Language-Conditioned Change-point Detection to Identify Sub-Tasks in Robotics Domains

TL;DR

This paper introduces a language-conditioned change-point detection method to identify sub-tasks within robot trajectories guided by natural language instructions, improving accuracy over baseline methods and analyzing sample complexity for real-world applicability.

Contribution

The work presents a novel approach that adapts video moment retrieval techniques to robot sub-task segmentation using language, with extensive experiments and sample complexity analysis.

Findings

Achieved 1.78% improvement over baseline in sub-task identification accuracy.

Demonstrated the feasibility of language-conditioned change-point detection in robotics.

Provided insights into sample complexity requirements for real robot scenarios.

Abstract

In this work, we present an approach to identify sub-tasks within a demonstrated robot trajectory using language instructions. We identify these sub-tasks using language provided during demonstrations as guidance to identify sub-segments of a longer robot trajectory. Given a sequence of natural language instructions and a long trajectory consisting of image frames and discrete actions, we want to map an instruction to a smaller fragment of the trajectory. Unlike previous instruction following works which directly learn the mapping from language to a policy, we propose a language-conditioned change-point detection method to identify sub-tasks in a problem. Our approach learns the relationship between constituent segments of a long language command and corresponding constituent segments of a trajectory. These constituent trajectory segments can be used to learn subtasks or sub-goals for planning or options as demonstrated by previous related work. Our insight in this work is that the language-conditioned robot change-point detection problem is similar to the existing video moment retrieval works used to identify sub-segments within online videos. Through extensive experimentation, we demonstrate a $1.78_{\pm 0.82}\%$ improvement over a baseline approach in accurately identifying sub-tasks within a trajectory using our proposed method. Moreover, we present a comprehensive study investigating sample complexity requirements on learning this mapping, between language and trajectory sub-segments, to understand if the video retrieval-based methods are realistic in real robot scenarios.