CN113753047A - State machine, state machine switching method and unmanned automobile - Google Patents
State machine, state machine switching method and unmanned automobile Download PDFInfo
- Publication number
- CN113753047A CN113753047A CN202110949108.5A CN202110949108A CN113753047A CN 113753047 A CN113753047 A CN 113753047A CN 202110949108 A CN202110949108 A CN 202110949108A CN 113753047 A CN113753047 A CN 113753047A
- Authority
- CN
- China
- Prior art keywords
- lane
- state
- switching
- state machine
- unmanned vehicle
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 16
- 230000003068 static effect Effects 0.000 claims description 50
- 230000006399 behavior Effects 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 14
- 230000004888 barrier function Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000001373 regressive effect Effects 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/005—Handover processes
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention relates to the technical field of unmanned driving, in particular to a state machine, a state machine switching method and an unmanned automobile. When the state machine is in a lane returning state, whether the unmanned vehicle successfully returns to the lane is judged, if yes, the unmanned vehicle is switched to a line patrol state, and safety can be improved. When the state machine is in the line patrol state, whether the lane needs to be switched is judged according to the current driving road condition, if so, the lane is switched to the lane switching state, and the behavior of the unmanned automobile is enabled to accord with the road condition. From the three aspects, the behavior of the unmanned automobile in the driving process can be accurately and stably planned by switching the states through the state machine.
Description
Technical Field
The embodiment of the invention relates to the technical field of unmanned driving, in particular to a state machine, a state machine switching method and an unmanned automobile.
Background
Behavior control of unmanned vehicles during driving is an important part of the field of automotive driving. The behavior control depends on positioning information, perception information, prediction information, map information and global planning information, and determines real-time behaviors which the unmanned automobile should execute, so that automatic unmanned driving is realized.
At present, the switching method of the state machine mainly depends on the accuracy of the perception information and the prediction result, and when the perception information and the prediction result are wrong or jump, stable planning is often difficult to make.
Disclosure of Invention
The technical problem mainly solved by the embodiment of the invention is to provide a state machine, a state machine switching method and an unmanned automobile, which can accurately and stably plan the behavior of the unmanned automobile in the driving process.
In order to solve the technical problem, in a first aspect, an embodiment of the present invention provides a switching method for a state machine, where the state machine is disposed in an unmanned vehicle and is used for implementing behavior planning of the unmanned vehicle, and the state machine includes four working states, i.e., a start state, a return lane state, a line patrol state, and a lane-cut state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in a lane switching state, the state machine sends a command of switching from a current lane to a target lane to a local planning module of the unmanned vehicle; the switching method of the state machine comprises the following steps:
when the state machine is in a starting state, checking whether input information is complete and variables related to an initialization task are detected, and if yes, switching to a regression lane state;
when the state machine is in a lane returning state, judging whether the driverless automobile successfully returns to the lane, and if so, switching to a line patrol state;
and when the state machine is in the line patrol state, judging whether the lane needs to be switched or not according to the current driving road condition, and if so, switching to the lane switching state.
In some embodiments, when the state machine is in the line patrol state, whether lane switching is required is determined according to the current driving road condition, and if so, the step of switching to the lane switching state includes:
respectively calculating a traffic value of each lane, wherein the traffic value is the number of lanes required to be switched when the lanes are switched to a turning lane, and the turning lane is a lane corresponding to the unmanned automobile when the unmanned automobile turns in the process of driving to the terminal;
and judging whether the lane needs to be switched and a target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes.
In some embodiments, the step of determining whether the lane needs to be switched and the target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes includes:
if no static barrier exists in front of the current lane within a first preset distance, determining that lane switching is not needed;
if a static obstacle exists in the front of the current lane within the first preset distance, calculating the switching cost of each lane, and determining that the lane needs to be switched and the target lane are the lanes with the minimum switching cost.
In some embodiments, the step of calculating the switching cost of each lane includes:
calculating the switching cost of a lane i according to the following formula, wherein the lane i is any one of the lanes;
wherein, cost(i)J represents whether a static obstacle exists in front of the lane i within the first preset distance or not, j is 1 when the static obstacle exists in front of the lane i within the first preset distance, j is 0 when the static obstacle does not exist in front of the lane i within the first preset distance, a represents a traffic value of the lane i, d represents a traffic value of the lane i, and j represents whether a static obstacle exists in front of the lane i within the first preset distance or notiRepresenting the distance of a static obstacle in front of the lane i, d0The distance of a static obstacle in front of a current lane is represented, b represents whether the lane i has no static obstacle and has a dynamic obstacle in front, b is equal to 1 when the lane i has no static obstacle and has a dynamic obstacle in front, otherwise b is equal to 0, c represents whether a pedestrian is in front of the lane i, c is equal to 1 when the lane i has a pedestrian in front, otherwise c is equal to 0, eiThe distance of the pedestrian ahead.
In some embodiments, further comprising:
if the lane-switching state lasts for a preset time and the direction of the target lane is consistent with the direction indicated by a steering lamp of the unmanned automobile, controlling the unmanned automobile to change the lane to the target lane;
otherwise, switching to the line patrol state.
In some embodiments, further comprising:
and if the deviation between the unmanned automobile and the current lane is greater than a preset deviation threshold value, switching to a lane returning state.
