Graph Neural Networks for Multi-Robot Active Information Acquisition

Tzes, Mariliza; Bousias, Nikolaos; Chatzipantazis, Evangelos; Pappas, George J.

doi:10.1109/icra48891.2023.10160723

Cited by 10 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the domain of homogeneous robot systems, researchers have concentrated on various applications within multi-robot exploration and coverage. These applications encompass a wide range of tasks, such as information gathering, active perception, exploration and mapping, region-of-interest reconstruction, and more [10]. Typically, the primary issue in addressing these diverse tasks is either exploration [11]- [13] or coverage [14]- [16], or a sequential of exploration followed by coverage [17], [18], rather than a combination of the both.…”

Section: A Multi-robot Exploration and Coveragementioning

confidence: 99%

Cooperative Search Strategy of Multi-UAVs Based on Reinforcement Learning

Zhao¹,

Cui

Hao³

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

In the tasks of multi-robot collaborative area search, we propose the unified approach for simultaneous mapping for sensing more targets (exploration) while searching and locating the targets (coverage). Specifically, we implement a hierarchical multi-agent reinforcement learning algorithm to decouple task planning from task execution. The role concept is integrated into the upper-level task planning for role selection, which enables robots to learn the role based on the state status from the upperview. Besides, an intelligent role switching mechanism enables the role selection module to function between two timesteps, promoting both exploration and coverage interchangeably. Then the primitive policy learns how to plan based on their assigned roles and local observation for sub-task execution. The welldesigned experiments show the scalability and generalization of our method compared with state-of-the-art approaches in the scenes with varying complexity and number of robots.

show abstract