quadruped_sim2sim: a reproducible sim-to-real evaluation loop #7

Hi maintainers,

I came across evronix/quadruped_sim2sim and noticed that it focuses on "Deploying a quadruped robot policy(DreamWaQ, walk-these-ways, HIMLoco) trained in Isaacgym to ROS2 Gazebo for Sim-to-Sim". That is close to a problem we are working on with EVA-CLIENT, a unified framework for real-robot deployment, evaluation, and LeRobot data collection.

If this direction looks relevant, you can take a look at EVA-CLIENT here: https://github.com/Noietch/EVA-CLIENT

For evronix/quadruped_sim2sim, EVA's ROS 2 transport could connect the existing nodes to a repeatable deployment/evaluation loop with synchronized video, state traces, and latency logs. A small first experiment could be to run one existing ROS 2 policy through EVA's headless/ZMQ path and inspect a single latency/state trace. We would be happy to prepare a minimal adapter or example around your current interfaces, rather than asking you to change the project architecture.

If this is useful, I would be glad to compare notes or help with a small integration. If it is not relevant, no worries—and we will not follow up.

Best,
EVA-CLIENT Team