CN113859267A - Route decision method and device and vehicle - Google Patents

Route decision method and device and vehicle Download PDF

Info

Publication number
CN113859267A
CN113859267A CN202111252800.9A CN202111252800A CN113859267A CN 113859267 A CN113859267 A CN 113859267A CN 202111252800 A CN202111252800 A CN 202111252800A CN 113859267 A CN113859267 A CN 113859267A
Authority
CN
China
Prior art keywords
vehicle
path
lane
obstacle
cost
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.)
Granted
Application number
CN202111252800.9A
Other languages
Chinese (zh)
Other versions
CN113859267B (en
Inventor
温勇兵
李攀
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.)
Guangzhou Xiaopeng Motors Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Autopilot 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 Guangzhou Xiaopeng Autopilot Technology Co Ltd filed Critical Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority to CN202111252800.9A priority Critical patent/CN113859267B/en
Publication of CN113859267A publication Critical patent/CN113859267A/en
Application granted granted Critical
Publication of CN113859267B publication Critical patent/CN113859267B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
    • 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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a path decision method, a path decision device and a vehicle. The method comprises the following steps: generating a predicted trajectory of the obstacle from the identified obstacle; matching the obstacle to a corresponding lane according to the predicted track of the obstacle; selecting a target lane of the self-vehicle from the selectable lanes according to a collision risk value of the self-vehicle and an obstacle in the selectable lanes; and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle. The scheme provided by the application can be combined with the surrounding environment to generate a specific recommended path, the requirement of automatic driving of the vehicle is met, and the safety of the automatic driving vehicle is guaranteed.

