MochiSwarm: A testbed for robotic blimps in realistic environments

2025-03-05

AI Summary

Autonomous operation of aerial robots—particularly airships—in real-world environments remains challenging under infrastructure-free conditions (i.e., without GPS or motion-capture systems), hindering scalable deployment for logistics delivery and surveillance. Method: This paper introduces the first lightweight, modular, fully autonomous, open-source airship swarm testbed. Its software stack integrates embedded visual servoing, onboard SLAM-compatible perception, distributed communication, and multi-agent cooperative control, enabling plug-and-play sensing and reconfigurable actuation (e.g., visual-servoed differential drive) for infrastructure-free, scene-adaptive autonomy. Contribution/Results: We experimentally validate end-to-end pick-and-deliver operations with a 12-airship swarm in unstructured real-world environments. The platform significantly improves scalability, robustness, and full autonomy while enabling low-power, wide-area aerial robot swarm deployment—a novel paradigm for infrastructure-agnostic aerial robotics.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Vision for Robotics & Autonomous Driving
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Testing aerial robots in tasks such as pickup-and-delivery and surveillance significantly benefits from high energy efficiency and scalability of the deployed robotic system. This paper presents MochiSwarm, an open-source testbed of light-weight robotic blimps, ready for multi-robot operation without external localization. We introduce the system design in hardware, software, and perception, which capitalizes on modularity, low cost, and light weight. The hardware allows for rapid modification, which enables the integration of additional sensors to enhance autonomy for different scenarios. The software framework supports different actuation models and communication between the base station and multiple blimps. The detachable perception module allows independent blimps to perform tasks that involve detection and autonomous actuation. We showcase a differential-drive module as an example, of which the autonomy is enabled by visual servoing using the perception module. A case study of pickup-and-delivery tasks with up to 12 blimps highlights the autonomy of the MochiSwarm without external infrastructures.

Problem

• Develops MochiSwarm for testing robotic blimps in realistic environments.
• Enables multi-robot operations without external localization support.
• Supports modular, low-cost, lightweight designs for enhanced autonomy.

Innovation

• Open-source testbed for lightweight robotic blimps
• Modular hardware for rapid sensor integration
• Detachable perception module enabling autonomous tasks