Towards Online Learning from Corrective Demonstrations

TL;DR

This paper introduces the SITU algorithm, enabling robots to efficiently update their task models through local corrections from humans, facilitating real-time learning in dynamic environments.

Contribution

The paper presents a novel local update method, SITU, that allows efficient incorporation of corrective demonstrations without reasoning over the entire model.

Findings

SITU enables faster task model updates.

Local reasoning reduces computational complexity.

Preliminary results show promising efficiency improvements.

Abstract

Robots operating in real-world human environments will likely encounter task execution failures. To address this, we would like to allow co-present humans to refine the robot's task model as errors are encountered. Existing approaches to task model modification require reasoning over the entire dataset and model, limiting the rate of corrective updates. We introduce the State-Indexed Task Updates (SITU) algorithm to efficiently incorporate corrective demonstrations into an existing task model by iteratively making local updates that only require reasoning over a small subset of the model. In future work, we will evaluate this approach with a user study.