We introduce a principled method for multi-robot coordination based on a general model
(termed a MacDec-POMDP) of multi-robot cooperative planning in the presence of …

In centralized multi-agent systems, often modeled as multi-agent partially observable
Markov decision processes (MPOMDPs), the action and observation spaces grow …

Given a partially observable Markov decision process (POMDP) with finite state, input and
measurement spaces, and costly measurements and control, we consider the problem of …

We investigate model-free multi-agent reinforcement learning (MARL) in environments
where off-beat actions are prevalent, ie, all actions have pre-set execution durations. During …

Scientific robot competitions are considered a powerful drive for advancing the state-of-the-
art in robotics research and development. This paper describes the research objectives and …

This work focuses on the application of Decision-Theoretic (DT) frameworks to scenarios in
Cooperative Robotics. We address both theoretical and practical issues involved in …

Online planning in single-agent partially observable environments scales to realistic
environments with billions of states. However, in centralised multi-agent systems, often …

The SocRob team has been representing ISR/IST since 1998 in the world's leading scientific
event on Artificial Intelligence and Robotics, RoboCup, as the application side of SocRob …

The SocRob@ Home team has a long record in scientific competitions and recently has
participated in ERL Smart Cities 2019, RoboCup 2021, and RoboCup 2023, among other …

This paper describes the research interest and technical information of the SocRob team for
the RoboCup@ Home 2016 competition. The SocRob team has been representing the …