用多流生成策略，少样本学机器人操作，效果提升近90%
MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
- 训练多个对象中心策略，在推理时组合提升泛化能力
- 仅需5次示范即达高质量性能，演示次数减少95%
- 支持零样本物体实例迁移，适合实际机器人部署
生成式机器人策略如流匹配可实现灵活、多模态策略学习，但样本效率低。尽管基于物体的策略提升了样本效率，仍无法根本解决该问题。本文提出多流生成策略（MSG），一种推理时组合的框架：训练多个对象中心策略，并在推理阶段融合以提升泛化性与样本效率。MSG 兼容多种生成模型和训练方式，仅需推理。我们在仿真与真实机器人上开展大量实验，结果表明，该方法仅需5次示范即可学习高质量生成策略，相较单流方法减少95%示范量，性能提升89%。我们还系统分析了不同组合策略，给出实用部署建议。此外，MSG 实现零样本物体实例迁移。代码已公开于 https://msg.cs.uni-freiburg.de。
原文摘要 · Abstract (English)
Generative robot policies such as Flow Matching offer flexible, multi-modal policy learning but are sample-inefficient. Although object-centric policies improve sample efficiency, it does not resolve this limitation. In this work, we propose Multi-Stream Generative Policy (MSG), an inference-time composition framework that trains multiple object-centric policies and combines them at inference to improve generalization and sample efficiency. MSG is model-agnostic and inference-only, hence widely applicable to various generative policies and training paradigms. We perform extensive experiments both in simulation and on a real robot, demonstrating that our approach learns high-quality generative policies from as few as five demonstrations, resulting in a 95% reduction in demonstrations, and improves policy performance by 89 percent compared to single-stream approaches. Furthermore, we present comprehensive ablation studies on various composition strategies and provide practical recommendations for deployment. Finally, MSG enables zero-shot object instance transfer. We make our code publicly available at https://msg.cs.uni-freiburg.de.
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。