# Mobile ALOHA

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

Repository: https://github.com/MarkFzp/mobile-aloha
Canonical: https://ross.abutalabs.com/products/mobile-aloha
Homepage: https://mobile-aloha.github.io/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: imitation-learning, robotics
Last push: 2024-06-22T18:27:51+00:00
Link (homepage): https://mobile-aloha.github.io/

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 82
- inputs: {"age_days": 1157, "days_push": 802, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4465, forks 734 (observed 2026-08-28T04:08:50.873072+00:00)

## What it is
Mobile ALOHA is an open-source system for low-cost whole-body teleoperation and data collection with a bimanual mobile manipulation robot, built on ROS and the ALOHA hardware stack. It pairs with the act-plus-plus repo for training imitation learning policies (behavior cloning) from collected demonstrations.

## Use cases
- collect demonstrations for mobile bimanual robot manipulation
- train imitation learning policies for whole-body robot control
- teleoperate a mobile dual-arm robot for household tasks
- set up ALOHA hardware with ROS for research
- co-train mobile and static manipulation datasets

## When to choose
- you are building or replicating a Mobile ALOHA hardware setup
- you need teleoperation and data collection code for bimanual mobile manipulation
- you want to train ACT-style behavior cloning policies on robot demonstrations

## When to avoid
- you need a general-purpose robotics framework or simulation
- you are not using the ALOHA/Interbotix hardware stack
- you require ROS 2 or Ubuntu 22.04 support, which is still in progress

## Facets
- artifact type: library
- maturity: active
- function: robotics, machine-learning, data-science
- domain: robotics, machine-learning, deep-learning
- platform: python
- tags: imitation-learning, teleoperation, behavior-cloning, bimanual-manipulation, ros, hardware, research, linux

## Member repositories
- MarkFzp/mobile-aloha (main) score 29
- MarkFzp/act-plus-plus (backend) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:50.873072+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 2026-08-29T18:20:38.841257+00:00, confidence not recorded.
  - readme: https://github.com/MarkFzp/mobile-aloha (fetched 2026-08-28T04:08:50.873072+00:00, sha 30aa963f00b4)
  - homepage: https://mobile-aloha.github.io/ (fetched 2026-08-29T09:07:14.594091+00:00, sha 991030f8e4b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.