HELP: Hierarchical Embodied Language Planner for Household Tasks

TL;DR

The paper introduces HELP, a hierarchical planning architecture using multiple LLM-based agents for household tasks, demonstrating its effectiveness in real-world embodied agent experiments with small open-source models.

Contribution

We propose a novel hierarchical embodied language planner (HELP) that leverages multiple LLM-based agents for complex household task planning.

Findings

Effective in real-world household tasks

Utilizes small open-source LLMs for deployment

Demonstrates hierarchical planning benefits

Abstract

Embodied agents tasked with complex scenarios, whether in real or simulated environments, rely heavily on robust planning capabilities. When instructions are formulated in natural language, large language models (LLMs) equipped with extensive linguistic knowledge can play this role. However, to effectively exploit the ability of such models to handle linguistic ambiguity, to retrieve information from the environment, and to be based on the available skills of an agent, an appropriate architecture must be designed. We propose a Hierarchical Embodied Language Planner, called HELP, consisting of a set of LLM-based agents, each dedicated to solving a different subtask. We evaluate the proposed approach on a household task and perform real-world experiments with an embodied agent. We also focus on the use of open source LLMs with a relatively small number of parameters, to enable autonomous deployment.