CN113788021A - Adaptive following cruise control method combined with preceding vehicle speed prediction - Google Patents
Adaptive following cruise control method combined with preceding vehicle speed prediction Download PDFInfo
- Publication number
- CN113788021A CN113788021A CN202111035789.0A CN202111035789A CN113788021A CN 113788021 A CN113788021 A CN 113788021A CN 202111035789 A CN202111035789 A CN 202111035789A CN 113788021 A CN113788021 A CN 113788021A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- speed
- distance
- self
- acceleration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000001133 acceleration Effects 0.000 claims description 51
- 230000015654 memory Effects 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 10
- 238000005265 energy consumption Methods 0.000 claims description 8
- 230000007787 long-term memory Effects 0.000 claims description 4
- 230000006403 short-term memory Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000002699 waste material Substances 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
- 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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
- B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
-
- 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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
- B60W30/162—Speed limiting therefor
-
- 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
- B60W40/105—Speed
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a self-adaptive following cruise control method combined with preceding vehicle speed prediction, which comprises the following steps of: step 10), constructing a front vehicle speed prediction model; step 20) obtaining the current operation condition information of the self vehicle and the front vehicle, and obtaining the speed of the front vehicle in the future time period by adopting the front vehicle speed prediction model; step 30) obtaining a safe vehicle distance by adopting a safe vehicle distance planning algorithm of a control invariant set according to the speed of the preceding vehicle in a future time period; and step 40) establishing a vehicle longitudinal dynamic system model, and calculating to obtain vehicle control parameters of the self vehicle by adopting a nonlinear model predictive control algorithm based on the safe vehicle distance obtained in the step 30). The invention combines the adaptive following cruise control method of the preceding vehicle speed prediction to predict the longitudinal speed of the preceding vehicle in the future time period, and constructs the time-varying safe following expected distance on the basis of the prediction, thereby realizing the safety-oriented and high-efficiency adaptive following.
Description
Technical Field
The invention belongs to the technical field of automatic driving of automobiles in intelligent traffic, and particularly relates to a self-adaptive following cruise control method combined with front automobile speed prediction.
Background
With the development of computer science, information science, control science and the like, the intellectualization and networking of the automobile are accelerated by the cross fusion between the disciplines. The progress in the field of automatic driving of automobiles also provides more possibilities for improving road traffic efficiency, road safety, energy conservation and emission reduction.
As a basic function in high-order auxiliary driving, the self-adaptive cruise control can take over an accelerator pedal to realize automatic control on longitudinal dynamics of the vehicle, and meanwhile, the distance and the speed of the front vehicle are sensed through a millimeter wave radar to realize automatic following of the front vehicle so as to prevent collision. Currently, adaptive cruise control has also made great progress with new sensors, communication systems and the addition of artificial intelligence. The automobile automatic driving system has the advantages that the automobile automatic driving system can sense the motion situation of not only the front vehicle in advance through farther front vehicle sensing distance, real-time communication information with lower time delay and a model with higher accuracy, and meanwhile the motion situation of the front traffic flow in a future period can be comprehensively predicted by combining road condition information of the front road. The method has important significance for improving various performance indexes of the automobile such as fuel economy, comfort, safety and the like.
The existing adaptive cruise control mainly adopts a constant-distance strategy and a constant-time-distance strategy as a vehicle-distance control strategy, and considers an adaptive method which is lack of nonlinear characteristics for acceleration and deceleration performance of vehicles under different road scenes and different weather environments. Meanwhile, the existing adaptive cruise control system depends on data output by sensors such as millimeter wave radar and ultrasonic radar, the resolution ratio of the identification of a target at a longer distance is still to be improved, and the traffic flow state under a dynamic traffic scene cannot be obtained.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method is characterized in that a front vehicle speed prediction-combined adaptive following cruise control method is provided, the longitudinal speed of a front vehicle in a future time period is predicted, a time-varying safe following expected distance is constructed on the basis of the prediction, and safe and efficient adaptive following is realized.
In order to solve the technical problem, the invention provides a self-adaptive following cruise control method combined with preceding vehicle speed prediction, which comprises the following steps:
step 10), constructing a front vehicle speed prediction model;
step 20) obtaining the current operation condition information of the self vehicle and the front vehicle, and obtaining the speed of the front vehicle in the future time period by adopting the front vehicle speed prediction model;
step 30) obtaining a safe vehicle distance by adopting a safe vehicle distance planning algorithm of a control invariant set according to the speed of the preceding vehicle in a future time period;
and step 40) establishing a vehicle longitudinal dynamic system model, and calculating to obtain vehicle control parameters of the self vehicle by adopting a nonlinear model predictive control algorithm based on the safe vehicle distance obtained in the step 30).
