Realistic Crowd Research Articles

EmoiPlanner: Human emotion and intention aware socially acceptable robot navigation in human‐centric environments

AbstractThe deployment of robots in human‐centric environments has significantly increased in recent years. It is crucial for robots to navigate human environments while understanding social norms and personal boundaries to ensure a harmonious coexistence between humans and robots. A socially aware robot should be capable of interpreting and responding appropriately to human cues, expressions, and intentions, thereby fostering trust and confidence among humans. However, prior studies were insufficient or unable to address the navigation challenges in human‐populated environments, as they perceive people as obstacles rather than social agents. Recent studies have utilized proxemic areas that are present in interpersonal interactions for human‐robot interaction scenarios, but they have enforced consistent proxemic areas for social robot navigation. This approach fails to fully capture the highly sophisticated behaviour and preferences of humans. Therefore, we propose a psychologically‐based adaptive proxemic area that fluctuates based on the human's emotional state. Furthermore, we integrate this feature into a reinforcement learning‐based social navigation framework, making our navigation framework robust to the unpredictable affections of humans. Additionally, our navigation framework includes human intention prediction to approximate the future proxemic area, thereby avoiding interference with the path to be taken by individuals. We have named our framework the Human Emotion and Intention Aware Path Planner (EmoiPlanner). Our framework has been subjected to case studies involving realistic crowd navigation scenarios, and the results indicate that it enables robots to navigate through crowds without causing discomfort to pedestrians who exhibit stochastic behaviours and emotional states, while also ensuring efficient path planning.

Novel Multimedia Feature Fusion Classification (Mffc) Model for Sports Game Design Enhancement

Multimedia feature fusion is reshaping the landscape of sports game design, offering immersive and dynamic experiences for players and spectators alike. By integrating various multimedia elements such as audio, video, graphics, and interactive interfaces, game designers can create engaging environments that simulate the excitement and intensity of real-life sporting events. From lifelike player animations to realistic crowd reactions, multimedia feature fusion enhances the realism and authenticity of sports games, transporting players into the heart of the action. Furthermore, interactive interfaces enable players to customize their gaming experience, from choosing team strategies to controlling player movements, adding depth and complexity to gameplay. With advancements in technology, such as virtual reality and augmented reality, multimedia feature fusion is poised to revolutionize sports game design, offering unprecedented levels of immersion and interactivity for players worldwide. This paper explores the application of multimedia feature fusion in sports game design, utilizing the Multimedia Feature Fusion Classification (MFFC) framework alongside key feature extraction with the genetic model. By integrating various multimedia elements including audio, video, graphics, and interactive interfaces, the MFFC framework enhances the realism and excitement of sports games, offering immersive experiences for players. Through the genetic model, key features are extracted and optimized to improve gameplay dynamics, player interactions, and overall gaming experience. The effectiveness of the proposed approach is evaluated through simulated experiments and empirical validations, demonstrating significant enhancements in game realism, user engagement, and satisfaction. Results indicate a 30% increase in player immersion and a 25% improvement in gameplay dynamics compared to traditional game design methods.

Behavioural characteristics influencing walking speed of pedestrians over elevated facilities: A case study of India

Walking speed is an essential parameter used in determining pedestrians' walking behavioural characteristics, the performance of a pedestrian facility, the capacity of the system, and several traffic engineering policy-related applications. While several studies have focussed on understanding walking behavioural patterns over at-grade facilities, there is still a paucity of research on understanding the influence of pedestrians' individual and group behavioural characteristics on walking speed over elevated facilities. This study uses extensive video data collected from different foot-over bridges (FOBs) and skywalks to comprehensively understand walking speed characteristics and their variations over both elevated facilities. The results of the study demonstrated the importance of considering socio-demographic factors with the associative activities involved in walking, group characteristics, and land use type in the estimation of pedestrians’ walking speed. The outcome of the study results would provide relevant policy-related strategies to designers and planners for improving infrastructures, developing realistic crowd behavioural simulation models, and estimating overall crowd dynamics.

