MAS-Project-2023 Home
- 1 1. General course information
- 1.1 Contact policy
- 2 2. What is this course about?
- 3 3. Learning Goals
- 4 4. Organization
- 4.1 Assignment Groups
- 4.2 Practical Sessions
- 4.3 Communication
- 5 5. Schedule
- 6 6. Grading
- 7 7. Resources
- 8 9. Corona rules
- 9 10. Inclusivity statement
- 10 11. Academic integrity and code of conduct
1. General course information
Course code: XM_0041
Duration: 4 weeks - Period 3 (Jan - Feb 2023)
Level: BSc 2 (Artificial Intelligence)
Credits: 6
Schedule and locations:
Lectures:
Tuesdays 13:30 - 15:15, WN-Q105 - No lecture in week 4
Practical sessions:
Tuesdays 15:30 - 19:15, location: see schedule / group-room assignment - Agent testing session in week 4
Fridays 9:00 - 12:15, location: see schedule / group-room assignment - No lab session in week 4
Instructors:
Koen Hindriks
Florian Kunneman
Merle Reimann
Teaching assistants (your assigned TA will be your main point of contact):
Isabella Gardner
Raihan Ishmam
Ioan Florea
Zahra Moradi
Piotr Sobecki
Zoë Blei
Selem Moneer
Contact policy
If you have any questions, first try to use the questions channel on the communication service https://discord.gg/26wfcZzDyf that we use for this project. If your question is not replied to (by other students or TAs), then contact your TA. If you have any other issues to report, also always first contact your group’s TA via Discord. If the question or issue cannot be resolved with your TA, ask your TA to take this up with us. Only if after that you still have not received any response within reasonable time (within a week that means), send the teachers a mail.
2. What is this course about?
In this course, you will gain an understanding of how Prolog and the MARBEL Agent Programming language can be integrated with the Social Interaction Cloud and Google Dialogflow to design and develop a conversational agent, that will help the user to select a recipe. You will learn how to set up the conversational agent, how to think of the user perspective and dialogue design, and how to best deploy the speech and visual interface as the conversational with the user evolves. Apart from following lectures, you will work in groups towards developing and evaluating your cooking assistant.
3. Learning Goals
By the end of this course, you should be able to:
(L1) Explain what a conversational agent is, and how it can be designed using the MARBEL Agent Programming
(L2) Explain the “what, why, and how” of each component of the conversational agent programming
(L3) Apply basic conversational design principles
(L4) Explain how verbal and visual communication influence the recipe selection and flow of the conversation or dialog
(P1) Perform a (pilot) user study to evaluate your conversational agent
4. Organization
The course consists of three main components:
Lectures (on campus) in which course material is presented. Some lectures will have assigned readings to prepare before class.
Group work on the project assignment, partly during practicals (on campus), which will result in a grade for the course
Individual work to learn about github and dialogflow and read papers, tested by obligatory quizzes
Assignment Groups
You will be working on the course assignment together in a group of 6 students. We will assign a teaching assistant (TA) to each group. Your teaching assistant is your main point of contact for any questions you have about the course and the assignment. Your TA will also monitor whether each group member individually contributes to the deliverables. Individual contribution and active participation in the course is required to pass the course.
Practical Sessions
Each week, there will be two practical sessions, on Tuesday afternoons and Friday mornings, in which groups can work on the assignment and talk with their TA about the progress and ask questions. It is obligatory for all members of the group to attend these meetings. In case you cannot make it, you need to inform your TA in advance and have an acceptable reason. Note that you are required to work together on the project during the whole week, and that your TA is available for questions on discord or additional meetings if needed during these days as well.
Communication
For communication when working on the project assignment, we will use Discord. Make sure you use your own name (and not a nickname) in Discord. For each group, we have created a group channel, and we have created channels for specific topics. In your group channel, you can privately talk with the other students in your group and your TA (no one else will have access). Discord is the way for you to communicate with your TA.
5. Schedule
The schedule for the course, including lectures and deliverables, can be found https://socialrobotics.atlassian.net/wiki/spaces/MAS23/pages/2145386497 . Make sure you follow it closely throughout the course in order not to miss any deadline.
Your TA will monitor your progress on the design document and updates to your GitHub repository. Because you will be asked to share deliverables in the GitHub repository that we will make available to each group, we expect you to continuously update that GitHub repository. We will take this into account when assessing your work.
6. Grading
The course is assessed based on the recipe recommendation agent functionalities, the coding and the final report.
Each of you also need to complete all canvas quizzes that will be made available to you during the course.
Individuals may be rewarded a higher or lower grade than the group based on their effort and cooperation. We will amongst others use the log books that you need to maintain for this purpose.
The project assignment must be completed in groups. The assignment are graded with a mark (0-100). There must be a minimum of 55 to pass the course.
The Rubric for the assessment can be found here: https://socialrobotics.atlassian.net/wiki/spaces/MAS23/pages/2145353729.
7. Resources
This course does not have a textbook, however, we encourage you to consult the following resources:
Other interesting/relevant resources
Overview of Dialogflow https://cloud.google.com/dialogflow/es/docs/agents-overview.
Overview of https://cloud.google.com/dialogflow/es/docs/intents-overview.
Overview of https://cloud.google.com/dialogflow/es/docs/entities-overview.
Making a Dialogflow Agent: https://medium.com/@erika.dauria/create-an-agent-f3bb5169f253, https://cloud.google.com/dialogflow/es/docs.
9. Corona rules
The latest Corona measures can be accessed here.
Please follow this decision tree to check whether you are allowed to be on campus, e.g., after travel, or if you or someone you were in contact with test positive.
10. Inclusivity statement
We strive to offer students a safe and inclusive classroom environment. We welcome the perspective of students of all ethnicities, genders, spiritual beliefs, and sexual orientations, among others. If you feel discriminated on the basis of your identity, please report it to the course staff.
If you have a disability and require accommodations, please let us know before the beginning of the course so that we can discuss your accommodations and needs to make the course as accessible to you as possible.
11. Academic integrity and code of conduct
Plagiarism is not tolerated for both reports and code. You are welcome to use any code you see fit for your project, as long as you appropriately cite your sources both in the report and in the code itself (as comments).
Any behavior that violated the VU rules for academic integrity and code of conduct will not be tolerated.