Methodological remarks on contraction theory

Because contraction analysis stems from a differential and incremental framework, the nature and methodology of contraction-based proofs are significantly different from those of their Lyapunov-based counterparts. This paper specifically studies this issue, and illustrates it by revisiting some classical examples traditionatly addressed using Lyapunov theory. Even in these cases, contraction tools can often yield significantly simplified analysis. The examples include adaptive control, robotics, and a proof of convergence of the deterministic Extended Kalman Filter.