Description

Route decision method and device and vehicle
Technical Field
The application relates to the technical field of automatic driving, in particular to a path decision method, a path decision device and a vehicle.
Background
With the development of science and technology, the automatic driving technology of vehicles is more mature. In an autonomous driving system of a vehicle, a behavior decision framework is responsible for making path, speed, priority and safety decisions on structured roads, intersections and open scenes, respectively, to enable the autonomous driving vehicle to observe and recognize its surroundings by using various sensors and to perform autonomous navigation tasks with little or no human intervention. Behavioral decisions, similar to motion planning, can be broken down into path decisions and velocity decisions.
The path decision in the related technology is mainly based on rules to carry out decision, and for a complex scene, interactive information with surrounding vehicles is not used, and a specific recommended path is not given, so that the requirement of automatic driving of the vehicle cannot be met.
Disclosure of Invention
In order to solve or partially solve the problems in the related art, the application provides a path decision method, a path decision device and a vehicle, which can generate a specific recommended path by combining with the surrounding environment, meet the requirement of automatic driving of the vehicle and ensure the safety of the automatic driving vehicle.
A first aspect of the present application provides a path decision method, including:
generating a predicted trajectory of the obstacle from the identified obstacle;
matching the obstacle to a corresponding lane according to the predicted track of the obstacle;
selecting a target lane of the self-vehicle from the selectable lanes according to a collision risk value of the self-vehicle and an obstacle in the selectable lanes;
and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle.
In one embodiment, the generating the candidate path according to the target lane sample includes:
sampling at a set first distance interval between the current position of the vehicle in the lane and the target lane by taking the current position of the vehicle in the lane as a starting point to obtain a plurality of sampling positions;
sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position;
and connecting the sampling nodes of each sampling position in the plurality of sampling positions to generate a plurality of candidate paths of the self vehicle.
In one embodiment, the selecting, from the candidate routes, a candidate route with a low route cost as the recommended route of the own vehicle includes: determining a path cost for each of the candidate paths;
and selecting a candidate route with low route cost as the recommended route of the self-vehicle.
In one embodiment, the determining the path cost of each of the candidate paths includes:
determining the path cost of each segmented path of each candidate path in the candidate paths;
and adding the path cost of each segmented path to obtain the path cost of each candidate path.
In an embodiment, the determining the path cost of each segment path of each candidate path of the candidate paths includes:
weighting each subsection path of each candidate path according to the preset path cost to obtain the path cost of each subsection path,
wherein the preset path cost comprises at least one of: path smoothness cost, lane centering cost, path consistency cost, static obstacle cost, dynamic obstacle cost.
In one embodiment, the selecting a target lane of the vehicle from the selectable lanes according to a collision risk value of the vehicle with an obstacle in the selectable lanes includes:
obtaining a collision risk coefficient of the vehicle and the obstacle in the selectable lane according to the predicted track of the vehicle and the predicted track of the obstacle in the selectable lane;
determining a collision risk parameter of the vehicle and the obstacle in the selectable lane according to the collision risk coefficient of the vehicle and the obstacle in the selectable lane;
determining a collision risk value of the vehicle and the obstacle in the selectable lane according to the collision risk parameter of the vehicle and the obstacle in the selectable lane;
and selecting a target lane of the self vehicle in the selectable lanes according to the collision risk value of the self vehicle and the obstacle in the selectable lanes.
In an embodiment, the collision risk factor comprises at least one of a collision time, a braking time, a minimum safety margin.
A second aspect of the present application provides a path decision apparatus, including:
the obstacle identification module is used for generating a predicted track of the obstacle according to the identified obstacle;
the obstacle matching module is used for matching the obstacles to the corresponding lanes according to the predicted track of the obstacles generated by the obstacle recognition module;
the lane selection module is used for selecting a target lane of the vehicle from the selectable lanes according to the collision risk value of the vehicle and the obstacle in the selectable lanes;
and the path selection module is used for generating candidate paths according to the target lane samples selected by the lane selection module, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle.
In one embodiment, the path selection module comprises:
the sampling module is used for sampling between the current position of the vehicle in the lane as a starting point and the target lane selected by the lane selection module at a set first distance interval to obtain a plurality of sampling positions, and sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position;
the path generation module is used for connecting the sampling node of each sampling position in the plurality of sampling positions obtained by the sampling module and generating a plurality of candidate paths of the self-vehicle;
a path cost calculation module for determining a path cost for each of the candidate paths;
and the selection module is used for selecting the candidate path with low path cost determined by the path cost calculation module as the recommended path of the self vehicle.
A third aspect of the application provides a vehicle comprising an apparatus as described above.
A fourth aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A fifth aspect of the present application provides a computer-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the method as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
according to the technical scheme, after the obstacles are matched to the corresponding lanes according to the predicted track of the obstacles, the target lane of the vehicle is selected from the selectable lanes according to the collision risk value of the vehicle and the obstacles in the selectable lanes; and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle. Through the processing, the candidate routes can be generated by utilizing the information of the own vehicle and the surrounding environment, and the recommended route with low route cost can be selected from the candidate routes, so that the driving requirement of complex automatic driving of the vehicle is met, and the safety of the automatic driving vehicle can be guaranteed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a schematic flow chart of a path decision method according to an embodiment of the present application;
fig. 2 is another flow chart diagram illustrating a path decision method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an alternative lane of a path decision method shown in an embodiment of the present application;
fig. 4 is a scene schematic diagram of a candidate path of a path decision method according to an embodiment of the present application;
fig. 5 is a schematic coordinate diagram of a candidate path of a path decision method according to an embodiment of the present application;
fig. 6 is a schematic diagram of sampling candidate paths in a path decision method according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a path decision device according to an embodiment of the present application;
fig. 8 is another schematic structural diagram of a path decision device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the accompanying drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
The embodiment of the application provides a path decision method which can be used for generating a specific recommended path by combining with the surrounding environment and meeting the requirement of automatic driving of a vehicle.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a path decision method according to an embodiment of the present application.
