Activity Planning for Assistive Robots Using Chance-Constrained Stochastic Programming

In this article, we present a framework for planning an activity to be executed with the support of robotic navigation assistant. The two main components are and motion planner. planner composes sequence abstract activities, chosen from given set, synthesize plan. Each is associated point interest in environment probabilistic parameters that depend on plan, which characterized by simulations realistic scenarios. low-level action pass next handled planner, secures physical feasibility actions their compatibility constraints posed user environment. Indeed, final plan must respect optimise his/her satisfaction activity. We show possible model problem as chance constrained optimization along efficient technique find high-quality solutions.