Deep reinforcement learning-based model-free path planning and collision avoidance for UAVs: A soft actor-critic with hindsight experience replay approach.
Myoung-Hoon LeeJun MoonPublished in: ICT Express (2023)
Keyphrases
- path planning
- collision avoidance
- model free
- actor critic
- reinforcement learning
- reinforcement learning algorithms
- temporal difference
- policy iteration
- unmanned aerial vehicles
- rl algorithms
- mobile robot
- function approximation
- aerial vehicles
- dynamic environments
- action selection
- policy gradient
- multi robot
- reinforcement learning methods
- average reward
- obstacle avoidance
- motion planning
- path finding
- multi agent
- degrees of freedom
- optimal control
- state space
- optimal policy
- optimal path
- collision free
- supervised learning
- artificial neural networks
- autonomous vehicles
- learning problems
- markov decision processes
- function approximators
- autonomous robots