EgoWalk: A Multimodal Dataset for Robot Navigation in the Wild

arXiv cs.RO / 4/21/2026

📰 NewsDeveloper Stack & InfrastructureSignals & Early TrendsModels & Research

共有:

Key Points

The paper introduces EgoWalk, a multimodal robot navigation dataset comprising 50 hours of human navigation data collected across diverse indoor and outdoor settings, seasons, and locations.
In addition to raw recordings and imitation-learning-ready data, the dataset provides derived resources such as natural-language goal annotations and traversability segmentation masks.
The authors include automated pipelines to generate subsidiary datasets for multiple navigation-related tasks, enabling broader downstream usage.
EgoWalk is supported by diversity studies, use cases, and benchmarks to demonstrate practical applicability and robustness in uncontrolled, real-world conditions.
All data processing pipelines and documentation of the data-collection hardware platform are released openly to facilitate future research and development in robot navigation.

Abstract

Data-driven navigation algorithms are critically dependent on large-scale, high-quality real-world data collection for successful training and robust performance in realistic and uncontrolled conditions. To enhance the growing family of navigation-related real-world datasets, we introduce EgoWalk - a dataset of 50 hours of human navigation in a diverse set of indoor/outdoor, varied seasons, and location environments. Along with the raw and Imitation Learning-ready data, we introduce several pipelines to automatically create subsidiary datasets for other navigation-related tasks, namely natural language goal annotations and traversability segmentation masks. Diversity studies, use cases, and benchmarks for the proposed dataset are provided to demonstrate its practical applicability. We openly release all data processing pipelines and the description of the hardware platform used for data collection to support future research and development in robot navigation systems.