Summary of Deep Uav Path Planning with Assured Connectivity in Dense Urban Setting, by Jiyong Oh et al.
Deep UAV Path Planning with Assured Connectivity in Dense Urban Setting
by Jiyong Oh, Syed M. Raza, Lusungu J. Mwasinga, Moonseong Kim, Hyunseung Choo
First submitted to arxiv on: 21 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Robotics (cs.RO); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a Deep Reinforcement Learning (DRL) framework for Unmanned Ariel Vehicle (UAV) path planning, addressing limitations in operator-controlled flights and manual static configurations. The proposed DUPAC (Deep UAV Path And Connectivity) framework determines the best route from a defined source to destination based on distance and signal quality, ensuring assured connectivity during flight. Evaluation of DUPAC under simulated urban scenarios using the Unity framework shows a 2% increase in path similarity to baseline methods while achieving an average 9% better connection quality throughout the flight. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps UAV services with 5G connectivity become more practical and efficient. Right now, people control UAV flights or set them up statically, which limits how many people can use this service. Some services rely on good cell phone reception while flying, but keeping that connection is hard in specific flight paths. The researchers created a new way to plan the best route for a UAV using artificial intelligence (AI). They tested it in virtual scenarios and found that their method works well, even slightly better than other methods, and only takes 2% more time. |
Keywords
» Artificial intelligence » Reinforcement learning
