Files
lerobot/examples/phone_so100_record.py
T
Pepijn e5ade5565d Integrate pipeline and add phone teleop (#1681)
* Add normalization processor and related components

- Introduced `NormalizationProcessor` to handle both observation normalization and action unnormalization.
- Added `ObservationNormalizer` and `ActionUnnormalizer` classes for specific normalization tasks.
- Updated `__init__.py` to include the new `NormalizationProcessor` in the module exports.
- Enhanced `ObservationProcessor` with registration in the `ProcessorStepRegistry` for better modularity.
- Created `RenameProcessor` for renaming keys in observations, improving flexibility in data processing.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Enhance processing architecture with new components

- Added `RenameProcessor` to facilitate key renaming in observations, improving data handling flexibility.
- Updated `__init__.py` to include `RenameProcessor` in module exports.
- Refactored `NormalizationProcessor` and `ObservationNormalizer` to use `rsplit` for better key handling.
- Introduced comprehensive tests for `NormalizationProcessor` and `RenameProcessor` to ensure functionality and robustness.

* chore (docs): add docstring for processor

* fix (test): test factory

* fix(test): policies

* Update tests/processor/test_observation_processor.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com>

* chore(test): add suggestion made by copilot regarding numpy test

* fix(test): import issue

* Refactor normalization components and update tests

- Renamed `ObservationNormalizer` to `NormalizerProcessor` and `ActionUnnormalizer` to `UnnormalizerProcessor` for clarity.
- Consolidated normalization logic for both observations and actions into `NormalizerProcessor` and `UnnormalizerProcessor`.
- Updated tests to reflect the new class names and ensure proper functionality of normalization and unnormalization processes.
- Enhanced handling of missing statistics in normalization processes.

* chore (docstrin):Improve docstring for NormalizerProcessor

* feat (device processor): Implement device processor

* chore (batch handling): Enhance processing components with batch conversion utilities

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(test): linting issue

* chore (output format): improves output format

* chore (type): add typing for multiprocess envs

* feat (overrides): Implement support for loading processors with parameter overrides

- Added the ability to provide non-serializable objects when loading processors from saved configurations using the `overrides` parameter.
- Enhanced error handling for invalid override keys and instantiation errors.
- Updated documentation and examples to illustrate the usage of overrides for both registered and unregistered steps.
- Added comprehensive tests to validate the new functionality and ensure backward compatibility.

* chore(normalization): addressing comments from copilot

* chore(learner): nit comment from copilot

* feat(pipeline): Enhance step_through method to support both tuple and dict inputs

* refactor(pipeline): Simplify observation and padding data handling in batch transitions

* Apply suggestions from code review

Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(pipeline): Introduce ComplementaryDataProcessor for handling complementary data in transitions

* fix(ci): temporary fix on dataset deps version

* feat(processors): Introduce processors for various policy types

- Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`.
- Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps.
- Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity.
- Enhanced test coverage to validate the integration of new processors with existing policy configurations.

* refactor(learner): Remove normalization from cached image features retrieval

- Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls.
- This change enhances clarity and aligns with the recent updates to policy processors.

* refactor(policies): Remove unnormalization step from action predictions

- Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction.
- This change improves code clarity and aligns with recent updates to policy processors.

* feat(train): Integrate preprocessor into training pipeline

* refactor(train): Update preprocessor initialization to include dataset statistics

* refactor(policies): Enhance processor creation and add NaN detection hook

* refactor(train): Update memory pinning logic for mps compatibility

* feat: initial commit phone teleop

* ugly delta control

* use quaternion

* Refactor observation preprocessing to use a modular pipeline system

- Introduced `RobotPipeline` and `ObservationProcessor` for handling observation transformations.
- Updated `preprocess_observation` to maintain backward compatibility while leveraging the new pipeline.
- Added tests for the new processing components and ensured they match the original functionality.
- Removed hardcoded logic in favor of a more flexible, composable architecture.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Refactor observation processing and improve modularity

- Updated `ObservationProcessor` to enhance the modular design for processing observations.
- Cleaned up imports and improved code readability by removing unnecessary lines and comments.
- Ensured backward compatibility while integrating new processing components.
- Added tests to validate the functionality of the updated processing architecture.

* Remove redundant tests for None observation and serialization methods in `test_observation_processor.py` to streamline the test suite and improve maintainability.

* Refactor processing architecture to use RobotProcessor

- Replaced instances of RobotPipeline with RobotProcessor across the codebase for improved modularity and clarity.
- Introduced ProcessorStepRegistry for better management of processing steps.
- Updated relevant documentation and tests to reflect the new processing structure.
- Enhanced the save/load functionality to support the new processor design.
- Added a model card template for RobotProcessor to facilitate sharing and documentation.