As a further improvement of the embodiment of the present invention, the step 10) specifically includes:
step 101) collecting vehicle driving condition data, wherein the vehicle driving condition data comprise self speed, acceleration, longitude, latitude and altitude of a vehicle in a typical road scene, and position and speed of a front vehicle relative to the self;
step 102) screening and cleaning the vehicle driving condition data, and dividing the vehicle driving condition data into a training data set and a verification data set;
step 103) constructing a long-short term memory neural network model with a memory door and forgetting door control function, wherein the long-short term memory neural network model has the input of the historical speed, the acceleration and the road gradient of the front vehicle and the output of the long-short term memory neural network model is the speed in the future time period;
and 104) inputting the training data set after normalization processing into the long and short term memory neural network model for training, and inputting the verification data set into the trained long and short term memory neural network model for cross verification to obtain a front vehicle speed prediction model.
As a further improvement of the embodiment of the present invention, the step 20) specifically includes:
step 201) obtaining current operation condition information of a preceding vehicle through a millimeter wave radar, wherein the current operation condition information of the preceding vehicle comprises the relative speed, the relative acceleration and the position relative to the own vehicle of the preceding vehicle;
step 202) obtaining current operation condition information of a self-vehicle through a satellite positioning system, wherein the current operation condition information of the self-vehicle comprises the position, the speed and the acceleration of the self-vehicle;
step 203) calculating to obtain the absolute position of the front vehicle according to the position of the front vehicle relative to the self vehicle and the position of the self vehicle; calculating to obtain the absolute speed of the front vehicle according to the relative speed of the front vehicle and the speed of the self vehicle; calculating to obtain the absolute acceleration of the front vehicle according to the relative acceleration of the front vehicle and the acceleration of the self vehicle;
step 204), acquiring the road gradient of the current position of the own vehicle and the highest and lowest speed limits of the current road through a geographic position information positioning system, the current position of the own vehicle and the current position of the previous vehicle;
step 205) inputting the absolute speed track, the absolute acceleration track and the gradient track of the preceding vehicle from the time when the preceding vehicle starts to follow to the current time into the speed prediction model of the preceding vehicle to obtain the speed track of the preceding vehicle in the future time period.
As a further improvement of the embodiment of the present invention, the step 30) specifically includes:
step 301) establishing a state space model of a front and rear vehicle following system shown in the vertical type (1):
wherein Δ s represents a distance between the subject vehicle and the preceding vehicle, vegoThe speed of the vehicle is shown as the speed of the vehicle,representing the predicted preceding vehicle speed, g (t) representing the longitudinal acceleration of the own vehicle,representing the acceleration of the preceding vehicle;
step 302) adopts an allowance set shown in an equation (2) to represent state quantities in state space models of front and rear vehicle following systems:
wherein χ represents a permissible set of state variables,/minThe minimum safety distance required to be ensured between the front vehicle and the self vehicle in an exquisite state is represented;
step 303) defining a state constraint security set as a control invariant set, and expressing by adopting a formula (3):
where ψ represents a state constraint security set,indicating the predicted minimum acceleration of the preceding vehicle, g (t)minRepresents a minimum acceleration of the own vehicle; h represents the allowable set of the feasible accelerations of the front vehicle, and I represents the allowable set of the feasible accelerations of the self vehicle;
step 304) braking the current position of the front vehicle at the maximum deceleration, and calculating to obtain the braking distance and the final parking position of the front vehicle; backing the vehicle from the last parking position of the front vehicle by the minimum vehicle distance, recording the position of backing as the reverse recursion starting position of the vehicle, calculating the absolute value of the maximum deceleration of the vehicle from the stop starting position of the vehicle, accelerating the vehicle in the reverse direction until the speed of the vehicle is equal to the maximum speed of the vehicle allowed on the current road, and recording the acceleration distance of the vehicle in the process and the last position of the vehicle; and subtracting the maximum position of the vehicle accelerated to the maximum allowable speed of the road from the final position of the vehicle decelerated to be static, and obtaining the relative distance as the current safe vehicle distance.
As a further improvement of the embodiment of the present invention, the step 40) specifically includes:
step 401) establishing a vehicle longitudinal dynamics system model, which satisfies the formula (4):
wherein T represents a torque applied to the wheel, R represents a wheel radius, CDDenotes the wind resistance coefficient of the vehicle, AfThe area of the windward side of the vehicle is represented, rho represents the air density, and m represents the total assembly mass of the vehicle;
discretizing the vehicle longitudinal dynamics system model to satisfy equation (5):
x (t +1) ═ f (u (t), x (t), θ (t), t) formula (5)
Step 402), according to a vehicle longitudinal dynamic system model, considering a following distance error, comfort of drivers and passengers and energy consumption required by a vehicle, establishing a quadratic objective function of the vehicle longitudinal dynamic system shown in a formula (6):
in the formula, δ d (k | t) represents the desired vehicle distance cost soft constraint, Δ a (k | t) represents the acceleration of the own vehicle, and f (k | t → t)0) Represents the cumulative energy consumption of the vehicle, R1A first weight coefficient, R, representing a cost function2A second weight coefficient, R, representing the cost function3Representing a cost functionA third weight coefficient;
step 403) establishing a constraint set of vehicle speed control according to the safe vehicle distance obtained in the step 30), wherein the constraint set comprises:
vehicle torque restraint: t isminω(k|t)≤T(k|t)≤Tmaxω(k|t),
And (3) vehicle speed extreme value constraint: v. ofmin≤v(k|t)≤vmax,
the expected vehicle distance soft constraint:
wherein the expected distance is added to the objective function shown in the formula (6) in the form of soft constraint;
step 404) solving to obtain the vehicle control parameters of the vehicle.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects: the self-adaptive following cruise control method combined with the preceding vehicle speed prediction comprises the steps of firstly constructing a preceding vehicle speed prediction model, predicting the speed of a preceding vehicle in a future time period by using the preceding vehicle speed prediction model during driving, then obtaining a safe vehicle distance by using a safe vehicle distance planning algorithm of a control invariant set, and finally calculating by using a nonlinear model prediction control algorithm to obtain vehicle control parameters of the self-vehicle based on the safe vehicle distance. The method provided by the embodiment of the invention utilizes the sensor configuration and information acquisition mode of the existing vehicle, considers the condition that the front vehicle is manually driven, and realizes safe, efficient and energy-saving driving control of the vehicle under the condition of saving cost as much as possible.
