CN107719369B - The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it - Google Patents
The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it Download PDFInfo
- Publication number
- CN107719369B CN107719369B CN201710828439.7A CN201710828439A CN107719369B CN 107719369 B CN107719369 B CN 107719369B CN 201710828439 A CN201710828439 A CN 201710828439A CN 107719369 B CN107719369 B CN 107719369B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- virtual target
- speed
- target
- dis
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000001133 acceleration Effects 0.000 claims abstract description 24
- 230000010354 integration Effects 0.000 claims abstract description 22
- 230000000694 effects Effects 0.000 claims abstract description 11
- 230000003993 interaction Effects 0.000 claims abstract description 10
- 230000001953 sensory effect Effects 0.000 claims abstract description 9
- 238000005303 weighing Methods 0.000 claims description 23
- 238000001914 filtration Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 15
- 238000011217 control strategy Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 11
- 230000003044 adaptive effect Effects 0.000 description 8
- 238000012216 screening Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 241000283070 Equus zebra Species 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000032696 parturition Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
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
- B60W30/143—Speed 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/107—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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
- B60W2720/00—Output or target parameters relating to overall vehicle dynamics
- B60W2720/10—Longitudinal speed
- B60W2720/106—Longitudinal acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of longitudinally controlled method, apparatus of automatic Pilot and with its automatic driving vehicle, which comprises S1 generates virtual target according to the expected path curvature information of this vehicle；S2 identifies real goal according to this vehicle sensory perceptual system；S3 is converted into virtual target according to traffic scene, CAR SERVICE function and integration of user interaction functionality；S4 is filtered out from each virtual target and real goal and is followed target；S5 plans the expectation acceleration of this vehicle according to target is followed.Each path point and traffic scene, the factors such as CAR SERVICE function and integration of user interaction functionality on expected path are conceptualized as virtual target by the present invention, it filters out maximum to the safety effects of this vehicle in virtual target and real goal again as unique and follows target, it is planned using acceleration of the unified control strategy to this vehicle, avoids the vehicle deceleration jump problem generated during control mode switch caused by changing in traditional control algorithm because of traffic scene.
Description
Technical field
The present invention relates to intelligent driving technical field, more particularly to a kind of longitudinally controlled method, apparatus of automatic Pilot and
With its automatic driving vehicle.
Background technique
Intelligent driving technology is particularly important component part in terms of intelligent transportation field, rapid with computing capability
It is promoted and the increasingly promotion of intelligent transportation automation demanding, research institution, more and more countries more closes with incorporated business
Infuse this field of intelligent driving.Intelligent driving technical research is related to mechano-electronic, pattern-recognition, artificial intelligence, control science
And the interdisciplines such as soft project, the subject knowledge that more intersects.And control section as most basic with most traditional part, and be divided into
Crosswise joint with it is longitudinally controlled.Wherein: crosswise joint refers to mainly controlling vehicle under conditions of known paths planned trajectory
Corner, to achieve the purpose that trajectory track.Longitudinally controlled is to lead known to path planning track and under the conditions of path tracing is preferable
Car speed is controlled, for the purpose of the safety, reasonability and the comfort that reach speed planning.Under complicated traffic environment
It automatically controls vehicle gentle start, constant speed, follow the bus, meet the function such as real goal ramp to stop, automatic emergency brake and stopping a train at a target point
Energy；It is instructed simultaneously according to decision rule layer and carries out speed control, cooperation crosswise joint realizes the behaviors such as the lane-change avoidance of vehicle.
The longitudinally controlled part as comparative basis in vehicle control, utilization is comparatively mature, and research method is less.Mesh
Preceding disclosed pertinent literature, report mainly carry out the longitudinally controlled of vehicle using the judgement of multiple modes and matching, realize
It is relatively simple, it is easy the frequent switching between multiple modes, but be the failure to consider that all kinds of real goals (such as traffic lights etc.) are right
In longitudinally controlled influence.Traditional vehicle longitudinal control uses cruise CC, adaptive cruise ACC and automatic emergency brake
The blending algorithm of AEB function, this algorithm are feasible for simple road conditions, but for slightly complicated traffic environment, due to shadow
There are many factor for ringing the behavior of automatic Pilot longitudinal direction, including setting cruising speed, front particle distance and relative velocity and user
Active behavior (such as requires parking or starting).As it can be seen that longitudinal behavior influence factor is more, and intersect between these factors
It influences, it is difficult to be described using consolidator frame, traditional vehicle longitudinal control method is cut because of state and the frequent of target
It changes and will cause car speed jump problem, comfort is poor.In traditional ADAS (Advanced Driver Assistant
Systems) in longitudinal research, and usually it is classified as ACC (Adaptive Cruise Control)+CC (Cruising
Control) three component parts of+AEB (Autonomous Emergency Braking), but due to three parts boundary condition weight
It is folded, it needs a large amount of IF-THEN logics to carry out scene switching, would potentially result in logical miss under real complex scene.Seriously
When out present condition control it is unreasonable, influence the safety of vehicle driving.
Summary of the invention
The purpose of the present invention is to provide a kind of longitudinally controlled method, apparatus of automatic Pilot come overcome or at least mitigate it is existing
At least one of drawbacks described above of technology.
To achieve the above object, the present invention provides a kind of longitudinally controlled method of automatic Pilot, and the automatic Pilot is longitudinally controlled
Method processed includes:
S1 generates the virtual target of characterization path velocity and position attribution according to the expected path curvature information of this vehicle；
S2 identifies the real goal with speed and position attribution according to this vehicle sensory perceptual system；
S3, according to traffic scene, CAR SERVICE function and integration of user interaction functionality, converting several for its feature has speed
The virtual target of degree and position attribution；
S4, from each virtual target and real goal in S1 and S3, filter out it is maximum to this vehicle safety effects with
With target；And
S5 plans the expectation of this vehicle according to the speed and range information for following target relative to this vehicle filtered out in S4
Acceleration.
Further, in S1, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows: dislon=THW × v
+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is the speed of this vehicle.
Further, in S3, virtual target includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows:
dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is
Speed limit value；
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonTable
Up to formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The virtual target
Speed be user psychology desired speed or be defaulted as road speed limit；
User's active control vehicle stops corresponding virtual target, fore-and-aft distance of the virtual target relative to this vehicle
dislonIt is directly proportional to the speed of this vehicle；The speed of the virtual target is 0km/h；
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonFor its relative to
The fore-and-aft distance of this vehicle；The speed of the virtual target is 0km/h.
Further, it in S4, filters out and maximum to this vehicle safety effects mesh calibration method is followed to specifically include:
S41 calculates the influence power of each virtual target and real goal in S1 and S3 according to following target selection model
Weight, the expression formula of target selection model are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle；
Lateral prediction distance for virtual target or real goal relative to this vehicle；
Impact factor for virtual target or real goal relative to the fore-and-aft distance of this vehicle；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle；
VrelSpeed for virtual target or real goal relative to this vehicle；
S42, the maximum virtual target of weighing factor Score or real goal being calculated via above-mentioned formula are to follow
Target.
Further, in S5, the calculation formula of " expectation acceleration " is as follows:
In formula: atargetIt is expected deceleration；
Vre lTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor；
TisFor speed term integration time constant；
TdsFor speed term derivative time constant；
KpdFor distance terms proportional control factor；
TidFor distance terms integration time constant；
TddFor distance terms derivative time constant.
The present invention also provides a kind of longitudinally controlled device of automatic Pilot, the longitudinally controlled device of automatic Pilot includes:
First virtual target generation module is used for the expected path curvature information according to this vehicle, generates characterization path speed
The virtual target of degree and position attribution；
Real goal generation module is used to be identified according to this vehicle sensory perceptual system true with speed and position attribution
Target；
Second virtual target generation module is used for according to traffic scene, CAR SERVICE function and integration of user interaction functionality, will
Its feature is converted into several virtual targets with speed and position attribution；
Object filtering module is used for raw from the first virtual target generation module and the second virtual target generation module
At each virtual target and the real goal generation module generate real goal in, filter out to this vehicle safety effects most
Big follows target；
It is expected that acceleration planning module, be used to be filtered out according to the object filtering module follows target relative to this
The speed and range information of vehicle plan the expectation acceleration of this vehicle.
Further, fore-and-aft distance of the virtual target that the first virtual target generation module generates relative to this vehicle
dislonExpression formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；It is described
The speed for the virtual target that first virtual target generation module generates is the speed of this vehicle；
The virtual target that the second virtual target generation module generates includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows:
dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is
Speed limit value；
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonTable
Up to formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The virtual target
Speed be user psychology desired speed or be defaulted as road speed limit；
User's active control vehicle stops corresponding virtual target, fore-and-aft distance of the virtual target relative to this vehicle
dislonIt is directly proportional to the speed of this vehicle；The speed of the virtual target is 0km/h；
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonFor its relative to
The fore-and-aft distance of this vehicle；The speed of the virtual target is 0km/h.
Further, the object filtering module specifically includes:
Weighing factor computing module is used to calculate first virtual target according to following target selection model and generate
The true mesh that each virtual target and the real goal generation module that module and the second virtual target generation module generate generate
Target weighing factor, the expression formula of target selection model are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle；
Lateral prediction distance for virtual target or real goal relative to this vehicle；
Impact factor for virtual target or real goal relative to the fore-and-aft distance of this vehicle；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle；
VrelSpeed for virtual target or real goal relative to this vehicle；
Target determination module is followed, the weighing factor Score that the weighing factor computing module is calculated is used for
Maximum virtual target or real goal, which are used as, follows target.
Further, the calculation formula of " the expectation acceleration " of the expectation acceleration planning module is as follows:
In formula: atargetIt is expected deceleration；
Vre lTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor；
TisFor speed term integration time constant；
TdsFor speed term derivative time constant；
KpdFor distance terms proportional control factor；
TidFor distance terms integration time constant；
TddFor distance terms derivative time constant.
The present invention also provides a kind of automatic driving vehicle, the automatic driving vehicle includes that automatic Pilot as described above is vertical
To control device.
The present invention is by each path point and traffic scene, the CAR SERVICE function and integration of user interaction functionality etc. on expected path
Factor is conceptualized as virtual target, then in virtual target and real goal it is maximum to the safety effects of this vehicle at screening
As uniquely target is followed, is planned using acceleration of the unified control strategy to this vehicle, greatly simplifie tradition
The logic switch of longitudinally controlled middle cruise, adaptive learning algorithms and automatic emergency brake control, effectively prevents tradition
The vehicle deceleration jump problem generated during control mode switch caused by changing in control algolithm because of traffic scene, thus
Improve the stationarity and comfort of vehicle longitudinal control.
Detailed description of the invention
Fig. 1 is the flow diagram of longitudinally controlled one embodiment of method of automatic Pilot provided by the present invention.
Fig. 2 is the generation method schematic diagram of the virtual target in the method for Fig. 1.
Fig. 3 is a variety of virtual targets in the method for Fig. 1 and the schematic diagram deposited.
Fig. 4 is the theory structure schematic diagram of longitudinally controlled one embodiment of device of automatic Pilot provided by the present invention.
Fig. 5 is the structural schematic diagram of one embodiment of object filtering module in Fig. 4.
Specific embodiment
In the accompanying drawings, same or similar element is indicated using same or similar label or there is same or like function
Element.The embodiment of the present invention is described in detail with reference to the accompanying drawing.
In the description of the present invention, term " center ", " longitudinal direction ", " transverse direction ", "front", "rear", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "top", "bottom" "inner", "outside" is that orientation based on the figure or position are closed
System, is merely for convenience of description of the present invention and simplification of the description, rather than the device or element of indication or suggestion meaning must have
Specific orientation is constructed and operated in a specific orientation, therefore should not be understood as limiting the scope of the invention.
As shown in Figure 1, the longitudinally controlled method of automatic Pilot provided by the present embodiment includes:
S1 generates the virtual target of characterization path velocity and position attribution according to the expected path curvature information of this vehicle.Phase
Routing information is hoped to be made of multiple path points, each path point has corresponding coordinate value and course angle, expected path information
It is the expected path information provided by camera identification lane line or differential GPS devices.Utilize existing curve-fitting method
Path point is sequentially connected in series by (least square method or Bezier fitting or using simple geometry teaching approximate calculation)
Connection, and calculate the curvature information of each selected path point.Interval phase between two adjacent selected path points
Together, the interval can according to the control accuracy requirement of automated driving system control module (such as: 0.1m) determine.
Preferably, in S1, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows: dislon=THW × v+
dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is the speed of this vehicle.
S2 identifies the real goal with speed and position attribution according to this vehicle sensory perceptual system.This vehicle sensory perceptual system can
To use radar, GPS, video camera etc., such as vehicle, bicycle and pedestrian are extracted in identification.Actual target information specifically includes:
Position coordinates point, Speed attribute.The coordinate value of each point referred in the present invention can be seen as the coordinate value in vehicle axis system,
Vehicle axis system can determine that details are not described herein using well known method.Longitudinal direction refers to the front-rear direction of vehicle, laterally refers to
Be vehicle left and right directions.
According to traffic scene, CAR SERVICE function and integration of user interaction functionality, its feature is turned as shown in Figures 2 and 3 by S3
Turn to several virtual targets with speed and position attribution.
Preferably, in S3, according to traffic scene, CAR SERVICE function and integration of user interaction functionality, traffic scene ratio therein
Such as road speed limit travels at a slow speed board and traffic lights.Virtual target includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows:
dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate that longitudinal safe distance, THW are usually arranged as 1.5-
2.3, according to driver's driving style (radical 1.5, general 1.8, guard 2.3) adjust.The corresponding virtual target of road speed limit
Speed is speed limit value.The corresponding virtual target of road speed limit is constant presence, and road speed limit refers to that institute's travel regulation permits
Perhaps Maximum speed limit.
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonTable
Up to formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate that longitudinal safe distance, THW are usually arranged
For 1.5-2.3, according to driver's driving style (radical 1.5, general 1.8, guard and 2.3) adjust.User psychology desired speed pair
The speed for the virtual target answered is user psychology desired speed or is defaulted as road speed limit.The corresponding void of user psychology desired speed
Quasi- target is constant presence.In practical applications, desired speed can be manually selected by user, or is defaulted as road speed limit.
User's active control vehicle stops corresponding virtual target, fore-and-aft distance of the virtual target relative to this vehicle
dislonIt is directly proportional to the speed of this vehicle；The speed that user's active control vehicle stops corresponding virtual target is 0km/h.User
Active control vehicle stops corresponding virtual target as condition presence.When user's initiative vehicle stops, giving birth to immediately at this time
At virtual target, the distance of the particle is directly proportional with car speed, i.e. the faster distance of speed is bigger, this is the same as vehicle actual travel mistake
Stopping distance needed for speed is higher in journey matches more greatly.After active is stopped, which will persistently exist, until user
Initiative vehicle launch, then the particle disappears automatically.
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonFor its relative to
The fore-and-aft distance of this vehicle.The speed of the corresponding virtual target of stopping a train at a target point is 0km/h.The corresponding virtual target of stopping a train at a target point is item
Part exists.When vehicle meets certain stopping a train at a target point condition, such as crossroad red light, it needs to stop before zebra stripes, vehicle
Library is returned to need at this moment to need to generate virtual target in parking stall parking etc..
S4, from each virtual target and real goal in S1 and S3, filter out it is maximum to this vehicle safety effects with
With target.
Preferably, it in S4, filters out and maximum to this vehicle safety effects mesh calibration method is followed to specifically include:
S41 calculates the influence power of each virtual target and real goal in S1 and S3 according to following target selection model
Weight, the expression formula of target selection model are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle, the influence because
Subrange 0~1 reduces with the increase of lateral prediction distance；
Lateral prediction distance for virtual target or real goal relative to this vehicle, usually predicts true mesh
The location information being marked in the following 2s time；
For virtual target or real goal relative to the fore-and-aft distance of this vehicle impact factor (influence because
1.0) son is usually；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle, the speed impact factor
It is usually arranged as 2.5；
VrelSpeed for virtual target or real goal relative to this vehicle；
S42, the maximum virtual target of weighing factor Score or real goal being calculated via above-mentioned formula are to follow
Target.
Target selection based on target selection model is screened to all targets of vehicle periphery, is extracted and is transported to vehicle
Dynamic state influences maximum target.The target of vehicle periphery mainly includes vehicle with lane real goal, neighbouring lane to be cut in advance/
The virtual targets such as the real goal and constant speed that cut out, speed limit signboard, crossroad, the present embodiment are based on energy field thought, adopt
Screening extraction is carried out to numerous targets with unified screening principle.
S5 plans the expectation of this vehicle according to the speed and range information for following target relative to this vehicle filtered out in S4
Acceleration.
Preferably, in S5, the calculation formula of " expectation acceleration " is as follows:
In formula: atargetIt is expected deceleration；
Vre lTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor, such as 0.5；
TisFor speed term integration time constant, such as 50；
TdsFor speed term derivative time constant, such as 0.02；
KpdFor distance terms proportional control factor, such as 0.1；
TidFor distance terms integration time constant, such as 200；
TddFor distance terms derivative time constant, such as 0.05.
Constant-speed-cruise control of the calculation formula of " expectation acceleration " in the present embodiment by tradition based on speed control and
Adaptive learning algorithms and automatic emergency brake control algolithm based on distance controlling blend, and form unified longitudinal P ID control
Algorithm processed greatly simplifies the longitudinally controlled middle cruise of tradition, adaptive learning algorithms and automatic because algorithm model is unified
The logic switch of emergency braking control effectively prevents control model caused by changing in traditional control algorithm because of traffic scene and cuts
The vehicle deceleration jump problem generated during changing, to improve the stationarity and comfort of vehicle longitudinal control.
As shown in figure 4, the present embodiment also provides a kind of longitudinally controlled device of automatic Pilot, the longitudinally controlled dress of the automatic Pilot
It sets including the first virtual target generation module 1, real goal generation module 2, the second virtual target generation module 3, object filtering
Module 4 and desired acceleration planning module 5, in which:
First virtual target generation module 1 is used for the expected path curvature information according to this vehicle, generates characterization path velocity
With the virtual target of position attribution.Expected path information is made of multiple path points, each path point has corresponding coordinate
Value and course angle, expected path information are the expected path information provided by camera identification lane line or differential GPS devices.
Using existing curve-fitting method, (least square method or Bezier fitting use simple geometry teaching approximation
Calculate) path point is sequentially connected in series, and calculate the curvature information of each selected path point.Adjacent two are selected
Path point between interval it is identical, the interval can according to the control accuracy requirement of automated driving system control module (such as
0.1m) determine.
Preferably, fore-and-aft distance of the virtual target that the first virtual target generation module 1 generates relative to this vehicle
dislonExpression formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；It is described
The speed for the virtual target that first virtual target generation module generates is the speed of this vehicle.
Real goal generation module 2 is for identifying the true mesh with speed and position attribution according to this vehicle sensory perceptual system
Mark.This vehicle sensory perceptual system can use radar, GPS, video camera etc., collect many real goals around expected path
Relevant information.Actual target information specifically includes: position coordinates point, Speed attribute.
As shown in Figures 2 and 3, the second virtual target generation module 3 is used for according to traffic scene, CAR SERVICE function and use
Its feature is converted several virtual targets with speed and position attribution by family interactive function.Traffic scene ratio therein
Such as road speed limit travels at a slow speed board and traffic lights.Virtual target includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows:
dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate that longitudinal safe distance, THW are usually arranged as 1.5-
2.3, according to driver's driving style (radical 1.5, general 1.8, guard 2.3) adjust.The corresponding virtual target of road speed limit
Speed is speed limit value.The corresponding virtual target of road speed limit is constant presence, and road speed limit refers to that institute's travel regulation permits
Perhaps Maximum speed limit.
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonTable
Up to formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate that longitudinal safe distance, THW are usually arranged
For 1.5-2.3, according to driver's driving style (radical 1.5, general 1.8, guard and 2.3) adjust.User psychology desired speed pair
The speed for the virtual target answered is user psychology desired speed or is defaulted as road speed limit.The corresponding void of user psychology desired speed
Quasi- target is constant presence.In practical applications, desired speed can be manually selected by user, or is defaulted as road speed limit.
User's active control vehicle stops corresponding virtual target, fore-and-aft distance of the virtual target relative to this vehicle
dislonIt is directly proportional to the speed of this vehicle；The speed that user's active control vehicle stops corresponding virtual target is 0km/h.User
Active control vehicle stops corresponding virtual target as condition presence.When user's initiative vehicle stops, giving birth to immediately at this time
At virtual target, the distance of the particle is directly proportional with car speed, i.e. the faster distance of speed is bigger, this is the same as vehicle actual travel mistake
Stopping distance needed for speed is higher in journey matches more greatly.After active is stopped, which will persistently exist, until user
Initiative vehicle launch, then the particle disappears automatically.
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonFor its relative to
The fore-and-aft distance of this vehicle.The speed of the corresponding virtual target of stopping a train at a target point is 0km/h.The corresponding virtual target of stopping a train at a target point is item
Part exists.When vehicle meets certain stopping a train at a target point condition, such as crossroad red light, it needs to stop before zebra stripes, vehicle
Library is returned to need at this moment to need to generate virtual target in parking stall parking etc..
Object filtering module 4 is used for raw from the first virtual target generation module 1 and the second virtual target generation module 3
At each virtual target and the real goal generation module 2 generate real goal in, filter out to this vehicle safety effects
It is maximum to follow target.
It is expected that acceleration planning module 5 follows target relative to this for what is filtered out according to the object filtering module 4
The speed and range information of vehicle plan the expectation acceleration of this vehicle.
The virtual target that the second virtual target generation module 3 generates includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows:
dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is
Speed limit value；
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonTable
Up to formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The virtual target
Speed be user psychology desired speed or be defaulted as road speed limit；
User's active control vehicle stops corresponding virtual target, fore-and-aft distance of the virtual target relative to this vehicle
dislonIt is directly proportional to the speed of this vehicle；The speed of the virtual target is 0km/h；
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonFor its relative to
The fore-and-aft distance of this vehicle；The speed of the virtual target is 0km/h.
As shown in figure 5, the object filtering module 4 specifically includes 41 He of weighing factor computing module in one embodiment
Follow target determination module 42, in which:
Weighing factor computing module 41 is used to calculate first virtual target according to following target selection model and generate mould
The real goal that each virtual target and the real goal generation module that block and the second virtual target generation module generate generate
Weighing factor, the expression formula of target selection model are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle, the influence because
Subrange 0~1 reduces with the increase of lateral prediction distance；
Lateral prediction distance for virtual target or real goal relative to this vehicle, usually predicts true mesh
The location information being marked in the following 2s time；
For virtual target or real goal relative to the fore-and-aft distance of this vehicle impact factor (influence because
1.0) son is usually；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle, the speed impact factor
It is usually arranged as 2.5；
VrelSpeed for virtual target or real goal relative to this vehicle.
Follow weighing factor Score of the target determination module 42 for the weighing factor computing module 41 to be calculated
Maximum virtual target or real goal, which are used as, follows target.
Target selection based on target selection model is screened to all targets of vehicle periphery, is extracted and is transported to vehicle
Dynamic state influences maximum target.The target of vehicle periphery mainly includes vehicle with lane real goal, neighbouring lane to be cut in advance/
The virtual targets such as the real goal and constant speed that cut out, speed limit signboard, crossroad, the present embodiment are based on energy field thought, adopt
Screening extraction is carried out to numerous targets with unified screening principle.
In one embodiment, the calculation formula of " the expectation acceleration " of the expectation acceleration planning module 5 is as follows:
In formula: atargetIt is expected deceleration；
VrelTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor, such as 0.5；
TisFor speed term integration time constant, such as 50；
TdsFor speed term derivative time constant, such as 0.02；
KpdFor distance terms proportional control factor, such as 0.1；
TidFor distance terms integration time constant, such as 200；
TddFor distance terms derivative time constant, such as 0.05.
Constant-speed-cruise control of the calculation formula of " expectation acceleration " in the present embodiment by tradition based on speed control, base
It is blended in the adaptive learning algorithms and automatic emergency brake control algolithm of distance controlling, forms unified longitudinal P ID control
Algorithm greatly simplifies the longitudinally controlled middle cruise of tradition, adaptive learning algorithms and automatic tight because algorithm model is unified
The logic switch of anxious control for brake effectively prevents control mode switch caused by changing in traditional control algorithm because of traffic scene
The vehicle deceleration jump problem generated in the process, to improve the stationarity and comfort of vehicle longitudinal control.
The present invention also provides a kind of automatic driving vehicle, the automatic driving vehicle includes described in the various embodiments described above
The longitudinally controlled device of automatic Pilot.The other parts of the automatic driving vehicle are the prior art, herein not reinflated description.
The present invention is by each path point and traffic scene, the CAR SERVICE function and integration of user interaction functionality etc. on expected path
Factor is conceptualized as virtual target, then in virtual target and real goal it is maximum to the safety effects of this vehicle at screening
As uniquely target is followed, is planned using acceleration of the unified control strategy to this vehicle, greatly simplifie tradition
The logic switch of longitudinally controlled middle cruise, adaptive cruise and automatic emergency brake control, effectively prevents Traditional control
The vehicle deceleration jump problem generated during control mode switch caused by changing in algorithm because of traffic scene, to improve
The stationarity and comfort of vehicle longitudinal control.
Finally it is noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations.This
The those of ordinary skill in field is it is understood that be possible to modify the technical solutions described in the foregoing embodiments or right
Part of technical characteristic is equivalently replaced；These are modified or replaceed, and it does not separate the essence of the corresponding technical solution originally
Invent the spirit and scope of each embodiment technical solution.
Claims (10)
1. a kind of longitudinally controlled method of automatic Pilot characterized by comprising
S1 generates the virtual target of characterization path velocity and position attribution according to the expected path curvature information of this vehicle；
S2 identifies the real goal with speed and position attribution according to this vehicle sensory perceptual system；
S3, according to traffic scene, CAR SERVICE function and integration of user interaction functionality, by its feature be converted into several with speed and
The virtual target of position attribution；
S4 is filtered out from each virtual target and real goal in S1 and S3 and maximum to this vehicle safety effects is followed mesh
Mark；And
S5 plans that the expectation of this vehicle accelerates according to the speed and range information for following target relative to this vehicle filtered out in S4
Degree.
2. the longitudinally controlled method of automatic Pilot as described in claim 1, which is characterized in that in S1, virtual target is relative to this
The fore-and-aft distance dis of vehiclelonExpression formula are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal
Safe distance；The speed of the virtual target is the speed of this vehicle.
3. the longitudinally controlled method of automatic Pilot as described in claim 1, which is characterized in that in S3, virtual target includes following
It is one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows: dislon
=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is speed limit
Value；
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula
Are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target
Degree is user psychology desired speed or is defaulted as road speed limit；
User's active control vehicle stops corresponding virtual target, fore-and-aft distance dis of the virtual target relative to this vehiclelonWith
The speed of this vehicle is directly proportional；The speed of the virtual target is 0km/h；
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonIt is it relative to this vehicle
Fore-and-aft distance；The speed of the virtual target is 0km/h.
4. the longitudinally controlled method of automatic Pilot as described in claim 1, which is characterized in that in S4, filter out to this Che Anquan
Property influence maximum mesh calibration method to be followed to specifically include:
S41 calculates the weighing factor of each virtual target and real goal in S1 and S3, mesh according to following target selection model
Mark the expression formula of preference pattern are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle；
Lateral prediction distance for virtual target or real goal relative to this vehicle；
Impact factor for virtual target or real goal relative to the fore-and-aft distance of this vehicle；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle；
VrelSpeed for virtual target or real goal relative to this vehicle；
S42, the maximum virtual target of weighing factor Score or real goal being calculated via above-mentioned formula are to follow mesh
Mark.
5. the longitudinally controlled method of automatic Pilot according to any one of claims 1 to 4, which is characterized in that in S5, " expectation
The calculation formula of acceleration " is as follows:
In formula: atargetIt is expected deceleration；
VrelTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor；
TisFor speed term integration time constant；
TdsFor speed term derivative time constant；
KpdFor distance terms proportional control factor；
TidFor distance terms integration time constant；
TddFor distance terms derivative time constant.
6. a kind of longitudinally controlled device of automatic Pilot characterized by comprising
First virtual target generation module, is used for the expected path curvature information according to this vehicle, generate characterization path velocity and
The virtual target of position attribution；
Real goal generation module is used to identify the true mesh with speed and position attribution according to this vehicle sensory perceptual system
Mark；
Second virtual target generation module is used for according to traffic scene, CAR SERVICE function and integration of user interaction functionality, Jiang Qite
Sign is converted into several virtual targets with speed and position attribution；
Object filtering module is used to generate from the first virtual target generation module and the second virtual target generation module
In the real goal that each virtual target and the real goal generation module generate, filter out maximum to this vehicle safety effects
Follow target；
It is expected that acceleration planning module, is used to follow target relative to this vehicle according to what the object filtering module filtered out
Speed and range information plan the expectation acceleration of this vehicle.
7. the longitudinally controlled device of automatic Pilot as claimed in claim 6, which is characterized in that first virtual target generates mould
Fore-and-aft distance dis of the virtual target that block generates relative to this vehiclelonExpression formula are as follows: dislon=THW × v+dissafe, v expression
The speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed for the virtual target that the first virtual target generation module generates
Degree is the speed of this vehicle；
The virtual target that the second virtual target generation module generates includes below one or more:
The corresponding virtual target of road speed limit, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula are as follows: dislon
=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target is speed limit
Value；
The corresponding virtual target of user psychology desired speed, fore-and-aft distance dis of the virtual target relative to this vehiclelonExpression formula
Are as follows: dislon=THW × v+dissafe, v indicates the speed of this vehicle, dissafeIndicate longitudinal safe distance；The speed of the virtual target
Degree is user psychology desired speed or is defaulted as road speed limit；
User's active control vehicle stops corresponding virtual target, fore-and-aft distance dis of the virtual target relative to this vehiclelonWith
The speed of this vehicle is directly proportional；The speed of the virtual target is 0km/h；
The corresponding virtual target of stopping a train at a target point, fore-and-aft distance dis of the virtual target relative to this vehiclelonIt is it relative to this vehicle
Fore-and-aft distance；The speed of the virtual target is 0km/h.
8. the longitudinally controlled device of automatic Pilot as claimed in claim 6, which is characterized in that the object filtering module is specifically wrapped
It includes:
Weighing factor computing module is used to calculate the first virtual target generation module according to following target selection model
The real goal that each virtual target and the real goal generation module generated with the second virtual target generation module generates
Weighing factor, the expression formula of target selection model are as follows:
In formula: Score is the weighing factor of virtual target；
Impact factor for virtual target or real goal relative to the lateral distance of this vehicle；
Lateral prediction distance for virtual target or real goal relative to this vehicle；
Impact factor for virtual target or real goal relative to the fore-and-aft distance of this vehicle；
DislonFore-and-aft distance for virtual target or real goal relative to this vehicle；
FactorspeedSpeed impact factor for virtual target or real goal relative to this vehicle；
VrelSpeed for virtual target or real goal relative to this vehicle；
Target determination module is followed, the weighing factor Score for being used to for the weighing factor computing module being calculated is maximum
Virtual target or real goal as following target.
9. the longitudinally controlled device of automatic Pilot as claimed in claim 6, which is characterized in that the expectation acceleration planning module
" expectation acceleration " calculation formula it is as follows:
In formula: atargetIt is expected deceleration；
VrelTo follow speed of the target relative to this vehicle；
EDis is the actual range for following target and this workshop and the deviation of desired distance；
KpsFor speed term proportional control factor；
TisFor speed term integration time constant；
TdsFor speed term derivative time constant；
KpdFor distance terms proportional control factor；
TidFor distance terms integration time constant；
TddFor distance terms derivative time constant.
10. a kind of automatic driving vehicle, which is characterized in that vertical including the automatic Pilot as described in any one of claim 6 to 9
To control device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710828439.7A CN107719369B (en) | 2017-09-14 | 2017-09-14 | The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710828439.7A CN107719369B (en) | 2017-09-14 | 2017-09-14 | The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107719369A CN107719369A (en) | 2018-02-23 |
| CN107719369B true CN107719369B (en) | 2019-05-10 |
Family
ID=61204667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710828439.7A Active CN107719369B (en) | 2017-09-14 | 2017-09-14 | The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107719369B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108556845B (en) * | 2018-04-10 | 2020-07-10 | 清华大学 | Vehicle following system and method |
| CN108944921B (en) * | 2018-07-03 | 2020-11-20 | 驭势（上海）汽车科技有限公司 | Method and device for longitudinal control of vehicle |
| CN108958264B (en) * | 2018-08-03 | 2021-07-23 | 北京智行者科技有限公司 | Road traffic inspection method based on automatic driving technology and vehicle |
| CN108983787B (en) * | 2018-08-09 | 2021-09-10 | 北京智行者科技有限公司 | Road driving method |
| CN109532832B (en) * | 2018-12-08 | 2020-12-15 | 华东交通大学 | Longitudinal planning method in intelligent driving |
| CN109582023B (en) * | 2018-12-21 | 2019-10-11 | 费子偕 | A kind of novel manned tool and the control method for being applicable in it |
