用深度学习让机器人优化算法自动调节参数,适应不同通信条件。
Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups

- 将黎曼优化器展开为可微迭代,实现自监督参数调整。
- 在真实场景下,目标函数值优于现有分布式方法。
- 适用于多机器人协同的几何优化,尤其适合异步通信。
现代机器人感知面临大规模几何优化问题,常分布于多个机器人或会话中。现有分布式求解器依赖脆弱的手动调参,且主要针对刚体位姿图。为此,我们提出 DeepCORD,一种基于通用矩阵李群的分布式因子图优化学习增强框架。通过将并行加速的黎曼优化器展开为可微迭代,DeepCORD 学习一种自监督反馈策略,根据优化阶段和通信状态动态调整求解器参数。该方法可在同步与异步通信条件下实现矩阵李群上的自适应分布式优化。在真实 $ m{SE}(3)$ 位姿图优化和 $ m{SL}(4)$ 投影子图配准任务上的大量实验表明,在多数基准和现实运行场景中,我们的方法取得比现有分布式基线更低的目标函数值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。