CN110466495A - A kind of intelligence automatic vectorization drives execution system and control method - Google Patents
A kind of intelligence automatic vectorization drives execution system and control method Download PDFInfo
- Publication number
- CN110466495A CN110466495A CN201910823128.0A CN201910823128A CN110466495A CN 110466495 A CN110466495 A CN 110466495A CN 201910823128 A CN201910823128 A CN 201910823128A CN 110466495 A CN110466495 A CN 110466495A
- Authority
- CN
- China
- Prior art keywords
- instruction
- entire car
- car controller
- controller
- judging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 49
- 230000008859 change Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000013024 troubleshooting Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000002405 diagnostic procedure Methods 0.000 claims description 2
- 230000036632 reaction speed Effects 0.000 claims 1
- 238000003786 synthesis reaction Methods 0.000 claims 1
- 210000004556 brain Anatomy 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 230000003862 health status Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000035876 healing Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000037380 skin damage Effects 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
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/04—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/20—Conjoint control of vehicle sub-units of different type or different function including control of 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
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- 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
- B60W2710/08—Electric propulsion units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/20—Steering systems
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
- Vehicle Body Suspensions (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a kind of intelligent automatic vectorizations to drive execution system and gear-shifting control method, the system comprises: including actuator and controller, controller includes receiving module, for receiving the instruction of entire car controller, an instant vehicle target motion vector and an alternative target motion vector；Whether judgment module, the instruction for judging entire car controller are correct；Depth self-learning module independently selects to execute order according to the judging result of judgment module, using the countermeasure, Xiang Yunduan search plan or emergency being arranged in original program.The present invention contains the steering assembly other than power assembly, also changes control mode, gives the right for independently going to school and selecting to execute of execution level.
Description
Technical field
Power assembly system the present invention relates to automobile driving system, in intelligent driving, especially automatic Pilot technical field
System.
Background technique
Demand of the people to Vehicular automatic driving is more and more obvious, and the R&D work of automatic Pilot makes much progress, and is had certainly
The dynamic vehicle for driving L2 has listed.
Automated driving system can be divided into three parts: sensing layer, decision-making level and execution level.Sensing layer is dependent on a variety of
Sensor, comprising: camera, millimetre-wave radar, ultrasonic radar, laser radar, night vision be infrared, positioning system, inertia measurement
Unit, car networking etc., there are also driver's motivation identifications etc. in the case where manned.
Does decision-making level include control centre, and main task is that the information got according to sense part determines where court is walked it walks more
Fastly the problem of vector controlled is carried out to vehicle here it is one.Simple path and environment can be easy to make a policy, complicated
The considerations of path and environment need many aspects, it is more complicated.
Once decision-making level gives direction and speed, what is relied on is exactly the implementation capacity for the level that executes.If executed
The unreachable position of layer, then good sensor, then good decision are all of no avail, and the tragedy for even resulting in car crash occurs.
The instruction of driver is also executed by manually-operated vehicle now.But, driving direction is led to by driver completely
The angular dimension of rotation steering wheel is crossed to realize, and the throttle that travel speed is stepped on by driver completely is determined with brake depth
It is fixed.The size of turn direction and the speed of travel speed are substantially mutually independent, between each other without what relationship or
It says and this relationship is determined by driver oneself completely.
Automated driving system now is also all continued to use and executes system used in manual drive system, is i.e. other side respectively
It is controlled to speed.Actuator is a completely passive component.It mechanically receives the instruction of controller just as former
As the operation for mechanically executing driver.Disadvantage of this is that actuators itself to improve, and place one's entire reliance upon vehicle
Controller.Perhaps, some entire car controllers can be made very perfect, and problem is with regard to little, but if changing a kind of entire car controller and existing
Some actuators, problem may be just relatively more.As soon as changing an outside vehicle environment, problem may be more.For a face
To the actuator of the versatility of society, it should not exclusively be restricted by entire car controller ability and should there is the intelligence of own to go not
It is disconnected to improve oneself, protect oneself.Just as human body, each organ of people is essentially all to receive what brain controlled, but be not
Only equal brains exclusively control all organs.For example the limb motion and language of normal person is controlled by brain, but muscle skin
Self healing of self healing, bone, self formation, the digestion of food of antibody after skin damage are not issued clearly by brain
Instruction is to control.Heartbeat is also not issue an instruction to directly control by brain, but breathing is that can be controlled by brain can also
With the behavior not controlled by brain.People can briefly suppress and breathe, can also after brain suspend mode Self-breathing.When walking,
The movement of hand and foot can be with automatic synchronization, also referred to as subconsciousness.The execution level of automatic Pilot includes multiple components, between them
Automatic synchronization says that subconsciousness coordination is also critically important.But human body, other than brain, other organs do not have self-teaching
Function.According to Darwinian evolutionism, biology is all the rule for following random variation natural selection and reaching natural evolution, rather than
The result that Active Learning is evolved.Just enter the stage of Active Learning and Active Evolution to modern humans.The component of machine also should
Intelligence towards Active Learning, self promotion strides forward.Execution unit in autonomous driving vehicle also should towards Active Learning, self
The intelligence of raising strides forward.Machine part self promotion consciousness can organ more each than human body individual consciousness it is stronger.It is even super
Personal range out, and there is a human body to evolve into a team automatic driving vehicle.One human body only one brain, and one
A team can have many brains, these certain brains all obey a unified leader or follow unified rule.
In many of vehicle control system subsystem, they have individual controller, and the ability of these controllers is all
It is very big, this just as the numerous members in a team with clever head, how to bring into play they aggressive property, bring into play
Their effect, optimization their own system is significantly.So it is contemplated that the execution level of automatic Pilot
It is overall intelligent.
Summary of the invention
One technical problem to be solved by the embodiment of the invention is that: a kind of intelligent automatic vectorization driving execution system is provided
And control method, to solve problems of the prior art.
A kind of intelligence automatic vectorization driving execution system, it is characterised in that: including actuator and controller, controller includes
Receiving module, for receiving the instruction of entire car controller, command content is that an instant vehicle target motion vector and one are pre-
Standby target motion vectors；Whether judgment module, the instruction for judging entire car controller are correct；Depth self-learning module, according to
The judging result of judgment module independently selects to execute order, the countermeasure using being arranged in original program, Xiang Yunduan search plan
Or emergency；Actuator includes power assembly, provides vehicle onward impulse, and turn to assembly, changes the driving direction of vehicle.
Preferably, the judgment module includes the first judging unit, for judging whether entire car controller is illegally robbed
It holds；
Second judgment unit, for judging in the case where the first judging unit confirmation entire car controller is not kidnapped illegally
Whether entire car controller state is healthy；
Third judging unit, for the judgement execution in the case where second judgment unit confirmation entire car controller state is healthy
Whether the state of device is normal and optimised；
Comprehensive descision unit, comprehensive first judging unit, second judgment unit, the judging result of third judging unit are right
Whether the instruction of entire car controller is correctly judged.
Preferably, depth self-learning module includes interior study module, refer in comprehensive descision unit judges entire car controller
Selection executes order when enabling correct, in comprehensive descision unit judges entire car controller instruction errors from the operation data of itself
Information is collected, is counted, derived, concluded, summarized, it was therefore concluded that, then using the countermeasure being arranged in original program；It searches outside
Rope module, to cloud search plan or emergency when not having corresponding measure in original program.
A kind of intelligence automatic vectorization drives the control method of execution system, comprising:
A) controller receives the instruction of entire car controller, an instant vehicle target motion vector and an alternative target fortune
Dynamic vector, and the correctness of instruction is judged, judge whether entire car controller is illegally kidnapped, if by illegally kidnapping,
Then make abduction processing, determines that the instruction for false command, if do not kidnapped illegally, judges whether entire car controller state is good for
Health makees ill processing if unhealthy, determines the instruction for false command, if healthy, judges that the state of actuator is
It is no normal and optimised, if the state of actuator is abnormal or not optimised, make optimization processing, determines the instruction for mistake
Instruction, if actuator state is normal and optimised, determines the instruction for right instructions；
When b) determining the instruction for false command, controller refusal receives to instruct simultaneously using the correspondence being arranged in original program
Measure passes through web search scheme or seeks advice and take and accordingly arrange if not having corresponding rescue measure in original program
It applies, search plan includes entire car controller in the operating experience and troubleshooting correction countermeasure, other vehicles for search for actuator
Health status and it is successfully processed experience, abduction and the precedent information of kidnapping, required assistance including related suspection opinion is passed through related portion
Door or individual are further analyzed and confirm, are counted to the measure and result that finally use, analyze, upload to cloud；
C) instruction is determined for right instructions, and controller controls power assembly and turns to the instruction that assembly presses entire car controller
Content operation.
Preferably, the step of whether entire car controller is illegally kidnapped judged, including use original object and midway more
Change target and form doubt early period, is obtained a result by external challenges with solving.
Preferably, judging the whether normal and optimised step of actuator state, including according to actual vector in target
The difference of vector judges the implementation capacity of execution unit, whether normal and optimised answers actuator state.
Preferably, judge entire car controller state whether Jian Kang step, including judging decision according to target vector
Correctness.
Compared with prior art, the present invention has the advantage that
Implement vector intelligent control driving to execute；Implement intelligence learning of actively going to school in system.
Detailed description of the invention
Fig. 1 is the structural schematic diagram that the intelligent automatic vectorization of the present invention drives execution system；
Fig. 2 is the structural schematic diagram of depth self-learning module in the present invention；
Fig. 3 is the decision flow chart of judgment module in the present invention.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.
A kind of intelligence automatic vectorization driving execution system, it is characterised in that: including actuator and controller, controller includes
Receiving module, for receiving the instruction of entire car controller, command content is that an instant vehicle target motion vector and one are pre-
Standby target motion vectors；Whether judgment module, the instruction for judging entire car controller are correct；Depth self-learning module, according to
The judging result of judgment module independently selects to execute order, the countermeasure using being arranged in original program, Xiang Yunduan search plan
Or emergency；Actuator includes power assembly, provides vehicle onward impulse, and turn to assembly, changes the driving direction of vehicle.
Preferably, the judgment module includes the first judging unit, for judging whether entire car controller is illegally robbed
It holds；
Second judgment unit, for judging in the case where the first judging unit confirmation entire car controller is not kidnapped illegally
Whether entire car controller state is healthy；
Third judging unit, for the judgement execution in the case where second judgment unit confirmation entire car controller state is healthy
Whether the state of device is normal and optimised；
Comprehensive descision unit, comprehensive first judging unit, second judgment unit, the judging result of third judging unit are right
Whether the instruction of entire car controller is correctly judged.
Preferably, depth self-learning module includes interior study module, refer in comprehensive descision unit judges entire car controller
Selection executes order when enabling correct, in comprehensive descision unit judges entire car controller instruction errors from the operation data of itself
Information is collected, is counted, derived, concluded, summarized, it was therefore concluded that, then using the countermeasure being arranged in original program；It searches outside
Rope module, to cloud search plan or emergency when not having corresponding measure in original program.
A kind of intelligence automatic vectorization drives the control method of execution system, comprising:
A) controller receives the instruction of entire car controller, an instant vehicle target motion vector and an alternative target fortune
Dynamic vector, and the correctness of instruction is judged, judge whether entire car controller is illegally kidnapped, if by illegally kidnapping,
Then make abduction processing, determines that the instruction for false command, if do not kidnapped illegally, judges whether entire car controller state is good for
Health makees ill processing if unhealthy, determines the instruction for false command, if healthy, judges that the state of actuator is
It is no normal and optimised, if the state of actuator is abnormal or not optimised, make optimization processing, determines the instruction for mistake
Instruction, if actuator state is normal and optimised, determines the instruction for right instructions；
When b) determining the instruction for false command, controller refusal receives to instruct simultaneously using the correspondence being arranged in original program
Measure passes through web search scheme or seeks advice and take and accordingly arrange if not having corresponding rescue measure in original program
It applies, search plan includes entire car controller in the operating experience and troubleshooting correction countermeasure, other vehicles for search for actuator
Health status and it is successfully processed experience, abduction and the precedent information of kidnapping, required assistance including related suspection opinion is passed through related portion
Door or individual are further analyzed and confirm, are counted to the measure and result that finally use, analyze, upload to cloud；
C) instruction is determined for right instructions, and controller controls power assembly and turns to the instruction that assembly presses entire car controller
Content operation.
Preferably, the step of whether entire car controller is illegally kidnapped judged, including use original object and midway more
Change target and form doubt early period, is obtained a result by external challenges with solving.
Preferably, judging the whether normal and optimised step of actuator state, including according to actual vector in target
The difference of vector judges the implementation capacity of execution unit, whether normal and optimised answers actuator state.
Preferably, judge entire car controller state whether Jian Kang step, including judging decision according to target vector
Correctness.
Implement vector intelligent control driving to execute；Implement intelligence learning of actively going to school in system.
The instruction that entire car controller provides is an instant vehicle target motion vector and an alternative target motion vector.
Each vector includes four scalars: x, y, z coordinate and amplitude, there is fixed relationship between amplitude and other scalars.X, y, z are sat
Mark is all using the real-time origin of vehicle and coordinate as reference point.X, y, z can also be replaced by 2 angles: vehicle body and advance target side
To angle；The angle of road plane and horizontal plane.
Vehicle can easily by control diverter so that vehicle body is changed direction on road plane, even if vehicle body direction and
The angle of target direction of advance is zero, i.e. direction is consistent.But vehicle cannot change the angle between road plane and horizontal plane, because
It can not be detached from ground for vehicle, ground can not be pierced, so the angle of road plane and horizontal plane is not control amount but defeated
Enter amount it is expected that actuator can preferably complete control to the angle of vehicle body and advance target direction and comfort etc.
Control.
Direction determines that vehicle body need to change the corner dimension of driving direction, the amplitude in motion vector immediately in motion vector
For determining the size of instant power source power output.Moving target vector instruction derives from entire car controller, the task one of actuator
As be exactly loyal completing entire car controller and giving for task.One there is the actuator of intelligence to need in the correct judgement to instruction
Executing two aspects with high quality has intelligence performance outstanding rather than a low side executor without IQ.
The present invention is additionally arranged the depth self-learning module of search, interior study outside one in controller.Outer search is actively
Search data is learnt, and its object is to obtain three aspect contents according to demand:
1. countermeasure is corrected in the operating experience of actuator and troubleshooting；
2. the health status of entire car controller and being successfully processed experience on other vehicles；
3. the precedent information kidnapped and kidnapped.
The intervention of artificial intelligence can assist data needed for quickly finding from numerous data.
Depth self study is to be counted from the improper phenomenon of operational data collection of itself, derives, concludes, summarizing
Conclusion out, then using the countermeasure being arranged in original program.If there is no corresponding rescue measure in original program, just
As already mentioned it is possible to actively to cloud search plan or seek advice.Certainly originally confidential to unite to the measure finally used and result
Cloud is analyzed and uploaded to meter.This is one of emphasis of the invention: " looking back at ", to summarize the real of used measure
Whether effect is good, if it find that existing treatment measures are bad, should just record the simultaneously later treatment measures of automatic straightening.Specifically
Embodiment be whether relationship between certain three scalar of x, y, z in special circumstances best whether its change procedure best it learns
The depth of habit is vector line-of-sight course: 1. gain new knowledge by reviewing old；2. vector value optimizes result；3. the optimization knot of vector changing value
Fruit.For example, on snowfield road surface, vector y is little in modulus change but absolute value is big, then will have to the change rate between x and y
Bigger limitation.The control of the control and wheel corner that implement to vehicle power source power output will restrain in a certain range.
Otherwise vehicle tumble or it is out of control just unavoidable.
The correctness of instruction will be judged.On the one hand consider be identification entire car controller whether make mistakes with it is not normal,
On the other hand it is whether identification controller is kidnapped by illegal kidnap.In both cases, this actuator will be refused to receive instruction
It breaks through or requires assistance with implementing.It requires assistance including that will be further analyzed and confirm by relevant department or individual in relation to suspection opinion
And take corresponding measure.Certainly both of these case, which must be accurately detected, can just take these measures, otherwise be exactly to disobey vehicle
The order of controller, device consequence are hardly imaginable.Gateway or entire car controller are answered on the general vehicle with Function for Automatic Pilot
There is the mechanism of anti-hijacking, but also have a possibility that careless omission, in addition it is total not much to be also required to power on the vehicle of Function for Automatic Pilot
At.The anti-hijacking function of power assembly is just leaned in anti-abduction on the vehicle of not Function for Automatic Pilot entirely.So deep learning
Module will also have certain range while having depth.Range is embodied in the three elements conclusion of the module:
1. entire car controller is illegally kidnapped
2. whether the entire car controller of vehicle healthy
3. whether power assembly state normal and optimised
Intelligence and deep learning are needed to the judgement of this three elements.If any one conclusion be it is negative,
It will take appropriate measures and be remedied.
At first view, above-mentioned vector line-of-sight course is the core of third element, but actually to the first, second element
There is identical effect, only the starting point not instead of motion vector, state.For example how to judge entire car controller whether halfway
Illegally kidnapped the present invention using original object and midway change target formed doubt early period, by external challenges and solve come
Reach.The present invention is used to any new destination, new driving style (motion vector changing rule), new driver, new
Control instruction style come increase to abduction locality suspect.External suspection is obtained from network.The shortcomings that this law is cannot to differentiate
The case where being kidnaped at the first time, needs time integral.
How to judge whether the entire car controller of this vehicle is healthy, the method that usual system uses redundancy adds controller
It is compared and whether consistent obtains.If inconsistent, wherein it is problematic for having one, but who can not determine and study carefully
Unexpectedly which controller is out of joint.In fact it is possible that two controllers are all out of joint.Redundancy increases the complexity of system
With cost and cannot really solve the problems, such as.The present invention does not use redundant fashion and uses and check oneself outer report mode.Check oneself is to pass through
Deep learning grasps three aspects such as program runtime, several emphasis causalities, output target vector rule and is counted, returned
It receives for verifying, then periodically externally orderly report.When the external world can not receive the information that receive, then entire car controller
It is exactly unsound.Then, intelligent power total performance eliminates the reliance on the instruction of the controller and enters troubleshooting mode.It grasps
The work of this regular three aspect of program runtime, several emphasis causalities, output target vector is all completed by software.It is exactly
Say, the target vector instruction needed for existing traditional control software executes in intelligent power assembly controller, there are also it is a set of from
Learning system is constantly being summarized from the inside and outside two parts of system, then has a set of supervision software systems always to concern
Event be compared, whether control and decision systems abnormal and feedback modification operation method carries out system in some cases
Self-perfection.
Do you how to judge whether this power assembly state normal and optimised the present invention uses target tracking accuracy diagnostic method.
In order to preferably differentiate the actuator function of power assembly: power function and turning function.Wherein target it will be divided into first object
With the second target.Whether first object refers to target vector tracking velocity, for judging the implementation capacity of execution decision, i.e., enough dynamic
Power, the second target is actual vector in the difference of target vector, for judging the control precision of execution unit.Only these two aspects
Correctly, so that it may judge whether this power assembly state is normal and optimised.
Here so-called deep learning is reviewed and is verified with the pervious judgement of determination after going back important affair after judging
It is whether correct, if pervious be out of one's reckoning, to adjust in later judgement, mistake is not allowed to repeat.Have just
True judgement, so that it may design and implement counter-measure.
Generally there are many sensors and controller on vehicle, once other sensors or certain subsystem are broken, frequently results in
Whole system failure.But after power assembly has certain intelligence, even if other systems are broken, power assembly still can be with
Completion groundwork: service point is gone home or is arrived in safety and possible low speed operation.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention,
Although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art, still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features,
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention
Within protection scope.
Claims (8)
1. a kind of intelligence automatic vectorization drives execution system, it is characterised in that: including actuator and controller, controller includes connecing
Module is received, for receiving the instruction of entire car controller, the content of instruction is that an instant vehicle target motion vector and one are pre-
Standby target motion vectors；Whether judgment module, the instruction for judging entire car controller are correct；Depth self-learning module, according to
The judging result of judgment module independently selects to execute order, the countermeasure using being arranged in original program, Xiang Yunduan search plan
Or emergency；Actuator includes power assembly, provides vehicle onward impulse；Assembly is turned to, the driving direction of vehicle is changed.
2. a kind of intelligent automatic vectorization according to claim 1 drives execution system, it is characterised in that: the judgment module
Including the first judging unit, for judging whether entire car controller is illegally kidnapped；
Second judgment unit, for judging vehicle in the case where the first judging unit confirmation entire car controller is not kidnapped illegally
Whether controller state is healthy；
Third judging unit, for judging actuator in the case where second judgment unit confirmation entire car controller state is healthy
Whether state is normal and optimised；
Comprehensive descision unit, comprehensive first judging unit, second judgment unit, the judging result of third judging unit, to vehicle
Whether the instruction of controller is correctly judged.
3. a kind of intelligent automatic vectorization according to claim 2 drives execution system, it is characterised in that: depth self study mould
Block includes interior study module, and when the instruction of comprehensive descision unit judges entire car controller is correct, selection executes order, is sentenced in synthesis
Information is collected from the operation data of itself when disconnected unit judges entire car controller instruction errors, counted, derived, concluded,
It summarizes, it was therefore concluded that, then using the countermeasure being arranged in original program；Outer search module does not correspond in original program
Measure when to cloud search plan or emergency.
4. a kind of intelligent automatic vectorization according to claim 3 drives execution system, it is characterised in that: depth self study mould
Whether the real effect of measure used by block is summarized is good, if it find that existing treatment measures are bad, should just record simultaneously certainly
The later treatment measures of dynamic correction, including whether most to control the relationship between three components of x, y, z in vector in special circumstances
It is good, whether its change procedure best, depth self-learning module study depth be vector line-of-sight course: 1) gain new knowledge by reviewing old；2)
Vector value optimizes result；3) the optimization result of vector changing value.
5. the control method that a kind of intelligence automatic vectorization drives execution system, it is characterised in that: include:
A) controller receives the instruction of entire car controller, an instant vehicle target motion vector and an alternative target movement arrow
Amount, and the correctness of instruction is judged, the first judging unit judges whether entire car controller is illegally kidnapped, if non-
Method is kidnapped, then makees abduction processing, determine the instruction for false command, if do not kidnapped illegally, second judgment unit judges whole
Whether vehicle controller state is healthy, if unhealthy, makees ill processing, determines the instruction for false command, if healthy,
Three judging units judge whether the state of actuator is normal and optimised, if the state of actuator is abnormal or not optimised,
Then make optimization processing, but do not determine the instruction for false command, if actuator state is normal and optimised, determines that the instruction is
Right instructions；
When b) determining the instruction for false command, controller refusal, which receives to instruct, is simultaneously arranged using the correspondence being arranged in original program
It applies, if there is no corresponding rescue measure in original program, by web search scheme or seeks advice and take corresponding measure,
Search plan includes the health of entire car controller in the operating experience and troubleshooting correction countermeasure, other vehicles for search for actuator
Situation and be successfully processed experience, abduction and the precedent information of kidnapping, require assistance including by related suspection opinion by relevant department or
Individual is further analyzed and confirms, is counted to the measure and result that finally use, analyzes, uploads to cloud；
C) instruction is determined for right instructions, and controller controls power assembly and turns to the command content that assembly presses entire car controller
Operation.
6. the control method that a kind of intelligent automatic vectorization according to claim 4 drives execution system, it is characterised in that: sentence
The step of whether disconnected entire car controller is illegally kidnapped, including doubt early period is formed using original object and midway change target,
It is obtained a result by external challenges with solving.
7. the control method that a kind of intelligent automatic vectorization according to claim 4 drives execution system, it is characterised in that: sentence
Disconnected entire car controller state whether Jian Kang step, including depth self-learning module learns to program runtime, emphasis cause and effect
Three aspects such as relationship, output target vector rule are counted, are concluded, being verified, then periodically externally orderly report, when outer
When boundary can not receive the information that receive, then entire car controller is exactly unsound.
