Multi-robot Cooperation Based Human Tracking System Using Laser Scanner
Date Issued
2010
Date
2010
Author(s)
Chou, Chen-Tun
Abstract
Human tracking has received tremendous amount of attention while human-robot interaction is getting more and more important nowadays. In this paper, we developed a hybrid approach to a Laser Range Finder (LRF) based human leg detection system that returns not only "true" or "false" type of answer but also a probability.
We first obtain the geometric information from measurements made by the laser range finder, and this set of measurement data is further decomposed into several sectors using segmentation. And then we apply a probabilistic model to compare these sectors with leg patterns to check if they belong to the set of human leg patterns or not. Next, we examine these leg sectors with a modified Inscribe Angle Variance (IAV) method in order to get if how likely these sectors are from human leg''s arc feature or not. Moreover, we also use motion detector to check if these objects move or not as an enhancement of the detection.
In our work, each robot of our system is equipped with a LRF and a hybrid approach as mentioned to human detection, so it can deliver the detected human information to our center control computer through the Inter-Process Communication (IPC). Within a prior map information and supposing each robot in the team has a localization module, we can map these results of human detection from each robot into the global coordinate. But in order to reduce the computational complexity while doing the data association among these robots in a team, we introduce a set of appropriate rules. Finally, we apply the observations to a SIR particle filter based human tracking system to keep tracking people being detected. This work has been evaluated through several experiments with a number of mobile robots and humans in an indoor environment, and promising performance has been observed.
Subjects
Laser Range Finder
Human Detection
Human Tracking
Multi-robot cooperation
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-99-R97921002-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):ed6328466dd54a9918da1d35c706e1d9