Loading...
Loading...

Go to the content (press return)

Continuous real time POMCP to find-and-follow people by a humanoid service robot

Author
Goldhoorn, A.; Garrell, A.; Alquezar, R.; Sanfeliu, A.
Type of activity
Presentation of work at congresses
Name of edition
14th IEEE-RAS International Conference on Humanoid Robots
Date of publication
2014
Presentation's date
2014
Book of congress proceedings
Proceedings of the IEEE-RAS 2014 International Conference on Humanoid Robots
First page
741
Last page
747
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/HUMANOIDS.2014.7041445 Open in new window
Repository
http://hdl.handle.net/2117/76344 Open in new window
URL
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7041445 Open in new window
Abstract
This study describes and evaluates two new methods for finding and following people in urban settings using a humanoid service robot: the Continuous Real-time POMCP method, and its improved extension called Adaptive Highest Belief Continuous Real-time POMCP follower. They are able to run in real-time, in large continuous environments. These methods make use of the online search algorithm Partially Observable Monte-Carlo Planning (POMCP), which in contrast to other previous approaches, can plan u...
Citation
Goldhoorn, A., Garrell, A., Alquezar, R., Sanfeliu, A. Continuous real time POMCP to find-and-follow people by a humanoid service robot. A: IEEE-RAS International Conference on Humanoid Robots. "Proceedings of the IEEE-RAS 2014 International Conference on Humanoid Robots". Madrid: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 741-747.
Keywords
humanoid robots, planning (artificial intelligence)
Group of research
VIS - Artificial Vision and Intelligent Systems

Participants