| CN111880521B (en) * | 2019-04-15 | 2022-06-14 | 比亚迪股份有限公司 | Vehicle control method and device, vehicle and electronic equipment |
| CN110320910B (en) * | 2019-07-01 | 2023-10-10 | 阿波罗智能技术(北京)有限公司 | Vehicle avoidance control method and device, electronic equipment and storage medium |
| CN110514224B (en) * | 2019-08-26 | 2021-04-02 | 中国人民解放军军事科学院国防科技创新研究院 | Method for evaluating local path planning performance of unmanned vehicle |
| CN110531771B (en) * | 2019-09-02 | 2022-08-16 | 广州小鹏汽车科技有限公司 | Speed planning method and device and vehicle |
| US11274936B2 (en) * | 2019-11-14 | 2022-03-15 | Nissan North America, Inc. | Safety-assured remote driving for autonomous vehicles |
| CN111367273A (en) * | 2019-12-31 | 2020-07-03 | 天嘉智能装备制造江苏股份有限公司 | Unmanned small-sized sweeping machine control system based on path tracking and control method thereof |
| CN111873998B (en) * | 2020-07-31 | 2021-07-06 | 重庆长安汽车股份有限公司 | Method for planning longitudinal acceleration of automatic driving vehicle |
| CN112193253B (en) * | 2020-10-23 | 2021-11-23 | 江苏大学 | Longitudinal control method for unmanned vehicle running on curve with variable curvature |
| CN113104034B (en) * | 2021-04-30 | 2022-05-20 | 东风汽车集团股份有限公司 | ACC self-adaptive cruise safety control method and device |
| CN113635918B (en) * | 2021-08-13 | 2022-11-25 | 中国汽车技术研究中心有限公司 | Automatic driving robot control system and method |
| CN113942505B (en) * | 2021-10-28 | 2023-11-03 | 长春一汽富晟集团有限公司 | Vehicle self-adaptive cruising algorithm |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2508464B (en) * | 2012-08-16 | 2015-03-11 | Jaguar Land Rover Ltd | Improvements in vehicle speed control |
| CN104742906B (en) * | 2013-12-26 | 2017-11-21 | 中国移动通信集团公司 | Realize the method and system of automatic Pilot |
| JP6350074B2 (en) * | 2014-07-30 | 2018-07-04 | アイシン・エィ・ダブリュ株式会社 | Vehicle driving support device, vehicle driving support method, and program |
| EP3156298B1 (en) * | 2015-10-13 | 2022-08-10 | Volvo Car Corporation | Driving aid arrangement, a vehicle and a method of controlling a longitudinal velocity of a vehicle |
| CN107284442B (en) * | 2017-05-15 | 2019-07-09 | 北京理工大学 | A kind of longitudinally controlled method of negotiation of bends for automatic driving vehicle |
-
2017
- 2017-09-14 CN CN201710828439.7A patent/CN107719369B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107719369A (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107719369B (en) | The longitudinally controlled method, apparatus of automatic Pilot and the automatic driving vehicle with it | |
| AU2022202150B2 (en) | Software validation for autonomous vehicles | |
| CN106338988B (en) | The control device of automatic driving vehicle | |
| US10606270B2 (en) | Controlling an autonomous vehicle using cost maps | |
| CN110386152B (en) | Human-computer interaction display control method and system based on L2-level intelligent piloting driving | |
| CN109969172A (en) | Control method for vehicle, equipment and computer storage medium | |
| US7487074B2 (en) | Road traffic simulation apparatus | |
| CN109345020A (en) | A kind of unsignalized intersection vehicle drive behavior prediction model under Complete Information | |
| CN110304074A (en) | A kind of hybrid type driving method based on stratification state machine | |
| KR20190030199A (en) | Supervision of vehicles | |
| CN108583578A (en) | The track decision-making technique based on multiobjective decision-making matrix for automatic driving vehicle | |
| CN109501799A (en) | A kind of dynamic path planning method under the conditions of car networking | |
| CN113291308A (en) | Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics | |
| CN107544518A (en) | The ACC/AEB systems and vehicle driven based on personification | |
| CN106062852A (en) | System for avoiding collision with multiple moving bodies | |
| CN103921719A (en) | Driver-interactive type commercial vehicle rollover warning method and system | |
| CN113212454B (en) | Method and device for adjusting running state of vehicle, computer equipment and storage medium | |
| CN208393354U (en) | Line operating condition automatic Pilot steering system is moved based on BP neural network and safe distance | |
| CN107985310A (en) | A kind of adaptive cruise method and system | |
| DE112016007501T5 (en) | CONTROL / CONTROL DEVICE AND CONTROL / CONTROL PROCEDURE | |
| CN109799821A (en) | A kind of automatic Pilot control method based on state machine | |
| Xiong et al. | Decision-making of lane change behavior based on RCS for automated vehicles in the real environment | |
| CN108045373A (en) | A kind of automatic Pilot longitudinal direction unified planning method and system | |
| CN109754626A (en) | Unmanned autonomous lane-change strategy | |
| CN112987711A (en) | Optimization method of automatic driving regulation algorithm and simulation testing device |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Building C-3, Northern Territory, Zhongguancun Dongsheng Science Park, 66 Xixiaokou Road, Haidian District, Beijing, 100176 Patentee after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 102208 Patentee before: Beijing Idriverplus Technology Co.,Ltd. |