CN103995915A - Crowd evacuation simulation system based on composite potential energy field - Google Patents
Crowd evacuation simulation system based on composite potential energy field Download PDFInfo
- Publication number
- CN103995915A CN103995915A CN201410108021.5A CN201410108021A CN103995915A CN 103995915 A CN103995915 A CN 103995915A CN 201410108021 A CN201410108021 A CN 201410108021A CN 103995915 A CN103995915 A CN 103995915A
- Authority
- CN
- China
- Prior art keywords
- potential energy
- energy field
- pedestrian
- frame
- gradient
- 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
- 238000005381 potential energy Methods 0.000 title claims abstract description 76
- 238000004088 simulation Methods 0.000 title abstract description 14
- 239000002131 composite material Substances 0.000 title abstract 3
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000002265 prevention Effects 0.000 claims abstract description 5
- 150000001875 compounds Chemical class 0.000 claims description 15
- 230000004888 barrier function Effects 0.000 claims description 11
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 239000003973 paint Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000011160 research Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 14
- 238000002474 experimental method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009510 drug design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Abstract
The invention provides a crowd evacuation simulation system based on a composite potential energy field. An improved potential energy field model is adopted for the system, a traditional potential energy field under Dirichlet boundary conditions is linearly combined with a potential energy field under Neumann boundary conditions, a local potential energy field for solving collision prevention problems between people is added into the combined potential energy field, and thus the composite potential energy field is obtained; by combining an update strategy of pedestrians and a pedestrian speed control method, the simulation system of personnel evacuation in emergency on different scales of scenes can be established according to the layout of the actual scene. In the crowd simulation process, influences of path plans of moving individuals on the evacuation are fully considered, and the potential energy field method can play a certain role in removing the influence factor. The system has extensive application prospects in research on simulation of safe and fast evacuation of a large number of personnel on difference scales of scenes, the design defects on the scenes can be found, and the crowd evacuation simulation system can assist in making execution schemes in emergency and is economically feasible.
Description
Technical field
The present invention relates to the crowd simulation field in computer graphics, more specifically, relate to the crowd evacuation emulation system based on compound potential energy field under a kind of different scales scene.
Background technology
Along with improving constantly of the level of urbanization, in city, there is timeliness and spatial crowded.Aspect timeliness, towards the working system in nine evenings five, caused the crowded of period on and off duty bus station, subway station; At the beginning of annual spring transportation has caused year the year before last, bus station, railway station and airport crowded.Aspect spatiality, crowd mainly concentrates on the places such as station, airport, exhibitions, and number has surpassed the number limit that its buildings allows often.Due to its high population density, add the special event of sending out such as fire, earthquake, if any personnel, accidentally fall, under panic mood, extremely easily cause the generation of the accident of trampling.
In addition, from city planning, consider, walking is a kind of trip mode of low-carbon environment-friendly.Along with metropolitan public transport is supporting more and more complete, in the face of the crowded situation of Urban Automobile Traffic, more and more people select to adopt the mode of walking-public transport to go on a journey.Yet passing traffic programme is " the light people of loaded vehicle ", the rational design of buildings in very few place of considering that the crowd is dense.Therefore, the safety issue in the place of how improving that the crowd is dense will become more and more important.
In recent years, the research emphasis of this respect comprises based on potential energy field evacuation emulation model.In this class model, motion unit is similar under the effect of field of electric force and moves, and is combined, thereby find a suitable path by the attractive force of impact point and the repulsive force of barrier.
But, in these realistic models, ignored locally optimal solution to evacuating the impact of process, the motion update strategy that interpersonal distance is too small simultaneously, people's speed of travel size is constant, individual etc. all has larger deviation with realistic situation.
In order reasonably to plan various communal facilitys and to dredge in time the stream of people in emergency situation, be necessary crowd evacuation to carry out emulation, the structure of intelligent city is also recent focus in addition, and crowd simulation is also to build the pacing items that intelligent city must possess.
Summary of the invention
In order to overcome the deficiencies in the prior art, the present invention proposes a kind of crowd evacuation emulation system based on compound potential energy field, based on compound potential energy field model, in conjunction with pedestrian's update strategy and the control method to pedestrian's speed, set up in different scales scene the in case of emergency analogue system of evacuating personnel.The path planning that this analogue system takes into full account motion unit in the process of crowd simulation on the impact of evacuating and potential energy field for the effect that solves this influence factor.
