CN115465288A - Control method and device for automatic driving vehicle, vehicle and storage medium - Google Patents
Control method and device for automatic driving vehicle, vehicle and storage medium Download PDFInfo
- Publication number
- CN115465288A CN115465288A CN202210967939.XA CN202210967939A CN115465288A CN 115465288 A CN115465288 A CN 115465288A CN 202210967939 A CN202210967939 A CN 202210967939A CN 115465288 A CN115465288 A CN 115465288A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- actual
- target
- target vehicle
- danger level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
-
- 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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- 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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- 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
- B60W40/107—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/801—Lateral distance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
Abstract
The present application relates to the field of vehicle automatic driving technology, and in particular, to a method, an apparatus, a vehicle and a storage medium for controlling an automatic driving vehicle, wherein the method comprises: acquiring actual running states of a plurality of target vehicles around the vehicle; calculating an actual danger level of each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and calculating an actual danger level of a traffic flow consisting of a plurality of target vehicles according to the actual danger level of each target vehicle; and when the actual danger level of the traffic flow is smaller than the preset level, controlling the vehicle to execute an acceleration action and/or a lane changing action, otherwise, controlling the vehicle to execute a deceleration action or keeping the current speed unchanged. Therefore, the problems that in the related art, the automatic driving decision of the vehicle is controlled based on the single-target danger degree generally, the influence of other dangerous factors on the decision is ignored, the decision planning is unreasonable, the driving safety is reduced, the user experience is poor and the like are solved.
Description
Technical Field
The present disclosure relates to the field of automatic driving technologies, and in particular, to a method and an apparatus for controlling an automatic driving vehicle, a vehicle, and a storage medium.
Background
The automatic driving technology mainly comprises three parts of environment perception, decision planning and control execution, wherein the environment perception is used as the front end of the automatic driving technology, the accuracy is crucial, and the full mining and use of information are especially important under the conditions that the performance of a current sensor is poor, the detection precision is insufficient, and the types of detectable targets are limited.
In the related art, vehicles are generally controlled to execute automatic driving decisions based on the degree of danger of a single target vehicle or a single target in an environmental state. However, in the related art, when the automatic driving decision of the vehicle is controlled based on the risk degree of the single target, the influence of other risk factors on the decision is ignored, so that the decision planning is easily unreasonable, the driving safety and the driving comfort of the user are reduced, and the vehicle using experience of the user is reduced.
Disclosure of Invention
The application provides a control method and device for an automatic driving vehicle, the vehicle and a storage medium, and aims to solve the problems that in the related art, the automatic driving decision of the vehicle is controlled based on the danger degree of a single target, the influence of other danger factors on the decision is ignored, the decision planning is unreasonable, the driving safety is reduced, the user experience is poor, and the like.
An embodiment of a first aspect of the present application provides a control method for an autonomous vehicle, including the following steps: acquiring actual running states of a plurality of target vehicles around the vehicle; calculating an actual danger level of each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and calculating an actual danger level of a traffic flow consisting of the plurality of target vehicles according to the actual danger level of each target vehicle; and when the actual danger level of the traffic flow is smaller than a preset level, controlling the vehicle to execute an acceleration action and/or a lane changing action, otherwise, controlling the vehicle to execute a deceleration action or keeping the current vehicle speed unchanged.
According to the technical means, the actual running state of the vehicle flow formed by a plurality of target vehicles and the vehicles around the running of the vehicle is obtained, the actual danger level of the vehicle flow formed by each target vehicle to the vehicle is calculated, when the actual danger level is small, the vehicle can be controlled to accelerate or change lanes, otherwise, the vehicle is controlled to decelerate or keep the lane running, so that the danger degree of the vehicle flow is accurately identified and evaluated, the vehicle is controlled to execute the automatic driving decision based on the danger degree of the vehicle flow, the automatic driving decision is more reasonable and humanized, the safety of the automatic driving vehicle is improved, and the use experience of a user is improved.
Optionally, the calculating an actual risk level of each target vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle includes: calculating the collision avoidance deceleration of the host vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration; the transverse distance ratio is calculated according to the transverse distance between the target vehicle and the lane line where the vehicle is located, the vehicle body width of the target vehicle and the lane width of the lane where the target vehicle is located, and the transverse danger level of each target vehicle is matched according to the transverse distance ratio; and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse risk coefficient and a longitudinal risk coefficient, and calculating the actual risk level of each target vehicle according to the longitudinal risk level, the transverse risk coefficient and the longitudinal risk coefficient.
According to the technical means, the collision deceleration and the transverse distance ratio between the vehicle and each target vehicle are calculated to respectively match the longitudinal danger level and the transverse danger level, the longitudinal distance between the vehicle and each target vehicle is used as an index, the transverse danger coefficient and the longitudinal danger coefficient are obtained by inquiring the table, the actual danger level of the target vehicle is obtained based on the longitudinal/transverse danger level and the coefficient, a basis is provided for a transverse/longitudinal planning decision making part of the automatic driving vehicle, the automatic driving function of the vehicle is enabled to be more reasonable, and the driving safety and the vehicle using experience of a user are improved.
Optionally, the calculating the collision avoidance deceleration of the host vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle includes: calculating longitudinal collision time and transverse collision time between the host vehicle and each target vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle; and when the difference value between the transverse collision time and the longitudinal collision time is smaller than a collision threshold value, calculating the collision avoidance deceleration according to the vehicle speed of the vehicle, the vehicle speed of the target vehicle and the longitudinal collision time, otherwise, judging that no collision risk exists between the vehicle and the target vehicle.
