Multi-Robot Collaborative Perception With Graph Neural Networks

• Published in: IEEE robotics and automation letters Vol. 7; no. 2; pp. 2289 - 2296
• Main Authors: Zhou, Yang, Xiao, Jiuhong, Zhou, Yue, Loianno, Giuseppe
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aerial systems applications; Decision making; deep learning for visual perception; Encoding; Estimation; Failure; Graph neural networks; Image segmentation; Inference; Multiple robots; Neural networks; Resilience; Robot kinematics; Robot sensing systems; Robots; Semantics; Situational awareness; Task analysis; Visual perception
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2022.3141661

Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents. To enhance the autonomous robot decision-making process and situational awareness, multi-robot systems have to coordinate their perception capabilities to collect, share, and fuse environment information among the agents efficiently to obtain context-appropriate information or gain resilience to sensor noise or failures. In this letter, we propose a general-purpose Graph Neural Network (GNN) with the main goal to increase, in multi-robot perception tasks, single robots' inference perception accuracy as well as resilience to sensor failures and disturbances. We show that the proposed framework can address multi-view visual perception problems such as monocular depth estimation and semantic segmentation. Several experiments both using photo-realistic and real data gathered from multiple aerial robots' viewpoints show the effectiveness of the proposed approach in challenging inference conditions including images corrupted by heavy noise and camera occlusions or failures.