Predictive Interfaces for Long-Distance Tele-Operations

Abstract

Humanoid robots have a practical advantage over other robotic platforms for use in space-based construction and maintenance because they can share tools and work interactively with astronauts. A major disadvantage is that they are difficult to control due to the large number of degrees of freedom, which makes it difficult to synthesize autonomous behavior using conventional means. We address the development of predictive tele-operator interfaces for humanoid robots with respect to two basic challenges. We first address automating the transition from fully tele-operated systems towards degrees of autonomy. We then develop compensation for the time-delay that exists when sending telemetry data from a remote operation point to robots located at low Earth orbit and beyond. Our primary goal is to show that within an operator’s movement, early prediction is possible while at the same time eliminating false predictions/alarms and minimizing missed detections.