According to the technical means, the method and the device for avoiding the collision of the vehicle calculate the longitudinal/transverse collision time based on the actual running state of the vehicle and the target vehicle, and when the difference between the transverse collision time and the longitudinal collision time is smaller than the collision threshold value, and the collision risk is higher, the required avoiding deceleration of the vehicle is continuously calculated; when the difference between the transverse collision time and the longitudinal collision time is greater than or equal to the collision threshold value, it is judged that the vehicle and the target vehicle have no collision risk, and when the vehicle has the collision risk, the avoiding deceleration required by the vehicle is automatically calculated, so that the vehicle is timely reminded to avoid collision, and the driving safety and the vehicle using experience of a user are improved.
Optionally, the calculating an actual risk level of a traffic flow composed of the plurality of target vehicles according to the actual risk level of each target vehicle includes: matching the weight of each target vehicle according to the relative position relationship between each target vehicle and the host vehicle; and carrying out weighted summation according to the actual danger level and the weight of each target vehicle to obtain a summation result, and determining the actual danger level of the traffic flow according to the summation result.
According to the technical means, the embodiment of the application determines the actual danger level of the traffic flow through the weighting of each target vehicle to the vehicle and the weighting summation of the weighting of each target vehicle and the actual danger level of the vehicle, and provides a basis for the influence of a plurality of targets on the vehicle in the driving process of the automatic driving vehicle under the condition of more vehicles, so that the driving safety and the vehicle using experience of a user are improved.
Optionally, the calculating an actual risk level of a traffic flow composed of the plurality of target vehicles according to the actual risk level of each target vehicle further includes: calculating the traffic flow speed and the traffic flow density of the traffic flow according to the actual running state of each target vehicle; matching the initial danger level of the traffic flow according to the traffic flow density and the speed difference between the vehicle and the traffic flow speed; and normalizing the summation result and the basic danger level by utilizing a first preset normalization processing strategy to obtain the actual danger level of the traffic flow.
According to the technical means, the danger levels of the vehicles are matched according to the speed and the density of the vehicles around the vehicle, the sum result is normalized to obtain the actual danger level of the traffic flow, the actual influence of the traffic flow around the vehicle on the vehicle is comprehensively considered, the driving safety of the vehicle is ensured according to the actual danger level, and the driving safety and the vehicle using experience of a user are improved.
Optionally, when the traffic flows composed of the multiple target vehicles are respectively located on two sides of the host vehicle, the calculating an actual danger level of the traffic flow composed of the multiple target vehicles according to the actual danger level of each target vehicle further includes: calculating the actual danger level of the traffic flow on any side based on the first preset normalization processing strategy; and normalizing the actual danger level of the traffic flow on the two sides of the vehicle and the initial danger level by using a second preset normalization processing strategy to obtain the actual danger level of the traffic flow around the vehicle.
According to the technical means, the actual danger level of the vehicle on one side is calculated firstly, then the actual danger levels of the traffic flows on two sides are superposed for normalization processing, the actual danger level of the traffic flow around the vehicle is obtained, the danger degree of the slow traffic flows on two sides is accurately evaluated, and driving safety and vehicle using experience of a user are improved.
An embodiment of a second aspect of the present application provides a control apparatus for an autonomous vehicle, comprising: the system comprises an acquisition module, a control module and a display module, wherein the acquisition module is used for acquiring the actual running states of a plurality of target vehicles around a vehicle; the calculation module is used for calculating the actual danger level of each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and calculating the actual danger level of a traffic flow consisting of a plurality of target vehicles according to the actual danger level of each target vehicle; and the control module is used for controlling the vehicle to execute an acceleration action and/or a lane changing action when the actual danger level of the traffic flow is less than a preset level, and otherwise, controlling the vehicle to execute a deceleration action or keeping the current speed unchanged.
Optionally, the computing module is configured to: calculating the collision avoidance deceleration of the host vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration; calculating a transverse distance ratio according to the transverse distance between the target vehicle and a lane line where the vehicle is located, the width of the vehicle body of the target vehicle and the width of a lane where the target vehicle is located, and matching the transverse danger level of each target vehicle according to the transverse distance ratio; and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse risk coefficient and a longitudinal risk coefficient, and calculating the actual risk level of each target vehicle according to the longitudinal risk level, the transverse risk coefficient and the longitudinal risk coefficient.
Optionally, the calculation module is further configured to: calculating longitudinal collision time and transverse collision time between the host vehicle and each target vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle; and when the difference value between the transverse collision time and the longitudinal collision time is smaller than a collision threshold value, calculating the collision avoidance deceleration according to the vehicle speed of the vehicle, the vehicle speed of the target vehicle and the longitudinal collision time, otherwise, judging that no collision risk exists between the vehicle and the target vehicle.
Optionally, the calculation module is further configured to: matching the weight of each target vehicle according to the relative position relationship between each target vehicle and the host vehicle; and carrying out weighted summation according to the actual danger level and the weight of each target vehicle to obtain a summation result, and determining the actual danger level of the traffic flow according to the summation result.
Optionally, the calculation module is further configured to: calculating the traffic flow speed and the traffic flow density of the traffic flow according to the actual running state of each target vehicle; matching the initial danger level of the traffic flow according to the traffic flow density and the speed difference between the vehicle and the traffic flow speed; and normalizing the summation result and the basic danger level by utilizing a first preset normalization processing strategy to obtain the actual danger level of the traffic flow.
Optionally, the calculation module is further configured to: calculating the actual danger level of the traffic flow on any side based on the first preset normalization processing strategy; and normalizing the actual danger level of the traffic flow on the two sides of the vehicle and the initial danger level by using a second preset normalization processing strategy to obtain the actual danger level of the traffic flow around the vehicle.
An embodiment of a third aspect of the present application provides a vehicle, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the control method of an autonomous vehicle as described in the above embodiments.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program for execution by a processor for implementing the control method of an autonomous vehicle as described in the above embodiments.
Therefore, the application has at least the following beneficial effects:
(1) According to the embodiment of the application, the actual running state of the traffic flow formed by a plurality of target vehicles and vehicles around the running of the vehicle is obtained, the actual danger level of the traffic flow formed by each target vehicle to the vehicle is calculated, when the actual danger level is small, the vehicle can be controlled to accelerate or change lanes, otherwise, the vehicle is controlled to decelerate or keep the lane running, so that the traffic flow danger degree is accurately identified and evaluated, the vehicle is controlled to execute the automatic driving decision based on the danger degree of the traffic flow, the automatic driving decision is more reasonable and humanized, the safety of the automatic driving vehicle is improved, and the use experience of a user is improved.
(2) According to the method and the device, the longitudinal danger level and the transverse danger level are respectively matched by calculating the collision deceleration and the transverse distance ratio between the vehicle and each target vehicle, the longitudinal distance between the vehicle and each target vehicle is used as an index, the transverse danger coefficient and the longitudinal danger coefficient are obtained by querying the table, the actual danger level of the target vehicle is obtained based on the longitudinal/transverse danger level and the coefficient, a basis is provided for a transverse/longitudinal planning decision making part of the automatic driving vehicle, the automatic driving function of the vehicle is more reasonable, and the driving safety and the vehicle using experience of a user are improved.
(3) According to the method and the device, the longitudinal/transverse collision time is calculated based on the actual running state of the vehicle and the target vehicle, and when the difference between the transverse collision time and the longitudinal collision time is smaller than the collision threshold value, the collision risk is higher, and the avoidance deceleration required by the vehicle is continuously calculated; when the difference between the transverse collision time and the longitudinal collision time is greater than or equal to the collision threshold value, it is determined that the vehicle and the target vehicle have no collision risk, and when the vehicle has the collision risk, the deceleration required by the vehicle is automatically calculated, so that the vehicle is reminded in time to avoid collision, and the driving safety and the vehicle using experience of a user are improved.
(4) According to the embodiment of the application, the weight of each target vehicle to the vehicle is weighted and summed with the actual danger level of the vehicle, the obtained summation result is used for judging the actual danger level of the traffic flow, and when the vehicles are more, a basis is provided for guaranteeing the influence of a plurality of targets on the vehicle in the driving process of the vehicle, so that the driving safety and the vehicle using experience of a user are improved.
(5) According to the embodiment of the application, the danger levels of the vehicles are matched according to the speed and the density of the vehicles around the vehicle, the sum result is subjected to normalization processing, the actual danger level of the traffic flow is obtained, the actual influence of the traffic flow around the vehicle on the vehicle is comprehensively considered, the driving safety of the vehicle is ensured according to the actual danger level, and the driving safety and the vehicle using experience of a user are improved.
(6) According to the embodiment of the application, the actual danger level of the vehicle on one side is calculated firstly, then the actual danger levels of the traffic flows on two sides are superposed for normalization processing, the actual danger level of the traffic flow around the vehicle is obtained, the danger degree of the slow traffic flows on two sides is accurately evaluated, and the driving safety and the vehicle using experience of a user are improved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a control method of an autonomous vehicle according to an embodiment of the application;
FIG. 2 is an exemplary diagram of a target around a host vehicle according to an embodiment of the present application;
FIG. 3 is a graph of a normalization function tanh according to an embodiment of the present application;
FIG. 4 is a block schematic diagram of a control arrangement for an autonomous vehicle according to an embodiment of the application;
fig. 5 is a schematic structural diagram of a vehicle according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The automatic driving technology mainly comprises three parts of environment perception, decision planning and control execution. The environment perception is used as the front end of the technology, the accuracy is crucial, and the full mining and use of the information are especially important under the conditions that the performance of the current sensor is poor, the detection precision is insufficient, and the types of detectable targets are limited.
In order to improve the environment perception capability in a complex traffic scene, the method needs to evaluate the traffic flow danger degree on two sides of the automatic driving vehicle by integrating the road form, the driving intention, the driving state and other information of target vehicles around the automatic driving vehicle, so that the rationality and the advance of decision planning can be ensured, sufficient processing time is reserved for a control execution part, and the driving safety and the comfort are improved.
The existing risk level estimation algorithms mainly have the following two types:
(1) The method is used for evaluating the influence of a single target on the safe driving of the vehicle, decision planning is carried out on the dangerous target, the factors of mutual influence of a plurality of targets are not considered, the evaluation result is too simple and mechanical, the planning control cannot treat the dangerous target in different traffic states differently, the difference between the planning control and the driving process operated by a driver is large, and the reasonableness is obviously insufficient.
(2) The method for estimating the target danger level based on the environmental state, the target vehicle intention state and the target vehicle type considers the influence of the environmental state on the target danger level, does not comprehensively consider a plurality of target danger levels in the environment, and cannot reflect the danger caused by the road information and the complexity of the driving environment in the driving environment to the vehicle.
Specifically, fig. 1 is a flowchart of a control method for an autonomous vehicle according to an embodiment of the present disclosure.
