Compositional autonomy for humanoid robots with risk-aware decision-making

Abstract

This paper lays the foundations of risk-aware decision-making within the context of compositional robot autonomy for humanoid robots. In a nutshell, the idea is to compose task-level autonomous robot behaviors into a holistic motion plan by selecting a sequence of actions from a feasible action set. In doing so, we establish a total risk function to evaluate and assign a risk value to individual robot actions which then can be used to find the total risk of executing a plan. As a result, various actions can be composed into a complete autonomous motion plan while the robot is being cognizant to risks associated with executing one composition over another. In order to illustrate the concept, we introduce two specific risk measures, namely, the collision risk and the fall risk. We demonstrate the results from this foundational study of risk-aware compositional robot autonomy in simulation using NASA's Valkyrie humanoid robot.