* fix(envs): set LiberoEnvConfig.fps default to 20 to match robosuite
LiberoEnvConfig.fps was set to 30, but the underlying robosuite
OffScreenRenderEnv always runs at its default control_freq of 20 Hz
since fps is never passed through. This mismatch silently decouples
the dataset/eval loop rate from the actual simulation step rate.
Set the default to 20 to match the real sim rate and avoid the
footgun.
Fixes#3368
* fix(libero): apply configured control frequency
---------
Co-authored-by: xinmotlanthua <275663218+xinmotlanthua@users.noreply.github.com>
* fix(damiao): make is_calibrated a plain property, not cached
`is_calibrated` was a `@cached_property`, so it froze at its first-read
value and never reflected later changes to `self.calibration` (set by
connect/calibrate/load). This caused the OpenArm teleop to re-run
calibration even when a calibration file existed, and to skip
`set_zero_position()` after a fresh calibration.
Switch to `@property` (matching the MotorsBus base contract and the
Feetech/SO-100 buses) and drop the now-unused `functools.cached_property`
import.
Co-authored-by: Cursor <cursoragent@cursor.com>
* don't set_zero_position() on connect
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(diffusion): add gradient checkpointing for memory optimization
Add gradient_checkpointing config option to DiffusionPolicy. When
enabled, wraps the UNet encoder, mid, and decoder residual blocks
with torch.utils.checkpoint.checkpoint to trade compute for memory.
Allows training with larger batch sizes or higher-resolution inputs
on memory-constrained GPUs. Disabled by default.
Usage: --policy.gradient_checkpointing=true
Part of the 0.6.0 roadmap item 3.3 (gradient checkpointing for all
policies).
* test(diffusion): verify gradient checkpointing parity
---------
Co-authored-by: Jash Shah <jashshah.999@gmail.com>
* gamepad does often work on macos
* review comments
* fix(gamepad): expose hidapi fallback in config
---------
Co-authored-by: Maxim Bonnaerens <maxim@bonnaerens.be>
* feat(annotate): run lerobot-annotate on HF Jobs via --job.target
Annotation needed a hand-edited launcher script (examples/annotations/run_hf_job.py)
to reach a GPU: users copied it, rewrote the embedded CMD string for their dataset,
and ran it with `python`. Fold that into the CLI instead, mirroring `lerobot-train`:
`lerobot-annotate --job.target=h200` submits the exact command you'd run locally.
- AnnotationJobConfig extends JobConfig with the annotation runtime's defaults
(vllm/vllm-openai image, 2h cap) plus --job.lerobot_ref, so an unmerged branch
can be exercised remotely without editing a script.
- lerobot.jobs.annotate builds the pod command by replaying the user's own CLI
flags (minus --job.*/--root, with --repo_id re-emitted from the config) after a
setup prelude that installs lerobot on top of the vLLM image. Job monitoring,
log tailing and Ctrl-C-detaches reuse the training submitter's plumbing.
- Remote runs require --repo_id; a local-only dataset is pushed privately first.
The generated pod command is byte-for-byte the script's old CMD.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(annotate): reject client-side config files on remote runs
draccus exposes `--config_path` plus a `--<field>` config-file arg for every
nested dataclass (`--vlm`, `--plan`, `--job`, ...). All name files on the
client's disk, so forwarding them to the pod silently dropped whatever settings
they carried. Reject them up front instead.
Bare `--job` also slipped past the `--job.` prefix filter, so a `--job=cfg.yaml`
holding `target: h200` would have reached the pod and had the job submit a job
of its own, recursively. It is dropped from the forwarded args as well.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(jobs): share the submit-and-follow loop between both submitters
`submit_annotate_to_hf` reused the leaf helpers (`_poll_until_done`, `_tail_logs`,
`_pod_forwarded_args`) but duplicated the orchestration around them: ~40 of the 50
lines that spawn the poll/log threads, install the Ctrl-C-detaches handler and
raise on a non-COMPLETED stage were identical in both files.
Extract that into `follow_job(job_id, *, detach, success_marker=None) -> bool`,
returning True when the job finished and False when we stopped watching without a
verdict (detach or Ctrl-C). Training keeps its model-pushed marker by passing it in;
annotation has no equivalent line (the CLI keeps working after the upload log to
write the card and tag) so its completion stays stage-based.
Kept in hf.py rather than a new module so every existing monkeypatch target in
test_hf.py still resolves.
Behaviour change: a training run whose job reaches COMPLETED without the marker
matching now prints its completion line instead of returning silently. The marker
was already documented as an optimisation with a stage-based fallback; the fallback
just never reported success.
Tests: adds annotate coverage for the non-detach path (completion and failure) —
previously only ever exercised with detach=true — plus a detach short-circuit test.
Both new annotate tests verified to fail under a mutation that stubs out follow_job.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(annotate): WGO-tuned subtask prompt (atomic completed-events + duration prior)
Rework the plan-module subtask segmentation prompt toward the WGO-Bench
atomic annotation protocol: segment by completed world-state changes
(grasp/place/open/close/pour/insert), fold approach+retreat into their
event, keep separate events separate, and add a 2-10s duration prior.
Drops the pi0.7 "fewer larger composites preferred" bias that drove
under-segmentation on the benchmark. Output JSON shape unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(annotate): seeded-relabeling second pass for subtasks
Add an opt-in relabel pass (plan.subtask_seeded_relabel) that, after
segmentation, re-labels each span using previous/current/next segment
contact sheets and the seed label as a strong prior, minimally correcting
it. Mirrors macrodata's best end-to-end labeling step. Boundaries are
untouched; one extra VLM call per span. Off by default.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(annotate): robust OpenAI-compat client for hosted VLMs
Guard against a choice with no message (safety filter or a thinking model
that spends its whole budget before emitting content) so one empty reply
no longer crashes the whole annotation run; treat it as an empty response
and let the existing JSON-retry path handle it.
Add an optional `reasoning_effort` knob on VlmConfig, forwarded to the
server when set, to cap a thinking model's reasoning (needed for Gemini
via its OpenAI-compatible endpoint).
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(annotate): legible tile-scaled timestamp on contact sheets
The burned-in timestamp used the ~10px bitmap default font, which blurs
once the model downsamples a full contact sheet into 768px tiles, so the
VLM can no longer read the exact source time a boundary depends on. Scale
the timestamp to the tile height (with a graceful fallback on older
Pillow) so the visual time cue stays readable at sheet resolution.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(annotate): lean GEPA-aligned subtask segmentation prompt
Replace the verbose, label-heavy segmentation prompt with a lean
adaptation of the blog's GEPA-found completed_events_duration_prior
recipe: focus on completed manipulation events, explicit no-split /
no-merge rules, a 2-10s duration prior, and an instruction to prioritize
temporally correct boundaries over label wording. The previous prompt
over-weighted label guidance, which traded away boundary precision.
Co-authored-by: Cursor <cursoragent@cursor.com>
* revert: restore original subtask segmentation prompt
The lean GEPA-aligned paraphrase (dd4b0110d) regressed Gemini on the
30-ep subset: Seg F1 0.259 -> 0.189 and E2E 0.184 -> 0.135, driven by
worse under-segmentation (224 -> 188 preds). The blog's 0.306 came from
the actual GEPA-search artifact, which a hand paraphrase does not
reproduce. Restore the original prompt, which remains our best config.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(annotate): env-var override for prompt templates
Allow LEROBOT_PROMPT_OVERRIDE_<name> to supersede the packaged prompt
file at load time. Enables prompt search (GEPA) to inject candidate
segmentation prompts into a remote annotate job via an env secret,
without committing a branch per candidate.
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs(annotate): genericize hosted-VLM comments (no model name)
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs(annotate): document seeded-relabel and reasoning_effort flags
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(annotate): update subtask-prompt marker to match WGO-tuned prompt
The three plan-module tests keyed the canned VLM responder on the
literal 'atomic subtasks', which the WGO-tuned segmentation prompt no
longer contains (it now segments 'COMPLETED manipulation events'). Point
the fixture markers at the current wording so the subtask call is matched
again.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add Isaac Teleop SO-101 leader-arm teleoperator
Add the NVIDIA Isaac Teleop teleoperator scaffolding and its first device:
SO101LeaderArm, a back-drivable SO-101 leader arm on Isaac Teleop's generic
joint-space device path. It reads the leader's joints from the so101_leader
plugin via JointStateSource and emits follower-ready {joint}.pos (rad2deg arm,
gripper -> RANGE_0_100) for direct 1:1 joint drive.
- IsaacTeleopTeleoperator base + IsaacTeleopConfig (shared session/CloudXR config)
- SO101LeaderArm / SO101LeaderArmConfig and leader_joints_to_robot_action
- examples/isaac_teleop_to_so101/teleoperate_leader.py example
- pure-numpy conversion tests
- isaac-teleop optional extra + NVIDIA PyPI index in pyproject
* Add Isaac Teleop XR controller teleoperator for SO-101
Add end-to-end XR (VR) controller teleoperation of an SO-101 follower arm via
the NVIDIA Isaac Teleop stack, layered on the Isaac Teleop scaffolding.
Teleoperator (src/lerobot/teleoperators/isaac_teleop/):
- XRController / XRControllerConfig: connect to the CloudXR runtime, auto-launch
the Isaac Teleop session, and expose get_action() emitting the raw base-frame
grip pose, squeeze, and trigger.
- MapXRControllerActionToRobotAction: stateless per-frame mapper from the XR
action to the IK input contract (absolute ee.x/y/z, ee.gripper_pos, wrist_roll).
- OverwriteWristRollFromAngle: post-IK step writing the operator wrist-roll [rad]
onto wrist_roll.pos [deg], recovering the under-determined roll DOF.
Example (examples/isaac_teleop_to_so101/):
- teleoperate.py: thin absolute-pose IK pipeline with an in-loop clutch (engage
latch + 1:1 delta rebase of position and orientation), EEBoundsAndSafety, and
InverseKinematicsEEToJoints; slews to a recorded home on startup.
- record_reset_pose.py / download_assets.py / webxr.env / .gitignore.
Also:
- Extend robot_kinematic_processor.py with EEBoundsAndSafety and
InverseKinematicsEEToJoints.
- Add XRControllerConfig + base_T_anchor to the Isaac Teleop config.
- Add docs/source/isaac_teleop.mdx and the _toctree entry.
- Add unit tests for the CloudXR launcher and the XR controller processor.
* Unify Isaac Teleop SO-101 scripts behind a mandatory device selector
Merge teleoperate.py (XR controller: clutch + soft-orientation IK) and
teleoperate_leader.py (SO-101 leader arm: 1:1 joint mirror) into a single
teleoperate.py driven by a `lerobot-teleoperate`-style draccus CLI: a follower
`--robot.*` and an input `--teleop.*`, where `--teleop.type` (xr_controller |
so101_leader) selects the Isaac device.
Uses a "dispatch, don't merge" shape: per-device setup_xr/setup_leader build a
Device bundle (compute / startup / cleanup / command); a shared slew() takes a
per-step target callable (XR a fixed reset pose, leader a live re-read so the
1:1 handoff stays continuous); one device-branchless outer loop runs both, with
compute() -> None meaning "hold at the measured pose" (XR disengaged or leader
stale). The entrypoint is @parser.wrap()'d over a TeleoperateConfig dataclass and
dispatches on the parsed config type; device knobs ride on --teleop.* (the leader
serial port is --teleop.port, forwarded to the plugin) and loop/launch knobs are
top-level (--launch_plugin=<path> collapses the old --launch-plugin/--plugin-bin
pair; --reset_to_origin/--align/--dry_run).
To let the Isaac devices claim the natural --teleop.type names without colliding
with the serial so101_leader of lerobot-teleoperate, give IsaacTeleopConfig its
own draccus choice registry (own _choice_registry, decoupled from the global
TeleoperatorConfig one) and register XRControllerConfig as "xr_controller" and
SO101LeaderArmConfig as "so101_leader" there; the example types its teleop field
as IsaacTeleopConfig so the choices resolve against that scoped registry. These
devices drive the bespoke clutch/IK/align loop and are not routed through
make_teleoperator_from_config, so dropping them from the global registry is inert.
YAGNI sweep of the commit train: delete the orphaned OverwriteWristRollFromAngle
(wrist_roll_processor.py) plus its export and tests -- no producer emits
wrist_roll; the live XR path uses orientation-weight IK on the 5-DOF arm by
design. Kept the load-bearing knobs (orientation_weight, raise_on_jump,
base_T_anchor) and the optional reset-pose recorder. Updated isaac_teleop.mdx
for the unified entrypoint and excised the stale roll-retargeter prose.
Net LOC down (two scripts 714 lines -> one), in-loop device branches reduced to
zero. Planned and reviewed via a 6-persona multi-agent panel (3-round planning
convergence + 2-round review). Verification (isaacteleop/placo not installable
here, so the device classes cannot connect, but their config dataclasses and the
script import fine via deferred imports): the teleoperators test suite passes
(45 passed, 2 skipped), draccus parsing of both target command lines yields the
right config subclass with scoped --teleop.type, --help renders the scoped
choices, the serial so101_leader stays in the global registry, and ruff
check/format are green.
Signed-off-by: Jiwen Cai <jiwenc@nvidia.com>
* Add Isaac Teleop SO-101 dataset recording script
record.py records a LeRobot dataset while driving the SO-101 follower
with either Isaac Teleop device (--teleop.type=xr_controller |
so101_leader), mirroring teleoperate.py's device dispatch.
* Extract shared Isaac Teleop SO-101 example infra into common.py
teleoperate.py and record.py both built the per-device pipeline and ran the
same read -> compute -> hold-when-idle -> sleep loop, with record.py importing
internals from teleoperate.py. Move the shared device/loop infrastructure
(Device, slew, Clutch, setup_xr/setup_leader + leader helpers, reset infra and
constants) into a new common.py, and add build_device() + hold_action() to
collapse the connect/dispatch/startup and idle-hold glue duplicated in both
entry points. The setup functions now type their config against a LoopConfig
Protocol, so common.py is decoupled from either CLI; both import from it.
Also rename record_reset_pose.py -> override_reset_pose.py so it is not confused
with record.py, and update the doc references.
* Add stdin keyboard backend so recording shortcuts work over SSH/headless
lerobot's init_keyboard_listener() uses pynput, which hooks GLOBAL key events
from the display server. Over SSH, under Wayland, or on a headless box with only a
TTY, keystrokes go to the terminal's stdin instead, so the listener never fires and
the Right/Left/Esc recording shortcuts silently do nothing.
Add a stdin (termios) keyboard backend to the example's common.py and an
init_keyboard_listener() that prefers it whenever stdin is an interactive TTY
(works over SSH / Wayland / headless-with-tty), falling back to lerobot's
pynput/headless listener for GUI launches with no controlling terminal. Selectable
via LEROBOT_KEYBOARD_BACKEND={auto,stdin,pynput,none}. The backend keeps ISIG so
Ctrl-C still works and always restores the terminal (on stop() and via atexit).
record.py now sources init_keyboard_listener from common; the Right/Left/Esc -> flag
mapping and the (listener, events) contract are unchanged.