* Add RobotProcessor tutorial to documentation

- Introduced a new tutorial on using RobotProcessor for preprocessing robot data.
- Added a section in the table of contents for easy navigation to the new tutorial.
- The tutorial covers key concepts, real-world scenarios, and practical examples for effective use of the RobotProcessor pipeline.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add normalization processor and related components

- Introduced `NormalizationProcessor` to handle both observation normalization and action unnormalization.
- Added `ObservationNormalizer` and `ActionUnnormalizer` classes for specific normalization tasks.
- Updated `__init__.py` to include the new `NormalizationProcessor` in the module exports.
- Enhanced `ObservationProcessor` with registration in the `ProcessorStepRegistry` for better modularity.
- Created `RenameProcessor` for renaming keys in observations, improving flexibility in data processing.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Enhance processing architecture with new components

- Added `RenameProcessor` to facilitate key renaming in observations, improving data handling flexibility.
- Updated `__init__.py` to include `RenameProcessor` in module exports.
- Refactored `NormalizationProcessor` and `ObservationNormalizer` to use `rsplit` for better key handling.
- Introduced comprehensive tests for `NormalizationProcessor` and `RenameProcessor` to ensure functionality and robustness.

* chore (docs): add docstring for processor

* fix (test): test factory

* fix(test): policies

* Update tests/processor/test_observation_processor.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com>

* chore(test): add suggestion made by copilot regarding numpy test

* fix(test): import issue

* Refactor normalization components and update tests

- Renamed `ObservationNormalizer` to `NormalizerProcessor` and `ActionUnnormalizer` to `UnnormalizerProcessor` for clarity.
- Consolidated normalization logic for both observations and actions into `NormalizerProcessor` and `UnnormalizerProcessor`.
- Updated tests to reflect the new class names and ensure proper functionality of normalization and unnormalization processes.
- Enhanced handling of missing statistics in normalization processes.

* chore (docstrin):Improve docstring for NormalizerProcessor

* feat (device processor): Implement device processor

* chore (batch handling): Enhance processing components with batch conversion utilities

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(test): linting issue

* chore (output format): improves output format

* chore (type): add typing for multiprocess envs

* feat (overrides): Implement support for loading processors with parameter overrides

- Added the ability to provide non-serializable objects when loading processors from saved configurations using the `overrides` parameter.
- Enhanced error handling for invalid override keys and instantiation errors.
- Updated documentation and examples to illustrate the usage of overrides for both registered and unregistered steps.
- Added comprehensive tests to validate the new functionality and ensure backward compatibility.

* chore(normalization): addressing comments from copilot

* chore(learner): nit comment from copilot

* feat(pipeline): Enhance step_through method to support both tuple and dict inputs

* refactor(pipeline): Simplify observation and padding data handling in batch transitions

* Apply suggestions from code review

Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(pipeline): Introduce ComplementaryDataProcessor for handling complementary data in transitions

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(pipeline): Transition from tuple to dictionary format for EnvTransition

- Updated the EnvTransition structure to use a dictionary format instead of a tuple, enhancing readability and maintainability.
- Replaced instances of TransitionIndex with TransitionKey for accessing transition components.
- Adjusted related processing functions and tests to accommodate the new dictionary format, ensuring consistent handling of transitions across the codebase.

* refactor(observation_processor): Improve observation processing by using constants and simplifying pixel handling

- Introduced constants for observation keys to enhance readability.
- Streamlined the handling of the "pixels" key by copying observations first and processing images more clearly.
- Updated the environment state and agent position assignments to use the new constants, improving maintainability.

* feat(pipeline): Add hook unregistration functionality and enhance documentation

- Implemented methods to unregister before, after, and reset hooks in the RobotProcessor class, allowing for more flexible hook management.
- Enhanced documentation to clarify hook execution semantics and the implications of modifying transitions within hooks.
- Added comprehensive tests to verify the correct behavior of hook registration and unregistration, including error handling for non-existent hooks.

* refactor(pipeline): Clarify hook behavior and improve documentation

- Updated the RobotProcessor class to ensure hooks are strictly for observation and do not modify transitions, enhancing clarity and maintainability.
- Refactored hook registration methods to reflect the new behavior, ensuring they accept only functions that do not return modified transitions.
- Enhanced documentation to clearly outline the purpose of hooks and their execution semantics.
- Added tests to verify that hooks are not executed during the step_through method while ensuring they function correctly during the __call__ method.

* feat(pipeline): Add __repr__ method to RobotProcessor for improved readability

- Implemented a __repr__ method in the RobotProcessor class to provide a clear string representation of the processor, including step names and optional parameters like name and seed.
- Added comprehensive tests to validate the __repr__ output for various scenarios, including empty processors, single and multiple steps, custom names, and seed values.
- Ensured that the representation handles long lists of steps with truncation for better readability.