Referring to fig. 1, a path decision method includes:
in S101, a predicted trajectory of the obstacle is generated from the recognized obstacle.
The self-vehicle can acquire the environmental information around the self-vehicle through the sensor, identify the obstacles around the self-vehicle and generate the predicted track of the obstacles according to the identified obstacles.
In S102, the obstacle is matched to the corresponding lane according to the predicted trajectory of the obstacle.
In this step, the position, speed, acceleration, orientation, and the like of the obstacle may be obtained from the predicted trajectory of the obstacle. Based on the position of the predicted trajectory of the obstacle, the obstacle may be matched into the corresponding lane, for example, into the own lane, an adjacent lane of the own lane, or another lane other than the adjacent lane.
In S103, a target lane of the host vehicle is selected from the selectable lanes according to a collision risk value of the host vehicle with an obstacle in the selectable lane.
According to the magnitude of the collision risk value of the vehicle and the obstacle in the selectable lane, the lane changing operation of the vehicle can be triggered, and the target lane is selected as the lane to be changed from the selectable lane. The selectable lanes comprise a local lane and adjacent lanes of the vehicle, and the adjacent lanes comprise a left lane and a right lane of the local lane.
In S104, candidate routes are generated from the target lane samples, and a candidate route with a low route cost is selected from the candidate routes as a recommended route for the own vehicle.
Generating candidate paths from the target lane samples may include: sampling at a set first distance interval between a current position of a vehicle in a lane and a target lane of the vehicle by taking the current position of the vehicle in the lane as a starting point to obtain a plurality of sampling positions; sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position; and connecting the sampling nodes of each sampling position in the plurality of sampling positions to generate a plurality of candidate paths of the self vehicle.
Selecting a candidate route with low route cost from the candidate routes as a recommended route of the own vehicle may include: determining a path cost of each candidate path in the candidate paths; and selecting a candidate route with low route cost as the recommended route of the self vehicle.
Wherein, the path cost of each segment path of each candidate path in the candidate paths can be determined; and adding the path cost of each segmented path to obtain the path cost of each candidate path.
Determining the path cost of each segment path of each candidate path in the candidate paths may include: performing weighting operation on each segmented path of each candidate path according to a preset path cost to obtain the path cost of each segmented path, wherein the preset path cost comprises at least one of the following items: path smoothness cost, lane centering cost, path consistency cost, static obstacle cost, dynamic obstacle cost.
According to the embodiment, after the obstacle is matched to the corresponding lane according to the predicted track of the obstacle, the target lane of the vehicle is selected from the selectable lanes according to the collision risk value of the vehicle and the obstacle in the selectable lanes; and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the own vehicle. Through the processing, the candidate routes can be generated by utilizing the information of the own vehicle and the surrounding environment, and the recommended route with low route cost can be selected from the candidate routes, so that the driving requirement of complex automatic driving of the vehicle is met, and the safety of the automatic driving vehicle can be guaranteed.
Fig. 2 is another flow chart diagram of a path decision method according to an embodiment of the present application. Fig. 2 describes the solution of the present application in more detail with respect to fig. 1.
Referring to fig. 2, a path decision method includes:
in S201, predicted trajectories of the own vehicle and the obstacle are acquired.
The vehicle can sense the environmental information around the vehicle through sensors such as vision sensors, millimeter wave radars and laser radars, identify obstacles around the vehicle, which can include pedestrians and vehicles, and can also include unfavorable passing or non-passing railings in other roads, etc. According to the identification of the obstacle of the current frame of the shot image, a tag can be generated for the obstacle of the current frame, and the tag for the obstacle can include: blind spot obstacles, pedestrians (e.g., off-road pedestrians, in-road stationary pedestrians, in-road moving pedestrians, etc.), vehicles (e.g., off-road stationary vehicles, longitudinally distant stationary vehicles, roadside left and right stationary vehicles, oncoming front vehicles, crossing vehicles, oncoming vehicles, left rear vehicles), etc.
The predicted track can be generated for each obstacle according to the historical track and the current state of each obstacle, the historical track of each obstacle can comprise historical position and historical speed, the current state of each obstacle can comprise the current position, speed, acceleration and orientation of each obstacle, and the predicted track of each obstacle can comprise the predicted position and speed. For vehicles around the own vehicle, a probabilistic predictive model (e.g., EKF (Extended Kalman Filter), UKF (Unscented Kalman Filter)) or an advanced probabilistic predictive model using data driving (e.g., LSTM-RNN (Long Short-Term Memory-Recurrent Neural Network), which is a variation of the Recurrent Neural Network), may be employed to predict the position and velocity of the vehicle based on its current position, velocity, acceleration, and orientation.
The predicted trajectory of the own vehicle may be a trajectory under Control input calculated by a Model Predictive Control (MPC) algorithm using a vehicle motion Model, or may be a trajectory planned last time.
In S202, an obstacle is matched to a corresponding lane according to the predicted trajectory of the obstacle.
In this step, the position, speed, acceleration, orientation, and the like of the obstacle may be obtained from the predicted trajectory of the obstacle. Based on the location of the predicted trajectory of the obstacle, the obstacle may be matched into the corresponding lane.
In S203, a collision risk value between the host vehicle and the obstacle in the selectable lane is obtained based on the predicted trajectory of the host vehicle and the predicted trajectory of the obstacle in the selectable lane.
As shown in fig. 3, the selectable lanes of the host vehicle include a host vehicle lane 301 where the host vehicle is currently located, a left lane 302 adjacent to the left side of the host vehicle lane 301 where the host vehicle is currently located, and a right lane 303 adjacent to the right side of the host vehicle lane 301 where the host vehicle is currently located.
The current selectable lanes of the vehicle comprise a lane 301, a left lane 302 and a right lane 303, and the road area of the selectable lanes of the vehicle can be divided into six areas: a front 3011, a rear front 3012, a front left 3021, a rear left 3022, a front right 3031, and a rear right 3032. The collision risk values of the own vehicle entering the six areas are evaluated according to the position and the speed of the own vehicle in the current lane 301 and the position and the speed of the obstacle in the current optional lane of the own vehicle to determine whether the area can be safely entered. Six zones in the selectable lane are determined as a dangerous zone and a safe zone according to the collision risk value of the vehicle and the obstacle in the selectable lane, for example, the safe zone in fig. 3 includes a front 3011, a rear 3012, a rear left 3022 and a front right 3031, and the dangerous zone includes a front left 3021 and a rear right 3032. Wherein the hazardous area and the safe area can be distinguished by different colors but is not limited thereto.
Current traffic conditions may be identified and evaluated based on the location, speed, acceleration, orientation of the host vehicle and the obstacles within the selectable lanes. For example, the collision risk of the vehicle entering each area in the selectable lane and the obstacle in the selectable lane under the current traffic condition is evaluated, and the collision risk value of the vehicle and each obstacle in the selectable lane is obtained, wherein the collision risk value can comprise a front collision risk value and a rear collision risk value. The collision risk value of the vehicle and each obstacle can be obtained by using collision risk coefficients of the vehicle and the obstacle, such as Time To Collision (TTC), Time To Brake (TTB), Minimum Safety Margin (MSM) and the like.
