Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge.
Doo Re SongChuanyu YangChristopher McGreavyZhibin LiPublished in: ICARCV (2018)
Keyphrases
- rough terrain
- gradient method
- humanoid robot
- quadruped robot
- legged locomotion
- autonomous navigation
- convergence rate
- negative matrix factorization
- step size
- motion planning
- optimization methods
- multi modal
- visual odometry
- neural network
- mobile robot
- convergence speed
- human motion
- human robot
- object recognition
- image segmentation