打造虚拟零售店环境，测试智能体购物能力。
Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents
- 构建高保真3D超市模拟环境，支持人机交互与智能体训练。
- 包含250+可操作商品，提供人类示范数据集SariBench。
- 适合研究具身智能、机器人导购与人机协作的学者使用。
我们提出Sari Sandbox，一个高保真、逼真的3D零售商店仿真环境，用于在购物任务中评估具身智能体与人类表现的差距。针对现有具身智能体训练中缺乏零售场景专用仿真环境的问题，Sari Sandbox 包含超过250个可交互生鲜商品，覆盖三种商店布局，并通过API实现控制。系统支持虚拟现实（VR）用于人类交互，也兼容基于视觉语言模型（VLM）的具身智能体。我们还推出了SariBench数据集，包含多种任务难度下的人类示范标注。该环境使智能体能够导航、检查和操作商品，为智能体性能提供与人类表现的基准对比。最后，我们给出了性能基准、分析结果及提升真实感与可扩展性的建议。源代码可通过https://github.com/upeee/sari-sandbox-env获取。
原文摘要 · Abstract (English)
We present Sari Sandbox, a high-fidelity, photorealistic 3D retail store simulation for benchmarking embodied agents against human performance in shopping tasks. Addressing a gap in retail-specific sim environments for embodied agent training, Sari Sandbox features over 250 interactive grocery items across three store configurations, controlled via an API. It supports both virtual reality (VR) for human interaction and a vision language model (VLM)-powered embodied agent. We also introduce SariBench, a dataset of annotated human demonstrations across varied task difficulties. Our sandbox enables embodied agents to navigate, inspect, and manipulate retail items, providing baselines against human performance. We conclude with benchmarks, performance analysis, and recommendations for enhancing realism and scalability. The source code can be accessed via https://github.com/upeee/sari-sandbox-env.
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。