Projects

Memory of Motion (Memmo)

The project Memmo aims to solve the problem of generating complex movements for arbitrary robots with arms and legs interacting in a dynamic environment by 1) relying on massive off-line caching of pre-computed optimal motions that are 2) recovered and adapted online to new situations with real-time tractable model predictive control and where 3) all available sensor modalities are exploited for feedback control going beyond the mere state of the robot for more robust behaviors.

Compliant Feedback Control of Legged Robots

The goal of this project is to achieve reliable locomotion behaviors in semi-structured environments with the humanoid robots HRP-2 and Pyrene. This project relies on model-based feedback control techniques, such as inverse-dynamics and model predictive control.

Robust Robotics

Nowadays legged robots are capable of performing locomotion and manipulation in semi-structured environments, but with a low level of reliability, which makes their application in disaster-recovery scenarios difficult, if not impossible. However, if we look at the results that researchers in robotics and animation have achieved in simulation, we can see that simulated robots/avatars can easily and reliably perform dynamic movements such as walking, running, jumping, kicking. What is preventing real robots from showing similar performance?

Recent Publications

More Publications

Talks

Balancing Legged Robots on Visco-Elastic Contacts - Workshop @ RSS 2019, Freiburg, Germany

The rise of the robots - GIZ tech2D, Technology Forum for Sustainable Development 2018, Frankfurt, Germany

Addressing Constraint Robustness to Torque Errors in Task-Space Inverse Dynamics - RSS 2015, Rome, Italy

Teaching

Advanced Optimization-Based Robot Control

Industrial Engineering Department, 2020, University of Trento (Trento, Italy)

A 60-hour course for master students. This course focuses on control of robotic systems, with special attention to methods based on optimization techniques. After reviewing the basic principles of robot modeling and numerical optimization, students will learn different control techniques, from the simplest and most well-known, to the most recent and advanced. Methods will be first studied in theory, and then implemented in simulation (with the Python language) to gain practical experience. The lab sessions will focus on industrial manipulators and legged robots, but most of the studied methods could also be applied to flying and wheeled robots. After completing the course, students will be able to: - understand the working principles of several control algorithms for robotic systems - choose the appropriate approach(es) to control a specific system for a given target application - implement, tune, and test control algorithms with the Python language

Prerequisite

Students should have consolidated knowledge in

  • Mechanics: Newtonian dynamics in 3D, homogeneous transformation for expressing vectors in different frames
  • Mathematics: linear algebra (eigenvalues, eigenvectors, rank, nullspace), multivariable differential calculus
  • Systems: state space representation, stability criteria for linear dynamical systems
  • Programming: object-oriented programming (if-else, for, while, objects, polymorphism)

Here you can find videos and slides of all the lectures of two academic years (19 /20 and 20 /21, even though in 19 /20 the first lectures have not been recorded). You can also find a virtual machine (password: iamarobot) containing the software needed for the lab sessions.

Optimization-Based Robot Control

Industrial Engineering Department, July 2019, University of Trento (Trento, Italy)

A 12-hour course for PhD students about reactive control (TSID) and trajectory optimization for humanoid robots. Here you can find the videos of all the lectures (except the first one, which wasn’t recorded). Here you can find the slides:

Task-Space Inverse Dynamics (TSID)

Memmo Winter School, January 28-31 2019, IDIAP (Martigny, Switzerland)

A 3-hour class about TSID, covering both theory and implementation. Here you can find videos and slides:

I have also given a class on robust TSID:

Events

“Second Workshop on Perception and Planning for Legged Robot Locomotion in Challenging Domains”

Organizers: D. Kanoulas, I. Havoutis, M. Fallon, A. Del Prete, E. Yoshida.

Full-day workshop at ICRA 2017, Singapore.

“Robust Optimization-Based Control and Planning for Legged Robots”

Co-organized with Russ Tedrake, (MIT, USA) and Alexander Herzog (Max Planck IS, Germany).

Full-day workshop at ICRA 2016, Stockholm (Sweden).

“Torque-Controlled Humanoids”

Co-organized with Luis Sentis (University of Texas, Austin).

Full-day workshop at Humanoids 2013, Atlanta (Georgia, USA).

Contact