Elite darts performance and the social influence of real crowds and simulated crowd noise

While the effect of missing audiences has been studied numerously in team sports with diverse effects, studies on individual performances are rare. The current investigation analyzes performances of professional dart players in (a) the absence of spectators, (b) the presence of real crowds, and (c) artificial crowd noise (simulated crowds) substituting live spectators during the COVID-19 pandemic. Empirical evidence suggests that performances in coordination-based accuracy tasks are negatively impacted by the presence of others. Therefore, we hypothesize that performance of elite darts players deteriorates in the presence of a real audience (RA) in comparison to no audience (NA) and simulated audience (SA). https://dartsorakel.com provided the data of professional tournaments played from 2018 to 2021, which included N = 26,724 individual performances from k = 442 players (98.8% male). How RA and SA impacted checkout percentage (CP) and three-dart average (3DA) was analyzed using separate multilevel models, adding various control variables. Competing with audiences (SA and RA) resulted in decreased CP with an effect of βstand_real = − .20, p < .001, and βstand_sim = − .14, p < .001. 3DA increased with SA, βstand_sim = .08, p < .001, and decreased with RA, βstand_sim = − .07, p < .001. The results show that real crowds appear to have a negative impact on darts performance, yet effect sizes are small.

Multi‐level crowd simulation using social LSTM

AbstractDue to the complex and subtle behaviors of humans, realistic crowd simulation is difficult. To that end, we propose a novel crowd simulation method that can generate realistic crowd animations with behaviors similar to real crowds and model complex pedestrian behaviors at multiple levels using social long short‐term memory (LSTM) neural networks. At the high level, our multi‐level simulation model provides global group navigation while at the low level, it can simulate local individual interactions with collision avoidance. We introduce a data‐driven method using an improved social LSTM for learning local motion decisions from real pedestrian trajectories in order to capture the subtle movements of the crowd. To achieve scalability, we formulate the low‐level and high‐level motion control in a force‐based scheme. Extensive simulation results demonstrate that our method can produce realistic crowd animations in a variety of scenarios. Evaluations in various metrics show that our method produces better crowd behaviors than previous methods.

A Privacy-Preserving Crowd Flow Prediction Framework Based on Federated Learning during Epidemics

Predicting and managing the movement of people in a region during epidemics’ outbreak is an important step in preventing outbreaks. The protection of user privacy during the outbreak has become a matter of public concern in recent years, yet deep learning models based on datasets collected from mobile devices may pose privacy and security issues. Therefore, how to develop an accurate crowd flow prediction while preserving privacy is a significant problem to be solved, and there is a tradeoff between these two objectives. In this paper, we propose a privacy-preserving mobility prediction framework via federated learning (CFPF) to solve this problem without significantly sacrificing the prediction performance. In this framework, we designed a deep and embedding learning approach called “Multi-Factors CNN-LSTM” (MFCL) that can help to explicitly learn from human trajectory data (weather, holidays, temperature, and POI) during epidemics. Furthermore, we improve the existing federated learning framework by introducing a clustering algorithm to classify clients with similar spatio-temporal characteristics into the same cluster, and select servers at the center of the cluster as edge central servers to integrate the optimal model for each cluster and improve the prediction accuracy. To address the privacy concerns, we introduce local differential privacy into the FL framework which can facilitate collaborative learning with uploaded gradients from users instead of sharing users’ raw data. Finally, we conduct extensive experiments on a realistic crowd flow dataset to evaluate the performance of our CFPF and make a comparison with other existing models. The experimental results demonstrate that our solution can not only achieve accurate crowd flow prediction but also provide a strong privacy guarantee at the same time.

An improved optimization model for crowd evacuation considering individual exit choice preference

AbstractGuidance‐assisted crowd evacuation is a process of combining individual exit choice behavior with managers' exit assignment control. The knowledge of individual exit choice preference is of great significance for optimizing global exit assignment planning. This study proposes an improved optimization model for crowd evacuation by integrating the individual‐level exit choice preference analysis with system‐level exit assignment optimization to represent more realistic crowd evacuation decisions. First, the impact factors of individual exit choice behavior are considered in a mixed logit model to predict the probability of each individual choosing each exit in specific situations. Second, a preference‐based exit filtering strategy is designed to analyze the sensible alternative exits for individuals or groups in multi‐scale evacuation cells. Finally, to pursue optimal exit assignment planning, a multi‐objective particle swarm optimization algorithm and an improved social force model are adopted to simulate the process of crowd evacuation and evaluate the performance of the specific exit assignment plans. The case study of an outdoor multiple‐exit scenario in Xi'an, China, indicates that the proposed model can help managers to understand the heterogeneity of individual evacuation behaviors. Furthermore, it will support more reliable and realistic evacuation decisions in real‐life situations than conventional plans that typically implement the top‐n strategy.

