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

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

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

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

82 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.

video arXiv [BibTex]

2018

am 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 [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 [BibTex]

On Time Optimization of Centroidal Momentum Dynamics

Ponton, B., Herzog, A., Prete, A. D., Schaal, S., Righetti, L.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

Abstract

Recently, the centroidal momentum dynamics has received substantial attention to plan dynamically consistent motions for robots with arms and legs in multi-contact scenarios. However, it is also non convex which renders any optimization approach difficult and timing is usually kept fixed in most trajectory optimization techniques to not introduce additional non convexities to the problem. But this can limit the versatility of the algorithms. In our previous work, we proposed a convex relaxation of the problem that allowed to efficiently compute momentum trajectories and contact forces. However, our approach could not minimize a desired angular momentum objective which seriously limited its applicability. Noticing that the non-convexity introduced by the time variables is of similar nature as the centroidal dynamics one, we propose two convex relaxations to the problem based on trust regions and soft constraints. The resulting approaches can compute time-optimized dynamically consistent trajectories sufficiently fast to make the approach realtime capable. The performance of the algorithm is demonstrated in several multi-contact scenarios for a humanoid robot. In particular, we show that the proposed convex relaxation of the original problem finds solutions that are consistent with the original non-convex problem and illustrate how timing optimization allows to find motion plans that would be difficult to plan with fixed timing.

video paper [BibTex]

am Ponton, B., Herzog, A., Prete, A. D., Schaal, S., Righetti, L. On Time Optimization of Centroidal Momentum Dynamics In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

video paper [BibTex]

2017

Pattern generation for walking on slippery terrains

Khadiv, M., Moosavian, A., Herzog, A., Righetti, L.

In 5th International Conference on Robotics and Mechatronics (ICROM), October 2017 (inproceedings)

[BibTex]

2017

mg Khadiv, M., Moosavian, A., Herzog, A., Righetti, L. Pattern generation for walking on slippery terrains In 5th International Conference on Robotics and Mechatronics (ICROM), October 2017 (inproceedings)

[BibTex]

2016

The Role of Measurement Uncertainty in Optimal Control for Contact Interactions

Workshop on the Algorithmic Foundations of Robotics, pages: 22, November 2016 (conference)

Abstract

Stochastic Optimal Control (SOC) typically considers noise only in the process model, i.e. unknown disturbances. However, in many robotic applications that involve interaction with the environment, such as locomotion and manipulation, uncertainty also comes from lack of pre- cise knowledge of the world, which is not an actual disturbance. We de- velop a computationally efficient SOC algorithm, based on risk-sensitive control, that takes into account uncertainty in the measurements. We include the dynamics of an observer in such a way that the control law explicitly depends on the current measurement uncertainty. We show that high measurement uncertainty leads to low impedance behaviors, a result in contrast with the effects of process noise variance that creates stiff behaviors. Simulation results on a simple 2D manipulator show that our controller can create better interaction with the environment under uncertain contact locations than traditional SOC approaches.

arXiv [BibTex]

2016

am The Role of Measurement Uncertainty in Optimal Control for Contact Interactions Workshop on the Algorithmic Foundations of Robotics, pages: 22, November 2016 (conference)

arXiv [BibTex]

Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid

Herzog, A., Rotella, N., Mason, S., Grimminger, F., Schaal, S., Righetti, L.

Autonomous Robots, 40(3):473-491, March 2016 (article)

am mg

video pdf DOI Project Page [BibTex]

am mg Herzog, A., Rotella, N., Mason, S., Grimminger, F., Schaal, S., Righetti, L. Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid Autonomous Robots, 40(3):473-491, March 2016 (article)

video pdf DOI Project Page [BibTex]

A Convex Model of Humanoid Momentum Dynamics for Multi-Contact Motion Generation

Ponton, B., Herzog, A., Schaal, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am mg

arxiv video Project Page [BibTex]

am mg Ponton, B., Herzog, A., Schaal, S., Righetti, L. A Convex Model of Humanoid Momentum Dynamics for Multi-Contact Motion Generation Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

arxiv video Project Page [BibTex]

Stepping stabilization using a combination of DCM tracking and step adjustment

Khadiv, M., Kleff, S., Herzog, A., Moosavian, S., Schaal, S., Righetti, L.

4th RSI International Conference on Robotics and Mechatronics, 2016 (conference)

am mg

arxiv [BibTex]

am mg Khadiv, M., Kleff, S., Herzog, A., Moosavian, S., Schaal, S., Righetti, L. Stepping stabilization using a combination of DCM tracking and step adjustment 4th RSI International Conference on Robotics and Mechatronics, 2016 (conference)

arxiv [BibTex]

Structured contact force optimization for kino-dynamic motion generation

Herzog, A., Schaal, S., Righetti, L.