As shown in fig. 1, the control method of the autonomous vehicle includes the steps of:
in step S101, the actual traveling states of a plurality of target vehicles around the host vehicle are acquired.
It is understood that the embodiment of the present application provides the acquired running states of a plurality of target vehicles around the own vehicle, in preparation for subsequent evaluation of the risk level thereof.
In step S102, an actual risk level of each target vehicle is calculated from the actual traveling state of the host vehicle and the actual traveling state of each target vehicle, and an actual risk level of a traffic flow composed of a plurality of target vehicles is calculated from the actual risk level of each target vehicle.
It can be understood that, in the embodiment of the application, the actual danger level of each target vehicle on the vehicle is calculated, the actual danger level of the traffic flow consisting of the multiple target vehicles is calculated, and the target danger levels are calculated by utilizing multiple latitudes from a single target to the whole traffic flow, so that a basis is provided for the vehicles to use different schemes for coping under different danger levels during running, the running safety and the driving comfort are improved, and the user experience is improved.
In the embodiment of the present application, calculating the actual risk level of each target vehicle from the actual running state of the own vehicle and the actual running state of each target vehicle includes: calculating the collision avoidance deceleration of the vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration; calculating a transverse distance ratio according to the transverse distance between the target vehicle and the lane line where the vehicle is located, the width of the vehicle body of the target vehicle and the width of the lane where the target vehicle is located, and matching the transverse danger level of each target vehicle according to the transverse distance ratio; and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse risk coefficient and a longitudinal risk coefficient, and calculating the actual risk level of each target vehicle according to the longitudinal risk level, the transverse risk coefficient and the longitudinal risk coefficient.
Wherein collision deceleration = (host vehicle speed-target speed)/TTC; the longitudinal danger level can be a danger level obtained by converting the deceleration data into an interval [0-1] after limiting the upper limit and the lower limit to [0-3.5 ]; the ratio of the lateral distances = the lateral distance of the target from the lane line of the host vehicle/[ (width of target lane-width of target)/2 ]; the lateral hazard level may be a hazard level obtained by limiting the value of the lateral distance ratio to-150,200.
The transverse risk coefficient can be obtained by looking up a table according to the speed of the vehicle and the longitudinal distance of the target, and the longitudinal risk coefficient = 1-transverse risk coefficient.
The preset coefficient table may be a coefficient table preset by a user, or a coefficient table obtained by a computer through multiple times of data, which is not specifically limited herein.
It can be understood that, in the embodiment of the application, the longitudinal danger level and the lateral danger level are respectively matched by calculating the collision deceleration and the lateral distance proportion between the vehicle and each target vehicle, the longitudinal distance between the vehicle and each target vehicle is used as an index, the lateral danger coefficient and the longitudinal danger coefficient are obtained by querying the table, the actual danger level of the target vehicle is obtained based on the longitudinal/lateral danger level and the coefficient, and a basis is provided for a lateral/longitudinal planning decision-making part of an automatic driving vehicle, so that the automatic driving function of the vehicle is more reasonable, and the driving safety and the vehicle using experience of a user are improved.
In the embodiment of the present application, calculating the collision avoidance deceleration of the host vehicle from the actual traveling state of the host vehicle and the actual traveling state of each target vehicle includes: calculating longitudinal collision time and transverse collision time between the host vehicle and each target vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle; and when the difference value between the transverse collision time and the longitudinal collision time is smaller than the collision threshold value, calculating collision avoidance deceleration according to the vehicle speed of the vehicle, the vehicle speed of the target vehicle and the longitudinal collision time, and otherwise, judging that no collision risk exists between the vehicle and the target vehicle.
Wherein the collision threshold may be TTC +0.1= tlc.
It can be understood that, in the embodiment of the present application, the longitudinal/lateral collision time is calculated based on the actual running state of the host vehicle and the target vehicle, and when the difference between the lateral collision time and the longitudinal collision time is smaller than the collision threshold, and the collision risk is higher at this time, the avoidance deceleration required by the host vehicle is continuously calculated; when the difference between the transverse collision time and the longitudinal collision time is greater than or equal to the collision threshold value, it is determined that the vehicle and the target vehicle have no collision risk, and when the vehicle has the collision risk, the deceleration required by the vehicle is automatically calculated, so that the vehicle is reminded in time to avoid collision, and the driving safety and the vehicle using experience of a user are improved.
In the embodiment of the present application, calculating the actual risk level of a flow made up of a plurality of target vehicles based on the actual risk level of each target vehicle includes: matching the weight of each target vehicle according to the relative position relationship between each target vehicle and the vehicle; and performing weighted summation according to the actual danger level and the weight of each target vehicle to obtain a summation result, and determining the actual danger level of the traffic flow according to the summation result.
The weight may be a specific gravity of the degree of risk of each target vehicle to the host vehicle with respect to the whole.
It can be understood that, in the embodiment of the present application, the weighting of each target vehicle on the vehicle is performed, and the weighting summation is performed on the weighting of each target vehicle and the actual danger level of the vehicle, so that the obtained summation result determines the actual danger level of the traffic flow, and when there are many vehicles, a basis is provided for influences of multiple targets on the vehicle in the driving process of the automatic driving vehicle, so as to improve the driving safety and the vehicle using experience of the user.
In the embodiment of the present application, calculating the actual risk level of a traffic flow made up of a plurality of target vehicles based on the actual risk level of each target vehicle further includes: calculating the traffic flow speed and the traffic flow density of the traffic flow according to the actual running state of each target vehicle; matching the initial danger level of the traffic flow according to the traffic flow density and the speed difference between the vehicle and the traffic flow speed; and normalizing the summation result and the basic danger level by using a first preset normalization processing strategy to obtain the actual danger level of the traffic flow.
The initial danger level is a danger level obtained by looking up a table according to the density of the traffic flow and the speed difference between the vehicle and the traffic flow.
The first preset normalization processing policy may be a normalization processing policy preset by a user, for example: and carrying out weighted summation on the actual danger level and the weight of each target vehicle around the vehicle to obtain a summation result, and carrying out normalization processing on the basic danger level of the traffic flow to obtain the danger level of the traffic flow.
It can be understood that, in the embodiment of the present application, the initial danger levels of the vehicles are matched according to the speed and the density of the vehicles around the vehicle, and the sum result of the initial danger levels is normalized to obtain the actual danger levels of the traffic flows, the actual influence of the traffic flows around the vehicle on the vehicle is comprehensively considered, the driving safety of the vehicle is ensured according to the actual danger levels, and the driving safety and the vehicle using experience of the user are improved.
Specifically, a summation result obtained by weighting and summing the actual risk level and the weight of each target vehicle around the host vehicle and a risk level of the traffic flow are obtained by normalizing the basic risk level of the traffic flow, and the formula is specifically as follows:
Left_Traffic_DF/Right_Traffic_DF＝tanh(1.6*DangerFactorTraffic+0.5*DangerFactorTargets)*100％。
in the embodiment of the present application, when the flows composed of a plurality of target vehicles are respectively located on both sides of the own vehicle, calculating the actual risk level of the flow composed of a plurality of target vehicles according to the actual risk level of each target vehicle, further includes: calculating the actual danger level of the traffic flow on any side based on a first preset normalization processing strategy; and normalizing the actual danger level and the initial danger level of the traffic flow on the two sides of the vehicle by using a second preset normalization processing strategy to obtain the actual danger level of the traffic flow around the vehicle.
The second preset normalization processing policy may be a normalization processing policy preset by a user, for example: and superposing the actual danger level of the traffic flow on one side around the vehicle and the initial danger level to perform normalization processing to obtain the actual danger level of the traffic flow around the vehicle.
It can be understood that, in the embodiment of the application, the actual danger level of the vehicle on one side is calculated first, and then the actual danger levels of the traffic flows on two sides are superposed for normalization processing, so that the actual danger level of the traffic flow around the vehicle is obtained, the calculated result is more accurate, and the driving safety and the vehicle using experience of a user are improved.
Specifically, the calculation formula of the risk level of the traffic flow on both sides is as follows: left _ Right _ Tracfc _ DF = tanh (1.5) _ Left _traffic _DF + 1.5) _ Right _traffic _ +0.4) _ DangerFactorTargets).
In step S103, when the actual danger level of the traffic flow is less than the preset level, the vehicle is controlled to perform an acceleration action and/or a lane change action, otherwise the vehicle is controlled to perform a deceleration action or the current vehicle speed is kept unchanged.
The preset grade may be a grade set by a user in advance, or may be a grade obtained by a computer through multiple times of experimental data, for example: the actual preset hazard level for traffic flow may be level 5 or level 4, etc.
It can be understood that when the actual danger level is small, the vehicle can be controlled to accelerate or change lanes, otherwise the vehicle is controlled to decelerate or keep driving on lanes, and the automatic driving of the vehicle can be planned to use different acceleration/deceleration or lane change methods and the like under the scenes of different danger levels, so that the automatic driving vehicle is more reasonable and humanized, and the driving safety and the vehicle using experience of a user are improved.
According to the control method of the automatic driving vehicle provided by the embodiment of the application, the actual driving state of a plurality of target vehicles around the driving of the vehicle and the traffic flow formed by the vehicles is obtained, the actual danger level of the traffic flow formed by each target vehicle to the vehicle is calculated, when the actual danger level is smaller, the vehicle can be controlled to accelerate or change lanes, otherwise, the vehicle is controlled to decelerate or keep the lane driving, so that the danger degree of the traffic flow is accurately identified and evaluated, the vehicle is controlled to execute the automatic driving decision based on the danger degree of the traffic flow, the automatic driving decision is more reasonable and humanized, the safety of the automatic driving vehicle is improved, and the use experience of a user is improved. Therefore, the problems that in the related art, the automatic driving decision of the vehicle is controlled based on the single-target danger degree generally, the influence of other dangerous factors on the decision is ignored, the decision planning is unreasonable, the driving safety is reduced, the user experience is poor and the like are solved.
Taking the specific scenario shown in fig. 2 as an example, when RT1 is relatively far away from the vehicle or does not exist, the autonomous vehicle travels at a high speed, gradually exceeds the slow traffic flow on the left or right side, and if the left or right side vehicle suddenly cuts into the lane on which the vehicle travels, there is a safety risk, and a strong oppressive feeling and a poor comfortable feeling are brought to the passengers. In order to improve the environment perception capability in a complex traffic scene, information such as road forms, target driving intentions and driving states around the vehicle needs to be integrated, the traffic flow danger degrees on two sides of the automatic driving vehicle are evaluated, the reasonability and the advance of decision planning are ensured, sufficient processing time is reserved for a control execution part, and the driving safety and the comfort are improved.