If two vehicles in the selectable lane continue to travel at the respective current velocities and predicted trajectories, the time required for the two vehicles to collide is taken as the time-to-collision (TTC). When the speed of the vehicle is very close to the vehicle in the adjacent lane, a small TTC value will be generated at this time, in which case it is very dangerous to perform the lane change operation. Evaluating the risk of collision using only the time to collision may be more difficult to evaluate the risk of collision of vehicles in adjacent lanes that are very close to the speed of the own vehicle, and therefore evaluating the risk of collision may further utilize the braking time and a minimum safety margin.
If the vehicle in the selectable lane keeps its current speed and predicted trajectory, the time required for the vehicle to collide with other vehicles is taken as the braking time. And a Minimum Safety Margin (MSM) may be the distance required to maintain minimum safety for two vehicles in the selectable lane.
In the step, according to the predicted track of the vehicle and the predicted track of the obstacle in the selectable lane, the collision risk coefficient of the vehicle and the obstacle in the selectable lane is obtained; obtaining collision risk parameters of the vehicle and the barriers in the selectable lane according to the obtained collision risk coefficients of the vehicle and the barriers in the selectable lane; and obtaining a collision risk value of the vehicle and the obstacle in the selectable lane according to the obtained collision risk parameter of the vehicle and the obstacle in the selectable lane.
Wherein each collision risk coefficient may be defined as:
Figure BDA0003322970820000081
Figure BDA0003322970820000091
MSM＝|sn-se|
in the formula, snAnd vnRespectively the position and speed of the nearest obstacle in each designated area at a certain time t. Variable seAnd veRespectively the position and the speed of the own vehicle at the time t.
With respect to the three collision risk coefficients, each risk parameter corresponding to TTC, TTB and MSM is defined as:
Figure BDA0003322970820000092
Figure BDA0003322970820000093
Figure BDA0003322970820000094
in the formula (I), the compound is shown in the specification,
Figure BDA0003322970820000095
and
Figure BDA0003322970820000096
the thresholds, TTC, TTB and MSM respectively, may be modified by vehicle sensor specifications, national traffic regulations, international safety standards, or per system specification.
The collision risk values may include a forward collision risk value and a rearward collision risk value. R (ttb) and r (msn) affect the front zone, and r (ttc) and r (msn) affect the rear zone, as defined for each collision risk factor. By combining the risk parameters r (ttc), r (ttb) and r (msn), the front and rear collision risk values may be defined as:
Figure BDA0003322970820000097
Figure BDA0003322970820000098
wherein R (FORWARD) is a front collision risk value, and R (BACKWARD) is a rear collision risk value.
In order to improve the calculation efficiency, when the distance between the vehicles is measured, the shape of the vehicles is composed of three disks with the same diameter, the circle center of the first disk is coincided with the middle point of the rear axle of the vehicle, the circle center of the second disk is coincided with the center of the vehicle, the circle center of the third disk is coincided with the center of the front axle of the vehicle, and the diameter of the third disk is equal to the width of the vehicle. For example, when measuring the vehicle in front of the vehicle, the shape of the vehicle in front of the vehicle is composed of three disks with the same diameter, the circle center of the first disk is coincided with the middle point of the rear axle of the vehicle, the circle center of the second disk is coincided with the center of the vehicle, the circle center of the third disk is coincided with the center of the front axle of the vehicle, and the diameter of the third disk is equal to the width of the vehicle. The distance between the self vehicle and the vehicle in front of the self vehicle is the distance between the circle center of the third disc of the self vehicle and the circle center of the first disc of the vehicle in front of the self vehicle.
In S204, the selectable lane in which the collision risk value of the vehicle with the obstacle in the selectable lane is smaller than the set risk threshold is selected as the target lane of the vehicle.
The vehicle can select a target lane of the vehicle from the selectable lanes according to the obtained collision risk value of the vehicle and the obstacle in the selectable lanes. For the current lane where the own vehicle is located, the own vehicle generally cannot run in the reverse direction, so the rear collision risk value generally cannot influence the operation decision. The lower speed of the front vehicle closest to the self vehicle in the selectable lane can trigger the lane changing operation of the self vehicle so as to improve the passing efficiency. For example, if the front collision risk value of the selectable lane is greater than or equal to 1, it indicates that the own vehicle collides with a front obstacle, the own vehicle cannot perform lane change operation, and the lane change operation of the own vehicle is not triggered; if the front collision risk value of the selectable lane is less than 1, the collision between the vehicle and the front obstacle is avoided, the vehicle can perform lane changing operation, and the lane changing operation of the vehicle can be triggered to improve the passing efficiency.
For a left lane adjacent to the left side of the lane where the self-vehicle is located, a fast-running vehicle behind (left rear) and a slow-running vehicle in front (left front) or a stopped vehicle in front of the left lane are checked, and whether the adjacent left lane can enter safely or not is evaluated according to a front collision risk value of the self-vehicle and an obstacle of the adjacent left lane so as to prevent the collision risk of the self-vehicle in the lane changing process to the adjacent left lane. For example, if the front collision risk value of the own vehicle with the obstacle of the adjacent left lane is less than 1, the own vehicle may safely enter the adjacent left lane, and the adjacent left lane whose collision risk value of the own vehicle with the obstacle is less than 1 may be selected as the target lane of the own vehicle.
For the right lane on the adjacent right side of the own lane where the own vehicle is located, a rear (right rear) fast running vehicle and a front (right front) slow running vehicle or a stopped vehicle of the adjacent right lane are checked, and whether the adjacent right lane can enter safely or not is evaluated according to a front collision risk value of the own vehicle and an obstacle of the adjacent right lane so as to prevent the collision risk of the own vehicle in the process of changing lanes to the adjacent right lane. For example, if the front collision risk value of the own vehicle with the obstacle of the adjacent right lane is less than 1, the own vehicle can safely enter the adjacent right lane, and the adjacent right lane with the collision risk value of the own vehicle with the obstacle less than 1 is selected as the target lane of the own vehicle.
In order to ensure the safety of lane changing of the vehicle, the gaps between the vehicle and the nearest rear vehicle of the target lane, between the vehicle and the nearest front vehicle in front of the vehicle, and between the vehicle in the nearest rear of the target lane and the nearest front vehicle of the target lane need to be ensured to be large enough; for the self-vehicle to keep the current road, the self-vehicle needs to ensure that the clearance with the previous vehicle exceeds a certain safe distance slk：
slk＝ve*τk+ck
In the formula, veIndicating the longitudinal speed, τ, of the vehiclekIs a constant lane keeping time interval, ckIs the minimum lane keeping distance.
For changing the lane of a bicycle, it is necessary to take into accountConsider the relative speed between the host vehicle and the nearest vehicle in front of and behind the target lane. A greater distance is required when the speed of the vehicle closest to the rear of the target lane is greater than the speed of the vehicle closest to the front of the target lane. The safety distance can then be designed as slc：
