Commit Graph

1157 Commits

Author SHA1 Message Date
Pepijn f04958527e Add sarm (#2639)
* add initial modeling

* make rewind pretrained policy

* add annotation

* small fix

* add sarm

* subtasks

* fix spawn

* fix rewind discrepancies

* Add script to generate embedding for dataset (#2138)

* Add generate and validate script

* fix precommit

* Improve generate embeddings function by using dataset tools (#2206)

---------

Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>

* cleanup

* change order train log

* print batch size

* update sarm processor

* add reward output

* change expected features

* add image validation

* change validation

* get state input from dataset stats

* raise if no state key is found

* pass stats

* cleanup and refactor

* add episode inddex to complementary data

* add subtask init and detection

* revert lerobot_train changes

* pass dataset metadata to policy

* change loadig subtasks

* add small logging

* fix progress conversion and adding initial frame

* use large offset for initial frame (ugly)

* Remove rewind, use clip tokenizer

* add tests, implement formula 1,2 correctly and cleanup

* use task from dataset, cleanup visualizer

* simplify

* simplify and cleanup code and move compute_temporal_proportions to utils

* fix normalization in visualization

* Fix visualization and change prompt

* fix formatting

* add visualize subtask annotations

* use qwen thinking

* try different prompt

* format

* update prompt

* higher temp, long output

* different settings

* use instruct

* show full resp

* split message

* Temp: increase tolerance dataset

* Fix RA-BC (#2572)

* Add next observation loading for RA-BC progress deltas

* Compute weights based on temporal progress deltas instead of static rewards

* Add hard-masking for negative progress deltas in weight computation

* Feat/add dual head (#2582)

* Add dual dense sparse head and annotation

* Add docs

* add dual to procesor

* cleanup

* change sampling in visualize and cleanup

* remove validation

* remove compile

* Feat/test uniform (#2587)

* test uniform

* add different string for misaligned

* Fix rewind and add tests

* uncomment text implementation

* run precommit

* Add head mode for ra-bc

* fix visalization of single task

* add

* return per sample loss

* Fix RA_BC (#2602)

* update rabc implementation

* compute rabc beforehand

* fix import

* add only progress calulation

* use precomputed progress

* multi gpu processing

* import

* fix dataset meta data extraction

* add logging

* logging

* log

* progress per episode

* split differently

* move clip to gpu

* pre decode frames for an episode

* fix cuda initalization

* fix import

* multi processing

* rename

* fix import

* fix

* fix rabc

* use last known progress if oob

* use last known progress if oob

* add misalignment loss with random embeddings

* discard previous changes

* add selection of models to docs for ra_bc

* add transformers dep

* extend tolerance

* initial commit with new codebase

* add tests

* fix

* remove temporal sampler

* drop last frame for sampler

* use original ref

* some fixes

* fix visualization

* remove smoothing and fix order subtasks

* add stride rabc computation

* add push to hub

* add explanation

* add kappa expllaination

* better rabc logging

* feedback pr

* remove dataset tolerance

* revert dataset tool

* revert dataset changes

* add credit

* run precommit

* change path for generate ra_bc

* fix type

* include sarm in all in pyproject

* fix precommit

* lazy import matplotlib

* lazy import qwen

* remove rich console

* skip if transformers is not installed?

* run only when we have faker

* place transformer lazy loading

* Dont test if low transformer version

* fix

* increase transformer

* increase as 4.57.0 is yanked

* remove pi from all

* go back

---------

Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
Co-authored-by: s1lent4gnt <kmeftah.khalil@gmail.com>
2025-12-18 12:50:32 +01:00
Steven Palma 4a151a9682 chore(ci): minor improvement bug-report template & pr auto label (#2676)
* chore(ci): minor improvement bug-report template

* chore(ci): change triggers for PR auto label
2025-12-18 00:23:23 +01:00
Steven Palma 8667b9ef08 chore(ci): minor improvements auto labeling (#2675) 2025-12-17 22:54:47 +01:00
Steven Palma 86eee5c1e2 fix(ci): close bracket pattern (#2674) 2025-12-17 22:40:33 +01:00
Steven Palma 469b855e42 fix(ci): better heuristic + issue type template fix (#2672)
* fix(ci): better heuristic + issue type template fix

