CN108248606A - Control method for vehicle, device and vehicle - Google Patents
Control method for vehicle, device and vehicle Download PDFInfo
- Publication number
- CN108248606A CN108248606A CN201611247780.5A CN201611247780A CN108248606A CN 108248606 A CN108248606 A CN 108248606A CN 201611247780 A CN201611247780 A CN 201611247780A CN 108248606 A CN108248606 A CN 108248606A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- attribute
- sample set
- decision
- status data
- 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.)
- Withdrawn
Links
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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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
- B60W30/14—Adaptive cruise control
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—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
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- 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
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/06—Combustion engines, Gas turbines
-
- 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
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/18—Braking system
-
- 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
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/20—Steering systems
-
- 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
- B60W2720/00—Output or target parameters relating to overall vehicle dynamics
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present invention provides a kind of control method for vehicle, device and vehicle, belongs to automatic control technology field.The method includes：Receive vehicle status data；And according to the vehicle status data and vehicle control model, determine that the control to vehicle operates.The embodiment of the present invention in real time, accurately, effectively, automatically, safely can determine to operate the control of vehicle, substantially increase the intelligent and safety of vehicle, and unmanned technical foundation is provided to realize.
Description
Technical field
The present invention relates to automatic control technology fields, and in particular, to a kind of control method for vehicle, a kind of vehicle control dress
It puts and a kind of vehicle.
Background technology
With the continuous development of science and technology, user needs the intelligence of vehicle higher and higher, such as unmanned skill
Art is studied, that is, vehicle is allowed to make rational behavior according to the environment perceived.However traffic environment is complicated, such as in four crossway
Mouthful, front right-turning vehicles and current through vehicles might have the right vehicle on the road of conflict or normally travel and have lane change
Behavior, at this moment current vehicle, which can accelerate to pass through or slow down, follows or lane-change traveling etc., how to be completed under similar situation automatic
Driving is the problem of unmanned vehicle Decision Control will be inquired into.
Present inventor has found that existing technical solution is generally based on finite state in the implementation of the present invention
Machine, and there are following defects for this scheme：(1) traffic environment is complicated, is difficult to cover based on state machine model all possible
Situation；(2) logic of each state can become increasingly complex with the increase of some new states.The quantity and shape of maintenance state
State logic complexity is a very big difficult point, needs reasonably to divide and reuse state；(3) state machine redirects condition one
Denier is unsatisfactory for, and will be stuck in some state always.
Invention content
To achieve these goals, an embodiment of the present invention provides a kind of control method for vehicle, this method includes：Receive vehicle
Status data；And according to the vehicle status data and vehicle control model, determine that the control to vehicle operates.
Optionally, the vehicle status data includes at least one of following：Vehicle speed, vehicle to stop line away from
From, conflict time and the barrier speed of vehicle offset distance, vehicle and barrier.
Optionally, the vehicle control model is established according to following steps：The step of establishing sample set, wherein the step packet
It includes：Training vehicle status data during acquisition user's driving vehicle drives the user as training condition attribute sample set
The control operation that corresponding to during vehicle, the trained vehicle status data was taken is as training decision attribute sample set；Wherein
The training condition attribute sample set includes multiple conditional attributes, and the multiple conditional attribute corresponds to training vehicle status data
Different types of data and the trained decision attribute sample set include multiple decision attributes, and the multiple decision attribute corresponds to
Different control operations；The step of establishing decision-tree model, the wherein step include：Calculate the training condition attribute sample set
In each conditional attribute information gain；According to the information gain and training decision attribute sample set calculated, decision tree is determined
Model.
Optionally, it is described that decision-tree model packet is determined according to the information gain calculated and training decision attribute sample set
It includes：Using the conditional attribute of the information gain value calculated maximum as root node；According to the information of each remaining conditional attribute
The sequence of yield value from big to small establishes each lower level node successively；And by the root node and each lower level node pair
The decision attribute answered node as a result.