The following will explain the evaluation method of the risk level of the automatic driving vehicle in detail, and the specific steps are as follows:
(1) Respectively calculating: target information is obtained after target original information obtained by sensors such as a camera, a millimeter wave radar, a laser radar and the like is fused, longitudinal collision time TTC (second) and transverse collision time TLC (second) of a target, deceleration taraccc (m/s ^ 2) required by the vehicle to avoid the target collision are respectively calculated according to the obtained target information, the target is in lane departure percentage LatPeer (the distance from the vehicle to the vehicle is less than 100; the distance from the vehicle to the vehicle is more than 100), traffic density trafficDensity, traffic speed trafficSpeed and speed difference DeltaV between the vehicle and the traffic are respectively calculated.
(2) Calculating the risk level of the single target: respectively calculating longitudinal collision time TTC (second) and transverse collision time TLC (second) between the vehicle and the target, and judging that collision risk exists when TTC +0.1 is larger than or equal to TLC;
calculating collision avoidance deceleration Taracc = (vehicle speed-target speed)/TTC, limiting the numerical limit of the deceleration Taracc (m/s ^ 2) to [0-3.5] and then converting to the interval [0-1] to obtain the longitudinal basic danger level long _ danger _ basic;
limiting the numerical value of the transverse distance occupation ratio lat _ percent to the upper limit and the lower limit to [ -150,200] and looking up a table to obtain a transverse basic danger level lat _ danger _ basic through the transverse distance occupation ratio lat _ percent = the transverse distance (dis _ lane)/[ (target lane width _ width-target width)/2 ] of the target distance vehicle lane line;
obtaining a transverse risk coefficient according to the speed of the vehicle and the longitudinal distance of the target by looking up a table, wherein the longitudinal risk coefficient = 1-transverse risk coefficient; and finally, calculating the horizontal/longitudinal basic danger level and the horizontal/longitudinal danger coefficient to obtain a single-target danger level Obj DangerFactor (DF).
(3) Calculating the danger level of the unilateral traffic flow: obtaining the basic danger level DangerFactorTransffof the traffic flow through table lookup according to the traffic flow density trafficDensity and the speed difference delta V between the vehicle and the traffic flow, and obtaining the danger level of the peripheral target by carrying out weighted summation and then carrying out normalization processing on the danger level of the peripheral target of the vehicle, wherein the formula is as follows:
DangerFactorTargets＝tanh(W1*DF_RT1+W3*DF_RT3+W4*DF_RT4+W5*DF_RT5+W6*DF_RT6+W7*DF_RT7+W8*DF_RT8++W19*DF_RT19++W20*DF_RT20)。
wherein, tanh is a normalization function, a curve of which is shown in fig. 3, DF _ RTn is the target risk level obtained from step 2 for the target RTn, and Wn is the target weight obtained from the following table:
| target number RTn | RT1 | RT3 | RT4 | RT5 | RT6 | RT7 | RT8 | RT19 | RT20 |
| Weight Wn | 0.6 | 1 | 1 | 0.7 | 0.7 | 0.8 | 0.8 | 0.4 | 0.4 |
And (3) integrating the basic danger level of the traffic flow and the danger level of the peripheral target, and obtaining the danger level of the traffic flow through normalization processing, wherein the formula is as follows:
Left_Traffic_DF/Right_Traffic_DF＝tanh(1.6*DangerFactorTraffic+0.5*DangerFactorTargets)*100％。
(4) And (3) calculating the dangerous level of the traffic flow on two sides: the calculation results obtained in the steps 2 and 3, the traffic flow danger levels on the two sides, and the formula is as follows:
Left_Right_Traffic_DF＝tanh(1.5*Left_Traffic_DF+1.5*Right_Traffic_DF+0.4*DangerFactorTargets)*100％。
in summary, the risk level of the target is calculated through the related target attributes of the target which are calculated respectively, then the risk level of the one-side traffic flow is obtained by integrating the target risk level and the attribute of the one-side traffic flow, and the risk levels of the traffic flows on two sides of the current vehicle are obtained by performing superposition and normalization processing according to the risk level of the one-side traffic flow.
Next, a control apparatus of an autonomous vehicle proposed according to an embodiment of the present application is described with reference to the drawings.
Fig. 4 is a block diagram schematically illustrating a control apparatus of an autonomous vehicle according to an embodiment of the present application.
As shown in fig. 4, the control device 10 for the autonomous vehicle includes: an acquisition module 100, a calculation module 200 and a control module 300.
The acquiring module 100 is configured to acquire actual driving states of a plurality of target vehicles around a host vehicle; the calculation module 200 is configured to calculate an actual risk level of each target vehicle according to an actual driving state of the host vehicle and an actual driving state of each target vehicle, and calculate an actual risk level of a traffic flow composed of a plurality of target vehicles according to the actual risk level of each target vehicle; the control module 300 is configured to control the vehicle to perform an acceleration action and/or a lane change action when the actual risk level of the traffic flow is less than a preset level, and otherwise control the vehicle to perform a deceleration action or keep the current vehicle speed unchanged.
In an embodiment of the present application, the computing module 200 is configured to: calculating the collision avoidance deceleration of the vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration; calculating a transverse distance ratio according to the transverse distance between the target vehicle and the lane line where the vehicle is located, the width of the vehicle body of the target vehicle and the width of the lane where the target vehicle is located, and matching the transverse danger level of each target vehicle according to the transverse distance ratio; and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse danger coefficient and a longitudinal danger coefficient, and calculating the actual danger level of each target vehicle according to the longitudinal danger level, the transverse danger coefficient and the longitudinal danger coefficient.
In an embodiment of the present application, the computing module 200 is further configured to: calculating longitudinal collision time and transverse collision time between the vehicle and each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle; and when the difference value between the transverse collision time and the longitudinal collision time is smaller than the collision threshold value, calculating collision avoidance deceleration according to the vehicle speed of the vehicle, the vehicle speed of the target vehicle and the longitudinal collision time, and otherwise, judging that no collision risk exists between the vehicle and the target vehicle.