* chore(pipeline): Move _CFG_NAME along other class member

* refactor(pipeline): Utilize get_safe_torch_device for device assignment

- Replaced direct torch.device instantiation with get_safe_torch_device to ensure safe device handling.
- This change enhances code readability and maintains consistency in device management across the RobotProcessor class.

* refactor(pipeline): Enhance state filename generation and profiling method

- Updated state filename generation to use the registry name when available, improving clarity in saved files.
- Modified the profile_steps method to include a warmup_runs parameter, allowing for more controlled performance profiling.
- Ensured consistent conditions during profiling by deep copying transitions for each run, enhancing accuracy in timing results.

* chore(doc): address pip install commant lerobot that not exist yet

* feat(pipeline): Enhance configuration filename handling and state file naming

- Introduced support for custom configuration filenames in the `save_pretrained` method, allowing users to specify a filename instead of the default.
- Improved state file naming to include step indices, preventing conflicts when multiple processors of the same type are saved.
- Added automatic detection for configuration files when loading from a directory, with error handling for multiple files.
- Updated tests to validate new features, including custom filenames and automatic config detection.

* refactor(pipeline): Improve state file naming conventions for clarity and uniqueness

- Enhanced state file naming to include the processor's sanitized name, ensuring uniqueness when multiple processors are saved in the same directory.
- Updated tests to reflect changes in state file naming, verifying that filenames now include the processor name and step indices to prevent conflicts.
- Added a new test to validate state file naming when using multiple processors, ensuring distinct filenames for each processor's state files.

* docs(pipeline): Add clarification for repo name sanitization process

* feat(processors): Introduce processors for various policy types

- Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`.
- Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps.
- Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity.
- Enhanced test coverage to validate the integration of new processors with existing policy configurations.

* refactor(learner): Remove normalization from cached image features retrieval

- Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls.
- This change enhances clarity and aligns with the recent updates to policy processors.

* refactor(policies): Remove unnormalization step from action predictions

- Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction.
- This change improves code clarity and aligns with recent updates to policy processors.

* feat(train): Integrate preprocessor into training pipeline

* refactor(train): Update preprocessor initialization to include dataset statistics

* refactor(policies): Enhance processor creation and add NaN detection hook

* feat(record): Integrate RobotProcessor into recording loop and update policy handling

- Added support for RobotProcessor in the record_loop function to enhance data processing capabilities.
- Updated the logic to reset both policy and processor when provided, ensuring proper state management.
- Modified action prediction to utilize the processor, improving the overall functionality of the recording process.
- Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities.

* feat(migration): Add script for migrating policy models with normalization layers

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models

- Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference.
- Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture.
- Refined the extraction and removal of normalization statistics and layers, streamlining the migration process.
- Improved error handling for missing mandatory configuration fields during model instantiation.

* feat(migrate): Add model card generation and saving to migration script

- Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags.
- Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility.
- Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub.

* feat(processor): Introduce ToBatchProcessor for handling observation batching

- Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing.
- Implemented functionality to add batch dimensions to state and image observations as needed.
- Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types.
- Ensured compatibility with existing transition keys and maintained the integrity of non-observation data.

* feat(processors): Add ToBatchProcessor to multiple policy processors

- Integrated ToBatchProcessor into various policy processors to handle observation batching.
- Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality.
- Ensured consistency across all processor implementations for improved data handling.

* refactor(factory): Remove unused imports and NaN detection hook from processor creation

* feat(batch_processor): Enhance ToBatchProcessor to handle action batching

- Updated ToBatchProcessor to add batch dimensions to actions in addition to observations.
- Implemented separate methods for processing observations and actions, improving code readability.
- Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration

- Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration.
- Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation.
- Refactored the loading of pretrained processors to utilize the new configuration options.

* refactor(factory): Clean up imports in factory.py

- Removed unused import of IdentityProcessor to streamline the code.

* feat(migrate): Extend load_model_from_hub to include train configuration

- Updated load_model_from_hub to return the train configuration alongside the model state_dict and config.
- Modified main function to handle the additional train configuration when loading models from both the hub and local paths.
- Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy.

* refactor(record): Rename processor parameters and update processing logic

- Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity.
- Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow.
- Ensured compatibility with existing functionality while improving code readability.

* feat(batch_processor): Add task field processing to ToBatchProcessor

- Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference.
- Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings.
- Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data.

* feat(normalization): Implement IDENTITY mode for normalization and unnormalization

- Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified.
- Updated processing logic to check normalization modes and handle missing statistics gracefully.
- Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios.
- Improved error handling for unsupported normalization modes.

