Abstract

The traditional navigation systems focus primarily on finding the shortest route, ignoring many things such as weather, traffic, accidents, parking and preferences of travelers. The recent work uses for the purpose of personalized trip planning various state-of-the-art technologies, such as machine learning, predictive analytics, NLP, LLMs and real-time data. The existing systems, however, are all built on a single task, rely on external APIs, and often do not provide any privacy considerations or validation of the real-world. This paper provides review of eight studies published in 2023-2026, identifies six research gaps. The paper proposes design of an AI-based smart travel assistant that is capable of taking into account external factors for the purpose of effective decision-making. The designed system features a data integration layer, a prediction engine, a multi-criteria decision processor and a module providing explanations of decision made. An implementation plan and evaluation process are presented. This paper contributes to literature by providing a grounded design of such a system and discussing research agenda for further study of the topic. The proposed system aims to improve travel efficiency by providing adaptive route recommendations based on changing real-time conditions and individual traveler preferences. Future work will focus on prototype implementation, real-world testing, and evaluating the system’s accuracy, reliability, and personalization.

Keywords

How to Cite This Article

Rights