Robust vision-based nonlinear formation control

Abstract

This paper presents vision-based strategies for decentralized stabilization of unmanned vehicle (UV) formations. The key point of the algorithms is that they only require knowledge of leader-follower relative distances or bearing angles. These data are computed using measurements from pan-controlled off-the-shelf cameras on-board following robots, eliminating sensitivity to information flow among vehicles. The approaches are based on output feedback algorithms that use high-gain observers to estimate the derivatives of the UV's relative positions. A Lyapunov stability analysis guarantees that the closed-loop system is stable and the formation error can be made arbitrarily small. A 3D virtual environment and a vision system are used to validate the proposed methodologies