Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Winds
This work addresses control challenges for quadrotors in dynamic environments, offering a method to improve adaptability, but it is incremental as it builds on existing meta-learning and MPC techniques.
The paper tackled the problem of controlling quadrotors in challenging wind conditions by proposing Proto-MPC, an encoder-prototype-decoder approach integrated with model predictive control, which demonstrated robust trajectory tracking performance in simulations under static and spatially varying side winds.
Quadrotors are increasingly used in the evolving field of aerial robotics for their agility and mechanical simplicity. However, inherent uncertainties, such as aerodynamic effects coupled with quadrotors' operation in dynamically changing environments, pose significant challenges for traditional, nominal model-based control designs. We propose a multi-task meta-learning method called Encoder-Prototype-Decoder (EPD), which has the advantage of effectively balancing shared and distinctive representations across diverse training tasks. Subsequently, we integrate the EPD model into a model predictive control problem (Proto-MPC) to enhance the quadrotor's ability to adapt and operate across a spectrum of dynamically changing tasks with an efficient online implementation. We validate the proposed method in simulations, which demonstrates Proto-MPC's robust performance in trajectory tracking of a quadrotor being subject to static and spatially varying side winds.