Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning.
Mirco TheileHongpeng CaoMarco CaccamoAlberto L. Sangiovanni-VincentelliPublished in: CoRR (2024)
Keyphrases
- path planning
- reinforcement learning
- mobile robot
- collision avoidance
- path planning algorithm
- dynamic environments
- matrix valued
- obstacle avoidance
- maximum a posteriori
- motion planning
- indoor environments
- multi robot
- path finding
- degrees of freedom
- trajectory planning
- path planner
- landmark recognition
- dynamic and uncertain environments
- optimal path
- autonomous vehicles
- multi agent
- state space
- multiple robots
- learning algorithm
- robot path planning
- dynamic programming
- optimal policy
- unknown environments
- configuration space
- autonomous navigation
- robot control
- collision free
- topological map
- aerial vehicles
- vector valued