Implicit Virtual Leader: Decentralized Vision-Only Relative Pose Estimation for Multi-Robot Formations

• URL: http://arxiv.org/abs/2607.15708v1
• Date: Fri, 17 Jul 2026 07:43:43 GMT
• Title: Implicit Virtual Leader: Decentralized Vision-Only Relative Pose Estimation for Multi-Robot Formations
• Abstract summary: We introduce a vision-only relative pose estimation framework based on Graph Neural Networks (GNNs)<n>The key idea is the implicit virtual leader (IVL), a non-physical formation reference frame that is not tied to any individual robot but is implicitly learned within the GNN.<n>Our framework achieves competitive pose estimation accuracy and generalizes naturally to heterogeneous robot platforms.
• Score: 15.727842962598471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 address these limitations by introducing a fully decentralized, vision-only relative pose estimation framework based on Graph Neural Networks (GNNs). The key idea is the implicit virtual leader (IVL): a non-physical formation reference frame that is not tied to any individual robot but is implicitly learned within the GNN using only monocular images and inter-robot communication. We attach a heteroscedastic GNLL head for aleatoric uncertainty and MC~Dropout for epistemic uncertainty, and conduct a systematic comparison across simulation and real-world test sets. Our framework achieves competitive pose estimation accuracy and generalizes naturally to heterogeneous robot platforms and varying formation sizes.

Related papers

• From Non-Rigid to Rigid: Safe Acquisition of Rigid Communication Graphs under Limited Sensing [1.8619748472447968]
  This paper provides a method for achieving an inter robot collision free, rigid time varying communication graph.<n>The proposed approach guarantees the realization of a rigid graph for nonlinear multi robot systems.
  arXiv  Detail & Related papers  (2026-07-11T07:20:20Z)
• Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming [17.173722576361673]
  We introduce Co-GLANCE, a real-time onboard perception and decision-making system for uncertainty resolution in robot teams.<n>To quantify perceptual uncertainty, Co-GLANCE combines conformal prediction with selective abstention to provide statistically valid coverage guarantees.<n>We also release an air-ground dataset for future research.
  arXiv  Detail & Related papers  (2026-06-07T00:02:21Z)
• Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning [56.240199425429445]
  Multi-robot motion planning requires each robot to generate collision-free trajectories from local observations.<n>Most existing planners generate trajectories from a static snapshot of the local observation.<n>This paper introduces Simulation-Informed Diffusion (SID), a decentralized framework built on constraint-aware diffusion models.
  arXiv  Detail & Related papers  (2026-05-26T21:17:53Z)
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation [66.02142169323521]
  Vision-Language-Action models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence.<n>Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise.<n>We introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution.
  arXiv  Detail & Related papers  (2026-03-30T15:06:41Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• Robotic Grasping and Placement Controlled by EEG-Based Hybrid Visual and Motor Imagery [64.82869118243723]
  We present a framework that integrates EEG-based visual and motor imagery (VI/MI) with robotic control to enable real-time, intention-driven grasping and placement.<n>Motivated by the promise of BCI-driven robotics, this system bridges neural signals with physical control by deploying offline-pretrained decoders in a zero-shot manner.
  arXiv  Detail & Related papers  (2026-03-03T17:41:42Z)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• From Vision to Decision: Neuromorphic Control for Autonomous Navigation and Tracking [10.144707192962068]
  We propose a parsimonious neuromorphic control framework for vision-guided navigation and tracking.<n>Image pixels from an onboard camera are encoded as inputs to dynamic neuronal populations.<n>Inspired by recently proposed mechanistic models of animal cognition and opinion dynamics, the neuromorphic controller provides real-time autonomy with a minimal computational burden.
  arXiv  Detail & Related papers  (2026-02-05T14:09:09Z)
• Mr. Virgil: Learning Multi-robot Visual-range Relative Localization [23.326282078324954]
  Mr. Virgil is an end-to-end learning multi-robot visual-range relative localization framework.<n>It consists of a graph neural network for data association between UWB rangings and visual detections, and a differentiable pose graph optimization (PGO) back-end.
  arXiv  Detail & Related papers  (2025-12-11T11:16:53Z)
• Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning [72.86540018081531]
  Unlabeled motion planning involves assigning a set of robots to target locations while ensuring collision avoidance. This problem forms an essential building block for multi-robot systems in applications such as exploration, surveillance, and transportation. We address this problem in a decentralized setting where each robot knows only the positions of its $k$-nearest robots and $k$-nearest targets.
  arXiv  Detail & Related papers  (2024-09-29T23:57:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.