Temporal and Spatial Memory-Based Deep Reinforcement Learning for Autonomous Navigation of UAV in Complex Environments.
Botong YangHongyan QianPublished in: ISCSIC (2023)
Keyphrases
- complex environments
- autonomous navigation
- reinforcement learning
- path planning
- dynamic environments
- spatial and temporal
- spatio temporal
- autonomous agents
- learning agents
- mobile robot
- space time
- sequential decision tasks
- position estimation
- unmanned aerial vehicles
- state space
- dynamic programming
- ego motion
- image sequences
- three dimensional
- particle filter
- least squares
- motion estimation
- multi agent
- agent learns