And if the deviation between the unmanned automobile and the current lane is less than or equal to the preset deviation threshold value, switching to a line patrol state.
In some embodiments, if the state machine also includes a park state,
the method further comprises:
and if the distance between the unmanned automobile and the driving terminal is less than or equal to a second preset distance, switching to a parking state.
In some embodiments, if the state machine also includes a checkpointed state,
the method further comprises:
and when the distance between the unmanned vehicle and the check point is less than or equal to a third preset distance, switching to a check point state, wherein the check point is a position point on the driving path of the unmanned vehicle.
In order to solve the technical problem, in a second aspect, an embodiment of the present invention provides a state machine, where the state machine is disposed in an unmanned vehicle and is used for implementing behavior planning of the unmanned vehicle, and the state machine is at least provided with four working states, namely a start state, a lane return state, a line patrol state, and a lane change state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in a lane switching state, the state machine sends a command of switching from a current lane to a target lane to a local planning module of the unmanned vehicle; the state machine includes:
the checking unit is used for checking whether input information is complete and variables related to the initialization task are detected when the state machine is in a starting state, and if yes, switching to a regression lane state;
the first judging unit is used for judging whether the driverless automobile successfully returns to the lane or not when the state machine is in the lane returning state, and if so, switching to the line patrol state;
and the second judgment unit is used for judging whether the lane needs to be switched or not according to the current driving road condition when the state machine is in the line patrol state, and if so, switching to the lane switching state.
In order to solve the above technical problem, in a third aspect, an embodiment of the present invention provides an unmanned vehicle, including: at least one processor, and
a memory communicatively coupled to the at least one processor, wherein,
the memory stores a program or instructions executable by the at least one processor, which when executed by the processor implements the state machine switching method as described in the first aspect.
The embodiment of the invention has the following beneficial effects: different from the situation of the prior art, the state machine switching method and the unmanned vehicle provided by the embodiment of the invention have the advantages that when the state machine is in the starting state, whether input information is complete or not and variables related to an initialization task are checked, if yes, the state machine is switched to the lane returning state, the unmanned vehicle can be ensured to accurately return to the lane, and the method is a precondition for safe operation. When the state machine is in a lane returning state, whether the unmanned vehicle successfully returns to the lane is judged, if yes, the unmanned vehicle is switched to a line patrol state, and safety can be improved. When the state machine is in the line patrol state, whether the lane needs to be switched is judged according to the current driving road condition, if so, the lane is switched to the lane switching state, and the behavior of the unmanned automobile is enabled to accord with the road condition. From the three aspects, the behavior of the unmanned automobile in the driving process can be accurately and stably planned by switching the states through the state machine.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a driving scene diagram of an unmanned vehicle according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 3 is a state transition diagram of a state machine provided by an embodiment of the present application;
fig. 4 is a schematic flowchart of a switching method of a state machine according to an embodiment of the present disclosure.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that, if not conflicted, the various features of the embodiments of the invention may be combined with each other within the scope of protection of the present application. Additionally, while functional block divisions are performed in apparatus schematics, with logical sequences shown in flowcharts, in some cases, steps shown or described may be performed in sequences other than block divisions in apparatus or flowcharts. Further, the terms "first," "second," "third," and the like, as used herein, do not limit the data and the execution order, but merely distinguish the same items or similar items having substantially the same functions and actions.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the automatic driving and the auxiliary driving, the unmanned automobile can sense the surrounding environment through the sensor. The sensor may include, but is not limited to, millimeter wave radar, laser radar, ultrasonic radar, and vision sensor, among others. The unmanned automobile can detect and classify the surrounding environment of the automobile through the sensor, and transmits the information to the control module to form the decision of the future driving direction and speed of the automobile, and finally the decision is executed through the actuator to complete the whole process of auxiliary driving or automatic driving. It will be appreciated that control of the drone vehicle is of paramount importance when the drone vehicle is traveling on a road.
In one example, a driving scenario for an unmanned vehicle is shown in FIG. 1. In the scenario shown in fig. 1, the unmanned vehicle needs to travel from a starting point to a destination, the unmanned vehicle travels on a road with 4 lanes, specifically, lane # 2, when there is an obstacle in front of the unmanned vehicle, the unmanned vehicle needs to be controlled to switch lanes for avoiding, when the unmanned vehicle needs to turn right but is in a straight lane, the unmanned vehicle needs to be controlled to switch to a right-turn lane, when the unmanned vehicle arrives at the destination soon, the unmanned vehicle needs to be controlled to park, and the like. It is understood that the unmanned vehicle has other behaviors that need to be controlled, and the above examples are not intended to be illustrative, and do not limit the driving scene and the control behaviors of the unmanned vehicle.
At present, a method for planning the behavior of an unmanned automobile mainly depends on the accuracy of perception information and a prediction result, and when the perception information and the prediction result are wrong or jump, stable control is often difficult to be performed.
Therefore, in order to ensure that the unmanned vehicle is accurately and stably controlled in the driving process, an embodiment of the present application provides a switching method of a state machine, where the state machine is disposed in the unmanned vehicle, and is used for implementing behavior planning of the unmanned vehicle, and accurately and stably planning the behavior of the unmanned vehicle in the driving process.
