SwiftBot: A Decentralized Platform for LLM-Powered Federated Robotic Task Execution
This addresses the challenge of scalable and efficient robotic task execution in federated settings, offering a novel decentralized approach that improves flexibility and performance.
The paper tackles the problem of federated robotic task execution by bridging natural language instructions to distributed robot control without centralized coordination, achieving 94.3% decomposition accuracy and reducing task startup latency by 1.5-5.4x through LLM-based task decomposition and intelligent container orchestration.
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.