Towards Preference Learning for Autonomous Ground Robot Navigation Tasks
This work addresses the challenge of personalizing robot navigation for users in exploration tasks, though it appears incremental as it builds on existing methods.
The paper tackles the problem of enabling autonomous ground robots to learn user preferences for navigation tasks through continued interactions, aiming to execute behaviors as expected by the user, with a work-in-progress approach that integrates reinforcement learning, motion planning, and natural language processing.
We are interested in the design of autonomous robot behaviors that learn the preferences of users over continued interactions, with the goal of efficiently executing navigation behaviors in a way that the user expects. In this paper, we discuss our work in progress to modify a general model for robot navigation behaviors in an exploration task on a per-user basis using preference-based reinforcement learning. The novel contribution of this approach is that it combines reinforcement learning, motion planning, and natural language processing to allow an autonomous agent to learn from sustained dialogue with a human teammate as opposed to one-off instructions.