To achieve these goals, technical scheme of the present invention is:
A crowd evacuation emulation system based on compound potential energy field, builds compound potential energy field model; In conjunction with pedestrian's update strategy and the control method to pedestrian's speed, set up in different scales scene the in case of emergency analogue system of crowd evacuation;
The compound potential energy field model of described structure obtains by local potential energy field and overall potential energy field weighted mean, and concrete mode is:
Adopt the linear combination of Dirichlet boundary conditions and Nuo Yiman boundary condition, by setting different λ values, find an equilibrium point to generate overall potential energy field P
w;
P
W=λP
D+(1-λ)P
N；
P wherein
dthe potential energy field function of producing with Dirichlet boundary conditions, P
nit is the potential energy field function of producing with Nuo Yiman boundary condition; Thereby λ is in practice according to scene dynamics, adjustment reaches an equilibrium point, and in experiment, value is 0.9;
Adopt local potential energy field to solve interpersonal collision prevention problem, for everyone the local visual field of setting an X*X, each constantly all carries out the solve operation identical with overall potential energy field to the grid of X*X, adopt the linear combination of Dirichlet boundary conditions and Nuo Yiman boundary condition, by setting different λ values, find an equilibrium point, thereby obtain local potential energy field, wherein people is treated as to barrier, ought be for export the edge of X*X grid;
If people is current in certain position, then the potential energy value of the potential energy value of its current present position and critical 8 directions is added to 1 obtains local potential energy field P
s, centered by this people present position, the potential energy value of its front, rear, left and right and four clinodiagonal direction positions is 8 directions; Again with overall potential energy field P
wweighted mean just obtains compound potential energy field P
total:
P
Total=γP
S+(1-γ)P
W；
Wherein γ is weighting coefficient, thereby according to scene dynamics, adjustment reaches an equilibrium point in practice, gets 0.01 o'clock more realistic effect of effect in experiment.
For the simulated effect of the analogue system that makes to set up better, first potential energy field model is improved in the present invention, then in conjunction with pedestrian's update strategy and the control to pedestrian's speed, comprehensive many factors, build realistic model, then according to the corresponding mathematical model of above-mentioned Building of Simulation Model.
Compared with prior art, advantage of the present invention is: this model, by introducing Nuo Yiman boundary condition, is zero character by normal derivative, has strengthened the path planning performance of potential energy field, thereby the situation of having avoided pedestrian to be absorbed in local optimum region occurs; Secondly, new method and traditional Potential field method are weighted stack, have realized by parameter and have controlled the distance between pedestrian and barrier, thereby improved the simulated effect to dissimilar scene; Then, by having introduced local potential energy field, strengthened the interaction between pedestrian and pedestrian, the distance between pedestrian is controlled effectively; Finally, in conjunction with pedestrian's update strategy and the control to pedestrian's speed, comprehensive many factors improves fidelity.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of 3D display systems.
Fig. 2 is the process flow diagram that overall potential energy field generates.
Fig. 3 is the scene schematic diagram at analogue system simulated fire station.
Fig. 4 is the operational effect sectional drawing at analogue system simulated fire station.
Fig. 5 is the operational effect sectional drawing of analogue system simulation office.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described, but embodiments of the present invention are not limited to this.
(1) improvement to potential energy field model
Traditional Potential field method is to be that on map, each point navigates according to overall barrier and outlet information, and this complexity is only relevant to the complexity of map, irrelevant with number, has overcome the shortcoming of legacy paths planning algorithm in crowd's application aspect.In addition, the repulsive force that has fully taken into account barrier also meets crowd's motion characteristics very much.Based on BVP(Boundary Value Problem) Potential field method of condition is very outstanding, but in complex scene, still easily calculate locally optimal solution (Local Optimum Solution, LOS).In this case, exist a non-frontier point or certain non-borderline region toward the partial derivative of other any directions all for just, that is to say that its value is around all large than it, if therefore have people to be trapped in such region, he otherwise as you were, vacillate now to the left, now to the right, cannot correctly from these both sides, region, pass through.
The Dirichlet boundary conditions that tradition potential energy field adopts is very effective aspect performance barrier repulsive force, and the present embodiment adopts Dirichlet boundary conditions to combine with Nuo Yiman boundary condition.Suppose that with the potential energy field function that Dirichlet boundary conditions is produced be P
d, with the potential energy field function that Nuo Yiman boundary condition is produced, be P
n, P so
dand P
nany linear combination still meet Laplace's equation, therefore there is following formula.By setting different λ values, find an equilibrium point, thus optimization Simulation effect.
P
W=λP
D+(1-λ)P
N
The overall potential energy field P that above formula generates
wbe mainly used in the collision prevention of path planning and static-obstacle thing, yet in the middle of the research of crowd simulation, also need to consider a key factor, that is exactly interpersonal collision prevention.Thereby λ is in practice according to scene dynamics, adjustment reaches an equilibrium point, and in experiment, value is 0.9.
In order to address this problem the visual field to everyone the local 10*10 of setting, each constantly all carries out the solve operation identical with overall potential energy field to the grid of 10*10, and people is treated as to barrier, ought be for export the edge of 10*10 grid.This method has been considered the problem of person to person's spacing from the angle of microcosmic part, the effect of solution is fine.Suppose that people is current in certain position, then just the potential energy value of himself and critical 8 directions is added to 1 obtains local potential energy field P
s, then with overall potential energy field P
wweighted mean just obtains formula below:
P
Total=γP
S+(1-γ)P
W
Thereby γ is in practice according to scene dynamics, adjustment reaches an equilibrium point, gets 0.01 o'clock more realistic effect of effect in experiment.By choose reasonable parameter, can allow overall potential energy field and local potential energy field balance each other, improve fidelity.
(2) control of pedestrian's update strategy and pedestrian's speed
(1) pedestrian's update strategy
Existing personage's update strategy is the gradient extent according to personage position and all directions, calculate and set personage toward the probability of all directions motion, the direction that people has very large probability to reduce toward potential energy value is walked, but the direction that also has very little probability to increase toward potential energy value is walked, this method has reasonable robustness, smooth but personage's movement locus is difficult to.
The present invention adopts the direction reducing along potential energy value to advance.In 8 directions, wherein the gradient of right angle orientation is: P
o-a, b, c, d=P
o-P
a, b, c, d, o is current location, a, and b, c, d is four square position; The gradient formula of this right angle orientation is that closing of 4 formulas write, and is respectively P
o-a=P
o-P
a, P
o-b=P
o-P
b, P
o-c=P
o-P
c, P
o-d=P
o-P
d, P wherein
o-ifor representing that o is to the gradient of i direction, P
ofor current location gradient, P
ifor the gradient of direction i, o is current present position, and i gets a, b, c, d, represents respectively four square position.
The gradient of diagonal is:
t be one 1 to
between number, P
o-ac, bc, ad, bdbe that closing of 4 potential energy write, be respectively P
o-ac, P
o-bc, P
o-ad, P
o-bd, P wherein
o-jfor representing that o is to the gradient of j direction, j gets ac, bc, ad or bd, is the point of clinodiagonal direction.
Aspect animation realizes, in order to make movement locus Paint Gloss, motion is each time segmented.Suppose that the working direction before personage is φ
0, by above formula, obtaining new working direction is φ
1.For the motion toward right angle orientation, be divided into 10 frames, establishing D is the grid length of side.
The working direction of i frame is:
The displacement of i frame is:
For the motion toward diagonal, be divided into 14 frames, establishing equally D is the grid length of side.
The working direction of i frame is:
The displacement of i frame is:
By setting respectively for right angle orientation and diagonal the frame number of playing up, can avoid toward the fast situation of speed of diagonal motion like this.Can be so that track be Paint Gloss and each frame is set to its personage's working direction.
(2) control of pedestrian's speed
Before several aspects have problem that consider to select velocity reversal, do not consider the size of speed.The size of speed also has a significant impact in last simulated effect.By a large amount of observations, people's speed and crowd's density dependent, crowd density is higher, and the probability that produces collision is just large, and the speed that crowd moves is just slow.Combine with local potential energy field, adopt a simple Linear Strategy here.Speed is divided into a plurality of deceleration grade s, and s equals the number of barrier in the region of its 5*5, and its movement velocity V has following relation:
V
0initial velocity, μ weighting parameters, the concrete reality of emulation more truly when getting 0.1 in experiment.