Also convert record.py's loop_kwargs to a dict literal (ruff C408).
* Wait for the XR headset to connect before driving the arm
On the xr_controller path the example connected CloudXR and immediately ran the
reset slew + control loop, even if no headset was connected — the arm moved before
the operator was in VR, and get_action() just returned zeros so the clutch never
engaged.
Add an is_tracking property to XRController (set from the controller stream's
optional group, mirroring SO101LeaderArm) and a _wait_for_xr_controller() helper in
common.py that prints connection instructions (CloudXR web client URL + this
workstation's candidate IPv4s, with loopback/link-local and virtual/bridge/USB-gadget
interfaces filtered out) and polls until the controllers stream (indefinite, 15s
reminder, Ctrl-C to abort). setup_xr.startup() now connects, waits for the headset,
THEN runs the reset slew and seeds the clutch — so the arm only moves once the
operator is connected and watching. Mirrors the leader path's _wait_for_leader; both
record.py and teleoperate.py inherit it via the shared setup_xr.
* Address review feedback on the Isaac Teleop -> SO-101 example
Review-response and CI fixes for the Isaac Teleop -> SO-101 example.
- Move the XR Clutch into src/lerobot/teleoperators/isaac_teleop/clutch.py
(pure numpy + Rotation, no isaacteleop import), export it, and add
tests/teleoperators/test_clutch.py.
- Drop the vendored stdin keyboard listener; record.py uses a small terminal-
first wrapper over upstream's TerminalKeyListener (works over SSH even with a
local X display), falling back to upstream init_keyboard_listener otherwise.
- record.py: pass rgb_encoder/depth_encoder to LeRobotDataset create()/resume()
(upstream removed camera_encoder), fixing the AttributeError at record time.
- build_device: derive motor names from robot.action_features instead of
robot.bus (supports non-bus robots), and disconnect the follower if any step
after connect() fails so a failed setup never leaks the connection.
- Read leader joints by the group's declared names (_joints_group_to_rad)
instead of positionally, so a layout mismatch can't silently mirror the wrong
DOF onto the follower; add tests including a reversed-layout group.
- base.py: hoist `from pathlib import Path` to module scope; only the
isaacteleop CloudXRLauncher import stays lazy (optional dep).
- Trim the common.py module docstring and point to docs/source/isaac_teleop.mdx.
- default.env: correct the NV_DEVICE_PROFILE comment (auto-webrtc is the default;
this file overrides to Quest3, which works for both Quest 3 and Pico 4).
- download_assets.py: correct the RAW_BASE comment (tracks main, not pinned) and
add `# nosec B310` next to the existing `# noqa: S310` for the bandit hook.
- uv.lock: add the isaac-teleop extra's deps so `uv sync --locked` matches
pyproject; regenerated with uv 0.8.0 to keep lockfile revision 2 (CI's uv).
- isaac_teleop.mdx: prettier formatting.
* fix(.gitignore): removing .gitignore and using lerobot cache folder instead to store local user files
* chore(docstrings): reducing docstrings in default.env
* feat(URDF): cleaning up and simplifying the URDF download procedure
* feat(robot guard): adding a guard in case an unsupported robot type is provided (so-arms only)
* fix(imports): enforcing a python module structure to simplify imports
* feat(safe read): extending the motor bus safe read rationale to reset pose setting
* chore(trim): trimming lenghty comments and docstrings
* fix(deps): use isaacteleop [retargeters-lite] extra to unblock aarch64 (DGX Spark) (#3933)
* fix(deps): drop isaacteleop [retargeters] extra to unblock aarch64
The [retargeters] extra pulls dex-retargeting (pins numpy<2.0, conflicting
with lerobot's numpy>=2.0) and nlopt>=2.8 (no aarch64 wheels), making
lerobot[isaac-teleop] unresolvable on ARM (DGX Spark, Jetson Thor, GH200)
and over-constrained on numpy everywhere else.
The LeRobot teleoperators only import isaacteleop.retargeting_engine,
isaacteleop.cloudxr and isaacteleop.teleop_session_manager, all shipped in
the base wheel (requires only numpy>=1.23), so the extra is unused.
Verified on DGX Spark (aarch64, Python 3.12): resolves and installs with
isaacteleop 1.3.131 + numpy 2.2.6; all imported symbols load.
* fix(deps): use isaacteleop [retargeters-lite] extra for aarch64 support
Pin to isaacteleop ~=1.3.131 (the release that added ARM64/aarch64 support)
and swap the full [retargeters] extra for the new [retargeters-lite] one
(scipy-only). The full extra drags in dex-retargeting (pins numpy<2,
conflicting with lerobot's numpy>=2.0) and nlopt>=2.8 (no aarch64 wheels),
making lerobot[isaac-teleop] unresolvable on ARM hosts (DGX Spark, Jetson
Thor, GH200) and over-constrained on numpy everywhere else.
The LeRobot teleoperators only import isaacteleop.retargeting_engine,
isaacteleop.cloudxr and isaacteleop.teleop_session_manager — all covered
by the base wheel + retargeters-lite.
Verified on DGX Spark (aarch64, Python 3.12/3.13): resolves and installs
with isaacteleop 1.3.131 + numpy 2.2.6 + scipy 1.18.
* feat(deps): re-add full [retargeters] extra gated to x86_64
Keep the dex-retargeting/nlopt-based retargeters available on x86_64 (where
their wheels exist) via an environment marker, while ARM hosts (DGX Spark,
Jetson Thor, GH200) resolve with base + [retargeters-lite] only.
Verified: uv lock resolves on both platforms; on aarch64 the compile
excludes nlopt/dex-retargeting, on x86_64 they are included.
---------
Co-authored-by: Johnny Nunez <22727137+johnnynunez@users.noreply.github.com>
* chore(docstrings): trimming latest docstrings
* chore(teleop): move isaac-teleop to examples + update docs + add readme with installation notes
* chore(deps): restore uv.lock
* fix(example: isaac teleop parsing config
* fix(examples): isaac atomic-gripper controller
* feat(Examples): isaac-teleop holdlatch
* chore(examples): some other minor improvements for isaac-teleop
* chore(examples): top-level imports isaac-teleop
* chore(Examples): address ai review isaac-teleop
---------
Signed-off-by: Jiwen Cai <jiwenc@nvidia.com>
Co-authored-by: Jiwen Cai <jiwenc@nvidia.com>
Co-authored-by: Johnny <johnnync13@gmail.com>
Co-authored-by: Johnny Nunez <22727137+johnnynunez@users.noreply.github.com>
Co-authored-by: Steven Palma <steven.palma@huggingface.co>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
* feat(policies): add EVO1 policy
* fix(evo1): infer batch size after normalizing image dims
`_collect_image_batches` read `batch_size = batch[camera_keys[0]].shape[0]`
before normalizing per-camera tensors to `(B, C, H, W)`. For an unbatched
`(C, H, W)` input (which the function tries to support via the `image.dim() == 3`
branch), this picked up the channel count `C` instead of the real batch size,
making the subsequent per-sample loop iterate `C` times and indexing go
out of bounds.
Normalize each camera tensor up-front, then read `batch_size` from the
normalized batch dim. Adds `test_collect_image_batches_handles_unbatched_chw`
covering the regression.
Reported by Copilot review on huggingface/lerobot#3545.
* chore(lock): regenerate uv.lock for evo1 extra
Adds the `evo1` entry to `[package.metadata.requires-dist]` and the
`provides-extras` list so that `uv sync --locked --extra test` (used by
fast_tests.yml) no longer reports the lockfile as stale.
Generated with `uv 0.8.0` (matching `UV_VERSION` in fast_tests.yml).
The non-evo1 marker tweaks are produced by `uv lock` re-resolving the
existing dep graph and are not introduced by this PR.
* chore(evo1): align with policy contribution guide conventions
- Add `src/lerobot/policies/evo1/README.md` symlink into `docs/source/evo1.mdx`
to match the in-tree README convention (mirroring the EO-1 layout).
- Convert `transformers` import in `internvl3_embedder.py` to the standard
`TYPE_CHECKING + _transformers_available` two-step gating used by other
optional-backbone policies (e.g. diffusion). The previous lazy-in-`__init__`
import was functionally equivalent for runtime gating but didn't expose the
real symbols to type checkers.
- Add `lerobot[evo1]` to the `all` extra in `pyproject.toml` so
`pip install 'lerobot[all]'` keeps installing every optional policy.
Per the guidance in https://moon-ci-docs.huggingface.co/docs/lerobot/pr_3534/en/contributing_a_policy.
* fix(evo1): finalize policy guide alignment
* docs(evo1): format results table
* Fix EVO1 LIBERO rollout processors
* Fix EVO1 LIBERO eval action postprocessing
* Fix eval action conversion for bf16 policies
* fix(evo1): move LIBERO padding into policy processors
* refactor(evo1): use native HF InternVL3-1B-hf, drop trust_remote_code
- Switch from OpenGVLab/InternVL3-1B (requires trust_remote_code=True)
to OpenGVLab/InternVL3-1B-hf (native transformers implementation).
- Replace manual _extract_feature + _prepare_and_fuse_embeddings with
a single model.forward() call — verified bit-for-bit identical output.
- Remove ~170 lines of manual ViT/pixel-shuffle/projection logic.
- Symlink README.md to docs/source/ following repo convention.
Weights are byte-identical between both model variants; only the module
naming differs. All 12 existing unit tests pass. Local training (10 steps)
on maximellerbach/omx_pickandplace confirmed working.
* refactor(policy): evo1 GPU-batched preprocessing + vectorized attention masking + remove dead code
* fix(style): pre-commit
oops
* chore(evo1): delete added test + reduce diff
* refactor(policies): use config for evo1 + local imports
* refactor(policies): multiple improvements
* chore: update docs + remove legacy codepaths
* feat(policies): implement RTC to EVO1
---------
Co-authored-by: javadcc_mac <javadcc1@sjtu.edu.cn>
Co-authored-by: Yiming Wang <145452074+JAVAdcc@users.noreply.github.com>
Co-authored-by: Martino Russi <nopyeps@gmail.com>
* Add GR00T N1.7 support
Add GR00T N1.7 policy configuration, checkpoint compatibility, processor parity, LIBERO documentation, and focused tests.
Co-authored-by: Ryan Halabi <ryhalabi@nvidia.com>
* Move Groot processor compatibility into Groot loader
* Restore GR00T Flash Attention install guidance
* Allow Groot fake RTC chunk prefetch
* Fix GR00T N1.7 RTC action decoding
* Trim GR00T N1.7 RTC chunks to valid horizon
* Ignore padded GR00T N1.7 RTC prefix rows
* removed n1.5 dependency
* removed remaining N1.5 traces
* groot: auto-enable LIBERO gripper action transform for libero_sim
GR00T N1.7 emits gripper in [0,1] but LIBERO expects [-1,1]. The decode
transform existed but was never auto-enabled for embodiment_tag=libero_sim,
so the policy scored 0% on LIBERO eval. Auto-set it in __post_init__ (still
overridable). LIBERO Spatial eval: 0% -> 98%.
* Reconnect GR00T relative action processors
* groot: remove dead N1.5 code (eagle2_hg_model, flow_matching_action_head, action_encoder)
N1.7 backbone is nvidia/Cosmos-Reason2-2B via Qwen3VLForConditionalGeneration,
not Eagle2 — eagle2_hg_model/ had zero refs outside its own dir.
GR00TN17ActionHead (groot_n1_7.py) re-implements MultiEmbodimentActionEncoder +
CategorySpecificLinear + swish + SinusoidalPositionalEncoding locally, so
flow_matching_action_head.py (N1.5 FlowmatchingActionHead) and its sole
dependency action_encoder.py are dead. Verified: no src/ or tests/ reference.
Removed (~2037 LOC):
- eagle2_hg_model/ (4 files, ~1575 LOC)
- action_head/flow_matching_action_head.py (408 LOC)
- action_head/action_encoder.py (54 LOC)
cross_attention_dit.py KEPT (DiT/AlternateVLDiT/SelfAttentionTransformer live in N1.7).
* groot: reuse lerobot get_device_from_parameters instead of inline lookup
modeling_groot.py duplicated next(self.parameters()).device twice. LeRobot
ships get_device_from_parameters in policies/utils.py (used by diffusion,
vqbet, tdmpc, gaussian_actor). Reuse it for consistency with the framework.
* groot: fix stale Eagle VLM docstring in processor (N1.7 uses Qwen3-VL backbone)
Addresses checker nit: processor_groot.py docstring still described the N1.5
Eagle VLM path with eagle_content/eagle_* keys that no longer exist in the code.
* test(groot): add N1.7 original-vs-LeRobot output parity test
Verifies the LeRobot GR00T N1.7 integration produces equivalent raw
action_pred to NVIDIA Isaac-GR00T for the same checkpoint, inputs, seed,
precision (fp32) and attention kernel (SDPA): max|diff|=8.9e-7 on the
libero_sim embodiment (GR00T-N1.7-LIBERO/libero_10).
The two impls pin incompatible transformers majors (orig 4.57.3 vs
LeRobot 5.x) and cannot share a process, so the original outputs + exact
collated inputs are produced out-of-process and loaded from an .npz. The
test skips on CI / when the checkpoint or artifact are absent.
* test(groot): parametrize N1.7 parity across all checkpoint embodiments
Generalize the original-vs-LeRobot N1.7 output-parity test from a single
libero_sim case to every embodiment tag in the checkpoint (libero_sim, oxe_droid,
real_g1, the real_r1_pro_sharpa family, and the xdof family). Inputs are built
generically from checkpoint metadata; the test discovers per-tag .npz artifacts
and runs one parametrized case each, loading the LeRobot model once via a fixture.
All 9 embodiments match the original to fp32 epsilon (max|diff| < 3e-6), confirming
the integration is correct across the model's full embodiment space and not overfit
to libero_sim.
* test(groot): self-contained parity test + in-repo producer + docs
- Rename test_groot_n1_7_vs_original.py -> test_groot_vs_original.py
- Make the test self-contained: producer script (dump_original_n1_7.py) now lives
next to the test; default artifact dir is repo-relative
(tests/policies/groot/artifacts/), overridable via GROOT_N1_7_PARITY_DIR. The
test only reads artifacts and skips if absent -- it never creates external dirs.
- Heavy .npz artifacts (~6-9MB each) are gitignored and regenerated by the producer;
never committed.
- Drop the verbose 'MULTIPLE EMBODIMENTS' docstring block (kept a one-line note).
- Document the parity procedure in the groot policy README (docs/source/policy_groot_README.md).
- Rename test fn test_groot_n1_7_get_action_parity -> test_groot_get_action_parity.
9/9 embodiments still pass (max|diff| < 3e-6, fp32 eps).
* docs(groot): drop WHY TWO ENVIRONMENTS block from parity test docstring
* test(groot): move parity producer into utils/ package
Mirror the tests/policies/pi0_pi05/utils convention: move dump_original_n1_7.py into
a tests/policies/groot/utils/ package (with __init__.py) and update all path
references in the test docstring/skip-message and the policy README.
