Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Bringing advantages of parallelism and robustness, distributed robotic systems have become an active subject of research since many years. Yet, the progress in that direction with Autonomous Underwater Vehicles (AUVs) has been limited. This project aims at developing a cooperative multi-AUV system for limnological surveying. Current underwater sensing techniques rely on manually deploying sensor probes, a tedious process that provides data at limited resolutions. In contrast, multiple robots equipped with measurement probes and operating in parallel can quickly obtain high-resolution 3D environmental snapshots â essential to capture small-scale, fast-changing phenomena. Several methods exist in literature for such cooperative sensing strategies with aerial and ground robots. However, underwater environments pose additional challenges, primarily with regard to navigation and communication. Considering the complexity and cost of existing solutions for large marine AUVs, a cooperative system with miniature AUVs calls for developing novel techniques. We aim to address the aforementioned challenges within this project. Subsequently, we intend to study how we can exploit in-water cooperation among several AUVs for improving navigation as well as quality and efficiency of the data gathering process.