Optionally, described the step of establishing sample set, further comprises：The training condition attribute sample set is carried out pre-
Processing；The pretreated training condition attribute sample set is subjected to attribute reduction；By the training condition attribute sample set
It is updated to the training condition attribute sample set after attribute reduction.
Optionally, the trained vehicle status data includes at least one of following：Vehicle speed, vehicle acceleration,
Vehicle to the distance of stop line, vehicle offset distance, lateral direction of car spacing, longitudinal direction of car spacing, vehicle and barrier the time that conflicts,
And the barrier speed.
Optionally, the control operation includes at least one of following：Idling, braking accelerate simultaneously track holding, slow down
And track keeps, slows down and turn left and slow down and turn right.
Correspondingly, the embodiment of the present invention additionally provides a kind of controller of vehicle, which includes：Receiving module is used for
Receive vehicle status data；And control module, for being determined pair according to the vehicle status data and vehicle control model
The control operation of vehicle.
Optionally, the vehicle status data includes at least one of following：Vehicle speed, vehicle to stop line away from
From, conflict time and the barrier speed of vehicle offset distance, vehicle and barrier.
Optionally, the vehicle control model is established according to following steps：The step of establishing sample set, wherein the step packet
It includes：Training vehicle status data during acquisition user's driving vehicle drives the user as training condition attribute sample set
The control operation that corresponding to during vehicle, the trained vehicle status data was taken is as training decision attribute sample set；Wherein
The training condition attribute sample set includes multiple conditional attributes, and the multiple conditional attribute corresponds to training vehicle status data
Different types of data and the trained decision attribute sample set include multiple decision attributes, and the multiple decision attribute corresponds to
Different control operations；The step of establishing decision-tree model, the wherein step include：Calculate the training condition attribute sample set
In each conditional attribute information gain；According to the information gain and training decision attribute sample set calculated, decision tree is determined
Model.
Optionally, it is described that decision-tree model packet is determined according to the information gain calculated and training decision attribute sample set
It includes：Using the conditional attribute of the information gain value calculated maximum as root node；According to the information of each remaining conditional attribute
The sequence of yield value from big to small establishes each lower level node successively；And by the root node and each lower level node pair
The decision attribute answered node as a result.
Optionally, described the step of establishing sample set, further comprises：The training condition attribute sample set is carried out pre-
Processing；The pretreated training condition attribute sample set is subjected to attribute reduction；By the training condition attribute sample set
It is updated to the training condition attribute sample set after attribute reduction.
Optionally, the trained vehicle status data includes at least one of following：Vehicle speed, vehicle acceleration,
Vehicle to the distance of stop line, vehicle offset distance, lateral direction of car spacing, longitudinal direction of car spacing, vehicle and barrier the time that conflicts,
And the barrier speed.
Optionally, the control operation includes at least one of following：Idling, braking accelerate simultaneously track holding, slow down
And track keeps, slows down and turn left and slow down and turn right.
In addition, the embodiment of the present invention additionally provides a kind of vehicle, which includes：Multiple detection devices, for detecting vehicle
Status data；And the controller of vehicle of the embodiment of the present invention, the controller of vehicle respectively with the multiple detection
Device connects.
Through the above technical solutions, according to the vehicle status data and vehicle control model that receive, can in real time,
Accurately, it effectively, automatically, safely determines that the control to vehicle operates, substantially increases the intelligent and safe of vehicle
Property, unmanned provide technical foundation to realize.
The other feature and advantage of the embodiment of the present invention will be described in detail in subsequent specific embodiment part.
Description of the drawings
Attached drawing is that the embodiment of the present invention is further understood for providing, and a part for constitution instruction, under
The specific embodiment in face is used to explain the embodiment of the present invention, but do not form the limitation to the embodiment of the present invention together.Attached
In figure：
Fig. 1 is a kind of structure diagram of the controller of vehicle of embodiment according to embodiments of the present invention；
Fig. 2 is the signal of the control process performed by a kind of controller of vehicle of embodiment according to embodiments of the present invention
Figure；And
Fig. 3 is a kind of example flow diagram of the control method for vehicle of embodiment according to embodiments of the present invention.
