Task-motion Planning via Tree-based Q-learning Approach for Robotic Object Displacement in Cluttered Spaces.
Giacomo GolluccioDaniele Di VitoAlessandro MarinoAlessandro BriaGianluca AntonelliPublished in: ICINCO (2021)
Keyphrases
- motion planning
- configuration space
- robotic tasks
- mobile robot
- manipulation tasks
- robotic arm
- object manipulation
- degrees of freedom
- path planning
- robot arm
- potential field
- trajectory planning
- humanoid robot
- autonomous mobile robot
- multi robot
- reinforcement learning
- mechanical systems
- learning algorithm
- robotic systems
- d objects
- nearest neighbor searching
- planning under uncertainty
- belief space
- real robot
- multi modal
- multi agent
- collision free
- robot control
- real time
- action selection
- dynamic environments
- viewpoint
- moving objects
- climbing robot