论文arXiv 2512.007759 天前
SAGAS框架实现无模型离线LTL规划零样本泛化
本文由 AI 根据公开内容整理,可能有误,请以原文为准:SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning(arXiv 2512.00775)
核心内容
针对线性时序逻辑(LTL)长程任务规划中模型依赖强、学习需在线交互的痛点,arXiv论文提出SAGAS框架。该方法专为离线、无模型场景设计,仅利用固定且任务无关的轨迹片段,无需动力学模型、任务演示或在线数据采集,解决了传统方法在模型精度与训练成本间的权衡难题。
SAGAS从碎片化离线数据中学习可复用的潜在可达性图及冻结的目标条件执行器。面对新LTL公式时,通过语义图增强将状态命题映射至图结构,并利用Büchi积搜索合成代价感知的路径点计划。该架构分离学习与规划,支持对未见公式及谓词的零样本泛化,在OGBench移动与操作任务套件验证了高成功率与低执行成本优势。
关键看点
- 离线无模型架构:仅依赖固定任务无关轨迹片段,无需动力学模型、任务演示或在线数据收集即可进行LTL规划
- 语义图增强机制:结合符号合成组合性与数据驱动可达性结构,通过Büchi积搜索生成代价感知的前后缀路径点计划
- 零样本泛化能力:学习与规划解耦,无需任务特定奖励或策略重训,即可适配未见过的LTL公式与新谓词
- 多域基准验证:在OGBench移动导航与机械臂操作任务套件中,成功率与执行成本指标均显著优于现有基线
工程与产业观察
SAGAS为具身智能长程任务规划提供了纯离线范式,通过解耦通用技能学习与逻辑推理,大幅降低了对环境建模和在线试错的依赖。这种基于图结构的零样本泛化能力,对于解决非结构化场景中复杂指令的冷启动问题具有重要工程参考价值,尤其适用于难以频繁重训的部署场景。
英文摘要 (Abstract)
Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in an offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph and applies B"uchi product search to synthesize a cost-aware accepting prefix--suffix waypoint plan executed by the frozen executor. This separation of learning and planning enables zero-shot generalization to unseen LTL formulas and new predicates supported by the offline data, without task-specific rewards, additional data collection, or policy retraining. Experiments on LTL task suites constructed from OGBench locomotion domains show that SAGAS achieves higher success rates and lower execution costs than baselines on diverse unseen tasks, with further evaluation in OGBench Scene demonstrating its applicability to robotic manipulation.
作者:Ruijia Liu, Ancheng Hou, Xiang Yin
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)