用分层语言规划器让机器人理解家庭任务指令并自主执行
HELP: Hierarchical Embodied Language Planner for Household Tasks
- 分层设计多个LLM代理，分别处理不同子任务
- 在真实机器人上验证，使用小参数开源LLM实现部署
- 擅长处理自然语言模糊性，适合家庭服务机器人
面对复杂场景的具身智能体（无论在真实还是仿真环境中），其成功依赖于强大的规划能力。当任务指令以自然语言形式给出时，具备丰富语言知识的大语言模型（LLMs）可承担规划角色。然而，要有效利用这些模型处理语言歧义、从环境获取信息以及基于可用技能进行决策的能力，必须设计合适的架构。本文提出一种分层具身语言规划器（HELP），由多个专用的LLM代理组成，各自负责解决不同的子任务。我们在家庭任务场景中评估该方法，并在真实机器人上进行了实验。研究特别关注使用参数量较小的开源大模型，以支持自主部署。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。