Master/Semester projects

Overview of available semester/master projects

DataScienceHardwareUX
Developement
Back end software development/
software architectures
DataBase ManagementApplication DevelopementSystem/low level programming
Learning to explain the predictions of neural networksX
Collaborative Text Analysis and Prediction – FULLX
The Stack Overflow Annual Survey:
A look into the future?
(Data Science) – FULL
X
A free MOOC market:
What makes a course successful?
(Data Science) – FULL
X
Deep design exploration
AR Application development
for learning Statics
XX
Idle Behavior Generation
Module for QTrobot – FULL
XX
User-Proxemics based Behavior
Generation Module for QTrobot – FULL
XX
Cognitive and Physical
Rehabilitation Game using Cellulo
XXX
Designing a 3D rehabilitation
game with Cellulo and IMU
XXX
Analysis of eye-gaze cues of
children playing games
X
Modular Cellulo topX
Developing a simulator for CelluloXXX
Tangible Classroom OrchestrationXXX
Cellulo shepherding activityXXXX
Localizing robots in classrooms
to support teacher awareness
XXX
Tangible Classroom OrchestrationXXX
Developing an event chart for
learning activities involving robots
XX

The CHILI lab is inventing learning technologies that exploit recent advances in human-computer interaction (e.g. eye tracking, augmented reality, …) and in human-robot interaction. We are working on several educational platforms described below. Each platforms offers possibilities for semester and master projects. While semester projects are often limited to development, master projects usually include an empirical study with learners, supervised by our team.  The platforms are:

  1. NEW ! We have funding for supporting master theses in the field of learning technologies in Fall 2019 and Spring 2020. In 2017, EPFL has launched the Swiss EdTech Collider which now gathers 77 start-ups in this field.  Some of them will be interested to host master theses. You will be supervised by Prof. Dillenbourg or his team members but you will  located in a start-up (different cities in CH).  Contact: pierre.dillenbourg (at) epfl.ch 
  2. A variety of projects in LEARNING ANALYTICS, i.e.  data sciences applied to education are offered by my lab (contact: jennifer.olsen (at) epfl.ch) as well  by the Center for Digital Education. See their project list here.
  3. REALTO and Training Needs Analysis are two parts of the project DUAL-T, which focuses on the Swiss Vocational Education and Training system. Realto is a social platform for vocational education. Apprentices collect pictures at the workplace and upload them on their class flow, where several picture annotation tools and augmented/virtual reality tools are available. Training needs analysis concerns itself with finding methods for identifying the newest skills needed for people in a profession, and involves the use of data science and applied machine learning. Current projects concern the augmented/virtual reality tools, as well as training needs analysis for software developers. Contact: kevin.kim (at) epfl.ch
  4. CELLULO is a small robot for education and rehabilitation. It moves by itself and can be moved by pupils. The hardware is ready and projects concern the software environments as well as designing and experimenting with new learning activities and rehabilitation games. Contact: hala.khodr (at) epfl.ch, arzu.guneysu (at) epfl.ch
  5. JUSTHINK project aims to improve the computational thinking skills of children by exercising algorithmic reasoning with and through graphs, where graphs are posed as a way to represent, reason with and solve a problem.
  6. CO-WRITER is a project in which kids who face writing difficulties are offered to teach Nao how to write. Nao is a small humanoid robot available on the market. The projects concerns smoothening the interaction between the robot and young children. Contact: thibault.asselborn (at) epfl.ch
  7. CLASSROOM ORCHESTRATION is a project to support teachers for managing learning activities with technologies, specifically educational robots. The project concerns designing awareness tools and intervention strategies about what students are doing with robots in the classroom. Contact: [email protected]

Some of these projects are described below, but since research is moving on permanently, we always have new opportunities. You can always contact the names above or pierre.dillenbourg (at) epfl.ch if you are interested in advancing digital education.


