01 January 2025
Awareness is a fundamental aspect of any agent capable of information integration into complex and rich internal representations, across a multitude of dimensions including perceptual, introspective and social facets. In this respect, it characterizes as a fundamental concept to engineer efficient and effective distributed loosely-coupled systems of synthetic agents, as it caters for the ability to communicate and interoperate by exchanging bits of semantically rich information, which are the awareness states possessed by the single agents. Awareness in biological agents has converging definitions when considering local states describing content-related awareness from an agent-specific perspective. However, it becomes highly debated when it comes to global states. The issue magnifies when considering collectives of artificial agents, such as in robotic swarms.
Several frameworks exist, all unsatisfactory in the limitations posed to agents’ heterogeneity and disappearance of the local self into an integrated state. Ultimately, existing awareness frameworks are ineffective in explaining, facilitating, and supporting cooperative behaviours in artificial agents. The lack of a compelling theory of global awareness in AI is currently a significant barrier to the effective deployment of artificial agents in the real world.
In this work, EMERGE partners introduce the concept of collaborative awareness as a means to enhance interoperability, resilience and self-regulation in synthetic agent collectives. The authors discuss the theoretical, computational and engineering framework of collaborative awareness and its application to distributed robotic systems.
Read the paper in the link below.
More Information
