MGRL: Graph neural network based inference in a Markov network with reinforcement learning for visual navigation.
Yi LuYaran ChenDongbin ZhaoDong LiPublished in: Neurocomputing (2021)
Keyphrases
- markov networks
- visual navigation
- reinforcement learning
- bayesian inference
- bayesian networks
- graphical models
- collision avoidance
- maximum likelihood
- neural network
- belief propagation
- first order logic
- posterior probability
- markov random field
- visual odometry
- obstacle avoidance
- probabilistic model
- hidden variables
- higher order
- autonomous vehicles
- document classification
- machine learning
- maximum a posteriori
- mobile robot
- conditional probabilities
- prior information
- directed acyclic graph
- conditional random fields
- dynamic environments
- state space
- dynamic programming
- special case