Search for: All records

Many domains of AI and its effects are established, which mainly rely on their integration modeling cognition of human and AI agents, collecting and representing knowledge using them at the human level, and maintaining decision-making processes towards physical action eligible to and in cooperation with humans. Especially in human-robot interaction, many AI and robotics technologies are focused on human- robot cognitive modeling, from visual processing to symbolic reasoning and from reactive control to action recognition and learning, which will support human-multi-agent cooperative achieving tasks. However, the main challenge is efficiently combining human motivations and AI agents’ purposes in a sharing architecture and reaching a consensus in complex environments and missions. To fill this gap, this workshop brings together researchers from different communities inter- ested in multi-agent systems (MAS) and human-robot interaction (HRI) to explore potential approaches, future research directions, and domains in human-multi-agent cognitive fusion. 

Safe and efficient maritime navigation is fundamental for autonomous surface vehicles to support many applications in the blue economy, including cargo transportation that covers 90% of the global marine industry. We developed MARCOL, a collision avoidance decision-making framework that provides safe, efficient, and explainable collision avoidance strategies and that allows for repeated experiments under diverse high-traffic scenarios. 

Navigation and obstacle avoidance in aquatic en-vironments for autonomous surface vehicles (ASVs) in high-traffic maritime scenarios is still an open challenge, as the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is not defined for multi-encounter situations. Current state-of-the-art methods resolve single-to-single encounters with sequential actions and assume that other obstacles follow COLREGs. Our work proposes a novel real-time non-myopic obstacle avoidance method, allowing an ASV that has only partial knowledge of the surroundings within the sensor radius to navigate in high-traffic maritime scenarios. Specifically, we achieve a holistic view of the feasible ASV action space able to avoid deadlock scenarios, by proposing (1) a clustering method based on motion attributes of other obstacles, (2) a geometric framework for identifying the feasible action space, and (3) a multi-objective optimization to determine the best action. Theoretical analysis and extensive realistic experiments in simulation considering real-world traffic scenarios demonstrate that our proposed real-time obstacle avoidance method is able to achieve safer trajectories than other state-of-the-art methods and that is robust to uncertainty present in the current information available to the ASV.