Crowd simulation is crucial for urban planning, traffic management, public safety, and immersive environments. A fundamental challenge is capturing adaptive human behaviors that evolve dynamically with social interactions and task demands. Recently, physics-informed neural networks (PINNs) seamlessly integrate interpretable physics-based models with flexible data-driven learning, significantly enhancing simulation realism. However, current PINN-based methods typically rely on rigid representations of pedestrian perceptions and static task priorities of motion planning, limiting their ability to capture real-world social complexities and behavioral adaptability. To this end, we introduce SA-PINN, a novel Self-Adaptive Physics-Informed Neural Network specifically designed for modeling adaptive crowd behaviors. SA-PINN features two innovative adaptive modules: a self-adaptive social perception module, guided by a visual-field physics model to capture context-dependent social interactions dynamically; and a self-adaptive multi-task PINN training module, automatically balancing key motion objectives such as goal-reaching, collision avoidance, and alignment with real data. By jointly enabling perception-level and task-level adaptations within a unified physics-informed framework, SA-PINN generates highly realistic and physically consistent crowd simulations across diverse environmental contexts. Comprehensive evaluations on three real-world datasets (Lane, Cross 90, and GC) reveal that SA-PINN achieves a 29.7% gain in microscopic trajectory accuracy and enhances macroscopic density similarity by 23.5% compared to the best-performing baselines.

Long-horizon planning in robotic manipulation tasks requires translating underspecified, symbolic goals into executable control programs satisfying spatial, temporal, and physical constraints. However, language model-based planners often struggle with long-horizon task decomposition, robust constraint satisfaction, and adaptive failure recovery. We introduce InstructFlow, a multi-agent framework that establishes a symbolic, feedback-driven flow of information for code generation in robotic manipulation tasks. InstructFlow employs a InstructFlow Planner to construct and traverse a hierarchical instruction graph that decomposes goals into semantically meaningful subtasks, while a Code Generator generates executable code snippets conditioned on this graph. Crucially, when execution failures occur, a Constraint Generator analyzes feedback and induces symbolic constraints, which are propagated back into the instruction graph to guide targeted code refinement without regenerating from scratch. This dynamic, graph-guided flow enables structured, interpretable, and failure-resilient planning, significantly improving task success rates and robustness across diverse manipulation benchmarks, especially in constraint-sensitive and long-horizon scenarios.

Guidance signage placement is a fundamental operation for crowd control in public places.The currentmethods mainly rely on manual design ormathematicalmodels, which are not flexible and effective enough for crowd control in large public places. To address this issue, this article proposes a multiobjective evolutionary framework that can search for high-quality guidance signage placement strategies automatically. In the proposed method, an agent-based crowd simulation model is proposed to simulate the wayfinding behaviors of pedestrians in public places. Furthermore, a new safety metric is proposed to quantitatively evaluate the quality of guidance signage placement strategies. On this basis, an indicator-based multiobjective evolutionary algorithm (IBEA) is utilized to search for optimal guidance signage placement strategies that have tradeoffs between crowd safety and pedestrians’ travel time. Simulation experiments on both synthetic and real-world scenes were conducted to evaluate the proposed method, and the simulation results show that the proposed framework can generate very promising guidance signage placement strategies in comparison with several existing methods.

Detecting and quantifying abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally and the scale of CABs could vary from one scenario to another. It is also challenging to quantify the risk level of these CABs from video surveillance. In this paper, we present an improved version of our crowd motion learning framework for CABs detection, multi-scale motion consistency network (MSMC-Net) with a dual-attention fusion process to accommodate both the spatio-temporal and scale variations of different CABs. In addition, we propose an assessment method to quantify the risk level of detected CABs based on the anomaly score generated from our MSMC-Net. The risk quantification is performed in an online and accumulated manner and it can reflect the risk level of CABs consistent with other offline assessment metrics (e.g., crowd pressure), but without the extraction of detailed crowd data (e.g., pedestrian trajectories). For empirical study, we evaluate our method on large-scale crowd event datasets, including UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could improve the AUC performance by 7.9%, 12.2% and 29.5% on three datasets respectively, compared to the best results of the state-of-the-art methods.

