多机器人协同建图，用分布式高斯过程实现全局感知。
A Distributed Gaussian Process Model for Multi-Robot Mapping
- 基于稀疏高斯过程分解结构，支持分布式异步训练。
- 性能接近集中式模型，动态连接下仍稳定运行。
- 适合通信不畅、持续学习的多机器人场景。
我们提出DistGP：一种多机器人协同学习全局函数的方法，仅依赖本地经验与计算。采用具有分布式结构分解的稀疏高斯过程（GP）模型，通过高斯信念传播（GBP）实现分布式训练。该环状模型优于树形高斯过程（Tree-Structured GPs），可在线训练且适应动态连接。实验表明，分布式异步训练虽收敛较慢，但性能可达集中式批处理模型水平。与分布式神经网络优化器DiNNO对比，DistGP精度更高，对稀疏通信更鲁棒，具备持续学习能力。
原文摘要 · Abstract (English)
We propose DistGP: a multi-robot learning method for collaborative learning of a global function using only local experience and computation. We utilise a sparse Gaussian process (GP) model with a factorisation that mirrors the multi-robot structure of the task, and admits distributed training via Gaussian belief propagation (GBP). Our loopy model outperforms Tree-Structured GPs \cite{bui2014tree} and can be trained online and in settings with dynamic connectivity. We show that such distributed, asynchronous training can reach the same performance as a centralised, batch-trained model, albeit with slower convergence. Last, we compare to DiNNO \cite{yu2022dinno}, a distributed neural network (NN) optimiser, and find DistGP achieves superior accuracy, is more robust to sparse communication and is better able to learn continually.
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。