Deep Reinforcement Learning-Based Adaptive Controller for Trajectory Tracking and Altitude Control of an Aerial Robot

Barzegar, Ali; Lee, Deok Jin

doi:10.3390/app12094764

Cited by 11 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the works of Barzegar and Lee (2022) and Quan (2017) , the system under study was subjected to the following forces:…”

Section: Dynamic Modelmentioning

confidence: 99%

On designing a configurable UAV autopilot for unmanned quadrotors

Bhar,

Sayadi

2024

Front. Neurorobot.

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) and quadrotors are being used in an increasing number of applications. The detection and management of forest fires is continually improved by the incorporation of new economical technologies in order to prevent ecological degradation and disasters. Using an inner-outer loop design, this paper discusses an attitude and altitude controller for a quadrotor. As a highly nonlinear system, quadrotor dynamics can be simplified by assuming several assumptions. Quadrotor autopilot is developed using nonlinear feedback linearization technique, LQR, SMC, PD, and PID controllers. Often, these approaches are used to improve control and to reject disturbances. PD-PID controllers are also deployed in the tracking and surveillance of smoke or fire by intelligent algorithms. In this paper, the efficiency using a combined PD-PID controllers with adjustable parameters have been studied. The performance was assessed by simulation using matlab Simulink. The computational study conducted to assess the proposed approach showed that the PD-PID combination presented in this paper yields promising outcomes.

show abstract

“…Based on the works of Barzegar and Lee (2022) and Quan (2017) , the system under study was subjected to the following forces:…”

Section: Dynamic Modelmentioning

confidence: 99%

On designing a configurable UAV autopilot for unmanned quadrotors

Bhar,

Sayadi

2024

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…During one of the tests, one drone hit a pigeon in flight, but it was able to finalize the mission, helped by our redundant technology approach. We propose for the future to also improve the autonomous flight capability [40].…”

Section: Ethical Considerations On Telemedicinementioning

confidence: 99%

Telemedicine System Applicability Using Drones in Pandemic Emergency Medical Situations

et al. 2022

View full text Add to dashboard Cite

Drones have evolved significantly in recent years, acquiring greater autonomy and carrier capacity. Therefore, drones can play a substantial role in civil medicine, especially in emergency situations or for the detection and monitoring of disease spread, such as during the COVID-19 pandemic. The aim of this paper is to present the real possibilities of using drones in field rescue operations, as well as in nonsegregated airspace, in order to obtain solutions for monitoring activities and aerial work in support of the public health system in crisis situations. The particularity of our conceptual system is the use of a “swarm” of fast drones for aerial reconnaissance that operate in conjunction, thus optimizing both the search and identification time while also increasing the information area and the operability of the system. We also included a drone with an RF relay, which was connected to a hub drone. If needed, a carrier drone with medical supplies or portable devices can be integrated, which can also offer two-way audio and video communication capabilities. All of these are controlled from a mobile command center, in real time, connected also to the national dispatch center to shorten the travel time to the patient, provide support with basic but life-saving equipment, and offer the opportunity to access remote or difficult-to-reach places. In conclusion, the use of drones for medical purposes brings many advantages, such as quick help, shortened travel time to the patient, support with basic but life-saving equipment, and the opportunity to access remote or difficult-to-reach places.

show abstract

“…Liu et al [19] used RL and probability map to create a search algorithm and improve the detection ability of the algorithm. Finally, deep RL is used for local motion planning in an unknown environment in [20], and for trajectory tracking and altitude control in [21].…”

Section: Related Workmentioning

confidence: 99%

A Multi-Objective Reinforcement Learning Based Controller for Autonomous Navigation in Challenging Environments

Dooraki

Lee

2022

Machines

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce a self-trained controller for autonomous navigation in static and dynamic (with moving walls and nets) challenging environments (including trees, nets, windows, and pipe) using deep reinforcement learning, simultaneously trained using multiple rewards. We train our RL algorithm in a multi-objective way. Our algorithm learns to generate continuous action for controlling the UAV. Our algorithm aims to generate waypoints for the UAV in such a way as to reach a goal area (shown by an RGB image) while avoiding static and dynamic obstacles. In this text, we use the RGB-D image as the input for the algorithm, and it learns to control the UAV in 3-DoF (x, y, and z). We train our robot in environments simulated by Gazebo sim. For communication between our algorithm and the simulated environments, we use the robot operating system. Finally, we visualize the trajectories generated by our trained algorithms using several methods and illustrate our results that clearly show our algorithm’s capability in learning to maximize the defined multi-objective reward.

show abstract

Deep Reinforcement Learning-Based Adaptive Controller for Trajectory Tracking and Altitude Control of an Aerial Robot

Cited by 11 publications

References 47 publications

On designing a configurable UAV autopilot for unmanned quadrotors

On designing a configurable UAV autopilot for unmanned quadrotors

Telemedicine System Applicability Using Drones in Pandemic Emergency Medical Situations

A Multi-Objective Reinforcement Learning Based Controller for Autonomous Navigation in Challenging Environments

Contact Info

Product

Resources

About