More than 3000 engineers find our updates useful. You can get them at your mail box!
Search your paper presentation and project titles:

Department/Area of interest: ( To list the projects / paper presentations)

Mechanical               Scada technology              Communication             Computer science           Alternative energy
Electrical                  Robotics                        Biometrics                     Artificial intelligence             Electronics

Paper presentations - Object recognition with robots

Title: Discovering and learning to recognize objects
Departments: Computer science, Digital signal processing, robotics.
Can be used: Research purpose, paper presentations and educational purposes.

This is an paper presentation which we collected from a sister site of MIT university. This is a paper published by the students of the prestigious university. This paper is completely about an application of the robots in the field of "Object recognizing and discovering." The title suggest all the content of the paper presentation here. It is an projects idea to design an robot which will be serving the purpose of object identification in the real world. This project is an attempt to improve and design an machine with an improved computer vision to achieve levels of robustness that will exceed the competitors.

Sample from the original paper presentation on robot to recognize objects: 
This work is implemented on the robot Cog, an upper torso humanoid. Cog has two arms, each of which has six degrees of freedom. The joints are driven by series elastic actuators. The arm is not designed to enact trajectories with high fidelity. For that a very stiff arm is preferable. Rather, it is designed to perform well when interacting with a poorly characterized environment, where collisions are frequent and informative events. Cog runs an attentional system consisting of a set of pre-attentive filters sensitive to motion, color, and binocular disparity. The different filters generate information on the likelihood that something interesting is happening in a certain region of the image. A voting mechanism is used to “decide” what to attend and track next. The pre-attentive filters are implemented on a space-variant imaging system, which mimics the distribution of photoreceptors in the human retina as in. The attentional system uses vision and non-visual sensors (e.g. inertial) to generate a range of oculomotor behaviors. Examples are saccades, smooth pursuit, vergence, and the vestibulo-ocular reflex (VOR).
Courtesy : MIT

Download this robotics paper presentation here :

Intense Debate Comments