从真实操作视频中预训练统一的机器人规划域，实现零样本泛化任务求解。
UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning
- 从1.2万段操作视频提取原子域，构建包含3137个操作符的统一规划域。
- 在未见过的任务上实现58%更高成功率、160%更优计划质量。
- 适合需要强泛化能力的机器人任务规划研究者使用。
现实世界中的机器人任务规划需要对语言和视觉中的隐含约束进行推理。尽管大语言模型（LLMs）和视觉语言模型（VLMs）提供了强大先验，但它们在长时序结构和符号接地方面表现不佳。现有结合LLMs与符号规划的方法多依赖手工设计或狭窄领域，限制了泛化能力。本文提出UniDomain框架，从机器人操作演示中预训练一个统一的PDDL领域，并用于在线机器人任务规划。该框架从12,393段操作视频中提取原子域，构建包含3137个操作符、2875个谓词和16481条因果边的统一领域。针对目标任务类别，它从统一领域中检索相关原子域，并系统融合生成高质量元领域，支持规划中的组合泛化。在多样化的现实任务实验中，UniDomain实现了零样本下复杂未见任务的求解，在任务成功率上比现有最优的LLM和LLM-PDDL基线提升最高达58%，计划最优性提升160%。
原文摘要 · Abstract (English)
Robotic task planning in real-world environments requires reasoning over implicit constraints from language and vision. While LLMs and VLMs offer strong priors, they struggle with long-horizon structure and symbolic grounding. Existing methods that combine LLMs with symbolic planning often rely on handcrafted or narrow domains, limiting generalization. We propose UniDomain, a framework that pre-trains a PDDL domain from robot manipulation demonstrations and applies it for online robotic task planning. It extracts atomic domains from 12,393 manipulation videos to form a unified domain with 3137 operators, 2875 predicates, and 16481 causal edges. Given a target class of tasks, it retrieves relevant atomics from the unified domain and systematically fuses them into high-quality meta-domains to support compositional generalization in planning. Experiments on diverse real-world tasks show that UniDomain solves complex, unseen tasks in a zero-shot manner, achieving up to 58% higher task success and 160% improvement in plan optimality over state-of-the-art LLM and LLM-PDDL baselines.
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。