Fast Computational Methods for Visually Guided Robots

This paper proposes numerical algorithms for reducing the computational cost of semi-supervised and active learning procedures for visually guided mobile robots from O(M 3 to O(M), while reducing the storage requirements from M 2 to M. This reduction in cost is essential for real-time interaction with mobile robots. The considerable speed ups are achieved using Krylov subspace methods and the fast Gauss transform. Although these state-of-the-art numerical algorithms are known, their application to semi-supervised learning, active learning and mobile robotics is new and should be of interest and great value to the robotics community. We apply our fast algorithms to interactive object recognition on Sony’s ERS-7 Aibo. We provide comparisons that clearly demonstrate remarkable improvements in computational speed.

Authors

• Maryam Mahdaviani
• Nando de Freitas
• Bob Fraser
• Firas Hamze

Keywords

• Mobile robots
• Humans
• Computational efficiency
• Gaussian processes
• Semisupervised learning
• Computer science
• Costs
• Uninterruptible power systems
• Object recognition
• Portable computers
• Active Learning
• Mobile Robot
• Semi-supervised Learning
• Storage Requirements
• Krylov Subspace
• Linear System
• Taylor Series
• Error Function
• Taylor Expansion
• Orthonormal
• Clusters Of Points
• Least Squares Problem
• Semi-supervised Learning Algorithm
• Visually guided mobile robots
• interactive robots
• learning
• Krylov subspace methods
• fast Gauss transform