1. Project number and Title – 5 - Learning to Detect Doorbell Buttons by Haptic Exploration

2. Should this project be considered for the Best Project award? No

3. Should this project be considered for the top 3 project awards? No

4. On a scale of 1 to 10, how would you rate the overall organization/clarity
of the project report? (1-10)  6

5. On a scale of 1 to 10, how would you rate the overall project idea? 6

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) 7


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?
The paper is well organized and is concise. However, clarity is lacking. There are some things explained in too much detail like the previous work section which was too technical. The sentence structures could be improved upon for easier reading; at times it was hard to understand what the author was getting at.


* How does the project idea and methodology fit within the framework
of Developmental Robotics?

The proposal extends an existing research on a robot learning to door- bell buttons by including haptic information, so it is about introducing another sensory modality. This research is expanding on the previous one by adding more complexity, but it is not a major change. The author could have used more arguments to sell the idea better.

* Describe what you like BEST about the project?
The Previous work section is well researched. The idea of a robot learning to figure out broken doorbell buttons autonomously sounds cool.

* Describe what you like LEAST about the project?

The project report is hard to understand. It could use some proof reading and better sentence construction.

* Do the methods, results and contributions of the final project correspond to what was presented in the initial project proposal?

The final report seems to have the robot touch a door bell mounted on a portable wooden platform. The robot uses two fingers to grasp the wood and the third to press the button. Although this is fine for testing purposes, I cannot think of a real world example where the robot would have to grasp in the same way. Most doorbells are mounted on a plane.

* Do the experimental results reported in the paper demonstrate success?

From the results mentioned in the paper, the robot has learned how to find a broken door bell. It classifies when a button is broken by running two routines - press doorbell and bell triggering press. If it is able to press the doorbell but is unable to hear it ring, then it is classified as broken.

* Future Work

It would be nice to see this generalised to door bells mounted  on a wall like surface as opposed to a wooden plank.


* 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?

While the project research is good, the report presentation needs some work before it can be published. Better sentence construction, proper proof reading, etc. are needed to polish it up a bit.

However I must say that I can see lot of improvement over the initial project proposal. Good work!