* fix(rebase): remove residual normalization layer:

* refactor(diffusion): remove normalization layer from input processing

* Add debug + calib

* cleanup

* Add pipeline

* fix int

* Add record example

* nit

* Add feature contract to pipelinestep and pipeline

* Add tests

* Add processor tests

* PR feedback

* encorperate pr feedback

* type in doc

* oops

* cleaned up steps and integrated pipeline with feature_contract

* refactor steps and robot to pipeline

* cleanup pipeline

* cleanup code further

* make it run

* feat(processors): Introduce processors for various policy types

- Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`.
- Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps.
- Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity.
- Enhanced test coverage to validate the integration of new processors with existing policy configurations.

* refactor(learner): Remove normalization from cached image features retrieval

- Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls.
- This change enhances clarity and aligns with the recent updates to policy processors.

* refactor(policies): Remove unnormalization step from action predictions

- Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction.
- This change improves code clarity and aligns with recent updates to policy processors.

* feat(train): Integrate preprocessor into training pipeline

* refactor(train): Update preprocessor initialization to include dataset statistics

* refactor(policies): Enhance processor creation and add NaN detection hook

* feat(record): Integrate RobotProcessor into recording loop and update policy handling

- Added support for RobotProcessor in the record_loop function to enhance data processing capabilities.
- Updated the logic to reset both policy and processor when provided, ensuring proper state management.
- Modified action prediction to utilize the processor, improving the overall functionality of the recording process.
- Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities.

* feat(migration): Add script for migrating policy models with normalization layers

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models

- Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference.
- Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture.
- Refined the extraction and removal of normalization statistics and layers, streamlining the migration process.
- Improved error handling for missing mandatory configuration fields during model instantiation.

* feat(migrate): Add model card generation and saving to migration script

- Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags.
- Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility.
- Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub.

* feat(processor): Introduce ToBatchProcessor for handling observation batching

- Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing.
- Implemented functionality to add batch dimensions to state and image observations as needed.
- Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types.
- Ensured compatibility with existing transition keys and maintained the integrity of non-observation data.

* feat(processors): Add ToBatchProcessor to multiple policy processors

- Integrated ToBatchProcessor into various policy processors to handle observation batching.
- Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality.
- Ensured consistency across all processor implementations for improved data handling.

* refactor(factory): Remove unused imports and NaN detection hook from processor creation

* feat(batch_processor): Enhance ToBatchProcessor to handle action batching

- Updated ToBatchProcessor to add batch dimensions to actions in addition to observations.
- Implemented separate methods for processing observations and actions, improving code readability.
- Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration

- Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration.
- Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation.
- Refactored the loading of pretrained processors to utilize the new configuration options.

* refactor(factory): Clean up imports in factory.py

- Removed unused import of IdentityProcessor to streamline the code.

* feat(migrate): Extend load_model_from_hub to include train configuration

- Updated load_model_from_hub to return the train configuration alongside the model state_dict and config.
- Modified main function to handle the additional train configuration when loading models from both the hub and local paths.
- Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy.

* refactor(record): Rename processor parameters and update processing logic

- Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity.
- Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow.
- Ensured compatibility with existing functionality while improving code readability.

* feat(batch_processor): Add task field processing to ToBatchProcessor

- Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference.
- Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings.
- Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data.

* feat(normalization): Implement IDENTITY mode for normalization and unnormalization

- Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified.
- Updated processing logic to check normalization modes and handle missing statistics gracefully.
- Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios.
- Improved error handling for unsupported normalization modes.

* fix(rebase): remove residual normalization layer:

* refactor(diffusion): remove normalization layer from input processing

* refactor(normalization): Remove unused state dict transformation methods and streamline imports

- Eliminated the _transform_state_dict_keys and _load_as_safetensor methods from PI0Policy, simplifying the model loading process.
- Cleaned up imports in modeling_pi0.py by removing log_model_loading_keys and init_logging.
- Updated TDMPCPolicy and VQBeTPolicy to handle action removal from batches during offline evaluation.
- Introduced hotswap_stats function in normalize_processor.py to update normalization statistics dynamically, with corresponding tests to ensure functionality.

* refactor(normalization): Clean up imports in normalize_processor.py

* feat(batch_processor): Add feature_contract method to ToBatchProcessor

- Introduced feature_contract method that returns features without modification, maintaining the no-op behavior of the processor.
- This addition enhances the flexibility of the ToBatchProcessor for future feature processing needs.

* fix(dependencies): Update transformers dependency constraint to allow only versions up to 4.52.0

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(tokenizer): Introduce TokenizerProcessor for text tokenization

- Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer.
- Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings.
- Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor.
- Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor.

* feat(language): Enhance language processing in TokenizerProcessor

- Added OBS_LANGUAGE constant to define the observation language key.
- Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature.
- Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization.
- Modified tests to validate the integration of language tokens and attention masks in the observation structure.

* feat(tokenizer): Add padding configuration to TokenizerProcessor

- Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction.
- Updated the `make_pi0_processor` function to include the new padding configuration.
- Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios.

* feat(processor): Add state management methods to Pi0NewLineProcessor

* feat(normalization): Track normalization and unnormalization info in complementary data

- Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes.
- Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions.
- Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys.

* feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs

- Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations.
- Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization.

* feat(processors): Integrate RenameProcessor into various processor configurations

- Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency.
- Updated the input steps to ensure compatibility with the new RenameProcessor integration.

* Do some todos and cleanup

* change feature_contract to dataset_features

* use one method for conversion pipeline output to add_frame dict and use base processors where possible

* Add back in and use record_loop

* update todo

* rename to_dataset_frame

* feat(smolvla): Refactor language processing and introduce new line processor (#1658)

- Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant.
- Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility.
- Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling.

* feat(processors): Integrate DeviceProcessor into multiple processor configurations

- Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines.
- Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix

* fix reference frame

* refactor(pipeline): Remove to() method for device management

- Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices.
- Removed associated unit tests that validated the functionality of the to() method across various scenarios.
- Streamlined the pipeline code by focusing on other device management strategies.

* feat(processor): Enhance DeviceProcessor with float dtype conversion

- Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types.
- Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype.
- Refactored tensor processing logic to streamline device movement and dtype conversion.
- Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios.

* update data visualization

* update teleop example

* fix record bugs

* Add replay

* Not code

* feature(pipeline): port tokenizer pipeline for VLA (#1645)

* feat(tokenizer): Introduce TokenizerProcessor for text tokenization

- Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer.
- Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings.
- Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor.
- Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor.

* feat(language): Enhance language processing in TokenizerProcessor

- Added OBS_LANGUAGE constant to define the observation language key.
- Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature.
- Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization.
- Modified tests to validate the integration of language tokens and attention masks in the observation structure.

* feat(tokenizer): Add padding configuration to TokenizerProcessor

- Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction.
- Updated the `make_pi0_processor` function to include the new padding configuration.
- Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios.

* feat(processor): Add state management methods to Pi0NewLineProcessor

* feat(normalization): Track normalization and unnormalization info in complementary data

- Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes.
- Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions.
- Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys.

* feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs

- Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations.
- Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization.

* feat(processors): Integrate RenameProcessor into various processor configurations

- Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency.
- Updated the input steps to ensure compatibility with the new RenameProcessor integration.

* feat(smolvla): Refactor language processing and introduce new line processor (#1658)

- Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant.
- Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility.
- Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling.

* feture(policies): add device processor (#1659)

* feat(processors): Integrate DeviceProcessor into multiple processor configurations

- Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines.
- Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(pipeline): Remove to() method for device management

- Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices.
- Removed associated unit tests that validated the functionality of the to() method across various scenarios.
- Streamlined the pipeline code by focusing on other device management strategies.

* feat(processor): Enhance DeviceProcessor with float dtype conversion

- Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types.
- Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype.
- Refactored tensor processing logic to streamline device movement and dtype conversion.
- Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios.

* feat(policies): Add new line processors and update module exports

* feat(processor): Enhance batch and device processors to handle index and task_index fields

- Added logic to ToBatchProcessor for unsqueezing 0D tensors for index and task_index fields, ensuring they are processed as 1D tensors.
- Updated DeviceProcessor to process index and task_index fields in complementary data, preserving their tensor types and ensuring non-tensor fields remain unchanged.
- Enhanced unit tests to validate the correct handling of index and task_index fields across various scenarios, including device compatibility and dtype preservation.

* Add eval script

* fix `q_curr` in InverseKinematicsEEToJoints to the IK solution

* feat(processors): Introduce processors for various policy types

- Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`.
- Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps.
- Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity.
- Enhanced test coverage to validate the integration of new processors with existing policy configurations.

* refactor(learner): Remove normalization from cached image features retrieval

- Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls.
- This change enhances clarity and aligns with the recent updates to policy processors.

* refactor(policies): Remove unnormalization step from action predictions

- Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction.
- This change improves code clarity and aligns with recent updates to policy processors.

* feat(train): Integrate preprocessor into training pipeline

* refactor(train): Update preprocessor initialization to include dataset statistics

* refactor(policies): Enhance processor creation and add NaN detection hook

* feat(record): Integrate RobotProcessor into recording loop and update policy handling

- Added support for RobotProcessor in the record_loop function to enhance data processing capabilities.
- Updated the logic to reset both policy and processor when provided, ensuring proper state management.
- Modified action prediction to utilize the processor, improving the overall functionality of the recording process.
- Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities.

