{"ID":2850086,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22740","arxiv_id":"2510.22740","title":"Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM","abstract":"We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly non-convex optimization objective, requiring repeated solving of normal equations, which often converge to local minima and thus produce suboptimal estimates. We propose a scalable, outlier-robust distributed planar PGO framework using Multi-Agent Reinforcement Learning (MARL). We cast distributed PGO as a partially observable Markov game defined on local pose-graphs, where each action refines a single edge's pose estimate. A graph partitioner decomposes the global pose graph, and each robot runs a recurrent edge-conditioned Graph Neural Network (GNN) encoder with adaptive edge-gating to denoise noisy edges. Robots sequentially refine poses through a hybrid policy that utilizes prior action memory and graph embeddings. After local graph correction, a consensus scheme reconciles inter-robot disagreements to produce a globally consistent estimate. Our extensive evaluations on a comprehensive suite of synthetic and real-world datasets demonstrate that our learned MARL-based actors reduce the global objective by an average of 37.5% more than the state-of-the-art distributed PGO framework, while enhancing inference efficiency by at least 6X. We also demonstrate that actor replication allows a single learned policy to scale effortlessly to substantially larger robot teams without any retraining. Code is publicly available at https://github.com/herolab-uga/policies-over-poses.","short_abstract":"We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly non-convex optimization objective, requiring repeated solving of normal equations, w...","url_abs":"https://arxiv.org/abs/2510.22740","url_pdf":"https://arxiv.org/pdf/2510.22740v1","authors":"[\"Sai Krishna Ghanta\",\"Ramviyas Parasuraman\"]","published":"2025-10-26T16:21:24Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Graph Neural Network\",\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":607765,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850086,"paper_url":"https://arxiv.org/abs/2510.22740","paper_title":"Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM","repo_url":"https://github.com/herolab-uga/policies-over-poses","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}