Deep Reinforcement Learning of Dexterous Pre-Grasp Manipulation for Human-Like Functional Categorical Grasping.
Dmytro PavlichenkoSven BehnkePublished in: CASE (2023)
Keyphrases
- manipulation tasks
- reinforcement learning
- human robot interaction
- object manipulation
- real robot
- robot control
- robot navigation
- motion planning
- function approximation
- learning algorithm
- humanoid robot
- state space
- service robots
- model free
- reinforcement learning algorithms
- human hand
- multi agent
- robotic systems
- markov decision processes
- categorical data
- temporal difference
- dynamic programming
- haptic feedback
- gesture recognition
- vision system
- human behavior
- learning process
- bdi agents
- machine learning
- robotic arm
- action space
- deep learning
- optimal policy
- human activities