Bridging the Sim-to-Real Gap with multipanda ros2: A Real-Time ROS2 Framework for Multimanual Systems

TL;DR

Bridging the sim-to-real gap in multi-arm torque control, the paper presents multipanda_ros2, a ROS2-based framework that coordinates multiple Franka Panda arms from a single process with real-time 1 kHz torque control and rapid controller switching. It combines a high-fidelity MuJoCo simulation plugin with a unified, ROS2-compatible control interface to benchmark performance and align simulated and real dynamics, including real-world inertial parameter identification to refine physics. The key contributions are the controllet architecture enabling ≤2 ms switching, the multimode controller that orchestrates controllets, and the demonstration of sim-to-real fidelity across rigid dual-arm, contact-rich tasks. Overall, the work provides a robust, reproducible platform for advanced robotics research that moves toward closing the sim2real gap in multi-arm manipulation.

Abstract

We present $multipanda\_ros2$, a novel open-source ROS2 architecture for multi-robot control of Franka Robotics robots. Leveraging ros2 control, this framework provides native ROS2 interfaces for controlling any number of robots from a single process. Our core contributions address key challenges in real-time torque control, including interaction control and robot-environment modeling. A central focus of this work is sustaining a 1kHz control frequency, a necessity for real-time control and a minimum frequency required by safety standards. Moreover, we introduce a controllet-feature design pattern that enables controller-switching delays of $\le 2$ ms, facilitating reproducible benchmarking and complex multi-robot interaction scenarios. To bridge the simulation-to-reality (sim2real) gap, we integrate a high-fidelity MuJoCo simulation with quantitative metrics for both kinematic accuracy and dynamic consistency (torques, forces, and control errors). Furthermore, we demonstrate that real-world inertial parameter identification can significantly improve force and torque accuracy, providing a methodology for iterative physics refinement. Our work extends approaches from soft robotics to rigid dual-arm, contact-rich tasks, showcasing a promising method to reduce the sim2real gap and providing a robust, reproducible platform for advanced robotics research.

Figures (2)

• Figure 1: An overview of multipanda_ros2, summarizing its core features.
• Figure 2: Architecture diagram of the multipanda_ros2.