RT-1 / RT-1-X (Robotics Transformer)
Robotics modelFiLM-EfficientNet + TokenLearner + 8-layer Transformer VLA policy family from Google Research and Google DeepMind, spanning the archived Apache-2.0 RT-1 TensorFlow repo (3 SavedModel checkpoints) and the Open X-Embodiment RT-1-X TensorFlow and JAX checkpoints. [1] [2] [3] [4]
Setup & usage →CheckpointsModel hub / homepageGetting started
- For
- Robotics and VLA researchers; Open X-Embodiment benchmark practitioners; TensorFlow / JAX robot learning engineers [1] [3]
- Embodiments
- Everyday Robots (EDR) mobile manipulator (RT-1), Kuka arm (rt1multirobot), Cross-embodiment 7-DoF arms in Open… [1] [3] [6]
- Source rights
- Named licenses are documented by part. Review licenses
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
Overview
RT-1 (google-research/robotics_transformer, commit 4569641b8111, archived read-only) and its cross-embodiment Open X-Embodiment successor RT-1-X (google-deepmind/open_x_embodiment, commit 9eeb68b989ef) form a foundational Vision-Language-Action (VLA) policy family that maps monocular workspace RGB frames and natural language task strings directly to discretized 7-DoF gripper actions. Five ungated checkpoints are hosted across Google Cloud Storage (RT-1-X TensorFlow and JAX) and Git LFS (three original RT-1 TensorFlow SavedModels). [1] [3] [4] [5] [6]
Model card summary
- Architecture
FiLM-conditioned EfficientNet image tokenizer + TokenLearner token compression + 8-layer decoder-only Transformer (configs/transformer_mixin.gin: num_layers 8, num_heads 8, layer_size 128, token_embedding_size 512, feed_forward_size 512, vocab_size 256, time_sequence_length 6).
Verified directly from transformer_network.py and configs/transformer_mixin.gin.
- Base model
EfficientNet (FiLM-conditioned image tokenizer) + Universal Sentence Encoder / language embedding
- Parameter count
Compact 8-layer transformer (~0.78 GB RT-1-X TF zip; ~1.37 GB JAX checkpoint; ~0.14 GB RT-1 main variables; exact scalar count not printed in README)
Exact parameter count is not stated in robotics_transformer README.md or open_x_embodiment README.md; verified checkpoint byte sizes are reported instead.
- Input modalities
- rgblanguage
Single workspace RGB camera image history (sequence length 6) plus natural language task string; no wrist camera, depth, or proprioception.
- Output modalities
- ee-pose-deltagripper-command
7 discretized gripper movement variables (x, y, z, roll, pitch, yaw, gripper opening) quantized into 256 bins (vocab_size 256); per OXE README each variable can represent absolute, delta, or velocity depending on embodiment convention.
- Action space
7-DoF gripper control (x, y, z, roll, pitch, yaw, gripper opening) discretized into 256 token bins per dimension (vocab_size: 256) plus termination/mode tokens.
- Control frequency
3 Hz (333 ms per step documented in Open X-Embodiment README)
- Trained / supported embodiments
- Everyday Robots (EDR) mobile manipulator (RT-1)
- Kuka arm (rt1multirobot)
- Cross-embodiment 7-DoF arms in Open X-Embodiment (RT-1-X)
- Training datasets
- Open X-Embodiment multi-robot dataset mixture (RT-1-X)
- Google Everyday Robots 700-task dataset, Kuka dataset, and sim+real data (RT-1 checkpoints)
Checkpoints
| Checkpoint | Format | Size | Access | Pinned revision |
|---|---|---|---|---|
| RT-1-X TensorFlow SavedModel (2,272,480 steps) | other | 0.78 GB | open | 2023-10-10 |
| RT-1-X JAX / Flax Checkpoint (GCS bucket) | other | 1.37 GB | open | main |
| RT-1 Main (700 tasks, Git LFS SavedModel) | other | 0.14 GB | open | 4569641b8111 |
| RT-1 Multi-Robot (EDR + Kuka, Git LFS SavedModel) | other | 0.45 GB | open | 4569641b8111 |
| RT-1 Sim + Real (Git LFS SavedModel) | other | 0.14 GB | open | 4569641b8111 |
Verified GCS HTTP 200 (0.775 GB zip, 1.368 GB JAX directory) and Git LFS variable sizes (141.8 MB, 445.6 MB, 141.5 MB).
Is this for you?
- Use cases
- Running offline or closed-loop 3 Hz RGB + language manipulation inference with RT-1-X TensorFlow or JAX checkpoints
- Benchmarking generalist cross-embodiment policies against a canonical Open X-Embodiment baseline
- Inspecting or running the three original RT-1 TensorFlow SavedModels (700-task main, multi-robot EDR+Kuka, sim+real)
- Known limitations
- google-research/robotics_transformer was archived on GitHub (last commit 2023-02-10, pushed 2024-01-31) and depends on legacy TensorFlow / TF-Agents / tensor2robot packages.
