Multi-UAVs end-to-end Distributed Trajectory Generation over Point Cloud Data

TL;DR

This paper presents an end-to-end neural network-based trajectory planning method for multi-UAV systems that efficiently generates collision-free paths in complex environments using point cloud data, with high success rates in simulations.

Contribution

The work introduces a novel neural network architecture for multi-UAV trajectory generation that integrates collision constraints and enables communication among agents.

Findings

Collision avoidance success rate of 85-100% in simulations.

Effective handling of environments with up to 25 robots and 25% obstacle density.

Saliency map method provides qualitative insights into point cloud data.

Abstract

This paper introduces an end-to-end trajectory planning algorithm tailored for multi-UAV systems that generates collision-free trajectories in environments populated with both static and dynamic obstacles, leveraging point cloud data. Our approach consists of a 2-fork neural network fed with sensing and localization data, able to communicate intermediate learned features among the agents. One network branch crafts an initial collision-free trajectory estimate, while the other devises a neural collision constraint for subsequent optimization, ensuring trajectory continuity and adherence to physicalactuation limits. Extensive simulations in challenging cluttered environments, involving up to 25 robots and 25% obstacle density, show a collision avoidance success rate in the range of 100 -- 85%. Finally, we introduce a saliency map computation method acting on the point cloud data, offering qualitative insights into our methodology.