Blind Hexapod Locomotion in Complex Terrain with Gait Adaptation Using Deep Reinforcement Learning and Classification.
Teymur AzayevKarel ZimmermanPublished in: J. Intell. Robotic Syst. (2020)
Keyphrases
- legged robots
- reinforcement learning
- quadruped robot
- classification accuracy
- supervised learning
- feature extraction
- support vector
- machine learning
- real robot
- training set
- multiresolution
- mobile robot
- learning algorithm
- image classification
- text classification
- gait patterns
- function approximation
- pattern classification
- real world
- rough terrain
- inverted pendulum
- feature selection
- optimal policy
- training data
- markov decision processes
- recognition rate
- decision trees
- support vector machine
- state space
- pattern recognition
- feature space