Socially Intelligent Robotics course at VU Amsterdam for MSc AI
Course Information: https://socialrobotics.atlassian.net/wiki/spaces/SIR2021/overview
- What is this course about? Robots are expected to enter several aspects of our daily lives (e.g., shopping malls, airports, hotels, the home) and will be expected to be socially intelligent for smooth integration in human environments. In this course we will take a user-centered approach to the design of social robots and look into AI techniques for developing a social robot that can interact with human users.
You will gain an understanding about social robotics and related AI techniques to control a social robot (e.g., conversational AI, techniques for making a robot more socially aware, expressive gestures, etc.) and apply this knowledge for designing a social robotics use case. In addition to lectures, you will be designing a socially interactive robot prototype on a Nao humanoid robot for a specific use case of your choosing. You will work (outside lectures) in groups towards developing your use case. You will be asked to perform a preliminary evaluation of prototype amongst your classmates. You will be challenged to take initiatives and direct your own learning, where your design choices will be grounded in existing (multi-disciplinary) literature.
- Learning Goals By the end of this course, you should be able to:
(L1) Explain what social robot interaction design is and create a problem and design scenario for a robot
(L2) Explain the “what, why, and how” of each component of the social robot interaction design methodology (SR-IDM)
(L3) Identify, analyze, and apply relevant human-factors knowledge to a social robot design
(L4) Reflect upon different evaluation approaches and create a procedure to evaluate a social robot
(L5) Apply basic conversational design principles to create a conversational design for a social robot
(L6) Explain what nonverbal communication and affect are and which parameters influence affect expression
(L7) Analyze different personalization strategies, discuss how they work and what their strengths and weaknesses are
(L8) Identify and explain basic techniques for making a robot socially aware.
(L10) Analyze and evaluate basic ethical dilemmas related to social robotics and your use case
(P1) Apply the social robot interaction design methodology (SR-IDM) while designing a social robot
(P2) Perform a (pilot) user study to evaluate a social robot design
- Organization The course consists of three main components:
Lectures (hybrid, in-person or through Zoom) in which course material is presented. Most lectures will have assigned readings on which you will be asked to write a short paragraph (reading assignments) before class.
Course assignment where you will work in group on course deliverables, such as the code for controlling the robot and a design document.
Practical sessions @VU campus where you will have access to a Nao robot to work on your course assignment.
Assignment Groups You will be working on the course assignment together in a group of 6 students (with some exceptions). We will assign a teaching assistant (TA) for 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 be able to pass the course.
Working with the Nao Robot: Practical Sessions Each week there will be two practical session of 3.5 hours on the VU campus. During these practical sessions you will have access to a Nao robot to test your code on the robot. Use these practical sessions as effectively as possible by focussing your effort during these sessions on tasks that require access to a robot. You will most likely find that you would have liked access to a robot for more than the time allocated for you. In other words, do not use these sessions for creating the design document and presentation deliverables. You can also develop code by simulating the microphone and speaker of the robot on your local machine. We have suggested some development targets for each week