Authors: Serhat Sönmez, Matthew J. Rutherford, Kimon P. Valavanis

Published on: February 06, 2024

Impact Score: 8.15

Arxiv code: Arxiv:2402.04418

Summary

• What is new: This research provides an updated comprehensive survey of learning-based algorithms for multirotor UAV navigation and control, focusing on developments since 2015.
• Why this is important: The challenge of safely operating multirotor UAVs in uncertain, dynamically changing environments with external disturbances.
• What the research proposes: A thorough analysis of offline and online learning-based algorithms, specifically machine learning, deep learning, and reinforcement learning, for navigating and controlling multirotor UAVs.
• Results: The paper identifies and categorizes the most effective real-time implementable learning algorithms for multirotor UAVs, explaining their operational efficiency and application scenarios.

Technical Details

Technological frameworks used: Offline and online learning categories, machine learning, deep learning, reinforcement learning

Models used: Data-driven models, parameter identification, object tracking, navigation controllers

Data used: Not explicitly stated

Potential Impact

Civilian and public domain applications including but not limited to surveillance, delivery services, and disaster response could greatly benefit or be disrupted.

Want to implement this idea in a business?

We have generated a startup concept here: AeroLearnTech.