A Kinodynamic Aggressive Trajectory Planner For Narrow Passages

TL;DR

This paper introduces the Kinodynamic Aggressive Trajectory (KAT) algorithm for planning aggressive, feasible paths for quadcopters through narrow passages, transforming global constraints into local ones for computational efficiency.

Contribution

The paper presents a novel kinodynamic planning method that divides robot states into local sets and plans around narrow passages, enabling efficient aggressive maneuver planning.

Findings

Successfully plans trajectories through narrow inclined holes

Average computation time is around 32 seconds for challenging scenarios

Transforms global constraints into local constraints for tractability

Abstract

Planning a path for a nonholonomic robot is a challenging topic in motion planning and it becomes more difficult when the desired path contains narrow passages. This kind of scenario can arise, for instance, when quadcopters search a collapsed building after a natural disaster. Choosing the quadcopter as the target platform, this paper proposes the Kinodynamic Aggressive Trajectory (KAT) motion planning algorithm, which aims to compute aggressive trajectories for narrow passages under nonholonomic constraints. This type of maneuvers is necessary because the dynamics of quadcopters entail that some narrow passages can only be traversed at high speed. To find the best path, the KAT uses RRT to determine a holonomic path first and then adjusts it to satisfy the nonholonomic constraints. The innovations in this process are: 1) The states of the robot are divided into near-holonomic set and non-holonomic set, which makes the constraints local rather than global; 2) For each of the most confined waypoints in the path, KAT plans forward and backward simultaneously around the waypoint to find a feasible local trajectory traversing the narrow passage. Our approach thus transforms a globally-constrained planning problem into a problem with local constraints, and as a result, the computation becomes tractable. We evaluate KAT by applying it to a quadcopter flying through two inclined holes that require aggressive maneuvers in a simulated environment. The average computation time to successfully find a solution for passing two 50 degree inclined holes is around 32 seconds.