Outline DRAFT

Modelling Human Hand-Eye Coordination Using Recurrent Neural Networks
  • Introduction
    • What the presentation is going to discuss/ introduce the project
·         Rationale
o    The goal of this project is to …
·         Background
A.      Recurrent neural network (RNN)
§  A RNN is a class of artificial neural network where connections between units form a directed cycle, allowing dynamic temporal behaviour.
§  Dynamic temporal behaviour
§  The trajectory of states, in a state space, followed by a system during a certain time interval[TM1] .
B.      Machine/reinforcement/deep learning
§   
C.      Eye movements and uses for navigation and coordination
§   
D.      Virtual Reality simulation
§  explain VR first (present the uses of VR in the experiment e.g. controlled variables and easy data collection)
·         Method
o    Collect hand, head, and gaze data from various subjects age ?-? (<=too specific?) using VR (go into more detail[TM2] )
·         Results
o     
·         Discussion
o    Discuss results and relate them to scope (papers I’ve been reading and how this can help future robotics e.g. navigation, task management, grasp, etc.)
·         Conclusion and future works[TM3] 
o    Make solid conclusions of research and what I’ve personally learned at RIT
·         My contributions
o    Assisted in the creation of an in-engine media system in which the simulation can be played, paused, move forward by a frame, and move backwards by a frame[TM4] .
o    Assisted in the implementation of multiple viewpoints within the simulation including, fixed position, ball tracking, and free camera[TM5] .





 [TM1]How can I explain this in laymen terms?


 [TM2]Explain what has been done to implement machine/etc. learning


 [TM3]Use the papers I’ve been analyzing to create a list of scopes this research could benefit in robotics development


 [TM4]Include video?


 [TM5]Should I include pictures/GIF’s of each for the presentation?

Comments

Post a Comment

Popular posts from this blog

Day 28

Today was a solid day. The majority of the day was finalizing my Presentation for tomorrow. And the rest of the day was getting the reinforcement code to launch via command line, and editing the code in visual studio. The internship is ending soon and all loose ties are being tied up. I'm beginning to think about all the things i must do in the coming months to prepare for my application to RIT this coming fall. I've much to do and after the internship ends, i will have no time to hesitate in my preparations to ensure i am not only accepted, but am received with priority or at least regard.
Read more

Day 26

Today has been a immensely productive day. I have been working on my Presentation and after getting it to a semi-presentable state i showed everyone at the weekly meeting to get as much critique as i can. I got a lot of positive critique and overall most of the senior staff were impressed with what i had currently shown and where i said i would take the presentation. I will continue to work on my presentation until every aspect is deemed perfect by my standards and the standards of those around me.
Read more

Day 19

Image
Today has been another routine day so far with more paper analysis, which is finally about to end as i am on the last paper. The paper i finished today detailed two methods of transporting an object via a multi-robotic system in which certain objectives are assigned to each robot, a very interesting paper with possible future applications to the transport of an object via interconnected nano-bots similar to what is seen in some Sci-Fy movies. The last paper is an unpublished currently under review version of the very project i'm currently working on, so when i finally analyze all of it i should be able to create a solid and confident Abstract, Structure, and Presentation. Problem is that i have absolutely no clue what some of the things the paper is taking about as the terms are not well defined in any literature. Kamran has already agreed to sit down with me and explain every single missing piece of information so that i can understand and connect everything. I have also found som...
Read more