Learning to automatically detect features for mobile robots using second-order Hidden Markov Models

TL;DR

This paper introduces a Hidden Markov Model-based method for automatically detecting features from temporal sensor data of mobile robots, demonstrating effectiveness in indoor and outdoor environments.

Contribution

It presents a novel application of second-order Hidden Markov Models for feature detection in mobile robot sensor sequences, improving interpretation accuracy.

Findings

Effective detection of indoor features like doors and intersections

Successful outdoor environment feature identification such as hills and rocks

HMM approach outperforms traditional pattern recognition methods

Abstract

In this paper, we propose a new method based on Hidden Markov Models to interpret temporal sequences of sensor data from mobile robots to automatically detect features. Hidden Markov Models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (such as neural networks) are their ability to model noisy temporal signals of variable length. We show in this paper that this approach is well suited for interpretation of temporal sequences of mobile-robot sensor data. We present two distinct experiments and results: the first one in an indoor environment where a mobile robot learns to detect features like open doors or T-intersections, the second one in an outdoor environment where a different mobile robot has to identify situations like climbing a hill or crossing a rock.