# RoboCap: A New Platform for Egocentric Robot Learning

arXiv: https://arxiv.org/abs/2610.07217 · HTML: https://mlsanity.com/paper/2610.07217/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 69 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Humanoid Policy ~ Human Policy](https://mlsanity.com/paper/2503.13441/) (2025)
- [Aria Everyday Activities Dataset](https://mlsanity.com/paper/2402.13349/) (2024)
- [EgoZero: Robot Learning from Smart Glasses](https://mlsanity.com/paper/2505.20290/) (2025)
- [OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure](https://mlsanity.com/paper/2202.09199/) (2022)
- [cuVSLAM: CUDA accelerated visual odometry and mapping](https://mlsanity.com/paper/2506.04359/) (2025)

## Abstract (arXiv)

Despite its promise for scaling robot learning, egocentric manipulation data is still scarce today. Collection at scale requires vertically integrating ergonomic hardware with centimeter-precise 3D algorithms, at a precision that has not been publicly demonstrated. To address this gap, we introduce RoboCap, a 250,g six-camera dual-IMU hat designed for in-the-wild egocentric data capture, and the Grounded API, a suite of device-agnostic 3D algorithms tuned for RoboCap. In this report, we demonstrate how hardware, calibration, and 3D algorithms interact to achieve state-of-the-art performance on the public benchmarks: our SLAM across diverse settings and rigs, our depth estimation on egocentric settings, and our hand tracking when adapted to third-party devices.