CRII: FRR: Cooperative Multi-Agent Systems Cognitive Modeling

The project aims to develop models for analyzing artificial intelligence (AI) robots’ (AI agents) motivations and behaviors and to understand their diverse relationships as they cooperate and adapt to the needs and behaviors of humans and other AI agents. The project’s novelty is its focus on modeling cooperative multi-agent systems (MAS) from the cognitive science perspective and investigating how they reach consensus and integrate human needs through a shared needs-oriented trust network in the interaction. The project’s impacts are in advancing artificial social systems (like multi-robot systems and self-driving cars) in human society and to help them to work harmoniously with us, supporting sustainable human development. Moreover, the success of this project could enable cognitive modeling for cooperability-aware MAS of advanced AI architectures and software, leading to new technologies and applications in the computing, communications, electronics, aerospace, transportation, agriculture, and defense industries. The lead research investigator is engaging in outreach activities involving teachers and K-12 students through hands-on exposure to advanced AI and robotics technologies. The project’s three main objectives are to (1) design self-regulating AI agents with self-goal setting, self-monitoring, self-instruction, and self-reinforcement learning abilities, (2) design multi-sensor AI agents and corresponding communication protocols that will allow the robots to quantify their needs, recognize their innate values, and reach a consensus through negotiation, and (3) build an interface to share human needs with robots in real-time, guaranteeing human and AI agents interact in the same needs-oriented trust network. Finally, the project combines the characteristics of three models into a single system and analyzes how robots interact within a multi-robot testbed. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.