Sharing Control Can Increase Excavation Productivity

Abstract

Researchers at the Georgia Institute of Technology have demonstrated that the completion time of common excavation tasks is decreased when an operator and an electronic agent share control of the actuator velocity commands. In this Blended Shared Control architecture, the intended operator task is estimated with a recursive algorithm; the task is optimized in real time; and a command perturbation is computed which results in a lower task completion time when summed with the operator command. Experimental results compare Blended Shared Control to conventional manual control and manual control supplemented with haptic feedback. Trials indicate that Blended Shared Control decreases task completion time by up to 15 percent.