Robust Evacuation for Multi-Drone Failure in Drone Light Shows

TL;DR

This paper presents a robust multi-drone evacuation algorithm for drone light shows that predicts drone failures and deploys hidden drones to ensure safety and continuity of the show.

Contribution

It introduces a novel deep learning-based evacuation strategy combining Social LSTM with hidden drones for failure mitigation in drone light shows.

Findings

Significantly improves safety by predicting drone trajectories.

Enables rapid recovery using strategically deployed hidden drones.

Reduces risk of cascading collisions during failures.

Abstract

Drone light shows have emerged as a popular form of entertainment in recent years. However, several high-profile incidents involving large-scale drone failures -- where multiple drones simultaneously fall from the sky -- have raised safety and reliability concerns. To ensure robustness, we propose a drone parking algorithm designed specifically for multiple drone failures in drone light shows, aimed at mitigating the risk of cascading collisions by drone evacuation and enabling rapid recovery from failures by leveraging strategically placed hidden drones. Our algorithm integrates a Social LSTM model with attention mechanisms to predict the trajectories of failing drones and compute near-optimal evacuation paths that minimize the likelihood of surviving drones being hit by fallen drones. In the recovery node, our system deploys hidden drones (operating with their LED lights turned off) to replace failed drones so that the drone light show can continue. Our experiments showed that our approach can greatly increase the robustness of a multi-drone system by leveraging deep learning to predict the trajectories of fallen drones.