CN110696836A - Behavior decision method and device for intelligently driving vehicle - Google Patents
Behavior decision method and device for intelligently driving vehicle Download PDFInfo
- Publication number
- CN110696836A CN110696836A CN201810746950.7A CN201810746950A CN110696836A CN 110696836 A CN110696836 A CN 110696836A CN 201810746950 A CN201810746950 A CN 201810746950A CN 110696836 A CN110696836 A CN 110696836A
- Authority
- CN
- China
- Prior art keywords
- lane
- behavior state
- driving vehicle
- intelligent driving
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008447 perception Effects 0.000 claims abstract description 79
- 230000008859 change Effects 0.000 claims description 71
- 230000007613 environmental effect Effects 0.000 claims description 25
- 230000004888 barrier function Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 283
- 230000008569 process Effects 0.000 abstract description 16
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 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
- 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
- B60W40/10—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 vehicle motion
-
- 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
-
- 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
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- 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
- B60W40/06—Road conditions
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The method comprises the steps that switching logics among various behavior states of the vehicle are established in advance, in the actual running process of the vehicle, according to the actual behavior state at the current moment, map priori knowledge and environment perception data are combined, the expected behavior state of the intelligent driving vehicle at the next moment is obtained through switching, and compared with the existing machine learning mode, the correct and safe behavior decision is provided for the full-automatic running of the intelligent driving vehicle on the structured road.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a behavior decision method and a behavior decision device for an intelligent driving vehicle.
Background
With the development of intelligent driving technology, safe and efficient driving of intelligent driving vehicles in structured roads has become a hot research spot. In a structured road, an intelligent vehicle needs to make a behavior decision according to the prior knowledge of a map and environmental information such as lane information and obstacle information acquired by a vehicle-mounted sensor. The behavior decision is a key ring in the intelligent driving technology, the function of the behavior decision is similar to that of the brain of a driver, namely, the behavior decision is used for receiving environmental information such as lane information, barrier information and the like and deciding the behavior action to be executed by the vehicle at the next moment in the current behavior state, so that the motion planning module is guided macroscopically and the task target and the function requirement of the intelligent driving system are realized.
The existing behavior decision method on the structured road mainly comprises the steps of collecting a driving scene and an experience sample data set of a driver, and carrying out recognition judgment, modeling prediction, intelligent decision and the like on the driving behavior based on a machine learning method.
Disclosure of Invention
In view of the above, the present invention provides a behavior decision method and apparatus for intelligently driving a vehicle, in order to achieve the purpose of providing a correct and safe behavior decision for automatic driving of the vehicle.
In order to achieve the above object, the following solutions are proposed:
a behavior decision method for intelligently driving a vehicle comprises the following steps:
obtaining map prior knowledge and environment perception data, wherein the map prior knowledge comprises lane attribute data and lane line data, and the environment perception data comprises barrier data;
according to the actual behavior state of the intelligent driving vehicle at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment is determined by combining the map priori knowledge and the environment perception data;
and analyzing to obtain the expected path and the expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
Optionally, the determining, according to the actual behavior state of the intelligent driving vehicle at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment by combining the map priori knowledge and the environmental perception data specifically includes:
when the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of parking, global right lane changing preparation, global left lane changing preparation and lane keeping according to the lane attribute data;
when the actual behavior state of the intelligent driving vehicle at the current moment is parking, determining the expected behavior state of the intelligent driving vehicle at the next moment as parking;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of the global right lane changing preparation and the global right lane changing preparation according to the state duration of the global right lane changing preparation and the obstacle data of the right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global right lane change preparation, global right lane change and lane keeping according to whether the vehicle completes the right lane change and barrier data of a right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane changing preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of the global left lane changing preparation and the global left lane changing preparation according to the state duration of the global left lane changing preparation and the obstacle data of the left lane contained in the environment perception data;
and when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global left lane change preparation, global left lane change and lane keeping according to whether the vehicle completes the left lane change and obstacle data of a left lane contained in the environment perception data.
Optionally, after the step of determining the expected behavior state of the intelligent driving vehicle at the next time as the lane keeping state according to the lane attribute data, and before the step of analyzing the expected path and the expected speed of the intelligent driving vehicle at the next time according to the expected behavior state, the method further includes:
determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of left overtaking preparation, right overtaking preparation and lane keeping according to the obstacle data of the vehicle lane, the obstacle data of the left lane and the obstacle data of the right lane which are contained in the environment perception data;
the method for determining the expected behavior state of the intelligent driving vehicle at the next moment according to the actual behavior state of the intelligent driving vehicle at the current moment and by combining the map priori knowledge and the environmental perception data specifically further comprises the following steps:
when the actual behavior state of the intelligent driving vehicle at the current moment is left overtaking preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment to be one behavior state of the left overtaking preparation, the left overtaking and the lane keeping according to the state duration of the left overtaking preparation, the obstacle data of the left lane and the obstacle data of the own lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is left overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of lane keeping, left overtaking and half left overtaking according to whether the vehicle completes left lane changing and obstacle data of a left lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is half-left overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of half-left overtaking, right lane changing and lane keeping according to the state duration of the half-left overtaking, the obstacle data of the right lane contained in the environment perception data and the obstacle data of the own lane;
when the actual behavior state of the intelligent driving vehicle at the current moment is a right lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state and a right lane change state according to whether the vehicle completes the right lane change and barrier data of a right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is right overtaking preparation, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the right overtaking preparation, the right overtaking preparation and the lane keeping according to the state duration of the right overtaking preparation, the obstacle data of the right lane and the obstacle data of the own lane, wherein the obstacle data of the right lane and the obstacle data of the own lane are contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is right overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state, a right overtaking state and a half right overtaking state according to whether the vehicle completes right lane changing and the obstacle data of the right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is half right overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of half right overtaking, left lane changing and lane keeping according to the state duration of the half right overtaking, the obstacle data of the left lane and the obstacle data of the own lane contained in the environment perception data;
and when the actual behavior state of the intelligent driving vehicle at the current moment is a left lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state and a left lane change state according to the obstacle data of the left lane and the obstacle data of the own lane, which are contained in the environment perception data.
