A human-in-the-loop, multi-agent GeoAI system is presented for Arctic eco-navigation. The system integrates operational, physical, ecological, and community-related criteria within a unified routing framework. Multiple specialized agents coordinate geospatial data acquisition and preparation, multi-objective route generation, and skyline-based decision support. Ecological criteria explicitly account for exposure to sensitive areas, including Essential Fish Habitat and seal critical habitat. The framework supports safer, more transparent, and socially responsible Arctic navigation by considering ecosystem impacts and potential community burdens while keeping consequential value judgments under human control. Project page and code are publicly available.
Source: https://arxiv.org/abs/2609.09374