CN112991544A - Group evacuation behavior simulation method based on panoramic image modeling - Google Patents
Group evacuation behavior simulation method based on panoramic image modeling Download PDFInfo
- Publication number
- CN112991544A CN112991544A CN202110424096.4A CN202110424096A CN112991544A CN 112991544 A CN112991544 A CN 112991544A CN 202110424096 A CN202110424096 A CN 202110424096A CN 112991544 A CN112991544 A CN 112991544A
- Authority
- CN
- China
- Prior art keywords
- individual
- panoramic
- model
- indoor
- behavior
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004088 simulation Methods 0.000 title claims abstract description 19
- 230000006399 behavior Effects 0.000 claims abstract description 63
- 230000002787 reinforcement Effects 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims abstract description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000000638 stimulation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Computer Graphics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Computer Security & Cryptography (AREA)
- Educational Administration (AREA)
- Alarm Systems (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a group evacuation behavior simulation method based on panoramic image modeling, which relates to the technical field of simulation and comprises the following steps: acquiring data in real time by using indoor environment acquisition equipment to acquire indoor panoramic map data of the intelligent building; fusing correction map data by using a BIM building information model of the intelligent building to generate a three-dimensional digital panoramic model; adding all devices of the intelligent building into the panoramic model according to the actual positions; the method comprises the steps that a positioning device is worn on an individual entering the intelligent building, and an individual movement track is obtained; setting individual types and behaviors under the panoramic model based on individual motion tracks, setting a Reward function based on the individual behaviors and the current environment, and then training the individual behavior model by utilizing an A3C reinforcement learning algorithm; when an emergency is simulated under the panoramic model, group evacuation behaviors are simulated by utilizing a plurality of individual behavior models based on individual position data of a real environment to obtain an optimal group evacuation scheme. The invention can improve the safety index of population evacuation.
Description
Technical Field
The invention relates to the technical field of analog simulation, in particular to a population evacuation behavior simulation method based on panoramic image modeling.
Background
In recent years, the deep Learning technology has been developed rapidly, and there are important breakthroughs that algorithms such as Supervised Learning (Supervised Learning), Unsupervised Learning (Unsupervised Learning) and Reinforcement Learning (Reinforcement Learning) have been obtained, and the commercialization speed of the deep Learning technology exceeds expectations, so that the deep Learning technology has been applied to many fields such as computer vision, image and video analysis, voice recognition and natural language processing, and the deep Learning brings subversive changes to the whole society.
Reinforcement learning, an important deep learning method, is a trial and error method for describing and solving the problem that an agent (agent) achieves maximum return or achieves a specific target through learning strategies in the interaction process with the environment. Through the task of interaction between the agent of the agent and the environment, under the stimulation of reward or punishment given by the environment, the agent gradually forms expectation to the stimulation, continuously learns to make optimal actions under different environments, and generates habitual behaviors which can obtain the maximum benefit. By utilizing the perception generation strategies, higher machine intelligence can be created, and the performance of people is better than that of people in applications such as competitive sports, games, robot control, work scheduling and the like on complex tasks at present.
Building Information Modeling, referred to as BIM for short, represents a Building Information model, and the BIM integrates engineering data models of various related Information of construction projects on the basis of a three-dimensional digital technology. With the continuous development of image processing technology, sensing technology and multimedia technology, the virtual simulation effect of a computer is more and more real, and BIM information is combined with panoramic images and sensing data of the Internet of things to form a brand-new digital model. With the increasing complexity of building structures, higher requirements are put forward on the safety treatment of emergencies such as fire, power failure, accidents and the like, in particular to the safety evacuation of building groups. Under the circumstance, how to effectively utilize the reinforcement learning technology and combine the simulation environment of panoramic image modeling to simulate more real group evacuation behaviors and discover the potential safety hazards of buildings in time becomes a problem to be solved urgently.
Disclosure of Invention
Aiming at the requirements and the defects of the prior art development, the invention provides a population evacuation behavior simulation method based on panoramic image modeling.