Learning Analytics 

Learning analytics involves applying techniques in data science for optimizing and understanding learning. In CHILI, the projects range from applying existing algorithms to new data sets, comparing the use of algorithms to address a goal, and visualizing data in a meaningful manner to support learning. 

Through written answers, we can assess a student’s understanding of a topic that does not emerge through test scores. Text-based answers can be difficult to assess due to the open nature of the questions. Within the CHILI Lab, we work on finding patterns within educational data to provide insights around the learning process. In this project, you will apply learning analytics methods, including text analytics, to find patterns among text answers and other learning variables. The goal of this project is to find patterns in how students answer short answer questions and how these features of the text relate to learning gain, the learning context, and student motivation.

For the project you, will have around 7,000 short answers around fractions learning to assess across over 200 students. You will use machine learning techniques to find patterns in the text answers, cluster different patterns, and find relationships/predictions of other learning measures.

Prerequisites: knowledge or interest in learning text mining techniques (feature extraction and analysis), prediction methods, clustering

Contact: jennifer.olsen (at) epfl.ch


REALTO and Training Needs Analysis

REALTO is a social platform for vocational education. Apprentices collect pictures (and videos) at the workplace and upload them on their class flow. Supervisors and teachers have the possibility to provide feedback on the students private flow and peers have the possibility to comment on other students pictures and videos. Over 2000 apprentices from a wide variety of disciplines such as florists, carpenters, fashion designers are currently registered on REALTO.

Training Needs Analysis is the identification of skills that will help people in a profession improve their performance and obtain the skills they need. Currently, we are focusing on performing training needs analysis on software developers, for whom we have much publicly available data, in the form of Stack Overflow questions, Stack Overflow Developer Survey, and Google Trends.

Following are the list of available projects and their descriptions. In case of interest, please send an email to the contact person. In your email, please include your CV and a short description of your specific interests.

Stack Overflow is a well-known Q&A website for developers, where users may ask questions and give answers about a wide variety of programming issues. Stack Overflow also runs an annual developer survey, where the participants answer questions about the programming languages and frameworks they use and the methods they have used to learn new languages. This annual survey happens in January and has been receiving over 60,000 responses each year since 2017, creating a rich dataset of what frameworks and languages developers used in the preceding year, what they will use in the next year, what kind of job they have, etc.

In this project, we look at data from the Developer Survey, along with data from Stack Overflow and Google Trends, to answer questions such as:

  • Are Google search volumes predictive of the changes that occur in programming language and framework usage, as indicated by the Developer Survey? In other words, how well can we predict the results of the next developer survey only using data that’s publicly available beforehand?
  • The question above, but inverted: are these transitions from one technology to another predictive of trends that will be seen throughout the year on Google Trends?
  • Do technologies that are becoming more popular also experience a surge in question counts on Stack Overflow? If that is the case for some technologies and not others, what are the common characteristics of each group of technologies?

Requirements are familiarity with Python, some experience in data analysis and applied machine learning, and preferably some familiarity with time series analysis. Having taken the course Applied Data Analysis (CS-401) or Lab in Data Science (EE-490) is a plus.

Contact: ramtin.yazdanian [at] epfl.ch

Udemy (udemy.com) is a platform for sharing MOOCs, where skill-centric, self-paced MOOCs can be uploaded by anyone. It therefore essentially constitutes a free MOOC market, as opposed to most MOOC platforms which are controlled by specific institutions. This platform offers many opportunities for people who are looking to share their expertise with others, either for free, or for a fee.

In this semester project, you will use various data analysis tools (machine learning models, statistical tests, etc.) to investigate and understand the dynamics of Udemy. You will be looking to answer questions like the following:

  • Does the (relative) popularity of these courses mirror the (relative) popularity of their subject matter on Google Trends? In other words, is demand as represented by course subscription mirrored by demand as represented by search volumes?
  • What are the common traits of courses that end up being successful?
  • Are the earliest courses the most successful in their subject matter? What are the common traits of courses that get a head start but don’t end up being the most successful in their subject matter? 
  • What are common patterns observable in the appearance of courses on a new subject? Is there a process we can identify?

