Multi-UAV simultaneous target assignment and path planning based on deep reinforcement learning in dynamic multiple obstacles environments

Xiaoran Kong, Yatong Zhou, Zhe Li, Shaohai Wang · 2024

Read Multi-UAV simultaneous target assignment and path planning based on deep reinforcement learning in dynamic multiple obstacles environments by Xiaoran Kong, Yatong Zhou, Zhe Li, Shaohai Wang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10839049.txt.

Description

Xiaoran Kong, Yatong Zhou, Zhe Li, and Shaohai Wang proposed in 2024 a deep reinforcement learning method that assigns targets and plans paths for a team of drones at once. Both jobs must be solved together in settings with moving obstacles and partial views. They framed the task as a partially observable decision process.

A target assignment network was added to a strong policy algorithm. At each step, the network assigns targets, the policy plans a path for that assignment, and its feedback trains the assignment network in turn. In three-dimensional scenes with many moving obstacles, the system gave complete, well-matched assignments and collision-free paths. It beat prior methods on target completion and adapted better to complex scenes.

Catalog record

CREATORXiaoran Kong, Yatong Zhou, Zhe Li, Shaohai Wang
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE46 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10839049

Browse the full library · About the Tower of Babel