Specific embodiment
The specific embodiment of the embodiment of the present invention is described in detail below in conjunction with attached drawing.It should be understood that this
Locate described specific embodiment and be merely to illustrate and explain the present invention embodiment, be not intended to restrict the invention embodiment.
In order in real time, accurately, effectively, automatically, safely determine that the control to vehicle is grasped according to vehicle-state
Make, the embodiment of the present invention considers various embodiments, will be described in detail one by one below：
Embodiment 1
Fig. 1 is a kind of structure diagram of the controller of vehicle 100 of embodiment according to embodiments of the present invention, such as Fig. 1
Shown, which can include：Receiving module 10 can be used in receiving vehicle status data, such as from each inspection in vehicle
It surveys in device or each data that can reflect vehicle-state is received from electronic control unit ECU；And control module 20,
It can be used in determining that the control to vehicle operates according to the vehicle status data and vehicle control model.
Specifically, the vehicle status data can include at least one of following：Vehicle speed, vehicle to stop line
Distance, vehicle offset distance, vehicle and barrier conflict time and the barrier speed.In addition, the vehicle-state number
According to any data that can reflect vehicle-state can also be included, such as vehicle acceleration, lateral direction of car spacing and vehicle are indulged
To spacing etc..Above-mentioned vehicle status data can directly acquire from electronic control unit ECU or from self-adaption cruise system
Middle acquisition.Later, control module 20 can determine the control to vehicle according to the vehicle status data and vehicle control model
System operation, i.e., can by the calculating of vehicle control module using the vehicle status data as the input of vehicle control model
To export control operation as a result, for example described control operation can be including at least one of following：Idling, adds braking
The vehicle control systems such as speed and track keep, slow down and track keeps, slows down and turn left and slows down and turn right.
Using the present embodiment, controller of vehicle 100 needs the vehicle status data received being input to vehicle control
Simulation, it will be able in real time, accurately, effectively, automatically, safely determine that the control to vehicle operates, greatly improve
The intelligent and safety of vehicle unmanned provides technical foundation to realize.
Embodiment 2
Fig. 2 is the control process performed by a kind of controller of vehicle 100 of embodiment according to embodiments of the present invention
Schematic diagram, as shown in Fig. 2, the vehicle status data that the control module 20 of controller of vehicle 100 will be received from receiving module 10
As the input of vehicle control model 200, vehicle control model 200 runs and exports operation result later, i.e., output with it is described
The corresponding control operation of vehicle status data.In the embodiment 2, in order to realize the purpose of the embodiment of the present invention, one kind is provided
Example vehicle Controlling model 200, controller of vehicle 100 can pre-establish vehicle control model 200.
Specifically, the vehicle control model 200 can be established according to following steps：
(1) step 1000 of sample set is established, wherein the step can include：
Training vehicle status data during acquisition user's driving vehicle is as training condition attribute sample set, by the user
The control operation that corresponding to when driving vehicle, the trained vehicle status data was taken is as training decision attribute sample set；
Wherein described training condition attribute sample set includes multiple conditional attributes, and the multiple conditional attribute corresponds to training vehicle-state number
According to different types of data and the trained decision attribute sample set include multiple decision attributes, the multiple decision attribute
Corresponding different control operation.For example, the trained vehicle status data can include vehicle speed, vehicle acceleration, vehicle
Distance, vehicle offset distance, lateral direction of car spacing, longitudinal direction of car spacing, vehicle to stop line and barrier conflict the time and
These different types of data, can be corresponded to different conditional attributes by the barrier speed, such as vehicle speed can be with
For conditional attribute A, vehicle acceleration can be conditional attribute B, vehicle to stop line distance can be conditional attribute C, vehicle
Offset distance can be conditional attribute D, lateral direction of car spacing can be conditional attribute E, longitudinal direction of car spacing can be conditional attribute F,
Vehicle and the time that conflicts of barrier can be conditional attribute G and the barrier speed can be conditional attribute H.Also,
The trained decision attribute sample set can include idling, braking, accelerate and track keeps, slows down and track keeps, slows down simultaneously
Turn left and slow down and turn right, can be by these corresponding multiple decision attributes of control operation, such as idling can be decision attribute
R1, braking can be decision attribute R2, accelerate and track keeps being that decision attribute R3, deceleration and track keep being certainly
It can be decision attribute R6 that plan attribute R4, deceleration and left-hand rotation, which can be decision attribute R5 and slow down and turn right, such as such as table 1
It is shown.
