Construction of a virtual reality platform for UAV deep learning

Wang, Shubo; Chen, Jian; Zhang, Zichao; Wang, Guangqi; Tan, Yu; Zheng, Yongjun

doi:10.1109/cac.2017.8243463

Cited by 19 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, an optimization problem for joint transmission and content caching is formulated and solved via the use of deep learning techniques combining liquid state machine spiking neural networks and echo state networks. In another context, authors in [44] provide a UAV VR simulation platform used to assess the performance of several DL-based solutions for UAVs such as autonomous path planning and obstacle avoidance. The constructed VR platform can generate images and data for UAV navigation that could be used in the training phase.…”

Section: Supervised and Unsupervised Solutions For Uavs-based Problemsmentioning

confidence: 99%

Artificial Intelligence for UAV-Enabled Wireless Networks: A Survey

Lahmeri

Kishk

Alouini

2021

IEEE Open J. Commun. Soc.

111

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) are considered as one of the promising technologies for the next-generation wireless communication networks. Their mobility and their ability to establish line of sight (LOS) links with the users made them key solutions for many potential applications. In the same vein, artificial intelligence (AI) is growing rapidly nowadays and has been very successful, particularly due to the massive amount of the available data. As a result, a significant part of the research community has started to integrate intelligence at the core of UAVs networks by applying AI algorithms in solving several problems in relation to drones. In this article, we provide a comprehensive overview of some potential applications of AI in UAV-based networks. We also highlight the limits of the existing works and outline some potential future applications of AI for UAVs networks.

show abstract

Section: Supervised and Unsupervised Solutions For Uavs-based Problemsmentioning

confidence: 99%

Artificial Intelligence for UAV-Enabled Wireless Networks: A Survey

Lahmeri

Kishk

Alouini

2021

IEEE Open J. Commun. Soc.

111

View full text Add to dashboard Cite

show abstract

“…Although Airsim with Unreal Engine simulator has many advantages, it still has some disadvantages that need to be improved. In fact, for drones, the high-resolution rendering does not replicate the sensing and control in the same way between a realworld environment and in a simulation environment [15,16]. Compared to high-resolution rendering, the accurate implementation of depth camera and air drag force models is more important to make the simulation environment close to the real-life environment [17].…”

Section: Introductionmentioning

confidence: 99%

High-Fidelity Drone Simulation with Depth Camera Noise and Improved Air Drag Force Models

Kim,

Luong,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Drone simulations offer a safe environment for collecting data and testing algorithms. However, the depth camera sensor in the simulation provides exact depth values without error, which can result in variations in algorithm behavior, especially in the case of SLAM, when transitioning to real-world environments. The aerodynamic model in the simulation also differs from reality, leading to larger errors in drag force calculations at high speeds. This disparity between simulation and real-world conditions poses challenges when attempting to transfer high-speed drone algorithms developed in the simulated environment to actual operational settings. In this paper, we propose a more realistic simulation by implementing a novel depth camera noise model and an improved aerodynamic drag force model. Through experimental validation, we demonstrate the suitability of our models for simulating real-depth cameras and air drag forces. Our depth camera noise model can replicate the values of a real depth camera sensor with a coefficient of determination (R2) value of 0.62, and our air drag force model improves accuracy by 51% compared to the Airsim simulation air drag force model in outdoor flying experiments at 10 m/s.

show abstract

“…Researchers have been exploring general drone flight training (O’Keeffe et al , 2017; Qi et al , 2018; Smolyanskiy and Gonzalez-Franco, 2017; Ware, 2017; Wlodyka and Dulat, 2015); however, challenges such as high costs, liability concerns and safety risks hinder the adaptation of such training in CEM education programs (Bu et al , 2015; De la Torre et al , 2016; Weldon and Kozak, 2017). These factors paved the way to introduce virtual reality (VR)-based simulators as safe, advantageous and efficient training alternatives (Balakirsky and Kootbally, 2012; Bu et al , 2015; De la Torre et al , 2016; Meyer et al , 2012; Sakib et al , 2020, 2021; Wang et al , 2017; Weldon and Kozak, 2017). Although drone building inspection flights and general flights seem to require similar piloting skills, there are distinctive flight operation characteristics pertaining to the construction domain.…”

Section: Introductionmentioning

confidence: 99%

“…Nguyen et al (2019) proposed a Web-based VR drone simulator based on real-world map data to assist operators in avoiding drone-associated building crashes and ensure safe drone landing. Stated advantages of using such simulators include the ability to train pilots for an unlimited time, in real-time, at reduced training costs and in different conditions and environments that are typically not available in non-virtual or real-world training (Balakirsky and Kootbally, 2012; De la Torre et al , 2016; Wang et al , 2017). These factors, in turn, reduce the risks of drone-associated real-world accidents and casualties caused by inexperienced pilots and increase the overall training efficiency (De la Torre et al , 2016; Wang et al , 2017).…”

Section: Introductionmentioning

confidence: 99%

“…Stated advantages of using such simulators include the ability to train pilots for an unlimited time, in real-time, at reduced training costs and in different conditions and environments that are typically not available in non-virtual or real-world training (Balakirsky and Kootbally, 2012; De la Torre et al , 2016; Wang et al , 2017). These factors, in turn, reduce the risks of drone-associated real-world accidents and casualties caused by inexperienced pilots and increase the overall training efficiency (De la Torre et al , 2016; Wang et al , 2017). Simulators also allow for a more straightforward evaluation of future pilots and enhanced opportunities to study different parameters that could otherwise be risky or difficult to evaluate in non-virtual or real-world flights (De la Torre et al , 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DroneSim: a VR-based flight training simulator for drone-mediated building inspections

Albeaino

Eiris

Gheisari

et al. 2021

View full text Add to dashboard Cite

Purpose This study aims to explore DroneSim, a virtual reality (VR)-based flight training simulator, as an alternative for real-world drone-mediated building inspection training. Design/methodology/approach Construction, engineering and management students were asked to pilot drones in the VR-based DroneSim space and perform common flight operations and inspection tasks within the spatiotemporal context of a building construction project. Another student group was also recruited and asked to perform a similar building inspection task in real world. The National Aeronautics and Space Administration (NASA)–Task Load Index (TLX) survey was used to assess students’ inflight workload demand under both Real and DroneSim conditions. Post-assessment questionnaires were also used to analyze students’ feedback regarding the usability and presence of DroneSim for drone building inspection training. Findings None of the NASA–TLX task load levels under real and DroneSim conditions were highly rated by students, and both groups experienced comparable drone-building inspection training. Students perceived DroneSim positively and found the VR experience stimulating. Originality/value This study’s contribution is twofold: to better understand the development stages involved in the design of a VR-based drone flight training simulator, specifically for building inspection tasks; and to improve construction students’ drone operational and flight training skills by offering them the opportunity to enhance their drone navigation skills in a risk-free, repeatable yet realistic environment. Such contributions ultimately pave the way for better integration of drone-mediated building inspection training in construction education while meeting industry needs.

show abstract

Construction of a virtual reality platform for UAV deep learning

Cited by 19 publications

References 1 publication

Artificial Intelligence for UAV-Enabled Wireless Networks: A Survey

Artificial Intelligence for UAV-Enabled Wireless Networks: A Survey

High-Fidelity Drone Simulation with Depth Camera Noise and Improved Air Drag Force Models

DroneSim: a VR-based flight training simulator for drone-mediated building inspections

Contact Info

Product

Resources

About