It is understood that a state machine is a program model running on a processor, the state machine defining a plurality of states and transitions between the states. The state machine operates in response to a series of events that, when satisfied by certain trigger conditions, cause the state machine to migrate from a current state to a next state. Among the plurality of states defined, there is at least one initial state and at least one final state, the state machine starting to run from the initial state and stopping when transitioning to the final state. The state machine operates according to state machine definitions (state diagrams). Wherein the states are different states of the thing.
The switching method of the state machine may be executed by a chip, a processor, or a control device, where the chip, the processor, or the control device may be installed in an electronic device, so that the switching method of the state machine provided in the embodiment of the present application is executed by the chip, the processor, or the control device. In some embodiments, the chip, processor or control device may also be installed in an unmanned vehicle, in which case the electronic device is an unmanned vehicle. It is to be understood that the electronic device may be any device with computing processing capability, such as a computer, a server, a mobile terminal, or the like, and the specific form of the electronic device is not limited in any way herein. When the electronic equipment is not the unmanned automobile, the electronic equipment is in communication connection with the unmanned automobile so as to send the control signal to the unmanned automobile and realize the control of the unmanned automobile.
Referring to fig. 2, the unmanned vehicle 10 includes at least one processor 11 and a memory 12 (fig. 2 illustrates a bus connection and a processor as an example) which are connected in communication.
The processor 11 is configured to provide calculation and control capabilities to control the unmanned vehicle 10 to perform corresponding tasks, for example, to control the unmanned vehicle 10 to perform any one of the state machine switching methods provided in the following embodiments.
It is understood that the Processor 11 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The memory 12, which is a non-transitory computer readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the switching method of the state machine in the embodiment of the present invention. The processor 11 may implement the switching method of the state machine in any of the method embodiments described below by running non-transitory software programs, instructions, and modules stored in the memory 12. In particular, the memory 12 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 12 may also include memory located remotely from the processor, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Hereinafter, a switching method of a state machine provided in the embodiment of the present application will be described in detail. The state machine is arranged in the unmanned automobile and used for achieving behavior planning of the unmanned automobile. The state machine comprises four working states, namely a starting state, a returning lane state, a line patrol state and a lane-switching state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the lane switching state, the state machine sends an instruction for switching the current lane to the target lane to a local planning module of the unmanned vehicle.
In some embodiments, as seen in the state transition diagram shown in fig. 3, the state machine includes a parking state, a checking point state, a task canceling state, and the like, in addition to a start state, a return lane state, a patrol state, and a lane cutting state.
The states can be switched, for example, in a line patrol state, if an obstacle exists 500 meters ahead (an event meets a trigger condition), the state is switched to a lane switching state, and after the lane switching state is completed, if a large deviation between the unmanned vehicle and the lane is found (the event meets the trigger condition), the state is switched to a lane returning state. It is understood that the switching between different operating states may occur by event triggering, and is not illustrated here. In this embodiment, it is the driving road condition that triggers the state of the state machine to switch.
Referring to fig. 4, the method includes, but is not limited to, the following steps:
s10: and when the state machine is in a starting state, checking whether the input information is complete and variables related to the initialization task are detected, and if so, switching to a regression lane state.
Wherein the start state is a start state of the state machine. The input information includes positioning information, map information, communication information of each sensor on the unmanned vehicle, and the like. It can be understood that the starting state refers to a default state when the state machine is started, and after the starting state of the state machine is entered, whether input information is complete or not is checked, so that whether subsequent state switching is accurate or not can be effectively ensured, and the method is a precondition for accurately planning the behavior of the unmanned automobile.
Then, the task-related variables are initialized, and specifically, the task-related functions need to be called and the variables in the functions need to be initialized. The task-related variables are variables required in determining the states of the state machine, and are variables in functions, which may include, for example, variables in a function for returning a lane, variables in a function for cruising, and variables in a function for cutting a lane.
Before switching to the state of the returning lane, whether the input information is finished or not and whether the variables related to the initialization task are finished or not are detected, so that the unmanned automobile can be ensured to accurately return to the lane, and the condition of safe operation is provided.
S20: and when the state machine is in a lane returning state, judging whether the driverless automobile successfully returns to the lane, and if so, switching to a line patrol state.
Wherein the regressive lane status is used to indicate a regressive lane operation, i.e. to make no deviation between the driverless vehicle and the current lane. The patrol state is used to indicate a patrol operation, i.e., to cause the driverless vehicle to travel along the current lane.
It can be understood that whether the lane returning operation is successful or not is a precondition for the unmanned vehicle to perform the line patrol operation. If the operation of returning to the lane is unsuccessful, the line patrol operation can deviate from the lane, and potential safety hazards are caused. Therefore, after the unmanned vehicle is judged to successfully return to the lane, the unmanned vehicle is switched to the line patrol state, and the safety can be improved.
S30: and when the state machine is in the line patrol state, judging whether the lane needs to be switched or not according to the current driving road condition, and if so, switching to the lane switching state.
The driving road condition refers to an external environment of the unmanned vehicle in the driving process, such as an obstacle, a pedestrian, other vehicles, a traffic light, a road sign, a curve or a parking space. The driving road condition can be sensed and obtained by sensors such as a millimeter wave radar, a laser radar, an ultrasonic radar and a visual sensor.
In this embodiment, the driving road condition triggers the state of the state machine to switch. After the driving road condition is acquired, whether the lane needs to be switched is judged according to the driving road condition, and if so, the lane is switched to a lane switching state so as to guide the behavior of the unmanned automobile.
