Simultaneous Spatial and Temporal Assignment for Fast UAV Trajectory Optimization Using Bilevel Optimization

In this letter, we propose a framework for fast trajectory planning unmanned aerial vehicles (UAVs). Our is reformulated from an existing bilevel optimization, in which the lower-level problem solves optimal with fixed time allocation, whereas upper-level updates allocation using analytical gradients. The incorporates safety-set constraints (in form of inequality constraints) and cast as convex quadratic program (QP). formulation modifies QP by excluding safety sets, significantly reduces computation time. are moved to problem, where feasible waypoints updated together gradients enabled OptNet. We validate our approach simulations, method's scales linearly respect number contrast state-of-the-art that exponentially.