ORFD: A Dataset and Benchmark for Off-Road Freespace Detection

TL;DR

This paper introduces ORFD, the first off-road free space detection dataset with diverse scenes and conditions, and proposes OFF-Net, a Transformer-based network with cross-attention for improved off-road freespace detection.

Contribution

The paper provides a new off-road freespace detection dataset and a novel Transformer-based network with cross-attention for better multi-modal fusion and detection accuracy.

Findings

The ORFD dataset contains 12,198 LiDAR and RGB pairs across diverse environments.

OFF-Net achieves state-of-the-art performance on the ORFD benchmark.

The proposed method effectively fuses LiDAR and RGB data for accurate off-road freespace detection.

Abstract

Freespace detection is an essential component of autonomous driving technology and plays an important role in trajectory planning. In the last decade, deep learning-based free space detection methods have been proved feasible. However, these efforts were focused on urban road environments and few deep learning-based methods were specifically designed for off-road free space detection due to the lack of off-road benchmarks. In this paper, we present the ORFD dataset, which, to our knowledge, is the first off-road free space detection dataset. The dataset was collected in different scenes (woodland, farmland, grassland, and countryside), different weather conditions (sunny, rainy, foggy, and snowy), and different light conditions (bright light, daylight, twilight, darkness), which totally contains 12,198 LiDAR point cloud and RGB image pairs with the traversable area, non-traversable area and unreachable area annotated in detail. We propose a novel network named OFF-Net, which unifies Transformer architecture to aggregate local and global information, to meet the requirement of large receptive fields for free space detection tasks. We also propose the cross-attention to dynamically fuse LiDAR and RGB image information for accurate off-road free space detection. Dataset and code are publicly available athttps://github.com/chaytonmin/OFF-Net.