SwiftBot: A Decentralized Platform for LLM-Powered Federated Robotic Task Execution

TL;DR

SwiftBot is a decentralized platform that combines large language model-based task decomposition with intelligent resource management, enabling scalable, efficient, and flexible federated robotic task execution without centralized control.

Contribution

It introduces a novel federated platform integrating LLM-based task decomposition with container orchestration over a DHT overlay, addressing limitations of existing systems.

Findings

Achieves 94.3% task decomposition accuracy across diverse tasks.

Reduces task startup latency by up to 5.4 times.

Improves tail latency under high load through federated container migration.

Abstract

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.