EXPERIMENTAL RESULTS OF ROBOTIC EXCAVATION USING FUZZY BEHAVIOR CONTROL

This paper presents experimental results of robotic excavation based o n fuzzy behavior programs. A robotic excavation goal is achieved throu gh several excavation tasks, while a task is completed through sequenc es of excavation behaviors carried out by an ordered application of pr imitive, machine-executable excavation actions. Both tasks and behavio rs are specified by finite state machines (FSM) that define all feasib le sequences of behaviors or actions. Behavior selection for state tra nsitions in a task FSM is achieved through situation assessment and be havior arbitration. For a behavior FSM, a method of terminating a beha vior execution based on the activation levels of its actions is propos ed. 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 indicate that the proposed formulatio n has led to a more efficient execution of excavation tasks than a pre vious formulation.