The invention discloses a group evacuation behavior simulation method based on panoramic image modeling, which adopts the following technical scheme for solving the technical problems:
a group evacuation behavior simulation method based on panoramic image modeling comprises the following steps:
s1, acquiring data in real time by using indoor environment acquisition equipment to acquire indoor panoramic map data of the intelligent building;
s2, carrying out fusion correction on the acquired indoor panoramic map data by using a BIM building information model of the intelligent building to generate a three-dimensional digital panoramic model;
s3, adding the Internet of things equipment and the control equipment of the intelligent building into the three-dimensional digital panoramic model according to the actual positions, and simultaneously displaying data acquired by the indoor environment acquisition equipment in real time into the three-dimensional digital panoramic model;
step S4, wearing a positioning device on an individual entering the intelligent building to obtain the motion track of the individual;
s5, setting individual types and behaviors under a three-dimensional digital panoramic model based on the acquired individual motion trail, setting a Reward function based on the individual behaviors and the current environment, and then training an individual behavior model by utilizing an A3C reinforcement learning algorithm;
and step S6, simulating the emergency A under the three-dimensional digital panoramic model, and simulating group evacuation behaviors by utilizing a plurality of individual behavior models based on the individual position data of the real environment to obtain an optimal group evacuation scheme.
Optionally, the related indoor environment acquisition equipment comprises a laser radar, a high-definition panoramic camera and an indoor positioning device;
the indoor environment acquisition equipment takes the mobile robot as a carrier to acquire indoor panoramic map data of the intelligent building in real time.
Further optionally, the laser radar is a radar system for detecting two characteristic quantities of the position and the speed of the target by emitting laser beams, and is used for obtaining point cloud data by scanning an indoor environment of the intelligent building.
Further optionally, the indoor environment image data of wisdom building is responsible for gathering to related high definition panorama camera.
Further optionally, the related indoor positioning device positions the data acquired by the high-definition panoramic camera and the laser radar in real time.
Further optionally, the mobile robot that relates carries out the free removal as the carrier in the wisdom building to integrate laser radar, high definition panorama camera and the data that indoor positioner gathered, acquire the indoor panorama map data of wisdom building.
Optionally, the internet of things equipment in the intelligent building comprises an intelligent building subsystem based on lighting, security, power distribution and metering, HVAC and electrical control.
Optionally, the specific operation process of executing step S5 to train the individual behavior model includes:
s5.1, acquiring the current virtual image of the individual through indoor environment acquisition equipment;
s5.2, based on the current virtual image, calculating an incentive result by an A3C reinforcement learning algorithm according to the next step of the individual behavior and a Reward function;
s5.3, repeatedly executing the steps S5.1-S5.2 to obtain individual behaviors and current virtual images under different environments for multiple times, and then counting Reward results obtained by a Reward function under different motion tracks;
and S5.4, selecting a motion track corresponding to the maximum reward result, and training an individual behavior model based on a neural network by an A3C reinforcement learning algorithm.
Optionally, in step S5, the type and behavior of the individual are set based on five basic data of height, sex, age, weight and movement track of the individual.
Preferably, a plurality of POI interest points are set in the three-dimensional digital panoramic model as emergency occurrence points, and the group evacuation behaviors under a plurality of events are simulated by using a plurality of individual behavior models based on the individual position data of the real environment to obtain an optimal group evacuation scheme.
Compared with the prior art, the population evacuation behavior simulation method based on panoramic image modeling has the beneficial effects that:
(1) according to the intelligent building crowd evacuation method, a robot carrier is used, a laser radar, a high-definition camera and an indoor positioning device are used as indoor environment acquisition equipment, indoor panoramic map data of the intelligent building are acquired in real time, a BIM building information model is combined, fusion correction is carried out on the indoor panoramic map data, a three-dimensional digital panoramic model is generated, an individual behavior model is trained in the three-dimensional digital panoramic model through an A3C reinforcement learning algorithm, when the three-dimensional digital panoramic model simulates an emergency, crowd evacuation behaviors are simulated by using a plurality of individual behavior models, an optimal crowd evacuation scheme is obtained, and meanwhile potential safety hazards in the intelligent building can be found;
(2) according to the invention, more diversified individual behavior models can be obtained by increasing individual types, so that the accuracy of simulation can be improved conveniently.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the technical scheme, the technical problems to be solved and the technical effects of the present invention more clearly apparent, the following technical scheme of the present invention is clearly and completely described with reference to the specific embodiments.