- RT-1-X takes only a single workspace RGB camera and a task string; wrist cameras, in-hand cameras, depth, and proprioception are not supported as inputs.
- Original RT-1 checkpoints in google-research/robotics_transformer are stored via Git LFS; RT-1-X checkpoints are hosted separately in a Google Cloud Storage bucket.
- Safety and limitations
- google-research/robotics_transformer is archived read-only and explicitly states it is not an officially supported Google product.
- Single-camera RGB input only; lacks wrist-camera, depth, and proprioceptive feedback and runs at a low 3 Hz control rate.
- Open X-Embodiment README licenses software under Apache-2.0 and non-software materials (including checkpoints/datasets) under CC-BY-4.0.
Compute & fine-tuning
- Inference compute
- Documented hardware: Google Colab / workstation GPU (per Open X-Embodiment inference Colab)
- Precision:
fp32 - Edge / consumer capable: Yes
Compact 0.78 GB SavedModel zip running at 3 Hz; exact minimum VRAM and latency_ms are not documented in README.
- Fine-tuning
- Supported: No
Upstream repositories release architecture code and inference checkpoints/Colabs rather than a turnkey end-to-end RT-1-X fine-tuning script.
- Host computer
Compact transformer footprint (~0.78 GB RT-1-X TF SavedModel zip, ~1.37 GB JAX checkpoint, 0.14-0.45 GB RT-1 SavedModel variables) runnable on standard workstation GPUs or Colab.
Inferred from verified checkpoint sizes and Open X-Embodiment Colab inference notebook.
- Operating system
- Linux
TensorFlow/JAX/Bazel robotics tooling targets Linux.
- Dependencies
- Python
- TensorFlow & TF-Agents (for RT-1 / RT-1-X TF)
- JAX & Flax (for RT-1-X JAX)
- Bazel (optional, for running robotics_transformer tests)
- Git LFS (for trained_checkpoints/ in robotics_transformer)
Setup & usage
Open the upstream getting-started guide [3]
- For RT-1-X TensorFlow inference, download rt_1_x_tf_trained_for_002272480_step.zip from GCS or follow the Open X-Embodiment inference Colab.
- For RT-1-X JAX inference, download gs://gdm-robotics-open-x-embodiment/open_x_embodiment_and_rt_x_oss/rt_1_x_jax via gsutil and run models/rt1_inference_example.py from google-deepmind/open_x_embodiment.
- For original RT-1 SavedModels, clone google-research/robotics_transformer with Git LFS, install requirements.txt, and load trained_checkpoints/{rt1main,rt1multirobot,rt1simreal} via tf.saved_model.load.
Upstream-reported benchmarks
Upstream-reported only: Open Source Robotics has not run training, inference, or hardware evaluations for these benchmarks.
| Benchmark | Upstream-reported score | Scope & caveats |
|---|---|---|
| RT-1 (arXiv:2212.06817) and Open X-Embodiment RT-1-X (arXiv:2310.08864) multi-robot evaluations | See arXiv:2212.06817 and arXiv:2310.08864 (no numeric table in repository READMEs) | Upstream-reported multi-robot and cross-embodiment evaluations; not independently reproduced by OSR. |
Project notes
Architecture, observation space, and checkpoints
In transformer_network.py and configs/transformer_mixin.gin, RT-1 combines a FiLM-conditioned EfficientNet image tokenizer, TokenLearner compression, and an 8-layer decoder-only Transformer (num_layers: 8, num_heads: 8, layer_size: 128, token_embedding_size: 512, feed_forward_size: 512, vocab_size: 256, time_sequence_length: 6). Per the Open X-Embodiment README, RT-1-X takes a single workspace RGB camera and a language instruction—without wrist cameras, depth, or proprioception—under an assumed 3 Hz control cadence (333 ms update interval, not a measured inference latency). It outputs seven discretized gripper action variables (x, y, z, roll, pitch, yaw, and gripper opening) quantized into 256 bins; per the README, each variable may represent an absolute value, a delta change, or a velocity depending on the embodiment convention, which must be established before interpreting predictions. [1] [3]
Metadata checks confirmed five public checkpoint artifacts without downloading or loading model payloads: an HTTP HEAD 200 response for the RT-1-X TensorFlow SavedModel archive (rt_1_x_tf_trained_for_002272480_step.zip, 0.78 GB), a GCS object-listing byte total of 1.37 GB for the RT-1-X JAX/Flax directory, and Git LFS pointer metadata inside robotics_transformer/trained_checkpoints/ showing variable-file sizes of 0.14 GB (rt1main), 0.45 GB (rt1multirobot), and 0.14 GB (rt1simreal). [1] [3] [4]
Documented inference routes and upstream-reported evaluations
Because google-research/robotics_transformer is archived and neither repository provides a turnkey end-to-end RT-1-X fine-tuning pipeline, the documented workflows are inference examples—offline episode inference in the Open X-Embodiment TensorFlow Colab and the JAX/Flax checkpoint loader in models/rt1_inference_example.py—which also makes the checkpoints suitable as an editorial baseline reference. Exact scalar parameter counts, minimum GPU VRAM, and per-step latency numbers are not listed in either README, and multi-robot evaluation tables live in arXiv:2212.06817 and arXiv:2310.08864; Open Source Robotics has not run training, fine-tuning, inference, or robot evaluations for this profile. [1] [3] [5] [6]
What we checked
None. Prepared from public upstream sources without hands-on training, fine-tuning, or robot execution.