In an embodiment of the present application, the calculation module is further configured to: matching the weight of each target vehicle according to the relative position relationship between each target vehicle and the vehicle; and performing weighted summation according to the actual danger level and the weight of each target vehicle to obtain a summation result, and determining the actual danger level of the traffic flow according to the summation result.
In an embodiment of the present application, the computing module 200 is further configured to: calculating the traffic flow speed and the traffic flow density of the traffic flow according to the actual running state of each target vehicle; matching the initial danger level of the traffic flow according to the traffic flow density and the speed difference between the vehicle and the traffic flow speed; and normalizing the summation result and the basic danger level by using a first preset normalization processing strategy to obtain the actual danger level of the traffic flow.
In an embodiment of the present application, the computing module 200 is further configured to: calculating the actual danger level of the traffic flow on any side based on a first preset normalization processing strategy; and normalizing the actual danger level and the initial danger level of the traffic flow on the two sides of the vehicle by using a second preset normalization processing strategy to obtain the actual danger level of the traffic flow around the vehicle.
It should be noted that the foregoing explanation of the embodiment of the control method for an autonomous vehicle is also applicable to the control device for an autonomous vehicle of this embodiment, and will not be described again here.
According to the control device of the automatic driving vehicle provided by the embodiment of the application, the actual driving state of a plurality of target vehicles around the driving of the vehicle and the traffic flow formed by the vehicles is obtained, the actual danger level of the traffic flow formed by each target vehicle to the vehicle is calculated, when the actual danger level is smaller, the vehicle can be controlled to accelerate or change lanes, otherwise, the vehicle is controlled to decelerate or keep the lane driving, so that the danger degree of the traffic flow is accurately identified and evaluated, the vehicle is controlled to execute the automatic driving decision based on the danger degree of the traffic flow, the automatic driving decision is more reasonable and humanized, the safety of the automatic driving vehicle is improved, and the use experience of a user is improved. Therefore, the problems that in the related art, the automatic driving decision of the vehicle is controlled based on the single-target danger degree generally, the influence of other dangerous factors on the decision is ignored, the decision planning is unreasonable, the driving safety is reduced, the user experience is poor and the like are solved.
Fig. 5 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:
The processor 502, when executing the program, implements the control method of the autonomous vehicle provided in the above-described embodiments.
Further, the vehicle further includes:
a communication interface 503 for communication between the memory 501 and the processor 502.
A memory 501 for storing computer programs that can be run on the processor 502.
The Memory 501 may include a high-speed RAM (Random Access Memory) Memory, and may also include a nonvolatile Memory, such as at least one disk Memory.
If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 may be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but that does not indicate only one bus or one type of bus.
Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 may complete communication with each other through an internal interface.
The processor 502 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
Embodiments of the present application also provide a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the above control method for an autonomous vehicle.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a programmable gate array, a field programmable gate array, or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A control method of an autonomous vehicle, characterized by comprising the steps of:
acquiring actual running states of a plurality of target vehicles around the vehicle;
calculating an actual danger level of each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and calculating an actual danger level of a traffic flow consisting of the plurality of target vehicles according to the actual danger level of each target vehicle;
and when the actual danger level of the traffic flow is smaller than a preset level, controlling the vehicle to execute an acceleration action and/or a lane changing action, otherwise, controlling the vehicle to execute a deceleration action or keeping the current speed unchanged.
2. The method of claim 1, wherein said calculating an actual risk level for each target vehicle based on an actual driving status of the host vehicle and an actual driving status of the each target vehicle comprises:
calculating the collision avoidance deceleration of the host vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration;
calculating a transverse distance ratio according to the transverse distance between the target vehicle and a lane line where the vehicle is located, the width of the vehicle body of the target vehicle and the width of a lane where the target vehicle is located, and matching the transverse danger level of each target vehicle according to the transverse distance ratio;
and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse danger coefficient and a longitudinal danger coefficient, and calculating the actual danger level of each target vehicle according to the longitudinal danger level, the transverse danger coefficient and the longitudinal danger coefficient.
3. The method of claim 2, wherein said calculating a collision avoidance deceleration of the host vehicle from the actual travel state of the host vehicle and the actual travel state of each target vehicle comprises:
calculating longitudinal collision time and transverse collision time between the host vehicle and each target vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle;
and when the difference value between the transverse collision time and the longitudinal collision time is smaller than a collision threshold value, calculating the collision avoidance deceleration according to the vehicle speed of the vehicle, the vehicle speed of the target vehicle and the longitudinal collision time, otherwise, judging that no collision risk exists between the vehicle and the target vehicle.
4. The method of claim 1, wherein said calculating an actual risk level for a flow of vehicles made up of said plurality of target vehicles based on said actual risk level for each target vehicle comprises:
matching the weight of each target vehicle according to the relative position relationship between each target vehicle and the host vehicle;
and performing weighted summation according to the actual danger level and the weight of each target vehicle to obtain a summation result, and determining the actual danger level of the traffic flow according to the summation result.
5. The method of claim 4, wherein said calculating an actual risk level for a flow of vehicles made up of said plurality of target vehicles based on said actual risk level for each target vehicle further comprises:
calculating the traffic flow speed and the traffic flow density of the traffic flow according to the actual running state of each target vehicle;
matching the initial danger level of the traffic flow according to the traffic flow density and the speed difference between the vehicle and the traffic flow speed;
and normalizing the summation result and the basic danger level by utilizing a first preset normalization processing strategy to obtain the actual danger level of the traffic flow.
