Semi-Markovian Planning to Coordinate Aerial and Maritime Medical Evacuation Platforms

TL;DR

This work deploys for the first time the watercraft exchange point by executing a mock patient transfer with a manikin between two HH-60M medical evacuation helicopters and an underway Army Logistic Support Vessel south of the Hawaiian island of Oahu.

Abstract

The transfer of patients between two aircraft using an underway watercraft increases medical evacuation reach and flexibility in maritime environments. The selection of any one of multiple underway watercraft for patient exchange is complicated by participating aircraft utilization history and a participating watercraft position and velocity. The selection problem is modeled as a semi-Markov decision process with an action space including both fixed land and moving watercraft exchange points. Monte Carlo tree search with root parallelization is used to select optimal exchange points and determine aircraft dispatch times. Model parameters are varied in simulation to identify representative scenarios where watercraft exchange points reduce incident response times. We find that an optimal policy with watercraft exchange points outperforms an optimal policy without watercraft exchange points and a greedy policy by 35% and 40%, respectively. In partnership with the United States Army, we deploy for the first time the watercraft exchange point by executing a mock patient transfer with a manikin between two HH-60M medical evacuation helicopters and an underway Army Logistic Support Vessel south of the Hawaiian island of Oahu. Both helicopters were dispatched in accordance with our optimized decision strategy.

Figures (8)

• Figure 1: An evacuation aircraft lowers a patient onto a watercraft while a second aircraft circles nearby. Using watercraft as exchange points between aircraft expedites patient movement and enables evacuation across vast distances.
• Figure 2: Action sequences for three categories of actions: watercraft exchange points, land exchange point, and direct to role three transfers. Time spans $F_i$ are associated with the action sequence for the Kauai aircraft, while time spans $A_i$ are associated with the action sequence for Oahu aircraft. $F_1$ includes the time required to pickup the patient from point of injury.
• Figure 3: Fused reward functions capturing non-linear survivability estimates in blue and linear battlefield clearance requirements in red.
• Figure 4: Casualty magnitude, distribution of patients, patients per evacuation request, and proportion of interisland transfer patients impact on total rewards and incident response time by platoon for various exchange point policies, and ratio of patient transfers moved via watercraft given an optimal watercraft exchange point policy.
• Figure 5: Watercraft exchange point availability impact on incident response times across aircraft cruise speeds and casualty magnitudes. Five aircraft are considered, each with a historic, current, or proposed role in medical evacuation.