Evasive Maneuvering for UAVs: An MPC Approach

Flying autonomously in a workspace populated by obstacles is one of the main goals when working with Unmanned Aerial Vehicles (UAV). To address this challenge, this paper presents a model predictive flight controller that drives the UAV through collision-free trajectories to reach a given pose or follow a way-point path. The major advantage of this approach lies on the inclusion of three-dimensional obstacle avoidance in the control layer by adding ellipsoidal constraints to the optimal control problem. The obstacles can be added, moved and resized online, providing a way to perform waypoint navigation without the need of motion planning. In addition, the delays of the system are considered in the prediction by an experimental first order with delay model of the system. Successful experiments in 3D path tracking and obstacle avoidance validates its effectiveness for sense-and-avoid and surveillance applications presenting the proper structure
to extent its autonomy and applications.