Learning User-Preferred Mappings for Intuitive Robot Control

TL;DR

This paper introduces a personalized, data-efficient method for learning human-preferred control mappings in robot teleoperation, improving intuitiveness and user experience by leveraging strong priors about human input behaviors.

Contribution

The authors propose a novel approach that learns individualized control mappings from few examples by incorporating priors, enhancing teleoperation intuitiveness over existing fixed or non-personalized methods.

Findings

Learning personalized mappings improves user performance.

Incorporating priors leads to data-efficient learning.

Method outperforms manual and non-intuitive alignments.

Abstract

When humans control drones, cars, and robots, we often have some preconceived notion of how our inputs should make the system behave. Existing approaches to teleoperation typically assume a one-size-fits-all approach, where the designers pre-define a mapping between human inputs and robot actions, and every user must adapt to this mapping over repeated interactions. Instead, we propose a personalized method for learning the human's preferred or preconceived mapping from a few robot queries. Given a robot controller, we identify an alignment model that transforms the human's inputs so that the controller's output matches their expectations. We make this approach data-efficient by recognizing that human mappings have strong priors: we expect the input space to be proportional, reversable, and consistent. Incorporating these priors ensures that the robot learns an intuitive mapping from few examples. We test our learning approach in robot manipulation tasks inspired by assistive settings, where each user has different personal preferences and physical capabilities for teleoperating the robot arm. Our simulated and experimental results suggest that learning the mapping between inputs and robot actions improves objective and subjective performance when compared to manually defined alignments or learned alignments without intuitive priors. The supplementary video showing these user studies can be found at: https://youtu.be/rKHka0_48-Q.