Internet of Robotic Things – Converging Sensing/Actuating, Hyperconnectivity, Artificial Intelligence and IoT Platforms

Ovidiu Vermesan, Arne Bröring, Ηλίας Τράγος, Martín Serrano, Davide Bacciu, Stefano Chessa, Claudio Gallicchio, Alessio Micheli, Mauro Dragone, Alessandro Saffiotti, Pieter Simoens, Filippo Cavallo, Roy BahrRiver 2022 · DOI · OpenAlex

Abstract: The Internet of Things (IoT) concept is evolving rapidly and influencing new developments in various application domains, such as the Internet of Mobile Things (IoMT), Autonomous Internet of Things (A-IoT), Autonomous System of Things (ASoT), Internet of Autonomous Things (IoAT), Internet of Things Clouds (IoT-C) and the Internet of Robotic Things (IoRT) etc. that are progressing/advancing by using IoT technology. The IoT influence represents new development and deployment challenges in different areas such as seamless platform integration, context based cognitive network integration, new mobile sensor/actuator network paradigms, things identification (addressing, naming in IoT) and dynamic things discoverability and many others. The IoRT represents new convergence challenges and their need to be addressed, in one side the programmability and the communication of multiple heterogeneous mobile/autonomous/robotic things for cooperating, their coordination, configuration, exchange of information, security, safety and protection. Developments in IoT heterogeneous parallel processing/communication and dynamic systems based on parallelism and concurrency require new ideas for integrating the intelligent “devices”, collaborative robots (COBOTS), into IoT applications. Dynamic maintainability, self-healing, self-repair of resources, changing resource state, (re-) configuration and context based IoT systems for service implementation and integration with IoT network service composition are of paramount importance when new “cognitive devices” are becoming active participants in IoT applications. This chapter aims to be an overview of the IoRT concept, technologies, architectures and applications and to provide a comprehensive coverage of future challenges, developments and applications.

The Evolution of IoT: From Sensing to Actuating

Traditionally, the Internet of Things (IoT) has focused on passive sensing and data collection—a "sensing-only" paradigm where devices act as observers. However, the field is undergoing a fundamental shift toward the Internet of Robotic Things (IoRT). This evolution represents a transition from simple data gathering to active physical agency, where autonomous, heterogeneous robots collaborate via distributed edge and cloud platforms.

Evolution of IoT from a centralized sensing model to a hyperconnected, autonomous future.

As illustrated in the comparison between current and future IoT states, the landscape is moving from a centralized hub-and-spoke model toward a dense mesh of hyperconnectivity. In the future, the network will not just connect static sensors but will integrate autonomous vehicles, drones, and collaborative robots (COBOTS) that must navigate unpredictable human environments and execute tasks safely without a central "brain" controlling every move.

Architectural Framework: The Six Pillars

The IoRT aims to solve the problem of technological fragmentation by creating an open, distributed architecture. The authors define the functional lifecycle of an IoRT device through six core characteristics:

  1. Sensing: Gathering environmental data.
  2. Actuating: Executing physical movements or changes.
  3. Control: Managing feedback loops for precise action.
  4. Planning: Determining the sequence of actions to achieve a goal.
  5. Perception: Interpreting sensor data to understand the environment.
  6. Cognition: Higher-level reasoning and decision-making.

To support these pillars, the paper advocates for a shift from centralized cloud computing to Distributed Edge Computing. This allows for low-latency "control loops" where processing happens close to the robot, which is essential for real-time interaction and collision avoidance.

Enabling Technologies: AI and Blockchain

Two key technological paradigms are identified as essential for the realization of IoRT:

  • Reservoir Computing (RC): A type of recurrent neural network noted for its low computational and memory footprint. RC is ideal for embedding intelligence directly into low-power robotic "things," allowing them to process complex temporal data locally.
  • Blockchain Integration: The paper proposes using blockchain for decentralized swarm coordination. This provides secure identity management (via Public/Private keys for robots) and enables automated machine-to-machine (M2M) payments for services, creating a trustless marketplace for robotic functions.

Key Insights and Challenges

Unlike static IoT sensors, robots are mobile, which multiplies the operational contexts they encounter. A robot must handle transitions like leaving a Wi-Fi zone or entering a private space as part of its core logic. Furthermore, while multiple applications can easily read the same sensor data, they cannot easily share an actuator. If two applications attempt to move a robot arm in opposite directions, a conflict arises. The paper identifies three interaction types for actuation: competitive, cooperative, and adversarial.

Market Potential and Future Hurdles

The economic shift is massive, with the "Silver Economy" (healthcare for the elderly) serving as a primary driver. The market for personal robots was expected to reach $34.1 billion by 2022. However, several research hurdles remain:

  • The Semantic Gap: While syntactic interoperability (connecting devices) is improving, "semantic interoperability"—getting a robot from Brand A to understand the "skills" and "goals" of a robot from Brand B—remains a major challenge.
  • Security vs. Safety: A security breach in an IoRT system is not just a data leak; it is a physical safety risk. Current IoT security measures are often insufficient for devices that can move and exert force.

Conclusion

The IoRT represents a convergence of sensing, actuation, and distributed intelligence. By moving from a "read-only" to a "read-write" relationship with the physical world, IoRT platforms will enable a new generation of autonomous services across healthcare, manufacturing, and smart cities.

Summary updated

Abstract

The Internet of Things (IoT) concept is evolving rapidly and influencing new developments in various application domains, such as the Internet of Mobile Things (IoMT), Autonomous Internet of Things (A-IoT), Autonomous System of Things (ASoT), Internet of Autonomous Things (IoAT), Internet of Things Clouds (IoT-C) and the Internet of Robotic Things (IoRT) etc. that are progressing/advancing by using IoT technology. The IoT influence represents new development and deployment challenges in different areas such as seamless platform integration, context based cognitive network integration, new mobile sensor/actuator network paradigms, things identification (addressing, naming in IoT) and dynamic things discoverability and many others. The IoRT represents new convergence challenges and their need 98to be addressed, in one side the programmability and the communication of multiple heterogeneous mobile/autonomous/robotic things for cooperating, their coordination, configuration, exchange of information, security, safety and protection. Developments in IoT heterogeneous parallel processing/communication and dynamic systems based on parallelism and concurrency require new ideas for integrating the intelligent “devices”, collaborative robots (COBOTS), into IoT applications. Dynamic maintainability, selfhealing, self-repair of resources, changing resource state, (re-) configuration and context based IoT systems for service implementation and integration with IoT network service composition are of paramount importance when new “cognitive devices” are becoming active participants in IoT applications. This chapter aims to be an overview of the IoRT concept, technologies, architectures and applications and to provide a comprehensive coverage of future challenges, developments and applications.
BibTeX
@inproceedings{vermesan2022internet,
  author = {Ovidiu Vermesan and Arne Bröring and Ηλίας Τράγος and Martín Serrano and Davide Bacciu and Stefano Chessa and Claudio Gallicchio and Alessio Micheli and Mauro Dragone and Alessandro Saffiotti and Pieter Simoens and Filippo Cavallo and Roy Bahr},
  title = {{Internet of Robotic Things – Converging Sensing/Actuating, Hyperconnectivity, Artificial Intelligence and IoT Platforms}},
  booktitle = {River},
  year = {2022},
  doi = {10.1201/9781003337584-4},
}
Figure