A behavior decision device for a smart-driving vehicle, comprising:
the system comprises an information acquisition unit, a traffic light acquisition unit and a traffic light processing unit, wherein the information acquisition unit is used for acquiring map priori knowledge and environment perception data, the map priori knowledge comprises lane attribute data and lane line data, and the environment perception data comprises barrier data and traffic light data;
the behavior state switching unit is used for determining the expected behavior state of the intelligent driving vehicle at the next moment according to the actual behavior state of the intelligent driving vehicle at the current moment and by combining the map priori knowledge and the environment perception data;
and the motion planning unit is used for analyzing and obtaining an expected path and an expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
Optionally, the behavior state switching unit specifically includes:
the first switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of parking, global right lane changing preparation, global left lane changing preparation and lane keeping according to the lane attribute data when the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping;
the second switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is parking when the actual behavior state of the intelligent driving vehicle at the current moment is parking;
the third switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global right lane changing preparation and the global right lane changing preparation according to the state duration of the global right lane changing preparation and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing preparation;
the fourth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global right lane changing preparation, global right lane changing and lane keeping according to whether the vehicle finishes right lane changing and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing;
the fifth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global left lane changing preparation and the global left lane changing preparation according to the state duration of the global left lane changing preparation and the obstacle data of the left lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane changing preparation;
and the sixth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is the global left lane change, determine, according to whether the vehicle completes the left lane change and the obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of the behavior states of preparing for the global left lane change, changing the global left lane, and keeping the lane.
Optionally, the behavior state switching unit further includes:
the seventh switching subunit is used for determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of left-overtaking preparation, right-overtaking preparation and lane keeping according to the obstacle data of the vehicle lane, the obstacle data of the left lane and the obstacle data of the right lane which are contained in the environment perception data after the first switching subunit determines the expected behavior state of the intelligent driving vehicle at the next moment as the lane keeping according to the lane attribute data;
the eighth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is the left overtaking preparation, determine, according to the state duration of the left overtaking preparation and the obstacle data of the left lane included in the environment sensing data, that the expected behavior state of the intelligent driving vehicle at the next moment is one of the left overtaking preparation, the left overtaking and the lane keeping;
the ninth switching subunit is configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a left overtaking, whether the vehicle completes a left lane change and obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state, a left overtaking state and a half left overtaking state;
the tenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is a half-left overtaking, determine that an expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the half-left overtaking, right lane changing and lane keeping according to the state duration of the half-left overtaking, the obstacle data of the right lane and the obstacle data of the own lane, which are included in the environment sensing data;
the eleventh switching subunit is configured to, when the actual behavior state of the intelligently driven vehicle at the current time is a right lane change, determine, according to whether the vehicle completes the right lane change and obstacle data of the right lane included in the environmental perception data, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state and a right lane change state;
a twelfth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a right overtaking preparation, that the expected behavior state of the intelligent driving vehicle at the next time is one of a right overtaking preparation behavior state, a right overtaking behavior state, and a lane keeping behavior state according to the state duration of the right overtaking preparation behavior, and the obstacle data of the right lane and the obstacle data of the own lane that are included in the environment sensing data;
a thirteenth switching subunit, configured to determine, when the actual behavior state of the intelligently driven vehicle at the current time is a right overtaking, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state, a right overtaking state and a half right overtaking state according to whether the vehicle completes a right lane change and obstacle data of a right lane included in the environmental perception data;
a fourteenth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a half-right overtaking, that the expected behavior state of the intelligent driving vehicle at the next time is one of a half-right overtaking, a left lane changing, and a lane keeping behavior state according to state duration of the half-right overtaking, obstacle data of the left lane and obstacle data of the own lane, where the obstacle data includes the environment sensing data;
and the fifteenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is a left lane change, determine, according to the obstacle data of the left lane and the obstacle data of the own lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state and a left lane change state.
Compared with the prior art, the technical scheme of the invention has the following advantages:
according to the behavior decision method for the intelligent driving vehicle, switching logics among various behavior states are established in advance, in the actual driving process of the vehicle, according to the actual behavior state at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment is obtained through switching in combination with map priori knowledge and environment perception data, and compared with the existing machine learning mode, the behavior decision method for the intelligent driving vehicle provides correct and safe behavior decision for full-automatic driving of the intelligent driving vehicle in a structured road.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a key name description diagram in an embodiment of the invention;
FIG. 2 is a flowchart of a behavior decision method for intelligently driving a vehicle according to an embodiment of the present invention;
fig. 3 is a schematic logical structure diagram of a behavior decision device for an intelligent driving vehicle according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Before describing the technical scheme of the present invention in detail, key terms related to the technical scheme of the present invention are explained to facilitate understanding of the technical scheme of the present invention, which is shown in fig. 1.
