Ludovic Righetti

Research Group Leader

Office: N2.010
Max-Planck-Ring 4
Tübingen
Germany

+49 7071 601 1825

https://mg.is.tuebingen.mpg.de/

Since September 2017, Ludovic Righetti is an Associate Professor in the Electrical and Computer Engineering Department and in the Mechanical and Aerospace Engineering Department at the Tandon School of Engineering of New York University. He is also a Senior Researcher at the Max-Planck Institute for Intelligent Systems (MPI-IS) in Tübingen, Germany.

He leads the Machines in Motion Laboratory at New York University and the Movement Generation and Control group at MPI-IS.

A complete list of his publications is available on his NYU laboratory website or on Google Scholar

If you are interested in working with us, either at MPI or NYU, please check out this page first https://wp.nyu.edu/machinesinmotion/working-with-us/ Any inquiry that does not contain: a CV, an unofiicial transcript and a clear description of your background, research interests and how they relate to our research will not receive an answer.

Autonomous Robotic Manipulation

We have developed algorithms which enable an autonomous manipulation system to grasp a wide range of objects and to perform a certain number of manipulation tasks, such as drilling, using a stapler, unlocking a door with a key or changing a tire \cite{Righetti_AR_2013}. More generally, we are interested in providing complete integra...

Ludovic Righetti Mrinal Kalakrishnan Peter Pastor Manuel Wüthrich Alexander Herzog Jeannette Bohg Stefan Schaal

Inverse Optimal Control

Tuning and designing robotic behavior by combining elementary objective terms is a tedious task which generally consists of finding proper representations for each new skill. Inverse Optimal Control (IOC) allows, by specifying a set of basis functions (or features), to learn the right association of objective terms defining a policy...

Jim Mainprice Mrinal Kalakrishnan Peter Pastor Nathan Ratliff Ludovic Righetti Stefan Schaal Andreas Doerr

Modeling Human Movement

An expressive model of human motion is the key component of methods for action classification, motion prediction and synthesis. To that end, we are exploring several deep network architectures to predict human movement.

Current methods for motion prediction typically do not work for a wide range of...

Julieta Martinez Judith Bütepage Javier Romero Hedvig Kjellström Michael Black Ludovic Righetti Partha Ghosh Sergey Prokudin

Motion Optimization

Motion generation is increasingly formalized as a large scale optimization over future outcomes of actions. For high dimensional manipulation platforms, this optimization is computationally so difficult that for a long time traditional approaches focused primarily on feasibility of the solution rather than even local optimality. Rec...

Nathan Ratliff Ludovic Righetti Jim Mainprice Jeannette Bohg Stefan Schaal

Optimal Control for Legged Robots

Planning dynamic behaviors for legged robots is a challenging task because the robot is subject to strong dynamic constraints due to its floating base (i.e. it can fall). It needs to take into account intermittent contacts with the environment and apply contact forces in order to move.

In this project, we address the probl...

Ludovic Righetti Alexander Herzog Nick Rotella Sean Mason Felix Grimminger John Rebula Brahayam Ponton Stefan Schaal

Physics of Body Shape and Motion

We, humans, live in a real world governed by the laws of physics, i.e. we apply and experiment forces, such as gravity, in our daily interactions with the world. In this project we allow virtual humans to interact with a virtual world subject to the laws of physics. How would ones’ bod...

Michael Black Sergi Pujades Meekyoung Kim Gerard Pons-Moll Javier Romero Ludovic Righetti

State Estimation and Sensor Fusion for the Control of Legged Robots

When developing controllers for legged robots, one assumes that important quantities like the Center of Mass of the robot (CoM), its position and orientation in space or its joint positions and velocities are know accurately to be used in feedback laws. While the estimation of such quantities is trivial in simulation, it becomes a s...

Nick Rotella Sean Mason Alexander Herzog Ludovic Righetti Stefan Schaal

Template-Based Learning of Model Free Grasping

Autonomous robotic grasping is one of the pre-requisites for personal robots to become useful when assisting humans in households. Seamlessly easy for humans, it still remains a very challenging task for robots. The key problem of robotic grasping is to automatically choose an appropriate grasp configuration given an object as perce...

