Local Path Planning with Turnabouts for Mobile Robot by Deep Deterministic Policy Gradient.
Tomoaki NakamuraMasato KobayashiNaoki MotoiPublished in: ICM (2023)
Keyphrases
- path planning
- mobile robot
- policy gradient
- obstacle avoidance
- dynamic environments
- collision avoidance
- indoor environments
- path planning algorithm
- function approximation
- autonomous robots
- reinforcement learning
- gradient method
- multi robot
- single agent
- path planner
- optimal path
- reinforcement learning algorithms
- path finding
- motion planning
- potential field
- autonomous navigation
- average reward
- optimal control
- approximation methods
- variance reduction
- multiple robots
- robotic systems
- optimal policy
- degrees of freedom
- partially observable markov decision processes
- collision free
- reinforcement learning methods
- markov decision processes