Figure BDA0003322970820000111
In the formula, vsRepresenting the longitudinal speed of the vehicle in the target lane, dsRepresenting the relative longitudinal distance, τ, of the nearest vehicle to the host vehicle in the target lanec1Is the time interval of the relative speed of a lane change, tauc2Is the minimum time interval allowed for a lane change, ccIs the minimum gap for lane change. dsGreater than 0 indicates that the target lane vehicle is in front of the own vehicle.
In addition, the speed of the front vehicle needs to be greater than or equal to the speed of the self vehicle and the rear vehicle to ensure that the gap is not reduced, and the length of the remaining path of the lane where the self vehicle is located currently needs to be large enough to meet the length of the lane change plan.
In S205, a plurality of candidate routes are generated between the own lane and the target lane of the own vehicle by sampling.
Sampling at a set first distance interval between a current position of a vehicle in a lane and a target lane of the vehicle by taking the current position of the vehicle in the lane as a starting point to obtain a plurality of sampling positions; sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position; and connecting the sampling nodes of each sampling position in the plurality of sampling positions to generate a plurality of candidate paths of the self vehicle.
As shown in fig. 4 and 5, the x-axis direction in fig. 4 is the transverse direction, and the y-axis direction is the longitudinal direction. The geometry of the road is determined by the center line of the lane, and a plurality of sampling positions are obtained by sampling the end point between the own lane of the own vehicle and the target lane in the transverse direction at a set first distance interval ds with the current position of the own vehicle in the own lane as the starting point in the Frenet coordinate system. For each sampling position 401 of the plurality of sampling positions, sampling is performed at a set second distance interval dl in the longitudinal direction, obtaining a plurality of sampling nodes 402 for each sampling position 401. A sampling space is generated from a plurality of sampling nodes 402 of each sampling location 401 of a plurality of sampling locations. The plurality of sampling nodes in the sampling space can be smoothly connected by using a spline curve, a spiral line or a Bezier curve to generate a plurality of candidate paths of the self-vehicle.
In S206, a path cost for each of the plurality of candidate paths is determined.
The multiple candidate paths generated by the smooth join may be traded off between security, smoothness, accuracy, and consistency.
As shown in fig. 6, discrete sampling may be performed on each candidate path of the plurality of candidate paths to obtain a plurality of discrete sampling points for each candidate path of the plurality of candidate paths:
Figure BDA0003322970820000121
Figure BDA0003322970820000122
according to the predicted track of the vehicle, the predicted track of the obstacle and the discrete sampling points of each candidate path of the candidate paths, the path cost of each subsection path of each candidate path in the candidate paths can be determined; and adding the path cost of each segmented path to obtain the path cost of each candidate path.
The method may further include performing weighting operation on each segment path of each candidate path according to a preset path cost to obtain a path cost of each segment path, where the preset path cost includes at least one of the following: path smoothness cost, lane centering cost, path consistency cost, static obstacle cost, dynamic obstacle cost. When the weight is set through the weighted operation, the weight of the obstacle collision cost can be set to be larger, and then the road centering cost is set.
(1) Cost of path smoothness: calculating a path smoothness cost c using curvature in consideration of a running comfort level when a vehicle moves laterallysmooth：
Figure BDA0003322970820000123
Where N represents the number of discrete points in the path smoothness cost of the evaluation candidate path; kappaiThe curvature of the ith candidate path point; kappamaxDetermining a minimum turning radius performable by the vehicle; omegasmoothIs a path smoothness cost weight. Cost of smoothness csmoothAccording to the curvature calculation of the candidate path points, smooth running during the transverse motion of the vehicle can be guaranteed, and the running comfort during the transverse motion of the vehicle is guaranteed.
Since the candidate path is generated in the Frenet coordinate system, the curvature k in the cartesian coordinate system can be obtained by:
Figure BDA0003322970820000131
wherein A and B are defined as:
Figure BDA0003322970820000132
B＝sgn(1-lκr)
in the formula, κrThe curvature of the projected point of the path point on the reference line; l,
Figure BDA0003322970820000133
Respectively representing 0-order, 1-order and 2-order derivatives of a transverse position l and a longitudinal distance s in a Frenet coordinate system; sgn (.) is a sign function.
(2) Lane centering cost: for a single lane, the lane centering cost C is such that the candidate path is as close as possible to the desired lane centerline offsetcenterCan be as follows:
Figure BDA0003322970820000134
where N represents the number of discrete points in the cost of evaluating path smoothness of the candidate path, liIs the lateral offset of the vehicle at the ith candidate waypoint; ldestThe distance of the expected candidate path point from the center line of the road can be preset according to the requirement; lmaxThe maximum planning width can be the half width of the road, and when the deviation is larger than the half width of the road, the cost is infinite; omegarefCost weight for lane centering.
(3) Path consistency cost: the sudden change of direction of the path occurs due to the sudden appearance of an obstacle. In order to prevent significant differences between the current candidate path and the last planned path, the consistency of the paths must be considered. For example, let s1To s2For the coverage area of the last planned path, the path consistency cost may be:
Figure BDA0003322970820000135
where M represents the number of discrete points in the path consistency cost of the evaluation candidate path; lioIs the lateral deviation corresponding to the ith candidate path point with the same arc length s in the last planned path; omegaconsistentA path consistency cost weight; liIs the lateral offset of the vehicle at the ith candidate waypoint; lmaxFor maximum planned width, it may be the half width of the road.
(4) Static barrier cost: the distance from the vehicle footprint to the barrier polygon may be used as a measure of the static barrier potential energy cost.
And according to the increase of the distance between the obstacle and the initial position of the self-vehicle, the obstacle is expanded properly. The longitudinal expansion should be more pronounced than the transverse expansion of the barrier. The static barrier cost is:
Figure BDA0003322970820000141
in the formula (I), the compound is shown in the specification,m represents the number of discrete points in the static obstacle cost of the evaluation candidate path; d represents the minimum distance between the outline of the vehicle represented by the candidate path point and the polygon of the static obstacle; dsafeIs the minimum safe distance; omegastaticStatic barrier cost weights.
(5) Dynamic barrier cost: since the planning frequency is sufficiently high, it is reasonable that the velocity profile of the previous planning cycle is used to assess potential collisions with dynamic obstacles. When the last planned path length is shorter or no last planned speed curve exists, a reasonable self-track needs to be planned according to the current position, speed and acceleration information. For an evaluation point s on the candidate path, the time t required at the current position is obtained from the own trajectory, and the position (x, y) of the evaluation point s can be predicted from the predicted trajectory of the moving obstacle. For a fixed time t, a dynamic obstacle may be considered a static obstacle. Similar to the static barrier cost, the dynamic barrier cost is:
Figure BDA0003322970820000142
different from the expansion mode of the static barrier, the expansion amplitude of the dynamic barrier is increased along with the extension of the prediction time. K represents a proportionality coefficient (a relatively large constant value) for increasing the cost of the collision risk.