For example, in the line patrol state, if there is an obstacle 500 m ahead (the event satisfies the trigger condition), the state is switched to the lane-switching state.
In the implementation, when the state machine is in the starting state, whether input information is complete or not and variables related to the initialization task are checked, if yes, the state is switched to the lane returning state, the fact that the unmanned vehicle can accurately return to the lane can be guaranteed, and the premise that the unmanned vehicle safely runs is achieved. When the state machine is in a lane returning state, whether the unmanned vehicle successfully returns to the lane is judged, and if yes, the unmanned vehicle is switched to a line patrol state, so that the safety can be improved. When the state machine is in the line patrol state, whether the lane needs to be switched is judged according to the current driving road condition, if so, the lane is switched to the lane switching state, and the behavior of the unmanned automobile is enabled to accord with the road condition. From the three aspects, the behavior of the unmanned automobile in the driving process can be accurately and stably planned by switching the states through the state machine.
In some embodiments, when the state machine is in the line patrol state, whether lane switching is required is determined according to the current driving road condition, and if so, the step of switching to the lane switching state includes:
respectively calculating a traffic value of each lane, wherein the traffic value is the number of lanes required to be switched when the lanes are switched to a turning lane, and the turning lane is a lane corresponding to the unmanned automobile when the unmanned automobile turns in the process of driving to the terminal;
and judging whether the lane needs to be switched and a target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes.
For example, as shown in fig. 1, an unmanned vehicle travels on a road having 4 lanes, lane 4# on the rightmost side is a right-turn lane, lane 1# is a left-turn lane, and lanes 2# and 3# are straight lanes. When the unmanned vehicle runs on the lane 2#, in order to drive to the destination, the unmanned vehicle needs to turn at least once, and the unmanned vehicle should turn right at the next intersection, so that the lane 4# is the corresponding turning lane when the unmanned vehicle turns in the process of driving to the destination. The traffic value of the lane 1# is the number of lanes required to be switched from the lane 1# to the lane 4#, i.e. the traffic value of the lane 1# is 3, the traffic value of the lane 2# is the number of lanes required to be switched from the lane 2# to the lane 4#, i.e. the traffic value of the lane 2# is 2, and the traffic value of the lane 3# is the number of lanes required to be switched from the lane 3# to the lane 4#, i.e. the traffic value of the lane 3# is 1, it can be understood that the lane 4# does not need to be switched, and the traffic value is 0. From this, it is understood that the larger the traffic value is, the more the number of lanes to be switched becomes, and the more the traffic becomes unfavorable.
If there is static obstacle in front of current lane 2# where unmanned car is, then need to change lane, if there is no static obstacle in the certain distance in front of lane 1# and lane 3# both, then change lane to lane 3# is the better choice, when convenient follow-up turn, can change lane to lane 4# fast.
Considering that the traffic value and the obstacle situation on each lane are main factors constituting the driving road condition, it is determined whether or not the lane needs to be switched and the target lane needs to be switched according to the traffic value of each lane and the static obstacle distance on each lane. Wherein, the target lane is the lane after the driverless automobile changes lanes. For example, in the above example, lane 3# is the target lane.
In the embodiment, whether the lanes need to be switched and the target lanes need to be switched are judged according to the traffic value of each lane and the distance of the static obstacles on each lane, so that the target lanes are more reasonable, and more optimal lane changing can be realized.
In some embodiments, the step of determining whether the lane needs to be switched and the target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes specifically includes:
if no static barrier exists in front of the current lane within a first preset distance, determining that lane switching is not needed;
if a static obstacle exists in the front of the current lane within the first preset distance, calculating the switching cost of each lane, and determining that the lane needs to be switched and the target lane are the lanes with the minimum switching cost.
The first preset distance is an experience value set manually, and may be, for example, 800 meters, that is, if there is no static obstacle (for example, no forbidden board or the like) in front of the current lane within 800 meters, the target lane is still the current lane, that is, the lane change is not needed, and the vehicle can continue to run along the current lane. And if static obstacles exist in the current lane within 800 meters, calculating the switching cost of each lane, and determining that the target lane is the lane with the minimum switching cost.
Wherein the switching cost reflects the degree of goodness of the lane as the target lane. For example, referring to fig. 1 again, if there is no static obstacle in front of lane 2# where the current unmanned vehicle is located, there is no need to switch lanes. If a static obstacle exists in front of a lane 2# where the current unmanned automobile is located, the lane needs to be switched. Specifically, if there is no static obstacle in the front of lane 1# and lane 3# within a certain distance, lane change to lane 3# is a better choice, and when a subsequent turn is facilitated, lane change to lane 4# can be performed quickly, and lane change to lane 1# is a poorer choice because, during a subsequent turn, lane change from lane 1# to lane 4# is also required, and lane change is not easy. Thus, in this example, the switching cost of lane 3# is less than the switching cost of lane 1 #. It can be understood that if there is a static obstacle in front of the current lane 2#, the switching cost of the current lane 2# is the largest, and if there is no static obstacle in front of the lane 4#, the traffic value of the lane 4# is larger than that of the lane 3#, then the switching cost of the lane 4# is larger than that of the lane 3#, and it can be obtained that the switching cost of the lane 3# is the smallest.