Detecting abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. In the recent decade, video anomaly detection (VAD) techniques have achieved remarkable success in detecting individual-level abnormal behaviors (e.g., sudden running, fighting and stealing), but research on VAD for CABs is rather limited. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally, and the scale of CABs could vary from one scenario to another. In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net). MSMC-Net first captures the spatial and temporal crowd motion consistency information in a graph representation. Then, it simultaneously trains multiple feature graphs constructed at different scales to capture rich crowd patterns. An attention network is used to adaptively fuse the multi-scale features for better CAB detection. For the empirical study, we consider three large-scale crowd event datasets, UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could substantially improve the state-of-the-art performance on all the datasets.

Hidden following is following behavior with special intentions, and detecting hidden following behavior can prevent many criminal activities in advance. The previous method uses gaze and spacing behaviors to distinguish hidden followers from normal pedestrians. However, they express gaze behaviors in a coarse-grained way with binary values, making it difficult to accurately depict the gaze state of pedestrians. To this end, we propose the Refined Hidden Follower Detection (RHFD) model by choosing a suitable mapping function based on the principle that the closer the gaze direction is to someone, the more likely it is to gaze at someone, which converts the gaze direction into a continuous estimated gaze state representing the complex and variable gaze behavior of pedestrians. Simultaneously, we introduce variations in the magnitude and direction of pedestrian velocity to refine the representation of pedestrian walking states. Experimental results on the surveillance dataset show that RHFD outperforms state-of-the-art methods.

Collision-avoidance control for UAV swarm has recently drawn great attention due to its significant implications in many industrial and commercial applications. However, traditional collision-avoidance models for UAV swarm tend to focus on avoidance at individual UAV level, and no explicit strategy is designed for avoidance among multiple UAV groups. When directly applying these models for multigroup UAV scenarios, the deadlock situation may happen. A group of UAVs may be temporally blocked by other groups in a narrow space and cannot progress toward achieving its goal. To this end, this article proposes a modeling and optimization approach to multigroup UAV collision avoidance. Specifically, group level collision detection and adaption mechanism are introduced, efficiently detecting potential collisions among different UAV groups and restructuring a group into subgroups for better collision and deadlock avoidance. A two-level control model is then designed for realizing collision avoidance among UAV groups and of UAVs within each group. Finally, an evolutionary multitask optimization method is introduced to effectively calibrate the parameters that exist in different levels of our control model, and an adaptive fitness evaluation strategy is proposed to reduce computation overhead in simulation-based optimization. The simulation results show that our model has superior performances in deadlock resolution, motion stability, and distance maintenance in multigroup UAV scenarios compared to the state-of-the-art collision-avoidance models. The model optimization results also show that our model optimization method can largely reduce execution time for computationally-intensive optimization process that involves UAV swarm simulation.

We raise a new and challenging multimedia application in video surveillance system, i.e., Hidden Follower Discovery (HFD). In contrast to the common abnormal behaviors that are occurring, hidden following is not an ongoing activity, but a preparatory action. Hidden following behavior does not have salient features, making it hard to be discovered. Fortunately, from a socio-cognitive perspective, we found and verified the phenomena that the gaze-flow pattern and the spacing-flow pattern between hidden and normal followers are different. To promote HFD research, we construct two pioneering datasets and devise an HFD baseline network based on the recognition of both gaze-flow and spacing-flow patterns from surveillance videos. Extensive experiments demonstrate their effectiveness.

