Quadcopter neural controller for take-off and landing in windy environments

Olaz, Xabier; Aláez, Daniel; Prieto, Manuel; Villadangos, J.; Astráin, José Javier

doi:10.1016/j.eswa.2023.120146

Cited by 7 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of reward, they used a cost function and minimized the sum of position, angular velocity and linear velocities. Olaz et al [13] used PPO and DDPG for stabilized taking-off and landing of the UAV in the windy environment. They made a decoupling by outputting target forces and momentum from the actor neural network and then linearly transforming those to motor angular velocities.…”

Section: Related Workmentioning

confidence: 99%

Learning Stabilization Control of Quadrotor in Near-Ground Setting Using Reinforcement Learning

Briliauskas

2024

ITC

View full text Add to dashboard Cite

With the development of intelligent systems, the popularity of using micro aerial vehicles (MAV) increases significantly in the fields of rescue, photography, security, agriculture, and warfare. New modern solutions of machine learning like ChatGPT that are fine-tuned using reinforcement learning (RL) provides evidence of new trends in seeking general artificial intelligence. RL has already been proven to work as a flight controller for MAV performing better than Proportional Integral Derivative (PID)-based solutions. However, using negative Euclidean distance to the target point as the reward function is sufficient in obstacle-free spaces, e.g. in the air, but fails in special cases, e.g. when training near the ground. In this work, we address this issue by proposing a new reward function with early termination. It not only allows to successfully train Proximal Policy Optimization (PPO) algorithm to stabilize the quadrotor in the near-ground setting, but also achieves lower Euclidean distance error compared to the baseline setup.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Stabilization Control of Quadrotor in Near-Ground Setting Using Reinforcement Learning

Briliauskas

2024

ITC

View full text Add to dashboard Cite

show abstract

“…From the control development perspective, the control of UAV systems is well established in the literature with both linear and nonlinear control techniques [6,[28][29][30]. Sliding-mode control (SMC) is a nonlinear control tool that is based on Lyapunov stability criteria.…”

Section: Introductionmentioning

confidence: 99%

Design and Control of an Innovative Overactuated Thrust Vectoring Six-DoF Quadrotor for Extreme and Challenging Environments

Kara-Mohamed,

Zhang,

Yan

2023

Un. Sys.

View full text Add to dashboard Cite

The wide spectrum of recent applications for UAVs imposes further challenges to their abilities and control. This is especially true when operating in harsh and hostile environments where disturbances are huge and actuators are prone to failure. Conventional systems and traditional control techniques are not sufficient for stability and tracking under these circumstances. This paper proposes a unique innovative overactuated quadrotor system that has six DoFs. The vehicle has four rotors and each rotor can tilt independently in the [Formula: see text]-plane. It has the ability to correct its position and attitude in a decoupled way which is different from the conventional quadrotor configurations. Sliding-mode control associated with switching control mode is used for the control algorithm of the system. The system shows agility in the face of large disturbances and robustness against actuator failure which makes it a perfect fit for extreme and challenging environments. The concept of the system and its ability are illustrated in simulation with promising results.

show abstract

Bridging the simulation-to-real gap of depth images for deep reinforcement learning

Jang,

Baek,

Jeon

et al. 2024

Expert Systems with Applications

View full text Add to dashboard Cite

Quadcopter neural controller for take-off and landing in windy environments

Cited by 7 publications

References 29 publications

Learning Stabilization Control of Quadrotor in Near-Ground Setting Using Reinforcement Learning

Learning Stabilization Control of Quadrotor in Near-Ground Setting Using Reinforcement Learning

Design and Control of an Innovative Overactuated Thrust Vectoring Six-DoF Quadrotor for Extreme and Challenging Environments

Bridging the simulation-to-real gap of depth images for deep reinforcement learning

Contact Info

Product

Resources

About