In actual system, speed is mainly to be decided by the frame number F playing up, and supposes generally toward right angle orientation walking, need to play up 10 frames, toward diagonal walking, need to play up 14 frames, so just has following relation:
F=(1+μs)F
0
F wherein
0refer to initial frame speed, F is the frame rate after conversion, revises the F after s.
(3) foundation of analogue system
System adopts three-dimensional simulation model, is mainly divided into two parts: the calculating generation of overall potential energy field and the 3D of system show.The calculating of overall situation potential energy field generates as shown in Figure 2, and the process flow diagram of 3D display systems as shown in Figure 1.System can be according to the corresponding simulating scenes of actual Construction plan design.What for example the scene sample of accompanying drawing 3 was mainly simulated is the railway station that has two outlets of an entrance, scene central authorities are larger barriers, here be mainly test emulation system aspect local optimum generation, two outlet symmetry aspect and the human world be apart from the performance of aspect, the effect sectional drawing of operation is as Fig. 4; The emulation sectional drawing of accompanying drawing 5 Shi Duiyige office complex scenes.
Above-described embodiments of the present invention, do not form limiting the scope of the present invention.Any modification of having done within spiritual principles of the present invention, be equal to and replace and improvement etc., within all should being included in claim protection domain of the present invention.
Claims (4)
1. the crowd evacuation emulation system based on compound potential energy field, is characterized in that, builds compound potential energy field model; In conjunction with pedestrian's update strategy and the control method to pedestrian's speed, set up in different scales scene the in case of emergency analogue system of crowd evacuation;
The compound potential energy field model of described structure obtains by local potential energy field and overall potential energy field weighted mean, and concrete mode is:
Adopt the linear combination of Dirichlet boundary conditions and Nuo Yiman boundary condition, by setting different λ values, find an equilibrium point to generate overall potential energy field P
w;
P
W=λP
D+(1-λ)P
N；
P wherein
dthe potential energy field function of producing with Dirichlet boundary conditions, P
nit is the potential energy field function of producing with Nuo Yiman boundary condition;
Adopt local potential energy field to solve interpersonal collision prevention problem, for everyone the local visual field of setting an X*X, each constantly all carries out the solve operation identical with overall potential energy field to the grid of X*X, adopt the linear combination of Dirichlet boundary conditions and Nuo Yiman boundary condition, by setting different λ values, find an equilibrium point, thereby obtain local potential energy field, wherein people is treated as to barrier, ought be for export the edge of X*X grid;
If people is current in certain position, then the potential energy value of the potential energy value of the current present position of people and critical 8 directions is added to 1 obtains local potential energy field P
s, centered by this people present position, the potential energy value of its front, rear, left and right and four clinodiagonal direction positions is 8 directions; Again with overall potential energy field P
wweighted mean just obtains compound potential energy field P
total:
P
Total=γP
S+(1-γ)P
W；
Wherein γ is weighting coefficient.
2. the crowd evacuation emulation system based on compound potential energy field according to claim 1, is characterized in that, the mode of described pedestrian's update strategy is: the direction that pedestrian reduces along potential energy value is advanced, in 8 directions,
Wherein the gradient of right angle orientation is: P
o-i=P
o-P
i, P wherein
o-ifor representing that o is to the gradient of i direction, P
ofor current location gradient, P
ifor the gradient of direction i, o is current present position, and i gets a, b, and c, d, represents respectively four square position;
The gradient of diagonal is:
p wherein
o-jfor representing that o is to the gradient of j direction, j gets ac, bc, ad or bd, is respectively four clinodiagonal directions, t be one 1 to
between numerical value;
Aspect animation realizes, motion is each time segmented; If the working direction before personage is φ
0, by gradient formula, obtaining new working direction is φ
1;
For the motion toward right angle orientation, be divided into 10 frames, establishing D is the grid length of side.Working direction and the displacement of i frame are as follows:
The working direction of i frame is:
The displacement of i frame is:
For the motion toward diagonal, be divided into 14 frames, establishing equally D is the grid length of side.Working direction and the displacement of i frame are as follows:
The working direction of i frame is:
The displacement of i frame is:
By setting respectively for right angle orientation and diagonal the frame number of playing up, avoid toward the fast situation of speed of diagonal motion; Each frame is set to its personage's working direction makes again track Paint Gloss.