ORCANet: Differentiable multi‐parameter learning for crowd simulation

AbstractRealistic crowd simulation has always been an important research field in computer graphics. While both agent‐based motion models and data‐driven behavior models have made some progress, they are still suffering from either huge effort of multi‐parameter tuning or limited realistic motion. In this article, we propose a novel and differentiable multi‐parameter learning method for crowd simulation, which is called ORCANet. The main idea is to learn from real data and inverse evaluating the multi‐parameter for subsequent simulation. ORCANet uses classic optimal reciprocal collision avoidance (ORCA) as a basic motion model which is integrated into the deep learning framework. Addressing the feature of linear programming and non‐differentiable operation, a Gaussian kernel is added to approximate the role of neighbor distance in collision avoidance, which turns the original discrete operation into a fully differentiable forward simulation. Furthermore, we leverage ORCANet to optimize the multi‐parameter combination in synthetic and real‐world datasets. ORCANet is proved to rapidly converge to correct parameter values and regenerate the input synthetic sequence. Moreover, experiments on real‐world datasets by the metric of pedestrian trajectories verified that a more realistic crowd simulation has been generated through ORCANet.

Modelling and simulating serpentine group behaviour in crowds using modified social force model

Crowd dynamics has emerged as an important topic of investigation in recent years. Several studies have been conducted to better understand the underlying factors that can influence crowd dynamics and lead to risky situations. Particularly, field studies are essential for realistically capturing the dynamics. This paper attempts to uncover one intriguing behaviour observed in the world’s largest mass religious gathering Kumbh Mela-2016, held in Ujjain, India. The authors define this behaviour, where groups attempt to overtake the others in the crowd, form flexible chains, and not allow non-group members to penetrate through them, as serpentine group behaviour. This behaviour has been modelled and simulated using a modified social force model which has been developed in this work. This can aid in the development of a realistic crowd simulation model that can handle such unique crowd behaviours and help manage large crowds and ensure safe movement.

DeepORCA: Realistic crowd simulation for varying scenes

AbstractCrowd simulation is a challenging problem, aiming to generate realistic pedestrians motions in virtual environment. Nowadays, ORCA is a widely used simulation algorithm in practice because of its stable and efficient performance. However, this algorithm cannot regenerate continuity and diversity of pedestrian motions in real data, leading to defects in motion fidelity. Otherwise, trajectory prediction methods based on deep learning have progressed in real pedestrians movement patterns mining. However, they are rarely applied in simulation due to the lack of ability to avoid collision and adapt to manufactured scenarios. Our work proposes a simulation method DeepORCA that integrates ORCA with a CVAE‐based velocity probability generator, which can model motion continuity, variable intentions, and scene semantics. Moreover, DeepORCA converts the velocity optimization into quadratic programming, which accelerates the calculation while maintaining the collision‐avoidance ability of ORCA. In the experiments of real and artificial scenes, our method produces more realistic crowd simulation results than ORCA quantitatively and qualitatively, while keeps the computational efficiency at the same order of magnitude.

The One-Man-Crowd: Single User Generation of Crowd Motions Using Virtual Reality.

Crowd motion data is fundamental for understanding and simulating realistic crowd behaviours. Such data is usually collected through controlled experiments to ensure that both desired individual interactions and collective behaviours can be observed. It is however scarce, due to ethical concerns and logistical difficulties involved in its gathering, and only covers a few typical crowd scenarios. In this work, we propose and evaluate a novel Virtual Reality based approach lifting the limitations of real-world experiments for the acquisition of crowd motion data. Our approach immerses a single user in virtual scenarios where he/she successively acts each crowd member. By recording the past trajectories and body movements of the user, and displaying them on virtual characters, the user progressively builds the overall crowd behaviour by him/herself. We validate the feasibility of our approach by replicating three real experiments, and compare both the resulting emergent phenomena and the individual interactions to existing real datasets. Our results suggest that realistic collective behaviours can naturally emerge from virtual crowd data generated using our approach, even though the variety in behaviours is lower than in real situations. These results provide valuable insights to the building of virtual crowd experiences, and reveal key directions for further improvements.

