Add compute_pd_gains / compute_action_scale to g1_utils (kp = armature*w^2,
kd = 4*armature*w, with a 2x factor on stiff ankle/waist joints), plus the G1
motor-model layout and shared NATURAL_FREQ/armature/effort constants. The config
now derives its default kp/kd from these instead of hand-tuned values.
Both controllers stop reading kp/kd from ONNX metadata: SONIC uses the config
gains (identical to its baked values), and Holosoma derives them with a hip-pitch
override (7520_14 instead of 7520_22) to match its checkpoint.
Co-authored-by: Cursor <cursoragent@cursor.com>
Drop the full-body pause/direct-publish reset special-casing (and the
_controller_paused plumbing) so SONIC uses the same reset path as the other
controllers. The removed logic is preserved on the better-reset branch.
Co-authored-by: Cursor <cursoragent@cursor.com>
The motion_token / motion_token_state constants are feature-key prefixes, not
secrets; mark them #nosec so the pre-commit bandit hook passes.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep g1_utils close to main: the lowstate -> obs mapping lives in unitree_g1
(where get_observation builds it, left unchanged from main) and the SONIC
controller imports it from there.
The ORT SessionOptions helper (thread-pool cap) is being split into its own
"ORT fix" PR. SONIC only needs quiet logs, so inline a minimal SessionOptions in
the decoder instead of depending on the shared helper.
Split the onboard-controller server/handshake/thin-client work out to
feat/g1_onboard_controller and revert it here:
- unitree_g1.py: drop client + onboard roles, wireless-remote parsing and
motion-service release; restore main's sim/socket-bridge transport. Keep only
the SONIC integration (implicit token action/state, full-body reset/pause,
controller kp/kd + shutdown).
- config: drop onboard/dds_interface/release_motion_control/physical_remote.
- run_g1_server.py + unitree_g1.mdx: reverted to main.
- gr00t/holosoma: keep the move into controllers/ but revert their content to
main (only the package-relative import changes).
Drop the ``sonic_token_action`` config flag; the 64-D latent-token
action/observation interface now switches on automatically whenever the
SONIC whole-body controller is selected (``controller == "SonicWholeBodyController"``).
Keyed via a ``_sonic_token`` property so client, onboard and sim roles agree.
* docs: fix code fences in env processor guide
The "Flexibility and Reusability" section wrapped a duplicated example
in a four-backtick fence and left a following block unclosed, so the
stray closing fence matched a later block. Everything in between
rendered as one code block that swallowed the surrounding prose.
Remove the duplicated block, add the missing closing fence after the
first example, and normalize the four-backtick fences to three so all
fences pair correctly.
* docs(pi0fast): fix typo 40kk -> 40k steps
* docs(integrate-hardware): fix so101 follower source link
* docs(hope_jr): fix dataset example link
The "example" link in the Record section pointed at the dataset's
`/settings` page, which returns HTTP 403 for readers. Drop the
`/settings` suffix so it links to the public dataset page the
sentence describes.
* docs(lekiwi): render emoji shortcodes as unicode
MDX does not expand `🤗` / `🤖` shortcodes, so they showed as
literal text in the rendered install step. Replace them with the 🤗 and
🤖 unicode characters, matching how the other robot pages write emoji.
* docs(smolvla): anchor record link to its section
The "Record a dataset" link dropped readers at the top of the
il_robots page instead of the relevant section. Point it at the
`#record-a-dataset` anchor (the `## Record a dataset` heading in
il_robots.mdx) so the link lands on the step it names.
* fix(utils): validate precise_sleep spin/margin args
Negative spin_threshold/sleep_margin make remaining arithmetic wrong
and can overshoot. Reject them early; cover the no-op path.
* test: drop flaky wall-clock assertion in no-op test
Per review: the 50ms wall-clock check can exceed its bound on a preempted
CI worker even when precise_sleep returns immediately. The direct calls
already exercise the non-positive no-op path, so the assertion is redundant.
* chore(tests): remove precise_sleep test negative values
---------
Co-authored-by: Bartok9 <danielrpike9@gmail.com>
* fix(utils): allow any JSON payload in write_json
The dict-only type stub blocked lists/scalars callers already dump.
Accept Any, set utf-8 encoding, and cover list roundtrip.
