Institute for Intelligent Interactive Systems

Open Opportunities

Advanced Co-Design Framework for Legged Robots ETH Zurich Computational robotics laboratory (Prof. Stelian Coros) This project seeks to advance the field of legged robotics by creating a versatile and accessible co-design framework that integrates mechanical design and control optimization. CAD/CAM Systems, Computer Graphics, Dynamical Systems, Intelligent Robotics, Mechanical and Industrial Engineering, Operations Research, Optimisation, Robotics and Mechatronics Master Thesis, Semester Project

Deliberate design of Digital Avatars for Learning and Creativity ETH Zurich Sensing, Interaction & Perception Lab Other organizations: Computer Graphics Laboratory In this project, we explore the design space of avatars in Virtual Reality to support learning and creativity. Computer Graphics, Computer-Human Interaction Master Thesis

Leveraging Human Motion Data from Videos for Humanoid Robot Motion Learning ETH Zurich ETH Competence Center - ETH AI Center Other organizations: Advanced Interactive Technologies, Course 6: Electrical Engineering and Computer Science, Learning and Adaptive Systems, Robotic Systems Lab The advancement in humanoid robotics has reached a stage where mimicking complex human motions with high accuracy is crucial for tasks ranging from entertainment to human-robot interaction in dynamic environments. Traditional approaches in motion learning, particularly for humanoid robots, rely heavily on motion capture (MoCap) data. However, acquiring large amounts of high-quality MoCap data is both expensive and logistically challenging. In contrast, video footage of human activities, such as sports events or dance performances, is widely available and offers an abundant source of motion data. Building on recent advancements in extracting and utilizing human motion from videos, such as the method proposed in WHAM (refer to the paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"), this project aims to develop a system that extracts human motion from videos and applies it to teach a humanoid robot how to perform similar actions. The primary focus will be on extracting dynamic and expressive motions from videos, such as soccer player celebrations, and using these extracted motions as reference data for reinforcement learning (RL) and imitation learning on a humanoid robot. Engineering and Technology Master Thesis

Collaborative Data Storytelling in Spreadsheets with Large Language Models ETH Zurich Programming, Education, and Computer-Human Interaction Lab (Prof. April Wang) This project aims to transform the way users engage with data in spreadsheets by creating an interactive, collaborative platform for data storytelling. The motivation is to make data analysis more engaging, accessible, and narrative-driven, allowing users to seamlessly weave stories around their data while leveraging the power of large language models (LLMs). The platform will feature a community-based web forum where users can access a variety of public datasets or upload their own. Each dataset can be imported into a storytelling system integrated within the spreadsheet environment. This system will allow users to perform common data operations, such as calculating averages, standard deviations, and generating visualizations (e.g., charts), while the LLM will offer suggestions for a cohesive narrative. For instance, the system can auto-generate explanatory text based on the user’s data manipulations, creating a comprehensive story of the dataset. The goal is to help users articulate insights, uncover trends, and communicate findings in a more structured and compelling way. (Target Venue: ACM UIST 2025) Interdisciplinary Engineering ETH Zurich (ETHZ), Master Thesis

Understanding Youth & Social Media: User Generated Content and Algorithm Bias ETH Zurich Programming, Education, and Computer-Human Interaction Lab (Prof. April Wang) This project seeks to raise awareness among young people about the presence and influence of algorithmic bias in social media apps. Youth often interact with these platforms without fully understanding how their interactions contribute to biased content curation. To address this, we propose the development of a web-based system that simulates a social media app, providing real-time feedback on how user-generated content can influence algorithmic bias. The web system will function as a mock social media platform where users, particularly young people, can post content as they would on real social media apps. When users submit posts, the system will generate a preview that shows how the content spreads through the platform. This preview will visually represent how the content engages with algorithms, potentially amplifying biases based on factors like language, content type, or context. By seeing this in action, users will learn how their posts can unintentionally reinforce algorithmic bias, encouraging them to be more mindful of their contributions. (Target Venue: ACM UIST 2025) Interdisciplinary Engineering Bachelor Thesis, ETH Zurich (ETHZ), Master Thesis

3D Avatar and Scene Interaction, Visualization, and Rendering ETH Zurich Sensing, Interaction & Perception Lab In this project, we aim to develop a visualization tool designed for rendering and interacting with 3D human motion and scenes. Computer Graphics, Computer Software, Computer Vision, Engineering and Technology, Virtual Reality and Related Simulation Bachelor Thesis, Semester Project