Scheduling for Urban Air Mobility using Safe Learning

TL;DR

This paper presents a safe, learning-based scheduling approach for Urban Air Mobility that guarantees hard deadlines and minimizes soft deadline misses using MDP modeling, safe exploration, and Monte Carlo Tree Search.

Contribution

It introduces an online safe scheduler for UAM that combines model-based learning with MCTS to optimize scheduling under uncertainty, ensuring deadline guarantees.

Findings

The proposed scheduler guarantees hard deadlines are never missed.

It minimizes the average cost of missing soft deadlines.

The approach outperforms traditional Value Iteration and random MCTS methods.

Abstract

This work considers the scheduling problem for Urban Air Mobility (UAM) vehicles travelling between origin-destination pairs with both hard and soft trip deadlines. Each route is described by a discrete probability distribution over trip completion times (or delay) and over inter-arrival times of requests (or demand) for the route along with a fixed hard or soft deadline. Soft deadlines carry a cost that is incurred when the deadline is missed. An online, safe scheduler is developed that ensures that hard deadlines are never missed, and that average cost of missing soft deadlines is minimized. The system is modelled as a Markov Decision Process (MDP) and safe model-based learning is used to find the probabilistic distributions over route delays and demand. Monte Carlo Tree Search (MCTS) Earliest Deadline First (EDF) is used to safely explore the learned models in an online fashion and develop a near-optimal non-preemptive scheduling policy. These results are compared with Value Iteration (VI) and MCTS (Random) scheduling solutions.