From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control

TL;DR

This paper introduces Learnable Latent Codes as Bridges (LCB), a novel architecture that enhances hierarchical robot control by enabling flexible goal communication and end-to-end finetuning, outperforming language-only interfaces on complex tasks.

Contribution

The paper proposes LCB, a learnable latent code interface that overcomes language limitations and facilitates finetuning in hierarchical robot control architectures.

Findings

LCB outperforms language-only interfaces on reasoning tasks.

Enables end-to-end finetuning without losing pre-trained embeddings.

Effective on benchmarks like Language Table and Calvin.

Abstract

Hierarchical control for robotics has long been plagued by the need to have a well defined interface layer to communicate between high-level task planners and low-level policies. With the advent of LLMs, language has been emerging as a prospective interface layer. However, this has several limitations. Not all tasks can be decomposed into steps that are easily expressible in natural language (e.g. performing a dance routine). Further, it makes end-to-end finetuning on embodied data challenging due to domain shift and catastrophic forgetting. We introduce our method -- Learnable Latent Codes as Bridges (LCB) -- as an alternate architecture to overcome these limitations. \method~uses a learnable latent code to act as a bridge between LLMs and low-level policies. This enables LLMs to flexibly communicate goals in the task plan without being entirely constrained by language limitations. Additionally, it enables end-to-end finetuning without destroying the embedding space of word tokens learned during pre-training. Through experiments on Language Table and Calvin, two common language based benchmarks for embodied agents, we find that \method~outperforms baselines (including those w/ GPT-4V) that leverage pure language as the interface layer on tasks that require reasoning and multi-step behaviors.