PerFACT: 基于LLM驱动的数据集合成与融合动作分块变换器的运动策略
PerFACT: Motion Policy with LLM-Powered Dataset Synthesis and Fusion Action-Chunking Transformers
AI总结：
PerFACT通过LLM驱动的数据集合成和融合动作分块变换器，提升机械臂运动规划的泛化能力和效率。
摘要：
深度学习方法通过利用规划数据集中的先验经验显著提升了机械臂运动规划的能力。然而，最先进的神经运动规划器主要是在人工生成的工作空间中训练于小数据集，限制了它们对分布外场景的泛化能力。此外，这些规划器往往依赖于单一大型网络架构，难以编码关键规划信息。为了解决这些挑战，我们引入了由大型语言模型（LLMs）驱动的数据集合成和融合动作分块变换器（PerFACT），该方法包含两个关键组件。首先，一种新颖的LLM驱动的工作空间生成方法MotionGeneralizer能够通过生成语义上可行的多样化工作空间实现大规模规划数据收集。其次，我们引入了融合运动策略网络（MpiNetsFusion），一种通用的神经运动规划器，它使用融合动作分块变换器更好地编码规划信号并处理多种特征模态。利用MotionGeneralizer，我们收集了350万条轨迹来训练和评估MpiNetsFusion，结果显示，所提出的MpiNetsFusion在评估任务上可以以几倍的速度进行规划。
英文摘要：
Deep learning methods have significantly enhanced motion planning for robotic manipulators by leveraging prior experiences within planning datasets. However, state-of-the-art neural motion planners are primarily trained on small datasets collected in manually generated workspaces, limiting their deployment in various everyday scenarios. Additionally, these planners often rely on monolithic network architectures that struggle to encode critical planning information. To address these challenges, we introduce Motion Policy with Dataset Synthesis powered by large language models (LLMs) and Fusion Action-Chunking Transformers (PerFACT), which incorporates two key components. Firstly, a novel workspace generation method, PerFACT, enables large-scale planning data collection by leveraging procedural primitive generation, and LLM-powered primitive suggestion and placement. Secondly, we introduce Fusion Motion Policy Networks (M$π$NetsFusion), an end-to-end, open-loop neural motion planner that uses a fusion action-chunking transformer to better encode planning signals and attend to multiple feature modalities. Leveraging PerFACT, we collect a dataset of 3.5M trajectories to train and evaluate M$π$NetsFusion against state-of-the-art planners. Results show that M$π$NetsFusion achieves consistently low planning time with sub-second inference, while maintaining competitive performance compared to both sampling-based and end-to-end neural benchmark planners. Project website: \href{https://davoodsz.github.io/perfact.github.io/}{https://davoodsz.github.io/perfact.github.io/}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
