MPG ETH CLS Student Projects


A2e27ddf 06bd 40db b571 4f8d5da70c4c.png 500 500

Deep Scale Learning for Visual Motion Estimation (MA/SA)

The goal of this project is to train a deep neural network to estimate scale for a purely visual motion estimation framework. This will enable robots to perform metric ego-motion estimation without use of additional information sources such as an IMU or wheel encoders.

SLAM Machine Learning Python C++ Robotics Computer Vision Convolutional Neural Networks (CNNs)

Read more



D81faf59 9988 47c4 890a ed7c3630b41b.png 500 500

Learning Visual Object Descriptors

The goal of this project is developing and evaluating a machine learning based full-object descriptor algorithm for object retrieval

C++ Python Machine Learning Convolutional Neural Networks (CNNs) TensorFlow Caffe Computer Vision Classification

Read more



08ebbbb2 42b4 402c 9cde a97f8dc7a863.png 500 500

Distributed Wireless Control

In a new research project, we seek to integrate recent advances in wireless networking with networked control to develop a superior solution for reliable and economic wireless control for cyber-physical systems (CPSs).

Distributed control networked control wireless networks cyber-physical systems theory application

Read more



Ee878de2 e66d 4ed4 90b3 879791a6bc20.jpg 500 500

Visual and Event-based Cameras for Robot Navigation

This project aims to explore the benefits of integrating the output of a conventional frame-based camera (capturing visible light) with that of an event-based camera, such as the Dynamic Vision Sensor (DVS) in the context of robot navigation and Simultaneous Localization And Mapping (SLAM).

Camera Calibration DVS Sensor Fusion Event-based processing Real-time SLAM Computer Vision

Read more



0754f77c 659b 4b2c ada2 8f18693e298a.png 500 500

Loop Closure in the Presence of Perceptual Aliasing

The goal of this project is to extend a place recognition system to return not only the best image but also an estimation of the error associated to the matched location to improve place recognition in environments presenting perceptual aliasing.

Place Recognition Loop Closure Odometry/SLAM Perceptual Aliasing Computer Vision

Read more



4b79557a 1019 48f4 81cb 3db0adaee70a.jpg 500 500

Learning Control

Machine learning for advanced control of intelligent systems

Control machine learing adaptive control robotics dynamic systems optimization intelligent systems

Read more