* feat(migration): Add script for migrating policy models with normalization layers

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models

- Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference.
- Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture.
- Refined the extraction and removal of normalization statistics and layers, streamlining the migration process.
- Improved error handling for missing mandatory configuration fields during model instantiation.

* feat(migrate): Add model card generation and saving to migration script

- Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags.
- Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility.
- Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub.

* feat(processor): Introduce ToBatchProcessor for handling observation batching

- Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing.
- Implemented functionality to add batch dimensions to state and image observations as needed.
- Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types.
- Ensured compatibility with existing transition keys and maintained the integrity of non-observation data.

* feat(processors): Add ToBatchProcessor to multiple policy processors

- Integrated ToBatchProcessor into various policy processors to handle observation batching.
- Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality.
- Ensured consistency across all processor implementations for improved data handling.

* refactor(factory): Remove unused imports and NaN detection hook from processor creation

* feat(batch_processor): Enhance ToBatchProcessor to handle action batching

- Updated ToBatchProcessor to add batch dimensions to actions in addition to observations.
- Implemented separate methods for processing observations and actions, improving code readability.
- Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration

- Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration.
- Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation.
- Refactored the loading of pretrained processors to utilize the new configuration options.

* refactor(factory): Clean up imports in factory.py

- Removed unused import of IdentityProcessor to streamline the code.

* feat(migrate): Extend load_model_from_hub to include train configuration

- Updated load_model_from_hub to return the train configuration alongside the model state_dict and config.
- Modified main function to handle the additional train configuration when loading models from both the hub and local paths.
- Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy.

* refactor(record): Rename processor parameters and update processing logic

- Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity.
- Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow.
- Ensured compatibility with existing functionality while improving code readability.

* feat(batch_processor): Add task field processing to ToBatchProcessor

- Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference.
- Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings.
- Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data.

* feat(normalization): Implement IDENTITY mode for normalization and unnormalization

- Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified.
- Updated processing logic to check normalization modes and handle missing statistics gracefully.
- Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios.
- Improved error handling for unsupported normalization modes.

* fix(rebase): remove residual normalization layer:

* refactor(diffusion): remove normalization layer from input processing

* refactor(normalization): Remove unused state dict transformation methods and streamline imports

- Eliminated the _transform_state_dict_keys and _load_as_safetensor methods from PI0Policy, simplifying the model loading process.
- Cleaned up imports in modeling_pi0.py by removing log_model_loading_keys and init_logging.
- Updated TDMPCPolicy and VQBeTPolicy to handle action removal from batches during offline evaluation.
- Introduced hotswap_stats function in normalize_processor.py to update normalization statistics dynamically, with corresponding tests to ensure functionality.

* refactor(normalization): Clean up imports in normalize_processor.py

* feat(batch_processor): Add feature_contract method to ToBatchProcessor

- Introduced feature_contract method that returns features without modification, maintaining the no-op behavior of the processor.
- This addition enhances the flexibility of the ToBatchProcessor for future feature processing needs.

* fix(dependencies): Update transformers dependency constraint to allow only versions up to 4.52.0

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feature(pipeline): port tokenizer pipeline for VLA (#1645)

* feat(tokenizer): Introduce TokenizerProcessor for text tokenization

- Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer.
- Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings.
- Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor.
- Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor.

* feat(language): Enhance language processing in TokenizerProcessor

- Added OBS_LANGUAGE constant to define the observation language key.
- Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature.
- Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization.
- Modified tests to validate the integration of language tokens and attention masks in the observation structure.

* feat(tokenizer): Add padding configuration to TokenizerProcessor

- Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction.
- Updated the `make_pi0_processor` function to include the new padding configuration.
- Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios.

* feat(processor): Add state management methods to Pi0NewLineProcessor

* feat(normalization): Track normalization and unnormalization info in complementary data

- Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes.
- Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions.
- Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys.

* feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs

- Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations.
- Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization.

* feat(processors): Integrate RenameProcessor into various processor configurations

- Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency.
- Updated the input steps to ensure compatibility with the new RenameProcessor integration.

* feat(smolvla): Refactor language processing and introduce new line processor (#1658)

- Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant.
- Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility.
- Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling.

* feture(policies): add device processor (#1659)

* feat(processors): Integrate DeviceProcessor into multiple processor configurations

- Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor.
- Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines.
- Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(pipeline): Remove to() method for device management

- Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices.
- Removed associated unit tests that validated the functionality of the to() method across various scenarios.
- Streamlined the pipeline code by focusing on other device management strategies.

* feat(processor): Enhance DeviceProcessor with float dtype conversion

- Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types.
- Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype.
- Refactored tensor processing logic to streamline device movement and dtype conversion.
- Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios.

