Abstract
This paper presents a practical real-time visual navigation system, including a vision system, a particle filter (PF) based localization system, and a path planning system, for humanoid robots in an indoor environment. A neural network (NN) converter system is used to solve the image distortion problem. The monocular vision system detects objects of interest in the scene, calculating their position in the image, and converting the position in the image to real world coordinates. The PF localization system estimates the current position by the robot's motion model and corrects the estimated position by using feedback from the data gathered by the vision system. The path planning system determines the next motion based on the result of the localization system. This paper uses a tree-like path planning method which not only guides the robot to the destination but also avoids obstacles at the same time. The navigation method allows a user to assign several different target destinations to the robot simultaneously. The proposed method is implemented on a humanoid robot "ROBOTIS DARwIn-OP", an open platform humanoid robot. The effectiveness of the system is demonstrated in an empirical evaluation.
Original language | English |
---|---|
Title of host publication | Innovation for Applied Science and Technology |
Pages | 1914-1918 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 2013 Feb 20 |
Event | 2nd International Conference on Engineering and Technology Innovation 2012, ICETI 2012 - Kaohsiung, Taiwan Duration: 2012 Nov 2 → 2012 Nov 6 |
Publication series
Name | Applied Mechanics and Materials |
---|---|
Volume | 284-287 |
ISSN (Print) | 1660-9336 |
ISSN (Electronic) | 1662-7482 |
Other
Other | 2nd International Conference on Engineering and Technology Innovation 2012, ICETI 2012 |
---|---|
Country | Taiwan |
City | Kaohsiung |
Period | 12/11/2 → 12/11/6 |
Fingerprint
Keywords
- Humanoid robot
- Navigation
- Particle filter
ASJC Scopus subject areas
- Engineering(all)
Cite this
Real-time navigation for a humanoid robot using particle filter. / Baltes, Jacky; Cheng, Chi Tai; Lau, Meng Cheng; Espínola, Andrés.
Innovation for Applied Science and Technology. 2013. p. 1914-1918 (Applied Mechanics and Materials; Vol. 284-287).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Real-time navigation for a humanoid robot using particle filter
AU - Baltes, Jacky
AU - Cheng, Chi Tai
AU - Lau, Meng Cheng
AU - Espínola, Andrés
PY - 2013/2/20
Y1 - 2013/2/20
N2 - This paper presents a practical real-time visual navigation system, including a vision system, a particle filter (PF) based localization system, and a path planning system, for humanoid robots in an indoor environment. A neural network (NN) converter system is used to solve the image distortion problem. The monocular vision system detects objects of interest in the scene, calculating their position in the image, and converting the position in the image to real world coordinates. The PF localization system estimates the current position by the robot's motion model and corrects the estimated position by using feedback from the data gathered by the vision system. The path planning system determines the next motion based on the result of the localization system. This paper uses a tree-like path planning method which not only guides the robot to the destination but also avoids obstacles at the same time. The navigation method allows a user to assign several different target destinations to the robot simultaneously. The proposed method is implemented on a humanoid robot "ROBOTIS DARwIn-OP", an open platform humanoid robot. The effectiveness of the system is demonstrated in an empirical evaluation.
AB - This paper presents a practical real-time visual navigation system, including a vision system, a particle filter (PF) based localization system, and a path planning system, for humanoid robots in an indoor environment. A neural network (NN) converter system is used to solve the image distortion problem. The monocular vision system detects objects of interest in the scene, calculating their position in the image, and converting the position in the image to real world coordinates. The PF localization system estimates the current position by the robot's motion model and corrects the estimated position by using feedback from the data gathered by the vision system. The path planning system determines the next motion based on the result of the localization system. This paper uses a tree-like path planning method which not only guides the robot to the destination but also avoids obstacles at the same time. The navigation method allows a user to assign several different target destinations to the robot simultaneously. The proposed method is implemented on a humanoid robot "ROBOTIS DARwIn-OP", an open platform humanoid robot. The effectiveness of the system is demonstrated in an empirical evaluation.
KW - Humanoid robot
KW - Navigation
KW - Particle filter
UR - http://www.scopus.com/inward/record.url?scp=84873906511&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84873906511&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMM.284-287.1914
DO - 10.4028/www.scientific.net/AMM.284-287.1914
M3 - Conference contribution
AN - SCOPUS:84873906511
SN - 9783037856123
T3 - Applied Mechanics and Materials
SP - 1914
EP - 1918
BT - Innovation for Applied Science and Technology
ER -