Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitives.
Neset Ünver AkmandorHongyu LiGary LvovEric DuselTaskin PadirPublished in: CoRR (2022)
Keyphrases
- dynamic environments
- robot navigation
- reinforcement learning
- mobile robot
- autonomous robots
- reinforcement learning agents
- autonomous agents
- path planning
- motion primitives
- scene understanding
- single agent
- dynamic programming
- autonomous navigation
- topological map
- learning algorithm
- optimal policy
- state space
- real robot
- real environment
- markov decision processes
- human motion
- real time
- neural network