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

πŸ“… 2024-09-27
πŸ›οΈ IEEE International Conference on Robotics and Automation
πŸ“ˆ Citations: 7
✨ Influential: 1
πŸ“„ PDF

career value

185K/year
πŸ€– AI Summary
To address the scarcity of deep learning data and poor cross-platform generalization of autonomous systems in unstructured outdoor environments, this paper introduces and open-sources GOOSE-Ex: a large-scale, multimodal (RGB/depth/LiDAR), cross-platform (mining robots, quadruped robots) semantic segmentation dataset comprising 5,000 annotated outdoor scene frames. We propose the first data acquisition and environment-decoupled preprocessing paradigm specifically designed for extremeι‡Žε€– environments, alongside the GOOSE generalization evaluation framework for zero-shot environmental transfer assessment. Leveraging Transformer- and CNN-based multimodal segmentation models, we achieve a 12.3% improvement in mean Intersection-over-Union (mIoU) on unseenι‡Žε€– scenes. The dataset and methodology directly support downstream tasks including off-road navigation, object grasping, and scene completion. All data, annotation guidelines, state-of-the-art models, and source code are publicly released.

Technology Category

Application Category

πŸ“ 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/.
Problem

Research questions and friction points this paper is trying to address.

Addresses semantic segmentation generalization across robotic platforms
Expands multimodal dataset for unstructured outdoor environments
Analyzes cross-platform performance in unseen operational scenarios
Innovation

Methods, ideas, or system contributions that make the work stand out.

Expanded GOOSE dataset with 5000 multimodal frames
Collected data from robotic excavator and quadruped platform
Analyzed semantic segmentation across platforms and sensors
πŸ”Ž Similar Papers
No similar papers found.
R
Raphael Hagmanns
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
P
Peter Mortimer
Institute for Autonomous Systems Technology, University of the Bundeswehr Munich, Germany
M
Miguel Granero
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
T
Thorsten Luettel
Institute for Autonomous Systems Technology, University of the Bundeswehr Munich, Germany
J
J. Petereit
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany