Addressed several issues found in the sim2sim tutorial after the recent Isaac Lab version update.

[kimtaehyeong99]

• Updated record and replay scripts in robotis_lab to ensure compatibility with the latest Isaac Lab version.
• Added exception handling to prevent runtime errors during data recording.
• Tuned robot physical parameters (effort, stiffness, damping) for more stable simulation behavior.

[gemini-code-assist]

Summary of Changes

Hello @kimtaehyeong99, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses critical compatibility and stability issues within the sim2sim tutorial following a recent Isaac Lab version update. It ensures that the demonstration recording and replaying functionalities work seamlessly, enhances the robustness of data processing by introducing exception handling, and refines the physical parameters of the simulated robots for improved stability and realism. These changes collectively aim to provide a more reliable and accurate simulation environment for robotics research and development.

Highlights

• Script Updates: The record and replay scripts in robotis_lab have been updated to ensure full compatibility with the latest Isaac Lab version, including changes to argument parsing and XR visualization integration.
• Robustness Improvements: Exception handling has been added to data recording and action conversion processes to prevent runtime errors and gracefully skip problematic episodes, improving the stability of the data collection pipeline.
• Robot Parameter Tuning: Physical parameters such as effort, stiffness, and damping for the FFW_BG2 and OMY robots have been re-tuned across various actuators to achieve more stable and realistic simulation behavior.
• Environment Configuration Refinements: Several environment configurations for pick-place and lift tasks have been updated, including robot asset references, initial joint poses, object randomization ranges, and camera/end-effector prim paths.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request significantly updates the sim2sim tutorial for Isaac Lab, ensuring compatibility with the latest version. Key improvements include enhanced error handling in data recording and processing, refined robot physical parameters for more stable simulation, and clearer documentation for users. The changes streamline the recording and replay scripts, integrate new XR visualization features, and adjust environment configurations for better task performance and realism.

[Copilot]

Pull Request Overview

This PR updates the sim2sim tutorial code to be compatible with the latest Isaac Lab version. The changes include API updates for device interfaces, robot configuration refactoring, physical parameter tuning, exception handling improvements, and path corrections for the robot hierarchy.

• Refactored robot configurations by removing separate "high PD" configurations and consolidating into single base configurations with updated physical parameters
• Updated Isaac Lab device API usage (Se3Keyboard now requires Se3KeyboardCfg)
• Added exception handling to data recording and conversion scripts to prevent runtime errors
• Corrected robot hierarchy paths in FFW_BG2 configurations to match updated USD file structure

Reviewed Changes

Copilot reviewed 15 out of 16 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/OMY/stack/joint_pos_env_cfg.py	Updated default joint pose and object spawn range for stack task
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/OMY/stack/ik_rel_env_cfg.py	Increased IK action scale from 0.1 to 0.15
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/OMY/lift/joint_pos_env_cfg.py	Switched from OMY_HIGH_PD_CFG to OMY_CFG
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/OMY/lift/ik_rel_env_cfg.py	Switched from OMY_HIGH_PD_CFG to OMY_CFG
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/FFW_BG2/pick_place/pick_place_env_cfg.py	Updated table position, added object position/rotation observations
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/FFW_BG2/pick_place/joint_pos_env_cfg.py	Refactored events, updated robot config, corrected camera/frame paths
source/robotis_lab/robotis_lab/simulation_tasks/manager_based/FFW_BG2/pick_place/ik_rel_env_cfg.py	Switched from FFW_BG2_PICK_PLACE_CFG to FFW_BG2_CFG
source/robotis_lab/robotis_lab/assets/robots/OMY.py	Removed OMY_HIGH_PD_CFG, tuned damping/stiffness parameters, expanded gripper joint control
source/robotis_lab/robotis_lab/assets/robots/FFW_BG2.py	Removed FFW_BG2_PICK_PLACE_CFG, tuned actuator parameters for grippers and head
scripts/sim2real/imitation_learning/recorder/record_demos.py	Added handling for dictionary actions with reset keys
scripts/sim2real/imitation_learning/mimic/action_data_converter.py	Added exception handling and error reporting for episode processing
scripts/sim2real/imitation_learning/dds_sdk/omy_sdk.py	Updated device state retrieval to use current robot joint positions
scripts/imitation_learning/isaaclab_recorder/replay_demos.py	Updated Se3Keyboard API to use Se3KeyboardCfg, added locomanipulation task import
scripts/imitation_learning/isaaclab_recorder/record_demos.py	Updated argparse help text, fixed parameter passing, added XR visualization setup, reordered demo completion check
README.md	Corrected script path and added reference to physical_ai_tools

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[GyuH13]

GOOD. Now it is syncronized with isaac lab.

[ola31]

Good