Urban mobility is a central challenge for sustainable and inclusive cities, as climate change, congestion, and spatial inequality expose mobility patterns as expressions of deeper social and spatial structures. Inclusive urban mobility examines whether transport systems equitably support the everyday movements and accessibility needs of historically marginalized and underserved populations. The integration of AI with geographic information science, together with multimodal geospatial data fusion, provides powerful tools to diagnose and address these disparities by combining heterogeneous sources such as satellite imagery, GPS traces, transit records, volunteered geographic information, and social sensing into scalable, high-resolution urban mobility analytics. The main aim of this paper is presenting a systematical review of recent GeoAI studies that fuse multiple geospatial modalities for key tasks such as accessibility mapping, demand forecasting, and origin–destination flow prediction, with particular emphasis on inclusive and equity-oriented applications. The survey synthesizes methodological trends across data-, feature-, and decision-level fusion, highlights the growing use of deep learning architectures, and examines emerging techniques including knowledge graphs, federated learning, and explainable AI shape equity-relevant insights in diverse urban contexts. Building on this synthesis, the review identifies persistent gaps in population coverage, multimodal integration, equity optimization, explainability, validation, and governance that constrain the inclusiveness and robustness of current GeoAI practices, and proposes a structured research roadmap linking these gaps to actual methodological and governance directions—such as equity-aware loss functions, adaptive fusion pipelines, participatory and human-in-the-loop workflows, and urban data trusts—to better align multimodal GeoAI with the goals of inclusive, just, and sustainable urban mobility systems.