Crowd evacuation simulation based on a hierarchy environmental model

Establishing three different environment models (i.e., single reservoir model, common reservoir model and independent reservoir model), we investigate the evolutional characteristic of the entangled system initially in Bell-like state by the pseudomode method. Through comparing the entanglement decays under the three different environment models, we find that the entangled Bell-like state cos θ |ee> + sin θ |gg> will be kept in the single reservoir model for a time longer than in the other two models. However, the entanglement decay behavior of Bell-like state cos θ |eg> + sin θ |ge> is dependent on the specific environment model. Meanwhile, the comparison of entanglement decay between the above two Bell-like states at the same environment models is performed.

With the advancement of robotics, the importance of service robots in society is increasing. It is crucial for service robots to understand their environment so that they can offer suitable responses to humans. To realize the use of space, robots primarily use an environment model. This paper is focused on the development of an environment model based on human behaviors. In this model, a new neural network structure called dynamic highway networks is applied to recognize humans’ behaviors. In addition, a two-dimensional pose estimator, Laban movement analysis, and the fuzzy integral are employed. With these methods, two new behavior-recognition algorithms are developed, and a method to record the relationship between behavior and environment is proposed. Based on the proposed environmental model, robots can identify abnormal behavior, provide an appropriate response and guide a person toward the desired normal behavior by identifying abnormal behavior. Simulations and experiments justify the proposed method with satisfactory results.

Google Earth Engine (GEE) is an ideal platform for large-scale geospatial agricultural and environmental modeling. However, using GEE to prepare agricultural land use data for geospatial agricultural and environment modeling requires not only the programming skills of GEE APIs but also the knowledge of the data. This paper presents a toolkit AgKit4EE to facilitate the use of the Cropland Data Layer (CDL) products over GEE platform. The toolkit contains a variety of frequently used functions for use of CDL products including crop sequence modeling, crop frequency modeling, confidence layer modeling, and land use change analysis, which can significantly reduce the workload for modelers who perform geospatial agricultural and environmental modeling with CDL data as well as developers who build the GEE-enabled cyberinfrastructure for agricultural land use modeling of the conterminous United States. This presentation was given at the Earth Science Information Partners (ESIP) Summer Meeting held online in July 2020.

In this paper, an environment modeling method with height dimension reduction for unmanned aerial vehicle (UAV) path planning is presented. Based on the traditional grid method, a plane being vertical to yz-plane and including the start point and end point is considered in this method. Comparing the height of this plane and obstacles, the environment model could be set up through re-dividing the plane by grid method. Above idea reduces the dimension of the 3D environment model and ignores the obstacles which are lower than the flying height of UAV. In this way, the accuracy of the proposed environment model method could be increased, and the efficiency of the path planning algorithm could be ensured further. Simulation experiment shows the effectiveness of this environment modeling method by applying A* algorithm for path planning.

This paper considers the problem of building environment models by fusing information gathered by robotic platforms with human perceptual information. Rich environment models are required in real applications for both autonomous operation of robots and to support human decision-making. Hierarchical models are well suited to represent complex environments because they: offer multiple abstractions of the available information to support analysis and decision-making, and permit the incorporation of higher-level human observations. The contributions of this paper are two-fold: (1) development of a probabilistic three-level environment model for distributed information gathering, and (2) experimental demonstration of fully decentralized, cooperative human-robot information gathering using an outdoor sensor network comprised of an unmanned air vehicle, a ground vehicle, and two human operators. Several information exchange patterns are presented which qualitatively demonstrate human-robot information fusion.

Existing crowd evacuation simulation methods commonly face challenges of low efficiency in path planning and insufficient realism in pedestrian movement during the evacuation process. In this study, we propose a novel crowd evacuation path planning approach based on the learning curve–deep deterministic policy gradient (LC‐DDPG) algorithm. The algorithm incorporates dynamic experience pool and a priority experience sampling strategy, enhancing convergence speed and achieving higher average rewards, thus efficiently enabling global path planning. Building upon this foundation, we introduce a double‐layer method for crowd evacuation using deep reinforcement learning. Specifically, within each group, individuals are categorized into leaders and followers. At the top layer, we employ the LC‐DDPG algorithm to perform global path planning for the leaders. Simultaneously, at the bottom layer, an enhanced social force model guides the followers to avoid obstacles and follow the leaders during evacuation. We implemented a crowd evacuation simulation platform. Experimental results show that our proposed method has high path planning efficiency and can generate more realistic pedestrian trajectories in different scenarios and crowd sizes.