The first embodiment is as follows:
with reference to fig. 1, the present embodiment provides a method for simulating a group evacuation behavior based on panoramic image modeling, which includes the following steps:
and S1, acquiring data in real time by using the indoor environment acquisition equipment to acquire indoor panoramic map data of the intelligent building. The indoor environment acquisition equipment comprises a laser radar, a high-definition panoramic camera and an indoor positioning device; the laser radar is a radar system which emits laser beams to detect two characteristic quantities of the position and the speed of a target and is used for scanning the indoor environment of the intelligent building to obtain point cloud data; the high-definition panoramic camera is used for collecting indoor environment image data of the intelligent building; and the indoor positioning device positions the data collected by the high-definition panoramic camera and the laser radar in real time.
In the step, the mobile robot is used as a carrier of indoor environment acquisition equipment, free movement is carried out in the smart building, data acquired by the laser radar, the high-definition panoramic camera and the indoor positioning device are integrated, and indoor panoramic map data of the smart building are acquired.
And S2, carrying out fusion correction on the acquired indoor panoramic map data by using a BIM building information model of the intelligent building to generate a three-dimensional digital panoramic model.
And S3, adding the Internet of things equipment and the control equipment of the intelligent building into the three-dimensional digital panoramic model according to the actual positions, and simultaneously displaying the data acquired by the indoor environment acquisition equipment in real time into the three-dimensional digital panoramic model.
In this step, the thing networking equipment among the wisdom building includes the wisdom building subsystem based on illumination, security protection, distribution and measurement, HVAC, electrical apparatus control.
And step S4, wearing a positioning device on the individual entering the intelligent building to acquire the motion trail of the individual.
S5, setting individual types and behaviors under a three-dimensional digital panoramic model based on the acquired individual motion trail, setting a Reward function based on the individual behaviors and the current environment, and then training the individual behavior model by using an A3C reinforcement learning algorithm, wherein the specific operation process comprises the following steps:
s5.1, acquiring the current virtual image of the individual through indoor environment acquisition equipment;
s5.2, based on the current virtual image, calculating an incentive result by an A3C reinforcement learning algorithm according to the next step of the individual behavior and a Reward function;
s5.3, repeatedly executing the steps S5.1-S5.2 to obtain individual behaviors and current virtual images under different environments for multiple times, and then counting Reward results obtained by a Reward function under different motion tracks;
and S5.4, selecting a motion track corresponding to the maximum reward result, and training an individual behavior model based on a neural network by an A3C reinforcement learning algorithm.
In the step, the type and the behavior of the individual are set based on five basic data of the height, the sex, the age, the weight and the movement track of the individual.
And step S6, simulating the emergency A under the three-dimensional digital panoramic model, and simulating group evacuation behaviors by utilizing a plurality of individual behavior models based on the individual position data of the real environment to obtain an optimal group evacuation scheme.
Certainly, a plurality of POI interest points can be set in the three-dimensional digital panoramic model as emergency occurrence points, and the group evacuation behaviors under a plurality of events are simulated by using a plurality of individual behavior models based on the individual position data of the real environment, so as to obtain the optimal group evacuation scheme.
In summary, by adopting the panoramic image modeling-based group evacuation behavior simulation method, the group evacuation behavior under an emergency can be simulated through the three-dimensional digital panoramic model and the trained individual behavior model, and the potential safety hazard of the intelligent building can be found in time on the premise of improving the group evacuation safety index.
The principles and embodiments of the present invention have been described in detail using specific examples, which are provided only to aid in understanding the core technical content of the present invention. Based on the above embodiments of the present invention, those skilled in the art should make any improvements and modifications to the present invention without departing from the principle of the present invention, and therefore, the present invention should fall into the protection scope of the present invention.
Claims (10)
1. A group evacuation behavior simulation method based on panoramic image modeling is characterized by comprising the following steps:
s1, acquiring data in real time by using indoor environment acquisition equipment to acquire indoor panoramic map data of the intelligent building;
s2, carrying out fusion correction on the acquired indoor panoramic map data by using a BIM building information model of the intelligent building to generate a three-dimensional digital panoramic model;
s3, adding the Internet of things equipment and the control equipment of the intelligent building into the three-dimensional digital panoramic model according to the actual positions, and simultaneously displaying data acquired by the indoor environment acquisition equipment in real time into the three-dimensional digital panoramic model;
step S4, wearing a positioning device on an individual entering the intelligent building to obtain the motion track of the individual;
s5, setting individual types and behaviors under a three-dimensional digital panoramic model based on the acquired individual motion trail, setting a Reward function based on the individual behaviors and the current environment, and then training an individual behavior model by utilizing an A3C reinforcement learning algorithm;
and step S6, simulating the emergency A under the three-dimensional digital panoramic model, and simulating group evacuation behaviors by utilizing a plurality of individual behavior models based on the individual position data of the real environment to obtain an optimal group evacuation scheme.