Requirements are familiarity with Python, general data analysis, and some applied machine learning. Having taken the course Applied Data Analysis (CS-401) or Lab in Data Science (EE-490) is a plus.

Contact: ramtin.yazdanian [at] epfl.ch

Description: On Realto, apprentices upload pictures taken from their workplaces (e.g., bouquets by florists or chairs by chair makers). We believe that these pictures can be a great source of design exploration. The idea is to allow the apprentices to explore design space by exploring variations of their own uploaded design. In this story, the goal of this project is to implement an algorithm that learns to generate design variations using convolutional neural networks.

Prerequisites: experience in following topics or interest in learning: deep learning, image processing, Python

Contact: kevin.kim (at) epfl.ch

Description:

Civil engineering and architecture students need to develop an ability to reason qualitatively about forces acting on building structures in order to design safe and aesthetic buildings. Within the field of educational technologies, interactive simulations have often been used to develop students’ qualitative reasoning. In the CHILI lab we have previously designed an app to develop carpenter apprentices’ intuition about building physics of structures. More information about the former project here

In this project, you will modify an existing app for learning statics that connects with tangible structures via an AR marker to incorporate additional features including visualizations for the changes in the state of the tangible structure, graphs and a data logger for logging user interactions with the interface.

Prerequisites: Experience in the following skills or interest in learning: AR application development, Unity development platform

Contact: aditi.kothiyal(at)epfl.ch


JUSThink

The JUSThink project aims to improve the computational thinking skills of children by exercising algorithmic reasoning with and through graphs, where graphs are posed as a way to represent, reason with and solve a problem. It targets at fostering children’s understanding of abstract graphs through a collaborative problem solving task, in a setup consisting of a QTrobot as the humanoid robot and touch screens as input devices.

To help improve the learning outcomes in this context of human-human-robot interaction, this project aims to use data generated in the experiments to explore models of engagement and mutual modelling for adapting the robot behavior in real time. 

QTrobot is a small humanoid robot capable of expressing a wide range of behaviors through composing various gestures, facial emotions and speech acts, which are essential for enhanced user experience and interaction. Specifically, a key element for a socially intelligent robot in educational settings is “What should I do when I don’t have anything to do?”. This project aims at improving what the humanoid robot does when it is idle, i.e. when it has no specific action to perform, see [1].

Well-designed idle behaviors (outside and inside the educational activity) could improve the user experience in terms of the perception of the robot and engagement with it and the whole activity, which could result in better learning outcomes. Thus, the purpose of this project is: 1) to develop idle behaviors that are predicted to not be disruptive towards the learning task, 2) to explore effective methods for the evaluation of such behaviors in terms of learning outcomes. Concretely, implementing the idle behavior generation module will in effect expand the current behavior (gesture, emotion, speech combined) library. The prerequisites for applying include experience in the following or interest in learning: ROS, python, git. A small user-feedback study may be conducted at the end to validate the QTrobot Idle Behavior Module.

[1] T. Asselborn, W. Johal, and P. Dillenbourg, “Keep on moving! Exploring anthropomorphic effects of motion during idle moments,” in 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2017, pp. 897–902.

Contact: utku.norman (at) epfl.ch  or jauwairia.nasir (at) epfl.ch or barbara.bruno (at) epfl.ch

This project aims to explore user-proxemics based behaviors for an immobile QTrobot (a small humanoid robot) in the context of Human-Robot Interaction and specifically in educational settings. In order for the robot to seamlessly integrate with humans in an educational environment, a key consideration for its design is to have appropriate behaviors when a person/multiple people approach it physically (within a certain radius), i.e., 1) to know when and how to be attentive to them, and 2) when and how to end the interaction. Such behaviors can eventually dictate people’s perception of the robot and the amount of information people are willing to share with the robot (psychological distancing [1]). 

