Model-free Online Motion Adaptation for Optimal Range and Endurance of Multicopters.
Andrea TagliabueXiangyu WuMark W. MuellerPublished in: ICRA (2019)
Keyphrases
- model free
- reinforcement learning
- average reward
- reinforcement learning algorithms
- function approximation
- policy iteration
- image sequences
- motion estimation
- dynamic programming
- optimal control
- artificial neural networks
- least squares
- impedance control
- machine learning
- text classification
- optical flow
- pattern recognition
- feature selection