<![CDATA[Artificial Intelligence (AI) is transforming the transportation systems with autonomous, efficient, and sustainable mobility. The swift transformation of it into a data-driven intelligence rather than a rule-based one has opened new possibilities of interconnecting transportation systems with electrical power networks. This study is a systematic review of AI applications in autonomous and sustainable transportation systems. The major academic databases, such as Scopus, IEEE Xplore, Web of Science, ScienceDirect, and SpringerLink, were searched to retrieve literature that was published in 2015-2025. Peer-reviewed journal and conference papers were screened using a structured screening process, which led to the selection of 35 studies to be included in qualitative synthesis. The review framework was based on thematic analysis in the fields of evolution, applications, methodologies, and energy integration. Results indicate that machine learning and deep learning are the most prevalent in the current transportation AI studies, especially in traffic prediction, autonomous navigation, and infrastructure monitoring. The most developed application areas are traffic management and autonomous vehicle systems, and energy-aware mobility, especially electric vehicle charging optimisation and vehicle-to-grid coordination, is developing quickly but is less advanced. Major obstacles are the data quality constraints, the challenges of model interpretability, the constraints of infrastructure, cybersecurity threats, and disjointed regulatory frameworks, particularly in developing areas. The review confirms the evident shift towards combined transportation-energy intelligence, where AI can facilitate coordinated mobility and power system optimisation. The future directions are federated learning, digital twin systems, explainable AI, and multi-modal intelligent transport systems, which facilitate scalable and sustainable mobility development.]]>