2. The population evacuation behavior simulation method based on panoramic image modeling according to claim 1, wherein the indoor environment acquisition equipment comprises a laser radar, a high-definition panoramic camera and an indoor positioning device;
indoor environment collection equipment uses mobile robot as the carrier, acquires the indoor panorama map data of wisdom building in real time.
3. The population evacuation behavior simulation method based on panoramic image modeling according to claim 2, wherein the lidar is a radar system that emits a laser beam to detect two characteristic quantities, namely a position and a speed of a target, and is used for obtaining point cloud data by scanning an indoor environment of the smart building.
4. The population evacuation behavior simulation method based on panoramic image modeling according to claim 3, wherein the high-definition panoramic camera is responsible for collecting indoor environment image data of the smart building.
5. The method of claim 4, wherein the indoor positioning device positions the data collected by the high-definition panoramic camera and the lidar in real time.
6. The population evacuation behavior simulation method based on panoramic image modeling according to claim 5, wherein the mobile robot is used as a carrier and moves freely in the smart building, and integrates data collected by the laser radar, the high-definition panoramic camera and the indoor positioning device to obtain indoor panoramic map data of the smart building.
7. The population evacuation behavior simulation method based on panoramic image modeling as claimed in claim 1, wherein the internet of things devices in the smart building comprise smart building subsystems based on lighting, security, power distribution and metering, HVAC, and electrical control.
8. The method of claim 1, wherein the specific operation process of performing the step S5 to train the individual behavior model comprises:
s5.1, acquiring the current virtual image of the individual through indoor environment acquisition equipment;
s5.2, based on the current virtual image, calculating an incentive result by an A3C reinforcement learning algorithm according to the next step of the individual behavior and a Reward function;
s5.3, repeatedly executing the steps S5.1-S5.2 to obtain individual behaviors and current virtual images under different environments for multiple times, and then counting Reward results obtained by a Reward function under different motion tracks;
and S5.4, selecting a motion track corresponding to the maximum reward result, and training an individual behavior model based on a neural network by an A3C reinforcement learning algorithm.
9. The method of claim 1, wherein in step S5, the type and behavior of the individual is set based on five basic data of the individual' S height, sex, age, weight and movement track.
10. The method according to claim 1, wherein a plurality of POI interest points are set in the three-dimensional digital panoramic model as emergency occurrence points, and the individual behavior models are used to simulate the group evacuation behavior under a plurality of events based on the individual position data of the real environment, so as to obtain the optimal group evacuation scheme.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110424096.4A CN112991544A (en) | 2021-04-20 | 2021-04-20 | Group evacuation behavior simulation method based on panoramic image modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110424096.4A CN112991544A (en) | 2021-04-20 | 2021-04-20 | Group evacuation behavior simulation method based on panoramic image modeling |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112991544A true CN112991544A (en) | 2021-06-18 |
Family
ID=76341220
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110424096.4A Pending CN112991544A (en) | 2021-04-20 | 2021-04-20 | Group evacuation behavior simulation method based on panoramic image modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112991544A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113569645A (en) * | 2021-06-28 | 2021-10-29 | 广东技术师范大学 | Track generation method, device and system based on image detection |
CN114608549A (en) * | 2022-05-10 | 2022-06-10 | 武汉智会创新科技有限公司 | Building measurement method based on intelligent robot |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679275A (en) * | 2017-08-31 | 2018-02-09 | 中国建筑第八工程局有限公司 | A kind of fire-fighting life-saving evacuation analogy method based on BIM technology |
WO2018212918A1 (en) * | 2017-05-18 | 2018-11-22 | Microsoft Technology Licensing, Llc | Hybrid reward architecture for reinforcement learning |
CN110632931A (en) * | 2019-10-09 | 2019-12-31 | 哈尔滨工程大学 | Mobile robot collision avoidance planning method based on deep reinforcement learning in dynamic environment |
