6-DOF UAV Path planning and tracking control for obstacle avoidance: a deep learning-based integrated approach

Path planning is crucial for achieving autonomous and safe flight of fixed-wing unmanned aerial vehicles (UAVs). The existing methods generally cannot simultaneously balance real-time performance, near optimality, and feasibility in three-dimensional obstacle environments. To this end, this paper proposes a deep learning-based integrated path planning and tracking control framework for obstacle avoidance. First, a fundamental framework, including an interfered fluid dynamical system (IFDS)-based path planning module and a backstepping control-based path tracking module, is established. Then, to satisfy high real-time requirements, a long short-term memory (LSTM)-based fast online decision-making network matched with the IFDS is developed. Extensive training samples are generated by the fundamental framework, and receding horizon control is employed to optimize these samples so that the LSTM can provide near-optimal coefficients for the IFDS. Furthermore, the dynamic characteristics of an actual UAV system and the performance of the tracking controller are fully considered during sample generation, enabling that the paths planned by the LSTM-assisted IFDS are highly feasible. Finally, the results of numerical simulations and hardware-in-the-loop experiments show that our method can plan near-optimal obstacle-free paths with high feasibility in real-time.