What's new in Vulcanexus: human-robot interaction and AI task planning for ROS 2
Between May and September 2026, eProsima presented three important developments in Vulcanexus, one of the building blocks of the ARISE framework: a modular toolkit for human-robot interaction, a more scalable way to share data about people, and a beta framework for AI-based task planning.
A robot working alongside people may need to know who is around, understand what they say and decide what to do next. Each of those capabilities depends on software that ROS 2 developers would otherwise have to build and connect themselves.
ARISE is a European project developing open technologies for human-centric robotics applications. Vulcanexus, the ROS 2 tool set developed and maintained by eProsima, is part of its technical foundation. Its latest developments address the three needs above.
Vulcanexus HRI: perception and interaction modules for ROS 2
Vulcanexus HRI is a set of modules that give a ROS 2 application information about the people around the robot, and ways to communicate with them. It covers face detection, human pose estimation, emotion recognition based on facial expressions, visual displays, speech-to-text and text-to-speech. Shared message definitions let these modules work together as one system.
Each module can run on its own or alongside the others. A team could use pose estimation to know where an operator is standing and text-to-speech to tell them a task is finished, without redesigning the rest of the application. Because Vulcanexus HRI runs within existing Vulcanexus and ROS 2 setups and builds on the latest Fast DDS features, it can be added to applications that are already running.
hri_msgs: keeping communication manageable when several people are present
Handling data about one detected person is relatively straightforward. As several people are tracked simultaneously, however, the communication architecture becomes more demanding. In many HRI designs, each detected person gets its own namespace, with its own topics, publishers and subscribers. The approach is clear, but the communication graph grows with every new person in the scene, and large ROS 2 systems can become saturated.
hri_msgs takes a different route. It relies on Fast DDS Keys, which let a single topic carry many instances of the same data type, each with its own identifier. All detected faces can share one topic and still be told apart. It also aggregates related data: a face’s region, landmarks and pose can travel in a single message instead of on separate topics.
The outcome is fewer topics and communication entities, less middleware overhead and simpler discovery. A smaller graph is easier to visualise and debug, which matters when an application moves from a demo to a real deployment.
VulcanAI: from a goal to a plan the robot can execute
Robots can already perceive, navigate, call services and execute actions. As applications grow, the harder part is deciding what to do first, what can run in parallel and how to recover when a step fails.
VulcanAI is a framework that uses language models as planning assistants. Given a request, it breaks it into sub-tasks, makes explicit which steps run in sequence and which in parallel, and selects the tools to carry them out from a registry. Steps can pass results to one another, and an iterative manager checks progress and regenerates the plan when needed.
VulcanAI comes with default ROS 2 tools for nodes, topics, services, actions, parameters and interfaces, so it can also help inspect and debug running systems. It sits on top of the existing middleware rather than replacing it. The project is in beta and under active development, so for now it is best suited to experimentation.
Why this matters for ARISE
Taken together, these developments cover different layers of the path from perceiving a person to acting on a request. For ARISE, they strengthen the middleware capabilities available for building human-centric robotic applications: Vulcanexus HRI provides reusable perception and interaction modules, hri_msgs makes human-related data exchange more manageable as applications scale, and VulcanAI extends the same ROS 2 environment with AI-based planning and tool-aware execution.
Get started
To try Vulcanexus HRI, see the Overview section of the Vulcanexus documentation
The original articles from eProsima:
- Vulcanexus HRI, building the next generation of human ware robotic systems. (28 May 2026)
- Vulcanexus HRI, a smarter way to scale human robot interaction in ros2 (18 September 2026)
- Introducing VulcanAI planning and reasoning for robotic applications (23 September 2026)
Vulcanexus continues to evolve, with new capabilities and improvements being introduced over time. We’ll be sharing regular updates as new developments become available, so stay tuned for what’s next.
On the Ground Insights Informing the SSH Framework
ARISE and FIWARE in the ADRA Book: Building Open Digital Infrastructures for Robotics
The recently published open-access book “Artificial Intelligence, Data and Robotics: Foundations, Transformations and Future Directions” provides a comprehensive overview of the technologies and initiatives shaping Europe’s digital future.
Published within the framework of the AI, Data and Robotics Association (ADRA), the book reflects the collective work of the European AI-Data-Robotics ecosystem, bringing together researchers, innovation projects, and industry stakeholders working to accelerate the development and deployment of these technologies across Europe.
Among the initiatives featured in the book is ARISE, together with its sister projects FORTIS and JARVIS, which are highlighted in the chapter “Advancing Industrial Collaboration: The Next Generation of Human-Robot Interaction.”
The book reflects the broader strategic vision behind the European AI, Data and Robotics Partnership, which aims to strengthen Europe’s leadership in these technologies while ensuring that innovation remains human-centric, trustworthy and aligned with European values.
Artificial intelligence, robotics and data technologies are increasingly converging to create new possibilities across sectors such as manufacturing, mobility, environmental monitoring and healthcare. This convergence is explored in the chapter “Data, AI, Robotics: Transformative Power in Industry 5.0” where the authors (among them partners in the ARISE project Polimi, Engineering and Cartif) explain how Industry 5.0 builds on the foundations of Industry 4.0 by integrating human-centric, resilient and sustainable manufacturing practices. This chapter reviews a series of European initiatives and industrial pilot cases demonstrating how AI, robotics and data technologies can support circular manufacturing processes, data sharing across value chains and new decision-support capabilities through technologies such as digital twins and real-time industrial data infrastructures.
However, unlocking the full potential of these technologies requires more than individual innovations. It requires digital infrastructures that allow heterogeneous systems to interoperate and share data seamlessly.
This is where open digital infrastructures become essential. Across the European ecosystem, researchers and innovators are increasingly focusing on building interoperable platforms and architectures that allow AI systems, robotics technologies and data infrastructures to work together across domains.
ARISE: contributing to the next generation of human-robot collaboration
In our chapter, we explore (together with our sister projects JARVIS and FORTIS) the evolution of human-robot interaction (HRI) and the technological foundations required to support collaborative robotics in industrial environments.
In particular, we present the ARISE framework, designed to accelerate the deployment of collaborative robotics systems that integrate human expertise with advanced automation technologies. Through experimentation in Testing and Experimentation Facilities (TEFs) and collaboration with SMEs, ARISE aims to bridge the gap between research and real industrial deployment.
Our work focuses on enabling more intuitive interaction between humans and robots, safer collaboration in industrial settings, scalable robotics deployments, and the integration of artificial intelligence into industrial decision-making processes.
FIWARE and ROS2: an open middleware for industrial robotics
A key innovation highlighted in the book is the architectural approach used in ARISE.
The project integrates FIWARE technologies with ROS2 robotics frameworks, creating an open middleware that enables interoperability between robotic systems, industrial applications and AI services.
This architecture allows data to flow seamlessly between robots, digital platforms and industrial systems, enabling:
real-time monitoring of robotic operations
integration of AI-based services
coordination between robots and industrial systems
scalable deployment of robotics applications.
By combining ROS2 robotics capabilities with FIWARE context-management technologies, ARISE demonstrates how open-source platforms can create a flexible and interoperable digital infrastructure for robotics.
This interoperability layer is essential for enabling complex industrial environments where robots, machines, sensors and digital platforms must work together.
Interoperable data infrastructures for AI and robotics
The role of FIWARE technologies is not limited to robotics architectures.
In another chapter of the book, dedicated to the CyclOps project, “CyclOps: Leveraging Semantic Technologies for AI and Data Life Cycle Management and Governance”, FIWARE technologies appear again through the use of NGSI-LD context brokers, which support interoperable data exchange and semantic data management across distributed environments.
FIWARE-based interoperability approaches are also referenced in discussions around emerging data ecosystems, such as in the chapter “Toward the Irish Mobility Data Space: Challenges, Opportunities, and Requirements”, which explores the technological foundations needed to enable cross-domain mobility data spaces.
Context brokers such as Orion-LD, Stellio and Scorpio, available within the FIWARE ecosystem, enable the storage, retrieval and sharing of contextual information across domains such as smart cities, Industry 4.0 and IoT applications.
These technologies illustrate how standardized data infrastructures can support the integration of AI and robotics systems within broader digital ecosystems.
Toward open digital infrastructures for robotics
Taken together, the projects and technologies presented in the book highlight an important transformation in the way Europe approaches technological innovation.
Rather than focusing solely on isolated technological components, the European AI-Data-Robotics ecosystem is increasingly building open digital infrastructures that allow different technologies to work together across sectors and domains.
Within this vision:
ARISE contributes to the development of human-centric robotics systems
FIWARE provides the interoperable data infrastructure that connects digital services, AI applications and industrial systems
This combination of open platforms, interoperable data architectures and collaborative robotics represents a key step toward the realization of Industry 5.0.
The inclusion of ARISE in this ADRA publication highlights the project’s contribution to Europe’s rapidly evolving AI, Data and Robotics ecosystem. By combining open-source technologies, interoperable architectures and human-centric design, ARISE demonstrates how collaborative robotics can be deployed in ways that enhance human capabilities while supporting industrial innovation. At the same time, the broader presence of FIWARE technologies across different chapters of the book reflects the growing importance of open standards and interoperable data infrastructures as foundations for the next generation of digital systems.
Together, initiatives such as ARISE and FIWARE are helping to build the open digital infrastructures that will support Europe’s future in AI, data and robotics.
VITAWELD: Vision, Intelligence and Human-Robot Teaming for the Future of Welding
VITAWELD tackles one of the most persistent challenges in industrial manufacturing: welding large metal components without compromising quality, efficiency, or accessibility. Traditional processes struggle with heat-induced distortions, late detection of defects, and manual parameter adjustments that slow production and introduce variability. Programming industrial robots for such tasks requires advanced technical expertise, creating a barrier for companies with limited resources.
The solution brings a fundamentally different approach to welding automation
VITAWELD blends advanced computer vision, AI, and natural user interfaces to keep the operator in control while enhancing their capabilities. The system enables robot programming through natural language and real-time visualization in augmented reality, making adjustments intuitive and immediate. AI-powered vision algorithms detect potential defects as they happen, while automated parameter optimization ensures repeatability and minimizes waste. Built on a modular ROS 2 and FIWARE architecture, the platform can adapt to different industrial contexts and scale with changing needs.
Within the ARISE project, VITAWELD exemplifies how collaborative robotics can democratize access to advanced automation. FIWARE integration ensures interoperability and supports a standards-based approach, making the solution replicable across industries. Most importantly, it reflects a vision where technology empowers rather than replaces, aligning closely with the principles of Industry 5.0.
The impact is measurable
Early projections indicate a reduction of more than 50% in robot programming time, over 30% improvement in first-time-right weld quality, and the ability to train new operators in less than two days. Energy consumption could be reduced by 15%, with significant savings in material waste. These advances not only improve productivity but also make welding safer and less physically demanding, encouraging greater diversity in the workforce.
Market potential is equally strong
The global industrial human-robot interaction market is expected to reach $8.6 billion by 2025, with the large-component welding segment valued at $1.2 billion. By focusing on amplifying human capabilities rather than replacing them, VITAWELD differentiates itself from conventional automation. Its modular design and human-centered philosophy allow rapid adaptation to other processes such as TIG, MIG, and additive manufacturing, delivering a return on investment in just 18 to 24 months.
Inclusivity is embedded in the design
Interfaces are multilingual and configurable, with universal iconography and color-blind-friendly visualizations. Ergonomic considerations accommodate operators of different heights, handedness, and working styles. The system can adapt to local cultural norms in units of measurement, alerts, and training materials, ensuring usability across global manufacturing environments.
VITAWELD represents more than a technical solution—it redefines the relationship between people and machines in industrial welding. By combining precision, adaptability, and inclusivity, it sets a new standard for human-robot teaming, one where innovation strengthens human expertise, fosters sustainable manufacturing, and builds a safer, more productive future.