3. the crowd evacuation emulation system based on compound potential energy field according to claim 2, it is characterized in that, the method that described pedestrian's speed is controlled is: adopt and combine with local potential energy field, pedestrian's speed is divided into a plurality of deceleration grade s, s is the number of barrier in the region of pedestrian Y*Y, and the current movement velocity V of its pedestrian has following relation:
V wherein
0be initial velocity, μ is weighting parameters.
4. the crowd evacuation emulation system based on compound potential energy field according to claim 3, is characterized in that described X=10, Y=5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410108021.5A CN103995915B (en) | 2014-03-21 | 2014-03-21 | A kind of crowd evacuation emulation system based on compound potential energy field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410108021.5A CN103995915B (en) | 2014-03-21 | 2014-03-21 | A kind of crowd evacuation emulation system based on compound potential energy field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103995915A true CN103995915A (en) | 2014-08-20 |
| CN103995915B CN103995915B (en) | 2017-03-01 |
Family
ID=51310080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410108021.5A Expired - Fee Related CN103995915B (en) | 2014-03-21 | 2014-03-21 | A kind of crowd evacuation emulation system based on compound potential energy field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103995915B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239636A (en) * | 2014-09-16 | 2014-12-24 | 北京航空航天大学 | Fire emergency evacuation simulation method |
| CN104299265A (en) * | 2014-10-22 | 2015-01-21 | 电子科技大学 | Group behavior control technology under fluid environment influence |
| CN106096168A (en) * | 2016-06-21 | 2016-11-09 | 哈尔滨工业大学 | A kind of space based on Auditory Perception crowd evacuation analogy method |
| CN108108688A (en) * | 2017-12-18 | 2018-06-01 | 青岛联合创智科技有限公司 | A kind of limbs conflict behavior detection method based on the extraction of low-dimensional space-time characteristic with theme modeling |
| CN108153945A (en) * | 2017-12-11 | 2018-06-12 | 中山大学 | A kind of crowd evacuation emulation model based on multi-Agent |
| CN108153966A (en) * | 2017-12-22 | 2018-06-12 | 中山大学 | The real-time evacuation emulation method of multiple exit potential energy field model crowd based on GPU |
| CN110765553A (en) * | 2019-10-30 | 2020-02-07 | 北京交通大学 | Airport passenger rapid transit system simulation environment construction method based on virtual reality |
| CN113901727A (en) * | 2021-11-16 | 2022-01-07 | 枫树谷(成都)科技有限责任公司 | Crowd evacuation simulation method based on molecular dynamics and machine learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103191533A (en) * | 2013-03-25 | 2013-07-10 | 武汉大学 | Intelligent fire monitoring and evacuation indicating system and method |
| CN103327082A (en) * | 2013-06-07 | 2013-09-25 | 同济大学 | Multiple ant colony evacuation optimizing exchanging method |
-
2014
- 2014-03-21 CN CN201410108021.5A patent/CN103995915B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103191533A (en) * | 2013-03-25 | 2013-07-10 | 武汉大学 | Intelligent fire monitoring and evacuation indicating system and method |
| CN103327082A (en) * | 2013-06-07 | 2013-09-25 | 同济大学 | Multiple ant colony evacuation optimizing exchanging method |
Non-Patent Citations (2)
| Title |
|---|
| F.DAPPER,ETC: "Simulating Pedestrian Behavior with Potential Fields", 《ADVANCED IN COMPUTER GRAPHICS, COMPUTER GRAPHICS INTERNATIONAL CONFERENCE》 * |
| 王兆其等: "人群疏散虚拟现实模拟系统——Guarder", 《计算机研究与发展》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239636A (en) * | 2014-09-16 | 2014-12-24 | 北京航空航天大学 | Fire emergency evacuation simulation method |
| CN104299265A (en) * | 2014-10-22 | 2015-01-21 | 电子科技大学 | Group behavior control technology under fluid environment influence |
| CN104299265B (en) * | 2014-10-22 | 2017-07-25 | 电子科技大学 | A kind of group behavior control method under the influence of fluid environment |
| CN106096168A (en) * | 2016-06-21 | 2016-11-09 | 哈尔滨工业大学 | A kind of space based on Auditory Perception crowd evacuation analogy method |
