Implicit Virtual Leader: Decentralized Vision-Only Relative Pose Estimation for Multi-Robot Formations
Year: 2026
Type: preprint
Abstract: Classical leader-follower formation control suffers from single points of failure and error propagation, and relies on absolute localization sensors that are ill-suited for GPS-denied environments. We present a learned, vision-only estimator that maps each robot's monocular image, together with messages exchanged over a communication graph, directly to its 6-DoF relative pose. Its key ingredient is the implicit virtual leader (IVL): a non-physical reference frame at the team centroid, implicitly learned inside a Transformer-based graph neural network, so that estimation has no privileged node and needs no absolute localization. The estimator additionally reports well-calibrated aleatoric (heteroscedastic GNLL) uncertainty alongside epistemic (MC~Dropout) uncertainty, compared systematically across simulation and real-world test sets. Trained only in simulation, the estimator generalizes to unseen scenes, to larger unseen team sizes, and to an external real-world benchmark. It exhibits no single point of failure: removing any one robot costs at most $1.24\times$ the median removal, and removing $71\%$ of the communication links costs $1.77\times$ in position error without retraining. Trained on real-robot data from a single platform, it transfers without modification to a heterogeneous team, estimating relative pose to $0.22$\,m and $1.6^\circ$ on physical robots, where it drives closed-loop formation control.
Source: arXiv (Cornell University)
Authors: Yang, Shiyuan, Wang, Zelin, Tao, Zhijia, Wang, Yilin, Hou, Zhengyu, Kong, Xiaosong, Zhang, Borong, Yeung, Yip Fun, Luo, Yuankai, Lee, Sharon, Li, Qingbiao
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7169766272
Cites:
Cited by:
Related to: