Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions.
André Yuji YasutomiHideyuki IchiwaraHiroshi ItoHiroki MoriTetsuya OgataPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- data driven
- reinforcement learning
- selective attention
- spatial information
- sufficient conditions
- spatio temporal
- real world conditions
- spatial relations
- visual information
- learning process
- spatial and temporal
- visual attention
- search space
- spatial distribution
- state space
- optimal control
- multi agent
- visual features
- spatial data
- function approximation
- visual perception
- visual processing
- visual scene
- neural network