# LookOut: Real-World Humanoid Egocentric Navigation

Source: [LookOut: Real-World Humanoid Egocentric Navigation](<https://www.sota2.com/research/paper/68fa7ab81e209131cea84c6f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:25:52.609Z

Authors: Boxiao Pan, Adam W. Harley, C. Karen Liu, Leonidas J. Guibas

Published: 2025-08-20T06:43:36.000Z

## Abstract

The ability to predict collision-free future trajectories from egocentric observations is crucial in applications such as humanoid robotics, VR / AR, and assistive navigation. In this work, we introduce the challenging problem of predicting a sequence of future 6D head poses from an egocentric video. In particular, we predict both head translations and rotations to learn the active information-gathering behavior expressed through head-turning events. To solve this task, we propose a framework that reasons over temporally aggregated 3D latent features, which models the geometric and semantic constraints for both the static and dynamic parts of the environment. Motivated by the lack of training data in this space, we further contribute a data collection pipeline using the Project Aria glasses, and present a dataset collected through this approach. Our dataset, dubbed Aria Navigation Dataset (AND), consists of 4 hours of recording of users navigating in real-world scenarios. It includes diverse situations and navigation behaviors, providing a valuable resource for learning real-world egocentric navigation policies. Extensive experiments show that our model learns human-like navigation behaviors such as waiting / slowing down, rerouting, and looking around for traffic while generalizing to unseen environments. Check out our project webpage at https://sites.google.com/stanford.edu/lookout.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Head Rotation Prediction on CEN All Scenarios (test)](<https://www.sota2.com/research/sota/head-rotation-prediction-on-cen-all-scenarios-test.md>): Head Rotation Prediction; CEN All Scenarios (test); Head L1 Error: 0.1224.

- [Head Rotation Prediction on CEN High-U Scenarios (test)](<https://www.sota2.com/research/sota/head-rotation-prediction-on-cen-high-u-scenarios-test.md>): Head Rotation Prediction; CEN High-U Scenarios (test); Head L1 Error: 0.1235.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.14466>)

[PDF](<https://arxiv.org/pdf/2508.14466.pdf>)