In an educational context, where the aforementioned interaction is followed by a learning activity in which the QTrobot is expected to give instructions, guidance, and motivation, the perception of the robot can greatly influence the willingness of the participants to engage/follow it. The student undertaking the project will investigate 1) detection of user-proxemics as a stand-alone sub-module that informs 2) the behavior generation sub-module (inside and outside the activity) including gaze, head movement, gestures, dialogue generation, etc. The prerequisites for applying include experience in the following or interest in learning: ROS, python, git. A small user-feedback study may be conducted at the end to validate the QTrobot Behavior Module. 

[1] J. Mumm and B. Mutlu, “Human-robot proxemics: Physical and psychological distancing in human-robot interaction,” 2011 6th ACM/IEEE International Conference on Human-Robot Interaction (HRI), Lausanne, 2011, pp. 331-338.

Contact: jauwairia.nasir (at) epfl.ch or utku.norman (at) epfl.ch or barbara.bruno (at) epfl.ch


CoWriter

The CoWriter Project aims at exploring how a robot can help children with the acquisition of handwriting, with an original approach: the children are the teachers who help the robot to better write! This paradigm, known as learning by teaching, has several powerful effects: it boosts the children’ self-esteem (which is especially important for children with handwriting difficulties), it get them to practise hand-wrtiing without even noticing, and engage them into a particular interaction with the robot called the Protégé effect: because they unconsciously feel that they are somehow responsible if the robot does not succeed in improving its writing skills, they commit to the interaction, and make particular efforts to figure out what is difficult for the robot, thus developing their metacognitive skills and reflecting on their own errors.


Cellulo

In the Cellulo Project, we are aiming to design and build the pencils of the future’s classroom, in the form of robots. We imagine these as swarm robots, each of them very simple and affordable, that reside on large paper sheets that contain the learning activities. Our vision is that these be ubiquitous, namely a natural part of the classroom ecosystem, as to shift the focus from the robot to the activity. With Cellulo you can actually grab and move a planet to see what happens to its orbit, or vibrate a molecule with your hands to see how it behaves. Cellulo makes tangible what is intangible in learning.

In the Cellulo project, we are designing tangible robots to be used in games for rehabilitation and healthy ageing. Our robots operate on tabletop paper sheets and are used as game elements where they can be physical input devices, objects and/or autonomous agents, moving and being moved, possibly at the same time.

One of our current goals is to explore game design options that create engaging interactive games through these tangible robots to promote Healthy Ageing.Following this research direction, and relying on the unique functionalities of Cellulo (i.e. haptic feedback, touch sensors and submillimeter precision localisation), we designed a physical Pacman game with Cellulo robots, tested it with over 80 participants including older adults and patients recovering from stroke, and found it to be indeed a good training for upper-arm motor learning. You can find the patients playing Pacman within the therapy concept in the video link: https://drive.google.com/file/d/0B8UFszzja-gPR21tellfVnJzRmM/view?usp=sharing 

However, physical training is only half of the story in the specific context of Healthy Ageing and Stroke Rehabilitation. Cognitive training, i.e., stimulating intellectual functions and processes such as attention, memory, judgement, reasoning and decision making, is crucial to slow down cognitive decline and thus enhance independent living and quality of life.

The goal of this project is to develop a physical Memory game with Cellulo robots, that combines configurable physical and cognitive training features. The LEDs on the top of the robots, or haptic feedback, can be used to define pairs, and the gameplay can require that one robot is physically moved towards its twin, to couple the cognitive and physical training. The resulting game will have configurable cognitive and physical features to allow for multiple levels of difficulty both in terms of cognitive and physical functions. A small healthy-user study will be conducted at the end to validate the player interaction with the developed game.

