A Data-Driven Dynamic Obstacle Avoidance Method for Liquid-Carrying Plant Protection UAVs

Autonomous sprayer UAVs are one of the most used aerial machines in modern agriculture. During flight missions, some common narrow obstacles appear flying zone. These non-detectable from satellite images and biggest challenges for autonomous farmland. This work introduces an obstacle avoidance architecture specifically UAVs. has generality spraying UAV problem, it reduces reliance on global mapping approach computes avoiding path based onboard sensor fusion system real-time. Moreover, autonomously determines transition several maneuver states using current liquid data dynamics obtained by offline identification. accurately tracks nonlinear time-variant systems. To verify performance approach, we performed multiple simulations with different method demonstrated a high coverage more than 98% while successfully all vertical obstacles. We also adaptability our control architecture; safe distance between can be changed specifying value high-level parameter controller. The proposed adds to precision agriculture, mission time, maximizes area coverage.