* test(groot): adopt test_groot_lerobot for GR00T N1.7, drop N1.5
The test loaded MODEL_PATH='aractingi/bimanual-handover-groot-10k', an N1.5
checkpoint (config base_model_path=nvidia/GR00T-N1.5-3B, no model_version). On
load, model_version defaults to n1.7 while the base path infers n1.5, so the
version-consistency guard in GrootConfig.__post_init__ raised ValueError and both
test_lerobot_groot_inference and test_lerobot_groot_forward_pass failed. N1.5 is no
longer a supported model_version.
Adopt the test for N1.7:
- MODEL_PATH -> nvidia/GR00T-N1.7-3B (root-level sharded safetensors; loads via
GrootPolicy.from_pretrained as a base N1.7 model).
- Embodiment tag 'gr1' (N1.5) -> 'gr1_unified' (valid N1.7 tag from the checkpoint
embodiment_id.json), via a single EMBODIMENT_TAG constant.
- DUMMY_ACTION_HORIZON 16 -> 40 to match N1.7's native action-chunk size.
- Docstrings/labels updated to 'GR00T N1.7'.
Both tests run and pass on CUDA; full tests/policies/groot/ suite is
73 passed / 0 failed / 0 skipped.
* docs(groot): document the N1.5 removal and the N1.7 parity test
- groot.mdx: breaking-change warning and migration path (pin lerobot==0.5.1 to
keep N1.5, or move to N1.7); the dead `huggingface-cli download` is replaced
with `hf download`.
- policy_groot_README.md: N1.5 removal note, updated paper / model-card links,
and the two-comparison (model parity + preprocessor parity) description of
the original-vs-LeRobot test, including the raw-observation artifacts and
recorded seed.
* fix(groot): N1.7 backbone loading and DiT parameter-count logging
- select_layer default tracks the N1.7-3B checkpoint value (16); real
checkpoint loads still override it from config.json.
- get_backbone_cls recognizes Cosmos-Reason2 / Qwen3-VL backbones by name and
warns (instead of silently assuming) when an unrecognized backbone is loaded
only on the strength of backbone_model_type='qwen'.
- 'revision' pins the GR00T checkpoint repo only and is no longer forwarded
into the unrelated backbone repo load; pin the backbone via
transformers_loading_kwargs instead.
- DiT / SelfAttentionTransformer parameter counts go through logging.debug
instead of print().
* fix(groot): N1.7 config defaults, N1.5 rejection, and processor/model runtime fixes
Covers the GR00T N1.7 source trio (configuration, processor, model wrapper).
Config:
- GrootConfig defaults are the N1.7 values; explicitly passed legacy N1.5-era
values (chunk_size=50, max_state_dim=64, ...) are remapped with a warning
instead of silently.
- action_decode_transform gains an 'auto' sentinel so an explicit 'none'
opt-out wins over the libero_sim default and survives save/load round-trips.
- action_delta_indices is cached on the inputs that determine it.
- Legacy N1.5 checkpoints/configs (tokenizer_assets_repo, model_type/
architectures/eagle backbone markers) are rejected with a single clear
error pointing to lerobot==0.5.1.
Processor:
- GrootN17ActionDecodeStep handles the 2-D (B, D) actions delivered by sync
select_action (relative eef/non-eef decode in eval/record flows).
- Postprocessor falls back to dataset stats when a raw checkpoint lacks the
configured embodiment tag; raw-state cache is per-instance, not
process-global; caller overrides (device, rename_map) are honored on the
raw-checkpoint branch.
- Camera/modality-key mismatches warn (including the zero-match fallback);
deprecated Qwen2VLImageProcessorFast replaced with Qwen2VLImageProcessor;
removed N1.5 processor steps are stubbed to raise the removal guidance and
the action-unpack step is re-registered as _v2.
Model:
- Flash-attention probe is diagnostic-only; forward raises on a missing loss;
print() replaced with logging; N1.5 base-path mismatch includes the
removal guidance.
* fix(groot): skip normalization overrides for training
* fix(groot): GPU/tensor N1.7 image preprocessing + resize to trained resolution
GR00T training was dataloader-bound (0->100->0 GPU-utilization sawtooth).
GrootN17VLMEncodeStep ran the Qwen3-VL image processor per frame on PIL images
on the single CPU main-loop thread, and that cost is timed inside dataloading_s
(preprocessor(batch) runs in the main process, not the dataloader workers), so
adding workers cannot hide it.
- Feed the torchvision-backed Qwen3-VL processor (C,H,W) uint8 tensors instead
of a per-frame Image.fromarray PIL roundtrip, and run resize/normalize/patchify
on config.device (GPU) when available. Bit-identical on CPU when no resize is
configured; with a resize only the PIL->torchvision bicubic backend differs
(<2/255 per pixel). The use_albumentations path stays PIL/cv2; reload on a box
without the saved device falls back to CPU.
- Default image_target_size/crop to the N1.7 backbone's training geometry
(256x256 / 230x230) when a checkpoint ships no image sizing (checkpoint_assets
is None, e.g. finetuning nvidia/GR00T-N1.7-3B via repo-id with a new
embodiment). Previously image_target_size=None disabled the resize, so
full-resolution frames were patchified into ~4.7x more vision tokens than the
model was trained on -- inflating dataloading_s (patchify) and update_s (VLM
sequence) and skewing the input distribution. Checkpoints that pin their own
sizing are honored; the default constants are shared with GR00T_N1_7_DEFAULTS.
Net: preprocessing leaves the CPU critical path and the VLM sees the resolution
it was trained on -- faster training/inference and a correct train/serve
distribution. Affects inference too (shared preprocessor); existing checkpoints
still load (backward compatible) but must be retrained to gain the benefits.
* refactor(groot): N1.7 style cleanup (utils, imports, flash-attn, config)
Mechanical refactor of the GR00T N1.7 policy to match the repo's architecture and
style standards. No change to policy algorithm/numerics; only UX/CLI and packaging
changes. Tests are intentionally left untouched (out of scope) and need updating
for the removed `model_version` field.
Cleanup & consolidation:
- Add `groot/utils.py` holding the pure, side-effect-free helpers (JSON I/O, value
coercion, stat flattening, rot6d/SE3 math, language/batch prep) shared by the
config and processor layers.
- Remove dead code: the unused `resolve_groot_n1_7_backbone_model` cache-resolver
cluster, `GR00TN17Config.to_filtered_dict/json`, and the `_copy_default` wrapper.
Imports & execution guards:
- Hoist nested imports to module top; relative imports within the package, absolute
for external modules. The version-gated Qwen3-VL classes import under the single
`_transformers_available` guard (transformers is pinned >=5.4, which ships them).
- No import-time side effects: `_register_with_transformers()` now runs in
`GR00TN17.__init__` (idempotent via `register(exist_ok=True)`), and the N1.5 step
stubs register lazily before pipeline deserialization (idempotent via the
registry, no run-once globals).
- Gate optional deps at the point of use with `require_package(..., extra="groot")`.
Dependencies & docs:
- Drop `flash-attn` (and its build-only dep `ninja`) from the `groot` extra; default
to SDPA (numerically equivalent) with opt-in via `--policy.use_flash_attention`.
Un-comment `lerobot[groot]` in the `all` extra and regenerate `uv.lock`.
- Rewrite the `groot.mdx` install section: flash-attn is a purely optional,
user-managed optimization that LeRobot neither installs nor requires.
