Memory-Enhanced Twin Delayed Deep Deterministic Policy Gradient (ME-TD3)-Based Unmanned Combat Aerial Vehicle Trajectory Planning for Avoiding Radar Detection Threats in Dynamic and Unknown Environments.
Jiantao LiTianxian ZhangKai LiuPublished in: Remote. Sens. (2023)
Keyphrases
- path planning
- trajectory planning
- unknown environments
- aerial vehicles
- obstacle avoidance
- dynamic environments
- mobile robot
- motion planning
- policy gradient
- unmanned aerial vehicles
- optimal path
- reinforcement learning algorithms
- reinforcement learning
- multi robot
- degrees of freedom
- single agent
- temporal difference
- object recognition