Optimal Interactive Learning on the Job via Facility Location Planning

TL;DR

This paper introduces COIL, a multi-task interactive learning framework for robots that minimizes human effort by strategically selecting query types, formulated as a facility location problem, and extended to handle uncertain preferences with belief space planning.

Contribution

The paper presents COIL, a novel multi-task interaction planner using facility location planning, capable of reducing human effort in robot learning across multiple tasks, including handling preference uncertainty.

Findings

Significantly reduces human effort in multi-task robot learning.

Maintains high task success rates with less human input.

Operates efficiently with polynomial-time algorithms.

Abstract

Collaborative robots must continually adapt to novel tasks and user preferences without overburdening the user. While prior interactive robot learning methods aim to reduce human effort, they are typically limited to single-task scenarios and are not well-suited for sustained, multi-task collaboration. We propose COIL (Cost-Optimal Interactive Learning) -- a multi-task interaction planner that minimizes human effort across a sequence of tasks by strategically selecting among three query types (skill, preference, and help). When user preferences are known, we formulate COIL as an uncapacitated facility location (UFL) problem, which enables bounded-suboptimal planning in polynomial time using off-the-shelf approximation algorithms. We extend our formulation to handle uncertainty in user preferences by incorporating one-step belief space planning, which uses these approximation algorithms as subroutines to maintain polynomial-time performance. Simulated and physical experiments on manipulation tasks show that our framework significantly reduces the amount of work allocated to the human while maintaining successful task completion.