Research

How to efficiently coordinate individual actors of open, large and complex cyber-physical systems in a scalable and robust way with quality of solution guarantees while considering both individual interest and system performance?

To answer this question, I use mostly the paradigm of multi-agent systems (MAS), combinatorial optimization, and artificial intelligence, where each (human, software, infrastructure, or robot) actor is a software agent making decisions independently and autonomously based on its local computations and the communication with others.

My research focus is on engineering distributed and scalable decision-making systems where a large decision problem should be decomposed into smaller and interconnected subproblems. The challenge in the distribution and decentralization of decision-making lies in the complexity both of the coordination problem at hand and a solution approach that should consider the balance between local computation and communication (information exchange) .

I develop both mathematical programming models that decompose computationally expensive coordination problems considering individual and shared decisional variables, objectives, and constraints as well as distributed and decentralized algorithms that solve the decision problem while managing the MAS’s bottlenecks.

The result is a distributed or decentralized decision-making architecture (one or the other, depending on the context) that enables each agent to decide in its best interest considering the context and system constraints. These constraints are modelled to influence individual decisions such that given fairness and social welfare criteria are optimized.

Among many open issues in large, open, and complex cyber-physical systems whose elements may be owned by multitudes of stakeholders, there is the one related with the ways to model the decision-making for relevant decision makers composing the system and the means to orchestrate and scale decision making considering desired system behavior and social welfare. There is also the question of incentives in a MAS composed of competitive agents whose emergent behavior should be controlled: how to incentivize agents to participate and how to create in them the sense of satisfaction when behaving collaboratively and not to rely only on negative reinforcement and punishment measures such as penalties to realize the MAS’s objectives.

The quality of solution in a cyber-physical system strongly depends on the quality of available information and is based on sensory and communication technologies, whose developments give rise to new real-time multi-agent coordination technologies applicable in various real-world industrial and business contexts.

My long term objective is to lower the inefficiency of the decision-making in competitive environments based on Nash equilibrium through plausible MAS coordination solutions that will get closer to the system optimum while increasing fairness and social welfare.

I apply my research to resolving societal challenges including:

· Smart and Green Transport and, in more specific, the development of distributed Route Guidance Systems (RGS) for the assignment of efficient, fair, and envy-free routes to users in a distributed way in real-time and the coordination of commercial fleets without the need for a dispatching center.

· Emergency Management: i) distributed coordination of Emergency Medical Systems with ambulances and ii) distributed coordination of evacuation routes in emergency evacuation of buildings, neighborhoods or cities. [ video ]

· Multi-Robot Coordination: i) mobile industrial robots within robot teams working on a factory shop-floor, agriculture, etc. and ii) teams of mobile service robots with humans for human assistance and support.