News

  • the IEEE RAS TC on Model-based Optimization for Robotics selected our inverse-dynamics MPC paper as finalists. This year jury members were Dr. Ko Ayusawa, Dr. Fanny Ficuciello, Dr. Zachary Manchester, Dr. Ludovic Righetti, Dr. Olivier Stasse, and Dr. Wei Zhang. The TC received 25 submissions and 11 were selected for jury evaluation. The quality of the papers was particularly high and we had a few tied-up top papers which required a second round evaluation by the jury members. We are deligthed to this recognition, which shows the high quality of the research work we conducted at the Robot Motor Intelligence (RoMI) lab.

  • Carlos Mastalli, Julian Eßer, Ioannis Havoutis, Shivesh Kumar, Gabriel Margolis, Claudio Semini, Olivier Stasse, and Oliver Urbann are organizing the first edition of the Workshop entitled 'Loco-Manipulation: Algorithms, Challenges & Applications' at ICRA'24, Yokohama, Japan.

    Locomotion and manipulation are two essential skills that enable robots to interact effectively with their environment. Recently, there has been significant interest in the robotics community regarding the integration of these skills, known as loco-manipulation. In this workshop, we will explore the latest advancements in loco-manipulation, covering topics such as

    1. planning and whole-body control strategies/li>
    2. perception and machine learning approaches
    3. the mechanical design of the loco-manipulation hardware

    We will also discuss the challenges that arise when combining these two skills, such as balancing stability and dexterity. This workshop aims at connecting people from various backgrounds with a rich mix of inspiring talks, interactive panel discussions, and encouraging poster sessions in the emerging field of loco-manipulation.

  • Carlos Mastalli, Francesco Ruscelli, Enrico Mingo Hoffman, and Luis Sentis are organizing the second edition of the Workshop entitled 'Advancements in Trajectory Optimization and Model Predictive Control for Legged Systems' at ICRA'24, Yokohama, Japan.

    Pursuing the thread initiated with the first edition of this workshop, we will focus on trajectory optimization and optimal control: successful approaches that exploit the robotic systems' dynamics, particularly under-actuated ones. In addition to traditional control techniques, this second edition of the workshop delves into the integration of machine learning approaches, such as reinforcement learning and deep learning. These approaches have gained tremendous traction in the field of planning and control due to their adaptability and ability to handle complex, non-linear systems.

    This will be a fantastic opportunity to share your thoughts and recent work related to some trendy topics like:

    1. Legged Loco-Manipulation
    2. Offline and Online Planning and Control
    3. Whole-Body Control
    4. Obstacles and Environments Modeling
    5. Co-design of Robot Structures
    6. Algorithms and Software Tools
    7. Optimal control and MPC methods
    8. Optimal Control and Reinforcement Learning synergies
    9. Real Robot Application

  • Our PI Carlos Mastalli introduced our research efforts on advancing autonomous inspecting capabilities on quadruped robots. Our work is featured in the Episote 5: Mechanical Menagerie. In this episote, Tony Robinson goes on safari to find majestic machines that are inspired by the animal kingdom and gets hands-on with a life-saving mechanical octopus.

  • Our PI Carlos Mastalli presented our work on 'agile and perceptive locomotion in legged robots' at IROS'23 Workshop on Reactive and Predictive Humanoid Whole-body Control (https://iros-2023-humanoid.github.io) in Detroit, USA. Carlos introduced our novel approaches for footstep region selection and swing trajectory planning. Additionally, he delved into the details of our inverse-dynamics MPC approach, including our numerical optimization and feedback MPC techniques. Our work enables the ANYmal robot to traverse challeging terrain conditions, such as damaged stairs and boxes.