Rsmdp-Based robust Q-Learning for Optimal Path Planning in a Dynamic Environment.
Yunfei ZhangWeilin LiClarence W. de SilvaPublished in: Int. J. Robotics Autom. (2016)
Keyphrases
- path planning
- dynamic environments
- potential field
- optimal path
- mobile robot
- collision avoidance
- path planning algorithm
- autonomous agents
- collision free
- obstacle avoidance
- path planner
- single agent
- motion planning
- multi robot
- dynamic programming
- indoor environments
- path finding
- robot path planning
- reinforcement learning
- autonomous vehicles
- reinforcement learning algorithms
- autonomous navigation
- trajectory planning
- degrees of freedom
- multi agent
- unmanned aerial vehicles
- unknown environments
- multiple robots
- dynamic and uncertain environments
- real environment
- configuration space
- changing environment
- navigation tasks
- optimal policy
- real time