GUARD: Toward a Compromise between Traditional Control and Learning for Safe Robot Systems

This paper presents the framework $\mathbf{\text{GUARD}}$ ($\mathbf{\text{G}}$uided robot control via $\mathbf{\text{U}}$ncertainty attribution and prob$\mathbf{\text{A}}$bilistic kernel optimization for $\mathbf{\text{R}}$isk-aware $\mathbf{\text{D}}$ecision making) that combines traditional control with an uncertainty-aware perception technique using active learning with real-time capability for safe robot collision avoidance. By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications. By unifying a reactive model predictive countouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique, \emph{GUARD} inherently handles the existing ambiguity of the term $\mathit{\text{safety}}$ that exists in robotics literature. Experimental studies indicate the high performance of \emph{GUARD}, thereby highlighting the relevance and need to broaden its applicability in future.