1. Project number and Title

Project number: 12
Title: Behavior-Grounded Object Identification, Grouping and Ordering by a Humanoid Robot

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)
8

5. On a scale of 1 to 10, how would you rate the overall project idea? (1-10)
7

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?

Yes.

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

The project idea fits within the framework of Developmental Robotics very well. Developmental Robotics assumes that the robot should be like human to undergo a development process. During the development, the robot will actively explore the environment around, to build its own representation to the environment or understand the environment on his own way as well as improve its skills for doing some tasks in the environment, so that it can adapt the environment better. 

First, without adding joystick and real robot, I am more willing to understand the snake as a mobile robot, which can move around with wheels under and an increasing body. Then, the project related problem will be more like a path planning problem in Artificial Intelligence and Mobile Robotics. While in Artificial Intelligence and Mobile Robotics the path planning problem is solved by approaches say Reinforcement Learning, the project trys to use intrinsic motivation, which is inspired by the developmental psychology. Intrinsic motivation models the exploration behavior of humans in an unknown environment. The project tries to use intrinsic motivation to guide the exploration behaivor of the mobile robot in a snake game, which fit within the framework of Developmental Robotics very well.

* Describe what you like BEST about the project?


I like the intrinsic motivation part in the project best. The project tries to use intrinsic motivation to guide the exploration of the robot. Intrisic motivation is very important in the autonomous mental development of human. Only recently, Roboticists begin to use it to guide the exploration of their robots. By intrinsic motivation, it is showed that the robot can learn more fast. Teaching the robot to play video game, especially adding intrinsic motivation in, is a very fascinating project.

* Describe what you like LEAST about the project?

Without adding the joystick and real robot, the project will be more like solving a path planning problem but not teaching the robot to play video game, which cut down the grades of the project very much.

* 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 final project correspond to what was presented in the initial project proposal very well. 

The object-oriented design is used to organize the functions. A snake game is created to provide a simulated environment. The snake is simulated as a mobile robot and the goal of the mobile robot is learning to catch the apple in the environment. The intrinsical motivation based on support vector machine is used to guide the learning of the snake. The learning performance seems to be very good from the result. Friend user interface is implemented, too.


* Are there any major details left out with regards to the methods,
algorithms, or experimental design described in the report?

Algorithm is very good but seems to be overkilled for the task in the project. Also the task seems to have been solved previously. The task may become more meaningful when the real robot is added. 

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

Yes, the snake can learn to catch the apple successfully using the intrinsical motivation based on support vector machine. 

* Do you have any suggestions for improvement and future work?

Using the intrinsic motivation to guide the robot's learning is just like an infant learns self-motivatedly. This is a very intreresting area. Algorithm is very good, and just find out its application on a more meaningful and complex task.

* 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?

Adding the robot into the task or choosing a more complex task can very possibly be got into a conference or journal paper.