Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)
For quadrotor control researchers, this paper presents an incremental improvement by changing the control output from RPMs to thrust vector, resulting in faster training and better performance.
This paper proposes a reinforcement learning-based control architecture for quadrotors that controls the thrust vector instead of individual rotor RPMs, using Soft Actor-Critic. The proposed method achieves faster training and smoother, more accurate path-following compared to conventional RPM controllers.
This paper proposes a new Reinforcement Learning (RL) based control architecture for quadrotors. With the literature focusing on controlling the four rotors' RPMs directly, this paper aims to control the quadrotor's thrust vector. The RL agent computes the percentage of overall thrust along the quadrotor's z-axis along with the desired Roll ($ϕ$) and Pitch ($θ$) angles. The agent then sends the calculated control signals along with the current quadrotor's Yaw angle ($ψ$) to an attitude PID controller. The PID controller then maps the control signals to motor RPMs. The Soft Actor-Critic algorithm, a model-free off-policy stochastic RL algorithm, was used to train the RL agents. Training results show the faster training time of the proposed thrust vector controller in comparison to the conventional RPM controllers. Simulation results show smoother and more accurate path-following for the proposed thrust vector controller.