Stochastic mobility prediction of ground vehicles over large spatial regions: a geostatistical approach

This paper describes a stochastic approach to vehicle mobility prediction over large spatial regions [> 5 × 5 (km 2 )]. The main source of uncertainty considered in this work derives from uncertainty in terrain elevation, which arises from sampling (at a finer resolution) a Digital Elevation Mode...

Full description

Saved in:
Bibliographic Details
Published in:Autonomous robots 2017-02, Vol.41 (2), p.311-331
Main Authors: González, Ramón, Jayakumar, Paramsothy, Iagnemma, Karl
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer simulation
Control
Digital Elevation Models
Engineering
Geostatistics
Mechatronics
Monte Carlo simulation
Pattern Recognition and Graphics
Robotics
Robotics and Automation
Uncertainty
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a stochastic approach to vehicle mobility prediction over large spatial regions [> 5 × 5 (km 2 )]. The main source of uncertainty considered in this work derives from uncertainty in terrain elevation, which arises from sampling (at a finer resolution) a Digital Elevation Model. In order to account for such uncertainty, Monte Carlo simulation is employed, leading to a stochastic analysis of vehicle mobility properties. Experiments performed on two real data sets (namely, the Death Valley region and Sahara desert) demonstrate the advantage of stochastic analysis compared to classical deterministic mobility prediction. These results show the computational efficiency of the proposed methodology. The robotic simulator ANVEL has also been used to validate the proposed methodology.
ISSN:0929-5593
1573-7527
DOI:10.1007/s10514-015-9527-z