arXiv cs.AI· Caelan Garrett, Neel Jawale, Fabio Ramos·· 2 天前AI 评分29
DemoStream：面向示教学习自动化的批量任务与运动规划优化
DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration
AI 导读
DemoStream 是一个通过优化示教质量来提升行为克隆成功率的 TAMP 系统，引入批量 TAMP 采样操作与批量约束满足算法以并行探索大量解。仿真实验消融了不同动作空间、代价函数和批量大小对下游策略成功率的影响，并利用 TAMP 的安全保证以平均每小时 66 条示教的速度直接采集真实世界示教数据。
正文 · 原文
Abstract:Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of massive amounts of demonstrations. Existing demonstration collection approaches either require constant human involvement, for example, via teleoperation or are specialized for a single task. Task and Motion Planning (TAMP) systems are able to autonomously solve and therefore generate demonstrations for general-purpose tasks; however, learning from their demonstrations has proven difficult due to multi-modality in their solutions. In this work, we build on recent work leveraging GPU acceleration for TAMP and propose DemoStream, a TAMP system that optimizes demonstration quality in order to improve behavior cloning success rates. First, we introduce batched TAMP sampling operations along with a new TAMP algorithm that correspondingly performs batched constraint satisfaction in order to explore many solutions in parallel. We conduct simulation experiments ablating different action spaces, cost functions, and batch sizes to analyze the effect of these choices on downstream policy success rates. Finally, we show that we can leverage the safety guarantees of TAMP to directly collect real-world demonstrations at an average rate of 66 demos per hour. See our website for policy rollout videos: this http URL.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.22020 [cs.RO] |
| (or arXiv:2610.22020v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22020 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Caelan Garrett [view email]
[v1]
Thu, 15 Oct 2026 15:01:01 UTC (4,862 KB)
来源：arXiv cs.AI · arxiv.org