In the embodiment, the target lane is determined to be the lane with the minimum switching cost, and the optimal lane change can be realized, so that the unmanned automobile can run more conveniently and reasonably.
In some embodiments, the step of calculating the switching cost of each lane includes:
calculating the switching cost of a lane i according to the following formula, wherein the lane i is any one of the lanes;
wherein, cost(i)J represents whether a static obstacle exists in front of the lane i within the first preset distance or not, j is 1 when the static obstacle exists in front of the lane i within the first preset distance, j is 0 when the static obstacle does not exist in front of the lane i within the first preset distance,a represents the traffic value of the lane i, diRepresenting the distance of a static obstacle in front of the lane i, d0The distance of a static obstacle in front of a current lane is represented, b represents whether the lane i has no static obstacle and has a dynamic obstacle in front, b is equal to 1 when the lane i has no static obstacle and has a dynamic obstacle in front, otherwise b is equal to 0, c represents whether a pedestrian is in front of the lane i, c is equal to 1 when the lane i has a pedestrian in front, otherwise c is equal to 0, eiThe distance of the pedestrian ahead.
It is understood that the lane i is any lane in the road, and may also be the current lane of the unmanned vehicle. When a static obstacle exists in the first preset distance in front of the lane i, the switching cost is infinite, and when no static obstacle exists in the first preset distance in front of the lane i, the traffic value, whether a dynamic obstacle b exists in front of the lane i or not and the distance d of the static obstacle in front of the lane i are considerediC whether there is a pedestrian in front and e distance of the pedestrian in frontiTo calculate the handover cost. The consideration is comprehensive, so that the switching cost can more accurately reflect the quality degree of the lane i as the target lane.
In this embodiment, the switching cost is calculated from a plurality of factors such as the traffic value, whether there is a dynamic obstacle in front, the distance of a static obstacle in front, whether there is a pedestrian in front, and the distance of the pedestrian in front, so that the switching cost can more accurately reflect the degree of goodness of the lane i as the target lane.
In some embodiments, the switching method of the state machine further includes:
if the lane-switching state lasts for a preset time and the direction of the target lane is consistent with the direction indicated by a steering lamp of the unmanned automobile, controlling the unmanned automobile to change the lane to the target lane; otherwise, switching to the line patrol state.
It is understood that the driveway switching state is entered, the unmanned vehicle is controlled to switch lanes, and the turn signal is required before changing lanes, for example, the turn signal should be turned left when changing lanes to the left, the turn signal should be turned right when changing lanes to the right, and the turn signal should be turned off when changing lanes to the right, and the driveway switching state is ended.
In order to ensure the safety when changing lanes, if the lane-switching state continues for a preset time, for example, the lane-switching state continues for 1s, the lane-switching state is stable, and no state jump occurs. If the lane switching state does not last for a preset time, for example, only lasts for 0.1s, and/or the direction of the target lane is not consistent with the direction indicated by the turn signal of the unmanned vehicle, for example, the direction of the target lane is right turn and left turn signal is turned, the lane switching state is switched to the line patrol state, that is, the vehicle continues to run along the current road, and the lane switching operation is not performed, so as to ensure the safety and stability when the lane is switched.
In some embodiments, the method further comprises:
and if the deviation between the unmanned automobile and the current lane is greater than a preset deviation threshold value, switching to a lane returning state.
And if the deviation between the unmanned automobile and the current lane is less than or equal to the preset deviation threshold value, switching to a line patrol state.
The deviation between the unmanned automobile and the current lane is an included angle between the direction of the head of the unmanned automobile and the current lane. It is understood that if the deviation between the unmanned vehicle and the current lane is greater than the preset deviation threshold, the unmanned vehicle may deviate from the current lane, and there is a risk of collision with vehicles in adjacent lanes. Therefore, it should be corrected in time, i.e., switched to the regressive lane state, to instruct the unmanned vehicle to regress to the current lane, reducing the deviation between the unmanned vehicle and the current lane.
And if the deviation between the unmanned automobile and the current lane is less than or equal to the preset deviation threshold value, switching to a line patrol state to indicate that the unmanned automobile continues to run along the current lane.
It will be understood that the preset deviation threshold is an empirical value set by a person skilled in the art, and may be determined according to actual conditions, and may be set to 20 °, for example.
In this embodiment, by monitoring the deviation between the unmanned vehicle and the current lane, the returning lane state and the line patrol state can be accurately determined, so as to reduce the risk of collision caused by unmanned driving.
In some embodiments, the state machine further comprises a parking state, and the parking state refers to a state from when the unmanned automobile starts parking to when parking is completed. That is, when the parking state is switched, the unmanned vehicle is controlled to start parking, and when the parking is completed, the parking state is completed.
The method further comprises the following steps:
and if the distance between the unmanned automobile and the driving terminal is less than or equal to a second preset distance, switching to a parking state.
In this embodiment, when the distance between the unmanned vehicle and the driving end point is less than or equal to a second preset distance, a parking state is entered to instruct the unmanned vehicle to decelerate and park. The second preset distance is an empirical value set by a person skilled in the art, and may be specifically set according to an actual situation, for example, the second preset distance may be 20 meters.
