Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-based Robot Navigation.
Thomas ChaffreJulien MorasAdrien Chan-Hon-TongJulien MarzatPublished in: ICINCO (2020)
Keyphrases
- robot navigation
- autonomous mobile robot
- autonomous robots
- reinforcement learning
- initially unknown
- continuous state
- real time stereo
- map building
- topological map
- robot localization
- landmark recognition
- mobile robot
- real robot
- real environment
- real time
- model free
- scene understanding
- transfer learning
- learning algorithm
- partially observable
- previously learned
- state space
- object recognition
- machine learning