Robot execution failure prediction using incomplete data

Authors:
Bhekisipho Twala
Affiliations:
Council for Scientific and Industrial Research, Modelling and Digital Science, Pretoria, South Africa
Venue:
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Year:
2009

Citing 5
Cited 0

Statistical analysis with missing data

Statistical analysis with missing data
Structured induction in expert systems

Structured induction in expert systems
Simplifying decision trees

International Journal of Man-Machine Studies - Special Issue: Knowledge Acquisition for Knowledge-based Systems. Part 5
C4.5: programs for machine learning

C4.5: programs for machine learning
Induction of Decision Trees

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Robust execution of robotic tasks is a difficult learning problem. Whereas correctly functioning sensors' statements are consistent, partially corrupted or otherwise incomplete measurements will lead to inconsistencies within the robot's learning model of the environment. So, methods of prediction (classification) of robot failure detection with erroneous or incomplete data deserve more attention. A probabilistic approach for the classification of incomplete data (which has three versions) is developed and evaluated using five robot execution failures datasets. We show that by improving the estimation of probabilities, our approach offers considerable computational savings and outperforms the other methods.