Periodic Reporting for period 1 - EMERGE (Emergent awareness from minimal collectives)
Período documentado: 2022-10-01 hasta 2023-09-30
How do robots in a collective know what the group as a whole is doing? How can connected devices make sense of the world around them with so many interconnections? How can a robotic arm composed of many independent parts understand how its body behaves as it reaches for an object? When intelligence is distributed across many parts, be they robots, devices, or objects, it can be tricky for the bigger picture to emerge. Yet answering these questions is key to making collective systems easy to design, monitor and control.
The EMERGE project will deliver a new philosophical, mathematical, and technological framework to demonstrate, both theoretically and experimentally, how collaborative awareness – a representation of shared existence, environment and goals – can arise from the perceptions and interactions of individual agents, without leveraging a pre-existing common language between them. This collaborative awareness envisioned by EMERGE will transform robotic systems, as well as all kinds of applications which involve providing a service over a loosely coupled collective of entities, both physical or virtual, such as Internet-of-Things (IoT) devices, smart services, biomedical nanodevices, and many others.
The EMERGE project will deliver a new philosophical, mathematical, and technological framework to demonstrate, both theoretically and experimentally, how collaborative awareness – a representation of shared existence, environment and goals – can arise from the perceptions and interactions of individual agents, without leveraging a pre-existing common language between them. This collaborative awareness envisioned by EMERGE will transform robotic systems, as well as all kinds of applications which involve providing a service over a loosely coupled collective of entities, both physical or virtual, such as Internet-of-Things (IoT) devices, smart services, biomedical nanodevices, and many others.
During its first year, EMERGE focused on establishing the concept of "dimensional awareness" as a minimal, yet operational, capability for AI systems to adapt to and reflect upon certain dimensions, such as spatial proximity, decision confidence, or energy levels. This form of awareness is distinct from consciousness; it is localized, compartmentalized, and scalable, and it significantly enhances interactions and coordination between AI systems, as well as between AI and humans. Such dimensional model of awareness has been completented by an engineering framework to concretize and measure the single awareness dimensions in both biological and artificial systems, paving the way for developing (in the continuation of the project) the methodology and tools to control the emergence of collaborative awareness in the systems. The conceptual framework has also been analysed from an ethical perspective, by compiling a mapping of the ethical risks in human interactions with collective aware AI. Empirical studies have also been conducted as regards human tendency to exploit AI systems and attribution of responsibility in unitary and collective AI agents. From a computational and technical perspective, EMERGE has produced a preliminary set of models inspired by dynamical systems processing, which are crucial mechanisms to create the adaptive processing system of the aware agents (the Archetypes Computing System), as well as to describe their micro/macro behaviour as a collective.
Artificial intelligence nowadays enables the translation of isolated local awareness states from biological to artificial agents using information about the environment which can be collected from mechanical (contact, vibration, collision, etc), and electromagnetic (radio, infrared, visible light, etc) stimuli. However, the cooperation among those units is often dependent on some kind of central processing unit which collects that information and establishes a centralised awareness which distributes commands to each unit. Although useful, this process allows for very specific and previously programmed situations to be navigated and problems to be solved. For artificial agents to be able to act in the unstructured conditions that the real-world demands, a new concept of collaborative awareness is needed. EMERGE’s goal is to establish, analyse, implement and test a new artificial intelligence framework that allows this collaborative awareness to emerge from the interplay of multiple individual units of local awareness. This collaborative awareness becomes an emergent process supporting complex, distributed, and loosely coupled systems capable of high degrees of collaboration, self-regulation, and interoperability without predefined protocols.
In terms of innovation impact, EMERGE aims to surpass limitations and barriers of the current state-of-the-art multi-agent collaborative systems, with potential to produce breakthroughs and open new markets in the next generation of robotic systems. For that, the project focuses on three use cases. The first use case is modular soft robots – self‐assembling, repairing or replicating robots made from soft materials which offer high freedom of movement, even in confined spaces, and better manipulation of delicate objects. In these robots, the body formed by a physically distributed collective needs to self-organise to account for the dynamic addition of components. The second use-case are robotic swarms – groups with a large number of robots whose behaviour arises from the interactions between themselves and with their environment. This is an example of a large-scale minimal collective where agents need coordination to achieve a collaborative goal. Finally, the third use case are collaborative robots, or cobots – robots interacting in direct contact with, or in close proximity to, humans. These represent a closer-to-market use case where interoperability is currently a significant barrier. While robotics provides the perfect testing ground for this new framework, EMERGE also envisions impact in areas such as Internet-of-Things (IoT), smart cities and transportation, microservice-based information and communications technology (ICT) systems, and biomedical nanodevices, among others.
In terms of innovation impact, EMERGE aims to surpass limitations and barriers of the current state-of-the-art multi-agent collaborative systems, with potential to produce breakthroughs and open new markets in the next generation of robotic systems. For that, the project focuses on three use cases. The first use case is modular soft robots – self‐assembling, repairing or replicating robots made from soft materials which offer high freedom of movement, even in confined spaces, and better manipulation of delicate objects. In these robots, the body formed by a physically distributed collective needs to self-organise to account for the dynamic addition of components. The second use-case are robotic swarms – groups with a large number of robots whose behaviour arises from the interactions between themselves and with their environment. This is an example of a large-scale minimal collective where agents need coordination to achieve a collaborative goal. Finally, the third use case are collaborative robots, or cobots – robots interacting in direct contact with, or in close proximity to, humans. These represent a closer-to-market use case where interoperability is currently a significant barrier. While robotics provides the perfect testing ground for this new framework, EMERGE also envisions impact in areas such as Internet-of-Things (IoT), smart cities and transportation, microservice-based information and communications technology (ICT) systems, and biomedical nanodevices, among others.