ForestSim: A Synthetic Benchmark for Intelligent Vehicle Perception in Unstructured Forest Environments

2026-03-29

AI Summary

This work addresses the critical lack of high-quality semantic segmentation datasets for unstructured off-road environments such as forests, which significantly hinders the development of intelligent vehicle perception systems. To bridge this gap, the authors introduce ForestSim—the first high-fidelity synthetic dataset encompassing diverse seasons, terrains, and vegetation densities. Built using Unreal Engine and Microsoft AirSim, ForestSim comprises 25 virtual forest scenes with 2,094 images annotated at pixel-level precision across 20 navigation-relevant semantic classes. Experimental results demonstrate that state-of-the-art segmentation models perform effectively on this dataset, confirming ForestSim’s validity as a public, extensible benchmark and filling a crucial data void in off-road environmental perception research.

Abstract

Robust scene understanding is essential for intelligent vehicles operating in natural, unstructured environments. While semantic segmentation datasets for structured urban driving are abundant, the datasets for extremely unstructured wild environments remain scarce due to the difficulty and cost of generating pixel-accurate annotations. These limitations hinder the development of perception systems needed for intelligent ground vehicles tasked with forestry automation, agricultural robotics, disaster response, and all-terrain mobility. To address this gap, we present ForestSim, a high-fidelity synthetic dataset designed for training and evaluating semantic segmentation models for intelligent vehicles in forested off-road and no-road environments. ForestSim contains 2094 photorealistic images across 25 diverse environments, covering multiple seasons, terrain types, and foliage densities. Using Unreal Engine environments integrated with Microsoft AirSim, we generate consistent, pixel-accurate labels across 20 classes relevant to autonomous navigation. We benchmark ForestSim using state-of-the-art architectures and report strong performance despite the inherent challenges of unstructured scenes. ForestSim provides a scalable and accessible foundation for perception research supporting the next generation of intelligent off-road vehicles. The dataset and code are publicly available: Dataset: https://vailforestsim.github.io Code: https://github.com/pragatwagle/ForestSim

Problem

• unstructured environments
• semantic segmentation
• synthetic dataset
• intelligent vehicles
• forest perception

Innovation

• synthetic dataset
• semantic segmentation
• unstructured environments
• ForestSim
• autonomous off-road perception