The proliferation of vehicle-to-vehicle (V2V) communication techniques has resulted in collaborative vehicle localization (CVL) approaches that localize a target vehicle by leveraging the state information of nearby vehicles. However, CVL approaches typically require a large search space to locate the real position of a target vehicle and assume small measurement errors of nearby vehicle information, which limit the efficiency and robustness of the existing methods. In this article, we propose an efficient and error-tolerant CVL approach (referred to asE2T-CVL) that increases localization efficiency and accuracy even in the case of large measurement errors of nearby vehicle information. Unlike the existing CVL approaches, our approach prunes the search space for the position of the target vehicle through a pruning-based strategy that considers the relative positions of nearby vehicles. To determine the position of the target vehicle from the search space, we propose a displacement-based selection method to reduce the influence of the measurement errors of nearby vehicle information. The localization accuracy and efficiency of the proposed approach are then evaluated using simulated global positioning system trajectories in a large road network in New York City. The experimental results show that the proposed approach achieves higher localization efficiency and greater accuracy even with large measurement errors compared to state-of-the-art CVL approaches.

For safety planning in crowd evacuation, it is important to predict the evacuation decisions made by different individuals and understand the reasons behind these decisions. To this end, this paper proposes an automated approach that can learn prioritized fuzzy decision rules from crowd data to predict and understand the evacuation decisions of a real human. A coevolutionary fuzzy rule miner based on genetic fuzzy-system is designed to select necessary decision features from available ones and learn both rule structure and associated rule parameters from training data. The learned fuzzy rule contains multiple sub-rules, each of which can represent evacuation strategies of different individuals in a given scenario and the features in the fuzzy condition of the sub-rule are organized and evaluated in a sequential order to reflect the priorities of different features. Based on training and testing on four evacuations scenarios of two real-world datasets, it is shown that our proposed approach can learn decision rules that are competitive to the existing evacuation decision models in terms of prediction accuracy. More importantly, it is also demonstrated that our learned rules complying with the proposed prioritized fuzzy rule representation can facilitate the interpretation of evacuation behaviors, such as “herding under zero visibility of exit” and “diminished importance on the distance to exit”, which are aligned to the field observations from real crowd evacuation.

Workflow scheduling problem (WSP) is a well-known combinatorial optimization problem, which is defined to assign a series of interconnected tasks to the available resources to meet user defined Quality of Service (QoS). The guided random search methods and heuristic based methods are two most common methods for solving WSP. However, these methods either require expensive computational cost or heavily rely on human's empirical knowledge, which makes them inconvenient for practical applications. Keeping this in mind, this paper proposes a cooperative coevolution hyper-heuristic framework to solve WSP with an objective of minimizing the completed time of workflow. In particular, in the proposed framework, two heuristic rules, namely, the task selection rule (TSR) and the resource selection rule (RSR), are learned automatically by a cooperative coevolution genetic programming (CCGP) algorithm. The TSR is used to select a ready task for scheduling, while the RSR is used to allocate resources to perform the selected task. To improve the search efficiency, a set of low-level heuristics are defined and used as building blocks to construct the TSR and RSR. Further, to validate the effectiveness of the proposed framework, randomly generated workflow instances and four real-world workflows are used as test cases in the experimental study. Compared with several state-of-the-art methods, e.g., the Heterogeneous Earliest Finish Time (HEFT) and the Predict Earliest Finish Time (PEFT), the high-level heuristics found by our proposed framework demonstrate superior performance on all the test cases in terms of several metrics including the schedule length ratio, speedup and efficiency.

In outdoor crimes such as robbery and kidnapping, suspects generally secretly follow their victims in public places and then look for opportunities to commit crimes. Video anomaly detection (VAD) has achieved fruitful results through deep neural networks (DNN). However, as an abnormal behavior without obvious abnormal physical features, hidden following is highly similar to ordinary walking and accompanying behaviors, so it is difficult to effectively detect hidden dangerous followers using video anomaly detection methods or traditional trajectory analysis methods. We propose "hidden follower'' detection (HFD) task and a HFD model based on gaze pattern extraction. It extracts gaze pattern features of pedestrians from gaze-interval-series and introduces a time series classification model to classify pedestrians with or without hidden following purposes. Based on this model, we propose a hidden follower detection framework (HFDF) to detect hidden followers from normal pedestrians, which utilizes the trajectories and gaze patterns extracted from videos. To cope with the lack of test data, we construct a dataset of 1200 pedestrians from the crowd simulation model to simulate scenes including hidden followers, and we also collected a surveillance video dataset including the hidden following behaviors. The experiments conducted on these two datasets show that HFDF can consistently outperform the state-of-the-art method by a notable margin in the HFD task on the commonly-used F1 benchmark.

