Proximity-Based Reward System and Reinforcement Learning for Path Planning.
Marc-André BlaisMoulay A. AkhloufiPublished in: ICCAE (2023)
Keyphrases
- path planning
- reinforcement learning
- path planning algorithm
- mobile robot
- dynamic environments
- state space
- multi robot
- collision avoidance
- indoor environments
- path planner
- obstacle avoidance
- optimal path
- model free
- reinforcement learning algorithms
- motion planning
- robot path planning
- optimal policy
- autonomous navigation
- learning algorithm
- degrees of freedom
- dynamic and uncertain environments
- reward function
- multi agent
- multiple robots
- learning agent
- unknown environments
- navigation tasks
- markov decision processes
- autonomous vehicles
- path finding
- control policy
- trajectory planning
- potential field