robot policy
ACT (Action Chunking with Transformers)
Imitation learning policy that predicts chunks of robot actions with a transformer, introduced with the low-cost ALOHA bimanual arms; LeRobot, OpenVINO and Qualcomm AI Hub ship it.
Levelmodel
Classrobot policy
Parametersnot in the notes
Contextnot in the notes
Released23 Apr 2023
Opennessopen source
Runs onmobile or NPU, CPU server
Statusactive
Identity
- Developer
- Stanford University
- Family
- not in the notes
- Released
- 23 Apr 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image, text
- Output
- action
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU, CPU server
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperStanford Universityuniversity, USA
Stanford Universityuniversity, USAModelACT (Action Chunking with Transformers)Stanford University, robot policy
ACT (Action Chunking with Transformers)Stanford University, robot policyR&D TopicsImitation Learning from Demonstrations
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- arxiv.org/abs/2304.13705 https://arxiv.org/abs/2304.13705
- github.com/tonyzhaozh/act https://github.com/tonyzhaozh/act
- aihub.qualcomm.com/models/act https://aihub.qualcomm.com/models/act
- huggingface.co/OpenVINO/act-fp16-ov https://huggingface.co/OpenVINO/act-fp16-ov
- modelscope.cn/models/lerobot/act_aloha_sim_transfer_cube_hu... https://www.modelscope.cn/models/lerobot/act_aloha_sim_transfer_cube_human
- github.com/open-mmlab/mmaction2/tree/main/projects/actio... https://github.com/open-mmlab/mmaction2/tree/main/projects/actionclip
- arxiv.org/abs/2109.08472 https://arxiv.org/abs/2109.08472
- arxiv.org/html/2304.13705 https://arxiv.org/html/2304.13705
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "ACT (Action Chunking with Transformers)", https://aurion.semai.id/models/act-action-chunking-transformer/, records of October 2026.