Intelligent VR-AR for Natural Disasters Management

García, Silvia; Trejo, Paulina; Garcı́a, A.

doi:10.5772/intechopen.99337

Cited by 4 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is no intelligent agent present to dynamically change the scenarios every time the user plays it. There is an AI component present in [4], where the system tries to recreate the scenario of disasters. The system is doing so with the dataset of earthquakes that occurred, inputting that information into a CART algorithm to predict what the scenario would have looked like.…”

Section: A Virtual Reality (Vr)mentioning

confidence: 99%

“…Virtual disaster training provides a cost-effective and safe way to conduct disaster evacuation preparedness training. There are many works in literature that use virtual reality technology for disaster preparedness training [1], [2], [3], [4], [5], [6]. With AR/VR and Metaverse being the latest, most popular and rapidly accelerating field today, it is a great time to switch to virtual methods of training with the fast technological advancement of the HMDs (Head Mounted Displays) by various companies, which would enable people to prepare for disasters in a much more cost-effective and safer manner.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Procedural Content Generation Using Reinforcement Learning for Disaster Evacuation Training in a Virtual 3D Environment

Agarwal,

Shridevi

2023

IEEE Access

View full text Add to dashboard Cite

This research addresses the need for effective disaster evacuation training methods by proposing a virtual reality system that utilizes Reinforcement Learning Procedural Content Generation (RL-PCG) algorithms. The aim of this study is to provide a cost-effective and safe way to conduct disaster evacuation preparedness training, surpassing the limitations of traditional real-life drills. The paper's objectives encompass the design of a novel 3-layer PCG architecture for generating realistic disaster simulations in virtual reality, the implementation of a working prototype for fire disaster scenarios, and the evaluation of the proposed system's effectiveness through comparison with existing RL agents. Significant findings include the superiority of the RL-PCG agent in generating diverse and realistic disaster scenarios with faster training time and lesser number of steps, even with limited processor capabilities. In conclusion, this research establishes that the RL-PCG Scenario for Disaster Evacuation Training in VR is a more effective method, leading to improved disaster preparedness for individuals, and opens avenues for further advancements in disaster training using virtual reality and reinforcement learning technologies. For a video demo of this work, please visit https://youtu.be/3WZnQOfUP94.INDEX TERMS Disaster evacuation training, procedural content generation, reinforcement learning, virtual reality.

show abstract

Section: A Virtual Reality (Vr)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Procedural Content Generation Using Reinforcement Learning for Disaster Evacuation Training in a Virtual 3D Environment

Agarwal,

Shridevi

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Trainees may be placed into the virtual environment and learn how to rescue people or human infrastructures buried by the debris flow. Several studies revealed that VR is widely used for such purposes, in the fields of fire safety (Chittaro and Ranon 2009;Smith and Ericson 2009;Rüppel and Schatz 2011) and earthquakes (Gong et al 2015;Ivanova et al 2016;Feng et al 2020). In our case, road users, early warning planners, and rescue operators can be trained on how and when to act after perceiving the debris flow hazard.…”

Section: Training Module For the First Responders For Safety Rescue O...mentioning

confidence: 99%

Realistic visualization of debris flow type landslides through virtual reality

et al. 2022

View full text Add to dashboard Cite

Immersive media technologies, such as virtual and augmented reality, have recently enabled a more holistic way to comprehend natural hazards. In this work, we aim at visualizing the temporal and spatial evolution of a debris flow in a virtual reality environment. We develop a framework to integrate the output results obtained from a debris flow numerical model into virtual reality. To guide the framework, a real debris flow event, which happened in Hunnedalen (Norway) in 2016 and blocked a road network, is considered as a case study. The debris flow is back-calculated using a depth-averaged numerical model and the simulation results are imported into a dedicated game engine to construct a digital model of the debris flow event. The debris flow is visualized using a Head-Mounted Display. We therefore discuss a wide range of potential applications of virtual reality to manage and grasp landslide phenomena: training for rescue operations; improving decision-making; studying early warning systems, and educating communities affected by natural hazards. We finally provide a quantitative evaluation of the hazard perception for a road user. We show that the debris flow movement is perceived at variable delayed times from the triggering of the landslide, depending on the position along the road where the debris flow is observed. Evaluating the realistic perception time of the natural hazard may be fundamental to designing more effective road networks, signs, and mitigation measures.

show abstract