Using Machine Learning to Take Stay-or-Go Decisions in Data-driven Drone Missions

TL;DR

This paper introduces machine learning techniques to optimize drone decision-making during data-driven missions, significantly reducing mission time by predicting whether to stay or move on based on runtime data analysis.

Contribution

It presents novel ML-based methods, including branch prediction and reinforcement learning, for real-time stay-or-go decisions in drone missions, outperforming existing regression approaches.

Findings

Up to 4.1x improvement in worst-case mission time

Median mission time within 2.7% of perfect knowledge

Consistent outperformance of regression-based methods

Abstract

Drones are becoming indispensable in many application domains. In data-driven missions, besides sensing, the drone must process the collected data at runtime to decide whether additional action must be taken on the spot, before moving to the next point of interest. If processing does not reveal an event or situation that requires such an action, the drone has waited in vain instead of moving to the next point. If, however, the drone starts moving to the next point and it turns out that a follow-up action is needed at the previous point, it must spend time to fly-back. To take this decision, we propose different machine-learning methods based on branch prediction and reinforcement learning. We evaluate these methods for a wide range of scenarios where the probability of event occurrence changes with time. Our results show that the proposed methods consistently outperform the regression-based method proposed in the literature and can significantly improve the worst-case mission time by up to 4.1x. Also, the achieved median mission time is very close, merely up to 2.7% higher, to that of a method with perfect knowledge of the current underlying event probability at each point of interest.