Adaptive Motion Planning Based on Decision-Making for Quadrotors

Adaptive ability is essential for a quadrotor to fly in a complex environment with various situations thus a lightweight motion planner is necessary to ensure the quadrotor’s maneuverability. At present, the ESDF-free framework has become a mainstream technology in the field of local motion planning. However, it models the collision cost explicitly which increases computational burden. In this article, an adaptive motion planning method is proposed based on decision making within the ESDF-free framework for quadrotors. At first, a decision making model is constructed based on the finite-state machine(FSM) which can improve the adaptive ability of quadrotors in complex environment. Then a local trajectory can be obtained within the ESDF-free framework and collision cost is considered implicitly through fitting a safe trajectory. The proposed method has been validated with a large number of experiments and it has shown excellent performance compared with the state-of-the-art methods.