Aucamp: An Underwater Camera-Based Multi-Robot Platform with Low-Cost, Distributed, and Robust Localization

2025-06-11

AI Summary

To address the challenges of low-cost, distributed, and robust localization in underwater multi-robot systems, this paper proposes a monocular vision-based cooperative localization and attitude control framework. Methodologically, we introduce a novel image-sharpness-driven monocular ranging model that eliminates reliance on feature matching or prior knowledge of landmarks; design a lightweight distributed state-update protocol integrating visual ranging with underwater dynamic constraints; and develop an explicit dynamics-based robust nonlinear attitude controller enabling sub-second recovery from instability. Experimental results demonstrate decimeter-level global positioning accuracy in complex underwater environments, strong disturbance rejection, and scalable collaborative perception capability. The framework significantly enhances the feasibility and reliability of deploying underwater sensor networks.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper introduces an underwater multi-robot platform, named Aucamp, characterized by cost-effective monocular-camera-based sensing, distributed protocol and robust orientation control for localization. We utilize the clarity feature to measure the distance, present the monocular imaging model, and estimate the position of the target object. We achieve global positioning in our platform by designing a distributed update protocol. The distributed algorithm enables the perception process to simultaneously cover a broader range, and greatly improves the accuracy and robustness of the positioning. Moreover, the explicit dynamics model of the robot in our platform is obtained, based on which, we propose a robust orientation control framework. The control system ensures that the platform maintains a balanced posture for each robot, thereby ensuring the stability of the localization system. The platform can swiftly recover from an forced unstable state to a stable horizontal posture. Additionally, we conduct extensive experiments and application scenarios to evaluate the performance of our platform. The proposed new platform may provide support for extensive marine exploration by underwater sensor networks.

Problem

• Achieving low-cost underwater multi-robot localization using monocular cameras
• Developing a distributed protocol for global positioning in underwater environments
• Ensuring robust orientation control for stable underwater robot postures

Innovation

• Low-cost monocular-camera-based sensing for localization
• Distributed update protocol for global positioning
• Robust orientation control for stable posture