8. the control method that a kind of intelligent automatic vectorization according to claim 4 drives execution system, it is characterised in that: sentence
Whether normal and optimised step wherein target will be divided into first using target tracking accuracy diagnostic method to disconnected actuator state
Whether target and the second target, first object refer to target vector tracking velocity, for judging the implementation capacity of execution decision, i.e., enough
Power, the second target is the difference and reaction speed of actual vector and target vector, for judging the control precision of execution unit,
These two aspects correctness, so that it may judge whether this power assembly state is normal and optimised.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823128.0A CN110466495B (en) | 2019-09-02 | 2019-09-02 | Intelligent automatic vector driving execution system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823128.0A CN110466495B (en) | 2019-09-02 | 2019-09-02 | Intelligent automatic vector driving execution system and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110466495A true CN110466495A (en) | 2019-11-19 |
| CN110466495B CN110466495B (en) | 2024-04-09 |
Family
ID=68514708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910823128.0A Active CN110466495B (en) | 2019-09-02 | 2019-09-02 | Intelligent automatic vector driving execution system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110466495B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111605565A (en) * | 2020-05-08 | 2020-09-01 | 昆山小眼探索信息科技有限公司 | Automatic driving behavior decision method based on deep reinforcement learning |
Citations (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130005529A1 (en) * | 2009-12-04 | 2013-01-03 | Hong Chen | Hybrid electric drive unit, hybrid drive system and control method thereof |
| CN103359123A (en) * | 2013-07-04 | 2013-10-23 | 陈根 | Intelligent vehicle speed control and management system and implementing method thereof |
| KR20140128090A (en) * | 2013-04-26 | 2014-11-05 | 주식회사 만도 | Fault sensing system of electric control device for vehicle and fault sensing method thereof |
| US20140350789A1 (en) * | 2011-07-04 | 2014-11-27 | Jaguar Land Rover Limited | Vehicle control system and method for controlling a vehicle |
| CN104627180A (en) * | 2014-12-19 | 2015-05-20 | 北京新能源汽车股份有限公司 | Semi-active cruise control system and method |
| CN104890526A (en) * | 2014-03-05 | 2015-09-09 | 福特全球技术公司 | Vehicle system and method |
| US20150355637A1 (en) * | 2014-06-10 | 2015-12-10 | Magtec Products, Inc. | Remote speed management system for vehicles |
| CN105292052A (en) * | 2015-11-12 | 2016-02-03 | 福州大学 | Automatic monitoring and alarming system for vehicle traffic safety |
| CN205113247U (en) * | 2015-11-12 | 2016-03-30 | 福州大学 | Automatic control of vehicle driving safety and alarm system |
| US20160167653A1 (en) * | 2014-12-15 | 2016-06-16 | Polaris Industries, Inc. | Autonomous ready vehicle |
| CN105730448A (en) * | 2016-02-19 | 2016-07-06 | 广州橙行智动汽车科技有限公司 | Intelligent switching method and device for automatic crawling and automatic parking of vehicle |
| US20160325725A1 (en) * | 2014-01-30 | 2016-11-10 | Byd Company Limited | Method for controlling engine unit in vehicle and vehicle |
| WO2016186383A1 (en) * | 2015-05-15 | 2016-11-24 | 주식회사 한글과컴퓨터 | Artificial intelligence (ai) unmanned smart car and method of operating same |
| CN106228755A (en) * | 2016-08-12 | 2016-12-14 | 深圳市元征科技股份有限公司 | Fatigue driving method for early warning and cloud server |
| CN106218553A (en) * | 2016-08-03 | 2016-12-14 | 北京新能源汽车股份有限公司 | Accelerator pedal sensor minimum voltage learning method, device and entire car controller |
| CN106240493A (en) * | 2016-07-21 | 2016-12-21 | 安徽师范大学 | Electric automobile wire-controlled apparatus based on CAN |
| US20170057506A1 (en) * | 2014-02-19 | 2017-03-02 | Jaguar Land Rover Limited | Control system and method |
| CN106515706A (en) * | 2016-09-30 | 2017-03-22 | 广州汽车集团股份有限公司 | Vehicle safety driving control method and vehicle safety driving control system |
| CN106774291A (en) * | 2016-12-26 | 2017-05-31 | 清华大学苏州汽车研究院（吴江） | A kind of electric-control system of automatic Pilot electric automobile |
| CN106878130A (en) * | 2017-03-14 | 2017-06-20 | 成都雅骏新能源汽车科技股份有限公司 | A kind of electric automobile CAN network method for detecting abnormality and device |
| CN107031600A (en) * | 2016-10-19 | 2017-08-11 | 东风汽车公司 | Automated driving system based on highway |
| CN107117162A (en) * | 2016-02-25 | 2017-09-01 | 福特全球技术公司 | Autonomous vehicle control conversion |
| US20170270798A1 (en) * | 2016-03-17 | 2017-09-21 | Hitachi, Ltd. | Auto driving control system |
| CN107264534A (en) * | 2017-05-23 | 2017-10-20 | 北京理工大学 | Intelligent driving control system and method, vehicle based on driver experience's model |
| US20170313314A1 (en) * | 2016-04-27 | 2017-11-02 | Honda Motor Co., Ltd. | Vehicle control system, vehicle control method, and vehicle control program |
| CN107415959A (en) * | 2016-05-17 | 2017-12-01 | 本田技研工业株式会社 | Vehicle control system, control method for vehicle and wagon control program |
| CN107640124A (en) * | 2017-07-28 | 2018-01-30 | 北京长城华冠汽车科技股份有限公司 | Onboard safety systems |
| CN107640159A (en) * | 2017-08-04 | 2018-01-30 | 吉利汽车研究院（宁波）有限公司 | A kind of automatic Pilot man-machine interactive system and method |
| CN107797534A (en) * | 2017-09-30 | 2018-03-13 | 安徽江淮汽车集团股份有限公司 | A kind of pure electronic automated driving system |
| CN107908186A (en) * | 2017-11-07 | 2018-04-13 | 驭势科技（北京）有限公司 | For the method and system for controlling automatic driving vehicle to run |
| KR20180103473A (en) * | 2017-03-10 | 2018-09-19 | 한국오므론전장주식회사 | System and Method for Controlling Autonomous Driving of Vehicle |
| US20180297585A1 (en) * | 2015-10-26 | 2018-10-18 | Byd Company Limited | Electric vehicle and active safety control system and method thereof |
| CN108881174A (en) * | 2018-05-25 | 2018-11-23 | 北京长城华冠汽车科技股份有限公司 | A kind of method and apparatus for taking precautions against new-energy automobile local attack |
| CN109291934A (en) * | 2017-07-24 | 2019-02-01 | 长城汽车股份有限公司 | Self-learning method, system and the vehicle of accelerator pedal minimum position |
| CN109324537A (en) * | 2018-08-13 | 2019-02-12 | 北京长城华冠汽车科技股份有限公司 | A kind of control system and control method of man-machine common operating and controlling vehicle |
| CN109460042A (en) * | 2018-12-29 | 2019-03-12 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot control method and system |
| CN109591733A (en) * | 2019-01-24 | 2019-04-09 | 北京长城华冠汽车科技股份有限公司 | Security system, control method and the vehicle of vehicle |
| CN109688135A (en) * | 2018-12-27 | 2019-04-26 | 东软集团股份有限公司 | Data transmission method, Vehicle Controller and the readable storage medium storing program for executing of Vehicle Controller |
| CN109969192A (en) * | 2017-12-28 | 2019-07-05 | 郑州宇通客车股份有限公司 | A kind of vehicle and automatic driving control system |
-
2019
- 2019-09-02 CN CN201910823128.0A patent/CN110466495B/en active Active
Patent Citations (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130005529A1 (en) * | 2009-12-04 | 2013-01-03 | Hong Chen | Hybrid electric drive unit, hybrid drive system and control method thereof |
| US20140350789A1 (en) * | 2011-07-04 | 2014-11-27 | Jaguar Land Rover Limited | Vehicle control system and method for controlling a vehicle |
| KR20140128090A (en) * | 2013-04-26 | 2014-11-05 | 주식회사 만도 | Fault sensing system of electric control device for vehicle and fault sensing method thereof |
| CN103359123A (en) * | 2013-07-04 | 2013-10-23 | 陈根 | Intelligent vehicle speed control and management system and implementing method thereof |
| US20160325725A1 (en) * | 2014-01-30 | 2016-11-10 | Byd Company Limited | Method for controlling engine unit in vehicle and vehicle |
| US20170057506A1 (en) * | 2014-02-19 | 2017-03-02 | Jaguar Land Rover Limited | Control system and method |
| CN104890526A (en) * | 2014-03-05 | 2015-09-09 | 福特全球技术公司 | Vehicle system and method |
| US20150355637A1 (en) * | 2014-06-10 | 2015-12-10 | Magtec Products, Inc. | Remote speed management system for vehicles |
| US20160167653A1 (en) * | 2014-12-15 | 2016-06-16 | Polaris Industries, Inc. | Autonomous ready vehicle |
| CN104627180A (en) * | 2014-12-19 | 2015-05-20 | 北京新能源汽车股份有限公司 | Semi-active cruise control system and method |
| WO2016186383A1 (en) * | 2015-05-15 | 2016-11-24 | 주식회사 한글과컴퓨터 | Artificial intelligence (ai) unmanned smart car and method of operating same |
| US20180297585A1 (en) * | 2015-10-26 | 2018-10-18 | Byd Company Limited | Electric vehicle and active safety control system and method thereof |
| CN105292052A (en) * | 2015-11-12 | 2016-02-03 | 福州大学 | Automatic monitoring and alarming system for vehicle traffic safety |
| CN205113247U (en) * | 2015-11-12 | 2016-03-30 | 福州大学 | Automatic control of vehicle driving safety and alarm system |
| CN105730448A (en) * | 2016-02-19 | 2016-07-06 | 广州橙行智动汽车科技有限公司 | Intelligent switching method and device for automatic crawling and automatic parking of vehicle |
| CN107117162A (en) * | 2016-02-25 | 2017-09-01 | 福特全球技术公司 | Autonomous vehicle control conversion |
| US20170270798A1 (en) * | 2016-03-17 | 2017-09-21 | Hitachi, Ltd. | Auto driving control system |
| US20170313314A1 (en) * | 2016-04-27 | 2017-11-02 | Honda Motor Co., Ltd. | Vehicle control system, vehicle control method, and vehicle control program |
| CN107415959A (en) * | 2016-05-17 | 2017-12-01 | 本田技研工业株式会社 | Vehicle control system, control method for vehicle and wagon control program |
| CN106240493A (en) * | 2016-07-21 | 2016-12-21 | 安徽师范大学 | Electric automobile wire-controlled apparatus based on CAN |
| CN106218553A (en) * | 2016-08-03 | 2016-12-14 | 北京新能源汽车股份有限公司 | Accelerator pedal sensor minimum voltage learning method, device and entire car controller |
| CN106228755A (en) * | 2016-08-12 | 2016-12-14 | 深圳市元征科技股份有限公司 | Fatigue driving method for early warning and cloud server |
| CN106515706A (en) * | 2016-09-30 | 2017-03-22 | 广州汽车集团股份有限公司 | Vehicle safety driving control method and vehicle safety driving control system |
| CN107031600A (en) * | 2016-10-19 | 2017-08-11 | 东风汽车公司 | Automated driving system based on highway |
| CN106774291A (en) * | 2016-12-26 | 2017-05-31 | 清华大学苏州汽车研究院（吴江） | A kind of electric-control system of automatic Pilot electric automobile |
| KR20180103473A (en) * | 2017-03-10 | 2018-09-19 | 한국오므론전장주식회사 | System and Method for Controlling Autonomous Driving of Vehicle |
| CN106878130A (en) * | 2017-03-14 | 2017-06-20 | 成都雅骏新能源汽车科技股份有限公司 | A kind of electric automobile CAN network method for detecting abnormality and device |
| CN107264534A (en) * | 2017-05-23 | 2017-10-20 | 北京理工大学 | Intelligent driving control system and method, vehicle based on driver experience's model |
| CN109291934A (en) * | 2017-07-24 | 2019-02-01 | 长城汽车股份有限公司 | Self-learning method, system and the vehicle of accelerator pedal minimum position |
| CN107640124A (en) * | 2017-07-28 | 2018-01-30 | 北京长城华冠汽车科技股份有限公司 | Onboard safety systems |
| CN107640159A (en) * | 2017-08-04 | 2018-01-30 | 吉利汽车研究院（宁波）有限公司 | A kind of automatic Pilot man-machine interactive system and method |
| CN107797534A (en) * | 2017-09-30 | 2018-03-13 | 安徽江淮汽车集团股份有限公司 | A kind of pure electronic automated driving system |
| CN107908186A (en) * | 2017-11-07 | 2018-04-13 | 驭势科技（北京）有限公司 | For the method and system for controlling automatic driving vehicle to run |
| CN109969192A (en) * | 2017-12-28 | 2019-07-05 | 郑州宇通客车股份有限公司 | A kind of vehicle and automatic driving control system |
| CN108881174A (en) * | 2018-05-25 | 2018-11-23 | 北京长城华冠汽车科技股份有限公司 | A kind of method and apparatus for taking precautions against new-energy automobile local attack |
| CN109324537A (en) * | 2018-08-13 | 2019-02-12 | 北京长城华冠汽车科技股份有限公司 | A kind of control system and control method of man-machine common operating and controlling vehicle |
| CN109688135A (en) * | 2018-12-27 | 2019-04-26 | 东软集团股份有限公司 | Data transmission method, Vehicle Controller and the readable storage medium storing program for executing of Vehicle Controller |
| CN109460042A (en) * | 2018-12-29 | 2019-03-12 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot control method and system |
| CN109591733A (en) * | 2019-01-24 | 2019-04-09 | 北京长城华冠汽车科技股份有限公司 | Security system, control method and the vehicle of vehicle |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111605565A (en) * | 2020-05-08 | 2020-09-01 | 昆山小眼探索信息科技有限公司 | Automatic driving behavior decision method based on deep reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110466495B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200331495A1 (en) | System for steering an autonomous vehicle | |
| US11150663B2 (en) | Detection of hazardous driving using machine learning | |
| JP7361775B2 (en) | Personal driving style learning for autonomous driving | |
| JP6712088B2 (en) | Method, system and non-transitory computer readable storage medium for controlling a vehicle | |
| US20180052453A1 (en) | Fault-tolerant method and device for controlling an autonomous technical system through diversified trajectory planning | |
| US9539999B2 (en) | Vehicle operator monitoring and operations adjustments | |
| Shia et al. | Semiautonomous vehicular control using driver modeling | |
| US10571920B2 (en) | Fault-tolerant method and device for controlling an autonomous technical system based on a consolidated model of the environment | |
| ES2302179T3 (en) | DEVICE DETECTION DEVICE OF A VEHICLE CONTROL SYSTEM. | |
| US20170080950A1 (en) | Method and device for operating a vehicle | |
| US20180267549A1 (en) | Error procedure for controlling an autonomous controlled object | |
| KR101155565B1 (en) | Method and system for providing vehicle control using of network | |
| CN108776481A (en) | A kind of parallel driving control method | |
| US20210237763A1 (en) | Operating method for an autonomously operatable device, and an autonomously operatable device | |
| CN113954069B (en) | Mechanical arm active fault-tolerant control method based on deep reinforcement learning | |
| WO2018089024A1 (en) | Autonomous vehicle control by comparative transition prediction | |
| Pellkofer et al. | EMS-Vision: Gaze control in autonomous vehicles | |
| CN110466495A (en) | A kind of intelligence automatic vectorization drives execution system and control method | |
| Grieser et al. | Assuring the safety of end-to-end learning-based autonomous driving through runtime monitoring | |
| CN111806451A (en) | Method and control device for detecting driver fatigue for a driver assistance system of a vehicle | |
| CN110770107B (en) | Method and device for evaluating the fatigue of an occupant of a vehicle | |
| US9797726B2 (en) | Reduced-order fail-safe IMU system for active safety application | |
| JP2019104486A (en) | Method and system for determining rack force, operation assisting method for work device, operation assisting device and work device | |
| CN211969415U (en) | Intelligent automatic vector driving execution system | |
| CN115605925A (en) | Method for determining the value of a variable of a controller |
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 |