What question did this study set out to answer?

The aim is to develop a framework that effectively reschedules tasks in UAM vertiports while handling ambiguity in operator requests.

February 12, 2026Open Access

Intent-Driven UAM Scheduling: An Explainable Hybrid AI Framework

Key Points

The aim is to develop a framework that effectively reschedules tasks in UAM vertiports while handling ambiguity in operator requests.
Implemented a hybrid AI framework combining Bayesian networks and Answer Set Programming.
Modelled the scheduling challenge as a resource-constrained project scheduling problem.
Utilized mixed-integer linear programming for generating schedules.
Inferred operator intent through dialogue to address ambiguity.
The framework allows for real-time updates to scheduling based on clarified inputs.
Operator intent is successfully identified, leading to more accurate scheduling.
The system effectively integrates initial plans with newly generated constraints.

Abstract

This paper presents a hybrid AI framework for rescheduling tasks within UAM vertiports. This scheduling challenge is approached as a resource-constrained project scheduling problem (RCPSP), typically solved via mixed-integer linear programming (MILP). However, unlike ideal models, real-world UAM operations are messy, and operator requests are frequently ambiguous. To handle this uncertainty, the proposed framework pairs a Bayesian network to infer intent via dialogue with Answer Set Programming (ASP) to categorize specific ambiguity types. Once the input is clarified, the system generates new MILP constraints and recalculates the schedule, allowing the operator to instantly verify changes against the initial plan.

Bookmark

View Full Paper

Cite This Study

Kim et al. (Tue,) studied this question.

synapsesocial.com/papers/698d6de45be6419ac0d532ef https://doi.org/https://doi.org/10.3390/aerospace13020165

Bookmark

View Full Paper