Organizing planning knowledge for automated vehicles and intelligent transportation systems

Intelligent Transportation Systems (ITS) are crucial for developing fully automated vehicles. While significant progress has been made with advanced driver assistance systems and automation technology, challenges remain, such as improving traffic information, enhancing planning and control systems, and developing better decision-making capabilities. Despite these hurdles, the potential benefits of ITS are so many that its challenges have attracted substantial industrial investment and research groups interested in the automated driving field. In this work, a methodology based on state space search for planning knowledge integration is proposed. The main goal of the proposal is to provide a planning system with the necessary information to perform properly any task related to lateral and longitudinal control, path following, trajectory generation, arbitration and behavior execution by localizing the vehicle with respect to a high-level road plan. To this end, this research compares cutting-edge methods for rapidly finding the K nearest neighbor in relatively high dimensional road plans constructed from the traffic information stored in a high definition map. During the experimentation phase, promising real-time results have been obtained for fast KNN algorithms, leading to a robust tree index-based methodology for decision making in self-driving vehicles combining path planning, trajectory tracking, trajectory creation, knowledge aggregation and precise vehicle control.