SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations.
Khaled NakhlehMinahil RazaMack TangMatthew AndrewsRinu BoneyIlija HadzicJeongran LeeAtefeh MohajeriKarina PalyutinaPublished in: ICRA (2023)
Keyphrases
- collision avoidance
- actor critic
- path planning
- dynamic environments
- path finding
- mobile robot
- reinforcement learning
- domain independent
- temporal difference
- function approximation
- approximate dynamic programming
- linear program
- policy gradient
- optimal control
- fuzzy neural network
- planning domains
- reinforcement learning algorithms
- heuristic search
- initial state
- dynamic programming
- machine learning