Wherein n represents the number of discrete points in the dynamic barrier cost of the evaluation candidate path; d represents the minimum distance between the outline of the vehicle represented by the candidate path point and the dynamic obstacle polygon; dsafeIs the minimum safe distance; omegadynamicIs a dynamic barrier cost weight.
In S207, a candidate route with a low route cost is selected as the recommended route of the own vehicle.
The path cost for each candidate path of the plurality of candidate paths may be:
L＝Csmooth+Ccenter+Cconsistent+Cstatic+Cdynamic
and comparing the path cost L of each candidate path of the plurality of candidate paths, and selecting the candidate path with the small path cost L from the plurality of candidate paths as the recommended path of the vehicle. For example, the candidate route with the smallest route cost L may be selected as the recommended route of the own vehicle without being limited thereto.
In the embodiment of the application, the candidate paths can be generated by utilizing the information of the self vehicle and the surrounding environment, and the recommended path with low path cost can be selected from the candidate paths, so that the driving requirement of complex automatic driving of the vehicle is met, and the safety of the automatic driving vehicle can be guaranteed.
Further, in the embodiment of the application, the collision risk value of the vehicle in the selectable lane can be obtained according to the predicted track of the vehicle and the predicted track of the obstacle in the selectable lane; according to the obtained collision risk value of the vehicle and the obstacle in the selectable lane, the target lane of the vehicle is selected from the selectable lanes, the vehicle can be prevented from colliding with the vehicle in the target lane in the lane changing process, and lane changing safety is guaranteed.
Further, in the embodiment of the application, a candidate route with low route cost can be selected as the recommended route of the self-vehicle between the self-vehicle lane and the target lane, the recommended route meeting the route cost constraint can be generated by utilizing the interactive information of the self-vehicle and the surrounding vehicles, the driving requirement of complex automatic driving of the vehicle is met, and the safety of lane changing of the automatic driving vehicle can also be guaranteed.
Corresponding to the embodiment of the application function implementation method, the application also provides a path decision device, a vehicle, an electronic device and corresponding embodiments.
Fig. 7 is a schematic structural diagram of a path decision device according to an embodiment of the present application.
Referring to fig. 7, a path decision apparatus 70 includes: an obstacle recognition module 71, an obstacle matching module 72, a lane selection module 73, a path selection module 74.
And an obstacle identification module 71, configured to generate a predicted trajectory of the obstacle according to the identified obstacle. The obstacle recognition module 71 may recognize an obstacle around the host vehicle by obtaining environmental information around the host vehicle through a sensor.
And the obstacle matching module 72 is used for matching the obstacles to the corresponding lanes according to the predicted track of the obstacles generated by the obstacle recognition module 71. The obstacle matching module 72 may derive the position, velocity, acceleration, orientation, etc. of the obstacle from the predicted trajectory of the obstacle. Based on the position of the predicted trajectory of the obstacle, the obstacle may be matched into the corresponding lane, for example, into the own lane, an adjacent lane of the own lane, or another lane other than the adjacent lane.
And the lane selection module 73 is used for selecting a target lane of the vehicle from the selectable lanes according to the collision risk value of the vehicle and the obstacle in the selectable lanes. The selectable lanes comprise a local lane and adjacent lanes of the vehicle, and the adjacent lanes comprise a left lane and a right lane of the local lane.
And a route selection module 74, configured to generate candidate routes according to the target lane samples selected by the lane selection module 73, and select a candidate route with a low route cost from the candidate routes as a recommended route of the own vehicle. The route selection module 74 may take the current position of the vehicle in the lane as a starting point, and perform sampling between the lane of the vehicle and the target lane at a set first distance interval to obtain a plurality of sampling positions; sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position; and connecting the sampling nodes of each sampling position in the plurality of sampling positions to generate a plurality of candidate paths of the self vehicle. Path selection module 74 may determine a path cost for each of the candidate paths; and selecting a candidate route with low route cost as the recommended route of the self vehicle.
According to the embodiment of the application, after the obstacle is matched to the corresponding lane according to the predicted track of the obstacle, the target lane of the vehicle is selected from the selectable lanes according to the collision risk value of the vehicle and the obstacle in the selectable lanes; and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the own vehicle. Through the processing, the candidate routes can be generated by utilizing the information of the own vehicle and the surrounding environment, and the recommended route with low route cost can be selected from the candidate routes, so that the driving requirement of complex automatic driving of the vehicle is met, and the safety of the automatic driving vehicle can be guaranteed.
Fig. 8 is another schematic structural diagram of a path decision device according to an embodiment of the present application.
Referring to fig. 8, a route decision device 80 includes an obstacle recognition module 71, an obstacle matching module 72, a lane selection module 73, and a route selection module 74. The path selection module 74 may include: a sampling module 741, a path generation module 742, a path cost calculation module 743, and a selection module 744.
The functions of the obstacle recognition module 71, the obstacle matching module 72, the lane selection module 73, and the path selection module 74 may be referred to in the description of fig. 7.
The sampling module 741 is configured to sample between the own vehicle and the target lane selected by the lane selection module at a set first distance interval with a current position of the own vehicle in the own vehicle as a starting point to obtain a plurality of sampling positions, and sample at a set second distance interval for each of the plurality of sampling positions to obtain a plurality of sampling nodes for each of the sampling positions.
And a path generating module 742, configured to connect the sampling node of each of the plurality of sampling positions obtained by the sampling module 741 to generate a plurality of candidate paths of the vehicle.
A path cost calculating module 743, configured to determine a path cost of each of the candidate paths.
The selecting module 744 is configured to select the candidate route with the low route cost determined by the route cost calculating module 743 as the recommended route of the host vehicle.
In an embodiment of the present application, a vehicle is further provided, and the vehicle includes the above-mentioned route decision device. The function of the vehicle path decision device can refer to fig. 7 or fig. 8, and will not be described herein.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 9 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 9, the electronic device 90 includes a memory 901 and a processor 902.
The Processor 902 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 901 may include various types of storage units, such as a system memory, a Read Only Memory (ROM), and a permanent storage device. Wherein the ROM may store static data or instructions for the processor 902 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. In addition, memory 901 may comprise any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash, programmable read-only memory), magnetic and/or optical disks, among others. In some embodiments, memory 901 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 901 has stored thereon executable code that, when processed by the processor 902, may cause the processor 902 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the various steps of the above-described methods in accordance with the present application.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (11)

1. A path decision method, comprising:
generating a predicted trajectory of the obstacle from the identified obstacle;
matching the obstacle to a corresponding lane according to the predicted track of the obstacle;
selecting a target lane of the self-vehicle from the selectable lanes according to a collision risk value of the self-vehicle and an obstacle in the selectable lanes;
and generating candidate paths according to the target lane samples, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle.
2. The method of claim 1, wherein generating candidate paths from target lane samples comprises:
sampling at a set first distance interval between the current position of the vehicle in the lane and the target lane by taking the current position of the vehicle in the lane as a starting point to obtain a plurality of sampling positions;
sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position;
and connecting the sampling nodes of each sampling position in the plurality of sampling positions to generate a plurality of candidate paths of the self vehicle.
3. The method according to claim 1, wherein the selecting a candidate route with a low route cost from the candidate routes as the recommended route of the own vehicle comprises:
determining a path cost for each of the candidate paths;
and selecting a candidate route with low route cost as the recommended route of the self-vehicle.
4. The method of claim 3, wherein determining the path cost for each of the candidate paths comprises:
determining the path cost of each segmented path of each candidate path in the candidate paths;
and adding the path cost of each segmented path to obtain the path cost of each candidate path.
5. The method of claim 4, wherein determining the path cost for each segment path of each of the candidate paths comprises:
weighting each subsection path of each candidate path according to the preset path cost to obtain the path cost of each subsection path,
wherein the preset path cost comprises at least one of: path smoothness cost, lane centering cost, path consistency cost, static obstacle cost, dynamic obstacle cost.
6. The method of claim 1, wherein selecting the target lane of the host vehicle among the selectable lanes according to a collision risk value of the host vehicle with an obstacle within the selectable lanes comprises:
obtaining a collision risk coefficient of the vehicle and the obstacle in the selectable lane according to the predicted track of the vehicle and the predicted track of the obstacle in the selectable lane;
determining a collision risk parameter of the vehicle and the obstacle in the selectable lane according to the collision risk coefficient of the vehicle and the obstacle in the selectable lane;
determining a collision risk value of the vehicle and the obstacle in the selectable lane according to the collision risk parameter of the vehicle and the obstacle in the selectable lane;
and selecting a target lane of the self vehicle in the selectable lanes according to the collision risk value of the self vehicle and the obstacle in the selectable lanes.
7. The method of claim 6, wherein the collision risk factors include at least one of collision time, braking time, minimum safety margin.
8. A path decision device, comprising:
the obstacle identification module is used for generating a predicted track of the obstacle according to the identified obstacle;
the obstacle matching module is used for matching the obstacles to the corresponding lanes according to the predicted track of the obstacles generated by the obstacle recognition module;
the lane selection module is used for selecting a target lane of the vehicle from the selectable lanes according to the collision risk value of the vehicle and the obstacle in the selectable lanes;
and the path selection module is used for generating candidate paths according to the target lane samples selected by the lane selection module, and selecting the candidate path with low path cost from the candidate paths as the recommended path of the self-vehicle.
9. The apparatus of claim 8, wherein the path selection module comprises:
the sampling module is used for sampling between the current position of the vehicle in the lane as a starting point and the target lane selected by the lane selection module at a set first distance interval to obtain a plurality of sampling positions, and sampling at a set second distance interval for each sampling position in the plurality of sampling positions to obtain a plurality of sampling nodes of each sampling position;
the path generation module is used for connecting the sampling node of each sampling position in the plurality of sampling positions obtained by the sampling module and generating a plurality of candidate paths of the self-vehicle;
a path cost calculation module for determining a path cost for each of the candidate paths;
and the selection module is used for selecting the candidate path with low path cost determined by the path cost calculation module as the recommended path of the self vehicle.
10. A vehicle, characterized in that it comprises a device according to claim 8 or 9.
11. A computer-readable storage medium having executable code stored thereon, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-7.
CN202111252800.9A 2021-10-27 2021-10-27 Path decision method and device and vehicle Active CN113859267B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111252800.9A CN113859267B (en) 2021-10-27 2021-10-27 Path decision method and device and vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111252800.9A CN113859267B (en) 2021-10-27 2021-10-27 Path decision method and device and vehicle