A vehicle body coordinate system: and a coordinate system which takes the center O of the rear axle of the vehicle as an origin, the right side of the vehicle body as the X direction and the head direction as the Y direction.
Structured road environment: the traffic road environment with the clear indication marking line.
Lane: in the structured road environment, a portion for a single tandem vehicle to travel is clearly divided by a road indication mark.
This lane: the lane in which the vehicle is currently traveling, i.e., the lane in which the vehicle rear axle center O is located.
Left lane: the lane adjacent to the left of the own lane.
Right lane: the lane adjacent to the right of the own lane.
Full-automatic driving mode: and the driving mode of the vehicle self-control is carried out only according to the input of the environment perception information without manual intervention.
The invention provides a method for switching different behavior states of a vehicle based on map prior knowledge and environment perception data, which provides correct and safe behavior decision for full-automatic driving of an intelligent driving vehicle on a structured road. The method for deciding the behavior of the intelligent driving vehicle is described in detail below, and referring to fig. 2, the method comprises the following steps:
s11: and acquiring the prior knowledge of the map and the environmental perception data.
The map prior knowledge is provided by a map engine module of the intelligent driving system. The map prior knowledge contains lane attribute data and lane line data. In this embodiment, the lane attribute data is 0, indicating that no lane exists; the lane attribute data is 1, which represents that the lane is prohibited to pass; the lane attribute data is 2, which represents that the lane is an optional lane; the lane attribute data is 3, which indicates that the lane is the optimal lane recommended by the map. The lane line data includes, but is not limited to, the presence or absence of each lane line, the coordinates of each lane line, the length of each lane line, the line type (i.e., solid line, broken line) of each lane line, the position of the forced lane change area of each lane line, and the like in the vehicle body coordinate system. The context awareness data comprises obstacle data and traffic light data. The obstacle data specifically includes obstacle data of a left lane, obstacle data of a host lane, and obstacle data of a right lane. A map engine module of the intelligent driving system outputs a virtual one-way lane at the intersection, and vehicles run on the one-way lane according to traffic light data, obstacle data and the like.
S12: and determining the expected behavior state of the intelligent driving vehicle at the next moment according to the actual behavior state of the intelligent driving vehicle at the current moment and by combining the map prior knowledge and the environmental perception data.
A plurality of behavior states, and switching logic between the various behavior states are predefined. When the vehicle is in a full-automatic driving mode, according to the actual behavior state at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment is determined by combining the map priori knowledge and the environmental perception data. The behavior state in this embodiment includes lane keeping, parking, global left lane change preparation, global left lane change, global right lane change preparation, and global right lane change. When the vehicle enters a full-automatic driving mode, initialization is carried out, namely the behavior state at the current moment is set as a lane keeping state, and environment perception data are emptied. The switching logic between the various behavior states is described in detail below.
When the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping, determining that the expected behavior state of the intelligent driving vehicle at the next moment is parking (1) if the left lane attribute data, the own lane attribute data and the right lane attribute data are not more than 1; (2) if the left lane attribute data and the own lane attribute data are not more than 1 and the right lane attribute data are more than 1, determining the expected behavior state of the intelligent driving vehicle at the next moment as global right lane change preparation; (3) if the right lane attribute data and the own lane attribute data are not more than 1 and the left lane attribute data are more than 1, determining the expected behavior state of the intelligent driving vehicle at the next moment as global left lane changing preparation; (4) if the attribute data of the vehicle lane is larger than 1, determining the expected behavior state of the intelligent driving vehicle at the next moment as a lane keeping state no matter what the attribute data of other lanes are; (5) if the attribute data of the vehicle lane is not more than 1 and the attribute data of the left lane and the attribute data of the right lane are both more than 1, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for global left lane changing if the attribute data of the left lane is more than the attribute data of the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for global right lane changing if the attribute data of the left lane is less than the attribute data of the right lane, and determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for global left lane changing or global right lane changing if the attribute data of the left lane is equal to the attribute data of the right lane.
And when the actual behavior state of the intelligent driving vehicle at the current moment is parking, determining the expected behavior state of the intelligent driving vehicle at the next moment as parking.
When the actual behavior state of the intelligent driving vehicle at the current moment is prepared for global right lane changing, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for global right lane changing if the duration time of the current actual behavior state does not exceed a first time threshold or a right lane is unsafe; (2) and if the duration of the current behavior state exceeds the first time threshold and the right lane is safe, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the global right lane change. Specifically, the criterion for the safety of the right lane is to analyze whether the vehicle in front of the right lane will collide with the right lane or cause sudden braking of the vehicle behind the right lane when the vehicle enters the right lane in the current motion state at the time according to the obstacle data (including the vehicle speed, the distance from the vehicle, and the like) of the right lane, and if the danger does not occur, the right lane is safe, otherwise, the right lane is unsafe. A specific first time threshold may be 1 s.
When the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for the global right lane change if the right lane is unsafe; (2) if the right lane is safe and the vehicle has not finished changing lanes to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the global right lane changing; (3) and if the vehicle finishes changing lanes to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state.
