Autonomous LHD loading

Abstract

Machine vision is used for guidance of the autonomous loading of ore during underground mining. Three dimensional spatial data of the ore pile is derived in real-time from camera images and is used for planning the scooping process. A sensory integration technique combines feedforward from the same vision system with wheel odometry to guide the vehicle to and from the ore pile. A computationally efficient kinematic model of the vehicle is derived and its application discussed. LHD (load-haul-dump) vehicles are used extensively in underground mining. Increasing production costs and the ongoing quest for improved safety provide a great incentive to automate their working cycle. This research concentrates on a major component of this task-automation of loading. The proposed loading controller will load an LHD swiftly and safely while leaving the ore pile in a suitable condition for subsequent bucket scoops.