Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups

Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups

|Authors: Jaeho Shin, Maani Ghaffari, Yulun Tian

|Venue: arXiv preprint | Year: 2026

|arXiv: 2607.08735v1

Abstract

Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, existing distributed solvers often depend on brittle hand tuning and primarily target rigid body pose graphs. To address this, we present DeepCORD, a learning-augmented framework for distributed factor graph optimization on general matrix Lie groups. By unfolding a parallel and accelerated Riemannian optimizer into differentiable iterations, DeepCORD learns a self-supervised feedback policy that dynamically adapts solver parameters according to the optimization phase and communication status. The resulting method enables adaptive distributed optimization over matrix Lie groups under both synchronous and asynchronous communication regimes. Extensive experiments on real-world $\mathrm{SE}$(3) pose graph optimization and $\mathrm{SL}$(4) projective submap alignment show that our method achieves lower objective values than existing distributed baselines on most benchmarks across realistic operating scenarios.

Key Contributions

• Modern robotic perception increasingly involves large-scale geometric optimization problems distr…
• However, existing distributed solvers often depend on brittle hand tuning and primarily target ri…
• To address this, we present DeepCORD, a learning-augmented framework for distributed factor graph…
• By unfolding a parallel and accelerated Riemannian optimizer into differentiable iterations, Deep…
• The resulting method enables adaptive distributed optimization over matrix Lie groups under both …

Topics

• vision
• reinforcement-learning
• benchmark

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Shin2026_260708735v1,
  title     = {Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups},
  author    = {Jaeho Shin and Maani Ghaffari and Yulun Tian},
  year      = {2026},
  eprint    = {2607.08735v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2607.08735v1}
}