It will be appreciated that parking in a lane is possible, as well as possibly in a parking space. If the vehicle stops in the lane, controlling the unmanned vehicle to stop at the stop line, namely controlling the unmanned vehicle to stop in front of the stop line of the given lane; and if the vehicle is parked in the parking space, controlling the unmanned vehicle to perform parking space parking behaviors, namely controlling the unmanned vehicle to enter the given parking space.
In this embodiment, whether to enter the parking state can be accurately determined based on the distance between the driverless vehicle and the driving end point.
In some embodiments, the state machine further comprises a checkpointed state.
The method further comprises the following steps:
and when the distance between the unmanned vehicle and the check point is less than or equal to a third preset distance, switching to a check point state, wherein the check point is a position point on the driving path of the unmanned vehicle.
Wherein the checkpoint state is a state when the unmanned vehicle travels to the vicinity of the checkpoint, i.e. when the unmanned vehicle travels to the vicinity of checkpoint a, the distance from checkpoint a does not exceed a third predetermined distance (e.g. 5 m), during which the checkpoint state is switched. The check point is a position point on the driving path and can be set on a dotting map. The position, orientation angle, curvature and various speed limit values of the check point are recorded on the check point
Thus, when the distance between the unmanned vehicle and the checkpoint is less than or equal to a third preset distance, switching to the checkpoint state is performed. It should be noted that the third preset distance is an empirical value set by a person skilled in the art, and may be set according to actual situations. In the state of the inspection point, the unmanned automobile can plan a local driving path according to the data recorded by the inspection point.
In this embodiment, whether to enter the checkpoint state can be accurately determined based on the distance between the unmanned vehicle and the checkpoint.
In summary, according to the switching method of the state machine provided by the application, when the state machine is in the starting state, whether input information is complete or not and variables related to an initialization task are checked, if yes, the state is switched to the lane returning state, the fact that an unmanned vehicle accurately returns to a lane can be guaranteed, and the method is a premise of safe operation. When the state machine is in a lane returning state, whether the unmanned vehicle successfully returns to the lane is judged, if yes, the unmanned vehicle is switched to a line patrol state, and safety can be improved. When the state machine is in the line patrol state, whether the lane needs to be switched is judged according to the current driving road condition, if so, the lane is switched to the lane switching state, and the behavior of the unmanned automobile is enabled to accord with the road condition. From the three aspects, the behavior of the unmanned automobile in the driving process can be accurately and stably planned by switching the states through the state machine.
Another embodiment of the application further provides a state machine, wherein the state machine is arranged in the unmanned automobile and used for realizing behavior planning of the unmanned automobile, and the state machine is at least provided with four working states, namely a starting state, a lane returning state, a line patrol state and a lane switching state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in a lane switching state, the state machine sends a command of switching from a current lane to a target lane to a local planning module of the unmanned vehicle; the state machine includes:
the checking unit is used for checking whether input information is complete and variables related to the initialization task are detected when the state machine is in a starting state, and if yes, switching to a regression lane state;
the first judging unit is used for judging whether the driverless automobile successfully returns to the lane or not when the state machine is in the lane returning state, and if so, switching to the line patrol state;
and the second judgment unit is used for judging whether the lane needs to be switched or not according to the current driving road condition when the state machine is in the line patrol state, and if so, switching to the lane switching state.
In this embodiment, when the state machine is in the starting state, the checking unit checks whether the input information is complete and the variables related to the initialization task are detected, and if yes, the state is switched to the lane returning state, so that the unmanned vehicle can be ensured to accurately return to the lane, and the condition is the premise of safe operation. When the state machine is in a lane returning state, the first judging unit judges whether the driverless vehicle successfully returns to the lane or not, if so, the driverless vehicle is switched to a line patrol state, and safety can be improved. And when the state machine is in the line patrol state, the second judgment unit judges whether the lane needs to be switched according to the current driving road condition, and if so, the lane is switched to the lane switching state, so that the behavior of the unmanned automobile accords with the road condition. By adopting the three units, the state is switched through the state machine, and the behavior of the unmanned automobile in the driving process can be accurately and stably planned.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A switching method of a state machine is provided, the state machine is arranged in an unmanned automobile and used for realizing the behavior planning of the unmanned automobile, and is characterized in that the state machine comprises four working states, namely a starting state, a returning lane state, a line patrol state and a lane switching state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in a lane switching state, the state machine sends a command of switching from a current lane to a target lane to a local planning module of the unmanned vehicle; the switching method of the state machine comprises the following steps:
when the state machine is in a starting state, checking whether input information is complete and variables related to an initialization task are detected, and if yes, switching to a regression lane state;
when the state machine is in a lane returning state, judging whether the driverless automobile successfully returns to the lane, and if so, switching to a line patrol state;
and when the state machine is in the line patrol state, judging whether the lane needs to be switched according to the current driving road condition, and if so, switching to the lane switching state.
2. The method according to claim 1, wherein when the state machine is in the line patrol state, whether the lane needs to be switched is judged according to the current driving road condition, and if so, the step of switching to the lane switching state comprises the following steps:
respectively calculating a traffic value of each lane, wherein the traffic value is the number of lanes required to be switched when the lanes are switched to a turning lane, and the turning lane is a lane corresponding to the unmanned automobile when the unmanned automobile turns in the process of driving to the terminal;
and judging whether the lane needs to be switched and a target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes.