CN110737989A (en) * | 2019-10-18 | 2020-01-31 | 中国科学院深圳先进技术研究院 | parallel intelligent emergency cooperation method, system and electronic equipment |
CN110750096A (en) * | 2019-10-09 | 2020-02-04 | 哈尔滨工程大学 | Mobile robot collision avoidance planning method based on deep reinforcement learning in static environment |
CN111625989A (en) * | 2020-03-18 | 2020-09-04 | 北京联合大学 | Intelligent vehicle influx method and system based on A3C-SRU |
CN111881625A (en) * | 2020-07-30 | 2020-11-03 | 青岛理工大学 | Crowd evacuation simulation method and system based on deep reinforcement learning |
-
2021
- 2021-04-20 CN CN202110424096.4A patent/CN112991544A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018212918A1 (en) * | 2017-05-18 | 2018-11-22 | Microsoft Technology Licensing, Llc | Hybrid reward architecture for reinforcement learning |
CN107679275A (en) * | 2017-08-31 | 2018-02-09 | 中国建筑第八工程局有限公司 | A kind of fire-fighting life-saving evacuation analogy method based on BIM technology |
CN110632931A (en) * | 2019-10-09 | 2019-12-31 | 哈尔滨工程大学 | Mobile robot collision avoidance planning method based on deep reinforcement learning in dynamic environment |
CN110750096A (en) * | 2019-10-09 | 2020-02-04 | 哈尔滨工程大学 | Mobile robot collision avoidance planning method based on deep reinforcement learning in static environment |
CN110737989A (en) * | 2019-10-18 | 2020-01-31 | 中国科学院深圳先进技术研究院 | parallel intelligent emergency cooperation method, system and electronic equipment |
CN111625989A (en) * | 2020-03-18 | 2020-09-04 | 北京联合大学 | Intelligent vehicle influx method and system based on A3C-SRU |
CN111881625A (en) * | 2020-07-30 | 2020-11-03 | 青岛理工大学 | Crowd evacuation simulation method and system based on deep reinforcement learning |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113569645A (en) * | 2021-06-28 | 2021-10-29 | 广东技术师范大学 | Track generation method, device and system based on image detection |
CN113569645B (en) * | 2021-06-28 | 2024-03-22 | 广东技术师范大学 | Track generation method, device and system based on image detection |
CN114608549A (en) * | 2022-05-10 | 2022-06-10 | 武汉智会创新科技有限公司 | Building measurement method based on intelligent robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11779837B2 (en) | Method, apparatus, and device for scheduling virtual objects in virtual environment | |
CN110781765B (en) | Human body posture recognition method, device, equipment and storage medium | |
Kim et al. | Interactive and adaptive data-driven crowd simulation | |
CN109543285B (en) | Crowd evacuation simulation method and system integrating data driving and reinforcement learning | |
CN112991544A (en) | Group evacuation behavior simulation method based on panoramic image modeling | |
CN106548675A (en) | Virtual military training method and device | |
Ghosh et al. | Sad-gan: Synthetic autonomous driving using generative adversarial networks | |
CN108376198B (en) | Crowd simulation method and system based on virtual reality | |
CN108362284A (en) | A kind of air navigation aid based on bionical hippocampus cognitive map | |
Mo et al. | Terra: A smart and sensible digital twin framework for robust robot deployment in challenging environments | |
JP7054255B2 (en) | Virtual intelligence and optimization with multi-source, real-time, context-aware real-world data | |
CN112106060A (en) | Control strategy determination method and system | |
CN112348285A (en) | Crowd evacuation simulation method in dynamic environment based on deep reinforcement learning | |
Mastorakis | Human-like machine learning: limitations and suggestions | |
Zhang et al. | Crowd evacuation simulation using hierarchical deep reinforcement learning | |
CN110956684A (en) | Crowd movement evacuation simulation method and system based on residual error network | |
Zhou et al. | Human-behaviour-based social locomotion model improves the humanization of social robots | |
CN108629121B (en) | Virtual reality crowd simulation method and system based on terrorist valley effect avoidance | |
CN114863352B (en) | Personnel group behavior monitoring method based on video analysis | |
Hu et al. | A pattern-based modeling framework for simulating human-like pedestrian steering behaviors | |
Sakellariou et al. | Crowd formal modelling and simulation: The sa'yee ritual | |
Peng et al. | Single shot state detection in simulation-based laparoscopy training | |
Quattrocchi et al. | Put Your PPE on: A Tool for Synthetic Data Generation and Related Benchmark in Construction Site Scenarios. | |
CN113848750A (en) | Two-wheeled robot simulation system and robot system | |
CN113255152A (en) | Rail transit operation management simulation training system based on VR interaction technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
RJ01 | Rejection of invention patent application after publication |