1. Project 3: Developmentally Learning the Support Affordance of a Platform

2. Should this project be considered for the Best Project award? Yes

3. Should this project be considered for the top 3 project awards? Yes

4. On a scale of 1 to 10, how would you rate the overall organization/clarity
of the project report? 9

5. On a scale of 1 to 10, how would you rate the overall project idea? 9

6. On a scale of 1 to 10, how would you rate the overall research
contribution of the project idea, methodology and/or results?  9


* Overall, is the project report clear, concise, and well-organized?
The organization of this report was really well done. The contents were relevant to the overall theme and there was consistent flow between the multiple sections. The visual components were appropriately discussed before or after the position of the images. This ensured that the readers could understand the relevant of the images. 


* How does the project idea and methodology fit within the framework
of Developmental Robotics?
The project idea on researching affordances in support structure is very integral to the framework of Development Robotics. Although the central idea was to implement affordances in support structure, there was critical research into the use of different classification algorithms. This really made significant impact in comparing and analyzing the different methodologies used within the framework of Developmental Robotics.


* Describe what you like BEST about the project?
I really like the project's use of visuals and language in describing the project. All the information needed to understand the purpose, methods, and results were available in the report. In addition, the project seems like a success. The team was able to use classifiers in aiding affordances in support structure. Lastly, there seems to be a lot of team effort put into this project.


* Describe what you like LEAST about the project?
One point I did not like about the project was the lack of comparison between the multiple algorithms. There was also no discussion on how well the project reaches the overall goal of affordances in support structure. 

* Do the methods, results and contributions of the final project
correspond to what was presented in the initial project proposal?
The team did a great job in implementing their final project with additional work from their initial project proposal. I really like the incorporation of Vladimir Sukhoy's entropy methodology as another possible control classifier. 

* Are there any major details left out with regards to the methods,
algorithms, or experimental design described in the report?
As mentioned before, there needs to be more content on comparing the different control classification algorithms and determining how each approach furthers the framework for affordances in support structure. There could also be a section on learned lessons or abnormal results. 


* Do the experimental results reported in the paper demonstrate success?
The experimental results reported in the paper did demonstrate success. Looking at the different algorithms, there seems to be consensus that success rate in using the control classifier correctly. Although this was achieve for four different support structures with limited trials, more diverse and longer experiments will be needed to verify the project's success.


* Do you have any suggestions for improvement and future work?
The use of confidence measurement in affordances is very intriguing. Perhaps the team could elaborate more on this approach and brainstorm different affordances that could benefit from this same framework. The section on Future Work is well done. The discussion on velocity calculation in different scenarios could lead to potential work that involves using better equipment.


* How close is the final project report to being publishable as a
conference or journal paper (consider the research papers that were
part of the course reading)? What would it take to get there?
This final project report is very close to being publishable. In my opinion, if the team could provide a platform for conducting this experiment in simulation, there would be enough material for readers. This alone will give the team more data, ease of use, and flexibility in deriving various scenarios. Besides that, the presentation and results of the project is publishable material. Nice work.