This paper describes experimental results for autonomous robotic rock excavation with fuzzy logic and neural networks. An excavation goal is decomposed into several tasks, whereas a take is accomplished by executing appropriate excavation behaviors. Finally, a behavior is carried out by a sequence of primitive, machine executing excavation actions. Excavation goals, tasks, and behaviors are specified using finite state machines (FSM) based on excavation heuristics and expertise from skilled human operators. The decision making in the FSMs are implemented using neural networks which are capable of improving their performance from previous task executions. Excavation actions are given using fuzzy logic rules acquired from human experience and heuristics. Several experiments are presented that demonstrate the system's ability to complete required excavation tasks effectively.

To automate a mining excavator the control issues resulting from environmental uncertainties must be solved. In particular the interactions between the excavation tool and the excavation environment are dynamic, unstructured and complex. Thus, generating rigorous mathematical models as required by conventional control techniques is extremely difficult if possible. This paper presents an excavator controller that uses fuzzy logic to interpret forces and torques gathered from a wrist mounted force/torque sensor during the excavation process. This approach enables the transfer of human heuristics and expert knowledge to the controller. Experimental results from several excavation tests using the fuzzy logic controller are given. These results represent the first step toward an integrated approach that uses force/torque, vision, and other sensor data to perform generic tasks in uncertain mining environments.>