An Agent-Based Simulation Model to Evaluate Contacts, Layout, and Policies in Entrance, Exit, and Seating in Indoor Activities Under a Pandemic Situation

The outbreak of the novel coronavirus SARS-CoV2 has dramatically changed the world and has been a severe health threat in 2020 and 2021. In this article, an agent-based simulation model of pedestrian dynamics is proposed for classroom-type indoor spaces (e.g., classroom, auditorium, food court, and meeting room), which will help organizations such as universities to evaluate alternative policies (namely entrance and exit policy, seating policy, and room layout) concerning the contact-caused risk associated with activities in such places during a pandemic situation. In particular, the proposed work focuses on solving the indoor seat allocation and traffic movement problem while practicing appropriate physical distancing measures. The proposed seating policy evaluates the distance of a seat from the doors and pathways facilitating the evaluation of contact-caused risk associated with the pathway and indoor area movement. Various statistics from two perspectives, risk, and logistics, are reported in the simulation results. The risk metrics used in evaluating different policies include average exposure duration and an average number of contacts with others. To develop a highly realistic crowd simulation considering physical distancing and human intervention nature, deadlock detection and resolution mechanisms are incorporated. From this study, it has been observed that the proposed social distancing (SD) seating policy and zonal exit policy can significantly reduce the contact number and exposure duration at a higher occupancy level. The proposed work helps the organizational policymakers to evaluate different policies and ensure the safe operation of the organizations under pandemic situations. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This article was motivated to ensure safer and efficient operations within indoor facilities by evaluating contact-caused risks and entrance/exit policies during a pandemic situation like coronavirus disease (COVID-19). Most of the recent works related to COVID-19 disease propagation focus on the evaluation of disease transmission at an organization level, however, limited studies focus on the operational aspect of indoor facilities within the organization. To bridge this gap, this article utilizes an agent-based modeling approach to model and understand the pedestrian dynamics in the classroom-like facilities considering physical distancing, seat assignment, and entry/exit policies. Comprehensive simulation modeling and analysis allows the amalgamation of real data, including layout, class schedules, seating arrangement, and allowable capacity to perform various what-if analyses under different policies. This article proposes and evaluates seating assignment based on the associated number and duration of contacts during movements in the pathway and entrance/ exit area of a confined space. In addition, this work evaluates different indoor layouts (e.g., classroom, meeting room, and office) and exit policies (e.g., zonal and non-zonal) at different occupancy levels for appropriate decision support. The proposed approach will aid organizations (e.g., educational institutions, corporate offices, and recreational facilities) to evaluate necessary policies (namely entrance and exit policy, seating policy, and room layout) for safe indoor operations with respect to the minimum contact-caused risk associated with the activities. As a future direction, the outputs from the proposed work can be utilized to obtain the realistic input parameters needed for organization-wide disease propagation models, which will provide decision support at an organizational level.

Data-driven Crowd Modeling Techniques: A Survey

Data-driven crowd modeling has now become a popular and effective approach for generating realistic crowd simulation and has been applied to a range of applications, such as anomaly detection and game design. In the past decades, a number of data-driven crowd modeling techniques have been proposed, providing many options for people to generate virtual crowd simulation. This article provides a comprehensive survey of these state-of-the-art data-driven modeling techniques. We first describe the commonly used datasets for crowd modeling. Then, we categorize and discuss the state-of-the-art data-driven crowd modeling methods. After that, data-driven crowd model validation techniques are discussed. Finally, six promising future research topics of data-driven crowd modeling are discussed.

Crowd-Sourced Identification of Characteristics of Collective Human Motion.

Crowd simulations are used extensively to study the dynamics of human collectives. Such studies are underpinned by specific movement models, which encode rules and assumptions about how people navigate a space and handle interactions with others. These models often give rise to macroscopic simulated crowd behaviours that are statistically valid, but which lack the noisy microscopic behaviours that are the signature of believable real crowds. In this article, we use an existing Turing test for crowds to identify realistic features of real crowds that are generally omitted from simulation models. Our previous study using this test established that untrained individuals have difficulty in classifying movies of crowds as real or simulated, and that such people often have an idealised view of how crowds move. In this follow-up study (with new participants) we perform a second trial, which now includes a training phase (showing participants movies of real crowds). We find that classification performance significantly improves after training, confirming the existence of features that allow participants to identify real crowds. High-performing individuals are able to identify the features of real crowds that should be incorporated into future simulations if they are to be considered realistic.

A hybrid data gathering and agent based cognitive architecture for realistic crowd simulations

ABSTRACT This paper proposes a realistic agent-based framework for crowd simulations that can encompass the input phase, the simulation process phase, and the output evaluation phase. In order to achieve this gathering, the three types of real-world data (physical, mental and visual) need to be considered. However, existing research has not used all the three data types to develop an agent-based framework since current data gathering methods are unable to collect all the three types. This paper introduces anew hybrid data gathering approach using a combination of virtual reality and questionnaires to gather all three data types. The data collected are incorporated into the simulation model to provide realism and flexibility. The performance of the framework is evaluated and benchmarked to prove the robustness and effectiveness of our framework. Various types of settings (self-set parameters and random parameters) are simulated to demonstrate that the framework can produce real-world like simulation.

Diego Armando Maradona i Ameryka Łacińska – historie splecione

On November 25th, 2020, Diego Armando Maradona, the legend of Argentine, Latin American and world football, passed away. Although his life has aroused controversy, being a series of bothspectacular ups and painful downs, the fans never turned away from him and Maradona’s funeral, despite the ongoing pandemic, gathered real crowds. This text attempts to explain the phenomenon of Diego Armando Maradona by presenting his story in relation to the history of Latin America and proving that the Argentine attacker was a reflection of both the advantages and the problems of the region he came from and with which he identified himself.

MACROSCOPIC FUNDAMENTAL FLOW DIAGRAMS OF A SPIRITUALLY MOTIVATED CROWD

Managing and monitoring large crowds pose a challenge to the crowd management authorities. Understanding the crowd dynamics in terms of its macroscopic parameters and its application to assess the maximum number of people likely to gather at a location or the number of people to be allowed to pass a point can go a long way in preventing situations of crowd risk. This paper presents a comparison of the fundamental diagrams of pedestrian flow at different locations of Kumbh mela and brings out differences in the flow patterns between a general crowd and a spiritually motivated crowd. The effect of spiritual motivation is reflected in terms of higher speeds of pedestrians at some locations and continuous flow despite higher densities. These results fill a significant research gap in the literature by highlighting the unique characteristics of spiritual crowd flows that must be incorporated for simulating a realistic crowd.

Agent Based Modelling and Simulation of Pedestrian Crowds in Panic Situations

The increasing occurrence of panic stampedes during mass events has motivated studying the impact of panic on crowd dynamics. Understanding the collective behaviors of panic stampedes is essential to reducing the risk of deadly crowd disasters. In this work, we use an agent-based formulation to model the collective human behavior in such crowd dynamics. We investigate the impact of panic behavior on crowd dynamics, as a specific form of collective behavior, by introducing a contagious panic parameter. The proposed model describes the intensity and spread of panic through the crowd. The corresponding panic parameter impacts each individual to represent a different variety of behaviors that can be associated with panic situations such as escaping danger, clustering, and pushing. Simulation results show contagious panic and pushing behavior, resulting in a more realistic crowd dynamics model.

A review on crowd simulation and modeling

Crowd simulation has emerged in the last decade as a widely used method of visual effects, computer games, and urban planning, etc. The improvement of hardware performance and the urgent need of special effect lead to an unprecedented wave of crowd simulation studies. This paper reports a review of crowd simulation models from traditional methods to recent methods (e.g. group simulation, emotion contagion). Traditional models can simulate general crowd dynamics which have the advantages of both microscopic and macroscopic models. The recent studies of crowd simulation from group simulation to social psychology crowds are possible to simulate realistic crowds. The purpose of this review is to introduce commonly used crowd simulation methods for newcomers to this field by making a systematic literature review, discussions and analysis of different models. The results reveal the traditional models can simulate most of the normal crowds, but lack expressiveness for special groups which needs to be solved urgently in the current applications, particularly on visual effects and urban planning. Group simulation and emotion contagion could improve the simulation realism, but it also needs to be improved in computation cost and model optimization. Also, future research directions are suggested aiming to develop new applications focused on more realistic, natural and efficient crowd simulation.

Crowd Modeling and Simulation for Safer Building Design

Crowd modeling and simulation are very important in the investigation and study of the dynamics of a crowd. They can be used not only to understand the behavior of a crowd in different environments, but also in risk assessment of spaces and in designing spaces that are safer for crowds, especially during emergency evacuations. This paper provides an overview of the use of the crowd simulation model for three main purposes; (1) as a modeling tool to simulate behavior of a crowd in different environments, (2) as a risk assessment tool to assess the risk posed in the environment, and (3) as an optimization tool to optimize the design of a building or space so as to ensure safer crowd movement and evacuation. Result shows that a simulation using the magnetic force model with a pathfinding feature provides a realistic crowd simulation and the use of ABC optimization can reduce evacuation time and improve evacuation comfort. This paper is expected to provide readers with a clearer idea on how crowd models are used in ensuring safer building planning and design.