MarketGen: A Scalable Simulation Platform with Auto-Generated Embodied Supermarket Environments
🤖 AI Summary
Existing robotic datasets and benchmarks predominantly focus on short-horizon, single-task domestic or desktop scenarios, lacking support for long-horizon, multi-task embodied intelligence research in complex commercial environments—e.g., supermarkets.
Method: We propose the first embodied intelligence research framework for supermarket settings, leveraging multi-agent procedural content generation (PCG) guided by textual/image inputs and real-world spatial design principles to automatically synthesize structured, scalable 3D supermarket environments. We curate a standardized 3D asset library containing 1,100+ grocery items and develop a modular agent architecture. Additionally, we establish the first dual-task benchmark for cashiering and shelf stocking, validated via cross-domain sim-to-real transfer.
Contribution/Results: This work bridges critical gaps in commercial embodied intelligence across data, environment, and evaluation. It enables efficient, scalable development and significantly improves generalization capability for real-world retail automation.
Application Category
📝 Abstract
The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and benchmarks, which primarily focus on household or tabletop settings with short-horizon tasks. To address this limitation, we introduce MarketGen, a scalable simulation platform with automatic scene generation for complex supermarket environments. MarketGen features a novel agent-based Procedural Content Generation (PCG) framework. It uniquely supports multi-modal inputs (text and reference images) and integrates real-world design principles to automatically generate complete, structured, and realistic supermarkets. We also provide an extensive and diverse 3D asset library with a total of 1100+ supermarket goods and parameterized facilities assets. Building on this generative foundation, we propose a novel benchmark for assessing supermarket agents, featuring two daily tasks in a supermarket: (1) Checkout Unloading: long-horizon tabletop tasks for cashier agents, and (2) In-Aisle Item Collection: complex mobile manipulation tasks for salesperson agents. We validate our platform and benchmark through extensive experiments, including the deployment of a modular agent system and successful sim-to-real transfer. MarketGen provides a comprehensive framework to accelerate research in embodied AI for complex commercial applications.
Problem
Research questions and friction points this paper is trying to address.
Addressing the lack of robotics datasets for complex commercial environments beyond household settings
Providing automated generation of realistic supermarket environments with multi-modal inputs
Establishing benchmarks for assessing embodied agents in long-horizon supermarket tasks
Innovation
Methods, ideas, or system contributions that make the work stand out.
Auto-generated embodied supermarket environments via PCG
Multi-modal inputs with text and reference images
Parameterized assets and modular agent benchmark system
🔎 Similar Papers
No similar papers found.