Updates
- Upstream last updated
- Jan 31, 2024 [1]
- Latest release
- Oct 10, 2023 [4]
- Profile updated
- Nov 21, 2026
- Sources last checked
- Nov 21, 2026
- Next review
- Feb 19, 2027
- Reviewed revision
- google-research/robotics_transformer@4569641b8111f3f402c32d8e24becd2a6e952ecc (archived); google-deepmind/open_x_embodiment@9eeb68b989efbcf474e8fb9019e01d02b962a604 · combined hardware and software repository
Separate license matrix
Foundational open-weights VLA model family with Apache-2.0 code and five ungated TensorFlow/JAX checkpoints across google-research/robotics_transformer and google-deepmind/open_x_embodiment.
| Layer | Availability / license |
|---|---|
| Code | available · Apache-2.0 Verified Apache License Version 2.0 in google-research/robotics_transformer/LICENSE and google-deepmind/open_x_embodiment README. [1] [2] [3] |
| Model weights | available · Apache-2.0 (RT-1 checkpoints in robotics_transformer); CC-BY-4.0 (RT-1-X checkpoints under Open X-Embodiment non-software materials) All five checkpoints (RT-1-X TF & JAX on GCS; rt1main, rt1multirobot, rt1simreal in Git LFS) are publicly downloadable without gating. [1] [2] [3] [4] |
| Training datasets | available · CC-BY-4.0 (Open X-Embodiment aggregate terms; individual constituent datasets carry their own licenses) [3] |
| Documentation | available · Apache-2.0 / CC-BY-4.0 [1] [3] |
Licensing split across repositories
All software in both google-research/robotics_transformer and google-deepmind/open_x_embodiment is licensed under Apache-2.0. The Open X-Embodiment README further specifies that non-software materials (including the RT-1-X checkpoints and dataset distribution) are licensed under CC-BY-4.0, while individual constituent datasets within Open X-Embodiment carry their own upstream terms. [2] [3]
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
- S001 google-research/robotics_transformer README.md, transformer_network.py, and configs/transformer_mixin.gin
Archived Apache-2.0 RT-1 TensorFlow repo with FiLM EfficientNet + TokenLearner + 8-layer Transformer (vocab_size 256, seq_len 6) and 3 Git LFS SavedModels (rt1main, rt1multirobot, rt1simreal).Revision, date & where cited
Google Research (GitHub) · github.com · revision
4569641· Commit 4569641b8111 (2023-02-10, repo archived 2024-01-31) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 6 more - S002 google-research/robotics_transformer root LICENSE file
Revision, date & where cited
Google Research (GitHub) · github.com · revision
4569641· LICENSE at commit 4569641b8111 · Accessed Nov 21, 2026
Used for: Separate license matrix - S003 google-deepmind/open_x_embodiment README.md (RT-1-X Model checkpoint & License)
Documents RT-1-X 3 Hz RGB + language observation space, 7-DoF gripper action space, TF Colab & JAX GCS checkpoint paths, Apache-2.0 software license, and CC-BY-4.0 non-software materials license.Revision, date & where cited
Google DeepMind (GitHub) · github.com · revision
9eeb68b· README.md at commit 9eeb68b989ef (2025-11-05) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 5 more - S004 GCS API and HTTP HEAD verification of RT-1-X TensorFlow and JAX checkpoints
rt_1_x_tf_trained_for_002272480_step.zip returns HTTP 200 (0.775 GB, Last-Modified 2023-10-10); rt_1_x_jax directory totals 1.368 GB.Revision, date & where cited
Google Cloud Storage (gdm-robotics-open-x-embodiment) · storage.googleapis.com · GCS bucket prefix open_x_embodiment_and_rt_x_oss/rt_1_x · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 5 more - S005 arXiv:2212.06817 — RT-1: Robotics Transformer for Real-World Control at Scale
Introduces RT-1 Robotics Transformer architecture for real-world language-conditioned control.Revision, date & where cited
arXiv · arxiv.org · arXiv:2212.06817v2 (2022-12-13) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Upstream-reported benchmarks, Documented inference routes and upstream-reported evaluations - S006 arXiv:2310.08864 — Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Introduces the Open X-Embodiment dataset and cross-embodiment RT-1-X model.Revision, date & where cited
arXiv · arxiv.org · arXiv:2310.08864v9 (2023-10-13) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Upstream-reported benchmarks, Documented inference routes and upstream-reported evaluations
Correction guidance · Discussion is not enabled · Profile format 0.8.0-draft.1
Change history
2026-11-21 — Initial 0.8.0-draft.1 model profile prepared from archived google-research/robotics_transformer@4569641b8111 and google-deepmind/open_x_embodiment@9eeb68b989ef.