ERC starting grant CONT-ACT

Control of contact interactions for robots acting in the world (June 2015 - November 2020)

Objectives

What are the algorithmic principles that would allow a robot to run through a rocky terrain, lift a couch while reaching for an object that rolled under it or manipulate a screwdriver while balancing on top of a ladder? By trying to answer these questions in CONT-ACT, we would like to understand the fundamental principles for robot locomotion and manipulation and endow robots with the robustness and adaptability necessary to efficiently and autonomously act in an unknown and changing environment. It is a necessary step towards a new technological age: ubiquitous robots capable of helping humans in an uncountable number of tasks.

Dynamic interactions of the robot with its environment through the creation of intermittent physical contacts is central to any locomotion or manipulation task. Indeed, in order to walk or manipulate an object, a robot needs to constantly physically interact with the environment and surrounding objects. Our approach to motion generation and control in CONT-ACT gives a central place to contact interactions. Our main hypothesis is that it will allow us to develop more adaptive and robust planning and control algorithms for locomotion and manipulation. The project is divided in three main objectives: 1) the development of a hierarchical receding horizon control architecture for multi-contact behaviors, 2) the development of algorithms to learn representations for motion generation through multi-modal sensing (e.g. force and touch sensing) and 3) the development of controllers based on multi-modal sensory information through optimal control and reinforcement learning.

Publications

2021

  1. DeepQ Stepper: A Framework for Reactive Dynamic Walking on Uneven Terrain
    Avadesh Meduri, Majid Khadiv, and Ludovic Righetti
    In 2021 IEEE-RAS International Conference on Robotics and Automation (ICRA) 2021
  2. Meta-learning via learned loss
    S Bechtle, A Molchanov, Y Chebotar, E Grefenstette, L Righetti, G S Sukhatme, and F Meier
    In 25th International Conference on Pattern Recognition 2021
  3. Reactive Balance Control for Legged Robots under Visco-Elastic Contacts
    Thomas Flayols, Andrea Del Prete, Majid Khadiv, Nicolas Mansard, and Ludovic Righetti
    Applied Sciences 2021
  4. Variable Horizon MPC with Swing Foot Dynamics for Bipedal Walking Control
    E Daneshmand, M Khadiv, F Grimminger, and L Righetti
    IEEE Robotics and Automation Letters 2021
  5. Impedance Optimization for Uncertain Contact Interactions Through Risk Sensitive Optimal Control
    B. Hammoud, M. Khadiv, and L. Righetti
    IEEE Robotics and Automation Letters 2021
  6. High-Frequency Nonlinear Model Predictive Control of a Manipulator
    Sebastien Kleff, Avadesh Meduri, Rohan Budhiraja, Nicolas Mansard, and Ludovic Righetti
    In 2021 IEEE-RAS International Conference on Robotics and Automation (ICRA) 2021
  7. Leveraging Forward Model Prediction Error for Learning Control
    Sarah Bechtle, Bilal Hammoud, Akshara Rai, Franziska Meier, and Ludovic Righetti
    In 2021 IEEE-RAS International Conference on Robotics and Automation (ICRA) 2021
  8. Learning a Centroidal Motion Planner for Legged Locomotion
    Julian Viereck, and Ludovic Righetti
    In 2021 IEEE-RAS International Conference on Robotics and Automation (ICRA) 2021
  9. Efficient Multi-Contact Pattern Generation with Sequential Convex Approximations of the Centroidal Dynamics
    B Ponton, M Khadiv, A. Meduri, and L Righetti
    IEEE Transactions on Robotics 2021

2020

  1. An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research
    F Grimminger, A. Meduri, M Khadiv, J. Viereck, M. Wüthrich, M. Naveau, V. Berenz, S. Heim, F. Widmaier, T. Flayols, J. Fiene, A. Badri-Spröwitz, and L. Righetti
    IEEE Robotics and Automation Letters 2020
  2. Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control
    C Mastalli, R Budhiraja, W.X. Merkt, G Saurel, B Hammoud, M Naveau, J Carpentier, L Righetti, S Vijayakumar, and N. Mansard
    In 2020 IEEE-RAS International Conference on Robotics and Automation (ICRA) 2020
  3. Walking Control Based on Step Timing Adaptation
    M Khadiv, A. Herzog, S A A Moosavian, and L Righetti
    IEEE Transactions on Robotics 2020
  4. Learning Variable Impedance Control for Contact Sensitive Tasks
    M. Bogdanovic, M. Khadiv, and L. Righetti
    IEEE Robotics and Automation Letters 2020

2019

  1. Leveraging Contact Forces for Learning to Grasp
    H. Merzic, M Bogdanovic, D Kappler, L Righetti, and J Bohg
    In 2019 IEEE International Conference on Robotics and Automation (ICRA) 2019
  2. Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction
    Y.-C. Lin, B Ponton, L. Righetti, and D. Berenson
    In 2019 IEEE International Conference on Robotics and Automation (ICRA) 2019
  3. A Robustness Analysis of Inverse Optimal Control of Bipedal Walking
    J Rebula, S Schaal, J Finley, and L Righetti
    IEEE Robotics and Automation Letters 2019
  4. Learning to Explore in Motion and Interaction Tasks
    M Bogdanovic, and L Righetti
    In IEEE/RSJ International Conference on Intelligent Robots and Systems 2019
  5. Robust Humanoid Locomotion Using Trajectory Optimization and Sample-Efficient Learning
    MH Yeganegi, M Khadiv, S A A Moosavian, JJ Zhu, A Del Prete, and L Righetti
    In IEEE-RAS International Conference on Humanoid Robots 2019
  6. Curious iLQR: Resolving Uncertainty in Model-based RL
    S Bechtle, Y Lin, A Rai, L Righetti, and F Meier
    In Proceedings of the Conference on Robot Learning 2019

2018

  1. Learning a Structured Neural Network Policy for a Hopping Task.
    Julian Viereck, Jules Kozolinsky, Alexander Herzog, and Ludovic Righetti
    IEEE Robotics and Automation Letters 2018
  2. An MPC Walking Framework With External Contact Forces
    Sean Mason, Nicholas Rotella, Stefan Schaal, and Ludovic Righetti
    In 2018 IEEE International Conference on Robotics and Automation (ICRA) 2018
  3. On Time Optimization of Centroidal Momentum Dynamics
    Brahayam Ponton, Alexander Herzog, Andrea Del Prete, Stefan Schaal, and Ludovic Righetti
    In 2018 IEEE International Conference on Robotics and Automation (ICRA) 2018
  4. Unsupervised Contact Learning for Humanoid Estimation and Control
    Nicholas Rotella, Stefan Schaal, and Ludovic Righetti
    In 2018 IEEE International Conference on Robotics and Automation (ICRA) 2018
  5. Learning Task-Specific Dynamics to Improve Whole-Body Control
    Andrej Gams, Sean Mason, Ales Ude, Stefan Schaal, and Ludovic Righetti
    In 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids) 2018

2017

  1. Pattern Generation for Walking on Slippery Terrains
    Majid Khadiv, S A A Moosavian, Alexander Herzog, and Ludovic Righetti
    In 2017 5th RSI International Conference on Robotics and Mechatronics (ICRoM) 2017
  2. Momentum-Centered Control of Contact Interactions
    Ludovic Righetti, and Alexander Herzog
    2017

2016

  1. On the Effects of Measurement Uncertainty in Optimal Control of Contact Interactions
    B Ponton, S. Schaal, and L. Righetti
    In Algorithmic Foundations of Robotics XII: Proceedings of the Twelfth Workshop on the Algorithmic Foundations of Robotics 2016
  2. Inertial Sensor-Based Humanoid Joint State Estimation
    N Rotella, S Mason, S. Schaal, and L. Righetti
    In 2016 IEEE International Conference on Robotics and Automation (ICRA) 2016
  3. Structured contact force optimization for kino-dynamic motion generation
    Alexander Herzog, Stefan Schaal, and Ludovic Righetti
    In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2016
  4. Stepping Stabilization Using a Combination of DCM Tracking and Step Adjustment
    Majid Khadiv, Sebastien Kleff, Alexander Herzog, S A A Moosavian, Stefan Schaal, and Ludovic Righetti
    In 2016 4th International Conference on Robotics and Mechatronics (ICROM) 2016
  5. Balancing and Walking Using Full Dynamics LQR Control With Contact Constraints
    S Mason, N Rotella, S. Schaal, and L. Righetti
    In 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids) 2016
  6. A Convex Model of Momentum Dynamics for Multi-Contact Motion Generation
    Brahayam Ponton, Alexander Herzog, Stefan Schaal, and Ludovic Righetti
    In 2016 IEEE-RAS 16th International Conference on Humanoid Robots Humanoids 2016
  7. Step Timing Adjustement: a Step toward Generating Robust Gaits
    M Khadiv, A. Herzog, S A A Moosavian, and L. Righetti
    In 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids) 2016

2015

  1. Trajectory generation for multi-contact momentum control
    A. Herzog, N Rotella, S. Schaal, and L. Righetti
    In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) 2015
  2. Humanoid Momentum Estimation Using Sensed Contact Wrenches
    N Rotella, A. Herzog, S. Schaal, and L. Righetti
    In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) 2015