Switchable constraints vs. max-mixture models vs. RRR - A comparison of three approaches to robust pose graph SLAM.
Niko SünderhaufPeter ProtzelPublished in: ICRA (2013)
Keyphrases
- mixture model
- gaussian mixture model
- probabilistic model
- density estimation
- expectation maximization
- em algorithm
- generative model
- unsupervised learning
- mobile robot
- maximum likelihood
- model selection
- pose estimation
- mixture modeling
- feature extraction
- data association
- partial occlusion
- missing data
- d objects
- feature vectors