Drawings
FIG. 1 is a flow chart of an adaptive following cruise control method according to an embodiment of the present invention;
FIG. 2 is a control system architecture diagram of an adaptive following cruise control method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a calculation method for obtaining a safe vehicle distance in the method according to the embodiment of the present invention.
FIG. 4 is a graph of simulation results of a method according to an embodiment of the present invention, wherein FIG. 4(a) is a vehicle speed graph, FIG. 4(b) is a vehicle distance graph, and FIG. 4(c) is a power consumption graph.
Detailed Description
The technical solution of the present invention will be explained in detail below.
The embodiment of the invention provides a self-adaptive following cruise control method combined with preceding vehicle speed prediction, which comprises the following steps as shown in figure 1:
step 10), constructing a front vehicle speed prediction model;
step 20) obtaining the current operation condition information of the self vehicle and the front vehicle, and obtaining the speed of the front vehicle in the future time period by adopting the front vehicle speed prediction model;
step 30) acquiring the road gradient of the preceding vehicle in the future time period, and obtaining the safe vehicle distance by adopting a safe vehicle distance planning algorithm of a control invariant set based on the speed of the preceding vehicle in the future time period and the road gradient of the preceding vehicle in the future time period;
and step 40) establishing a vehicle longitudinal dynamic system model, and calculating to obtain vehicle control parameters of the self vehicle by adopting a nonlinear model predictive control algorithm based on the safe vehicle distance obtained in the step 30).
The self-adaptive following cruise control method combined with the preceding vehicle speed prediction comprises the steps of firstly constructing a preceding vehicle speed prediction model, predicting the speed of a preceding vehicle in a future time period by using the preceding vehicle speed prediction model during driving, then obtaining a safe vehicle distance by using a safe vehicle distance planning algorithm of a control invariant set, and finally calculating by using a nonlinear model prediction control algorithm to obtain vehicle control parameters of the self-vehicle based on the safe vehicle distance. The method provided by the embodiment of the invention utilizes the sensor configuration and information acquisition mode of the existing vehicle, considers the condition that the front vehicle is manually driven, and realizes safe, efficient and energy-saving driving control of the vehicle under the condition of saving cost as much as possible.
Preferably, the step 10) specifically includes:
step 101), collecting vehicle driving condition data, wherein the vehicle driving condition data comprises self speed v (t), acceleration a (t), longitude lon (t), latitude lat (t) and altitude alt (t) of a self vehicle in a typical road scene, and position d of a front vehicle relative to the self vehicler(t) And velocity vr(t) of (d). The number of data items collected should be 104The above.
Step 102) screening and cleaning the vehicle driving condition data, and eliminating the data except the data in the scene of non-following vehicles. And segmenting the vehicle driving condition data in batches into a training data set and a verification data set. Wherein 200 pieces of data in the dataset are validated per segment. For example, the first 90% of the data is used as the training data set, and the remaining 10% is used as the verification data set.
And step 103) constructing a long-short term memory neural network model with a memory door and forgetting door control function, wherein the long-short term memory neural network model has the input of the historical speed, the acceleration and the road gradient of the front vehicle and the output of the long-short term memory neural network model is the speed in the future time period.
Step 104) in order to improve the accuracy of prediction, the training data set is normalized, specifically, a zero-mean normalization mode is adopted, that is, the average value of the data is obtained, and all the data are averaged by taking 0 as the mean value, and the specific formula is as follows:
in the formula, XiRepresenting a sequence of historical state vectors for the leading vehicle,a sequence of average values representing historical state variables of the leading vehicle,represents the average of the historical distance vectors of the preceding vehicles,indicating the historical speed direction of the front vehicleThe average value of the amounts is,represents the average of the historical acceleration vectors of the preceding vehicle,an average value representing a gradient of a past driving road of the preceding vehicle, sig represents a standard deviation of each state variable of the preceding vehicle, X*Representing the processed historical state vector.