* feat(policies): Add new line processors and update module exports

* feat(processor): Enhance batch and device processors to handle index and task_index fields

- Added logic to ToBatchProcessor for unsqueezing 0D tensors for index and task_index fields, ensuring they are processed as 1D tensors.
- Updated DeviceProcessor to process index and task_index fields in complementary data, preserving their tensor types and ensuring non-tensor fields remain unchanged.
- Enhanced unit tests to validate the correct handling of index and task_index fields across various scenarios, including device compatibility and dtype preservation.

* refactor(processors): Standardize processor naming conventions

- Updated processor names across various files to use a consistent "robot_preprocessor" and "robot_postprocessor" format.
- Modified the make_processor functions in factory, act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet to reflect the new naming scheme.
- Enhanced the pipeline configuration to align with the updated processor names, improving clarity and maintainability.

* refactor(factory): Update processor configuration and type hints

- Changed return type of get_policy_class to type[PreTrainedPolicy] for improved type safety.
- Enhanced make_processor function to utilize dataset_stats in processor creation for better flexibility.
- Updated ProcessorConfigKwargs to include dataset_stats, allowing for more comprehensive processor configurations.
- Streamlined processor initialization by removing unnecessary kwargs and ensuring clarity in processor type handling.

* Fix eval and android gripper

* add some tests

* refactor(factory, pi0fast): Update processor function names and parameters

- Renamed make_pi0_processor to make_pi0fast_processor for clarity and consistency.
- Updated parameter names in the factory's make_processor function to use pretrained_model_name_or_path instead of source, enhancing readability and alignment with naming conventions.

* fix(train.py) push postprocessor with preprocessor
- Add preprocesser policy overrides for device and rename_map
- Add rename_map to DatasetRecordConfig (record.py)

