Does GR00T N1.7 run on reBot Arm B601-DM?
Capabilities
| Capability | State | Notes | Evidence |
|---|---|---|---|
| Train / fine-tune | works | Fine-tuned from nvidia/GR00T-N1.7-3B with --embodiment-tag NEW_EMBODIMENT; six arm joints as relative actions, gripper absolute. | ev-gr00t-rebot |
| Real-robot inference | works | Closed-loop deployment via run_gr00t_server.py plus the eval_rebot_arm_dm.py client; the README shows only open-loop plots, no closed-loop success rates. | ev-gr00t-rebot, ev-gr00t-rebot-client |
| Simulation inference | no verified evidence | — | |
| Teleop + record | no verified evidence | — |
Caveats
- Documented in NVIDIA's Isaac-GR00T repository, not through LeRobot's groot policy: the real-robot client uses Seeed's LeRobot fork plus the lerobot-robot-seeed-b601 plugin (--robot.type=seeed_b601_dm_follower), not LeRobot's native rebot_b601_follower.
- Covers the reBot Arm B601-DM (Damiao-motor variant); datasets must be converted from LeRobot v3 to v2 before Isaac-GR00T fine-tuning.
- The example landed on Isaac-GR00T main (2026-07-30) after the n1.7-release tag; it is not part of a tagged release.
Evidence 2 sources; the cell shows the highest tier
- T1 · upstream documentedofficial-docssource 2026-07-30verified 2026-10-24 (1d ago)
NVIDIA's Isaac-GR00T example fine-tunes GR00T N1.7 on reBot Arm B601-DM data and evaluates it on the real robot.
“This guide shows how to finetune dataset collected from [rebot arm b601 dm](https://www.seeedstudio.com/reBot-Arm-B601-DM-Bundle.html) robot, and evaluate the model on the real robot.”
https://github.com/NVIDIA/Isaac-GR00T/blob/b9955401d50c92a29258732e3ad6ccd579f1bdc0/examples/rebot-arm-dm/README.md - T1 · upstream documentedsource-codesource 2026-07-30verified 2026-10-24 (1d ago)
The deployment client depends on Seeed's LeRobot fork and the lerobot-robot-seeed-b601 robot plugin at pinned commits.
“"lerobot-robot-seeed-b601 @ git+https://github.com/Seeed-Projects/lerobot-robot-seeed-b601.git@5d36bef6e352ddfc4cefc40a16db02772e25655c",”
https://github.com/NVIDIA/Isaac-GR00T/blob/b9955401d50c92a29258732e3ad6ccd579f1bdc0/examples/rebot-arm-dm/pyproject.toml
GR00T N1.7 inference speed by hardware robot-independent · inference cost only
| Compute | Runtime | Precision | Cams | p50 / p95 ms | Inference | Platform | Source |
|---|---|---|---|---|---|---|---|
| H100 80GB | TensorRT | bf16 | 2 @256x256 | 22.9 / — | 43.67 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| RTX PRO 6000 Blackwell Server | TensorRT | bf16 | 2 @256x256 | 24.7 / — | 40.49 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| L40 | TensorRT | bf16 | 2 @256x256 | 35 / — | 28.57 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| Jetson AGX Thor 128GB | TensorRT | mixed | 2 @256x256 | 35.6 / — | 28.09 Hz | jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Mixed NVFP4 quantization (enum has no fp4 value). | T3 · community reported |
| RTX PRO 6000 Blackwell Server | torch.compile | bf16 | 2 @256x256 | 52.1 / — | 19.19 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| H100 80GB | torch.compile | bf16 | 2 @256x256 | 53.4 / — | 18.73 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| L40 | torch.compile | bf16 | 2 @256x256 | 66.8 / — | 14.97 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| RTX PRO 6000 Blackwell Server | PyTorch eager | bf16 | 2 @256x256 | 75.7 / — | 13.21 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| Jetson AGX Thor 128GB | TensorRT | bf16 | 2 @256x256 | 76.8 / — | 13.02 Hz | jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| Jetson AGX Thor 128GB | torch.compile | bf16 | 2 @256x256 | 100.5 / — | 9.95 Hz | jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| H100 80GB | PyTorch eager | bf16 | 2 @256x256 | 101.5 / — | 9.85 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| Jetson AGX Thor 128GB | PyTorch eager | bf16 | 2 @256x256 | 106.8 / — | 9.36 Hz | jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| L40 | PyTorch eager | bf16 | 2 @256x256 | 123.7 / — | 8.08 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| Jetson Orin Nano 8GB (Super) | TensorRT | fp16 | 3 @640x480 | 273.7 / 275.4 | 3.66 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 256x256; 4 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 5.78 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. Three camera views, each with two frames (GR00T N1.7 temporal input). | T3 · community reported |
Embed this cell
Badge for READMEs and model cards. It always shows the current state.
[](https://caniembody.pages.dev/compat/rebot-b601/groot-n1-7)<iframe src="https://caniembody.pages.dev/embed/rebot-b601/groot-n1-7" width="380" height="132" style="border:0" title="GR00T N1.7 on reBot Arm B601-DM | CanIEmbody"></iframe>History
- 2026-10-25 fecccd1 Initial release: robot policy compatibility matrix · Danilo Znamerovszkij