3. The method according to claim 2, wherein the step of determining whether the lane needs to be switched and the target lane needs to be switched according to the traffic values and the static obstacle distances on the lanes comprises:
if no static barrier exists in front of the current lane within a first preset distance, determining that lane switching is not needed;
if a static obstacle exists in the front of the current lane within the first preset distance, calculating the switching cost of each lane, and determining that the lane needs to be switched and the target lane are the lanes with the minimum switching cost.
4. The method of claim 3, wherein the step of calculating the switching cost for each lane comprises:
calculating the switching cost of a lane i according to the following formula, wherein the lane i is any one of the lanes;
wherein, cost(i)J represents whether a static obstacle exists in front of the lane i within the first preset distance or not, j is 1 when the static obstacle exists in front of the lane i within the first preset distance, j is 0 when the static obstacle does not exist in front of the lane i within the first preset distance, a represents a traffic value of the lane i, d represents a traffic value of the lane i, and j represents whether a static obstacle exists in front of the lane i within the first preset distance or notiRepresenting the distance of a static obstacle in front of the lane i, d0The distance of a static obstacle in front of a current lane is represented, b represents whether the lane i has no static obstacle and has a dynamic obstacle in front, b is equal to 1 when the lane i has no static obstacle and has a dynamic obstacle in front, otherwise b is equal to 0, c represents whether a pedestrian is in front of the lane i, c is equal to 1 when the lane i has a pedestrian in front, otherwise c is equal to 0, eiThe distance of the pedestrian ahead.
5. The method of claim 4, wherein the method comprises:
if the lane-switching state lasts for a preset time and the direction of the target lane is consistent with the direction indicated by a steering lamp of the unmanned automobile, controlling the unmanned automobile to change the lane to the target lane;
otherwise, switching to the line patrol state.
6. The method according to any one of claims 1-5, further comprising:
and if the deviation between the unmanned automobile and the current lane is greater than a preset deviation threshold value, switching to a lane returning state.
And if the deviation between the unmanned automobile and the current lane is less than or equal to the preset deviation threshold value, switching to a line patrol state.
7. The method according to any one of claims 1-5, wherein the state machine further comprises a parking state,
the method further comprises:
and if the distance between the unmanned automobile and the driving terminal is less than or equal to a second preset distance, switching to a parking state.
8. The method of any of claims 1-5, wherein the state machine further comprises a checkpointed state,
the method further comprises:
and when the distance between the unmanned vehicle and the check point is less than or equal to a third preset distance, switching to a check point state, wherein the check point is a position point on the driving path of the unmanned vehicle.
9. The state machine is arranged in an unmanned automobile and used for achieving behavior planning of the unmanned automobile, and is characterized in that the state machine is at least provided with four working states, namely a starting state, a lane returning state, a line patrolling state and a lane switching state; when the unmanned vehicle is in a starting state, the state machine checks whether input information is complete and variables related to an initialization task are detected, and when the unmanned vehicle is in a regression lane state, the state machine sends a command of regression lane operation to a local planning module of the unmanned vehicle; when the unmanned vehicle is in the line patrol state, the state machine sends a command of driving along the current route to a local planning module of the unmanned vehicle; when the unmanned vehicle is in a lane switching state, the state machine sends a command of switching from a current lane to a target lane to a local planning module of the unmanned vehicle; the state machine includes:
the checking unit is used for checking whether input information is complete and variables related to the initialization task are detected when the state machine is in a starting state, and if yes, switching to a regression lane state;
the first judging unit is used for judging whether the driverless automobile successfully returns to the lane or not when the state machine is in the lane returning state, and if so, switching to the line patrol state;
and the second judgment unit is used for judging whether the lane needs to be switched or not according to the current driving road condition when the state machine is in the line patrol state, and if so, switching to the lane switching state.
10. An unmanned vehicle, comprising: at least one processor, and
a memory communicatively coupled to the at least one processor, wherein,
the memory stores a program or instructions executable by the at least one processor, the program or instructions when executed by the processor implementing the method of switching the state machine of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110949108.5A CN113753047B (en) | 2021-08-18 | 2021-08-18 | State machine, state machine switching method and unmanned automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110949108.5A CN113753047B (en) | 2021-08-18 | 2021-08-18 | State machine, state machine switching method and unmanned automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113753047A true CN113753047A (en) | 2021-12-07 |
| CN113753047B CN113753047B (en) | 2023-06-09 |
Family
