Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning

2026-04-01

AI Summary

This study addresses the challenge of simultaneously optimizing multiple objectives while accommodating personalized accessibility requirements in path planning—a limitation of conventional approaches. To this end, the authors propose Preference-Guided Iterative Pareto Reference Optimization (PG-IPRO), a method that integrates multi-objective decision theory with an interactive human-in-the-loop feedback mechanism. By dynamically adjusting optimization targets based on users’ real-time preferences over candidate paths, PG-IPRO efficiently guides the search without requiring computation of the full Pareto front. Experimental results demonstrate that PG-IPRO significantly outperforms information-gain-based methods in early iterations, markedly reducing user waiting time, enhancing computational efficiency, and improving overall user experience.

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.

Problem

• accessible route planning
• Pareto optimisation
• user preference
• urban navigation
• interactive optimisation

Innovation

• Preference-guided optimization
• Iterative Pareto optimization
• Accessible route planning
• User-in-the-loop interaction
• Computational efficiency