Config & CLI:
- Surface previously-frozen knobs on `GrootConfig` (plumbed into `GR00TN17Config`;
no-ops at their defaults): inference — `num_inference_timesteps`, `rtc_ramp_rate`,
`use_flash_attention`; fine-tuning — `tune_top_llm_layers` (partial-LLM tuning)
and `tune_vlln` (previously hardwired to True).
- Convert the single-valued `model_version` and `n1_7_backbone_model` fields to
internal constants.
- Keep `base_model_path`: it is NOT equivalent to `pretrained_path` (raw NVIDIA
checkpoints have no LeRobot `type` field and load only via `base_model_path`) and
is genuinely user-tunable.
- Keep the deprecated Isaac-GR00T/N1.5 fields (and the dead LoRA fields) as a
back-compat block so a v0.5.1 N1.5 `config.json` still parses under draccus and is
rejected with the friendly N1.5 removal message instead of an opaque decode error.
* Optimize GR00T N1.7 image preprocessing
* Remove PIL fallback from GR00T preprocessing
* Fix GROOT relative action training stats
* Address GROOT relative action review feedback
* Fix GROOT N1.7 relative action stats
* Fix GROOT relative action training stats
* Fix GROOT relative action padding and RTC leftovers
* Reset rollout state after robot episode end
* Revert "Reset rollout state after robot episode end"
This reverts commit 1322f45aec.
* Move GROOT relative stats out of train script
* Guard GR00T relative action stepwise decode
* Match GR00T N1.7 OSS preprocessing and relative actions
* Apply LIBERO action decode override after loading
* Format GR00T OSS parity changes
* chore(policies): add guards, warnings and comments + recover tests n1.5 check
* fix(style): pre-commit
* fix(ci): guard dependecy checks
* chore(groot): move cv2 to the top as its in the default install tag
* chore(policies): add explicit dataset dependecy to gr00t implementation
* fix(test): add guard
* fix(groot): make N1.7 letterbox opt-in
* feat(groot): activate checkpoint-configured N1.7 raw-state dropout during training
Isaac-GR00T applies dual state regularization during fine-tuning: raw-state
zeroing driven by the processor sidecar's state_dropout_prob (0.2 for the
inspected N1.7 checkpoint) plus encoded-feature dropout. Baseline LeRobot kept
the processor in deterministic mode, so the raw-state dropout never activated
(RCA Tier-2 contributor to the LeRobot-trained SO-101 failures).
- GrootN17PackInputsStep: runtime-only 'training' flag + state_dropout_prob;
whole-sample state zeroing gated on torch.is_grad_enabled() so eval and
no_grad validation paths are unaffected
- sidecar loader reads state_dropout_prob from processor_config.json
- state_dropout_prob serializes with the step; the training flag intentionally
does not (reloaded pipelines default to eval, re-enabled only when processors
are rebuilt with dataset_meta)
- _set_groot_preprocessor_training toggles any dataclass step exposing a
'training' field on serialized-pipeline reloads
Verification: tests/policies/groot/test_groot_state_dropout.py (4 passed) on
RTX PRO 6000 / CUDA 13.3.
* fix(groot): align N1.7 fine-tuning optimizer/scheduler/precision with Isaac-GR00T
Evidence from the LeRobot-vs-OSS checkpoint comparison: the LeRobot/HF 8k
checkpoint's DiT moved only ~19% as far from base as the OSS-trained one
(0.0547 vs 0.285 relative L2) - undertrained because the scheduler decayed over
a hardcoded 10k steps regardless of --steps, on top of beta1/clip mismatches.
- AdamW betas (0.95, 0.999) -> (0.9, 0.999) and grad_clip_norm 10.0 -> 1.0
(Isaac defaults)
- scheduler: hardcoded CosineDecayWithWarmup(10k decay, floor 10% peak) ->
DiffuserSchedulerConfig HF cosine with ceil(max_steps * warmup_ratio) warmup,
deriving num_training_steps from the outer --steps at runtime
- model_params_fp32 (default true): keep master weights in FP32 and compute
under BF16 autocast like the native N1.7 recipe (fixes optimizer-update
numerics vs pure-BF16 params)
- weight-decay grouping via transformers get_parameter_names: biases and norm
parameters excluded from decay
- restore the TF4 lm_head/embedding weight tie so the unused Qwen LM head stays
frozen and deduplicated in checkpoints
- action_mask kept in native dtype for the masked flow-matching loss
- drop_n_last_frames: exclude episode tails that cannot supply a complete
action chunk (Isaac sampler behavior)
Verification: tests/policies/groot/test_groot_training_optim_contract.py
(7 passed) + remaining groot suite 11 passed/5 skipped on RTX PRO 6000 /
CUDA 13.3. Note: tests/policies/groot/test_groot_n1_7.py does not collect on
the base branch (pre-existing ImportError, fixed in PR #37).
* feat(groot): train-time random crop for N1.7 (eval keeps center crop)
Isaac-GR00T crops a random crop_fraction window during training and the
deterministic center window at eval, replaying the sampled window across all
camera views of a sample. This contract is unchanged since the N1.5 release
(gr00t/data/transform/video.py: "If mode is 'train', return a random crop
transform. If mode is 'eval', return a center crop transform.") and mirrors
LeRobot's own Diffusion/VQBeT crop_is_random pattern. The LeRobot N1.7 port
used the eval center crop for training too, so the fine-tuned projector/DiT
never sees frame borders and trains on a single fixed appearance point.
Scope: crop geometry ONLY - no color jitter, no new dependencies. The random
window is plain numpy slicing inside the existing cv2 eval transform:
- _transform_n1_7_image_for_vlm_albumentations gains crop_position=(y, x)
fractions; None keeps the center crop byte-identical to before (verified
by test)
- GrootN17VLMEncodeStep gains a runtime-only 'training' flag (never
serialized; reloaded pipelines default to eval); training samples ONE
window per sample and reuses it across (timestep, view) frames - Isaac's
cross-view consistency
- gated on torch.is_grad_enabled() so no_grad validation and frozen-eval
paths are unaffected
- wired via dataset_meta is not None in make_groot_pre_post_processors and
the existing _set_groot_preprocessor_training on serialized reloads
Verification: tests/policies/groot/test_groot_train_random_crop.py (8 passed:
center-crop bit-exactness with crop_position=None, corner/center windows,
cross-view replay, train!=eval, no_grad gating, seed reproducibility,
serialization contract) + groot suite 23 passed / 5 skipped on RTX PRO 6000 /
CUDA 13.3.
* docs(groot): update Training & hardware Evaluation commands
Replace the multi-GPU accelerate-launch Training snippet with the current
single-command 'uv run lerobot-train' N1.7 recipe (relative actions excluding
gripper, bf16, flash attention, chunk/n_action_steps=16, bs64/20k steps).
Replace the bimanual 'Evaluate in your hardware setup' rollout example with the
SO-101 follower RTC 'uv run lerobot-rollout' command (strategy.type=base,
inference.type=rtc, wrist+front cameras, place-the-vial task).
Docs-only; no source/test changes.
* docs(groot): parameterize commands with env vars + fill LIBERO results
- Introduce BASE_MODEL / DATASET_ID / REPO_ID / JOB_NAME / OUTPUT_DIR env vars
in the training command and reuse OUTPUT_DIR + BASE_MODEL in the rollout cmd.
- Fill the LIBERO benchmark table with GR00T-LeRobot success rates
(Spatial 94%, Object 98%, Goal 93%, LIBERO 10/Long 90%; avg 93.75%),
drop the OSS column and XX placeholders. LeRobot-focused.