When the actual behavior state of the intelligent driving vehicle at the current moment is prepared for global left lane changing, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for global left lane changing if the duration time of the current behavior state does not exceed a first time threshold or a left lane is unsafe; (2) and if the duration of the current behavior state exceeds the first time threshold and the left lane is safe, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the global left lane change. The judgment standard of the left lane safety is similar to that of the right lane safety, and the description is omitted.
When the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for the global left lane change if the left lane is unsafe; (2) if the left lane is safe and the vehicle has not finished changing lanes to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is global left lane changing; (3) and if the vehicle finishes changing lanes to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state.
S13: and analyzing to obtain the expected path and the expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
The lane keeping is a behavior state in which the vehicle keeps running in the own lane. The global left lane changing is prepared for continuously detecting whether the left lane is safe or not in the process of driving the vehicle in the lane. The global left lane change is a behavior state of the vehicle in the process of changing lanes from the vehicle lane to the left lane. The global right lane changing is prepared for continuously detecting whether the right lane is safe or not in the process of driving the vehicle in the lane. The global right lane change is a behavior state of the vehicle in the process of changing the lane from the vehicle lane to the right lane. Parking is the behavior of a vehicle from a driving state to a safe parking. In the prior art, a scheme of analyzing and obtaining an expected path and an expected speed of an intelligent driving vehicle according to an expected behavior state can be adopted, and the invention is not limited.
According to the behavior decision method for the intelligent driving vehicle, switching logics among various behavior states are established in advance, in the actual driving process of the vehicle, according to the actual behavior state at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment is obtained through switching in combination with map prior knowledge and environment perception data, and compared with the existing machine learning mode, the behavior decision method for the intelligent driving vehicle provides correct and safe behavior decision for full-automatic driving of the intelligent driving vehicle on a structured road.
The behavior states may include left overtaking preparation, left overtaking, half left overtaking, right lane changing, right overtaking preparation, right overtaking, half right overtaking, and right lane changing, in addition to lane keeping, parking, global left lane changing preparation, global right lane changing preparation, and global right lane changing. The left overtaking preparation is the behavior state that whether the left lane is safe or not is continuously detected in the process that the vehicle runs in the lane. The left overtaking is the behavior state of the vehicle in the process of changing the lane from the lane to the left lane. The half-left overtaking is a behavior state that the vehicle keeps running in the lane and whether the right lane is safe or not is continuously detected. The right lane changing is a behavior state of the vehicle in the process of changing the lane from the vehicle lane to the right lane. The right overtaking preparation is the behavior state that whether the right lane is safe or not is continuously detected in the process that the vehicle runs in the lane. The right overtaking is the behavior state of the vehicle in the process of changing the lane from the vehicle lane to the right lane. The half right overtaking is a behavior state that the vehicle keeps running in the lane and whether the left lane is safe or not is continuously detected. The left lane changing is a behavior state of the vehicle in the process of changing the lane from the vehicle lane to the left lane. The switching logic between the various behavior states is described in detail below.
After the step of determining the expected behavior state of the intelligent driving vehicle at the next moment as keeping the lane according to the lane attribute data, analyzing, (1) if an obstacle with the speed lower than a speed threshold exists in front of the vehicle, the safety of a left lane exists, and the road condition of the left lane is superior to that of the vehicle, determining the expected behavior state of the intelligent driving vehicle at the next moment as preparation for left-hand overtaking; (2) and if an obstacle with the speed lower than the speed threshold exists in front of the vehicle, the left lane is unsafe or the road condition of the left lane is not better than the road condition of the vehicle, the right lane is safe, and the road condition of the right lane is better than the road condition of the vehicle, determining that the expected behavior state of the intelligent driving vehicle at the next moment is prepared for right-hand overtaking. (3) In other cases, the expected behavior state of the intelligent driving vehicle at the next moment is determined to be lane keeping. That is, the expected behavior state of the intelligent driving vehicle is determined to be lane keeping at the next moment, and whether the behavior state is modified to other behavior states is judged according to the conditions so as to realize efficient driving in the scene of traffic flow convergence. The judgment standard that the road condition of the left lane is better than that of the lane is that the average speed of the obstacles in the left lane in front of the vehicle is greater than that of the obstacles in the lane in front of the vehicle, and the road condition of the left lane is considered to be better than that of the lane.
When the actual behavior state of the intelligent driving vehicle at the current moment is prepared for left-hand overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is left-hand overtaking if the duration time of the current behavior state exceeds a first time threshold and is less than a second time threshold, the left lane is safe, and the left lane road condition is superior to the road condition of the lane; (2) if the duration time of the current behavior state exceeds a second time threshold, giving up left overtaking, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (3) and otherwise, determining the expected behavior state of the intelligent driving vehicle at the next moment to prepare for left-hand overtaking. A specific second time threshold may be 10 s.
When the actual behavior state of the intelligent driving vehicle at the current moment is left overtaking, giving up left overtaking if the left lane is unsafe, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (2) if the left lane is safe and the vehicle does not complete lane change from the vehicle lane to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is left overtaking; (3) and if the vehicle finishes changing lanes from the vehicle lane to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is half-left overtaking.
When the actual behavior state of the intelligent driving vehicle at the current moment is half left-hand overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is right lane changing if the duration time of the current behavior state exceeds a first time threshold and is less than a second time threshold, the right lane is safe, and the right lane road condition is superior to the road condition of the lane; (2) if the duration time of the current behavior state exceeds a second time threshold, giving up returning to the original lane, and determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state; (3) and otherwise, determining that the expected behavior state of the intelligent driving vehicle at the next moment is half left overtaking.
When the actual behavior state of the intelligent driving vehicle at the current moment is lane changing on the right, giving up lane changing on the right if the right lane is unsafe, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (2) if the right lane is safe and the vehicle does not complete lane changing from the vehicle lane to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is right lane changing; (3) and if the vehicle finishes changing lanes from the vehicle lane to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state.
When the actual behavior state of the intelligent driving vehicle at the current moment is ready for right-hand overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is right-hand overtaking if the duration time of the current behavior state exceeds a first time threshold and is less than a second time threshold, the right lane is safe, and the right lane road condition is superior to the road condition of the lane; (2) if the duration time of the current behavior state exceeds a second time threshold, giving up right overtaking, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (3) and otherwise, determining the expected behavior state of the intelligent driving vehicle at the next moment to prepare for right overtaking.
When the actual behavior state of the intelligent driving vehicle at the current moment is right overtaking, giving up left overtaking if the right lane is unsafe, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (2) if the right lane is safe and the vehicle does not complete lane change from the vehicle lane to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is right overtaking; (3) and if the vehicle finishes changing lanes from the vehicle lane to the right lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is half right overtaking.
When the actual behavior state of the intelligent driving vehicle at the current moment is half right overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is left lane changing if the duration time of the current behavior state exceeds a first time threshold and is less than a second time threshold, the left lane is safe, and the left lane road condition is superior to the road condition of the lane; (2) if the duration time of the current behavior state exceeds a second time threshold, giving up returning to the original lane, and determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state; (3) and otherwise, determining that the expected behavior state of the intelligent driving vehicle at the next moment is half right overtaking.
When the actual behavior state of the intelligent driving vehicle at the current moment is lane changing on the left side, giving up lane changing on the left side if the lane on the left side is unsafe, and determining the expected behavior state of the intelligent driving vehicle at the next moment as lane keeping; (2) if the left lane is safe and the vehicle does not complete lane changing from the vehicle lane to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is left lane changing; (3) and if the vehicle finishes changing lanes from the vehicle lane to the left lane, determining that the expected behavior state of the intelligent driving vehicle at the next moment is the lane keeping state.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
The present embodiment provides a behavior decision device for an intelligent driving vehicle, and as shown in fig. 3, the device includes: an information acquisition unit 11, a behavior state switching unit 12, and an exercise planning unit 13.
The information acquisition unit 11 is configured to acquire map prior knowledge and environment sensing data, where the map prior knowledge includes lane attribute data and lane line data, and the environment sensing data includes obstacle data and traffic light data;
the behavior state switching unit 12 is configured to determine an expected behavior state of the intelligently driven vehicle at the next moment according to the actual behavior state of the intelligently driven vehicle at the current moment and by combining the map priori knowledge and the environmental perception data;
and the motion planning unit 13 is used for analyzing and obtaining an expected path and an expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
The behavior state switching unit specifically includes: the first switching subunit, the second switching subunit, the third switching subunit, the fourth switching subunit, the fifth switching subunit and the sixth switching subunit.
The first switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of parking, global right lane changing preparation, global left lane changing preparation and lane keeping according to the lane attribute data when the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping;
the second switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is parking when the actual behavior state of the intelligent driving vehicle at the current moment is parking;
the third switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global right lane changing preparation and the global right lane changing preparation according to the state duration of the global right lane changing preparation and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing preparation;
the fourth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global right lane changing preparation, global right lane changing and lane keeping according to whether the vehicle finishes right lane changing and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing;
the fifth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global left lane changing preparation and the global left lane changing preparation according to the state duration of the global left lane changing preparation and the obstacle data of the left lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane changing preparation;
and the sixth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is the global left lane change, determine, according to whether the vehicle completes the left lane change and the obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of the behavior states of preparing for the global left lane change, changing the global left lane, and keeping the lane.
The behavior state switching unit may further include: a seventh switching subunit, an eighth switching subunit, a ninth switching subunit, a tenth switching subunit, an eleventh switching subunit, a twelfth switching subunit, a thirteenth switching subunit, a fourteenth switching subunit, and a fifteenth switching subunit.
