ros integration

To address challenges in the Internet of Robotic Things (IoRT)—including limited onboard perception, insufficient environmental semantic understanding, and poor real-time performance in dynamic obstacle avoidance—this paper proposes a ROS-based collaborative architecture integrating intelligent spaces with mobile robots. Methodologically, it introduces a distributed environmental perception network as an external sensing enhancement module within ROS, enabling closed-loop coordination among multi-source sensor fusion, semantic environmental modeling, and autonomous robot decision-making. Additionally, a lightweight real-time collision prediction algorithm is designed to reduce reliance on individual robot intelligence. Experimental results demonstrate significant improvements in complex dynamic environments: obstacle avoidance success rate increases by 23.6%, and system response latency decreases by 41%. These findings validate the effectiveness and scalability of the proposed IoRT architecture for cost-constrained robotic systems.

This work addresses the limitations of existing robotic middleware—such as ROS 2—whose architectural complexity, poor interoperability, and steep learning curve hinder the development of efficient cross-platform robotic systems. To overcome these challenges, we propose Meta-ROS, a lightweight middleware architecture built upon modern communication protocols like Zenoh and ZeroMQ. Meta-ROS streamlines integration, supports multimodal data transmission—including audio and video—and enables seamless cross-platform deployment. Experimental results demonstrate that Meta-ROS achieves up to 30% higher throughput, lower message latency, and reduced resource consumption compared to ROS 2, thereby providing a highly compatible, low-latency foundation for real-time robotic AI applications.

This study addresses the challenge of simultaneously achieving spatial abstraction, temporal predictability, and state continuity in ROS 2 middleware operating within dynamic, resource-constrained wireless environments. For the first time, it introduces a three-dimensional “space–time–state” analytical framework, integrating architectural analysis, formal modeling, and a comprehensive literature review to systematically investigate the underlying mechanisms and structural trade-offs of ROS 2 middleware—particularly DDS and Zenoh—in discovery protocols, data exchange, and state management. The work uncovers critical performance bottlenecks in existing approaches concerning modular deployment, real-time control, and disconnected operation recovery. These insights lay a theoretical foundation and offer concrete design guidelines for developing robust, scalable next-generation robotic middleware.

To address the challenges of ROS 2—including reliance on local deployment, poor reproducibility, high educational barriers, and significant security risks—this paper introduces ROS2Wasm, the first native browser-based ROS 2 execution framework. Leveraging WebAssembly cross-compilation and RoboStack containerization, ROS2Wasm enables zero-installation, in-browser execution of the ROS 2 core, RoboStack ecosystem, and the Robotics Toolbox for Python. A lightweight communication middleware—built upon WebSockets and SharedArrayBuffer—supports real-time TF visualization, sensor simulation, and Python script execution. Furthermore, integration with the Swift Web simulator and PyTorch/Open3D Web bindings ensures safe, sandboxed execution with strict isolation guarantees. Deployed at ros2wasm.dev, the system achieves startup latency under 500 ms and supports all major browsers. ROS2Wasm significantly enhances reproducibility in robotics research, accessibility in education, and runtime security—all without compromising functionality or performance.

This work addresses the challenge of simultaneously achieving certifiable real-time control and advanced perception capabilities in autonomous flight systems, a balance that existing architectures struggle to maintain due to inherent trade-offs between reliability and flexibility. To bridge this gap, the authors propose a hybrid architecture that integrates NASA’s F´ flight software framework with the ROS 2 middleware, leveraging Protocol Buffers for efficient communication between vision-based navigation and flight control modules. Implemented and validated in closed-loop on an embedded quadrotor platform, this approach represents the first seamless integration of the certifiable F´ framework with the flexible ROS 2 ecosystem. Flight tests totaling 32.25 minutes demonstrate high performance: position estimation at 87.19 Hz, 99.90% data continuity, an average latency of 11.47 ms, only 15.19% CPU utilization, and successful execution of all 15 ground commands, collectively confirming the system’s efficiency, robustness, and certification potential.

This work proposes multipanda_ros2, an open-source multi-arm control framework built on ROS 2 to address the challenges of control accuracy, real-time performance, and dynamic consistency in sim-to-real transfer for multi-manipulator systems. The framework enables single-process real-time control of an arbitrary number of Franka arms, integrates high-fidelity MuJoCo simulation, and enhances force/torque accuracy through inertial parameter identification. It introduces a novel controllet-feature design pattern that achieves controller switching latency of ≤2 ms and extends soft robotics methodologies to rigid dual-arm contact tasks, establishing quantitative metrics to bridge the sim-to-real gap. Experimental results demonstrate stable 1 kHz torque control and significantly improved consistency between simulation and physical execution, offering a reproducible, high-fidelity platform for complex multi-arm cooperative tasks.

Standard ROS 2 faces challenges such as network congestion, naming conflicts, and high computational overhead in dense multi-agent perception scenarios. This work proposes a resource-aware collaborative perception framework that employs structured fully qualified names to achieve traffic isolation, integrates Fast DDS directional routing with lightweight inter-process communication (IPC) optimizations, and introduces on-demand centralized decoding alongside hardware abstraction containers to enable zero-configuration deployment across heterogeneous accelerators. The proposed approach reduces network traffic control complexity to O(1), decreases per-subscriber CPU overhead by 72.3% compared to standard ROS 2, and maintains low latency, thereby significantly enhancing system scalability and efficiency.

This work addresses the tight coupling between reference signal processing and control law implementation in ROS 2 controllers, which leads to code redundancy and poor reusability. To resolve this, the authors propose a modular architecture that decouples reference generation logic from the controller for the first time in ROS 2, introducing a dedicated Reference Generator component. This component uniformly handles reference acquisition, validation, and interpolation in both joint and Cartesian spaces, and integrates seamlessly with downstream controllers via the ros2_control chainable controller mechanism. Leveraging this architecture, several novel controllers—including PD with gravity compensation, Cartesian pose, and admittance controllers—were developed. Experimental validation on Universal Robots and Franka Emika manipulators demonstrates stable and reliable reference tracking, significantly reduced code duplication, and enhanced controller reusability and development efficiency.

This work addresses the limited generalizability and transferability of current foundation models in robotics, which often require custom integration of perception, actuation, and safety mechanisms. To overcome this, the authors propose ROSClaw—a model-agnostic execution layer that enables plug-and-play deployment of arbitrary foundation models on any ROS 2 robot by integrating the OpenClaw agent runtime with ROS 2. Key innovations include standardized capability discovery, multimodal observation normalization, action validation within configurable safety bounds, and structured audit logging. Experiments across three robotic platforms and four foundation models demonstrate up to a 4.8× difference in non-policy action proposal rates and show that the proposed execution layer significantly improves task success rates and safety across diverse frameworks.

This work addresses the distortion inherent in existing ROS 2 introspection tools, which perturb system behavior through intrusive probe injection. To overcome this limitation, the authors propose a non-intrusive observation framework that reconstructs the communication topology by parsing the DDS discovery protocol and performs efficient kernel-space filtering of packets belonging to specified topics. This approach enables precise, semantically complete observation of actual subscription content without introducing probe effects, while maintaining compatibility with standard tooling interfaces. Evaluated across diverse hardware platforms and DDS implementations, the method demonstrates negligible overhead: communication graph inflation remains below 0.5%, zero message loss is achieved, and CPU and memory consumption are reduced to 1/7 and 1/28, respectively, of those incurred by state-of-the-art tools.