* docs(groot): drop export block, reference env vars directly
Use $DATASET_ID / $BASE_MODEL / $REPO_ID / $OUTPUT_DIR / $JOB_NAME as
bare placeholders in the commands without concrete export assignments.
* docs(groot): keep BASE_MODEL export in training command
* docs(groot): use literal HF repo IDs for dataset/policy repo_id
Public-facing Hub references (--dataset.repo_id, --policy.repo_id) shown as
concrete IDs; local-only values ($OUTPUT_DIR, $JOB_NAME) stay as placeholders.
* docs(groot): add LIBERO training command example
* docs(groot): remove LIBERO checkpoints subdirectory section
* docs(groot): use $BASE_MODEL for base_model_path in LIBERO eval
* docs(groot): drop hf download step from LIBERO eval, fix intro
* docs(groot): restore suite checkpoint download intro sentence
* docs(groot): remove checkpoint download note above LIBERO eval
* docs(groot): update training and rollout commands with new parameters and dependencies
* Add sample so101 training command
* Remove sample so101 training command
* docs(groot): remove optional Flash Attention setup instructions and update base model path for evaluation
* docs(groot): update training command with image transformation parameters
* docs(groot): add note on inference.queue_threshold value for stable inference
* chore(style): pre-commit gr00t
* docs(groot): update
* chore(policies): minor details
* fix(groot): license headers + test guards
* chore(policies): fix tests
* docs(groot): relative actions param doc
* chore(policy): address some of the AI review items
---------
Co-authored-by: Andrew Wrenn <awrenn@nvidia.com>
Co-authored-by: Ryan Halabi <ryhalabi@nvidia.com>
Co-authored-by: nv-sachdevkartik <ksachdev@nvidia.com>
Co-authored-by: groot-validation <groot-validation@localhost>
Co-authored-by: johnnynunez <johnnynuca14@gmail.com>
Co-authored-by: lbenhorin <lbenhorin@nvidia.com>
* feat(policies): add LingBot-VA autoregressive video-action world model
Port the LingBot-VA policy (Wan2.2 dual-stream video+action world model) into
LeRobot, following the EO-1 / VLA-JEPA conventions. Covers inference, checkpoint
conversion, and predicted-video saving (training is deferred to a follow-up PR).
- Vendored Wan transformer/attention/flex/VAE/scheduler modules (key names preserved
for near-identity conversion); torch SDPA default, flashattn/flex lazy-guarded.
- LingBotVAConfig (registered "lingbot_va") + processor with fixed-quantile action
unnormalization; full dual-stream sampling loop with CFG, two flow-matching
schedulers and KV cache, mapped onto select_action with observed-keyframe feedback.
- convert_lingbot_va_checkpoints.py (libero/robotwin variants): bundles the ~5B
transformer, lazy-pulls the frozen VAE+UMT5 from the source repo.
- Predicted-video plumbing in lerobot_eval (predicted_frames_callback; opt-in via
--policy.save_predicted_video) and ConstantWithWarmupSchedulerConfig.
- pyproject: widen diffusers-dep to <0.37, add lingbot_va + imageio-dep extras,
add lingbot_va and (missing) eo1 to `all`.
- Factory + policies/__init__ wiring, docs page + toctree, and tests.
Note: the LIBERO success-rate correctness gate must be validated on a CUDA GPU
with the converted checkpoint.
* feat(lingbot_va): RoboTwin eef-pose eval, single-file model, Hub checkpoints
Make the LingBot-VA port runnable on both LIBERO and RoboTwin and clean up the
package to LeRobot conventions.
- Consolidate all vendored Wan2.2 model code (transformer, attention, VAE helpers,
flow-matching scheduler, grid utils, flex-attention) into a single
modeling_lingbot_va.py; remove the separate wan_*/schedulers modules.
- Move the fixed action (un)normalization quantiles out of the config and into the
post-processor (LIBERO 7-DoF + RoboTwin 16-d eef); remove the conversion script in
favour of ready-to-use LeRobot-format checkpoints on the Hub.
- Fixes found via on-sim validation: undo LIBERO's 180-degree image flip
(image_hflip), encode obs as a multi-frame streaming-VAE clip, reset the streaming
VAE cache between episodes, run the transformer in config.dtype, lazy-load frozen
VAE/UMT5 by subfolder with the text encoder on CPU.
- RoboTwin: add an end-effector-pose action mode to RoboTwinEnv (16-d per-arm
xyz+quat+gripper deltas composed onto the initial eef pose, executed via CuRobo IK)
and the robotwin_tshape latent layout (full-res head + half-res wrists via a second
streaming VAE) with the upstream RoboTwin action quantiles + camera mapping.
- Predicted-video saving works for both benchmarks; docs + tests updated.
* feat(lingbot_va): implement training / fine-tuning (flow-matching loss)
- Implement LingBotVAPolicy.forward(): dual-stream flow-matching training loss
(latent + action, timestep-weighted, action-masked) ported from upstream train.py;
VAE-encodes camera clips, UMT5-encodes the task, noises both streams, runs the
block-causal flex-attention training pass (forward_train).
- training_loss_from_streams() core + _build_training_streams() data prep (action
scatter into the 30-d space, multi-frame VAE encode incl. robotwin_tshape).
- get_optim_params returns only trainable transformer params (LoRA/PEFT friendly);
VAE/UMT5 stay frozen. Training needs attn_mode='flex'.
- Add a tiny-config single-training-step test (forward->loss->backward->AdamW) and a
Training/fine-tuning section in the docs.
* fix(lingbot_va): CI quality gate + fast-test collection
- Add tests/policies/lingbot_va/__init__.py so the test files don't clash by basename
with tests/policies/vla_jepa/* under pytest's default import mode (fast-test collection error).
- Fix vendored typos flagged by the typos hook (pach_scale->patch_scale, total_tolen->
total_token_len, stablized->stabilized) and a mypy union-attr in RoboTwinEnv._read_eef_pose.
- Apply Prettier formatting to docs/source/lingbot_va.mdx.
* docs(lingbot_va): document EEF action-channel schema + camera order
* Update lingbot_va.mdx
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update pyproject.toml
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update pyproject.toml
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* refactor(lingbot_va): drop hardcoded action quantiles; source from checkpoint
The LIBERO/RoboTwin action (un)normalization quantiles were hardcoded as module
constants in processor_lingbot_va.py. They are already serialized into each
checkpoint's policy_postprocessor.json (via LingBotVAActionUnnormalizeStep.get_config)
and restored on load by PolicyProcessorPipeline.from_pretrained, so the constants are
dead at eval/load time for the released checkpoints (verified: libero_long/robotwin/base
all carry their quantiles on the Hub).
- Remove LIBERO_ACTION_Q01/Q99, ROBOTWIN_ACTION_Q01/Q99 and _default_action_quantiles.
- make_lingbot_va_pre_post_processors now defaults a fresh (unconverted) build to a
neutral [-1, 1] mapping (identity rescale); real per-benchmark stats come from the
saved checkpoint (or postprocessor_overrides), analogous to dataset-stats normalization.
- Update the config doc comment to point at the checkpoint as the source of truth.
- Tests: replace the LIBERO-default assertion with a neutral-default check, and add a
save_pretrained/from_pretrained round-trip guard for the quantile serialization.
* docs(lingbot_va): trim verbose comments
- configuration_lingbot_va.py: condense multi-line field comments to one-liners
(keep the ── section headers).
- processor_lingbot_va.py: shorten the action-quantile explanation block.
- modeling_lingbot_va.py: drop the bare "# ----" separator rules, keeping the
one-line section headers.
No code changes.
* docs(lingbot_va): trim provenance comments; default wan path to base repo
- configuration_lingbot_va.py: drop the "──" decorations and the
"(from transformer/config.json)" note; default wan_pretrained_path to
robbyant/lingbot-va-base (has the frozen vae/text_encoder/tokenizer subfolders).
- modeling_lingbot_va.py: remove the vendored-code banner and the
"(upstream wan_va/...)" section-header provenance/dash decorations; condense the
transformer-dtype comment to one line.
No code changes.
* refactor(lingbot_va): use built-in UnnormalizerProcessorStep for actions
Replace the bespoke LingBotVAActionUnnormalizeStep with the standard
UnnormalizerProcessorStep in QUANTILES mode, which computes the identical
(action + 1) / 2 * (q99 - q01) + q01 mapping. The per-channel q01/q99 are stored
as the step's saved state (a safetensors file) and restored on load; a fresh build
has no action stats so the step is an identity passthrough.
The 3 Hub checkpoints (lerobot/lingbot_va_{libero_long,robotwin,base}) have been
re-uploaded with the new post-processor (policy_postprocessor.json +
*_unnormalizer_processor.safetensors); reloading from the Hub round-trips q01/q99.
- processor_lingbot_va.py: drop the custom step + registry; build the post-processor
with UnnormalizerProcessorStep (explicit ACTION->QUANTILES norm_map so the
preprocessor / training path is unchanged).
- tests: assert the built-in step is used, identity-when-no-stats, correct quantile
unnormalization, and a save_pretrained/from_pretrained stats round-trip.
* docs(lingbot_va): point checkpoint paths at the lerobot org
The LeRobot-format checkpoints moved from pepijn223/* to lerobot/* (libero_long,
robotwin, base). Update the eval/train --policy.path examples accordingly.
* docs(lingbot_va): condense processor normalization comments
* fix(lingbot-va): align RoboTwin evaluation (#3784)
Thank you for the RoboTwin fix, and alignment!
* applying fixes
* updating uv lock and linting
* adjusting test to match expected values
* cleaning up deps
* cleaning up top level imports, styling, and deps guards
* cleanup
* moving wan utils and loading utils to `utils.py`
* removing ftfy by replicating the prompt_clean function without it (we don't expect to have weird chars given in the prompt anyway)
* removing unused function
* guarding for scipy dep, renaming test to avoid collision
* adding back accelerate for peak memory usage optim + justifying robotwin description dep
---------
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
Co-authored-by: pepijn223 <pepijn223@hf.co>
Co-authored-by: Gangwei XU <gwxu@hust.edu.cn>
Co-authored-by: Maxime Ellerbach <maxime.ellerbach@huggingface.co>
* fix(train): drive Accelerate mixed precision from policy.dtype
`accelerator.autocast()` was always a no-op because `mixed_precision`
was never set, so `--policy.dtype=bfloat16` only cast the model params
(via the policy) while autocast-eligible ops still ran in fp32/tf32.
Map the active policy's `dtype` onto Accelerate's `mixed_precision`
(bfloat16 -> bf16, float16 -> fp16, float32 -> no) so autocast is active
for bf16/fp16 and stays full precision for float32. Policies without a
string `dtype` field fall back to Accelerate's launcher default, so
existing behavior is preserved.
* style(train): condense mixed-precision comment to one line
* fix(depth unit): storing raw depth units in the dataset metadata for correct depth statistics and depth raw frames handling. The unit is stored as a string ("m","mm") under "depth_unit" at the same level as "is_depth_map". Unit is inferred from the depth frame type.
* feat(raw frame unit): adapting dataset reader so that raw depth frames are scaled according to the requested unit
* feat(stats units): rescaling stats when loading a dataset so that the stats are given in the requested unit
* tests(unit): adapting and extending depth tests to units manipulations
* chore(format): formating code
* feat(warning): adding a warning when depth unit is not specified in the dataset
* chore(infer_depth_unit): moving the depth unit inference utility in a more accessible location
* feat(rerun unit): adding correct depth unit display for rerun (foxglove does not support units yet)
* feat(unit getter): adding a proper output_depth_unit getter to LeRobotDataset for cleaner integration
* fix(streaming dataset): extending support for depth units to streaming datasets
* test(rerun): fixing rerun tests
* Add Foxglove display mode for teleoperate
Add a --display_mode flag (rerun|foxglove) to lerobot-teleoperate. When set
to foxglove, stream observations/actions over a Foxglove WebSocket server:
images as RawImage/CompressedImage, scalars as typed JSON channels with
schemas generated from the feature names (sanitized so paths don't need
quoting). Adds a `foxglove` extra.
* Add Foxglove display mode to lerobot-record
Wire the --display_mode flag (rerun|foxglove) into lerobot-record, matching
lerobot-teleoperate: route init/log through the backend-agnostic dispatchers
and stop the visualization backend on exit.
* update foxglove-sdk to 0.25.1
* Use static lerobot.Scalars schema for Foxglove state topics
Replace the per-topic JSON schema derived from feature names with a single
static lerobot.Scalars schema: a scalars array of {label, value} objects. The
same schema fits any robot regardless of which observation/action features it
reports, and the label field lets Foxglove name each series automatically so
one filtered path plots every feature.
* add foxglove option to dataset viz
* Make Foxglove dataset playback loop the sole frame emitter
Address review: the listener no longer emits frames, it only mutates
playback state and queues a one-shot seek index that the playback loop
services. The loop is now the only caller of emit_frame, so concurrent
random access into the on-disk dataset / video decoder never overlaps.
Also remove the dead server_holder and tighten the _foxglove_safe_name
docstring to state what it does and why.
* Label Foxglove dataset scalars with feature dimension names
Use the dataset's per-dimension feature names (e.g. joint names) as the
Foxglove series labels for /observation/state and /action/state instead
of bare indices. LeRobot stores `names` inconsistently (flat list,
{category: [...]}, or {name: index}), so _feature_dim_names handles each
and falls back to indices on any unknown format or length mismatch.
* Make Foxglove server host bindable and refactor topic/channel handling
Pass display_ip through as the Foxglove WebSocket bind host (127.0.0.1
for local only, 0.0.0.0 for all interfaces) instead of always binding
locally. In lerobot-dataset-viz, fold the separate --port into --web-port
so one flag covers both the Rerun web viewer and the Foxglove server port.
Add a _foxglove_topic() helper and thread a per-topic channel cache
through the log helpers so dataset playback stays self-contained instead
of mutating the module-global cache. Promote SUCCESS to constants.py.
* feat(viz): add support for foxglove in rollout + add to viz tag
* fix(docs): remove misleading installation note
* fix(visualization): no duplicated prefix, consolidated norm + warnings log
* chore(viz): minor improvements
* refactor(viz): split files + autoplay + updated docs + added minimal tests
* fix(viz): right tags + warning
* feat(deprecated ws-port): removing rerun's depreacted ws-port parameter in dataset visualization
* chore(web ports): adding global variables for default foxglove/rerun web ports
* feat(depth): adding depth support to foxglove visualizer. Because of foxglove limitations (min and max values on RawImage cannot be set from the SDK), depth is normalized between [0,1] when a depth range is provided.
* fix(rerun depth range): making rerun depth range computation safe against missing stats
* chore(foxglove depth): make it simple, and make it work.
* fix(scaling): fixing depth frames scaling
---------
Co-authored-by: Roman Shtylman <roman@foxglove.dev>
Co-authored-by: Caroline Pascal <caroline8.pascal@gmail.com>
draccus re-parses each config class's source on every parse() to extract
field help text (~2.5s for TrainPipelineConfig). Memoize it for the test
session; the source is constant within a run.
Fast Tests test time: 664s -> 404s (-39%).
Steven Palma