Scalable Networked Feature Selection with Randomized Algorithm for Robot Navigation

We address the problem of sparse selection of visual features for localizing a team of robots navigating in an unknown environment, where robots can exchange relative position measurements with neighbors. We select a set of the most informative features by anticipating their importance in robots localization by simulating trajectories of robots over a prediction horizon. Through theoretical proofs, we establish a crucial connection between graph Laplacian and the importance of features. We leverage a scalable randomized algorithm for sparse sums of positive semidefinite matrices to efficiently select a set of the most informative features.

Authors

• Vivek Pandey
• Arash Amini
• Guangyi Liu 0004
• Ufuk Topcu
• Qiyu Sun
• Kostas Daniilidis
• Nader Motee

Keywords

• Location awareness
• Visualization
• Accuracy
• Uncertainty
• Navigation
• Prediction algorithms
• Feature extraction
• Robot localization
• Trajectory
• Sparse matrices
• Robot Navigation
• Feature Information
• Relative Measure
• Selection Problem
• Prediction Horizon
• Graph Laplacian
• Unknown Environment
• Sum Of Matrices
• Swarm Robotics
• Performance Measures
• Random Sampling
• Computational Complexity
• Covariance Matrix
• Information Content
• Localization Accuracy
• Edge Weights
• Position Vector
• Visual Model
• Fisher Information
• Position Estimation
• Simultaneous Localization And Mapping
• Feature Selection Algorithm
• Communication Graph
• Position Uncertainty
• Feature Selection Problem
• Sparse Feature
• Uniform Random Sampling
• Robot Motion
• Mean Vector