1 decision attribute table of table
(2) step 1001 of decision-tree model is established, wherein the step can include：
Calculate the information gain of each conditional attribute in the training condition attribute sample set, i.e. design conditions attribute A to H
Information gain, later according to the information gain that is calculated and training decision attribute sample set, determine decision-tree model.
Specifically, using the conditional attribute of the information gain value calculated maximum as root node, later according to each residue
The information gain value sequence from big to small of conditional attribute establish each lower level node successively；And by the root node and institute
State the corresponding decision attribute of each lower level node node as a result.
Later, established decision-tree model can be verified, if decision-tree model does not reach expected accuracy,
The re -training model, i.e. cycle perform above-mentioned (1) (2) step, until model reaches expected accuracy.
Using the embodiment, the decision-tree model about vehicle-state and control operation can be established, is unpiloted
Control operation selection provides basis.
Embodiment 3
In the embodiment 3, the model established in embodiment 2 is advanced optimized, in order to further improve decision tree mould
The accuracy of type and the complexity for reducing model further can carry out denoising to above-mentioned training condition attribute sample set,
Remove the conditional attribute little with decision attribute correlation.
Specifically, the step 1000 for establishing sample set can further include：To the training condition attribute sample
Collection is pre-processed, such as carries out the pretreatment of discretization and normalization etc., and table 2 shows pretreated above-mentioned condition category
Property.
2 pretreated conditional attribute of table
Later, can also the pretreated training condition attribute sample set be further subjected to attribute reduction, removed
The little conditional attribute with decision attribute correlation.It is, for example, possible to use rough entropy concept is brief to attribute progress in information theory
It is as follows：
1. calculate absolute attribute weight of each attribute a ∈ U (U is domain, i.e., above-mentioned training condition attribute sample set) in U
The property wanted SGF (a, U), wherein SGF (a, U)=max SGF (b, U) | and b ∈ a-U }=max { E (U)-E (U ∪ { a }) }；
2. acquire the core attributes L=CORE (a) of property set U；
3. calculating the rough entropy E (L) of core attributes, when E (L)=E (U), L is most properties brief, wherein E (L), E
(U), E (U ∪ { a }) substitutes into the following formula and calculates rough entropy, rough entropyRepresent Xi in domain
Probability in U, | Xi | represent the radix of set X.
It substitutes into and calculates using above-mentioned each conditional attribute A to H as above-mentioned attribute a, removed wherein according to the L values of calculating
Conditional attribute B and D can be removed according to calculating in little conditional attribute, such as above-mentioned table 2 with decision attribute correlation.
The training condition attribute sample set training condition attribute sample set being updated to after attribute reduction, i.e. item
The set of part attribute A, C, E, F, G, H.
Later, decision-tree model is established using updated above-mentioned training condition attribute sample set：
Calculate the information gain of each conditional attribute in the training condition attribute sample set, i.e. design conditions attribute A to H
Information gain, later according to the information gain that is calculated and training decision attribute sample set, determine decision-tree model.
Specifically, using the conditional attribute of the information gain value calculated maximum as root node, later according to each residue
The information gain value sequence from big to small of conditional attribute establish each lower level node successively；And by the root node and institute
The corresponding decision attribute of each lower level node node as a result is stated, the decision-tree model of foundation can be as shown in table 3 below, table 3
In show foundation decision-tree model part.
