Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques.
Linda Dotto de MoraesVictor Augusto KichAlisson Henrique KollingJair Augusto BottegaRicardo Bedin GrandoAnselmo Rafael CuklaDaniel Fernando Tello GamarraPublished in: CoRR (2023)
Keyphrases
- mobile robot
- low dimensional
- reinforcement learning
- obstacle avoidance
- indoor environments
- unstructured environments
- unknown environments
- autonomous navigation
- sensor fusion
- robot control
- path planning
- high dimensional
- real robot
- outdoor environments
- navigation tasks
- potential field
- dimensionality reduction
- function approximation
- manifold learning
- high dimensional data
- topological map
- autonomous robots
- mobile robotics
- autonomous vehicles
- temporal difference
- feature space
- principal component analysis
- motion control
- reinforcement learning algorithms
- input space
- multi robot
- collision avoidance
- sensor networks
- multi agent
- euclidean space
- robotic systems
- data points
- nonlinear dimensionality reduction
- machine learning
- linear subspace
- robot navigation
- markov decision processes
- state space
- face recognition
- pairwise distances
- multidimensional scaling
- formation control
- initially unknown
- neural network
- learning algorithm
- learning process
- high resolution
- collision free
- graph embedding
- dynamic programming
- supervised learning
- optimal policy
- model free