6. The method according to claim 5, wherein said calculating an actual risk level of a flow made up of said plurality of target vehicles from an actual risk level of each of said plurality of target vehicles when the flow made up of said plurality of target vehicles is located on both sides of said own vehicle, respectively, further comprises:
calculating the actual danger level of the traffic flow on any side based on the first preset normalization processing strategy;
and normalizing the actual danger level of the traffic flow on the two sides of the vehicle and the initial danger level by using a second preset normalization processing strategy to obtain the actual danger level of the traffic flow around the vehicle.
7. A control apparatus of an autonomous vehicle, characterized by comprising:
the device comprises an acquisition module, a control module and a display module, wherein the acquisition module is used for acquiring the actual running states of a plurality of target vehicles around the vehicle;
the calculation module is used for calculating the actual danger level of each target vehicle according to the actual running state of the vehicle and the actual running state of each target vehicle, and calculating the actual danger level of a traffic flow consisting of a plurality of target vehicles according to the actual danger level of each target vehicle;
and the control module is used for controlling the vehicle to execute an acceleration action and/or a lane changing action when the actual danger level of the traffic flow is less than a preset level, and otherwise, controlling the vehicle to execute a deceleration action or keep the current speed unchanged.
8. The apparatus of claim 7, wherein the computing module is configured to:
calculating the collision avoidance deceleration of the host vehicle according to the actual running state of the host vehicle and the actual running state of each target vehicle, and matching the longitudinal danger level of each target vehicle according to the collision avoidance deceleration;
calculating a transverse distance ratio according to the transverse distance between the target vehicle and a lane line where the vehicle is located, the width of the vehicle body of the target vehicle and the width of a lane where the target vehicle is located, and matching the transverse danger level of each target vehicle according to the transverse distance ratio;
and inquiring a preset coefficient table by taking the longitudinal distance between the vehicle and the target vehicle as an index to obtain a transverse danger coefficient and a longitudinal danger coefficient, and calculating the actual danger level of each target vehicle according to the longitudinal danger level, the transverse danger coefficient and the longitudinal danger coefficient.
9. A vehicle, characterized by comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of controlling an autonomous vehicle of any of claims 1-6.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing the control method of an autonomous vehicle as claimed in any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210967939.XA CN115465288A (en) | 2022-08-12 | 2022-08-12 | Control method and device for automatic driving vehicle, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210967939.XA CN115465288A (en) | 2022-08-12 | 2022-08-12 | Control method and device for automatic driving vehicle, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115465288A true CN115465288A (en) | 2022-12-13 |
Family
ID=84365840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210967939.XA Pending CN115465288A (en) | 2022-08-12 | 2022-08-12 | Control method and device for automatic driving vehicle, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115465288A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115635963A (en) * | 2022-12-22 | 2023-01-24 | 福思(杭州)智能科技有限公司 | Target object screening method, target object screening device, electronic device, storage medium and vehicle |
-
2022
- 2022-08-12 CN CN202210967939.XA patent/CN115465288A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115635963A (en) * | 2022-12-22 | 2023-01-24 | 福思(杭州)智能科技有限公司 | Target object screening method, target object screening device, electronic device, storage medium and vehicle |
| CN115635963B (en) * | 2022-12-22 | 2023-03-07 | 福思(杭州)智能科技有限公司 | Target object screening method, target object screening device, electronic device, storage medium and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111123933B (en) | Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle | |
| US9889858B2 (en) | Confidence estimation for predictive driver assistance systems based on plausibility rules | |
| US9308919B2 (en) | Composite confidence estimation for predictive driver assistant systems | |
| US9552733B2 (en) | Course evaluation apparatus and course evaluation method | |
| CN112242069A (en) | Method and device for determining vehicle speed | |
| US20200391747A1 (en) | Vehicle control device | |
| CN114987498B (en) | Anthropomorphic trajectory planning method and device for automatic driving vehicle, vehicle and medium | |
| CN112859838B (en) | Automatic driving control method, device, equipment and medium | |
| CN115465288A (en) | Control method and device for automatic driving vehicle, vehicle and storage medium | |
| US11427200B2 (en) | Automated driving system and method of autonomously driving a vehicle | |
| CN113370800A (en) | Vehicle torque control method and device and vehicle | |
| CN115649195A (en) | Method and device for predicting forward target convergence cut, electronic device and storage medium | |
| US9230443B2 (en) | Method and system for predictive vehicle systems performance selection for enhanced maneuverability | |
| CN114475608A (en) | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium | |
| WO2021109164A1 (en) | Prediction method for lane changing of vehicle to behind vehicle ahead in target lane in automatic driving | |
| CN114475607B (en) | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium | |
| US20220396264A1 (en) | Vehicle for tracking speed profile and control method thereof | |
| CN115431961A (en) | Vehicle control method and device, vehicle and storage medium | |
| CN115489530A (en) | Lane changing method and device for vehicle, vehicle and storage medium | |
| CN115107787A (en) | Adaptive cruise offset control method and device for vehicle, vehicle and storage medium | |
| KR102645059B1 (en) | Apparatus and method for controlling transmission of vehicle | |
| US20210261126A1 (en) | System and method for vehicle lane assignment | |
| WO2021109165A1 (en) | Prediction method in automatic driving for performing lane change to overtake leading vehicle in target lane | |
| CN113071488A (en) | Vehicle speed control method and device | |
| CN115123227A (en) | Lane changing decision method and device 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 |