Prerequisites: Experience in the following skills or interest in learning: Qt/QtQuick development, QML programming, game design, git.
Contact: arzu.guneysu (at) epfl.ch, barbara.bruno (at) epfl.ch 

The goal of this project is to recognise selected 3D arm gestures for interaction with Cellulo robots. Using a wearable device, we can define and detect a set of rehabilitation exercise motions and use them to select and control one or many Cellulo’s. The two technologies are already integrated through ROS and a pointing gesture recognition system is implemented (building on the framework previously used to control small drones, as you can see from this video link.

This project will focus on the design of the 3D game by combining the Cellulo platform with one or two IMU sensors placed on the wrist of the patient in order to enable rehabilitation activities in the 3D space. The project will require:

  • Design of a game using the 3D space and a map for interaction with the robots
  • Detecting basic 3D upper limb exercise gestures through IMU data (at most 4-5 gestures) and mapping them to different robot behaviors
  • Handling the switch between continues control of the robots (through pointing gesture) and exercise activity detection.
  • A small healthy-user study will be conducted at the end to validate the player interaction with the developed game.

This project is a continuation of a collaborative project between the CHILI Lab and IDSIA where you can find the corresponding report in infoscience.

Prerequisites: Experience in the following skills or interest in learning Python, ROS, Game Design, Human Activity Recognition, git.
Contact: barbara.bruno (at) epfl.ch, arzu.guneysu (at) epfl.ch, hala.khodr (at) epfl.ch

Gaze cues are effective factors in determining the focus of our attention. In this project we aim to extract inattention and impulsivity (acting before thinking) cues from eye-gaze data collected from healthy children, children having attention problems and high potential children while they are playing our Cellulo Pacman Game and Cellulo Imitation Task.  These cues can be quantified by different measures such as total time child looking at the ghost, total time child looking at the targets etc. The project will investigate how these two games and game hardness (increased speed.) affects the attention of different groups of children and what is the relationship between game performance and both inattention and impulsivity. The project will consist of annotation of the eye-gaze data to extract meaningful cues, analysis of eye-gaza data as well as game-play data of the children. Main questions we want to answer are:

  • How inattention/divided attention metrics correlate with game performance?
  • How much children can maintain their attention during the game and between games?
  • Are impulsivity and inattention higher in imitation game (a task based game) compared to Pacman (complex game)?

Prerequisites: Experience in the following skills or interest in learning: data analysis, eye-gaze data, git.
Contact: arzu.guneysu (at) epfl.ch, jennifer.olsen (at) epfl.ch

In the Cellulo project, we are designing tangible swarm robots to be used in elementary school classrooms for learning activities. In its current version, the Cellulo top has illuminated touch buttons. In this project, we would like to have a modular top which will allow us to add/change peripherals, such as an illuminated touch buttons, a force sensor, a 9-axis IMU, a gripper, an ACM. The student will:

  • Re-design the top to allow an easy modular change
  • Design the electronics and printed circuit board necessary for the communication to the main microcontroller.
  • Choose one example of a peripheral and Implement the firmware to demonstrate the idea

Prerequisites: Experience in the following skills or interest in learning. Embedded systems design, electronics design, mechanical design, prototyping

Contact: hala.khodr (at) epfl.ch , arzu.guneysu (at) epfl.ch

In the Cellulo project, we are designing tangible tabletop robots to be used in a wide variety of applications ranging from classroom learning activities for children and games to physical and cognitive rehabilitation for older adults and people suffering from motor/cognitive disabilities. The Cellulo robots can move and localize themselves on tabletop paper sheets, as well as interact with the user via touch sensors, force feedback, and LEDs.

The goal of this project is to support the creation of new activities using Cellulo as core element, by developing a simulator for the robot. Specifically, starting from an existing Cellulo simulator developed with Webots (https://www.cyberbotics.com/), the student will:

  • tune the model parameters to correctly represent the real robots’ dynamics and kinematics (updating and revising the existing model)
  • enhance the existing simulator with Cellulo’s sensors and interaction elements, with a specific focus on haptic interaction, by simulating human withholding of the robot via the long-pressing of mouse keys and the robot’s force feedback via visual display of the force vector

Prerequisites: Experience in the following skills or interest in learning: Robot simulators, C programming, ROS, git.