| CN106096168B (en) * | 2016-06-21 | 2018-03-16 | 哈尔滨工业大学 | A kind of space crowd evacuation analogy method based on Auditory Perception |
| CN108153945A (en) * | 2017-12-11 | 2018-06-12 | 中山大学 | A kind of crowd evacuation emulation model based on multi-Agent |
| CN108108688A (en) * | 2017-12-18 | 2018-06-01 | 青岛联合创智科技有限公司 | A kind of limbs conflict behavior detection method based on the extraction of low-dimensional space-time characteristic with theme modeling |
| CN108108688B (en) * | 2017-12-18 | 2021-11-23 | 青岛联合创智科技有限公司 | Limb conflict behavior detection method based on low-dimensional space-time feature extraction and topic modeling |
| CN108153966A (en) * | 2017-12-22 | 2018-06-12 | 中山大学 | The real-time evacuation emulation method of multiple exit potential energy field model crowd based on GPU |
| CN108153966B (en) * | 2017-12-22 | 2021-06-15 | 中山大学 | GPU-based multi-outlet potential energy field model crowd real-time evacuation simulation method |
| CN110765553A (en) * | 2019-10-30 | 2020-02-07 | 北京交通大学 | Airport passenger rapid transit system simulation environment construction method based on virtual reality |
| CN113901727A (en) * | 2021-11-16 | 2022-01-07 | 枫树谷(成都)科技有限责任公司 | Crowd evacuation simulation method based on molecular dynamics and machine learning |
| CN113901727B (en) * | 2021-11-16 | 2022-02-22 | 枫树谷(成都)科技有限责任公司 | Crowd evacuation simulation method based on molecular dynamics and machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103995915B (en) | 2017-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103995915A (en) | Crowd evacuation simulation system based on composite potential energy field | |
| CN105740510B (en) | Evacuation crowd behaviour analogue system based on grid-density-relationship and its method | |
| CN107330147A (en) | A kind of subway station personnel emergency evacuation emulation mode and system | |
| CN100524363C (en) | Laminated barrier-avoiding method for dynamic body | |
| Ji et al. | A cellular automata model for high-density crowd evacuation using triangle grids | |
| CN105740514A (en) | Computer simulation system for large-size crowd evacuation and method therefor | |
| CN103043084A (en) | Method and system for optimizing urban railway transit transfer | |
| Sarmady et al. | Modeling groups of pedestrians in least effort crowd movements using cellular automata | |
| CN101567017B (en) | Urban-evacuation simulation method based on multi-resolution images | |
| Li et al. | A numerical simulation strategy on occupant evacuation behaviors and casualty prediction in a building during earthquakes | |
| CN108550186B (en) | City scene model layout constraint method based on building specifications | |
| Zhang et al. | Multi-agent based modeling and simulating for evacuation process in stadium | |
| Zhao et al. | The microscopic characteristics of escape behaviours from a three-dimensional lecture theatre under conditions of good and zero visibility | |
| Bradsher | Speedy trains transform China | |
| Zhang et al. | Crowd evacuation simulation using hierarchical deep reinforcement learning | |
| Zhang et al. | Simulation of fire emergency evacuation in metro station based on cellular automata | |
| Wang et al. | A modified floor field model combined with risk field for pedestrian simulation | |
| Dong et al. | Urban rail emergency response using pedestrian dynamics | |
| Ji et al. | Simulation of evacuation characteristics using a 2-dimensional cellular automata model for pedestrian dynamics | |
| Meng et al. | Research and application of metro station evacuation simulation | |
| Liu et al. | Fire evacuation in complex underground space of personnel | |
| CN102693329A (en) | Urban dispersion simulation method based on multiresolution chart | |
| Huang et al. | Simulation of the emergency evacuation about social groups in a complex subway station | |
| Sukor | Pedestrian Movement at the Unpaid Concourse Area in KLCC Train Station | |
| Sun et al. | Pedestrian transfer time optimization of urban rail transit based on ACP approach |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170301 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |