Task and behavior formulations for robotic rock excavation

Abstract

This paper presents a formulation of excavation tasks and behaviors using finite state machines (FSM). A robotic excavation goal is achieved through several excavation tasks, while a task is completed through sequences of excavation behaviors, which are carries out by an ordered application of primitive, machine executable excavation actions. Both tasks and behaviors are specified by finite state machines that define all feasible sequences of behaviors or actions. The behavior selection for state transitions in a task FSM is achieved through situation assessment and behavior arbitration. For a behavior FSM, a method of terminating a behavior execution based on the activation levels of its actions is proposed. Since it is almost impossible to infer the exact status of bucket/environment interaction from force/torque data, excavation actions are specified using fuzzy logic rules acquired from human experience and heuristics. Experimental results have indicated that the proposed formulation has lead to a more efficient execution of excavation tasks than the authors' previous formulation.