Difference between revisions of "C-SLAM"
DavideTateo (Talk | contribs) (→Logical Structure) |
m |
||
| (36 intermediate revisions by one other user not shown) | |||
| Line 10: | Line 10: | ||
|start=2013/04/12 | |start=2013/04/12 | ||
|end=2014/10/31 | |end=2014/10/31 | ||
| − | |status= | + | |status=Closed |
|level=Ms | |level=Ms | ||
|type=Thesis | |type=Thesis | ||
| Line 18: | Line 18: | ||
The main idea is to extract high level features, like objects in the image and use them to localize an autonomous robot. | The main idea is to extract high level features, like objects in the image and use them to localize an autonomous robot. | ||
| + | |||
| + | Source code can be found [https://github.com/AIRLab-POLIMI/C-SLAM here]. | ||
| + | The thesis can be found in [https://www.politesi.polimi.it/handle/10589/97664 politesi]. | ||
=Logical Structure= | =Logical Structure= | ||
| Line 36: | Line 39: | ||
[[File:C_slam_architecture.svg|500px|center]] | [[File:C_slam_architecture.svg|500px|center]] | ||
| + | |||
| + | =Experimental Results= | ||
| + | |||
| + | <gallery mode=nolines widths=250px heights=200px> | ||
| + | File:C_SLAM_Detection.png|Detection algorithm output | ||
| + | File:C_SLAM_Recognition1.png|Recognition of a door | ||
| + | File:C_SLAM_Recognition2.png|Recognition of a Whiteboard | ||
| + | File:C_SLAM_Tracker1.png|Tracking some objects | ||
| + | File:C_SLAM_Tracker2.png|Same objects from another viewpoint | ||
| + | </gallery> | ||
Latest revision as of 23:19, 5 August 2017
C-SLAM
| |
| Short Description: | Development of a Cognitive SLAM system |
| Coordinator: | AndreaBonarini (andrea.bonarini@polimi.it) |
| Tutor: | AndreaBonarini (andrea.bonarini@polimi.it) |
| Collaborator: | |
| Students: | DavideTateo (davide.tateo@polimi.it) |
| Research Area: | Robotics |
| Research Topic: | Robot development |
| Start: | 2013/04/12 |
| End: | 2014/10/31 |
| Status: | Closed |
| Level: | Ms |
| Type: | Thesis |
The Aim of this project is to build a Cognitive SLAM system.
The main idea is to extract high level features, like objects in the image and use them to localize an autonomous robot.
Source code can be found here. The thesis can be found in politesi.
Logical Structure
The reasoner is the fundamental part of the system. The reasoner implements a fuzzy tree classification, similar to fuzzy decision trees.
Object detection is done on the whole image, while object recognition is done only on detected objects.
The tracking algorithm used is a long term tracking algorithm. We use a C++ implementation of the CMT algorithm.
Localization is done using sensor fusion algorithm, based on maximum likelihood estimation on a factor graph.
System Architecture
The system is developed using the ROS middleware.
The sensor fusion algorithm used to implement localization is developed using the ROAMFREE library.
Parser for the knowledge base languages are developed using Flex and Bison.
Vision algorithms are based on OpenCV2.
Experimental Results
Detection algorithm output
Recognition of a door
Recognition of a Whiteboard
Tracking some objects
Same objects from another viewpoint