* chore(ci): remove keywords in performance tag
2025-12-17 22:31:22 +01:00
Steven Palma 292333cafc chore(ci): update issue template (#2666) 2025-12-17 18:02:20 +01:00
Steven Palma f0c98e23f1 feat(ci): simple automatic labelling (#2667)
* ci: add pr labeler

* ci: add issue labeler

* ci: minor fixes for labelers

* fix(ci): add explicit path for pr labeler
2025-12-17 17:52:45 +01:00
Steven Palma 7621af5acd chore(ci): update PR template (#2665)
* chore: update code of conduct to transformers one

* chore: update PR template
2025-12-17 17:10:04 +01:00
Steven Palma 92fdbe9bbf docs(dataset): add visualization section (#2664) 2025-12-17 14:14:31 +01:00
Steven Palma b303d1ab38 feat(scripts): add more info to lerobot-info (#2663) 2025-12-17 14:14:23 +01:00
Steven Palma b1d162f333 fix(policies): add device back to smolvlm expert (#2662) 2025-12-17 12:12:03 +01:00
Steven Palma 2b304eeb84 feat(dataset): expose tolerance_s argument to training config (#2653) 2025-12-16 00:53:19 +01:00
Sota Nakamura 4e6048a221 finalize the dataset after recording (#2496)
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-15 17:57:04 +01:00
./c² 81ebcac8d7 docs: update IL robots API example and add OpenCV workaround (#2648)
* docs: update IL robots API example and add OpenCV workaround

- Fix import path from lerobot.record to lerobot.scripts.lerobot_record
- Add required processor parameters to record_loop calls
- Document fourcc="MJPG" workaround for OpenCV async errors
- Improve code formatting in robot configuration examples

Fixes compatibility issues for users following the tutorial on embedded systems
and ensures API examples match current codebase requirements.

* Update il_robots.mdx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: ./c² <cagataycali@icloud.com>

---------

Signed-off-by: ./c² <cagataycali@icloud.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-15 17:56:33 +01:00
Martino Russi a6c3a0fa09 Feat/add mj env (#2613)
* add sim support

* close fix threading issues
2025-12-15 16:22:27 +01:00
Woojin Wie c2fb644613 feat(robot): Add support for OMX robot (#2614)
* upload

* feat(omx): simplify motor initialization and remove default calibration files

* feat(omx): read motor positions without normalization for improved accuracy

* update calibration method for return factory value

Signed-off-by: Junha Cha <ckwnsgk1@gachon.ac.kr>

* change the drive mode

* refactor: clean up code by removing unnecessary blank lines in omx_follower and omx_leader modules

* feat(omx): update calibration method to set drive modes for motors

* feat(pyproject): add 'ROBOTIS' to extend-ignore-identifiers-re list

* feat(omx): enhance calibration method to write default drive modes to motors

* Update src/lerobot/robots/omx_follower/__init__.py

Add informations about the robot

Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Signed-off-by: Woojin Wie <dnldnwls1123@gmail.com>

---------

Signed-off-by: Junha Cha <ckwnsgk1@gachon.ac.kr>
Signed-off-by: Woojin Wie <dnldnwls1123@gmail.com>
Co-authored-by: Junha02 <chajunha2023@naver.com>
Co-authored-by: Junha Cha <ckwnsgk1@gachon.ac.kr>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-15 15:50:29 +01:00
Jade Choghari 1d07a4aefd add auto in docs (#2645)
Signed-off-by: Jade Choghari <chogharijade@gmail.com>
2025-12-13 17:11:19 +01:00
Michel Aractingi ce348a3460 enable variable image sizes to pi0/pi0.5 (#2609)
* enable variable image sizes to pi0/pi0.5