Inputting the normalized training set data into the long-short term memory neural network model for training, inputting the verification data set into the trained long-short term memory neural network model for cross verification, and adjusting the hyper-parameters of the neural network according to the training result until the prediction result of the neural network can meet the condition that the relative error value is less than a certain fixed value, thereby obtaining the front vehicle speed prediction model.
The root mean square error is introduced as a measurement standard, and the specific standard is that RMSE is less than or equal to 10-2. RMSE is defined as:
wherein Y (t) represents an actual observed value in the validation dataset,represents the predicted estimate of the neural network output and N represents the dimension of the input variable to the neural network.
The preceding vehicle speed prediction model constructed by the embodiment of the invention can reasonably predict the speed of the preceding vehicle in a shorter time domain based on the strong learning capability of the long-short term memory network on the time sequence type data, thereby enhancing the driving safety, the energy saving performance and the high efficiency.
Preferably, the step 20) specifically includes:
step 201) obtaining the current operation condition information of the front vehicle through the millimeter wave radar. As shown in fig. 2, the ID of the preceding vehicle is i, and the following vehicle startsIf the time is the current time, the obtained current operation condition information of the preceding vehicle comprises the relative speed v of the preceding vehicler(t | i), relative acceleration ar(t | i) and a position d relative to the vehicler(t|i)。
Step 202), obtaining current operation condition information of the self-vehicle through a satellite positioning system, wherein the current operation condition information of the self-vehicle comprises a position x (t), a speed v (t) and an acceleration a (t) of the self-vehicle.
Step 203) calculating the absolute position x of the preceding vehicle by using the formula (9) according to the position of the preceding vehicle relative to the own vehicle and the position of the own vehiclep(t) of (d). The absolute speed v of the preceding vehicle is calculated by the formula (10) based on the relative speed of the preceding vehicle and the speed of the own vehiclep(t) of (d). The absolute acceleration a of the preceding vehicle is calculated by the equation (11) based on the relative acceleration of the preceding vehicle and the acceleration of the own vehiclep(t)。
xp(t)=x(t)+dr(t | i) formula (9)
vp(t)=v(t)+vr(t | i) formula (10)
ap(t)=a(t)+ar(t | i) formula (11)
Step 203) positioning the system through the geographic position information, and the position x (t) of the self vehicle and the absolute position x of the front vehiclep(t) obtaining road slopes θ (t) and θ of the current position of the host vehiclep(t), the highest speed limit v of the road where the vehicle is currently locatedminWith the lowest limit speed vmax。
Step 204) inputting the absolute speed track, the absolute acceleration track and the gradient track of the preceding vehicle from the time when the preceding vehicle starts to follow to the current time into the speed prediction model of the preceding vehicle to obtain the speed track of the preceding vehicle in the future time period
Preferably, as shown in fig. 3, step 30) specifically includes:
step 301) establishing a state space model of a front and rear vehicle following system shown in the vertical type (1):
wherein Δ s represents a distance between the host vehicle and the preceding vehicle, vegoThe speed of the vehicle is shown as the speed of the vehicle,representing the predicted preceding vehicle speed, g (t) representing the longitudinal acceleration of the own vehicle,indicating the acceleration of the preceding vehicle.
Step 302) adopts an allowance set shown in an equation (2) to represent state quantities in state space models of front and rear vehicle following systems:
wherein χ represents a permissible set of state variables,/minThe minimum safety distance required to be ensured between the front vehicle and the self vehicle in a delicate state is represented.
Step 303) defining a state constraint security set as a control invariant set, and expressing by adopting a formula (3):
where ψ represents a state constraint security set,indicating the predicted minimum acceleration of the preceding vehicle, g (t)minRepresents a minimum acceleration of the own vehicle; h represents the allowable set of possible accelerations of the preceding vehicle, and I represents the allowable set of possible accelerations of the own vehicle.
Step 304) from the current position x of the front vehiclep(t) at maximum deceleration apminBraking, calculating the braking distance and the last parking position x of the front vehiclepn。
Retreating from the last parking position of the preceding vehicle by a minimum vehicle distance lminRecording the backward position as the reverse recursion starting position of the vehicle, and calculating the absolute value of the maximum deceleration of the vehicle from the reverse recursion starting position, accelerating the vehicle in the reverse direction from the rest state until the speed of the vehicle is equal to the maximum speed v allowed by the vehicle on the current roadmaxRecording the acceleration distance x of the bicycle during the periodaclAnd the last position x of the own vehiclen。
Accelerating the vehicle to the maximum position x of the maximum allowable speed of the roadnAnd the final position x of the preceding vehicle decelerating to a standstillpnSubtracting the distance to obtain the current safe distance dsafe。
The method of the embodiment of the invention adopts the safe vehicle distance obtained by the control invariant set to better adapt to different traffic conditions, and dynamically considers the dynamic characteristics of the front vehicle in the prediction time domain. Compared with the traditional invariant set algorithm, the method is relatively non-conservative on the premise of ensuring safety, can achieve higher car following efficiency and traffic flow density, and further improves economy and comfort.
