Inverting Learned Dynamics Models for Aggressive Multirotor Control
This addresses control accuracy for multirotor drones in challenging conditions, though it appears incremental as it builds on existing model learning and inverse dynamics approaches.
The paper tackles the problem of accurate multirotor control under disturbances and modeling errors by applying inverse dynamics to a learned acceleration error model, achieving reduced tracking error for aggressive trajectories with accelerations over 7 m/s² in simulation and hardware.
We present a control strategy that applies inverse dynamics to a learned acceleration error model for accurate multirotor control input generation. This allows us to retain accurate trajectory and control input generation despite the presence of exogenous disturbances and modeling errors. Although accurate control input generation is traditionally possible when combined with parameter learning-based techniques, we propose a method that can do so while solving the relatively easier non-parametric model learning problem. We show that our technique is able to compensate for a larger class of model disturbances than traditional techniques can and we show reduced tracking error while following trajectories demanding accelerations of more than 7 m/s^2 in multirotor simulation and hardware experiments.