* add square image assertion
2025-12-10 19:41:11 +01:00
Jade Choghari cb920235c4 docs: update X-VLA training strategies/commands (#2611) 2025-12-09 19:08:09 +01:00
Jade Choghari 7f40b3bf82 feat(dataset): add tool to convert images to video datasets (#2560)
* add video encoding tool

* style

* make it work

* more fixes
2025-12-08 18:50:21 +01:00
Michel Aractingi 2e9c9fd832 Replay while loop in sample actions with for loops (#2600) 2025-12-08 14:47:54 +01:00
Steven Palma f9cb5e659c chore(ci): skip workflows if not lerobot repository (#2601)
Co-authored-by: Alex Tyshka <atyshka15@gmail.com>
2025-12-08 12:44:36 +01:00
Michel Aractingi 0217e1e3ad Fix dataset aggreagation for multi video datasets' (#2550) 2025-12-05 16:09:25 +01:00
Vladislav Sovrasov d79dd6d31f Add a documentation page with a brief intro to hw backends (#2385) 2025-12-05 13:32:58 +01:00
Steven Palma 56b43cc888 fix(scripts): missing so101 import (#2577)
* fix(scripts): missing so101 import

Co-authored-by: Skyler <skylerwiernik@gmail.com>

* fix(scripts): move urdf to cli args

* refactor(scripts): improve find_joints_limits

---------

Co-authored-by: Skyler <skylerwiernik@gmail.com>
2025-12-03 18:20:26 +01:00
Kevin Thomas 77fe5a09ed fix(docs): argument typo (#2361)
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 17:57:18 +01:00
Austin King 89ae7813a7 Reorganize assembly instructions setup before assembly (#2333)
Motors should be set up before the arm is assembled. 

Moving the entire motor setup section before the part cleaning and assembly section.

Signed-off-by: Austin King <shout@ozten.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 17:56:58 +01:00
./c² e003108cf8 Fix link to lerobot-train script in documentation (#2466)
* Fix link to lerobot-train script in documentation

Signed-off-by: ./c² <cagataycali@icloud.com>

* Update link to lerobot record script

Signed-off-by: ./c² <cagataycali@icloud.com>

---------

Signed-off-by: ./c² <cagataycali@icloud.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 15:46:26 +01:00
Steven Palma 5766eea377 fix(docs): remove duplicated package in install instructions (#2573) 2025-12-03 15:45:56 +01:00
Steven Palma f8a4cf225b feat(robots): add earth rover robot support (#2575)
Co-authored-by: somthecoder <sbaner64@gmail.com>
Co-authored-by: randomSmarts <Aarshsmittal@gmail.com>
Co-authored-by: Hassoonu <halsae2@illinois.edu>
Co-authored-by: Saketh06 <saketh.kantipudi@gmail.com>
Co-authored-by: sairajshetye <sairajshetye2@gmail.com>
Co-authored-by: Khalil Meftah <kmeftah.khalil@gmail.com>
2025-12-03 15:36:22 +01:00
Jade Choghari 43b0f17eb9 feat(policies): Add X-VLA (#2405)
* first commit

* more fixes

* add franka action

* update testing script

* add changes

* update files

* logits matching

* add imagenet as a norm type

* logits matching atol1e-2

* more eval fixes

* more changes

* xvla works on libero

* remove seed

* more refactoring

* more fixes

* more changes

* more changes

* more fixes

* migrate policy revert

* major pre-commit cleanup

* renaming

* revert to self.transformer

* refactor

* new changes

* clean

* update libero

* more changes

* make it work

* more changes:

* remove imagenet dependency

* style

* more

* more refactor

* remove proprio

* add loss

* more

* more

* add freeze/unfreeze options

* add testing

* upgrade transformers version

* update testing

* add installation

* remove .sh file

* fix testing

* silent linter in xvlatest

* fix failing test

* upgrade test, fix failing

* fix testing

* more fixes to testing

* require cuda in tests

* temp check

* add xvla docs

* fix styling

* update libero doc

* remove timm dep

* add different dtype support

* remove timm skip

* remove white lines

* Enhance X-VLA finetuning documentation with optimizer details (#2537)

Added detailed instructions for implementing a custom optimizer and modifying parameter retrieval for X-VLA finetuning.

Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com>

* fix style

* iterate on review

* iterate on cpilot

* revert xvla dep

* free up ci

* test(xvla): remove main test (#2565)

* Add xvla custom optim and dtype (#2567)

* add custom optim

* add custom optim

* add auto mode

* more changes

* add identity to all

* add auto

* release

* add docs

* make image smaller docs

* smaller image in doc

* evan smaller image doc

* finalize doc

---------

Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com>
Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 15:29:14 +01:00
Steven Palma b0b755471b Revert "Earth Rover Mini Plus integration (#2544)" (#2574)
This reverts commit 35c5a27352.
2025-12-03 14:43:07 +01:00
s1lent4gnt 35c5a27352 Earth Rover Mini Plus integration (#2544)
* feat: Add EarthRover Mini Plus robot integration with Frodobots SDK

* refactor: Clean up

* refactor: Remove VirtualCamera implementation for EarthRover Mini Plus integration

* fix: Reduce timeout for camera requests

* fix: Add empty cameras dict for compatibility with recording script

* refactor: Remove record.py script for EarthRover Mini Plus use lerobot_record instead

* refactor: Update documentation for EarthRover Mini Plus integration

* refactor keyboard teleoperation

* refactor: Remove angular velocity

* docs: Add documentation for EarthRover Mini Plus integration

* Add earthrover_mini_plus robot to replay and teleoperate scripts

* refactor: Update stop key from Space to X

* refactor: Implement caching for camera frames and robot telemetry data

* refactor

* refactor: Replace string literals with constants for action and observation keys

* Add Earth Rover Mini to robots section in documentation

Co-authored-by: somthecoder sbaner64@gmail.com
Co-authored-by: randomSmarts Aarshsmittal@gmail.com
Co-authored-by: Hassoonu halsae2@illinois.edu
Co-authored-by: Saketh06 saketh.kantipudi@gmail.com
Co-authored-by: sairajshetye sairajshetye2@gmail.com
2025-12-03 14:24:57 +01:00
vinoyang afb90e17e7 doc: fix wrong package name in installation doc (#2513) 2025-12-03 13:36:59 +01:00
Daniel San José Pro 9ec9ee781a feat(policies): Allow users to register 3rd party policies - pip install lerobot_policy_mypolicy (#2308)
* feat: Register external policies

* ruff fix

* move policy util functions to policy factory

* refactor register_third_party_devices -> register_third_party_plugins

* feat: Update docs with bring your own policies

* Improve docs for new policies

* fix: Inconsistent quotation marks

* fix: Remove print statement

* fix: wrong base class name in documentation

* fix: Handle better how the models are parsed

* fix: precommit passing

* Update docs/source/bring_your_own_policies.mdx

Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Signed-off-by: Daniel San José Pro <42489409+danielsanjosepro@users.noreply.github.com>

---------

Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>
Signed-off-by: Daniel San José Pro <42489409+danielsanjosepro@users.noreply.github.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 12:09:24 +01:00
Md. Muhaimin Rahman 0b497fc37d Make transport module Mypy Compliant [issue#1731] (#2433)
* latest

* Delete =3.0.0

Signed-off-by: Md. Muhaimin Rahman <sezan92@gmail.com>

* Update src/lerobot/transport/utils.py

Signed-off-by: Md. Muhaimin Rahman <sezan92@gmail.com>

---------

Signed-off-by: Md. Muhaimin Rahman <sezan92@gmail.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-02 22:12:15 +01:00
Michel Aractingi 797cd2725a fix pi05 forward compile (#2551) 2025-12-02 11:01:43 +01:00
Steven Palma af4766b602 fix(ci): move hub artifacts to /mnt to avoid runners' No space left on device (#2564)
* fix(ci): move hub & lerobot artefacts to /mnt to avoid No space left on device in the future