Alexander Herzog Peter Pastor Mrinal Kalakrishnan Ludovic Righetti Jeannette Bohg Stefan Schaal

Whole-body control of legged robots

Legged robots are expected to locomote autonomously in an uncertain and potentially dynamically changing environment. Active interaction with contacts becomes inevitable to move and apply forces in a goal-directed way and withstand unpredicted changes in the environment. Therefore, we need to design algorithms that exploit interacti...

Ludovic Righetti Alexander Herzog Nick Rotella Sean Mason Felix Grimminger Stefan Schaal

Learning contact dynamics

In this project, we are interested in using machine learning techniques to handle robot behaviors with hard impact dynamics and contacts, such as walking, jumping or catching a ball. We investigate reinforcement learning techniques to learn dynamic motions under contact. We also use statistical learning tools to find representations...

Ludovic Righetti Julian Viereck Avadesh Merduri Felix Grimminger Majid Khadiv

Movement Representation for Reactive Behavior

An important part of our research is concerned with the problem of movement representations. The way motion and contacts are represented is crucial to derive efficient planning and control algorithms, for example by significantly simplifying the underlying optimization problems. The way sensory information can be integrated to gen...

Ludovic Righetti Stefan Schaal Peter Pastor Mrinal Kalakrishnan

Multi-contact trajectory optimization

In this project, we investigate the problem of computing movements for robots with arms and legs in intermittent contact with their environment that are physically correct. Our approach uses trajectory optimization and optimal control techniques. In particular, we study how the physics of mechanical systems impose a structure to the...

Ludovic Righetti Alexander Herzog Andrea Del Prete Maximilien Naveau Brahayam Ponton Majid Khadiv Sean Mason Nick Rotella

Sensor fusion for legged robots

In this project, we explore the problem of fusing sensor information from inertial, position and force measurements to recover quantities fundamental for the feedback control of legged robots. Our final goal is to find a systematic way of fusing multiple sensor modalities to improve the control of legged robots.

Ou...
Ludovic Righetti Nick Rotella Sean Mason Alexander Herzog Stefan Schaal

71 results (View BibTeX file of all listed publications)

2018

Leveraging Contact Forces for Learning to Grasp

Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., Bohg, J.

arXiv, September 2018, Submitted to ICRA'19 (article) Submitted

Abstract

Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two- fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

am mg

video arXiv [BibTex]

2018

am mg Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., Bohg, J. Leveraging Contact Forces for Learning to Grasp arXiv, September 2018, Submitted to ICRA'19 (article) Submitted

video arXiv [BibTex]

Robust Physics-based Motion Retargeting with Realistic Body Shapes

Borno, M. A., Righetti, L., Black, M. J., Delp, S. L., Fiume, E., Romero, J.

Computer Graphics Forum, 37, pages: 6:1-12, July 2018 (article)

Abstract

Motion capture is often retargeted to new, and sometimes drastically different, characters. When the characters take on realistic human shapes, however, we become more sensitive to the motion looking right. This means adapting it to be consistent with the physical constraints imposed by different body shapes. We show how to take realistic 3D human shapes, approximate them using a simplified representation, and animate them so that they move realistically using physically-based retargeting. We develop a novel spacetime optimization approach that learns and robustly adapts physical controllers to new bodies and constraints. The approach automatically adapts the motion of the mocap subject to the body shape of a target subject. This motion respects the physical properties of the new body and every body shape results in a different and appropriate movement. This makes it easy to create a varied set of motions from a single mocap sequence by simply varying the characters. In an interactive environment, successful retargeting requires adapting the motion to unexpected external forces. We achieve robustness to such forces using a novel LQR-tree formulation. We show that the simulated motions look appropriate to each character’s anatomy and their actions are robust to perturbations.

mg ps

pdf video Project Page Project Page [BibTex]

mg ps Borno, M. A., Righetti, L., Black, M. J., Delp, S. L., Fiume, E., Romero, J. Robust Physics-based Motion Retargeting with Realistic Body Shapes Computer Graphics Forum, 37, pages: 6:1-12, July 2018 (article)

pdf video Project Page Project Page [BibTex]

Learning a Structured Neural Network Policy for a Hopping Task.

Viereck, J., Kozolinsky, J., Herzog, A., Righetti, L.

IEEE Robotics and Automation Letters, 3(4):4092-4099, October 2018 (article)