TGK-Planner: An Efficient Topology Guided Kinodynamic Planner for Autonomous Quadrotors

In this letter, we propose a lightweight yet effective Topology Guided Kinodynamic planner (TGK-Planner) for quadrotor aggressive flights with limited onboard computing resources. The proposed system follows the traditional hierarchical planning workflow, novel designs to improve robustness and efficiency in both pathfinding trajectory optimization sub-modules. Firstly, topology guided graph, which roughly captures topological structure of environment guides state sampling sampling-based kinodynamic planner. way, significantly finding safe dynamically feasible trajectory. Then, refine smoothness continuity an framework, incorporates homotopy constraint guarantee safety program is formulated as sequence quadratic programmings (QPs) can be iteratively solved few milliseconds. Finally, integrated into fully autonomous validated various simulated real-world scenarios. Benchmark comparisons show that our method outperforms state-of-the-art methods regard quality. Moreover, will release code open-source package.