* Cleanup pr

* fix more git diff pr issues

* add path as type in save_pretrained

* small nit

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* rename test file

* fix: make dataset_features/feature_contract is optional

* fix tests

* Encorperate pr feedback

* clean up record.py

* add ascii art, fix normal record

* remove merge issues

* fix merge

* remove features

* Add feedback PR

* fix last 4 tests

* remove features check

* rename to transform_features

* add transform_features

* fix lekiwi eval and update eval api example

---------

Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
2025-08-07 16:13:34 +02:00

216 lines
7.1 KiB
Python

# !/usr/bin/env python
# Copyright 2025 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from lerobot.cameras.opencv.configuration_opencv import OpenCVCameraConfig
from lerobot.datasets.lerobot_dataset import LeRobotDataset
from lerobot.datasets.pipeline_features import aggregate_pipeline_dataset_features
from lerobot.datasets.utils import merge_features
from lerobot.model.kinematics import RobotKinematics
from lerobot.processor.converters import (
to_output_robot_action,
to_transition_robot_observation,
to_transition_teleop_action,
)
from lerobot.processor.pipeline import RobotProcessor
from lerobot.record import record_loop
from lerobot.robots.so100_follower.config_so100_follower import SO100FollowerConfig
from lerobot.robots.so100_follower.robot_kinematic_processor import (
AddRobotObservationAsComplimentaryData,
EEBoundsAndSafety,
EEReferenceAndDelta,
ForwardKinematicsJointsToEE,
GripperVelocityToJoint,
InverseKinematicsEEToJoints,
)
from lerobot.robots.so100_follower.so100_follower import SO100Follower
from lerobot.teleoperators.phone.config_phone import PhoneConfig, PhoneOS
from lerobot.teleoperators.phone.phone import Phone
from lerobot.teleoperators.phone.phone_processor import MapPhoneActionToRobotAction
from lerobot.utils.control_utils import init_keyboard_listener
from lerobot.utils.utils import log_say
from lerobot.utils.visualization_utils import _init_rerun
NUM_EPISODES = 10
FPS = 30
EPISODE_TIME_SEC = 60
RESET_TIME_SEC = 30
TASK_DESCRIPTION = "My task description"
HF_REPO_ID = "<hf_username>/<dataset_repo_id>"
# Initialize the robot and teleoperator
camera_config = {"front": OpenCVCameraConfig(index_or_path=0, width=640, height=480, fps=FPS)}
robot_config = SO100FollowerConfig(
port="/dev/tty.usbmodem58760434471",
id="my_awesome_follower_arm",
cameras=camera_config,
use_degrees=True,
)
teleop_config = PhoneConfig(phone_os=PhoneOS.IOS) # or PhoneOS.ANDROID
# Initialize the robot and teleoperator
robot = SO100Follower(robot_config)
phone = Phone(teleop_config)
# NOTE: It is highly recommended to use the urdf in the SO-ARM100 repo: https://github.com/TheRobotStudio/SO-ARM100/blob/main/Simulation/SO101/so101_new_calib.urdf
kinematics_solver = RobotKinematics(
urdf_path="./src/lerobot/teleoperators/sim/so101_new_calib.urdf",
target_frame_name="gripper_frame_link",
joint_names=list(robot.bus.motors.keys()),
)
# Build pipeline to convert phone action to ee pose action
phone_to_robot_ee_pose = RobotProcessor(
steps=[
MapPhoneActionToRobotAction(platform=teleop_config.phone_os),
AddRobotObservationAsComplimentaryData(robot=robot),
EEReferenceAndDelta(
kinematics=kinematics_solver,
end_effector_step_sizes={"x": 0.5, "y": 0.5, "z": 0.5},
motor_names=list(robot.bus.motors.keys()),
),
EEBoundsAndSafety(
end_effector_bounds={"min": [-1.0, -1.0, -1.0], "max": [1.0, 1.0, 1.0]},
max_ee_step_m=0.20,
max_ee_twist_step_rad=0.50,
),
],
to_transition=to_transition_teleop_action,
to_output=lambda tr: tr,
)
# Build pipeline to convert ee pose action to joint action
robot_ee_to_joints = RobotProcessor(
steps=[
InverseKinematicsEEToJoints(
kinematics=kinematics_solver,
motor_names=list(robot.bus.motors.keys()),
initial_guess_current_joints=True,
),
GripperVelocityToJoint(
motor_names=list(robot.bus.motors.keys()),
speed_factor=20.0,
),
],
to_transition=lambda tr: tr,
to_output=to_output_robot_action,
)
# Build pipeline to convert joint observation to ee pose observation
robot_joints_to_ee_pose = RobotProcessor(
steps=[
ForwardKinematicsJointsToEE(kinematics=kinematics_solver, motor_names=list(robot.bus.motors.keys()))
],
to_transition=to_transition_robot_observation,
to_output=lambda tr: tr,
)
# Build dataset ee action features
action_ee = aggregate_pipeline_dataset_features(
pipeline=phone_to_robot_ee_pose,
initial_features=phone.action_features,
use_videos=True,
patterns=["action.ee"],
)
# Get gripper pos action features
gripper = aggregate_pipeline_dataset_features(
pipeline=robot_ee_to_joints,
initial_features={},
use_videos=True,
patterns=["action.gripper.pos", "observation.state.gripper.pos"],
)
# Build dataset ee observation features
observation_ee = aggregate_pipeline_dataset_features(
pipeline=robot_joints_to_ee_pose,
initial_features=robot.observation_features,
use_videos=True,
patterns=["observation.state.ee"],
)
dataset_features = merge_features(action_ee, gripper, observation_ee)
print("All dataset features: ", dataset_features)
# Create the dataset
dataset = LeRobotDataset.create(
repo_id=HF_REPO_ID,
fps=FPS,
features=dataset_features,
robot_type=robot.name,
use_videos=True,
image_writer_threads=4,
)
# Initialize the keyboard listener and rerun visualization
_, events = init_keyboard_listener()
_init_rerun(session_name="recording_phone")
# Connect the robot and teleoperator
robot.connect()
phone.connect()
episode_idx = 0
while episode_idx < NUM_EPISODES and not events["stop_recording"]:
log_say(f"Recording episode {episode_idx + 1} of {NUM_EPISODES}")
record_loop(
robot=robot,
events=events,
fps=FPS,
teleop=phone,
dataset=dataset,
control_time_s=EPISODE_TIME_SEC,
single_task=TASK_DESCRIPTION,
display_data=True,
teleop_action_processor=phone_to_robot_ee_pose,
robot_action_processor=robot_ee_to_joints,
robot_observation_processor=robot_joints_to_ee_pose,
)
# Reset the environment if not stopping or re-recording
if not events["stop_recording"] and (episode_idx < NUM_EPISODES - 1 or events["rerecord_episode"]):
log_say("Reset the environment")
record_loop(
robot=robot,
events=events,
fps=FPS,
teleop=phone,
control_time_s=RESET_TIME_SEC,
single_task=TASK_DESCRIPTION,
display_data=True,
teleop_action_processor=phone_to_robot_ee_pose,
robot_action_processor=robot_ee_to_joints,
robot_observation_processor=robot_joints_to_ee_pose,
)
if events["rerecord_episode"]:
log_say("Re-recording episode")
events["rerecord_episode"] = False
events["exit_early"] = False
dataset.clear_episode_buffer()
continue
dataset.save_episode()
episode_idx += 1
# Clean up
log_say("Stop recording")
robot.disconnect()
phone.disconnect()
dataset.push_to_hub()