用深度展开方法实时调整机器人协同优化的参数，提速近10倍且可拓展。
Deep-Unfolded Coordination
- 将优化迭代过程展开为神经网络，学习动态调节协同优化参数。
- 在车辆与四旋翼仿真中，速度提升6.18至9.44倍，轨迹质量相当。
- 适用于大规模系统部署，训练规模达8倍仍保持性能优势。
分布式优化是解决多智能体机器人问题的高可扩展、结构透明方法，但常需针对具体问题进行高度专门化的超参数调优。本文提出 Deep Coordinator，一种基于深度展开的框架，可在求解过程中根据优化器表现动态调整 ADMM-DDP（一种主流机器人任务分布式求解器）的超参数。其架构将固定次数的 ADMM-DDP 迭代展开为带有可学习函数的神经网络，层间映射优化器状态至下一阶段超参数。据我们所知，Deep Coordinator 是首个在求解时自适应非凸优化器惩罚参数的深度展开框架；我们发现主流监督学习在训练此类模型时可能导致退化解，并提出无监督学习方案。在车队与四旋翼的仿真中，Deep Coordinator 生成的轨迹质量与传统求解器相当，但速度提升 6.18–9.44 倍。此外，该方法在部署到比训练规模大 8 倍的系统时仍保持性能优势。
原文摘要 · Abstract (English)
Distributed optimization is a highly scalable and structurally transparent technique to solve multi-agent robotics problems; however, such methods often suffer from the need for highly-specialized, problem-specific hyperparameter tunings. In this work, we propose Deep Coordinator, a deep-unfolding framework that learns to dynamically adjust the hyperparameters of ADMM-DDP, a popular distributed solver for robotics tasks, at solve-time in response to optimizer performance. Our architecture consists of unrolling a fixed number of ADMM-DDP iterations into a neural network with learnable functions between layers mapping the optimizer state to the next hyperparameters. To the best of our knowledge, Deep Coordinator is the first deep-unfolding framework to adapt the penalty parameters of a non-convex optimizer at solve-time; we show that the mainstream supervised approach can yield degenerate solutions when training such models, and propose an unsupervised learning scheme. On simulations with fleets of cars and quadrotors, Deep Coordinator produces trajectories of comparable quality 6.18-9.44x faster than conventional solvers. Furthermore, Deep Coordinator retains its performance benefits when deployed to systems up to 8x larger than trained on.
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。