Deep Reinforcement Learning With Action Masking for Differential-Drive Robot Navigation Using Low-Cost Sensors.
Konstantinos TsampazisManos KirtasPavlos TosidisNikolaos PassalisAnastasios TefasPublished in: MLSP (2023)
Keyphrases
- robot navigation
- reinforcement learning
- continuous state
- low cost sensors
- action selection
- autonomous mobile robot
- autonomous robots
- action space
- low cost
- sensor data
- state action
- landmark recognition
- state space
- markov decision processes
- initially unknown
- scene understanding
- topological map
- human visual system
- partially observable
- mobile platform
- vision system
- mobile robot