Run TFLITE models on the web
Using either the TFJS Task API or the TFLITE Web API you can now deploy Tensorflow Lite models on the web without even needing to convert them into …
Robotics Researcher at ETH Zürich
I'm a Master's student in Robotics, Systems and Control at ETH Zürich. My research focuses on state estimation and autonomy for quadrotors, multi-agent drone systems, and reinforcement learning. I'm currently working on RL-based sign language interpretation with a humanoid robot.


Through a series of collaborative competitions, the Sapience initiative fosters innovation in search and rescue …

HASCY is a remote-controlled sled that drives on a rail that is mounted at the top of a tunnel. It is equipped with …

This project presents a multi-mission transformer robot capable of operating both as a ground …

This project implements real-time gesture classification using the uMyo EMG sensors. The system is designed to be …

Extended an existing Deep Reinforcement Learning navigation framework to support the TurtleBot3 platform with realistic …

This page contains a short collage of some of the hardware projects I worked on over the years, starting with school …
Using either the TFJS Task API or the TFLITE Web API you can now deploy Tensorflow Lite models on the web without even needing to convert them into …
The TensorFlow Lite Model Maker library is a high-level library that simplifies the process of training a TensorFlow Lite model using a custom …
D2Go is a production-ready software system from FacebookResearch, which supports end-to-end model training and deployment for mobile platforms. D2Go …
TensorFlow.js is a deep learning library providing you with the power to train and deploy your favorite deep learning models in the browser and …
With the recently released official Tensorflow 2 support for the Tensorflow Object Detection API, it's now possible to train your own custom object …