Model-based deep reinforcement learning for data-driven motion control of an under-actuated unmanned surface vehicle: Path following and trajectory tracking.
Zhouhua PengEnrong LiuChao PanHaoliang WangDan WangLu LiuPublished in: J. Frankl. Inst. (2023)
Keyphrases
- motion control
- data driven
- trajectory tracking
- physical constraints
- control law
- control system
- reinforcement learning
- visual servoing
- kinematic model
- robot control
- model free
- real robot
- autonomous robots
- control algorithm
- closed loop
- mobile robot
- path planning
- control scheme
- optimal control
- obstacle avoidance
- adaptive control
- motion planning
- nonlinear systems
- autonomous navigation
- real time
- function approximation
- sliding mode
- three dimensional
- iterative learning
- control strategy
- vision system
- d objects
- state space
- dynamic programming
- variable structure
- fuzzy controller
- dynamic model
- fuzzy logic
- learning algorithm
- desired trajectory
- control method
- fuzzy control
- multi robot
- dynamic environments
- image sequences
- machine learning