3 decision-tree model structure table of table
| Conditional attribute | Decision attribute |
| C4 A3 | R4 |
| C3 G1 A2 H2 | R3 |
| C3 G0 A2 H1 F2 | R2 |
| C3 G0 A2 H2 F2 | R3 |
| C3 G1 A2 H1 F2 | R4 |
| C2 G0 A2 H1 F2 | R4 |
| C1 G0 A1 H1 F0 E7 | R5 |
Later, established decision-tree model can be verified, if decision-tree model does not reach expected accuracy,
The re -training model, i.e. cycle perform above-mentioned modeling procedure, until model reaches expected accuracy.
Using the present embodiment, the decision-tree model accuracy of foundation it is high and and reduce the complexity of model, including this
The controller of vehicle 100 of decision-tree model needs the vehicle status data received being input to vehicle control model, just
It can in real time, accurately, effectively, automatically, safely determine that the control to vehicle operates, and substantially increases the intelligence of vehicle
Can property and safety, unmanned provide technical foundation to realize.
Embodiment 4
In this embodiment, a kind of vehicle is provided, which can include：Multiple detection devices, for detecting vehicle shape
State data, such as trailer-mounted radar, test the speed, self-adaption cruise system etc.；And any one in above-described embodiment 1-3 or the group of more persons
The controller of vehicle of conjunction, the controller of vehicle are connect respectively with the multiple detection device, for receiving multiple detections
Device collects vehicle status data and automatically carries out control operation according to the vehicle status data.
For example, when receiving the vehicle status data of the speed for representing the vehicle and vehicle to the distance of stop line, vehicle
It can judge that user wish to slow down and be maintained on current lane and travels under present case according to above-mentioned decision-tree model, therefore
Vehicle can be automatically controlled and carry out the operation slowed down and track is kept.Later, corresponding vehicle can be sent control signals to
Equipment (such as throttle, steering wheel etc.), it is possible to realize to the unmanned of vehicle.
Using the present embodiment, vehicle only needs the vehicle status data that will be received to be input to vehicle control model, with regard to energy
The enough control in real time, accurately, effectively, automatically, safely determined to vehicle operates, and substantially increases the intelligence of vehicle
Property and safety, unmanned provide technical foundation to realize.
Fig. 3 is a kind of example flow diagram of the vehicle traveling image-recognizing method of embodiment according to embodiments of the present invention,
As shown in figure 3, this method may comprise steps of：
Step S11 receives vehicle status data；And
Step S12 according to the vehicle status data and vehicle control model, determines that the control to vehicle operates.
Optionally, the vehicle status data can include at least one of following：Vehicle speed, vehicle to stop line
Distance, vehicle offset distance, vehicle and barrier conflict time and the barrier speed.
Optionally, the vehicle control model is established according to following steps：The step of establishing sample set, wherein the step packet
It includes：Training vehicle status data during acquisition user's driving vehicle drives the user as training condition attribute sample set
The control operation that corresponding to during vehicle, the trained vehicle status data was taken is as training decision attribute sample set；Wherein
The training condition attribute sample set includes multiple conditional attributes, and the multiple conditional attribute corresponds to training vehicle status data
Different types of data and the trained decision attribute sample set include multiple decision attributes, and the multiple decision attribute corresponds to
Different control operations；The step of establishing decision-tree model, the wherein step include：Calculate the training condition attribute sample set
In each conditional attribute information gain；According to the information gain and training decision attribute sample set calculated, decision tree is determined
Model.
Optionally, it is described that decision-tree model packet is determined according to the information gain calculated and training decision attribute sample set
It includes：Using the conditional attribute of the information gain value calculated maximum as root node；According to the information of each remaining conditional attribute
The sequence of yield value from big to small establishes each lower level node successively；And by the root node and each lower level node pair
The decision attribute answered node as a result.
Optionally, described the step of establishing sample set, further comprises：The training condition attribute sample set is carried out pre-
Processing；The pretreated training condition attribute sample set is subjected to attribute reduction；By the training condition attribute sample set
It is updated to the training condition attribute sample set after attribute reduction.
Optionally, the trained vehicle status data includes at least one of following：Vehicle speed, vehicle acceleration,
Vehicle to the distance of stop line, vehicle offset distance, lateral direction of car spacing, longitudinal direction of car spacing, vehicle and barrier the time that conflicts,
And the barrier speed.
Optionally, the control operation includes at least one of following：Idling, braking accelerate simultaneously track holding, slow down
And track keeps, slows down and turn left and slow down and turn right.
It should be understood that each specific embodiment of above-mentioned control method for vehicle, in example vehicle control device
Embodiment in done and explain (as described above) in detail, details are not described herein.
In addition, controller of vehicle provided in an embodiment of the present invention can be realized, such as can in the form of hardware or software
To be applied in the form of software in any appropriate scene to vehicle control, such as vehicle control plane, electronics control
Unit ECU and other mobile units processed etc., can also be of the invention in the form of hardware with the integration of equipments in above-mentioned scene
Embodiment is to this without limiting.Those skilled in the art can be according to embodiments of the present invention open select above-mentioned various implementations
Any one of example selects the combination of above-mentioned various embodiments controller of vehicle and vehicle is configured, and other
Alternative embodiment also falls into the protection domain of the embodiment of the present invention.
The optional embodiment of the embodiment of the present invention is described in detail above in association with attached drawing, still, the embodiment of the present invention is simultaneously
The detail being not limited in the above embodiment, can be to of the invention real in the range of the technology design of the embodiment of the present invention
The technical solution for applying example carries out a variety of simple variants, these simple variants belong to the protection domain of the embodiment of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case of shield, it can be combined by any suitable means.In order to avoid unnecessary repetition, the embodiment of the present invention pair
Various combinations of possible ways no longer separately illustrate.
It will be appreciated by those skilled in the art that all or part of the steps of the method in the foregoing embodiments are can to pass through
Program is completed to instruct relevant hardware, which is stored in a storage medium, is used including some instructions so that one
A (can be microcontroller, chip etc.) or processor (processor) perform the whole of each embodiment the method for the application
Or part steps.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
In addition, arbitrary combination can also be carried out between a variety of different embodiments of the embodiment of the present invention, as long as it is not
The thought of the embodiment of the present invention is violated, should equally be considered as disclosure of that of the embodiment of the present invention.
Claims (9)
1. a kind of control method for vehicle, which is characterized in that this method includes：
Receive vehicle status data；And
According to the vehicle status data and vehicle control model, determine that the control to vehicle operates.
2. according to the method described in claim 1, it is characterized in that, the vehicle status data include it is following at least one
Person：
Vehicle speed, the distance of vehicle to stop line, vehicle offset distance, vehicle and barrier conflict time and the obstacle
Object speed.
3. according to the method described in claim 1, it is characterized in that, the vehicle control model is established according to following steps：
The step of establishing sample set, the wherein step include：
Training vehicle status data during acquisition user's driving vehicle drives the user as training condition attribute sample set
The control operation that corresponding to during vehicle, the trained vehicle status data was taken is as training decision attribute sample set；Wherein
The training condition attribute sample set includes multiple conditional attributes, and the multiple conditional attribute corresponds to training vehicle status data
Different types of data and the trained decision attribute sample set include multiple decision attributes, and the multiple decision attribute corresponds to
Different control operations；
The step of establishing decision-tree model, the wherein step include：
Calculate the information gain of each conditional attribute in the training condition attribute sample set；
According to the information gain and training decision attribute sample set calculated, decision-tree model is determined.
It is 4. according to the method described in claim 3, it is characterized in that, described according to the information gain calculated and training decision category
Property sample set determines that decision-tree model includes：
Using the conditional attribute of the information gain value calculated maximum as root node；
Each lower level node is established successively according to the information gain value sequence from big to small of each remaining conditional attribute；And
By the root node and the corresponding decision attribute of each lower level node node as a result.
5. method according to claim 3 or 4, which is characterized in that described the step of establishing sample set further comprises：
The training condition attribute sample set is pre-processed；
The pretreated training condition attribute sample set is subjected to attribute reduction；
The training condition attribute sample set training condition attribute sample set being updated to after attribute reduction.
