3D G-learning in UAVs

Luan, Shangzhen; Ye, Yun; Wang, Hainan; Zhang, Baochang; Yu, Baoguo; He, Chenglong

doi:10.1109/iciea.2017.8282976

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the visual technology used in autonomous driving cars, UAVs use cameras to capture real-time images and identify possible obstacles and safe flying spaces [12], [13]. In addition to deep learning, Q-learning in reinforcement learning was also used for path planning in [14], and Luan et al in [15] used G-learning to iteratively optimize the path by calculating the cost function in real time. Lei et al in [16] modeled the UAV navigation problem as a Markov decision process and proposed a model interpretation method based on feature attributes to explain the behavior of the UAV in the path planning process.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

School of Teacher, Nanjing Xiao Zhuang University, Nanjing, 210000, China

Wang¹

2017

Advances in Psychological Science

View full text Add to dashboard Cite

The nuclide 14 C can be produced in the atmosphere by high energy particles and γ-rays from high-energy phenomena. Through the carbon cycle, some of 14 CO 2 produced in the atmosphere can be retained in annual tree rings 1, 2 . Four events of rapid increase of the 14 C content occurred in AD 775, AD 994, BC 660 and BC 3371 were found 3-6 . Recently, the data of Jull et al. (2020) was inconsistent with our records around BC 3371. We measured our sample again and found the 14 C records are consistent with the value in Wang et al. (2017). Therefore, our 14 C records are robust. The inconsistency may be caused by the difference of calendar ages for the wood samples, or the physical origin of the event. First, crossdating on ring width can be performed only between trees whose growth has the same environmental conditions. Because the master tree-ring for dendrochronology is lack for Chinese trees. The master tree-ring from California has to be used. Therefore, the calendar ages derived from dendrochronology may be not precise. Second, the 14 C even may be not global. One evidence

show abstract

Section: Related Workmentioning

confidence: 99%

“…With the transition equation, the objective function is shown in equation ( 14) and the initial condition in equation (15).…”

Section: A Dynamic Programming Adjustmentmentioning

confidence: 99%

School of Teacher, Nanjing Xiao Zhuang University, Nanjing, 210000, China

Wang¹

2017

Advances in Psychological Science

View full text Add to dashboard Cite

show abstract

“…Reinforcement learning has been used for high-accuracy tracking of hydraulic systems in recent years [70]. The G-learning method has been proposed in [71] to solve the problems of path planning in 3-D-based UAV path planning scenarios. This algorithm is used to compute the cost matrix based on a geometric distance for UAV path planning.…”

Section: E Machine Learning Modelsmentioning

confidence: 99%

Dynamic Navigation in Unconstrained Environments Using Reinforcement Learning Algorithms

Chronis,

Anagnostopoulos,

Politi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The potential for the use of drones in logistics and transportation is continuously growing, with multiple applications both in urban and rural environments. The safe navigation of drones in such environments is a major challenge that requires sophisticated algorithms and systems, that can quickly and efficiently estimate the situation, find the shortest path to the target, and detect and avoid obstacles. Traditional path planning algorithms are unable to handle the dynamic and uncertain nature of real environments, while traditional machine learning models are insufficient due to the constantly changing conditions that affect the drone location and the location of obstacles. Reinforcement learning (RL) algorithms have been widely used for autonomous navigation problems, however, computational complexity and energy demands of such methods can become a bottleneck to the execution of UAV flights. In this paper, we propose the use of a minimum set of sensors and reinforcement learning (RL) algorithms for the safe and efficient navigation of drones in urban and rural environments. Our approach considers the complex and dynamic nature of such environments by incorporating real-time data from low-cost onboard sensors. After performing a thorough review of the existing solutions in drone path planning and navigation in 3-D environments, we experimentally evaluate our proposed approach in a simulated environment, and in various scenarios. The test results demonstrate the effectiveness of the proposed RL-based approach in the navigation of drones in complex and unconstrained environments. The implemented approach can serve as a basis for the development of advanced and robust navigation systems for drones, which can improve safety and efficiency in transportation applications in the near future.INDEX TERMS actor-critic algorithm, drone navigation, dynamic path planning, proximal policy optimization, reinforcement learning.

show abstract

“…Over the years, curative and preventive methods have been developed to mitigate the adverse effects of liquid loading in gas wells. Typical curative techniques are the use of velocity strings, plunger lift, foaming of the liquid, gas lifting, beam pumping and swabbing while preventive techniques involves the use of critical velocity models that predicts the onset of liquid loading, the film reversal models and the use of dynamic simulation (Ikpeka and Okolo, 2019, Li et al, 2001, Luan and He, 2012. Turner et al (1969) pioneered the investigation of liquid loading phenomenon in gas wells.…”

mentioning

confidence: 99%

Prediction of Liquid Accumulation in Gas Wells to Forecast the Critical Flowrate and the Loading Status of Individual Wells

Joseph¹,

Bassey²

2022

jasem

View full text Add to dashboard Cite

Liquid accumulation is a major problem in gas wells. The inability of gas to lift coproduced liquids to the surface imposes back pressure on the reservoir, limits the ultimate recovery and ultimately kills the well if improperly managed. Therefore, accurate prediction of its occurrence and reliable monitoring strategy is key to effectively handling liquid accumulation in gas wells. In this study, machine learning algorithms were used to develop regression and classification models to accurately predict the critical flowrate and the loading status of individual wells. The regression models used are the feed-forward neural network and a least squares support vector machine models while the decision trees model was used as the classification model to characterize the loading status of the wells investigated. These models were validated using actual published data and it was observed that the feed-forward neural network performed better in predicting the critical rate compared to the least squares support vector machine model with an R2 value of 0.9833, and thus was adopted. The feed-forward neural network model was further compared with other critical rate models; and a consistent result with least percent error of 5.571% was also observed. Form this study, it is obvious that the neural network model provide benefits and good prospects in investigating liquid loading phenomena in gas wells compared to empirical models that apply so many simplifying assumptions.

show abstract

3D G-learning in UAVs

Cited by 4 publications

References 14 publications

School of Teacher, Nanjing Xiao Zhuang University, Nanjing, 210000, China

School of Teacher, Nanjing Xiao Zhuang University, Nanjing, 210000, China

Dynamic Navigation in Unconstrained Environments Using Reinforcement Learning Algorithms

Prediction of Liquid Accumulation in Gas Wells to Forecast the Critical Flowrate and the Loading Status of Individual Wells

Contact Info

Product

Resources

About