Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents
This provides a domain-specific tool for researchers and developers in embodied AI to train and evaluate agents in retail scenarios, though it is incremental as it builds on existing simulation frameworks.
The authors tackled the lack of retail-specific simulation environments for embodied AI agents by introducing Sari Sandbox, a high-fidelity 3D retail store simulation with over 250 interactive items and a dataset of human demonstrations, enabling benchmarking against human performance in shopping tasks.
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.