1. Proposal number: 1

2. Should this proposal be considered for the Best Proposal prize? (yes/no) yes

3. On a scale of 1 to 10, how would you rate the overall organization/clarity of the proposal? (1-10) 9

4. On a scale of 1 to 10, how would you rate the overall project idea? (1-10) 9

* Overall, is the proposal clear, concise, and well-organized?
The paper is extremely well laid out and organized. On my read I did find a paragraph that I think was meant for another section, the last paragraph on page 3 referenced a study,
but seemed out of context. Referenced preliminary data was omitted from page 7. Overall though this is a very well thought out and ambitious project.

* Does the proposal meet the posted proposal guidelines? Yes

* How does the project idea fit within the framework of Developmental Robotics?
The project idea involves several of the core topical areas within developmental robotics including, self-detection, grounding, developmental psychology, and tool use.

* Describe what you like BEST about the project idea.
I think the topic selected for study is excellent as it is a very practical need within developmental robotics. In real-life applications we will want robots that are autonomously
capable of dealing with containers and their contents. This topical area is very important fundamental research. Solving this problem using a learning approach could ultimately
lead to the development of flexible and generalizable algorithms instead of rigid engineered approaches. These capabilities are necessary for the creation of robots that can
reliably perform many everyday tasks in a variety o contexts. I think bringing in the concept grounding of ‘inside’ was a nice added dimension to the project. (I also liked the
Cookie Monsters :) )

* Describe what you like LEAST about the project idea.
What I liked least was that that the same object when flipped over is classified as a non-container.

* Do you have any concerns about the project?
This not at all related to the person who is doing the self-detection work (I am sure he is very competent and committed), but anytime part of a project is not directly under your
control well, it’s out of your control.

* Does it seem doable in the remaining time?
I think the project is ambitious, but the author is quite experienced. Developmental robotics is his core area of study so he has quite a few related projects and papers under his
belt, so has probably got a decent understanding of some pitfalls he may encounter when working with the robot. I am assuming he has good access to the facilities, and tools
necessary to complete the work. He also is working with an experienced collaborator on the project. (I know I cited as a project risk too, but overall it is a benefit.)

* Does it seem too difficult?
The author is stretching himself by incorporating the deep learning architecture, but has attended seminars and done quite a bit of research ing the area. It is probably the
highest risk aspect of the project.

* Are there any major details left out?
I would have liked a little more detail about how the novel images will be incorporated into the study and tested. I also would have liked a bit more detail about how the concept
grounding was going to be incorporated into the work.

* Does the idea rely upon technologies that are not currently available?
The deep learning architecture will be adapted for this project, so I would classify that as new technology in this context.

* Do you have any suggestions for improvement?
I would prefer a setup where the robot would be able to try different orientations to determine whether the object is a container or not and to have included some true
non-containers, such as a cylinder and solid object. I was unclear as to how the non-containers would be used here.


* Do you have any suggestions for related work that should be cited? No.

* Any other comments or suggestions?
Good Luck - I see that your project will likely have been completed before you see these comments. You are already very accomplished in the field of robotics, so there is likely
not much I can add.