Preferably, the step 40) specifically includes:
step 401) establishing a vehicle longitudinal dynamics system model, which satisfies the formula (4):
wherein T represents a torque applied to the wheel, R represents a wheel radius, CDDenotes the wind resistance coefficient of the vehicle, AfThe area of the windward side of the vehicle is shown, rho represents the air density, m represents the total loading mass of the vehicle, and theta represents the road gradient.
Discretizing the vehicle longitudinal dynamics system model to satisfy equation (5):
x (t +1) ═ f (u (t), x (t), θ (t), t) formula (5)
Wherein, the control variable of the system is the torque T (t) of the wheels of the vehicle, and the state variable is the vehicleSpeed v (t) and cumulative energy consumption f (t | t) of the vehicle0)。
Step 402), according to a vehicle longitudinal dynamic system model, considering a following distance error, comfort of drivers and passengers and energy consumption required by a vehicle, establishing a quadratic objective function of the vehicle longitudinal dynamic system shown in a formula (6):
in the formula, δ d (k | t) represents a desired vehicle distance cost soft constraint, here representing a vehicle; Δ a (k | t) represents the acceleration of the own vehicle, which represents the comfort of the vehicle running herein; f (k | t → t)0) The energy-saving performance of the vehicle is represented by the accumulated energy consumption of the vehicle; r1A first weight coefficient, R, representing a cost function2A second weight coefficient, R, representing the cost function3A third weight coefficient representing the cost function.
Step 403) establishing a constraint set C for controlling the vehicle speed according to the safe vehicle distance obtained in the step 30), wherein the constraint set comprises:
vehicle torque restraint: t isminω(k|t)≤T(k|t)≤Tmaxω(k|t),
And (3) vehicle speed extreme value constraint: v. ofmin≤v(k|t)≤vmax,
the expected vehicle distance soft constraint:
wherein the desired inter-vehicle distance is added to the objective function shown in equation (6) in the form of soft constraints.
And step 404), solving the established model predictive control problem by taking 20s as the predicted time domain length and 0.5s as the sampling time step length.
And finally, solving the nonlinear speed planning problem to obtain the wheel torque control quantity, namely the required control output. The torque of the vehicle is sent to a lower controller, and the lower controller is responsible for converting the signal and then sending the signal to an actuating mechanism for execution.
The invention adopts a nonlinear model predictive control algorithm, can display and express the state quantity and the control quantity constraint of the system, and conveniently constructs an objective function to realize different control target requirements.
The method of the embodiment of the invention is simulated, and the simulation result is shown in FIG. 4. The preceding vehicle speed prediction model in the embodiment of the invention shown in fig. 4(a) can reasonably predict the actual vehicle speed of the preceding vehicle, and the curve cluster of the predicted vehicle speed can better fit the actual preceding vehicle speed curve. Under different control strategies, the vehicle speed curve of the safe vehicle distance planning algorithm provided by the invention is smoother than the vehicle speed curve adopting the self-adaptive cruise control algorithm, so that a plurality of unnecessary acceleration and deceleration behaviors are reduced, and the comfort of passengers is improved. It can be seen from fig. 4(b) that the vehicle distance change by the method of the embodiment of the present invention is smoother, and the vehicle distance by the normal adaptive cruise algorithm has a certain jitter at the beginning, which causes unnecessary energy waste and uncomfortable feeling. In fig. 4(c), a pure electric vehicle is taken as an example, the method in the embodiment of the present invention can better save the electric energy consumption of the vehicle, and simultaneously, the torque output of the vehicle is smoother compared with the conventional adaptive cruise, and can better meet the requirements of comfort and energy saving.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are intended to further illustrate the principles of the invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention, which is also intended to be covered by the appended claims. The scope of the invention is defined by the claims and their equivalents.
Claims (5)
1. An adaptive following cruise control method combined with a preceding vehicle speed prediction is characterized by comprising the following steps:
step 10), constructing a front vehicle speed prediction model;
step 20) obtaining the current operation condition information of the self vehicle and the front vehicle, and obtaining the speed of the front vehicle in the future time period by adopting the front vehicle speed prediction model;
step 30) obtaining a safe vehicle distance by adopting a safe vehicle distance planning algorithm of a control invariant set according to the speed of the preceding vehicle in a future time period;
and step 40) establishing a vehicle longitudinal dynamic system model, and calculating to obtain vehicle control parameters of the self vehicle by adopting a nonlinear model predictive control algorithm based on the safe vehicle distance obtained in the step 30).
