DocumentCode :
580789
Title :
Creating and using probabilistic costmaps from vehicle experience
Author :
Murphy, Liz ; Martin, Steven ; Corke, Peter
Author_Institution :
CyPhy Lab., Queensland Univ. of Technol., Brisbane, QLD, Australia
fYear :
2012
fDate :
7-12 Oct. 2012
Firstpage :
4689
Lastpage :
4694
Abstract :
Probabilistic costmaps provide a means of maintaining a representation of the uncertainty in the robot´s model of the environment; in contrast to the ubiquitous assumptive costmaps which abstract this uncertainty away. In this work we show for the first time how probabilistic costmaps can be learned in a self-supervised manner by a robot navigating in an outdoor environment. Traversability estimates garnered from onboard sensing are used in conjunction with colour information from a-priori available overhead imagery to extrapolate the traversability of locations previously traversed by the robot to a much larger area. Gaussian processes are used to predict the traversability at unknown locations in the 2D map, and a number of techniques to deal with heteroscedastic noise and varying confidence in the training data are evaluated. A prior technique to exploit the probabilistic nature of the map in a probabilistic heuristic for A* search demonstrates that planning over these maps can also be done efficiently.
Keywords :
Gaussian processes; learning (artificial intelligence); mobile robots; path planning; road vehicles; search problems; 2D map; A* search; Gaussian processes; colour information; heteroscedastic noise; locations traversability; outdoor environment; overhead imagery; probabilistic costmaps; probabilistic nature; robot model; robot navigation; self-supervised learned manner; training data; ubiquitous assumptive costmaps; vehicle experience; Data models; Mathematical model; Noise; Planning; Probabilistic logic; Robots; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on
Conference_Location :
Vilamoura
ISSN :
2153-0858
Print_ISBN :
978-1-4673-1737-5
Type :
conf
DOI :
10.1109/IROS.2012.6386118
Filename :
6386118
Link To Document :
بازگشت