Adaptive Coverage Path Planning Policy for a Cleaning Robot with Deep Reinforcement Learning.
Dong-Ki NohWooju LeeHyoung-Rock KimIl-Soo ChoIn-Bo ShimSeungMin BaekPublished in: ICCE (2022)
Keyphrases
- path planning
- reinforcement learning
- mobile robot
- path planning algorithm
- optimal policy
- obstacle avoidance
- multi robot
- collision avoidance
- dynamic environments
- policy search
- motion planning
- path planner
- potential field
- navigation tasks
- trajectory planning
- autonomous navigation
- real robot
- unknown environments
- action selection
- multiple robots
- path finding
- dynamic and uncertain environments
- markov decision processes
- indoor environments
- robot path planning
- policy gradient
- collision free
- action space
- search and rescue
- dead ends
- degrees of freedom
- autonomous vehicles
- robot control
- optimal path
- agent learns
- landmark recognition
- reward function
- robotic systems
- outdoor environments
- state space
- agent receives