* fix(utils): json type
---------
Co-authored-by: Bartok9 <danielrpike9@gmail.com>
* fix(utils): mark Transition.complementary_info NotRequired
TypedDict class-body ``= None`` does not make a key optional and confuses
type checkers. Use ``NotRequired[...]`` so transitions without metadata
are valid.
* refactor(utils): complete NotRequired
---------
Co-authored-by: Bartok9 <danielrpike9@gmail.com>
* fix(utils): raise ValueError from get_safe_torch_device
Bare asserts vanish under python -O and look like programmer bugs.
Convert unavailable CUDA/MPS/XPU requests into clear ValueErrors.
* style: combine nested with in device util tests (ruff)
---------
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
* fix(utils): reject zero-norm / invalid quaternions in Rotation
Zero or non-finite inputs previously slipped through and produced NaN
rotation matrices on later convert/apply. Validate shape and scept for
norm > 0 before normalizing.
* fix(teleop): degrade phone AR quat parse like missing pose
Address review on #3988: Rotation.from_quat now rejects zero/NaN
quaternions. Wrap HEBI iOS ARKit permission in ValueError and return the
existing (False, None, None, None) path so teleop does not die mid-session
before tracking is ready.
* style: ruff format long ValueError in rotation.py
---------
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
* Connect, test and disconnected camera instances sequentially
* Add warmup-s cli argument to lerobot-find-cameras script
* Reduce default record time from 6 to 2 seconds in find_cameras
* Annotate return value of save_image function
* Initialize logging configuration in find_cameras
* fix(robot): type FK-to-EE action features as ACTION not STATE
ForwardKinematicsJointsToEEAction.transform_features declared its
end-effector action features (ee.x/y/z/wx/wy/wz/gripper_pos) with
FeatureType.STATE, copied verbatim from the sibling
ForwardKinematicsJointsToEEObservation (where STATE is correct for
OBSERVATION features). Every other action-producing step in this file
(EEReferenceAndDelta, InverseKinematicsEEToJoints, InverseKinematicsRLStep)
types its ACTION-bucket features as FeatureType.ACTION.
The mismatch mis-classifies the converted EE actions as state, which
propagates a wrong feature schema to downstream consumers keyed on
FeatureType (e.g. normalization norm_map, policy input/output feature
classification).
* test(robot): FK-to-EE step feature-type contract (action vs observation)
Asserts ForwardKinematicsJointsToEEAction emits EE features in the ACTION
bucket typed FeatureType.ACTION, and ForwardKinematicsJointsToEEObservation
emits them in the OBSERVATION bucket typed FeatureType.STATE.
* chore: delete user file
* chore(processor): reduce verbosity
---------
Co-authored-by: Jaagat-P <jaagatp05@gmail.com>
* fix(evo1): re-pad normalizer stats when loading from checkpoint
reconcile_evo1_processors did not re-pad the (un)normalizer stats to
max_state_dim/max_action_dim on the checkpoint-load path. When
lerobot-train loads a checkpoint (e.g. stage2 from a stage1 checkpoint)
it injects the raw dataset stats via processor overrides, so LIBERO's
8-dim state stats normalized a 24-dim padded state and crashed with
"size of tensor a (24) must match tensor b (8)".
Restore _refresh_evo1_normalization_steps (removed in the "remove legacy
codepaths" refactor) and call it from reconcile_evo1_processors so the
loaded stats/features are re-padded to EVO1's fixed widths. Padding is a
no-op when stats are already at the target width.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(evo1): cover reconcile re-padding of overridden normalizer stats
Regression test for the stage2-from-checkpoint crash: reloading a
checkpoint with raw (unpadded) dataset stats injected via processor
overrides must be re-padded to max_state_dim/max_action_dim by
reconcile_evo1_processors, otherwise normalizing the padded state
raises a shape mismatch.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Martino Russi <martino@huggingface.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Revert pyproject.toml and import_utils.py to main: the onnxruntime-gpu
detection fallback and the _onnxruntime_available/_onnx_available flags
are unnecessary. Controllers now import onnx/onnxruntime unconditionally
(matching main) which also works with onnxruntime-gpu since the import
name is stable. Drop the require_package() calls we had added.
Remove the stdin e-stop listener from serve_onboard_controller and the
now-unused os/sys imports; Ctrl-C still triggers graceful shutdown.
Martino Russi