Interactive Task Encoding System for Learning-from-Observation

TL;DR

The paper introduces ITES, an interactive system that combines verbal instructions and visual demonstrations to teach household robots manipulative tasks efficiently through multimodal learning-from-observation.

Contribution

ITES is a novel input system that enhances robot programming by integrating multimodal cues and interactive correction within a learning-from-observation framework.

Findings

Successful teaching of multiple tasks on a real robot

Enhanced robustness through multimodal input

Effective interactive correction improves recognition accuracy

Abstract

We present the Interactive Task Encoding System (ITES) for teaching robots to perform manipulative tasks. ITES is designed as an input system for the Learning-from-Observation (LfO) framework, which enables household robots to be programmed using few-shot human demonstrations without the need for coding. In contrast to previous LfO systems that rely solely on visual demonstrations, ITES leverages both verbal instructions and interaction to enhance recognition robustness, thus enabling multimodal LfO. ITES identifies tasks from verbal instructions and extracts parameters from visual demonstrations. Meanwhile, the recognition result was reviewed by the user for interactive correction. Evaluations conducted on a real robot demonstrate the successful teaching of multiple operations for several scenarios, suggesting the usefulness of ITES for multimodal LfO. The source code is available at https://github.com/microsoft/symbolic-robot-teaching-interface.