Laboratory-based multi-node wireless testbeds are essential to building and experimenting with mobile wireless networks such as MANETs, DTNs, or custom radios and protocols. Several systems based on many-to-many channel emulators have been built, however these systems rely on either a simple deterministic channel model such as free-space path loss, or a general stochastic channel model, where the only input determining channel characteristics is node distance. In order to more thoroughly test radio and protocol performance in a wider variety of scenarios, it is necessary to incorporate site-specific channel characteristics. We have experimented with using RF ray-tracing software to model site-specific real-world environments at the University of Maryland (UMD) campus. We have used these channel model predictions to drive two different types of channel emulator-based wireless testbeds, and have compared results from those testbeds to field tests in the actual locations. Finally, we have experimented with various levels of detail in our environment models to evaluate the payoff, in terms of realism, for spending extra time and resources to build highly-detailed environmental models.

This paper presents a model structure aimed at offering an overview of the various elements of a strategy and exploring their multidimensional effects through time in an efficient way. It treats a strategy as a set of discrete events planned to achieve a certain strategic goal and develops a new form of causal networks as an interfacing component between decision makers and environment models, e.g., life cycle inventory and material flow models. The causal network receives a strategic plan as input in a discrete manner and then outputs the updated parameter sets to the subsequent environmental models. Accordingly, the potential dynamic evolution of environmental systems caused by various strategies can be stepwise simulated. It enables a way to incorporate discontinuous change in models for environmental strategy analysis, and enhances the interpretability and extendibility of a complex model by its cellular constructs. It is exemplified using an urban water management case in Kunming, a major city in Southwest China. By utilizing the presented method, the case study modeled the cross-scale interdependencies of the urban drainage system and regional water balance systems, and evaluated the effectiveness of various strategies for improving the situation of Dianchi Lake.

環境モデルにおける省CO2技術と環境性能評価 （第4報）環境モデルビル実現への高効率化技術の導入プロセス

The Global Navigation Satellite System (GNSS) is currently one of the important tools for landslide monitoring and early warning. However, the majority of GNSS devices are installed in mountainous areas and a variety of vegetation. These harsh environments lead to defective signals at high elevation angles, rendering real-time successive and reliable positioning results for monitoring difficult. In this study, an environmental model derived from signal-to-noise ratio (SNR) is proposed to enhance the precision and convergence time of positioning in harsh environments. A series of experiments are conducted on weighting and ambiguity-fixed models to evaluate performance. The results indicate that the proposed SNR-dependent environment model could lead to a significant improvement in precision and convergence time; with an obtained root mean squared result on the millimeter level, a convergence time of a few seconds, and utilization which could reach 100%, for continuous and reliable positioning results. These results indicate that the proposed SNR-dependent environment model enhances the performance of GNSS monitoring and early warning to provide continuous and reliable positioning results in real-time.

This paper focuses on the cutting-edge and difficult issues in the field of navigation and positioning of service robots. By exploring the technical approach to practical service robot environment modeling and positioning, a new topology SLAM method is proposed. This paper focus on the key technologies involved in 3D SLAM of robots based on large-scale spatial point clouds, including back-end optimization and closed-loop, high-precision sensor calibration technology. Further propose topological map construction strategies, and focus on designing map-generating algorithms based on graphs or tree structures. The research results will provide innovative ideas and practical solutions for environmental modeling and navigation control of service robots, and strongly support technological advances in related research fields based on three-dimensional environmental perception.

This paper presents a localization algorithm for indoor environments. The environmental model is topological and the approach describes how a multimodal perception increases the reliability for the topological localization problem for mobile robots, by using the Bayesian Programming formalism. For the topological framework the fingerprint concept is used. This type of representation permits a reliable and distinctive environment modeling. Experimental results of a mobile robot equipped with a multi sensor system composed of two 180° laser range finders and an omni-directional camera are reported.

This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.

In some environments where manual work cannot be carried out, snake manipulators are instead used to improve the level of automatic work and ensure personal safety. However, the structure of the snake manipulator is diverse, which renders it difficult to establish an environmental model of the control system. It is difficult to obtain an ideal control effect by using the traditional manipulator control method. In view of this, this paper proposes a data-driven snake manipulator control algorithm. After collecting data, the algorithm uses the strong learning and decision-making ability of the deep deterministic strategy gradient to learn these system data. A data-driven controller based on the deep deterministic policy gradient was trained in order to solve the manipulator system control problem when the control system environment model is uncertain or even unknown. The data of simulation experiments show that the control algorithm has good stability and accuracy in the case of model uncertainty.

This paper describes an evolutionary way to lean behaviors of a mobile robot for recognizing environments. We have proposed AEM (Action-based Environment Modeling) which is an appropriate approach for a simple mobile robot to recognize environments, and made experiments using a real robot. The suitable behaviors for AEM have been described by a human designer. However the design is very difficult for them because of the huge search space. Thus we propose the evolutionary design method of such behaviors using genetic algorithm and make experiments in which a robot recognizes the environments with different structures. As results, we found out that the evolutionary approach is promising to automatically acquire behaviors for AEM.