A 3D Q-Learning Algorithm for Offline UAV Path Planning with Priority Shifting Rewards.
Kevin Braathen de CarvalhoHiago B. BatistaIure L. de OliveiraAlexandre Santos BrandãoPublished in: LARS/SBR/WRE (2022)
Keyphrases
- path planning
- learning algorithm
- reinforcement learning
- mobile robot
- path planning algorithm
- unmanned aerial vehicles
- collision avoidance
- obstacle avoidance
- dynamic environments
- dynamic and uncertain environments
- degrees of freedom
- real time
- multi robot
- potential field
- optimal path
- path finding
- motion planning
- aerial vehicles
- indoor environments
- trajectory planning
- multi agent
- autonomous vehicles
- multiple robots
- navigation tasks
- training samples
- path planner
- robot path planning
- state space
- search and rescue
- autonomous navigation
- unknown environments
- markov decision processes