2024-09-06 魔门塔(苏州)科技有限公司 Vehicle passing efficiency determination method and apparatus, and vehicle
CN115973158A (en) * 2023-03-20 2023-04-18 北京集度科技有限公司 Lane changing track planning method, vehicle, electronic equipment and computer program product
CN116564097B (en) * 2023-07-11 2023-10-03 蘑菇车联信息科技有限公司 Intersection passing decision-making method, device and system of vehicle and electronic equipment
CN116564097A (en) * 2023-07-11 2023-08-08 蘑菇车联信息科技有限公司 Intersection passing decision-making method, device and system of vehicle and electronic equipment
CN117261903A (en) * 2023-11-21 2023-12-22 杭州鉴智机器人科技有限公司 Lane changing method and device for automatic driving vehicle
CN117302224B (en) * 2023-11-30 2024-02-23 上海鉴智其迹科技有限公司 Lane changing method, automatic driving method, device and vehicle
CN117302224A (en) * 2023-11-30 2023-12-29 上海鉴智其迹科技有限公司 Lane changing method, automatic driving method, device and vehicle
CN117601867A (en) * 2024-01-18 2024-02-27 杭州鉴智机器人科技有限公司 Vehicle lane changing method, vehicle lane changing device, storage medium and vehicle control system
CN117681879A (en) * 2024-02-04 2024-03-12 上海鉴智其迹科技有限公司 Vehicle lane changing method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112455445A (en) Automatic driving lane change decision method and device and vehicle
CN112099496B (en) Automatic driving training method, device, equipment and medium
CN112985445B (en) Lane-level precision real-time motion planning method based on high-precision map
US10576976B2 (en) Drivable area setting device and drivable area setting method
KR102306939B1 (en) Method and device for short-term path planning of autonomous driving through information fusion by using v2x communication and image processing
CN110954122B (en) Automatic driving track generation method under high-speed scene
CN110333659B (en) Unmanned vehicle local path planning method based on improved A star search
CN112068545A (en) Method and system for planning driving track of unmanned vehicle at crossroad and storage medium
CN106114507A (en) Local path planning method and device for intelligent vehicle
CN105675000A (en) Lane-level path planning method and system based on high precision map
JP5663942B2 (en) Traveling track creation device
CN113295177B (en) Dynamic path planning method and system based on real-time road condition information
CN115230719B (en) Driving track planning method and device
CN112033426B (en) Driving path planning method and device and electronic equipment
CN113741453A (en) Path planning method, device, equipment and medium for unstructured environment
US6842694B2 (en) Car navigation system
CN114527761A (en) Intelligent automobile local path planning method based on fusion algorithm
CN104875740A (en) Method, host vehicle and following space management unit for managing following space
CN115140096A (en) Spline curve and polynomial curve-based automatic driving track planning method
CN113701774B (en) Path planning method and device for recommending lane abrupt change
EP3779363B1 (en) Method and system for vehicle routing based on parking probabilities
Jiang et al. A review of traffic behaviour and intelligent driving at roundabouts based on a microscopic perspective
CN114407919B (en) Collision detection method and system based on automatic driving
CN115339441A (en) Vehicle trajectory prediction method and device, storage medium and processor
CN113778102A (en) AVP global path planning system, method, vehicle 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210309