Publications (2)

Publication Number Publication Date
CN113859267A true CN113859267A (en) 2021-12-31
CN113859267B CN113859267B (en) 2023-08-25

Family

ID=78998334

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111252800.9A Active CN113859267B (en) 2021-10-27 2021-10-27 Path decision method and device and vehicle

Country Status (1)

Country Link
CN (1) CN113859267B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle 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
CN115220449A (en) * 2022-07-14 2022-10-21 小米汽车科技有限公司 Path planning method and device, storage medium, chip and vehicle

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109949611A (en) * 2019-03-28 2019-06-28 百度在线网络技术（北京）有限公司 The lane change method, apparatus and storage medium of unmanned vehicle
CN111898804A (en) * 2020-07-10 2020-11-06 东风商用车有限公司 Road self-adaptive sampling method for local planning
CN112362074A (en) * 2020-10-30 2021-02-12 重庆邮电大学 Intelligent vehicle local path planning method under structured environment
CN112455445A (en) * 2020-12-04 2021-03-09 苏州挚途科技有限公司 Automatic driving lane change decision method and device and vehicle
CN112639849A (en) * 2020-01-17 2021-04-09 华为技术有限公司 Route selection method and route selection device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109949611A (en) * 2019-03-28 2019-06-28 百度在线网络技术（北京）有限公司 The lane change method, apparatus and storage medium of unmanned vehicle
CN112639849A (en) * 2020-01-17 2021-04-09 华为技术有限公司 Route selection method and route selection device
CN111898804A (en) * 2020-07-10 2020-11-06 东风商用车有限公司 Road self-adaptive sampling method for local planning
CN112362074A (en) * 2020-10-30 2021-02-12 重庆邮电大学 Intelligent vehicle local path planning method under structured environment
CN112455445A (en) * 2020-12-04 2021-03-09 苏州挚途科技有限公司 Automatic driving lane change decision method and device and vehicle

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle and storage medium
CN115220449A (en) * 2022-07-14 2022-10-21 小米汽车科技有限公司 Path planning method and device, storage medium, chip and vehicle
CN115220449B (en) * 2022-07-14 2023-11-21 小米汽车科技有限公司 Path planning method, device, storage medium, chip 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
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

Also Published As

Publication number Publication date
CN113859267B (en) 2023-08-25

Similar Documents

Publication Publication Date Title
US11465619B2 (en) Vehicle collision avoidance based on perturbed object trajectories
CN113859267B (en) Path decision method and device and vehicle
US20220113723A1 (en) Lane change detection system and method for an autonomous vehicle
EP3474254B1 (en) Surrounding environment recognition device
US10266175B2 (en) Vehicle collision avoidance
CN108604421B (en) The travel control method of vehicle and the travel controlling system of vehicle
CN113932823A (en) Unmanned multi-target-point track parallel planning method based on semantic road map
CN110667578A (en) Lateral decision making system and lateral decision making determination method for automatic driving vehicle
CN110632921A (en) Robot path planning method and device, electronic equipment and storage medium
CN111552284A (en) Method, device, equipment and medium for planning local path of unmanned vehicle
CN112639849A (en) Route selection method and route selection device
CN113960996A (en) Planning method and device for obstacle avoidance path of driving device
US20200172098A1 (en) Multi-headed recurrent neural network (rnn) for multi-class trajectory predictions
US12036980B2 (en) Course prediction device, computer readable medium, and course prediction method
CN112577506B (en) Automatic driving local path planning method and system
KR102178992B1 (en) Method and Apparatus for Planning Car Motion
US11312373B2 (en) Vehicle detection and response
CN112660128A (en) Apparatus for determining lane change path of autonomous vehicle and method thereof
US20220314979A1 (en) Apparatus and Method for Controlling Driving of Vehicle
JP7037956B2 (en) Vehicle course prediction method, vehicle travel support method, and vehicle course prediction device
CN114103993A (en) Vehicle driving control device and method
CN114475649A (en) Automatic driving control device and automatic driving control method
KR20230167301A (en) High-Definition Map-based Local Path Planning Method and Apparatus for Dynamic and Static Obstacle Avoidance
US20220396290A1 (en) Apparatus for Controlling Vehicle, System Including Same and Method Thereof
WO2021157194A1 (en) Course planning device, course planning method, and course planning program

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
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20240228

Address after: 510000 No.8 Songgang street, Cencun, Tianhe District, Guangzhou City, Guangdong Province

Patentee after: GUANGZHOU XIAOPENG MOTORS TECHNOLOGY Co.,Ltd.

Country or region after: China

Address before: Room 46, room 406, No.1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou City, Guangdong Province

Patentee before: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right