Simulation of Drone Controller using Reinforcement Learning AI with Hyperparameter Optimization

Bakar, Mohamad Hafiz Abu; Shamsudin, Abu Ubaidah; Rahim, Ruzairi Abdul

doi:10.1109/icset51301.2020.9265381

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is an extension of the study originally presented by Bakar et al, [9] that previously highlighted the optimization hyperparameter for the system developed based on the Q-learning algorithm. The advancement of drones is also factored in the development of a world surrounded by technologies.…”

Section: Introductionmentioning

confidence: 91%

“…To control drone movements using Q-Learning and SARSA algorithms, the drone must be in direct interaction with the environment. Therefore, a proper simulation system will be setup with the best possible parameters based on the optimization of the hyperparameter suggested in Table 2 [9]. Based on this purpose, the hyperparameter will be considered an important part of the first setup to find the best performance during the training session and also can assist agent learn effectively.…”

Section: Fig 3 Input and Output The Drone For Simulationmentioning

confidence: 99%

See 1 more Smart Citation

Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning

Bakar

Shamsudin

Rahim

et al. 2023

ARASET

View full text Add to dashboard Cite

Nowadays, the advancement of drones is also factored in the development of a world surrounded by technologies. One of the aspects emphasized here is the difficulty of controlling the drone, and the system developed is still under full control by the users as well. Reinforcement Learning is used to enable the system to operate automatically, thus drone will learn the next movement based on the interaction between the agent and the environment. Through this study, Q-Learning and State-Action-Reward-State-Action (SARSA) are used in this study and the comparison of results involving both the performance and effectiveness of the system based on the simulation of both methods can be seen through the analysis. A comparison of both Q-learning and State-Action-Reward-State-Action (SARSA) based systems in autonomous drone application was performed for evaluation in this study. According to this simulation process is shows that Q-Learning is a better performance and effective to train the system to achieve desire compared with SARSA algorithm for drone controller.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Fig 3 Input and Output The Drone For Simulationmentioning

confidence: 99%

Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning

Bakar

Shamsudin

Rahim

et al. 2023

ARASET

View full text Add to dashboard Cite

show abstract

“…The maximum height of the drone through Wi-Fi link communication was only 8 meters, between the sensors and coverage zone. By increasing the number of antennas of the drone, the connectivity can be improved [20]. In other research, 5G communication technology was proposed for the drone application to improve data protection and enhance the location data of the drone through mobile applications [21].…”

Section: Communicationmentioning

confidence: 99%

Review of Implementing the Internet of Things (IoT) for Robotic Drones (IoT Drones)

Hajjaj,

Moktar,

Weng

2024

E3S Web Conf.

View full text Add to dashboard Cite

Drone and the Internet of Things are different technologies, actively utilised and implemented across various fields. Connectivity is the difference between the IoT drone and the regular drone. IoT drones can receive and transmit data and command signals in real-time while being controlled through the IoT network. By implementing both drone and IoT, the flying IoT (IoT-Drone) is built as a new form of IoT device. This work improves how to use the drone effectively in many aspects; data transferring, data collecting, real-time monitoring, and control. With the emergence of the Internet of Things, Artificial Intelligence, and advanced communication, the IoT drone technology has been utilized in many fields, especially in agriculture and inspection, and discussed in smart cities, logistic delivery, and the military. This paper reviews the IoT drone implementation in those fields and reviews the researchers’ discussion and studies on IoT drone optimization.

show abstract

The Use of Swarms of Unmanned Aerial Vehicles in Mitigating Area Coverage Challenges of Forest-Fire-Extinguishing Activities: A Systematic Literature Review

Alsammak

Mahmoud

Aris

et al. 2022

Forests

View full text Add to dashboard Cite

The use of Unmanned Aerial Vehicles (UAVs), colloquially known as drones, has grown rapidly over the past two decades and continues to expand at a rapid pace. This has resulted in the production of many research papers addressing the use of UAVs in a variety of applications, such as forest firefighting. The main purpose of this paper is to provide a comprehensive overview of UAV-based forest-fire-extinguishing activity (FFEA) operations. To achieve this goal, a systematic literature review was conducted to answer a specific set of questions, which were carefully formulated to address the results of research conducted between 2008 and 2021. This study aims to (i) expand our understanding of the development of UAVs and their current contributions to the FFEA; (ii) identify particularly novel or unique applications and characteristics of UAV-based fire-extinguishing systems; (iii) provide guidance for exploring and revising further ideas in this field by identifying under-researched topics and other areas in which more contributions are needed; and (iv) explore the feasibility of using UAV swarms to enable autonomous firefighting in the forest without human intervention. Of the 1353 articles systematically searched across five databases (Google Scholar, ACM Digital Library, Science Direct, Scopus, and IEEE Explore), 51 highly relevant articles were found to meet the inclusion criteria; therefore, they were analyzed and discussed. The results identified several gaps in this field of study among them the complexity of coordination in multi-robotic systems, the lack of evaluation and implementation of fire extinguishing systems, the inability of handling multiple spot fires, and poor management of time and resources. Finally, based on the conducted review, this paper provides significant research directions that require further investigations by researchers in this field including, the deployment of UAV-based Swarm Robotics, further study on the characteristics of the fire extinguishing systems; design more effective area coverage; and the propose of a self-firefighting model that enables individuals to decide on the course of events efficiently and locally for better utilization and management of time and resources.

show abstract

Simulation of Drone Controller using Reinforcement Learning AI with Hyperparameter Optimization

Cited by 3 publications

References 30 publications

Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning

Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning

Review of Implementing the Internet of Things (IoT) for Robotic Drones (IoT Drones)

The Use of Swarms of Unmanned Aerial Vehicles in Mitigating Area Coverage Challenges of Forest-Fire-Extinguishing Activities: A Systematic Literature Review

Contact Info

Product

Resources

About