2. The adaptive cruise control with following vehicle combined with preceding vehicle speed prediction according to claim 1, characterized in that said step 10) comprises in particular:
step 101) collecting vehicle driving condition data, wherein the vehicle driving condition data comprise self speed, acceleration, longitude, latitude and altitude of a vehicle in a typical road scene, and position and speed of a front vehicle relative to the self;
step 102) screening and cleaning the vehicle driving condition data, and dividing the vehicle driving condition data into a training data set and a verification data set;
step 103) constructing a long-short term memory neural network model with a memory door and forgetting door control function, wherein the long-short term memory neural network model has the input of the historical speed, the acceleration and the road gradient of the front vehicle and the output of the long-short term memory neural network model is the speed in the future time period;
and 104) inputting the training data set after normalization processing into the long and short term memory neural network model for training, and inputting the verification data set into the trained long and short term memory neural network model for cross verification to obtain a front vehicle speed prediction model.
3. The adaptive cruise control with following vehicle combined with preceding vehicle speed prediction according to claim 1, characterized in that said step 20) comprises in particular:
step 201) obtaining current operation condition information of a preceding vehicle through a millimeter wave radar, wherein the current operation condition information of the preceding vehicle comprises the relative speed, the relative acceleration and the position relative to the own vehicle of the preceding vehicle;
step 202) obtaining current operation condition information of a self-vehicle through a satellite positioning system, wherein the current operation condition information of the self-vehicle comprises the position, the speed and the acceleration of the self-vehicle;
step 203) calculating to obtain the absolute position of the front vehicle according to the position of the front vehicle relative to the self vehicle and the position of the self vehicle; calculating to obtain the absolute speed of the front vehicle according to the relative speed of the front vehicle and the speed of the self vehicle; calculating to obtain the absolute acceleration of the front vehicle according to the relative acceleration of the front vehicle and the acceleration of the self vehicle;
step 204), acquiring the road gradient of the current position of the own vehicle and the highest and lowest speed limits of the current road through a geographic position information positioning system, the current position of the own vehicle and the current position of the previous vehicle;
step 205) inputting the absolute speed track, the absolute acceleration track and the gradient track of the preceding vehicle from the time when the preceding vehicle starts to follow to the current time into the speed prediction model of the preceding vehicle to obtain the speed track of the preceding vehicle in the future time period.
4. The adaptive cruise control with following vehicle combined with preceding vehicle speed prediction according to claim 1, characterized in that said step 30) comprises in particular:
step 301) establishing a state space model of a front and rear vehicle following system shown in the vertical type (1):
wherein Δ s represents a distance between the subject vehicle and the preceding vehicle, vegoThe speed of the vehicle is shown as the speed of the vehicle,representing the predicted preceding vehicle speed, g (t) representing the longitudinal acceleration of the own vehicle,representing the acceleration of the preceding vehicle;
step 302) adopts an allowance set shown in an equation (2) to represent state quantities in state space models of front and rear vehicle following systems:
wherein χ represents a permissible set of state variables,/minThe minimum safety distance required to be ensured between the front vehicle and the self vehicle in an exquisite state is represented;
step 303) defining a state constraint security set as a control invariant set, and expressing by adopting a formula (3):
where ψ represents a state constraint security set,indicating the predicted minimum acceleration of the preceding vehicle, g (t)minRepresents a minimum acceleration of the own vehicle; h represents the allowable set of the feasible accelerations of the front vehicle, and I represents the allowable set of the feasible accelerations of the self vehicle;
step 304) braking the current position of the front vehicle at the maximum deceleration, and calculating to obtain the braking distance and the final parking position of the front vehicle; backing the vehicle from the last parking position of the front vehicle by the minimum vehicle distance, recording the position of backing as the reverse recursion starting position of the vehicle, calculating the absolute value of the maximum deceleration of the vehicle from the stop starting position of the vehicle, accelerating the vehicle in the reverse direction until the speed of the vehicle is equal to the maximum speed of the vehicle allowed on the current road, and recording the acceleration distance of the vehicle in the process and the last position of the vehicle; and subtracting the maximum position of the vehicle accelerated to the maximum allowable speed of the road from the final position of the vehicle decelerated to be static, and obtaining the relative distance as the current safe vehicle distance.
