1. Project number and Title:  (2) Behavior-Grounded Object Identification, Grouping and Ordering by a Humanoid Robot

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? 10



Overall, is the project report clear, concise, and well-organized?
	The report is quite clear in its entirety and is concise enough, however, it did not meet the page length requirement (which I feel should not be a large impact on the review of this project).  As far as conciseness is concerned, the proposal does not bother repeating information that has already been given and only talks about topics that are relevant to the project.  It also gives enough information about what is being done so that is easily understood.
 	This project is organized quite well.  The flow of information given to the reader makes sense.  The reader is briefly introduced to the general idea of the project and is given a quick rundown of the organization of the paper.  The reader then learns about relevant studies in psychology as well as robotics and is finally introduced to the actual approach this project will take.


How does the project idea and methodology fit within the framework of Developmental Robotics?
	This idea clearly fits in the framework of developmental robotics.  First off, it involves solving various tasks that children can do:  recognizing objects, categorizing objects, predicting the category an object belongs in, and ordering objects.  Secondly, this idea builds upon previous work that has been done in the field by doing similar experiments on a larger scale.  Another reason that it fits in the framework is that behaviors are being used to ground representations of objects in order to organize them.


Describe what you like BEST about the project?
	I really liked how thoroughly they explained their idea.  The methods for conducting the experiment and analyzing the data are quite clearly explained.  As far as the idea itself is concerned, I like that they are conducting trials with so many different objects.  A research group can run tests with a few objects and claim that their results are excellent, but the results don't mean very much because objects can vary to extreme extents and could cause their algorithms to fail on untested objects.  This project works with objects of many different types (20) and large numbers of objects (100 total).


Describe what you like LEAST about the project?
	This idea was a pretty good idea and there is not much to dislike about it.  However, I think that this project does not really give any practical applications of the research.  It solves a good problem, but immediately I do not see how this can be used in a real-life situation.


Do the methods, results and contributions of the final project correspond to what was presented in the initial project proposal?
	The methods, results, and contributions of the project are very close to what was originally proposed.


Are there any major details left out with regards to the methods, algorithms, or experimental design described in the report?
	There were no major details left out.  Their methods for conducting the experiment were very clear and specific enough know what is going on.  The algorithms were explained very well and were easy to relate to based on my programming experience.  The design of the experiment was excellent and of a sufficient size.


Do the experimental results reported in the paper demonstrate success?
	The results of this project demonstrate quite a success (in my opinion).  The robot was able to recognize objects, group objects accuractely, match objects to their correct categories, and order objects by height and weight with very high accuracies.  They proved the idea that a larger diversity of sensory modalities will allow greater predicition abilities in all the sets of experiements they conducted.


Do you have any suggestions for improvement and future work?
	This paper was excellent and I feel that there is not much that can be done to improve it.  The future work seems to be more directed toward how this specific experiment can be extended.  I feel like more examples of the potential applications of a more refined version of what the authors have should be included.


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?
	There is not much that would have to be done to this paper to prepare it for a conference or journal paper in my opinion.  It is very thorough, easy to read/understand, and has excellent results.  I feel one of the few things that may be done though is to form the paper in more of an academic form (which it mostly is) instead of discussing it as a project, but this a minor change.