Paolo Speziali, Mehrdad Asadi, Diederik M. Roijers, Ann Nowe
Traditional route planning systems often fail to address individual user needs, overlooking critical factors such as accessibility, safety, and personal mobility constraints. This research explores innovative approaches to develop adaptive route planning technologies that can dynamically understand and accommodate diverse user preferences without too many explicit questionnaires.By integrating advanced techniques like Inverse Reinforcement Learning, Multi-Objective Reinforcement Learning, and Fuzzy Logic Operators, we are constructing a sophisticated framework that can infer user path preferences through behavioral analysis.The proposed methodology holds significant potential for urban mobility, particularly in contexts like the Amsterdam use case of the PEER Project, where the objective is to provide seamless navigation for all residents, including those with disabilities.This poster was featured at the PEER Project review meeting in Amsterdam, where it was presented to the entire project consortium and external reviewers.
Speziali, P, Asadi, M, Roijers, DM & Nowe, A 2024, 'Adaptive Learning and Optimization in Multi-Objective Route Planning Based on User Preferences', EU Project Review Meeting, Amsterdam, Netherlands, 6/12/24.
Speziali, P., Asadi, M., Roijers, D. M., & Nowe, A. (2024). Adaptive Learning and Optimization in Multi-Objective Route Planning Based on User Preferences. Poster session presented at EU Project Review Meeting, Amsterdam, Netherlands.
@conference{12a6aba2c08146ca81f4ed1c2a80e7ca,
title = "Adaptive Learning and Optimization in Multi-Objective Route Planning Based on User Preferences",
abstract = "Traditional route planning systems often fail to address individual user needs, overlooking critical factors such as accessibility, safety, and personal mobility constraints. This research explores innovative approaches to develop adaptive route planning technologies that can dynamically understand and accommodate diverse user preferences without too many explicit questionnaires.By integrating advanced techniques like Inverse Reinforcement Learning, Multi-Objective Reinforcement Learning, and Fuzzy Logic Operators, we are constructing a sophisticated framework that can infer user path preferences through behavioral analysis.The proposed methodology holds significant potential for urban mobility, particularly in contexts like the Amsterdam use case of the PEER Project, where the objective is to provide seamless navigation for all residents, including those with disabilities.This poster was featured at the PEER Project review meeting in Amsterdam, where it was presented to the entire project consortium and external reviewers.",
author = "Paolo Speziali and Mehrdad Asadi and Roijers, {Diederik M.} and Ann Nowe",
year = "2024",
language = "English",
note = "EU Project Review Meeting ; Conference date: 06-12-2024",
}