5. The adaptive cruise control with following vehicle combined with preceding vehicle speed prediction according to claim 1, characterized in that said step 40) comprises in particular:
step 401) establishing a vehicle longitudinal dynamics system model, which satisfies the formula (4):
wherein T represents a torque applied to the wheel, R represents a wheel radius, CDDenotes the wind resistance coefficient of the vehicle, AfThe area of the windward side of the vehicle is represented, rho represents the air density, and m represents the total assembly mass of the vehicle;
discretizing the vehicle longitudinal dynamics system model to satisfy equation (5):
x (t +1) ═ f (u (t), x (t), θ (t), t) formula (5)
Step 402), according to a vehicle longitudinal dynamic system model, considering a following distance error, comfort of drivers and passengers and energy consumption required by a vehicle, establishing a quadratic objective function of the vehicle longitudinal dynamic system shown in a formula (6):
in the formula, δ d (k | t) represents the desired vehicle distance cost soft constraint, Δ a (k | t) represents the acceleration of the own vehicle, and f (k | t → t)0) Represents the cumulative energy consumption of the vehicle, R1A first weight coefficient, R, representing a cost function2A second weight coefficient, R, representing the cost function3A third weight coefficient representing the cost function;
step 403) establishing a constraint set of vehicle speed control according to the safe vehicle distance obtained in the step 30), wherein the constraint set comprises:
vehicle torque restraint: t isminω(k|t)≤T(k|t)≤Tmaxω(k|t),
And (3) vehicle speed extreme value constraint: v. ofmin≤v(k|t)≤vmax,
the expected vehicle distance soft constraint:
the expected vehicle distance is added into an objective function shown in the formula (6) in the form of soft constraint;
step 404) solving to obtain the vehicle control parameters of the vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111035789.0A CN113788021B (en) | 2021-09-03 | 2021-09-03 | Adaptive following cruise control method combined with preceding vehicle speed prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111035789.0A CN113788021B (en) | 2021-09-03 | 2021-09-03 | Adaptive following cruise control method combined with preceding vehicle speed prediction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113788021A true CN113788021A (en) | 2021-12-14 |
CN113788021B CN113788021B (en) | 2022-08-12 |
Family
ID=79182762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111035789.0A Active CN113788021B (en) | 2021-09-03 | 2021-09-03 | Adaptive following cruise control method combined with preceding vehicle speed prediction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113788021B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114407893A (en) * | 2022-01-25 | 2022-04-29 | 中寰卫星导航通信有限公司 | Self-adaptive cruise control method and device |
CN114407895A (en) * | 2022-02-25 | 2022-04-29 | 清华大学 | Vehicle predictive cruise control method, device, electronic equipment and storage medium |
CN114516325A (en) * | 2022-02-24 | 2022-05-20 | 重庆长安汽车股份有限公司 | Self-adaptive cruise sliding oil saving method and device based on preceding vehicle behavior prediction |
CN114913714A (en) * | 2022-05-05 | 2022-08-16 | 中国第一汽车股份有限公司 | Method for determining a safe distance of a vehicle |
CN115171414A (en) * | 2022-06-10 | 2022-10-11 | 哈尔滨工业大学重庆研究院 | CACC following traffic flow control system based on Frenet coordinate system |
CN115285120A (en) * | 2022-07-07 | 2022-11-04 | 东南大学 | Vehicle following hierarchical control system and method based on model predictive control |
CN116176579A (en) * | 2023-04-27 | 2023-05-30 | 安徽中科星驰自动驾驶技术有限公司 | Automatic driving following distance measuring and calculating device and method |
WO2023138100A1 (en) * | 2022-01-24 | 2023-07-27 | 广州小鹏自动驾驶科技有限公司 | Vehicle following distance calculation method and device, vehicle and storage medium |
CN117037524A (en) * | 2023-09-26 | 2023-11-10 | 苏州易百特信息科技有限公司 | Lane following optimization method and system under intelligent parking scene |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107808027A (en) * | 2017-09-14 | 2018-03-16 | 上海理工大学 | It is adaptive with car algorithm based on improved model PREDICTIVE CONTROL |
WO2019042273A1 (en) * | 2017-08-28 | 2019-03-07 | 腾讯科技(深圳)有限公司 | Method, apparatus and system for controlling vehicle-following speed, computer device, and storage medium |
CN110162046A (en) * | 2019-05-21 | 2019-08-23 | 同济人工智能研究院(苏州)有限公司 | Unmanned vehicle path following method based on event trigger type model predictive control |
CN111123701A (en) * | 2019-11-27 | 2020-05-08 | 武汉理工大学 | Automatic driving path tracking anti-interference control method based on pipeline prediction model |
CN111665853A (en) * | 2020-07-07 | 2020-09-15 | 中国人民解放军国防科技大学 | Unmanned vehicle motion planning method for planning control joint optimization |
-
2021
- 2021-09-03 CN CN202111035789.0A patent/CN113788021B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019042273A1 (en) * | 2017-08-28 | 2019-03-07 | 腾讯科技(深圳)有限公司 | Method, apparatus and system for controlling vehicle-following speed, computer device, and storage medium |
CN107808027A (en) * | 2017-09-14 | 2018-03-16 | 上海理工大学 | It is adaptive with car algorithm based on improved model PREDICTIVE CONTROL |
CN110162046A (en) * | 2019-05-21 | 2019-08-23 | 同济人工智能研究院(苏州)有限公司 | Unmanned vehicle path following method based on event trigger type model predictive control |
