# OpenTeleVision/TeleVision

[CoRL 2024] Open-TeleVision: Teleoperation with Immersive Active Visual Feedback

Repository: https://github.com/OpenTeleVision/TeleVision
Canonical: https://ross.abutalabs.com/products/opentelevision-television
Homepage: https://robot-tv.github.io/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-09-27T02:38:47+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 61
- inputs: {"age_days": 860, "days_push": 706, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1301, forks 135 (observed 2026-08-28T04:04:17.668248+00:00)

## What it is
Open-TeleVision is an open-source immersive robot teleoperation system that streams stereoscopic visual feedback to VR headsets (Apple Vision Pro, Meta Quest) while mirroring the operator's arm and hand movements onto a robot. It also includes imitation learning pipelines for training and deploying policies from collected teleoperation data.

## Use cases
- teleoperate a robot with immersive VR visual feedback
- collect robot demonstration data for imitation learning
- mirror operator arm and hand motions onto a humanoid robot
- teleoperate a robot remotely over long distances
- train and deploy imitation learning policies on real robots
- run teleoperation experiments in Isaac Gym simulation

## When to choose
- you need immersive stereo teleoperation for robot data collection
- you want to train imitation learning policies from human demonstrations
- you have a Vision Pro or Quest headset and a ZED stereo camera
- you are doing robotics research on humanoid manipulation

## When to avoid
- you need a production-grade, plug-and-play teleoperation product
- you lack VR hardware or NVIDIA GPUs / Isaac Gym
- you need a simple 2D camera-based teleop setup
- you want a stable, well-documented SDK rather than research code

## Facets
- artifact type: library
- maturity: active
- function: robotics, computer-vision, machine-learning, streaming, simulation
- domain: robotics, machine-learning, computer-vision, autonomous-vehicles
- platform: python
- tags: teleoperation, vr-headset, vision-pro, quest, imitation-learning, zed-camera, isaac-gym, humanoid-robots, research-code, corl-2024, linux, gpu

## Member repositories
- OpenTeleVision/TeleVision (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.668248+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:52:13.531776+00:00, confidence not recorded.
  - readme: https://github.com/OpenTeleVision/TeleVision (fetched 2026-08-28T04:04:17.668248+00:00, sha c431c180dcdb)
  - homepage: https://robot-tv.github.io/ (fetched 2026-08-29T12:09:38.074631+00:00, sha e618dff38217)
- Data as of 2026-08-30T08:39:29.467469+00:00.