Bsc/Msc/PhD

PhD Positions

Every year, the Dynamic Legged Systems lab (HyQ Project) has open PhD positions in the PhD Program Bioengineering and Robotics (curriculum: Advanced and Humanoid Robotics) of the Istituto Italiano di Tecnologia (IIT), an English language Institute. All the positions are fully funded.

Bachelor and Master Students

The Dynamic Legged Systems lab is constantly looking for Bachelor and Master students who wish to perform an intership or their Bsc/Msc thesis in our labs. A list of currently available projects can be found below. To learn more about the project description, requirements and application procedure, click on the "Read More" button for each of the projects. For spontaneous applications, apart from the projects below, please send your CV to This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Currently available projects

Implementation of a Decision Maker for Locomotion (internship)

The aim of this student project is to increase the level of autonomy of our locomotion framework. An effective locomotion framework encompasses different levels of autonomy. At a lower level we have several locomotion strategies (e.g. different gaits) that take care of keeping the stability while dealing with the terrain features but require high level commands (e.g. desired velocities from the user). On the other hand, at a higher level, the focus is on improving autonomy, by orchestrating the locomotion modules to fulfill higher level user requirements. These algorithms should take care of choosing the most suitable locomotion strategy and adapting the gait parameters (according to the terrain difficulty) in order to ensure task accomplishment (e.g. reach a goal, pick up an object).
Read More

Model-Based Motion Planning for Quadruped Robots (internship)

The aim of this student project is to support the team’s effort to extend of the motion capabilities of the HyQ robot to adapt its gait to complex geometry environments using nonlinear optimization. In this internship project we propose to support the team in the writing of new formulations. Depending on the time availability, the student may also be asked to contribute to the synthesis of a new optimization solver tailored for legged locomotion applications.
Read More

Machine Learning Model Implementation for Legged Robots (internship)

This project consists on the implementation of machine learning algorithms for a range of diverse applications for quadruped locomotion (vision, model reduction, navigation, feasibility constraints handling) to adapt to complex environments. We are currently looking for a highly motivated, full-time candidate to do an internship working on the implementation, evaluation and further development of learning algorithms into our locomotion framework.
Read More

State Estimation for Legged Robots (internship)

This project aims to further improve the implementation of state estimation algorithms for a range of diverse applications for quadruped robots. Some examples include probabilistic foot contact estimation and hetrogeneous sensor fusion for accurate state estimation. We are currently looking for a highly motivated, full-time internship position to work on the implementation, evaluation, and further development of state estimation algorithms into our legged robot framework.
Read More

Contact Detection and Localization in Legged Robots (internship)

Our team is currently looking for a highly motivated student to conduct studies on algorithms for leg collision detection and localization. The accuracy of such information has direct impact on the locomotion performance and robustness, with strong impacts also on the algorithms responsable to estimate the robot world position and velocities. Therefore, precisely detecting where contacts happen is of high relevance for the robot navigation quality on natural and unstructed environments. In this project the student will have the opportunity to: do scientific development with state-ofthe-art algorithms; simulate proposed algorithms on the DLS software framework and experimentally test them on the real robot HyQ.
Read More

Computer Vision for Legged Robots (internship)

Autonomous legged robots are required to handle a wide range of tasks in complex environments. Current computer vision algorithms are not robust in dynamic environments, however, using computer vision is critical to improving autonomy. It is well-known that video images provide rich information about the environment which is critical for localization in environments without a priori maps. The appointed candiate will work on the development and implementation of state-of-the-art computer vision algorithms
Read More