让机器人无需中心控制，用大模型分解任务并智能调度资源。
SwiftBot: A Decentralized Platform for LLM-Powered Federated Robotic Task Execution
- 用大模型解析自然语言指令，自动拆解任务
- 任务启动延迟降低1.5至5.4倍，训练延迟降1.4至2.5倍
- 适合大规模分布式机器人协作场景
联邦式机器人任务执行系统需在异构边缘设备间将自然语言指令映射为分布式机器人控制，并高效管理计算资源，而无需中心化协调。现有方法存在三大局限：依赖人工编码的固定规划器需大量领域工程、中心化协调违背联邦协作理念、静态资源分配无法动态共享容器。本文提出SwiftBot，一个融合大模型任务分解与基于DHT覆盖网络的智能容器编排的联邦任务执行平台，使机器人可在无中心控制下协同执行任务。实验显示，SwiftBot在多样化任务上达到94.3%的任务分解准确率，任务启动延迟降低1.5–5.4倍，平均训练延迟降低1.4–2.5倍，高负载下尾部延迟改善1.2–4.7倍，得益于联邦预热容器迁移机制。多媒体任务评估验证了语义理解与联邦资源管理联合设计，在机器人任务控制中实现了灵活性与效率的统一。
原文摘要 · Abstract (English)
Federated robotic task execution systems require bridging natural language instructions to distributed robot control while efficiently managing computational resources across heterogeneous edge devices without centralized coordination. Existing approaches face three limitations: rigid hand-coded planners requiring extensive domain engineering, centralized coordination that contradicts federated collaboration as robots scale, and static resource allocation failing to share containers across robots when workloads shift dynamically. We present SwiftBot, a federated task execution platform that integrates LLM-based task decomposition with intelligent container orchestration over a DHT overlay, enabling robots to collaboratively execute tasks without centralized control. SwiftBot achieves 94.3% decomposition accuracy across diverse tasks, reduces task startup latency by 1.5-5.4x and average training latency by 1.4-2.5x, and improves tail latency by 1.2-4.7x under high load through federated warm container migration. Evaluation on multimedia tasks validates that co-designing semantic understanding and federated resource management enables both flexibility and efficiency for robotic task control.
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。