QuaDUE-CCM: Interpretable Distributional Reinforcement Learning using Uncertain Contraction Metrics for Precise Quadrotor Trajectory Tracking.
Yanran WangJames O'KeeffeQiuchen QianDavid E. BoylePublished in: CoRL (2022)
Keyphrases
- trajectory tracking
- reinforcement learning
- closed loop
- dynamic model
- bi directional
- iterative learning
- control system
- physical constraints
- control law
- function approximation
- control method
- visual servoing
- iterative learning control
- state space
- sliding mode
- learning algorithm
- machine learning
- model free
- robot control
- dynamical systems
- control scheme
- optimal control
- learning process
- computer vision
- neural network