The development of vehicle-to-vehicle (V2V) communication techniques have proliferated collaborative vehicle localization (CVL) approaches to estimate the absolute positions of the nearby vehicles. In general, the information of the nearby vehicles in terms of geometry information and historical states are utilized to increase localization accuracy. However, the geometry information can be unknown and the historical states of the nearby vehicles cannot be obtained under certain circumstances. In this paper, a Bayesian-based localization approach, named as BayesNVL is proposed to estimate the absolute positions of the nearby vehicles from an ego vehicle through incorporating the GPS measurements and measured relative positions. Different from the existing work, our pro-posed approach can be applied to the real driving scenarios without the geometry information of road network and the historical states of the nearby vehicles. We evaluate the proposed approach in terms of localization accuracy and efficiency by using a real dataset containing the trajectories of vehicles. The experimental results show that our proposed approach is able to achieve higher localization accuracy compared with the existing approaches and acceptable localization efficiency.

This paper presents a framework for managing flexible waste-to-energy (WTE) systems based on decision rules. In the operation of a WTE system, the decision rule is used for decision-makers to adaptively select flexible strategies in response to a changing environment. Compared to the existing methods that use either fixed plans or manually defined rules, our framework adopts an evolutionary approach to automatically optimize decision rules based on the simulation of WTE operation environment. The proposed framework is applied to a case study of an anaerobic digestion WTE system and the decision rule is generated for providing an intuitive guidance to exercise capacity expansion strategy in the given system. The experimental results show that the decision rule being generated based on our framework can help to improve the WTE system's expected net present value compared to the fixed expansion design.

Abstract How to realistically model an agent's steering behaviour is a critical issue in agent‐based crowd simulation. In this work, we investigate some proactive steering strategies for agents to minimize potential collisions. To this end, a behaviour‐based modelling framework is first introduced to model the process of how humans select and execute a proactive steering strategy in crowded situations and execute the corresponding behaviour accordingly. We then propose behaviour models for two inter‐related proactive steering behaviours, namely gap seeking and following. These behaviours can be frequently observed in real‐life scenarios, and they can easily affect overall crowd dynamics. We validate our work by evaluating the simulation results of our model with the real‐world data and comparing the performance of our model with that of two state‐of‐the‐art crowd models. The results show that the performance of our model is better or at least comparable to the compared models in terms of the realism at both individual and crowd levels.

Generating suitable game scenarios that can cater for individual players has become an emerging challenge in procedural content generation. In this paper, we propose a data-driven scenario generation framework for game-based training. An evolutionary scenario generation process is designed with a fitness evaluation methodology that integrates the processes of AI player modeling, simulation and model training based on artificial neural networks. The fitness function for scenario evaluation can be automatically constructed based on the proposed methodology. To further enhance the evaluation of scenarios, we specifically study the impact of the timing of events in a scenario and propose a generic scenario representation model that characterizes individual scenario based on the types and timing of events in the scenario. We present an extensive evaluation of our framework by validating our AI player model, demonstrating the impact of timing of events in a scenario and comparing the effectiveness of our data-driven framework with our previous heuristic-based approach and a random baseline. The results show that it is necessary to consider the timing of events for scenario evaluation and the proposed framework works well in generating scenarios for game-based training.

Research on agent-based crowd simulation has gained tremendous momentum in recent years due to the increase of computing power. One key issue in this research area is to develop various behavioral models to capture the microscopic behaviors of individuals (i.e., agents) in a crowd. In this paper, we propose a novel behavior model for modeling the gap seeking behavior which can be frequently observed in real world scenarios where an individual in a crowd proactively seek for gaps in the crowd flow so as to minimize potential collision with other people. We propose a two-level modeling framework and introduce a gap seeking behavior model as a proactive conflict minimization maneuver at global navigation level. The model is integrated with the reactive collision avoidance model at local steering level. We evaluate our model by simulating a real world scenario. The results show that our model can generate more realistic crowd behaviors compared to the classical social-force model in the given scenario.