ID=78790287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110949108.5A Active CN113753047B (en) | 2021-08-18 | 2021-08-18 | State machine, state machine switching method and unmanned automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113753047B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101596903A (en) * | 2009-07-07 | 2009-12-09 | 清华大学 | Transverse driving of multipurpose automobile householder method and ancillary system thereof |
| CN107415945A (en) * | 2016-05-24 | 2017-12-01 | 通用汽车环球科技运作有限责任公司 | For assessing the automotive drive system and its application method of track lane-change |
| CN107792073A (en) * | 2017-09-29 | 2018-03-13 | 东软集团股份有限公司 | A kind of vehicle lane-changing control method, device and relevant device |
| JP2019074431A (en) * | 2017-10-17 | 2019-05-16 | クラリオン株式会社 | Travel support device and travel support method |
| US20190143982A1 (en) * | 2017-11-15 | 2019-05-16 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
| CN110487562A (en) * | 2019-08-21 | 2019-11-22 | 北京航空航天大学 | One kind being used for unpiloted road-holding ability detection system and method |
| US20190359202A1 (en) * | 2018-05-23 | 2019-11-28 | Baidu Usa Llc | Method for determining lane changing trajectories for autonomous driving vehicles |
| CN111717204A (en) * | 2019-03-18 | 2020-09-29 | 长城汽车股份有限公司 | Lateral control method and system for automatic driving vehicle |
| CN111994076A (en) * | 2020-09-02 | 2020-11-27 | 中国第一汽车股份有限公司 | Control method and device for automatic driving vehicle |
| CN112590812A (en) * | 2020-11-30 | 2021-04-02 | 中汽数据(天津)有限公司 | Local path planning state switching method based on automatic driving |
| CN112874503A (en) * | 2021-01-11 | 2021-06-01 | 广东科学技术职业学院 | Method and device for controlling unmanned vehicle and unmanned vehicle |
| US20210197823A1 (en) * | 2019-12-30 | 2021-07-01 | Baidu Usa Llc | Central line shifting based pre-change lane path planning |
| CN113147784A (en) * | 2021-04-13 | 2021-07-23 | 银隆新能源股份有限公司 | Control method and control device for unmanned vehicle and unmanned vehicle |
-
2021
- 2021-08-18 CN CN202110949108.5A patent/CN113753047B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101596903A (en) * | 2009-07-07 | 2009-12-09 | 清华大学 | Transverse driving of multipurpose automobile householder method and ancillary system thereof |
| CN107415945A (en) * | 2016-05-24 | 2017-12-01 | 通用汽车环球科技运作有限责任公司 | For assessing the automotive drive system and its application method of track lane-change |
| CN107792073A (en) * | 2017-09-29 | 2018-03-13 | 东软集团股份有限公司 | A kind of vehicle lane-changing control method, device and relevant device |
| JP2019074431A (en) * | 2017-10-17 | 2019-05-16 | クラリオン株式会社 | Travel support device and travel support method |
| US20190143982A1 (en) * | 2017-11-15 | 2019-05-16 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
| US20190359202A1 (en) * | 2018-05-23 | 2019-11-28 | Baidu Usa Llc | Method for determining lane changing trajectories for autonomous driving vehicles |
| CN111717204A (en) * | 2019-03-18 | 2020-09-29 | 长城汽车股份有限公司 | Lateral control method and system for automatic driving vehicle |
| CN110487562A (en) * | 2019-08-21 | 2019-11-22 | 北京航空航天大学 | One kind being used for unpiloted road-holding ability detection system and method |
| US20210197823A1 (en) * | 2019-12-30 | 2021-07-01 | Baidu Usa Llc | Central line shifting based pre-change lane path planning |
| CN111994076A (en) * | 2020-09-02 | 2020-11-27 | 中国第一汽车股份有限公司 | Control method and device for automatic driving vehicle |
| CN112590812A (en) * | 2020-11-30 | 2021-04-02 | 中汽数据(天津)有限公司 | Local path planning state switching method based on automatic driving |
| CN112874503A (en) * | 2021-01-11 | 2021-06-01 | 广东科学技术职业学院 | Method and device for controlling unmanned vehicle and unmanned vehicle |
| CN113147784A (en) * | 2021-04-13 | 2021-07-23 | 银隆新能源股份有限公司 | Control method and control device for unmanned vehicle and unmanned vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113753047B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11119479B2 (en) | Vehicle control apparatus | |
| WO2018216333A1 (en) | Electronic control device, vehicle control method, and vehicle control program | |
| CN110447057B (en) | Vehicle control device | |
| US11312394B2 (en) | Vehicle control device | |
| US11348463B2 (en) | Travel control device, travel control method, and storage medium storing program | |
| KR20210044960A (en) | Apparatus for controlling lane change of autonomous vehicle and method thereof | |
| JP2015168406A (en) | Lane change assist system | |
| US20200207373A1 (en) | Automatic driving proposal device and automatic driving proposal method | |
| JP2019144691A (en) | Vehicle control device | |
| JP2019200464A (en) | Driving support method and driving support device | |
| US20200255029A1 (en) | Vehicle control device | |
| CN111373457A (en) | Vehicle control device, vehicle, and vehicle control method | |
| US11535249B2 (en) | Vehicle action determining method and vehicle action determining device | |
| JP7377822B2 (en) | Driving support method and driving support device | |
| US11440546B2 (en) | Travel control apparatus, vehicle, travel control method, and non-transitory computer-readable storage medium | |
| KR20210004799A (en) | Method for autonomously operating vehicle, controller device for vehicle, and vehicle | |
| CN114537441A (en) | Vehicle driving intention prediction method, device and system and vehicle | |
| JP6691902B2 (en) | Vehicle control device | |
| CN113753047B (en) | State machine, state machine switching method and unmanned automobile | |
| CN115358415A (en) | Distributed training method of automatic driving learning model and automatic driving method | |
| JP7145178B2 (en) | Travel control device, travel control method and program | |
| US20200385023A1 (en) | Vehicle control apparatus, vehicle, operation method of vehicle control apparatus, and non-transitory computer-readable storage medium | |
| JP6606154B2 (en) | Vehicle control device | |
| WO2019235358A1 (en) | Vehicle control device | |
| CN114407930B (en) | Vehicle track prediction method and device, electronic equipment and vehicle |
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 |