Experience-Based Models of Surface Proximal Aerial Robot Flight Performance in Wind

摘要: This work presents an experiment-driven aerodynamic disturbance modeling technique that leverages experiences from past flights to construct a predictive model of the exogenous forces acting on aerial robot. Specifically, we consider operation in turbulent air stemming interaction between wind and nearby surfaces. To model, employ Locally Weighted Projection Regression relate robot’s state experimentally learned freestream estimated during flight through environment. The approach is validated set tests indoor environment with artificially generated airflow illustrate computation this its generalizability across flow conditions, utility for disturbance-aware motion planning.