Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentation

TL;DR

This paper introduces the GOOSE-Ex dataset, expanding the original GOOSE dataset with 5000 new multimodal frames from diverse environments and platforms, to improve semantic segmentation generalization for outdoor robotic perception.

Contribution

It provides a new open-source dataset, GOOSE-Ex, with diverse environments and platforms, enabling better generalization of semantic segmentation models in unstructured outdoor settings.

Findings

Semantic segmentation performance varies across platforms and environments.

Combined datasets improve robustness for downstream tasks.

Pre-trained models demonstrate effective transferability.

Abstract

The successful deployment of deep learning-based techniques for autonomous systems is highly dependent on the data availability for the respective system in its deployment environment. Especially for unstructured outdoor environments, very few datasets exist for even fewer robotic platforms and scenarios. In an earlier work, we presented the German Outdoor and Offroad Dataset (GOOSE) framework along with 10000 multimodal frames from an offroad vehicle to enhance the perception capabilities in unstructured environments. In this work, we address the generalizability of the GOOSE framework. To accomplish this, we open-source the GOOSE-Ex dataset, which contains additional 5000 labeled multimodal frames from various completely different environments, recorded on a robotic excavator and a quadruped platform. We perform a comprehensive analysis of the semantic segmentation performance on different platforms and sensor modalities in unseen environments. In addition, we demonstrate how the combined datasets can be utilized for different downstream applications or competitions such as offroad navigation, object manipulation or scene completion. The dataset, its platform documentation and pre-trained state-of-the-art models for offroad perception will be made available on https://goose-dataset.de/. \