Abstract by Meher Shaikh
When does a human replan? Exploring intent-based replanning in multi-objective path planning,
In navigating a robot in a dynamic environment, human intent can mean to choose a trade-off between multiple competing objectives such as Go quickly and stealthily. Given human intentions about a path, the path should obey the intent throughout the entire navigation. If the path drifts from the human’s intent because the environment changes, then a new robotic-path needs to be planned — referred to as path-replanning.
To re-plan paths, our interactive interface considers three system-initiated triggers, and one user-generated trigger. These triggers are to replan at: regular time intervals, when the current robotic path deviates from the intent, when a better path can be obtained from a different homotopy, and when the user pauses the robot. We address two critical questions: When is a re-planned path acceptable to a human? and How should a planner involve a human in replanning?.