论文/arXiv 2610.07649·22 天前

OntoPlan：一种面向可扩展机器人任务规划的本体支撑场景表示与智能体框架

针对大环境长程任务中LLM规划退化，OntoPlan以本体场景表示检索相关信息并生成可执行计划，在室内任务上验证。

AI 整理

• 具身模型

原文链接：OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning（arXiv 2610.07649 · 发布日期：2026-10-06）

OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning

针对大环境长程任务中LLM规划退化，OntoPlan以本体场景表示检索相关信息并生成可执行计划，在室内任务上验证。

核心要点

• LLM以文本接收空间信息时易丢失上下文，且随环境增大令牌成本上升。
• OntoPlan用共享符号词汇对齐物体、空间、关系和状态，支持空间推理与规划。
• 在150个跨五个室内环境的任务上，平均任务成功为0.89，高于最强基线0.27。
• 平均每任务使用18.1k令牌，约比最高效基线少5.6倍，并已公开代码。

验证范围与局限：验证范围为150个通用任务、五个室内环境和三种场景尺度。

英文摘要 (Abstract)

Large language model (LLM)-based robot task planning is promising for open-ended instruction following, but degrades on long-horizon tasks in large environments. When spatial information is conveyed to the LLM through text, the model can fail to capture spatial context, and token cost grows with environment size. Generating action sequences directly with an LLM also makes it difficult to satisfy the current world state and action preconditions. We address this with an ontology-grounded scene representation that aligns objects, spaces, relations, and states in a shared symbolic vocabulary for spatial reasoning and task planning, and with OntoPlan, an agentic framework that interprets instructions, selectively retrieves task-relevant information, formalizes goals and constraints, and produces executable plans. Across 150 general tasks spanning five indoor environments and three scene scales, OntoPlan achieves 0.89 average task success, compared with 0.27 for the strongest baseline, while using 18.1k total tokens per task on average, about 5.6$\times$ fewer than the most efficient baseline. These advantages persist as scene scale increases, whereas prior methods degrade more sharply in success and remain far more costly in tokens. OntoPlan also responds appropriately to ambiguous or infeasible instructions by asking follow-up questions or reporting insufficient information rather than committing to invalid plans. Code available at https://github.com/namhyeongwoo/OntoPlan.

作者：Hyeongwoo Nam, Woongje Cho, Juwon Kim, Jongeun Choi

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.07649：OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning访问 2026-10-21