Contact: barbara.bruno (at) epfl.ch & hala.khodr (at) epfl.ch

[Cross listed under Classroom Orchestration]

Within the CHILI Lab, we work on both tangible robotics and classroom orchestration. In this project, we aim to connect these two parts of the lab by using the tangible robots for control and awareness aspects of the classroom orchestration.

In this project, you will work with two prominent technologies in the lab: Cellulo and CHILI FROG. Cellulo is a tangible tabletop robot that moves and can be moved on printed paper sheets (with sub-mm localization) and that can provide both visual and haptic feedback. CHILI FROG is an online orchestration engine that supports the running of digital learning activities in the classroom.

The goal of this project is to develop Cellulo as a tool for classroom orchestration through its connection with CHILI FROG. The project will consist of two components: the control of Cellulo by the teacher to take orchestration actions and the integration of Cellulo data in CHILI FROG, to make the teacher aware of classroom information. The resulting design will be able to take configurable paper sheets to express different types of orchestration actions. If interest and time permitting, a small user study can be conducted at the end of the project to validate the interactions and awareness with users.

In this project, you will be developing the shared information between Cellulo and CHILI FROG in both directions, developing the awareness indicators, and different ideas for orchestration maps with the support of the project contacts.

Prerequisites: QML programming, git, Javascript/REACT

Contact: barbara.bruno (at) epfl.ch, jennifer.olsen (at) epfl.ch, aditi.kothiyal (at) epfl.ch

In the Cellulo Project, we are exploring new ways of human learning by interacting with tangible swarms, with the ultimate goal to design a play-based learning environment to learn complex systems. A distinctly “swarm-ish” interaction type is to indirectly influence a swarm by changing the environment in which it operates. Among the examples of indirect swarm-manipulation provided by nature, the shepherding problem is particularly fascinating: how can one control the shepherds such that they gather the sheep and herd them towards a goal location (https://youtu.be/tDQw21ntR64)?

In this project, we aim at replicating that scenario, using Cellulo robots as the sheep while the humans will be controlling the shepherds. The goal of the project is to develop the activity, to study how and to what extent novices can learn to control a swarm through environmental influence.

Prerequisites: Experience in the following skills or interest in learning: Qt/QtQuick development, QML programming, game design, git.

Contact: hala.khodr (at) epfl.ch, barbara.bruno (at) epfl.ch


Classroom Orchestration

[Cross listed under Cellulo]

Within the CHILI Lab, we work on both tangible robotics and classroom orchestration. In this project, we aim to connect these two parts of the lab by using the tangible robots for control and awareness aspects of the classroom orchestration.

In this project, you will work with two prominent technologies in the lab: Cellulo and CHILI FROG. Cellulo is a tangible tabletop robot that moves and can be moved on printed paper sheets (with sub-mm localization) and that can provide both visual and haptic feedback. CHILI FROG is an online orchestration engine that supports the running of digital learning activities in the classroom.

The goal of this project is to develop Cellulo as a tool for classroom orchestration through its connection with CHILI FROG. The project will consist of two components: the control of Cellulo by the teacher to take orchestration actions and the integration of Cellulo data in CHILI FROG, to make the teacher aware of classroom information. The resulting design will be able to take configurable paper sheets to express different types of orchestration actions. If interest and time permitting, a small user study can be conducted at the end of the project to validate the interactions and awareness with users.

In this project, you will be developing the shared information between Cellulo and CHILI FROG in both directions, developing the awareness indicators, and different ideas for orchestration maps with the support of the project contacts.

Prerequisites: QML programming, git, Javascript/REACT

Contact: barbara.bruno (at) epfl.ch, jennifer.olsen (at) epfl.ch, aditi.kothiyal (at) epfl.ch