ABSTRACT Serious games have recently shown great potential to be adopted in many applications, such as training and education. However, one critical challenge in developing serious games is the authoring of a large set of scenarios for different training objectives. In this paper, we propose a data‐driven approach to automatically generate scenarios for serious games. Compared with other scenario generation methods, our approach leverages on the simulated player performance data to construct the scenario evaluation function for scenario generation. To collect the player performance data, an artificial intelligence (AI) player model is designed to imitate how a human player behaves when playing scenarios. The AI players are used to replace human players for data collection. The experiment results show that our data‐driven approach provides good prediction accuracy on scenario's training intensities. It also outperforms our previous heuristic‐based approach in its capability of generating scenarios that match closer to specified target player performance.Copyright © 2014 John Wiley & Sons, Ltd.

ABSTRACT For a virtual training system, how to effectively and quickly generate training scenarios has become a challenging issue. A scenario generation system is needed to produce scenarios that can meet different objectives and at the same time be customized for individuals. In this paper, we introduce a scenario generation framework for mission‐based virtual training, which aims to generate scenarios from both trainer and trainee's perspective. The framework allows a trainer to direct the scenario generation process, so that the generated scenarios reflect the trainer's preferences over different mission objectives. It also considers how the scenarios could adapt to different trainees’ skill levels. The representation of scenario beat is proposed, and the scenario generation process adopts a combinatorial optimization approach generating the sequence of scenario beats. The efficacy of the proposed framework is demonstrated through an empirical study of human players in a simple food distribution mission game. The results show that a trainee can achieve better performance improvement when playing the customized scenarios tailored to the trainee's skill level as compared with the uncustomized scenarios. Copyright © 2013 John Wiley & Sons, Ltd.

Generating human-like behaviors for virtual agents has become increasingly important in many applications, such as crowd simulation, virtual training, digital entertainment, and safety planning. One of challenging issues in behavior modeling is how virtual agents make decisions given some time-critical and uncertain situations. In this paper, we present HumDPM, a decision process model for virtual agents, which incorporates two important factors of human decision making in time-critical situations: experience and emotion. In HumDPM, rather than relying on deliberate rational analysis, an agent makes its decisions by matching past experience cases to the current situation. We propose the detailed representation of experience case and investigate the mechanisms of situation assessment, experience matching and experience execution. To incorporate emotion into HumDPM, we introduce an emotion appraisal process in situation assessment for emotion elicitation. In HumDPM, the decision making process of an agent may be affected by its emotional states when: 1) deciding whether it is necessary to do a re-match of experience cases, 2) determining the situational context, and 3) selecting experience cases. We illustrate the effectiveness of HumDPM in crowd simulation. A case study for emergency evacuation in a subway station scenario is conducted, which shows how a varied crowd composition leads to different evacuation behaviors, due to the retrieval of different experiences and the variation of agents' emotional states.

Abstract Human crowd is a fascinating social phenomenon in nature. This paper presents our work on designing behavior model for virtual humans in a crowd simulation under normal‐life and emergency situations. Our model adopts an agent‐based approach and employs a layered framework to reflect the natural pattern of human‐like decision making process, which generally involves a person's awareness of the situation and consequent changes on the internal attributes. The social group and crowd‐related behaviors are modeled according to the findings and theories observed from social psychology (e.g., social attachment theory). By integrating our model into an agent execution process, each individual agent can response differently to the perceived environment and make realistic behavioral decisions based on various physiological, emotional, and social group attributes. To demonstrate the effectiveness of our model, a case study has been conducted, which shows that realistic human behaviors can be generated at both individual and group level. Copyright © 2008 John Wiley & Sons, Ltd.