6. according to the method described in claim 5, it is characterized in that, the trained vehicle status data include it is following at least
One：
Vehicle speed, vehicle acceleration, the distance of vehicle to stop line, vehicle offset distance, lateral direction of car spacing, longitudinal direction of car vehicle
Conflict time and the barrier speed away from, vehicle with barrier.
7. according to the method described in claim 5, it is characterized in that, it is described control operation include it is at least one of following：
Idling, braking accelerate simultaneously track holding, simultaneously track of slowing down to keep, slow down and turn left and slow down and turn right.
8. a kind of controller of vehicle, which is characterized in that the device includes：
Receiving module, for receiving vehicle status data；And
Control module, for determining the control operation to vehicle according to the vehicle status data and vehicle control model.
9. a kind of vehicle, which is characterized in that the vehicle includes：
Multiple detection devices, for detecting vehicle status data；And
Controller of vehicle according to claim 8, the controller of vehicle connect respectively with the multiple detection device
It connects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611247780.5A CN108248606A (en) | 2016-12-29 | 2016-12-29 | Control method for vehicle, device and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611247780.5A CN108248606A (en) | 2016-12-29 | 2016-12-29 | Control method for vehicle, device and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108248606A true CN108248606A (en) | 2018-07-06 |
Family
ID=62720781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611247780.5A Withdrawn CN108248606A (en) | 2016-12-29 | 2016-12-29 | Control method for vehicle, device and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108248606A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109656245A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | The determination method and apparatus of normal danger |
| CN109795508A (en) * | 2018-12-29 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Safe driving control method and device |
| CN110008317A (en) * | 2019-01-23 | 2019-07-12 | 艾肯特公司 | Natural expression processing method, response method, equipment and the system of natural intelligence |
| CN110083110A (en) * | 2019-01-23 | 2019-08-02 | 艾肯特公司 | End to end control method and control system based on natural intelligence |
| CN110989622A (en) * | 2019-12-25 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Automatic driving control method, device, storage medium and computer equipment |
| CN111038497A (en) * | 2019-12-25 | 2020-04-21 | 苏州智加科技有限公司 | Automatic driving control method and device, vehicle-mounted terminal and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070283188A1 (en) * | 2006-04-13 | 2007-12-06 | Dspace Digital Signal Processing And Control Engineering Gmbh | Diagnosis in automotive applications |
| CN103971523A (en) * | 2014-05-21 | 2014-08-06 | 南通大学 | Mountainous road traffic safety dynamic early-warning system |
| CN103996287A (en) * | 2014-05-26 | 2014-08-20 | 江苏大学 | Vehicle forced lane changing decision-making method based on decision-making tree model |
| WO2016013885A1 (en) * | 2014-07-25 | 2016-01-28 | Samsung Electronics Co., Ltd. | Method for retrieving image and electronic device thereof |
| CN105667506A (en) * | 2016-03-15 | 2016-06-15 | 江苏大学 | Dynamic emergency collision avoidance control method of vehicle |
| CN106080590A (en) * | 2016-06-12 | 2016-11-09 | 百度在线网络技术（北京）有限公司 | Control method for vehicle and device and the acquisition methods of decision model and device |
| CN108263371A (en) * | 2016-12-29 | 2018-07-10 | 乐视汽车（北京）有限公司 | Controller of vehicle and vehicle |
-
2016
- 2016-12-29 CN CN201611247780.5A patent/CN108248606A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070283188A1 (en) * | 2006-04-13 | 2007-12-06 | Dspace Digital Signal Processing And Control Engineering Gmbh | Diagnosis in automotive applications |
| CN103971523A (en) * | 2014-05-21 | 2014-08-06 | 南通大学 | Mountainous road traffic safety dynamic early-warning system |
| CN103996287A (en) * | 2014-05-26 | 2014-08-20 | 江苏大学 | Vehicle forced lane changing decision-making method based on decision-making tree model |
| WO2016013885A1 (en) * | 2014-07-25 | 2016-01-28 | Samsung Electronics Co., Ltd. | Method for retrieving image and electronic device thereof |
