Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space.
Yuhang HeIrving FangYiming LiRushi Bhavesh ShahChen FengPublished in: Robotics: Science and Systems (2023)
Keyphrases
- feature space
- high dimensional feature space
- image sequences
- motion estimation
- motion analysis
- embedding space
- metric learning
- multi dimensional scaling
- topological map
- high dimensional
- feature vectors
- optical flow
- motion model
- camera motion
- dot product
- space time
- kernel function
- classification accuracy
- motion capture
- human motion
- image representation
- autonomous navigation
- dimensionality reduction
- principal component analysis
- support vector machine
- motion segmentation
- data points
- input space
- motion parameters
- motion field
- metric space
- mean shift
- feature points
- low dimensional
- hyperplane
- motion detection
- humanoid robot
- spatio temporal
- dissimilarity measure
- geometric structure
- distance function
- riemannian manifolds
- input data
- reinforcement learning
- feature extraction
- computer vision