* chore(ci): remove dh -h steps
2025-12-01 20:14:51 +01:00
Martino Russi 37f43df88a Feat/add unitree g1 robot (#2530)
* add unitree_g1_robot_class

* finish locomotion loading code

* precommit

* separate groot locomotion logic

* remove leftover locomotion variable, unify kp kd

* format config

* properly comment config, example locomotion and unitree_g1 class

* ready to review

* download policy from the hub in `examples/unitree_g1/gr00t_locomotion`

* fix linter

* make precommit happy, add ignore flags

* linter pt3

* linter pt4

* [done] make precommit happy

* fix linter 5

* add docs

* push utils

* feat(robots): add Unitree G1 humanoid support with ZMQ bridge (#2539)

* feat(robots): add Unitree G1 humanoid support with ZMQ bridge

- Use JSON + base64 serialization for secure communication instead of pickle
- Add documentation section
- Rename robot_server to run_g1_server
- Add dependecies to pyproject.toml

* nit in docs

* remove globals use

* cast robot data to int/float

* ensure robot is connected before changing mode

* temperature can be list, average in such case

---------

Co-authored-by: Martino Russi <nopyeps@gmail.com>

* style nit

* remove transform_imu_data

* remove scipy dependency

* modify toml, add external unitree_sdk2py dep

* return actions from send_action

* cleaning

* add instructions for local deployment

* Update src/lerobot/robots/unitree_g1/unitree_g1.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com>

* update config and readme

* update docs

* update docs

* remove torch import

* fix docs

* remove ip from docs

* add licence header

---------

Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-01 16:10:13 +01:00
Sota Nakamura 5f7b5f2817 remove the sampler cause the relative index is added (#2521)
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
2025-11-30 22:28:32 +01:00
Steven Palma c55fbe1b3e chore(dependencies): Bump lerobot to 0.4.3 (#2540) 2025-11-28 10:39:02 +01:00
Steven Palma 58f70b6bd3 fix(scripts): better prints teleop (#2538) v0.4.2 2025-11-27 16:54:17 +01:00
Steven Palma b07160eb1b feat(utils): precise_sleep() less CPU hungry without sacrificing accuracy (#2526) 2025-11-26 17:42:16 +01:00
Caroline Pascal 648ea8f485 fix(benchmark) : fixing video benchmark (#2094)
* fix(time benchmark): removing deprecated TimeBenchmark dependency

* fix(typo): renaming frames in an up-to-date fashion

* feat(duets): rearanging crf and g parameters in a proper unique combination manner

* fix(segfault): fixing segfault by adding a lock in ThreadPoolExecutor

* chore(update) : update datasets, codecs and backends to the latest versions

* chore(unused files): removing unused files

* fix(dataset paths): fix datasets paths to live among lerobot datasets
2025-11-26 17:41:31 +01:00
Caroline Pascal 581dd45eae feat(parallel encoding): making parallel encoding the default choice over all platforms (#2525) 2025-11-26 14:57:34 +01:00
Steven Palma 17581a9449 fix(examples): wrap all of them into a main function (#2524) 2025-11-26 14:28:04 +01:00
Steven Palma 87bee86640 feat(dataset): dynamic compress_level depending on the type of dataset (video or image) (#2517) 2025-11-25 19:11:12 +01:00
Steven Palma 18b32dced9 feat(dataset): speed-up encoding time (#2514)
* feat(dataset): speed-up encoding time

* feat(dataset): add parallel encoding option

* feat(datasets): parallel encoding only if num_cams > 2

* feat(datasets): implement feedback
2025-11-25 16:46:12 +01:00
Jade Choghari 36e8feefe3 docs: Add LeIsaac x LeRobot Envhub tutorial (#2498)
* add leisaac doc

* depreciate il in sim

* fix readme

* more

* fix styling

* update title

* more changes

* more

* fix style

* more

* fix style
2025-11-25 16:23:12 +01:00
Michel Aractingi 0f551df8f4 add absolute_to_reative_idx for remapping indicies when a subset of data is loaded (#2490) 2025-11-20 14:05:31 +01:00