Learning modular language-conditioned robot policies through attention

1Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Training language-conditioned policies is typically time-consuming and resource-intensive. Additionally, the resulting controllers are tailored to the specific robot they were trained on, making it difficult to transfer them to other robots with different dynamics. To address these challenges, we propose a new approach called Hierarchical Modularity, which enables more efficient training and subsequent transfer of such policies across different types of robots. The approach incorporates Supervised Attention which bridges the gap between modular and end-to-end learning by enabling the re-use of functional building blocks. In this contribution, we build upon our previous work, showcasing the extended utilities and improved performance by expanding the hierarchy to include new tasks and introducing an automated pipeline for synthesizing a large quantity of novel objects. We demonstrate the effectiveness of this approach through extensive simulated and real-world robot manipulation experiments.

Cite

CITATION STYLE

APA

Zhou, Y., Sonawani, S., Phielipp, M., Ben Amor, H., & Stepputtis, S. (2023). Learning modular language-conditioned robot policies through attention. Autonomous Robots, 47(8), 1013–1033. https://doi.org/10.1007/s10514-023-10129-1

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free