Abstract by Meher Shaikh
Intent-based Robotic Path Replanning: When to Adapt New Paths in Dynamic Environments
For a goal-based robot navigation task in a dynamic environment, intent includes expectations about a path in terms of objectives to be met. If the planned path drifts from the human's intent as the environment changes, a new path needs to be planned --- called path replanning.
The replanning framework has three elements: (a)~integrating and adapting a fast online path-planning algorithms that generate trajectories conforming to the given intent; (b)~a mathematical model that says when a replanning must happen and (c)~evaluating replanning events, which we call `triggers'. An interactive graphical user interface enables a human to first communicate intent to the robot and then to replan via triggers. With a study of 50 MTurk participants, we assess here: what replanning triggers best enable a human-robot collaboration to persistently satisfy intent?