Frequency map enhancement: introducing dynamics into static environment models

Krajnik, Tomas and Pulido Fentanes, Jaime and Santos, Joao and Duckett, Tom (2016) Frequency map enhancement: introducing dynamics into static environment models. In: ICRA Workshop AI for Long-Term Autonomy, 16 May, 2016, Stockholm, Sweden.

Documents
fremen-ailta.pdf
[img]
[Download]
[img]
Preview
PDF
fremen-ailta.pdf - Whole Document

1MB
Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive

Abstract

We present applications of the Frequency Map Enhancement (FreMEn), which improves the performance of mobile robots in long-term scenarios by introducing the notion of dynamics into their (originally static) environment models. Rather than using a fixed probability value, the method models the uncertainty of the elementary environment states by their frequency spectra. This allows to integrate sparse and irregular observations obtained during long-term deployments of mobile robots into memory-efficient spatio-temporal models that reflect mid- and long-term pseudo-periodic environment variations. The frequency-enhanced spatio-temporal models allow to predict the future environment states, which improves the efficiency of mobile robot operation in changing environments. In a series of experiments performed over periods of weeks to years, we demonstrate that the proposed approach improves mobile robot localization, path and task planning, activity recognition and allows for life-long spatio-temporal exploration.

Keywords:mobile robotics, spatio-temporal mapping
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:23261
Deposited On:07 Jun 2016 11:41

Repository Staff Only: item control page