A5101410079- Evacuation and Crowd Dynamics
- Traffic control and management
- Transportation Planning and Optimization
- Human Mobility and Location-Based Analysis
- Autonomous Vehicle Technology and Safety
- Data Visualization and Analytics
- Traffic and Road Safety
- Traffic Prediction and Management Techniques
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Urban Transport and Accessibility
- Evolutionary Algorithms and Applications
- Digital Games and Media
- Building Energy and Comfort Optimization
- Artificial Intelligence in Games
- Human Motion and Animation
- Mobile Crowdsensing and Crowdsourcing
- Urban Design and Spatial Analysis
Agency for Science, Technology and Research
2013-2018
Institute of High Performance Computing
2016-2018
Nanyang Technological University
2010-2012
The development of competent AI for real-time strategy games such as StarCraft is made difficult by the myriad strategic and tactical reasonings which must be performed concurrently. A significant portion gameplay in managing conflict with opposing forces. We present a modular framework simulating vs. conflicts through an XML specification, whereby behavioural components each force can varied. Evolutionary computation employed on aspects scenario to yield superior solutions. Through...
With the increasing popularity of Digital Twin, there is an opportunity to employ deep learning models in symbiotic simulation system. Symbiotic can replicate multiple what-if instances from its real-time reference (base simulation) for short-term forecasting. Hence, it a useful tool just-in-time decision making process. Recent trends on studies emphasize combination with machine learning. Despite success and usefulness, very few works focus application such hybrid system microscopic traffic...
In this paper, we propose a new approach to modeling natural steering behaviors of virtual humans. We suspect that small number strategies are sufficient for generating typical pedestrian observed in daily-life situations. Through these limited show complex generated by executing appropriate at the time. our model, decisions on selection, scheduling and execution given situation based matching results between currently perceived spatial-temporal patterns prototypical cases an agent's...
Symbiotic simulation systems that incorporate data-driven methods (such as machine/deep learning) are effective and efficient tools for just-in-time (JIT) operational decision making. With the growing interest on Digital Twin City, such ideal real-time microscopic traffic simulation. However, learning-based models heavily biased towards training data could produce physically inconsistent outputs. In terms of simulation, this lead to unsafe driving behaviours causing vehicle collisions in As...
Abstract In this paper, we propose a framework for modeling lower‐level pedestrian navigational behaviors. We aim not only to generate realistic simulation results but also make our flexible and extendible, easy use model developers. A divide‐and‐conquer methodology is first adopted divide the complex behaviors into three levels, which allows us focus on intermediate level. then pattern‐based behavior at framework, spatial‐temporal patterns are used represent situational perception,...
Surrogate models are commonly used to approximate the multivariate input or output behavior of complex systems. In this paper, surrogate assisted calibration frameworks proposed calibrate crowd model. To integrate into evolutionary framework, both offline and online training based approaches developed. The needs generate set in advance, while can adaptively build re-build model along process. Our simulation results demonstrate that framework with is effective using artificial neural network...
We report an approach to achieve effective crowd control strategies through adaptively evolving agent-based model of Crowd Simulation for Military Operations (COSMOS). COSMOS is a complex system simulation platform developed address challenges posed by the in Urban Terrains (MOUT). Modeling and simulating soldiers' tactical behaviors MOUT scenarios challenging due emerging crowds large parameter space models. Consequently, it difficult search tuning parameters manually. employ adaptive...