OT-Drive: Out-of-Distribution Off-Road Traversable Area Segmentation via Optimal Transport

2026-01-15

AI Summary

This work addresses the performance degradation of drivable area segmentation in autonomous driving under out-of-distribution (OOD) scenarios in unstructured environments by proposing an optimal transport-based multimodal fusion framework. The method formulates the fusion of RGB and surface normal features as a distribution alignment problem and introduces a novel semantic anchor generator to construct weather-, time-, and road-type-invariant semantic anchors that guide cross-modal feature alignment. Evaluated on OOD scenarios from the ORFD dataset, the model achieves a mean Intersection-over-Union (mIoU) of 95.16%, surpassing prior methods by 6.35%. Furthermore, it attains 89.79% mIoU in cross-dataset transfer tasks, significantly outperforming the baseline by 13.99%, thereby demonstrating markedly enhanced generalization to unseen environments.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches often suffer from degraded segmentation performance in out-of-distribution (OOD) scenarios, consequently impairing downstream driving tasks. To address this issue, we propose OT-Drive, an Optimal Transport--driven multi-modal fusion framework. The proposed method formulates RGB and surface normal fusion as a distribution transport problem. Specifically, we design a novel Scene Anchor Generator (SAG) to decompose scene information into the joint distribution of weather, time-of-day, and road type, thereby constructing semantic anchors that can generalize to unseen scenarios. Subsequently, we design an innovative Optimal Transport-based multi-modal fusion module (OT Fusion) to transport RGB and surface normal features onto the manifold defined by the semantic anchors, enabling robust traversable area segmentation under OOD scenarios. Experimental results demonstrate that our method achieves 95.16% mIoU on ORFD OOD scenarios, outperforming prior methods by 6.35%, and 89.79% mIoU on cross-dataset transfer tasks, surpassing baselines by 13.99%.These results indicate that the proposed model can attain strong OOD generalization with only limited training data, substantially enhancing its practicality and efficiency for real-world deployment.

Problem

• out-of-distribution
• traversable area segmentation
• autonomous driving
• unstructured environments
• generalization

Innovation

• Optimal Transport
• Out-of-Distribution Generalization
• Multi-modal Fusion
• Traversable Area Segmentation
• Scene Anchor Generator