| CN105667506A (en) * | 2016-03-15 | 2016-06-15 | 江苏大学 | Dynamic emergency collision avoidance control method of vehicle |
| CN106080590A (en) * | 2016-06-12 | 2016-11-09 | 百度在线网络技术（北京）有限公司 | Control method for vehicle and device and the acquisition methods of decision model and device |
| CN108263371A (en) * | 2016-12-29 | 2018-07-10 | 乐视汽车（北京）有限公司 | Controller of vehicle and vehicle |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109656245A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | The determination method and apparatus of normal danger |
| CN109795508A (en) * | 2018-12-29 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Safe driving control method and device |
| CN110008317A (en) * | 2019-01-23 | 2019-07-12 | 艾肯特公司 | Natural expression processing method, response method, equipment and the system of natural intelligence |
| CN110083110A (en) * | 2019-01-23 | 2019-08-02 | 艾肯特公司 | End to end control method and control system based on natural intelligence |
| CN110989622A (en) * | 2019-12-25 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Automatic driving control method, device, storage medium and computer equipment |
| CN111038497A (en) * | 2019-12-25 | 2020-04-21 | 苏州智加科技有限公司 | Automatic driving control method and device, vehicle-mounted terminal and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108248606A (en) | Control method for vehicle, device and vehicle | |
| CN107169567B (en) | Method and device for generating decision network model for automatic vehicle driving | |
| US11084494B2 (en) | Method for detecting safety of driving behavior, apparatus, device and storage medium | |
| CN110027553A (en) | A kind of anti-collision control method based on deeply study | |
| CN110789576B (en) | Collaborative formation train safety protection scene division method and device | |
| CN103496368B (en) | There is Automobile cooperative type self-adaptive adaptive cruise control system and the method for learning ability | |
| CN111267830B (en) | Hybrid power bus energy management method, device and storage medium | |
| CN105788360B (en) | A kind of methods, devices and systems of vehicle collision avoidance | |
| CN107878457A (en) | A kind of adaptive cruise torque control method, device and electric automobile | |
| KR101876063B1 (en) | Method for deciding a road surface using vehicle data | |
| CN110949398A (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| CN110516746A (en) | A kind of driver's follow the bus behavior genre classification method based on no label data | |
| CN108569287A (en) | The method and apparatus of generation vehicle control order, vehicle control device, storage medium | |
| CN108263371A (en) | Controller of vehicle and vehicle | |
| CN113722835A (en) | Modeling method for anthropomorphic random lane change driving behavior | |
| CN113548054A (en) | Vehicle lane change intention prediction method and system based on time sequence | |
| CN106427771A (en) | Sound control method and device | |
| US9415778B2 (en) | Apparatus and method for determining careless driving | |
| Koenig et al. | Bridging the gap between open loop tests and statistical validation for highly automated driving | |
| CN105679092B (en) | A kind of driving behavior analysis system and method | |
| CN112918488B (en) | Vehicle control method, device and storage medium | |
| CN113657265A (en) | Vehicle distance detection method, system, device and medium | |
| CN114091223A (en) | Construction method of simulated traffic flow and simulation equipment | |
| CN108241866A (en) | A kind of method, apparatus guided to driving behavior and vehicle | |
| EP4209854A1 (en) | Overtaking planning method and apparatus, and electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180719 Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Rui Chi intelligent automobile (Guangzhou) Co., Ltd. Address before: 100026 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Applicant before: Music Automotive (Beijing) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| CB02 | Change of applicant information |
Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Rui Chi intelligent automobile (Guangzhou) Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190315 Address after: 100015 Building No. 7, 74, Jiuxianqiao North Road, Chaoyang District, Beijing, 001 Applicant after: FAFA Automobile (China) Co., Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180706 |
|
| WW01 | Invention patent application withdrawn after publication |