The seventh switching subunit is used for determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of left-overtaking preparation, right-overtaking preparation and lane keeping according to the obstacle data of the vehicle lane, the obstacle data of the left lane and the obstacle data of the right lane which are contained in the environment perception data after the first switching subunit determines the expected behavior state of the intelligent driving vehicle at the next moment as the lane keeping according to the lane attribute data;
the eighth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is the left overtaking preparation, determine, according to the state duration of the left overtaking preparation and the obstacle data of the left lane included in the environment sensing data, that the expected behavior state of the intelligent driving vehicle at the next moment is one of the left overtaking preparation, the left overtaking and the lane keeping;
the ninth switching subunit is configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a left overtaking, whether the vehicle completes a left lane change and obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state, a left overtaking state and a half left overtaking state;
the tenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is a half-left overtaking, determine that an expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the half-left overtaking, right lane changing and lane keeping according to the state duration of the half-left overtaking, the obstacle data of the right lane and the obstacle data of the own lane, which are included in the environment sensing data;
the eleventh switching subunit is configured to, when the actual behavior state of the intelligently driven vehicle at the current time is a right lane change, determine, according to whether the vehicle completes the right lane change and obstacle data of the right lane included in the environmental perception data, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state and a right lane change state;
a twelfth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a right overtaking preparation, that the expected behavior state of the intelligent driving vehicle at the next time is one of a right overtaking preparation behavior state, a right overtaking behavior state, and a lane keeping behavior state according to the state duration of the right overtaking preparation behavior, and the obstacle data of the right lane and the obstacle data of the own lane that are included in the environment sensing data;
a thirteenth switching subunit, configured to determine, when the actual behavior state of the intelligently driven vehicle at the current time is a right overtaking, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state, a right overtaking state and a half right overtaking state according to whether the vehicle completes the right lane and obstacle data of the right lane included in the environmental perception data;
a fourteenth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a half-right overtaking, that the expected behavior state of the intelligent driving vehicle at the next time is one of a half-left overtaking, a left lane changing, and a lane keeping behavior state according to state duration of the half-right overtaking, obstacle data of the left lane and obstacle data of the own lane, where the obstacle data includes the environment sensing data;
and the fifteenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is a left lane change, determine, according to the obstacle data of the left lane and the obstacle data of the own lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state and a left lane change state.
The above-described embodiments of the apparatus are merely illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical 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. One of ordinary skill in the art can understand and implement it without inventive effort.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A behavior decision method for intelligently driving a vehicle is characterized by comprising the following steps:
obtaining map prior knowledge and environment perception data, wherein the map prior knowledge comprises lane attribute data and lane line data, and the environment perception data comprises barrier data;
according to the actual behavior state of the intelligent driving vehicle at the current moment, the expected behavior state of the intelligent driving vehicle at the next moment is determined by combining the map priori knowledge and the environment perception data;
and analyzing to obtain the expected path and the expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
2. The behavior decision method according to claim 1, wherein the determining an expected behavior state of the intelligently driven vehicle at a next time according to the actual behavior state of the intelligently driven vehicle at the current time by combining the map prior knowledge and the environmental perception data specifically comprises:
when the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of parking, global right lane changing preparation, global left lane changing preparation and lane keeping according to the lane attribute data;
when the actual behavior state of the intelligent driving vehicle at the current moment is parking, determining the expected behavior state of the intelligent driving vehicle at the next moment as parking;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of the global right lane changing preparation and the global right lane changing preparation according to the state duration of the global right lane changing preparation and the obstacle data of the right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global right lane change preparation, global right lane change and lane keeping according to whether the vehicle completes the right lane change and barrier data of a right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane changing preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of the global left lane changing preparation and the global left lane changing preparation according to the state duration of the global left lane changing preparation and the obstacle data of the left lane contained in the environment perception data;
and when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global left lane change preparation, global left lane change and lane keeping according to whether the vehicle completes the left lane change and obstacle data of a left lane contained in the environment perception data.
3. The method of claim 2, wherein after the step of determining the expected behavior state of the intelligent driving vehicle at the next time as lane keeping according to the lane attribute data and before the step of analyzing the expected path and the expected speed of the intelligent driving vehicle at the next time according to the expected behavior state, further comprising:
determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of left overtaking preparation, right overtaking preparation and lane keeping according to the obstacle data of the vehicle lane, the obstacle data of the left lane and the obstacle data of the right lane which are contained in the environment perception data;
the method for determining the expected behavior state of the intelligent driving vehicle at the next moment according to the actual behavior state of the intelligent driving vehicle at the current moment and by combining the map priori knowledge and the environmental perception data specifically further comprises the following steps:
when the actual behavior state of the intelligent driving vehicle at the current moment is left overtaking preparation, determining the expected behavior state of the intelligent driving vehicle at the next moment to be one behavior state of the left overtaking preparation, the left overtaking and the lane keeping according to the state duration of the left overtaking preparation, the obstacle data of the left lane and the obstacle data of the own lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is left overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of lane keeping, left overtaking and half left overtaking according to whether the vehicle completes left lane changing and obstacle data of a left lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is half-left overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of half-left overtaking, right lane changing and lane keeping according to the state duration of the half-left overtaking, the obstacle data of the right lane contained in the environment perception data and the obstacle data of the own lane;
when the actual behavior state of the intelligent driving vehicle at the current moment is a right lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state and a right lane change state according to whether the vehicle completes the right lane change and barrier data of a right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is right overtaking preparation, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the right overtaking preparation, the right overtaking preparation and the lane keeping according to the state duration of the right overtaking preparation, the obstacle data of the right lane and the obstacle data of the own lane, wherein the obstacle data of the right lane and the obstacle data of the own lane are contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is right overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state, a right overtaking state and a half right overtaking state according to whether the vehicle completes right lane changing and the obstacle data of the right lane contained in the environment perception data;
when the actual behavior state of the intelligent driving vehicle at the current moment is half right overtaking, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of half right overtaking, left lane changing and lane keeping according to the state duration of the half right overtaking, the obstacle data of the left lane and the obstacle data of the own lane contained in the environment perception data;
and when the actual behavior state of the intelligent driving vehicle at the current moment is a left lane change, determining that the expected behavior state of the intelligent driving vehicle at the next moment is one of a lane keeping state and a left lane change state according to the obstacle data of the left lane and the obstacle data of the own lane, which are contained in the environment perception data.
