Twin Delayed Deep Deterministic Policy Gradient-Based Target Tracking for Unmanned Aerial Vehicle With Achievement Rewarding and Multistage Training.
Najmaddin Abo MosaliSyariful Syafiq ShamsudinOmar AlfandiRosli OmarNajib AL-FadhaliPublished in: IEEE Access (2022)
Keyphrases
- multistage
- target tracking
- unmanned aerial vehicles
- optimal policy
- kalman filter
- single stage
- data fusion
- finite horizon
- dynamic programming
- multi sensor
- particle filter
- mean shift
- lot sizing
- reinforcement learning
- video camera
- stochastic programming
- data association
- moving target
- object tracking
- visual tracking
- optical flow
- image processing
- real time
- multiscale
- image sequences