CN111123701A (en) * | 2019-11-27 | 2020-05-08 | 武汉理工大学 | Automatic driving path tracking anti-interference control method based on pipeline prediction model |
CN111665853A (en) * | 2020-07-07 | 2020-09-15 | 中国人民解放军国防科技大学 | Unmanned vehicle motion planning method for planning control joint optimization |
Non-Patent Citations (4)
Title |
---|
吴经贤等: "一种基于AT89S52的车辆防追尾预警系统设计", 《集美大学学报(自然科学版)》 * |
戴旭彬等: "基于MPC的自适应巡航算法改进研究", 《机电工程》 * |
明学星等: "基于混沌理论的预测PID控制器参数优化研究", 《热能动力工程》 * |
邓国红等: "协同自适应巡航控制系统跟车算法设计", 《重庆理工大学学报(自然科学)》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023138100A1 (en) * | 2022-01-24 | 2023-07-27 | 广州小鹏自动驾驶科技有限公司 | Vehicle following distance calculation method and device, vehicle and storage medium |
CN114407893A (en) * | 2022-01-25 | 2022-04-29 | 中寰卫星导航通信有限公司 | Self-adaptive cruise control method and device |
CN114516325A (en) * | 2022-02-24 | 2022-05-20 | 重庆长安汽车股份有限公司 | Self-adaptive cruise sliding oil saving method and device based on preceding vehicle behavior prediction |
CN114516325B (en) * | 2022-02-24 | 2023-10-13 | 重庆长安汽车股份有限公司 | Adaptive cruising and sliding oil saving method and device based on front vehicle behavior prediction |
CN114407895A (en) * | 2022-02-25 | 2022-04-29 | 清华大学 | Vehicle predictive cruise control method, device, electronic equipment and storage medium |
CN114407895B (en) * | 2022-02-25 | 2023-08-29 | 清华大学 | Vehicle predictive cruise control method, device, electronic equipment and storage medium |
CN114913714A (en) * | 2022-05-05 | 2022-08-16 | 中国第一汽车股份有限公司 | Method for determining a safe distance of a vehicle |
CN115171414A (en) * | 2022-06-10 | 2022-10-11 | 哈尔滨工业大学重庆研究院 | CACC following traffic flow control system based on Frenet coordinate system |
CN115285120B (en) * | 2022-07-07 | 2023-08-18 | 东南大学 | Model predictive control-based vehicle following hierarchical control system and method |
CN115285120A (en) * | 2022-07-07 | 2022-11-04 | 东南大学 | Vehicle following hierarchical control system and method based on model predictive control |
CN116176579B (en) * | 2023-04-27 | 2023-06-27 | 安徽中科星驰自动驾驶技术有限公司 | Automatic driving following distance measuring and calculating device and method |
CN116176579A (en) * | 2023-04-27 | 2023-05-30 | 安徽中科星驰自动驾驶技术有限公司 | Automatic driving following distance measuring and calculating device and method |
CN117037524A (en) * | 2023-09-26 | 2023-11-10 | 苏州易百特信息科技有限公司 | Lane following optimization method and system under intelligent parking scene |
CN117037524B (en) * | 2023-09-26 | 2023-12-22 | 苏州易百特信息科技有限公司 | Lane following optimization method and system under intelligent parking scene |
Also Published As
Publication number | Publication date |
---|---|
CN113788021B (en) | 2022-08-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113788021B (en) | Adaptive following cruise control method combined with preceding vehicle speed prediction | |
CN107117170B (en) | A kind of real-time prediction cruise control system driven based on economy | |
CN111439260B (en) | Network-connected commercial diesel vehicle cruise running optimization control system oriented to individual requirements | |
CN106740846B (en) | A kind of electric car self-adapting cruise control method of double mode switching | |
CN103003854B (en) | Systems and methods for scheduling driver interface tasks based on driver workload | |
CN111768616B (en) | Vehicle fleet consistency control method based on vehicle-road cooperation in mixed traffic scene | |
US11643080B2 (en) | Trailing vehicle positioning system based on detected pressure zones | |
CN105857309A (en) | Automotive adaptive cruise control method taking multiple targets into consideration | |
CN103085816A (en) | Trajectory tracking control method and control device for driverless vehicle | |
Zhang et al. | Data-driven based cruise control of connected and automated vehicles under cyber-physical system framework | |
CN113593275B (en) | Intersection internet automatic driving method based on bus signal priority | |
CN113722835B (en) | Personification random lane change driving behavior modeling method | |
CN112660126A (en) | Vehicle cooperative control method and device for adaptive cruise and vehicle | |
CN113741199A (en) | Vehicle economy speed planning method based on intelligent network connection information | |
CN116118730B (en) | Control method, device, equipment and medium of predictive cruise system | |
CN103231710B (en) | Driver workload based system and method for scheduling driver interface tasks | |
CN114154227B (en) | Self-adaptive learning method for braking process of heavy trailer | |
CN113561976B (en) | Vehicle energy-saving prediction adaptive cruise control method and device based on feedback optimization | |
CN113635900B (en) | Channel switching decision control method based on energy management in predicted cruising process | |
CN116142231A (en) | Multi-factor-considered longitudinal control method and system for automatic driving vehicle | |
CN115071712A (en) | Intelligent control method for energy recovery intensity of new energy automobile under sliding working condition | |
CN103264697B (en) | Based on the system and method for chaufeur work load scheduling driver interface task | |
CN116946162B (en) | Intelligent network combined commercial vehicle safe driving decision-making method considering road surface attachment condition | |
CN114771520B (en) | Electric automobile economical self-adaptive cruise control method and system based on reinforcement learning | |
CN116494974B (en) | Road risk assessment-based adaptive cruise control method, system and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |