Paolo Speziali, Arno De Greef, Mehrdad Asadi, Willem Röpke, Ann Nowe, Diederik M. Roijers
We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for people with different accessibility requirements and preferences. With this algorithm the user can interact with the system by giving feedback on a route, i.e., the user can say which objective should be further minimized, or conversely can be relaxed. This leads to intuitive user interaction, that is especially effective during early iterations compared to information-gain-based interaction. Furthermore, due to PG-IPRO's iterative nature, the full set of alternative, possibly optimal policies (the Pareto front), is never computed, leading to higher computational efficiency and shorter waiting times for users.
Speziali, P, De Greef, A, Asadi, M, Röpke, W, Nowe, A & Roijers, DM 2026, Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning. in ALA 2026 - Workshop at AAMAS 2026. The 25th International Conference on Autonomous Agents
and Multiagent Systems, Paphos, Cyprus, 25/05/26.
Speziali, P., De Greef, A., Asadi, M., Röpke, W., Nowe, A., & Roijers, D. M. (Accepted/In press). Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning. In ALA 2026 - Workshop at AAMAS 2026
@inproceedings{95058b68e8374ec4aed5d4a933fbbbc3,
title = "Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning",
abstract = "We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for people with different accessibility requirements and preferences. With this algorithm the user can interact with the system by giving feedback on a route, i.e., the user can say which objective should be further minimized, or conversely can be relaxed. This leads to intuitive user interaction, that is especially effective during early iterations compared to information-gain-based interaction. Furthermore, due to PG-IPRO's iterative nature, the full set of alternative, possibly optimal policies (the Pareto front), is never computed, leading to higher computational efficiency and shorter waiting times for users.",
author = "Paolo Speziali and \{De Greef\}, Arno and Mehrdad Asadi and Willem R{\"o}pke and Ann Nowe and Roijers, \{Diederik M.\}",
year = "2026",
month = apr,
day = "15",
language = "English",
booktitle = "ALA 2026 - Workshop at AAMAS 2026",
note = "The 25th International Conference on Autonomous Agents<br/>and Multiagent Systems, AAMAS 2026 ; Conference date: 25-05-2026 Through 29-05-2026",
url = "https://cyprusconferences.org/aamas2026/",
}