4. A behavior decision device for an intelligent driven vehicle, comprising:
the system comprises an information acquisition unit, a traffic light acquisition unit and a traffic light processing unit, wherein the information acquisition unit is used for acquiring map priori knowledge and environment perception data, the map priori knowledge comprises lane attribute data and lane line data, and the environment perception data comprises barrier data and traffic light data;
the behavior state switching unit is used for determining the expected behavior state of the intelligent driving vehicle at the next moment according to the actual behavior state of the intelligent driving vehicle at the current moment and by combining the map priori knowledge and the environment perception data;
and the motion planning unit is used for analyzing and obtaining an expected path and an expected speed of the intelligent driving vehicle at the next moment according to the expected behavior state.
5. The behavior decision device according to claim 4, wherein the behavior state switching unit specifically includes:
the first switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of parking, global right lane changing preparation, global left lane changing preparation and lane keeping according to the lane attribute data when the actual behavior state of the intelligent driving vehicle at the current moment is lane keeping;
the second switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is parking when the actual behavior state of the intelligent driving vehicle at the current moment is parking;
the third switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global right lane changing preparation and the global right lane changing preparation according to the state duration of the global right lane changing preparation and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing preparation;
the fourth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of global right lane changing preparation, global right lane changing and lane keeping according to whether the vehicle finishes right lane changing and the obstacle data of the right lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global right lane changing;
the fifth switching subunit is used for determining that the expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the global left lane changing preparation and the global left lane changing preparation according to the state duration of the global left lane changing preparation and the obstacle data of the left lane contained in the environment perception data when the actual behavior state of the intelligent driving vehicle at the current moment is the global left lane changing preparation;
and the sixth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is the global left lane change, determine, according to whether the vehicle completes the left lane change and the obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of the behavior states of preparing for the global left lane change, changing the global left lane, and keeping the lane.
6. The apparatus of claim 5, wherein the behavior state switching unit further comprises:
the seventh switching subunit is used for determining the expected behavior state of the intelligent driving vehicle at the next moment as one behavior state of left-overtaking preparation, right-overtaking preparation and lane keeping according to the obstacle data of the vehicle lane, the obstacle data of the left lane and the obstacle data of the right lane which are contained in the environment perception data after the first switching subunit determines the expected behavior state of the intelligent driving vehicle at the next moment as the lane keeping according to the lane attribute data;
the eighth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is the left overtaking preparation, determine, according to the state duration of the left overtaking preparation and the obstacle data of the left lane included in the environment sensing data, that the expected behavior state of the intelligent driving vehicle at the next moment is one of the left overtaking preparation, the left overtaking and the lane keeping;
the ninth switching subunit is configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a left overtaking, whether the vehicle completes a left lane change and obstacle data of the left lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state, a left overtaking state and a half left overtaking state;
the tenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current moment is a half-left overtaking, determine that an expected behavior state of the intelligent driving vehicle at the next moment is one behavior state of the half-left overtaking, right lane changing and lane keeping according to the state duration of the half-left overtaking, the obstacle data of the right lane and the obstacle data of the own lane, which are included in the environment sensing data;
the eleventh switching subunit is configured to, when the actual behavior state of the intelligently driven vehicle at the current time is a right lane change, determine, according to whether the vehicle completes the right lane change and obstacle data of the right lane included in the environmental perception data, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state and a right lane change state;
a twelfth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a right overtaking preparation, that the expected behavior state of the intelligent driving vehicle at the next time is one of a right overtaking preparation behavior state, a right overtaking behavior state, and a lane keeping behavior state according to the state duration of the right overtaking preparation behavior, and the obstacle data of the right lane and the obstacle data of the own lane that are included in the environment sensing data;
a thirteenth switching subunit, configured to determine, when the actual behavior state of the intelligently driven vehicle at the current time is a right overtaking, that the expected behavior state of the intelligently driven vehicle at the next time is one of a lane keeping state, a right overtaking state and a half right overtaking state according to whether the vehicle completes a right lane change and obstacle data of a right lane included in the environmental perception data;
a fourteenth switching subunit, configured to determine, when the actual behavior state of the intelligent driving vehicle at the current time is a half-right overtaking, that the expected behavior state of the intelligent driving vehicle at the next time is one of a half-right overtaking, a left lane changing, and a lane keeping behavior state according to state duration of the half-right overtaking, obstacle data of the left lane and obstacle data of the own lane, where the obstacle data includes the environment sensing data;
