1. Project number and Title Team: Corey Gwin Title: Perceiving the Unseen for Enhanced Tool Use: Body Schema Extension via a Vibrotactile Feedback Mechanism Number: 15 2. Should this project be considered for the Best Project award? (yes/no) no 3. Should this project be considered for the top 3 project awards? (yes/no) no 4. On a scale of 1 to 10, how would you rate the overall organization/clarity of the project report? (1-10) 9 5. On a scale of 1 to 10, how would you rate the overall project idea? (1-10) 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? (1-10) 6 Then write approximately 2 pages of helpful feedback to the project's author(s). The following questions should help you organize your feedback: * Overall, is the project report clear, concise, and well-organized? Organization was very good. I thought included diagrams were all very helpful. Especially useful were the diagrams showing the test cases. The pictures in the conclusion and discussion I felt were unnecessary. They just seemed to take up space and drag on the report in page length. While the report flowed well, I felt the project overview was too long. It was six pages almost entirely of text before the report reaches the previous work section. While it gave me a good understanding of many systems that are similar in nature to the one developed in the project, I felt it turned into “fluff” after a while and didn’t contribute anything to the project report. * How does the project idea and methodology fit within the framework of Developmental Robotics? The project works with a haptic feedback system. The idea of adding and manipulating sensory modalities of humans is an important topic to understand if researchers are to approach developmental robotics correctly. Although this experiment wasn’t necessarily work in developmental robotics the idea and approach of a human learning to add sensors to their body is still important to the field. * Describe what you like BEST about the project? As with most things, my favorite part was the results. I was disappointed to see the Kinect was such a limiting factor. I will admit when I reviewed the proposal I didn’t know much about the Kinect and was hopeful to see it in application. After reading the project report, however, it is obvious that the Kinect was a major limiting factor. I still thought it was interesting to use it over a more standard object detection system. The results for all the experiments were well presented and organized. It made them easy to read and understand; I appreciated this. * Describe what you like LEAST about the project? My least favorite part of the project was the length of the project overview and conclusion/discussion. The overview is supposed to briefly summarize the entirety of the paper. Since only ~20% of the overview was dedicated to explaining the proposed solution and target audience I felt like there was a lot of wasted typing. A few examples would have sufficed for the background. While I learned a handful of things from the extensive background section, it didn’t help that significantly to contribute to my understanding of the project. I think the question about any section of this sort of paper should be “How does this section contribute to my reader’s understanding?” In my opinion much of the introduction did not contribute. Similarly the discussion and conclusion section was quite long. Although I enjoy future work sections usually more than anything else in a paper (helps me inside the authors head), this one seemed almost too elaborate. Usually it suffices for future work to just list the topics you have considered and not go into detail. Leave the reader wondering slightly what exactly you are planning to do next, while giving them an idea of your direction. This lets them know (hopefully) that you are competent while leaving them thirsting to learn more. Overall I thought the meat of the paper was fantastic, I just felt it needed trimmed slightly. * Do the methods, results and contributions of the final project correspond to what was presented in the initial project proposal? Yes. The project proposal proposed the idea, the final project saw the idea become a reality. Although there were plenty of bugs that seemed to have popped up along the way and a scope reduction or two, there always are. Overall I think the author did a wonderful job of implementing the project he proposed. * Are there any major details left out with regards to the methods, algorithms, or experimental design described in the report? I would have been interested in more detail as to how the Kinect works. A quick overview of the functions of the OpenKinect library used or something similar would have been appreciated. The same thing goes for the visualization and the processing and arduino code. Including a diagram of system flow would be great for future projects. I think the biggest issue here was a difference between who the author saw as his audience and who I believe his audience should have been. To me this paper is written for the TA, instructor and students of CprE 585X. This means the audience has a strong technical background (assume graduate level), are competent in basic developmental robotics theories and generally are nerdy with a thirst for technical details. The paper gave me the vibe that it was written for a technical out-of-major reader who is assumed little to no background in developmental robotics. * Do the experimental results reported in the paper demonstrate success? Yes. The results all demonstrate success when both haptic and visual feedback are used. This was expected from the start so I would say expectation is on par with results. * Do you have any suggestions for improvement and future work? I think the most interesting future work would be looking into the diminishing return of such a system. If the system stops working over time it implies that the sensors are being used more as optional tools and less as additional sensor modalities or that we judge the extra sensor data is not important. * 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? I would say the paper is on the track to being publishable. The idea is definitely solid. The biggest improvements that need made were addressed by the author: improved haptic feedback system, improved vision system, more test subjects. With these three things and a controlled test environment I definitely think this paper could be worth of publishing. Kudos to you, it was a job well done!