A Drone Scheduling Method for Emergency Power Material Transportation Based on Deep Reinforcement Learning Optimized PSO Algorithm
Problem
Existing drone flight trajectory optimization models cannot meet the needs of emergency power material distribution in mountainous areas after disasters.
Why it matters
Fast material delivery is essential to quickly restoring power systems after disasters.
What the AI did
A TD3PSO algorithm combining TD3 deep reinforcement learning with particle swarm optimization was used in a two-layer dynamic task-solving framework for drone task allocation.
Results
TD3PSO significantly outperformed the conventional algorithm on the Solomon dataset with an improvement of 26.3% (metric truncated in abstract).
Impact
Evidence supports a 26.3% improvement over a conventional algorithm in a dataset experiment, not real-world deployment.
Record
| Venue | Sustainability |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Wenjiao Zai, Junjie Wang, Guohui Li |
| Citations | 13 (OpenAlex, at import time) |
| References | 31 |
| Model or method | TD3PSO (TD3 reinforcement learning with PSO updating) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/su151713127 |
| Open access | gold |
| Keywords | drone scheduling, reinforcement learning, TD3, particle swarm optimization, disaster relief |
Importance rating
significant — thousands to millions affected
Post-disaster power material delivery affects disaster-hit populations, but abstract only reports Solomon dataset experiments, not real-world deployment or scale.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People | 2021 | 48 |
6
|
| 5 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|