and the fifteenth switching subunit is configured to, when the actual behavior state of the intelligent driving vehicle at the current time is a left lane change, determine, according to the obstacle data of the left lane and the obstacle data of the own lane included in the environmental perception data, that the expected behavior state of the intelligent driving vehicle at the next time is one of a lane keeping state and a left lane change state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810746950.7A CN110696836A (en) | 2018-07-09 | 2018-07-09 | Behavior decision method and device for intelligently driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810746950.7A CN110696836A (en) | 2018-07-09 | 2018-07-09 | Behavior decision method and device for intelligently driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110696836A true CN110696836A (en) | 2020-01-17 |
Family
ID=69192807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810746950.7A Pending CN110696836A (en) | 2018-07-09 | 2018-07-09 | Behavior decision method and device for intelligently driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110696836A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111907521A (en) * | 2020-06-15 | 2020-11-10 | 浙江吉利汽车研究院有限公司 | Transverse control method and device for automatic driving vehicle and storage medium |
| CN111994089A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Driver lane change intention identification method and system based on hybrid strategy game |
| 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 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5761629A (en) * | 1994-12-13 | 1998-06-02 | Lucas Industries Public Limited Company | Method and apparatus for cruise control |
| JP2002092795A (en) * | 2000-09-18 | 2002-03-29 | Toshiba Corp | Vehicle guide device |
| KR20090128873A (en) * | 2008-06-11 | 2009-12-16 | 현대자동차주식회사 | Adaptive cruise control system |
| CN106708040A (en) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | Sensor module of automatic driving system, automatic driving system and automatic driving method |
| CN107215339A (en) * | 2017-06-26 | 2017-09-29 | 地壳机器人科技有限公司 | The lane-change control method and device of automatic driving vehicle |
| CN107264531A (en) * | 2017-06-08 | 2017-10-20 | 中南大学 | The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment |
| CN108225364A (en) * | 2018-01-04 | 2018-06-29 | 吉林大学 | A kind of pilotless automobile driving task decision system and method |
-
2018
- 2018-07-09 CN CN201810746950.7A patent/CN110696836A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5761629A (en) * | 1994-12-13 | 1998-06-02 | Lucas Industries Public Limited Company | Method and apparatus for cruise control |
| JP2002092795A (en) * | 2000-09-18 | 2002-03-29 | Toshiba Corp | Vehicle guide device |
| KR20090128873A (en) * | 2008-06-11 | 2009-12-16 | 현대자동차주식회사 | Adaptive cruise control system |
| CN106708040A (en) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | Sensor module of automatic driving system, automatic driving system and automatic driving method |
| CN107264531A (en) * | 2017-06-08 | 2017-10-20 | 中南大学 | The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment |
| CN107215339A (en) * | 2017-06-26 | 2017-09-29 | 地壳机器人科技有限公司 | The lane-change control method and device of automatic driving vehicle |
| CN108225364A (en) * | 2018-01-04 | 2018-06-29 | 吉林大学 | A kind of pilotless automobile driving task decision system and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111907521A (en) * | 2020-06-15 | 2020-11-10 | 浙江吉利汽车研究院有限公司 | Transverse control method and device for automatic driving vehicle and storage medium |
| CN111907521B (en) * | 2020-06-15 | 2022-11-22 | 浙江吉利汽车研究院有限公司 | Transverse control method and device for automatic driving vehicle and storage medium |
| CN111994089A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Driver lane change intention identification method and system based on hybrid strategy game |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102446518B1 (en) | Position-dependent support for autonomous vehicle control systems | |
| CN110362077B (en) | Unmanned vehicle emergency hedge decision making system, method and medium | |
| JP6691634B2 (en) | Object drivability determination for autonomous vehicles | |
| CN113165652B (en) | Verifying predicted trajectories using a mesh-based approach | |
| CN108437986B (en) | Vehicle driving assistance system and assistance method | |
| US9734390B2 (en) | Method and device for classifying a behavior of a pedestrian when crossing a roadway of a vehicle as well as passenger protection system of a vehicle | |
| US10606264B2 (en) | Control method and control device of automatic driving vehicle | |
| CN104417561B (en) | Context aware threat-response judges | |
| JP6478415B2 (en) | Vehicle control system, vehicle control method, and vehicle control program | |
| US10832577B2 (en) | Method and system for determining road users with potential for interaction | |
| KR20190054374A (en) | Autonomous drive learning apparatus and method using drive experience information | |
| CN108604413B (en) | Display device control method and display device | |
| CN110816540B (en) | Traffic jam determining method, device and system and vehicle | |
| CN110696836A (en) | Behavior decision method and device for intelligently driving vehicle | |
| JP7289760B2 (en) | electronic controller | |
| CN109828573B (en) | Unmanned vehicle control method, device and storage medium | |
| CN115871672A (en) | Improvements in or relating to driver assistance systems | |
| CN113085852A (en) | Behavior early warning method and device for automatic driving vehicle and cloud equipment | |
| CN112424850A (en) | Method and device for assisting a driver in a vehicle | |
| CN113176778A (en) | Control method and control device for unmanned vehicle and unmanned vehicle | |
| CN106296869B (en) | Processing method, processing system and the automobile data recorder of running information | |
| CN110606091B (en) | Object tracking after an object leaves the road of a host vehicle | |
| KR20180052811A (en) | Method for Making Autonomous or Automated Driving System and a Driving System | |
| CN110696828A (en) | Forward target selection method and device and vehicle-mounted equipment | |
| Takatori et al. | Stand-alone collision warning systems based on information from on-board sensors: Evaluating performance relative to system penetration rate |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200624 Address after: 201203 Shanghai Zhangjiang High Tech Park of Pudong New Area Songtao Road No. 563 Building No. 1 room 509 Applicant after: SAIC MOTOR Corp.,Ltd. Address before: 201203 Shanghai Zhangjiang High Tech Park of Pudong New Area Songtao Road No. 563 Building No. 1 room 509 Applicant before: SAIC Motor Corp.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |