CN102609599A - Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents - Google Patents
Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents Download PDFInfo
- Publication number
- CN102609599A CN102609599A CN2012101049675A CN201210104967A CN102609599A CN 102609599 A CN102609599 A CN 102609599A CN 2012101049675 A CN2012101049675 A CN 2012101049675A CN 201210104967 A CN201210104967 A CN 201210104967A CN 102609599 A CN102609599 A CN 102609599A
- Authority
- CN
- China
- Prior art keywords
- operator
- state
- expression
- rule
- memory
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to road traffic safety and design and aims at providing an ideal method for designing road alignment and transverse clear distance. For achieving the purpose, the technical scheme is that the method for designing the emulational underground road alignment and the transverse clear distance based on multiple intelligent agents adopts an SOAR cognitive framework to model driver intelligent agents driving in underground roads and comprises working memory, long-term memory, a procedural operator selecting method and a learning mechanism sub-module. The method for designing emulational underground road alignment and transverse clear distance based on the multiple intelligent agents is mainly applied to the design of the road alignment and the transverse clear distance.
Description
Technical field
The present invention relates to traffic safety and design, specifically relate to based on the linear and horizontal clear distance method for designing of the road tunnel of multiple agent emulation.
Background technology
Reality shows; Road tunnel is owing to its closure and hide the limitation in space; The occurrence frequency of traffic safety accident is several times of Ordinary Rd; The order of severity is very high and very easily cause the generation of follow-up accident, and the road tunnel traffic engineering design that several aspects such as people, car, road and environment are comprehensively considered, is considered to one of important measures that solve highway road tunnel traffic safety problem.In various means and method that the road tunnel traffic engineering relates to; Road tunnel optimal design linear and horizontal clear distance can help the driver to make more effective driving behavior decision-making; Reducing and drive anxiety and pressure, is one of means that really can guarantee road tunnel traffic safety, the raising traffic capacity.
Nederlandse Centrale Organisatie Voor Toegepast-natuurwetenschappelijk Onderzoek (TNO) thinks that the particular design in tunnel comprises the length in tunnel, type, width, and number, curvature and the fluctuation etc. of tunnel route curve affect driver's the behavior and the subjective sense of security to a great extent.But these researchs all are the research to vcehicular tunnel, the research of underground road are mainly concentrated on the qualitative analysis etc. of design, gateway speed change lane length and the traffic safety of transversal section, and less driving behavior to the city road tunnel is studied.
Summary of the invention
The present invention is intended to solve the deficiency that overcomes prior art, provides a kind of comparatively ideal road tunnel linear and horizontal clear distance method for designing.For achieving the above object; The technical scheme that the present invention takes is; Based on the linear and horizontal clear distance method for designing of the road tunnel of multiple agent emulation; Adopt the SOAR cognitive frame that the intelligence of the driver in underground road travel body is carried out modeling, comprise intelligent body running memory, long-term memory, procedural operator system of selection and study mechanism submodule;
SOAR cognitive frame working memory comprises the multidate information all about the world and internal reasoning of SOAR intelligence body; It comprises perception information; Intermediate computations, the state of classification and relevant operator and target etc., all reasonings of intelligent body are all carried out in working memory with decision-making;
SOAR cognitive frame long-term memory characterizes with production rule through the procedural memory of road tunnel driving behavior; At first; " if " part with each rule removes to mate the element in the working memory; If " if " of rule part is mated with the working memory element fully, this rule will be triggered, and arrives the information of kinematic system or produces the suggestion that changes current state through sending one then; Cause that " then " part triggers, promptly any and current goal, state and operator matching rules can change current target and state;
The program mode operator is selected: through adopting the numerical value preference in the SOAR cognitive frame of road tunnel; Every rule in the long-term memory rule base comprises that matching condition and matching condition satisfy the operator that can advise down; And the numerical value preference value of advising this operator under this condition; New regulation of every interpolation need be judged the initial value preference size of operator in this rule, and in decision process, the size of this value is upgraded so that it is more near truth according to the feedback in the external world;
Study mechanism: in the processing procedure of sub-state, learn chunking rule.When predicament produces, meaning in the long-term memory of current system does not have utilizable operator to make problem solving process in problem space, move forward; Need to create a new rule automatically and solve current predicament, the foundation of chunking rule need be analyzed production rule relevant with reaching the result in the long-term memory and episodic memory clue.
The initial long-term memory rule of SOAR cognitive frame long-term memory
In the last table, r1, r2, r3, r4, r5 represent rule numbers, and IF/THEN representes trigger condition and triggers result, [I] expression condition; [T] representes action, R-A1, R-A2, C-D; S-D, P-D, Tem, Des; D-S1, D-S2 are the abbreviation of object properties, represent linear, linear eigenwert, lateral separation respectively, block up, predicted congestion, mood, destination, transport condition, transport condition eigenwert.R-A1 (a) expression is linear to be a class, a=1 wherein, and 2,3 represent straight-line segment, left-turning pathways and right-hand rotation bend respectively; The turning radius of the linear eigenwert of R-A2 (b) expression is the b level, have only when for bend just has characteristic when linear, b=1,2,3,4 represent respectively turning radius be little, in, big, especially big; The horizontal clear distance value of C-D (c) expression is the c level, c=1 wherein, the horizontal clear distance of 2,3 expressions be little, in, big; S-D (d1, d2, d3), P-D (d1, d2; D3) the perception degree of blocking up and the predicted congestion perception degree of the current road junction ahead CW corresponding road section of expression are d1, d2, and the d3 level, wherein the parameter occurrence 1; 2,3,4 the expression unobstructed, generally block up and seriously block up; D-S1 (e) expression transport condition classification is e, e=1 wherein, and 2,3 expressions are kept straight on, turn left, are turned right; D-S2 (f1, f2) expression transport condition eigenwert rank is f1 and f2, f1=1 wherein, 2 expression travel speed and angles, f2=1,2,3,4 expression speed and angle rank from small to large, occurrence is demarcated through experiment; Tem (g) expression current driver's mood classification is g, g=1 wherein, 2 represent respectively happy and irritable; The current destination of Des (h) expression direction is h, h=1 wherein, and 2,3 expression is left, preceding, right respectively.
The program mode operator is selected to be specially:
1) make the candidate's operator under O (s) the expression state s gather, if its radix | O (s) | equal 1, then select o ∈ O (s) to get into working memory, otherwise continue;
2) if | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]>=and τ (s), then from O (s), select to get into working memory, otherwise continue when pre-operator with roulette mechanism; P [o wherein
Max(s)], p [o
Sec(s)] preference of optimum operator and suboptimum operator under the expression state s, operator is directly selected threshold value under τ (s) the expression state s;
3) if O (s)=Φ or | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]＜and τ (s), then can not directly carry out operator and select, then produce predicament, get into the chunk learning phase.
Study mechanism comprises the solution and the chunking rule submodule of predicament:
When the program mode memory can not be selected operator to current state, adopt following steps to solve predicament:
1) order is from original state s
0Shifting the current state that obtains through the i next state is s
iIf, O (s
i)=Φ or | O (s
i) |＞1, p [o
Max(s
i)]-p [o
Sec(s
i)]＜τ (s), then meet the chunk condition for study, make j=i+1, continue; Otherwise adopt program mode memory carrying out operator to select;
2) if j=0 changes 5); Otherwise j=j-1;
3) in all episodic memory storehouses, comprise s in the searching state transition path
jThe operator set of episodic memory, be designated as O
q(s
j), if O
q(s
j)=Φ changes 2), otherwise continue;
4) at O
q(s
j) the optimum operator entering of middle selection working memory, solve current predicament;
5) if O is (s
i)=Φ changes the matching precision of current state with step-length 0.1, up to the operator set O that satisfies current state (s '
i) appearance, wherein s '
iExpression changes the new state behind the matching precision;
6) at O (s
i) or O (s '
i) the middle roulette mechanism selection operator entering working memory that adopts, solve current predicament;
Chunking rule:
If intelligent body ran into predicament in state transitions, then explaining has partial status not have operator perhaps can not directly select in the decision process, after the decision-making this time of so intelligent body, needs to adopt chunk learning method establishment rule and preference to upgrade, if G is (s
e)-G
e(s
e)≤η
z, then the operator that solves predicament is carried out a chunk and upgrades, wherein G
e(s
e) represent that intelligent body is at state s
eUnder expectation drive target, G (s
e) expression intelligent body action actual driving target, η
zFor regular chunk upgrades threshold value; Upgraded by chunk if same rule is double, then corresponding operator is added to and run into the predicament state in the decision process, the chunk success;
No matter be that chunk forms or the rule that has existed; All to carry out feedback learning behind the intelligence body to the operator that this decision-making relates to; Because decision process relates to a plurality of states and operator, therefore adopt each state and the distance of dbjective state to distribute the feedback preference of corresponding operator; Decision-making period t state transition path in the corresponding operator o (s of k state
k) the feedback preference value be λ [d (s
k, s
e)] p
r(s
e), p wherein
r(s
e)=[G (s
e)-G
e(s
e)]
αBe end-state s
eUnder total preference value of feedback, parameter alpha gets 0.5 among this paper; λ [d (s
k, s
e), r (s
k)] be p
r(s
e) be assigned to o (s
k) on weight, it is state s
kTo s
eApart from d (s
k, s
e) and s
kState transition path r (the s at place
k) function, this paper
Wherein | r (s
k) | be s
kThe number of states that the path, place comprises.
Technical characterstic of the present invention and effect:
Adopt simulation frame of the present invention, can obtain highway layout parameter and the mutual relationship of conflicting, obtain the linear and horizontal clear distance of comparatively ideal road tunnel, promptly reduce the cost of road construction, improved travel safety again.
Description of drawings
The structure of Fig. 1 SOAR framework.
The memory of Fig. 2 driver's intelligence body running.
Linear and the horizontal clear distance optimization Simulation of Fig. 3 road tunnel framework.
Linear and the horizontal clear distance scene 1 of Fig. 4 road tunnel.
Linear and the horizontal clear distance scene 2 of Fig. 5 road tunnel.
Fig. 6 road tunnel simulated scenario 1.
Fig. 7 road tunnel simulated scenario 2.
Traffic conflict figure (car) during Fig. 8 straight-line segment goes under the different horizontal clear distances.
Traffic conflict figure (truck) during Fig. 9 straight-line segment goes under the different horizontal clear distances.
Traffic conflict figure (car) under the different horizontal clear distances of Figure 10 negotiation of bends.
Traffic conflict figure (truck) under the different horizontal clear distances of Figure 11 negotiation of bends.
Embodiment
The present invention mainly sets up oversize vehicle multiple agent model based on the SOAR cognitive frame; Traffic behavior and traffic flow character under different road alignments and the horizontal clear distance carry out emulation and analysis, propose the linear and horizontal clear distance design of the road tunnel suggested design of optimizing.
6.1.1 general highway section is to the impact analysis of driving behavior
The general linear influence to driving behavior in highway section mainly contains:
1) long straight line road can make the driver produce the hypnosis phenomenon in the process of moving, and reaction slows up, dispersion attention, thus cause error in judgement in the driving;
2) horizontal curve of correct radial is given the suitable anxiety sense of driver, helps traffic safety.Irrational horizontal curve design can make the driver in conjecture and anxiety, drive, and makes them be easy to fatigue by health, and cardiac load is excessive, and judgment descends, and is slow in reacting.The stopping sight distance that too small sweep can reduce the driver makes them can not observe turning, the place ahead in advance, can not accomplish to know what's what to the tendency of road alignment;
3) long and steep downgrade is prone to cause driver's frequently braking, feels fatigue, anxiety;
4) convex vertical curve is prone to cause driver's sighting distance not enough, can't see the place ahead traffic conditions and causes the mood dysphoria; Vertical sag curve place sighting distance on without a licence at the night bright road road is not enough, is prone to cause driver's nervous psychology.
6.1.2 road tunnel is to the impact analysis of driving behavior
Road tunnel linear to driving behavior except having the influence similar with general highway section, also have its singularity, wherein linear change is more obvious to the influence of the speed of a motor vehicle and changes in heart rate.
