# Human2LocoMan dataset

From the catalogue. Listed by one researcher from one source page.

- id: `human2locoman-dataset`
- kind: teleop
- robot or device: LocoMan quadruped with two leg-mounted loco-manipulators (class: legged)
- how collected: Apple Vision Pro teleoperation via Open-TeleVision, plus egocentric human data
- size as stated: robot: 6 tasks, 30-150 trajectories each, about 101 min; human: about 242 min
- hours: 4 | hours only claimed: none | episodes: not stated
- year: 2025
- organisation: Carnegie Mellon University, Google DeepMind, Bosch Center for AI
- licence: not stated (class: not stated)
- access: open (human2bots.github.io) (class: open)
- link (paper): https://arxiv.org/html/2506.16475v2
- note: Paired robot teleop and human egocentric data in one frame.

Confirm the licence at the link before relying on it.