Agriculture robotics gets photorealistic large scale simulated fields

AgriGen: Large-Scale Scene Generation Framework for Photorealistic Agricultural Robotics Simulation

RoboticsGraphics

Summary

Growing robots for farming face challenges because real farms vary a lot by location and season, so getting enough data is hard. The authors made a computer simulation tool that creates very realistic farm scenes on a big scale, including many types of crops like orchards and vineyards. This helps test and train farm robots without needing constant field access. The tool works with popular robot software and can be expanded to more crop types.

What this means in practice

Authors

Utkarsh Bajpai, Serge Tleiji, Cédric Pradalier, Stéphanie Aravecchia

Abstract

Agricultural robotics is advancing rapidly, yet progress remains constrained by limited field access, lack of control over field conditions, geographic variability, and seasonal crop cycles. These factors make it difficult and costly to acquire diverse agricultural datasets, resulting in limited evaluation and reduced system robustness. While other robotics domains have scaled learning and evaluation through high-fidelity simulation, agricultural robotics still lacks comparably capable tools. In this paper, we present a ROS-integrated framework, built on Isaac Sim, for large-scale procedural generation of agricultural environments. The framework supports photorealistic rendering, physics simulation, and domain randomization at scales relevant to robotics research, with built-in support for row crops, orchards, and vineyards and straightforward extensibility to additional crop categories. Project Page: https://baj31415.github.io/agrigen/