Robotics: Science and Systems (RSS 2023): Paper and Presentation
We are delighted to share our conference paper on optical flow control for Micro Air Vehicles (MAVs)! This paper introduces an efficient data-driven Incremental Nonlinear Dynamic Inversion (INDI) control scheme that addresses the challenge of nonlinear optical flow observables. Our method directly estimates the inverse of the time-varying control effectiveness in real-time, eliminating the need for the constant assumption and avoiding high computation in traditional INDI. We demonstrate the robustness and efficiency of this approach through numerical simulations and real-world flight tests, showcasing successful tracking and landings on both static and dynamic surfaces.