The Simulation of Adaptive Coverage Path Planning Policy for an Underwater Desilting Robot Using Deep Reinforcement Learning.
Y. ZhaoPeichen SunChang Gyoon LimPublished in: RiTA (2022)
Keyphrases
- path planning
- mobile robot
- real robot
- reinforcement learning
- multi robot
- obstacle avoidance
- path planning algorithm
- optimal policy
- dynamic environments
- collision avoidance
- path planner
- motion planning
- trajectory planning
- action selection
- robot path planning
- collision free
- optimal path
- autonomous vehicles
- multiple robots
- indoor environments
- navigation tasks
- degrees of freedom
- potential field
- state space
- dynamic and uncertain environments
- autonomous navigation
- path finding
- robot soccer
- unknown environments
- landmark recognition
- search and rescue
- markov decision processes
- aerial vehicles
- autonomous robots
- action space
- partially observable markov decision processes
- reward function
- policy gradient
- mobile robotics
- biologically inspired
- dead ends
- configuration space