1) speed of a motor vehicle: the road tunnel gateway is that driver psychology changes significantly and highway section fast.Discover that general vehicle has obvious deceleration getting into the last set a distance in tube crossing, in road tunnel, the speed of a motor vehicle generally fluctuates up and down in the reduced levels scope, and obvious accelerator is arranged going out the tube crossing.The main cause that causes road tunnel to import and export regional speed of a motor vehicle variation is visual adaptation and the road alignment factor that the inside and outside light difference of road tunnel causes.According to No. two road tunnels in the Qinling Mountains and Zhonnanshan Mountain road tunnel are discovered that vehicle 5s design speed travel range operating speed before and after road tunnel is imported and exported all receives linear influence.Guo Zhongyin etc. study the security of operation that underground road is imported and exported, and think that importing and exporting linear transition is one of major influence factors of road tunnel safety.
Different linear road tunnel gateways produce Different Effects to internal environment; The straight line road tunnel is unfavorable for the light transition; Can not effectively regulate driver psychology, the deceleration that can't avoid " black-hole effect " and " white hole effect " to cause enters the hole, the appearance of the phenomenon of quickening to appear.The highway road tunnel overwhelming majority of Switzerland and Northern European countries makes curved, and this helps improving driver's notice, and road tunnel gateway segment of curve can effectively solve " black and white hole " problem, the generation of minimizing accident.
In road tunnel, go, driver's the visual field receives the influence of many factors, and the visual field changes with the variation of the speed of a motor vehicle, and same, the speed of a motor vehicle changes with the variation in the visual field, always promptly the driver selects travel speed according to its visual field size.When the place ahead minor radius horizontal curve, longitudinal gradient, road tunnel hole etc. occurred the visual field is diminished, the driver can underspeed accordingly; When the place ahead is long straight line or long radius horizontal curve intervisibility when good, visual field increase, the driver can improve speed.
2) heart rate: discover that there is big correlativity in the turning radius of driver's heart rate increment and road tunnel.The minor radius road tunnel increases owing to reasons such as centrifugal force, sighting distance, improper ventilation are prone to cause driver's heart rate, and driver's perception, mood impacted.In addition, the confined space of road tunnel is prone to cause driver's constriction, and sensation road tunnel inside lane width diminishes; The curve road tunnel can cause the fear that bumps against with the road tunnel inwall to the driver; Produce so-called " abutment wall effect ", motoring pressure increases greatly, and might lose one's temper; Misoperation causes accident.The road tunnel of one-way trip should be set to sweeping curve, and what the suitable heart rate of driver increased, psychological stress is beneficial to notice concentrates, and sweeping curve road tunnel illumination transitionality is good, is beneficial to driver's light process.
Investigation data based on road tunnel crowd highway section, the Western Han Dynastry of the Chang An University high speed Qinling Mountains; The road tunnel longitudinal gradient changes because of climb and fall the influence of driver psychology to some extent, and up highway section upward slope process heart rate increment rate changes with the gradient is different, in the longitudinal gradient process of changing from small to big; The driver is in order to dash the gradient more; General speed promotes, and it is big that the heart rate increment rate becomes, and reaches the peak in longitudinal gradient 2.7% left and right sides heart rate increment rate; The gradient continues to increase, and then the driver takes conservative measure, low-grade speed stabilizing climbing, and heart rate descends to some extent; Along with the gradient continues to increase, the climbing difficulty increases, and driver psychology is nervous, and heart rate raises once more.Descending process changes in heart rate receives speed of a motor vehicle control influence, is that the heart rate increment is maximum between 3～4% the time in the gradient, and the gradient continues to increase, driver's control speed of a motor vehicle of braking, and heart rate reduces on the contrary.
3) horizontal clear distance: in " highway road tunnel design specifications " highway road tunnel stopping sight distance has been made clear and definite regulation, the safe-stopping sight distance that is wherein adopted is consistent with the stopping sight distance of common roadbed.Because the restriction of profile in the road tunnel, the horizontal clear distance in the hole (distances of barriers such as viewpoint to hole wall or maintaining roadway) is much smaller than the horizontal clear distance value of common roadbed.The horizontal clear distance of road tunnel is more little, requires minimum radius of horizontal curve big more; Unidirectional two-way traffic road tunnel, the horizontal clear distance of left-hand lane is less than the horizontal clear distance of right-hand lane; According to vehicle heading, the horizontal clear distance of left-hand bend road tunnel is less than right-hand bend, and the road tunnel left-hand bend curve road tunnel curve road tunnel of turning right is unfavorable for safety.Therefore, the road tunnel radius of horizontal curve should take measures to strengthen the horizontal clear distance of road tunnel during less than minimum sighting distance radius.
6.2SOAR cognitive frame general introduction
The full name of SOAR is state, operator and target (State; Operator and Result); Be by a kind of framework that be called " universal intelligent " of people such as Allen Newell in the nineteen eighty-three exploitation; Main discussion knowledge, thinking, intelligence and memory are cognitive structures that range of application is very wide.Wherein, state is that current situation about will deal with problems characterizes, and operator is the operation that can change state, produce new state, and target is the desired result that need deal with problems.The operation of SOAR is exactly to use operator and the process of selecting next operator up to this problem realization of goal constantly at problem space.
The SOAR framework mainly comprises I/O interface, long-term memory district, working memory district three parts, also has some other potential mechanism such as decision-making period, learning process etc.Be illustrated in fig. 1 shown below:
As shown in Figure 1, SOAR must be mutual with extraneous generation through perception/action interface, by perception the external world is mapped in the working memory, through action sign returning to external environment and generation action that working memory is inner.SOAR inside has the working memory district and the long-term memory district of different forms of characterization, is used for describing the current state and the long-term memory of problem solving respectively.Working memory is represented result, moving target and the movable operator etc. of the perception data relevant with current state, middle reasoning with the state/object diagram with hierarchical organization.Long-term memory comprises procedural memory, the memory of semanteme property and episodic memory.SOAR passes through a fixing treatment mechanism---decision-making period, functions such as the selection of completion SOAR and application operator.Being accompanied by decision-making period SOAR has four kinds of different study mechanisms, is respectively intensified learning, chunk, episodic study and semantic inquiry learning.
6.3 be applied to the SOAR intelligence body design of the linear and horizontal clear distance emulation of road tunnel
This joint adopts the SOAR cognitive frame that the intelligence of the driver in underground road travel body is carried out modeling, comprises intelligent body running memory, long-term memory, procedural operator system of selection and study mechanism etc.
6.3.1 driver's intelligence body running memory design through road tunnel
Working memory comprises the multidate information all about the world and internal reasoning of SOAR intelligence body, and it comprises perception information, intermediate computations, and the state of classification and relevant operator and target etc., all reasonings of intelligent body are all carried out in working memory with decision-making.Information among the SOAR in all working memory is organized into graph structure, and Fig. 2 is some graph structure through the memory of road tunnel driver intelligence body running.
As shown in Figure 2, the state S1 in the working memory comprises five attributes, and wherein the value of vehicle, driver, IO attribute is object V1, D1 and I1, and all the other two attributes represent that respectively the name of this state is called s1, and it does not have father's state.The relevant information of the V1 attribute representation intelligence body component units vehicle of state S1, it is little to comprise that the expression vehicle is of a size of, and the purposes of vehicle is a private car, and present speed is very fast.The D1 attribute representation driver's of S1 relevant information comprises that driver's sex is the man, and the age is 45, and the driving age is 20 years, and monthly income is 8000, and personality is steady type, and is very familiar to road network, and the matching precision of current driver's is 1, and current location is an initial position.The IO attribute is the input and output of S1; Realize through input-link and output-link interface respectively; Wherein the identifier I1 of input-link has four attributes; Represent the information relevant that intelligent body perceives from the external world respectively, comprise that attribute Road-alignment, Clear-distance, Sense-density, Velocity, Turn-angle represent respectively that the perception of current vehicle place road is linear, lateral separation, perception are blocked up degree, speed, angle of turn with highway section and surrounding enviroment.The identifier O1 of output interface output-link representes the output under this state, such as the operator of selecting to use and use operator the result that influences of working memory and surrounding enviroment is exported by the attribute under the I3.
The input and output of table 6-1 working memory
6.3.2 driver's intelligence body long-term memory design in the road tunnel driving
The long-term memory district is an achievement memory district.Most important and procedural knowledge the most effectively in the long-term memory, episodic knowledge only just works when procedural knowledge is not enough to support decision-making, in driving behavior, does not relate to semantic sex knowledge.SOAR intelligence body characterizes with production rule through the procedural memory of road tunnel driving behavior.At first; " if " part with each rule removes to mate the element in the working memory; If " if " of rule part is mated with the working memory element fully, this rule will be triggered, and arrives the information of kinematic system or produces the suggestion that changes current state through sending one then; Cause that " then " part triggers, promptly any and current goal, state and operator matching rules can change current target and state.
SOAR intelligence body is the specific experience and the memory of intelligent body through the episodic memory of road tunnel; It is the Knowledge Source of episodic study; In case the driving behavior decision-making is accomplished; Just current behavior, corresponding decision-making state transfer path and feedback preference value are carried out record, use when making a strategic decision predicament in order to running in next time.
The initial long-term memory rule of part of certain driver's intelligence body of table 6-2
In the last table, r1, r2, r3, r4, r5 represent rule numbers, and IF/THEN representes trigger condition and triggers result, [I] expression condition; [T] representes action, R-A1, R-A2, C-D; S-D, P-D, Tem, Des; D-S1, D-S2 are the abbreviation of object properties, represent linear, linear eigenwert, lateral separation respectively, block up, predicted congestion, mood, destination, transport condition, transport condition eigenwert.R-A1 (a) expression is linear to be a class, a=1 wherein, and 2,3 represent straight-line segment, left-turning pathways and right-hand rotation bend respectively; The turning radius of the linear eigenwert of R-A2 (b) expression is the b level, have only when for bend just has characteristic when linear, b=1,2,3,4 represent respectively turning radius be little, in, big, especially big; The horizontal clear distance value of C-D (c) expression is the c level, c=1 wherein, the horizontal clear distance of 2,3 expressions be little, in, big; S-D (d1, d2, d3), P-D (d1, d2; D3) the perception degree of blocking up and the predicted congestion perception degree of the current road junction ahead CW corresponding road section of expression are d1, d2, and the d3 level, wherein the parameter occurrence 1; 2,3,4 the expression unobstructed, generally block up and seriously block up; D-S1 (e) expression transport condition classification is e, e=1 wherein, and 2,3 expressions are kept straight on, turn left, are turned right; D-S2 (f1, f2) expression transport condition eigenwert rank is f1 and f2, f1=1 wherein, 2 expression travel speed and angles, f2=1,2,3,4 expression speed and angle rank (occurrence is demarcated through experiment) from small to large; Tem (g) expression current driver's mood classification is g, g=1 wherein, 2 represent respectively happy and irritable; The current destination of Des (h) expression direction is h, h=1 wherein, and 2,3 expression is left, preceding, right respectively.Above-mentioned rule is the part of certain driver's intelligence body initial rules, and length is limit, and does not list in detail.In addition, driver's intelligence body rule can increase and deletion through study mechanism is dynamic in learning process.
The episodic memory of inducing obedience behavior of SOAR intelligence body is the specific experience and the memory of intelligent body; It is the Knowledge Source of episodic study; In case inducing the obedience behavior decision-making accomplishes; Just current behavior, corresponding decision-making state transfer path and feedback preference value are carried out record, use when making a strategic decision predicament in order to running in next time.
6.3.3 the program mode operator is selected
Adopt the numerical value preference in the SOAR intelligence body through road tunnel.Every rule in the long-term memory rule base comprises that matching condition and matching condition satisfy the operator that can advise down, and advises the numerical value preference value of this operator under this condition.New regulation of every interpolation need be judged the initial value preference size of operator in this rule, and in decision process, according to the feedback in the external world size of this value is upgraded so that it is more near truth, for driver's decision-making provides information more accurately.
1) make the candidate's operator under O (s) the expression state s gather, if its radix | O (s) | equal 1, then select o ∈ O (s) to get into working memory, otherwise continue;
2) if | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]>=and τ (s), then from O (s), select to get into working memory, otherwise continue when pre-operator with roulette mechanism; P [o wherein
Max(s)], p [o
Sec(s)] preference of optimum operator and suboptimum operator under the expression state s, operator is directly selected threshold value under τ (s) the expression state s;
3) if O (s)=Φ or | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]＜and τ (s), then can not directly carry out operator and select, then produce predicament, get into the chunk learning phase.
6.3.4 study mechanism
The main chunk mode of learning that adopts is described the learning functionality of driver through the road tunnel driving behavior.Chunk is that SOAR carries out learning mechanism when predicament solves, and promptly in the processing procedure of sub-state, learns chunking rule.When predicament produces, meaning in the long-term memory of current system does not have utilizable operator to make problem solving process in problem space, move forward; Need to create a new rule automatically and solve current predicament, the foundation of chunking rule need be analyzed production rule relevant with reaching the result in the long-term memory and episodic memory clue.
6.3.4.1 the solution of predicament
When the program mode memory can not be selected operator to current state, adopt following steps to solve predicament.
1) order is from original state s
0Shifting the current state that obtains through the i next state is s
iIf, O (s
i)=Φ or | O (s
i) |＞1, p [o
Max(s
i)]-p [o
Sec(s
i)]＜τ (s), then meet the chunk condition for study, make j=i+1, continue; Otherwise adopt program mode memory carrying out operator to select, see 3.4;
2) if j=0 changes 5; Otherwise j:=j-1;
3) in all episodic memory storehouses, comprise s in the searching state transition path
jThe operator set of episodic memory, be designated as O
q(s
j).If O
q(s
j)=Φ changes 2, otherwise continues;
4) at O
q(s
j) the optimum operator entering of middle selection working memory, solve current predicament;
5) if O is (s
i)=Φ changes the matching precision of current state with step-length 0.1, up to the operator set O that satisfies current state (s '
i) appearance, wherein s '
iExpression changes the new state behind the matching precision;
6) at O (s
i) or O (s '
i) the middle roulette mechanism selection operator entering working memory that adopts, solve current predicament.
6.3.4.2 chunking rule
The intelligent body of process road tunnel is except initial program memory rule, and most rules are created by chunk.If intelligent body ran into predicament in state transitions, then explaining has partial status not have operator perhaps can not directly select in the decision process, after the decision-making this time of so intelligent body, needs to adopt chunk learning method establishment rule and preference to upgrade.If G is (s
e)-G
e(s
e)≤η
z, then the operator that solves predicament is carried out a chunk and upgrades, wherein G
e(s
e) represent that intelligent body is at state s
eUnder expectation drive target, G (s
e) expression intelligent body action actual driving target, η
zFor regular chunk upgrades threshold value.Upgraded by chunk if same rule is double, then corresponding operator is added to and run into the predicament state in the decision process, the chunk success.
No matter be that chunk forms or the rule that has existed; All to carry out feedback learning behind the intelligence body to the operator that this decision-making relates to; Because decision process relates to a plurality of states and operator, therefore adopt each state and the distance of dbjective state to distribute the feedback preference of corresponding operator.Decision-making period t state transition path in the corresponding operator o (s of k state
k) the feedback preference value be λ [d (s
k, s
e)] p
r(s
e), p wherein
r(s
e)=[G (s
e)-G
e(s
e)]
αBe end-state s
eUnder total preference value of feedback, parameter alpha gets 0.5 among this paper; λ [d (s
k, s
e), r (s
k)] be p
r(s
e) be assigned to o (s
k) on weight, it is state s
kTo s
eApart from d (s
k, s
e) and s
kState transition path r (the s at place
k) function, this paper
Wherein | r (s
k) | be s
kThe number of states that the path, place comprises.
6.4 simulation frame
As shown in Figure 3.
6.5 emulation experiment and analysis
This emulation experiment at first designs the SOAR intelligence body of and horizontal clear distance linear towards road tunnel; Then to carrying out emulation experiment under the different linear and horizontal clear distance conditions; Experimental result under the different simulated conditions is analyzed, and provides the optimum suggested design under this experiment scene.
6.5.1 simulating scenes setting
Simulating scenes is the underground road in Tianjin; Unidirectional three tracks; Linear in the simulating scenes, horizontal clear distance etc. is after carrying out adjustment to a certain degree on the former design proposal basis; Carry out emulation experiment respectively, on the The simulation experiment result analysis foundation, obtain horizontal clear distance and linear prioritization scheme under the different condition.Fig. 4,5 is the part scene photo.
Based on this road tunnel design proposal, adopt uc win/road to carry out three-dimension virtual reality and make up, the basis of the parameter calibration that is used for experimentizing, road tunnel is set to three tracks, and design speed is 40 kilometers, and the partial simulation scene is as shown in Figure 6.
6.5.2 emulation experiment
Under road tunnel straight-line segment and negotiation of bends condition, under the different rows vehicle speed, the standard lateral clear distance is carried out the certain amplitude adjustment, horizontal clear distance under this chapter general condition and sighting distance radius are shown in following table 6-3 and 6-4.
Horizontal clear distance under the table 6-3 road tunnel general condition
Sighting distance radius under the table 6-4 road tunnel general condition
6.5.2.1 the horizontal clear distance emulation of road tunnel straight-line segment
Under road tunnel straight-line segment car driving conditions; Horizontal clear distance is reduced with 5% step-length on general basis or increases by 15%; Adopt this chapter emulation mode that vehicle is carried out emulation through straight-line segment, following table is corresponding traffic conflict data of different emulation experiments under the different speed of a motor vehicle on the 200m highway section in 300 minutes.
The different speed of a motor vehicle of table 6-5 and road tunnel straight-line segment under the different horizontal clear distances traffic conflict data (car) of going
Under road tunnel straight-line segment truck driving conditions; Horizontal clear distance is reduced with 5% step-length on general basis or increases by 20%; Adopt this chapter emulation mode that vehicle is carried out emulation through straight-line segment, following table is corresponding traffic conflict data of different emulation experiments under the different speed of a motor vehicle in 300 minutes.
Road tunnel straight-line segment under the different speed of a motor vehicle of the table 6-6 traffic conflict data (truck) of going
Under the friction speed with horizontal clear distance under the traffic conflict curve map be shown in the following figure.
6.5.2.2 the horizontal clear distance emulation of road tunnel bend
Under road tunnel bend section car driving conditions; Horizontal clear distance is reduced with 5% step-length on general basis or increases by 20%; Adopt this chapter emulation mode that vehicle is carried out emulation through straight-line segment, following table is corresponding traffic conflict data of different emulation experiments under the different speed of a motor vehicle in 30 minutes.
Road tunnel negotiation of bends traffic conflict data (car) under the different speed of a motor vehicle of table 6-7
Under the friction speed with horizontal clear distance under the traffic conflict curve map be shown in the following figure.
Under road tunnel bend truck driving conditions; Horizontal clear distance is reduced with 5% step-length on general basis or increases by 20%; Adopt this chapter emulation mode that vehicle is carried out emulation through straight-line segment, following table is corresponding traffic conflict data of different emulation experiments under the different speed of a motor vehicle in 30 minutes.
Road tunnel negotiation of bends traffic conflict data (truck) under the different speed of a motor vehicle of table 6-8
Under the friction speed with horizontal clear distance under the traffic conflict curve map shown in figure 11.
6.5.3 interpretation of result
1) can know that to 6-11 when horizontal clear distance increased, the traffic conflict number average under the friction speed was on a declining curve by table 6-5 to 6-8 and Fig. 6-8, this explains that horizontal clear distance increase helps the lifting of road tunnel traffic safety.
2) see on the whole; Increase along with horizontal clear distance; The speed that traffic conflict reduces is slowed down; This explanation road tunnel horizontal clear distance has between certain sensitizing range the influence of traffic safety, when horizontal clear distance increases to 110% under the general standard when above, continues increase the influence of traffic conflict is significantly reduced.
3) as far as being the traffic flow of chief component with the car, in straight-line segment went, when the speed of a motor vehicle during greater than 60km/h, laterally clear distance increased to 5% when above of general standard, continues increase the influence of traffic conflict is significantly reduced; When the speed of a motor vehicle during,, also little to the traffic conflict influence even laterally clear distance is reduced to 90% of general standard smaller or equal to 40km/h.Therefore under this paper experiment condition; When the car straight-line segment went, when design speed during more than or equal to 60 kilometers, the horizontal clear distance standard of recommendation was 105% of a general standard; When design speed during smaller or equal to 40 kilometers, the horizontal clear distance standard of recommendation is 90% of a general standard.
4) as far as being the traffic flow of chief component with the car, in negotiation of bends, when the speed of a motor vehicle during greater than 60km/h, laterally clear distance increases to 15% of general standard, and is still remarkable to the influence of traffic conflict; When the speed of a motor vehicle during,, also little to the traffic conflict influence even laterally clear distance is reduced to 105% of general standard smaller or equal to 40km/h.Therefore under this paper experiment condition; During the car negotiation of bends, when design speed during more than or equal to 60 kilometers, the horizontal clear distance standard of recommendation is 115% of a general standard; When design speed during smaller or equal to 40 kilometers, the horizontal clear distance standard of recommendation is 105% of a general standard.
5) as far as being the traffic flow of chief component with the truck, in straight-line segment went, when the speed of a motor vehicle during greater than 60km/h, laterally clear distance increased to 5% when above of general standard, continues increase the influence of traffic conflict is significantly reduced; When the speed of a motor vehicle during, on the general standard basis, increase the traffic conflict influence not remarkable smaller or equal to 40km/h.Therefore under this paper experiment condition; When the truck straight-line segment went, when design speed during more than or equal to 60 kilometers, the horizontal clear distance standard of recommendation was 105% of a general standard; When design speed during smaller or equal to 40 kilometers, the horizontal clear distance standard of recommendation is the general standard recommendation.
6) as far as being the traffic flow of chief component with the truck, in negotiation of bends, horizontal clear distance is all remarkable to all velocity shootings; Therefore under this paper experiment condition; During the truck negotiation of bends, the horizontal clear distance of recommendation increases under feasible condition as far as possible, to improve travel safety.
Claims (4)
1. linear and horizontal clear distance method for designing of the road tunnel based on multiple agent emulation; It is characterized in that; Adopt the SOAR cognitive frame that the intelligence of the driver in underground road travel body is carried out modeling, comprise intelligent body running memory, long-term memory, procedural operator system of selection and study mechanism submodule:
SOAR cognitive frame working memory comprises the multidate information all about the world and internal reasoning of SOAR intelligence body; It comprises perception information; Intermediate computations, the state of classification and relevant operator and target etc., all reasonings of intelligent body are all carried out in working memory with decision-making;
SOAR cognitive frame long-term memory characterizes with production rule through the procedural memory of road tunnel driving behavior; At first; " if " part with each rule removes to mate the element in the working memory; If " if " of rule part is mated with the working memory element fully, this rule will be triggered, and arrives the information of kinematic system or produces the suggestion that changes current state through sending one then; Cause that " then " part triggers, promptly any and current goal, state and operator matching rules can change current target and state;
The program mode operator is selected: through adopting the numerical value preference in the SOAR cognitive frame of road tunnel; Every rule in the long-term memory rule base comprises that matching condition and matching condition satisfy the operator that can advise down; And the numerical value preference value of advising this operator under this condition; New regulation of every interpolation need be judged the initial value preference size of operator in this rule, and in decision process, the size of this value is upgraded so that it is more near truth according to the feedback in the external world;
Study mechanism: in the processing procedure of sub-state, learn chunking rule; When predicament produces, meaning in the long-term memory of current system does not have utilizable operator to make problem solving process in problem space, move forward; Need to create a new rule automatically and solve current predicament, the foundation of chunking rule need be analyzed production rule relevant with reaching the result in the long-term memory and episodic memory clue.
2. the linear and horizontal clear distance method for designing of the road tunnel based on multiple agent emulation as claimed in claim 1 is characterized in that: the initial long-term memory of SOAR cognitive frame long-term memory is regular like following table:
In the last table, r1, r2, r3, r4, r5 represent rule numbers, and IF/THEN representes trigger condition and triggers result, [I] expression condition; [T] representes action, R-A1, R-A2, C-D; S-D, P-D, Tem, Des; D-S1, D-S2 are the abbreviation of object properties, represent linear, linear eigenwert, lateral separation respectively, block up, predicted congestion, mood, destination, transport condition, transport condition eigenwert, and R-A1 (a) expression is linear to be a class; A=1 wherein, 2,3 represent straight-line segment, left-turning pathways and right-hand rotation bend respectively; The turning radius of the linear eigenwert of R-A2 (b) expression is the b level, have only when for bend just has characteristic when linear, b=1,2,3,4 represent respectively turning radius be little, in, big, especially big; The horizontal clear distance value of C-D (c) expression is the c level, c=1 wherein, the horizontal clear distance of 2,3 expressions be little, in, big; S-D (d1, d2, d3), P-D (d1, d2; D3) the perception degree of blocking up and the predicted congestion perception degree of the current road junction ahead CW corresponding road section of expression are d1, d2, and the d3 level, wherein the parameter occurrence 1; 2,3,4 the expression unobstructed, generally block up and seriously block up; D-S1 (e) expression transport condition classification is e, e=1 wherein, and 2,3 expressions are kept straight on, turn left, are turned right; D-S2 (f1, f2) expression transport condition eigenwert rank is f1 and f2, f1=1 wherein, 2 expression travel speed and angles, f2=1,2,3,4 expression speed and angle rank from small to large, occurrence is demarcated through experiment; Tem (g) expression current driver's mood classification is g, g=1 wherein, 2 represent respectively happy and irritable; The current destination of Des (h) expression direction is h, h=1 wherein, and 2,3 expression is left, preceding, right respectively.
3. the linear and horizontal clear distance method for designing of the road tunnel based on multiple agent emulation as claimed in claim 1 is characterized in that, the program mode operator is selected to be specially:
1) make the candidate's operator under O (s) the expression state s gather, if its radix | O (s) | equal 1, then select o ∈ O (s) to get into working memory, otherwise continue;
2) if | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]>=and τ (s), then from O (s), select to get into working memory, otherwise continue when pre-operator with roulette mechanism; P [o wherein
Max(s)], p [o
Sec(s)] preference of optimum operator and suboptimum operator under the expression state s, operator is directly selected threshold value under τ (s) the expression state s;
3) if O (s)=Φ or | O (s) |＞1, p [o
Max(s)]-p [o
Sec(s)]＜and τ (s), then can not directly carry out operator and select, then produce predicament, get into the chunk learning phase.
4. the linear and horizontal clear distance method for designing of the road tunnel based on multiple agent emulation as claimed in claim 1 is characterized in that, study mechanism comprises the solution and the chunking rule submodule of predicament:
When the program mode memory can not be selected operator to current state, adopt following steps to solve predicament:
1) order is from original state s
0Shifting the current state that obtains through the i next state is s
iIf, O (s
i)=Φ or | O (s
i) |＞1, p [o
Max(s
i)]-p [o
Sec(s
i)]＜τ (s), then meet the chunk condition for study, make j=i+1, continue; Otherwise adopt program mode memory carrying out operator to select;
2) if j=0 changes 5); Otherwise j=j-1;
3) in all episodic memory storehouses, comprise s in the searching state transition path
jThe operator set of episodic memory, be designated as O
q(s
j), if O
q(s
j)=Φ changes 2), otherwise continue;
4) at O
q(s
j) the optimum operator entering of middle selection working memory, solve current predicament;
5) if O is (s
i)=Φ changes the matching precision of current state with step-length 0.1, up to the operator set O that satisfies current state (s '
i) appearance, wherein s '
iExpression changes the new state behind the matching precision;
6) at O (s
i) or O (s '
i) the middle roulette mechanism selection operator entering working memory that adopts, solve current predicament;
Chunking rule:
If intelligent body ran into predicament in state transitions, then explaining has partial status not have operator perhaps can not directly select in the decision process, after the decision-making this time of so intelligent body, needs to adopt chunk learning method establishment rule and preference to upgrade, if G is (s
e)-G
e(s
e)≤η
z, then the operator that solves predicament is carried out a chunk and upgrades, wherein G
e(s
e) represent that intelligent body is at state s
eUnder expectation drive target, G (s
e) expression intelligent body action actual driving target, η
zFor regular chunk upgrades threshold value; Upgraded by chunk if same rule is double, then corresponding operator is added to and run into the predicament state in the decision process, the chunk success;
No matter be that chunk forms or the rule that has existed; All to carry out feedback learning behind the intelligence body to the operator that this decision-making relates to; Because decision process relates to a plurality of states and operator; Therefore adopt each state and the distance of dbjective state to distribute the feedback preference of corresponding operator, decision-making period t state transition path in the operator o (s of k state correspondence
k) the feedback preference value be λ [d (s
k, s
e)] p
r(s
e), p wherein
r(s
e)=[G (s
e)-G
e(s
e)]
αBe end-state s
eUnder total preference value of feedback, parameter alpha gets 0.5; λ [d (s
k, s
e), r (s
k)] be p
r(s
e) be assigned to o (s
k) on weight, it is state s
kTo s
eApart from d (s
k, s
e) and s
kState transition path r (the s at place
k) function, get
Wherein | r (s
k) | be s
kThe number of states that the path, place comprises.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210104967.5A CN102609599B (en) | 2012-04-11 | 2012-04-11 | Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210104967.5A CN102609599B (en) | 2012-04-11 | 2012-04-11 | Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102609599A true CN102609599A (en) | 2012-07-25 |
| CN102609599B CN102609599B (en) | 2014-03-12 |
Family
ID=46526967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210104967.5A Active CN102609599B (en) | 2012-04-11 | 2012-04-11 | Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102609599B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198182A (en) * | 2013-03-20 | 2013-07-10 | 天津市市政工程设计研究院 | Pedestrian guide sign design method based on visual perception analogue simulation technology |
| CN104239636A (en) * | 2014-09-16 | 2014-12-24 | 北京航空航天大学 | Fire emergency evacuation simulation method |
| CN103793570B (en) * | 2014-02-08 | 2016-09-21 | 东南大学 | A kind of road alignment safety analytical method based on dynamics of multibody systems |
| CN111612162A (en) * | 2020-06-02 | 2020-09-01 | 中国人民解放军军事科学院国防科技创新研究院 | Reinforced learning method and device, electronic equipment and storage medium |
| CN113239566A (en) * | 2021-05-27 | 2021-08-10 | 大连理工大学 | Emotion-fused post-disaster three-level hierarchical simulation system and method based on intelligent agent |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604204A (en) * | 2009-07-09 | 2009-12-16 | 北京科技大学 | Distributed cognitive technology for intelligent emotional robot |
| CN101814235A (en) * | 2010-01-22 | 2010-08-25 | 天津市市政工程设计研究院 | Method for assigning traffic in port area in reservation congregation mode |
-
2012
- 2012-04-11 CN CN201210104967.5A patent/CN102609599B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604204A (en) * | 2009-07-09 | 2009-12-16 | 北京科技大学 | Distributed cognitive technology for intelligent emotional robot |
| CN101814235A (en) * | 2010-01-22 | 2010-08-25 | 天津市市政工程设计研究院 | Method for assigning traffic in port area in reservation congregation mode |
Non-Patent Citations (2)
| Title |
|---|
| RON SUN 等: "Imagery in cognitive architecture: Representation and control at multiple levels of abstraction", 《COGNITIVE SYSTEMS RESEARCH》 * |
| SHIQUAN ZHONG等: "Guidance Compliance Behavior on VMS Based on SOAR Cognitive Architecture", 《MATHEMATICAL PROBLEMS IN ENGINEERING》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198182A (en) * | 2013-03-20 | 2013-07-10 | 天津市市政工程设计研究院 | Pedestrian guide sign design method based on visual perception analogue simulation technology |
| CN103198182B (en) * | 2013-03-20 | 2015-10-28 | 天津市市政工程设计研究院 | The pedestrian guide sign design method of view-based access control model perception simulation technology |
| CN103793570B (en) * | 2014-02-08 | 2016-09-21 | 东南大学 | A kind of road alignment safety analytical method based on dynamics of multibody systems |
| CN104239636A (en) * | 2014-09-16 | 2014-12-24 | 北京航空航天大学 | Fire emergency evacuation simulation method |
| CN111612162A (en) * | 2020-06-02 | 2020-09-01 | 中国人民解放军军事科学院国防科技创新研究院 | Reinforced learning method and device, electronic equipment and storage medium |
| CN111612162B (en) * | 2020-06-02 | 2021-08-27 | 中国人民解放军军事科学院国防科技创新研究院 | Reinforced learning method and device, electronic equipment and storage medium |
| CN113239566A (en) * | 2021-05-27 | 2021-08-10 | 大连理工大学 | Emotion-fused post-disaster three-level hierarchical simulation system and method based on intelligent agent |
| CN113239566B (en) * | 2021-05-27 | 2021-11-09 | 大连理工大学 | Emotion-fused post-disaster three-level hierarchical simulation system and method based on intelligent agent |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102609599B (en) | 2014-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Analytical analysis of the effect of maximum platoon size of connected and automated vehicles | |
| WO2021077725A1 (en) | System and method for predicting motion state of surrounding vehicle based on driving intention | |
| CN102609599B (en) | Method for designing emulational underground road alignment and transverse clear distance based on multiple intelligent agents | |
| Novi et al. | Real-time control for at-limit handling driving on a predefined path | |
| Stefansson et al. | Human-robot interaction for truck platooning using hierarchical dynamic games | |
| CN102505591A (en) | Method for determining lengths of upstream transition regions of construction operation area | |
| CN114265398A (en) | Trajectory planning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| Pirdavani et al. | Travel time evaluation of a U-turn facility: comparison with a conventional signalized intersection | |
| CN103077280A (en) | Traffic design method for branch and confluent areas of underground road for safety of large vehicles | |
| Xu et al. | New design method for horizontal alignment of complex mountain highways based on “trajectory–speed” collaborative decision | |
| CN113538940A (en) | Real-time optimal lane selection method suitable for vehicle-road cooperative environment | |
| Wang et al. | Research on autonomous driving decision-making strategies based deep reinforcement learning | |
| Tan | Impact of risk illusions on traffic flow in fog weather | |
| Cheng et al. | Enhancing mixed traffic flow safety via connected and autonomous vehicle trajectory planning with a reinforcement learning approach | |
| CN102505644A (en) | Method for confirming set positions of speed limit signs and size of speed limit during road construction | |
| CN116935671A (en) | Automatic road intersection management method based on projection type constraint strategy optimization | |
| Wang et al. | Research on Car‐Following Model considering Driving Style | |
| Kou et al. | Dual-objective intelligent vehicle lane changing trajectory planning based on polynomial optimization | |
| Qi et al. | Behavioral investigation of stochastic lateral wandering patterns in mixed traffic flow | |
| Dayi et al. | Research on coordinated control of vehicle’s speed in new mixed traffic flow | |
| Zhang et al. | Safety-aware vehicle-following driving optimization of intelligent and connected vehicle at signalized road intersection | |
| Lin et al. | Adaptive prediction-based control for an ecological cruise control system on curved and hilly roads | |
| Xing et al. | Comprehensive safety assessment model of road long tunnel based on VISSIM | |
| Huang et al. | General Optimal Trajectory Planning: Enabling Autonomous Vehicles with the Principle of Least Action | |
| Chen et al. | Optimal control methods in intelligent vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 300051 No. 239, Yingkou Road, Heping District, Tianjin Patentee after: Tianjin municipal engineering design and Research Institute Co.,Ltd. Address before: 300051 No. 239, Yingkou Road, Heping District, Tianjin Patentee before: TIANJIN MUNICIPAL ENGINEERING DESIGN & Research Institute |
|
| CP01 | Change in the name or title of a patent holder |