In International Conference on Intelligent Robots and Systems (IROS) 2016, pages: 2703-2710, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016 (inproceedings)

am mg

video pdf link (url) [BibTex]

am mg Herzog, A., Schaal, S., Righetti, L. Structured contact force optimization for kino-dynamic motion generation In International Conference on Intelligent Robots and Systems (IROS) 2016, pages: 2703-2710, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016 (inproceedings)

video pdf link (url) [BibTex]

Step Timing Adjustment: A Step Toward Generating Robust Gaits

Khadiv, M., Herzog, A., Moosavian, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am mg

arxiv video [BibTex]

am mg Khadiv, M., Herzog, A., Moosavian, S., Righetti, L. Step Timing Adjustment: A Step Toward Generating Robust Gaits Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

arxiv video [BibTex]

Balancing and Walking Using Full Dynamics LQR Control with Contact Constraints

Mason, S., rotella, N., Schaal, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am mg

[BibTex]

am mg Mason, S., rotella, N., Schaal, S., Righetti, L. Balancing and Walking Using Full Dynamics LQR Control with Contact Constraints Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

[BibTex]

2015

Trajectory generation for multi-contact momentum-control

Herzog, A., Rotella, N., Schaal, S., Righetti, L.

In IEEE-RAS International Conference on Humanoid Robots (Humanoids), November 2015 (inproceedings)

am mg

link (url) Project Page Project Page [BibTex]

2015

am mg Herzog, A., Rotella, N., Schaal, S., Righetti, L. Trajectory generation for multi-contact momentum-control In IEEE-RAS International Conference on Humanoid Robots (Humanoids), November 2015 (inproceedings)

link (url) Project Page Project Page [BibTex]

Kinematic and gait similarities between crawling human infants and other quadruped mammals

Righetti, L., Nylen, A., Rosander, K., Ijspeert, A.

Frontiers in Neurology, 6(17), Febuary 2015 (article)

am mg

[BibTex]

am mg Righetti, L., Nylen, A., Rosander, K., Ijspeert, A. Kinematic and gait similarities between crawling human infants and other quadruped mammals Frontiers in Neurology, 6(17), Febuary 2015 (article)

[BibTex]

Momentum Estimation, Planning and Control for Force-Centric Bipedal Locomotion

Rotella, N., Herzog, A., Schaal, S., Righetti, L.

In Proceedings of Dynamic Walking, 2015 (inproceedings)

am mg

Project Page [BibTex]

am mg Rotella, N., Herzog, A., Schaal, S., Righetti, L. Momentum Estimation, Planning and Control for Force-Centric Bipedal Locomotion In Proceedings of Dynamic Walking, 2015 (inproceedings)

Project Page [BibTex]

Multi-Contact Interaction with Hierarchical Inverse Dynamics and Momentum Trajectory Generation

Herzog, A., Rotella, N., Mason, S., Grimminger, F., Schaal, S., Righetti, L.

In Proceedings of Dynamic Walking, 2015 (inproceedings)

am mg

[BibTex]

am mg Herzog, A., Rotella, N., Mason, S., Grimminger, F., Schaal, S., Righetti, L. Multi-Contact Interaction with Hierarchical Inverse Dynamics and Momentum Trajectory Generation In Proceedings of Dynamic Walking, 2015 (inproceedings)

[BibTex]

From Humans to Robots and Back: Role of Arm Movement in Medio-lateral Balance Control

Huber, M. E., Chiovetto, E., Righetti, L., Schaal, S., Giese, M., Sternad, D.

In Proceedings of Dynamic Walking, 2015 (inproceedings)

am mg

[BibTex]

am mg Huber, M. E., Chiovetto, E., Righetti, L., Schaal, S., Giese, M., Sternad, D. From Humans to Robots and Back: Role of Arm Movement in Medio-lateral Balance Control In Proceedings of Dynamic Walking, 2015 (inproceedings)

[BibTex]

Full Dynamics LQR Control for Bipedal Walking

Mason, S., Schaal, S., Righetti, L.

Proceedings of Dynamic Walking, 2015 (conference)

am mg

[BibTex]

am mg Mason, S., Schaal, S., Righetti, L. Full Dynamics LQR Control for Bipedal Walking Proceedings of Dynamic Walking, 2015 (conference)

[BibTex]

Humanoid Momentum Estimation Using Sensed Contact Wrenches

Rotella, N., Herzog, A., Schaal, S., Righetti, L.

Proceedings of the 2015 IEEE-RAS International Conference on Humanoid Robots, 2015 (conference)

am mg

Project Page Project Page [BibTex]

am mg Rotella, N., Herzog, A., Schaal, S., Righetti, L. Humanoid Momentum Estimation Using Sensed Contact Wrenches Proceedings of the 2015 IEEE-RAS International Conference on Humanoid Robots, 2015 (conference)

Project Page Project Page [BibTex]

Wrong and Useful: Metrics to Assess Simple Walking Models

Rebula, J., Righetti, L., Schaal, S.

In Proceedings of Dynamic Walking, 2015 (inproceedings)

am mg

[BibTex]

am mg Rebula, J., Righetti, L., Schaal, S. Wrong and Useful: Metrics to Assess Simple Walking Models In Proceedings of Dynamic Walking, 2015 (inproceedings)

[BibTex]

2014

Dual Execution of Optimized Contact Interaction Trajectories

Toussaint, M., Ratliff, N., Bohg, J., Righetti, L., Englert, P., Schaal, S.

In Proceedings of the International Conference on Intelligent Robots and Systems, Chicago, IL, October 2014 (inproceedings)

Abstract

Efficient manipulation requires contact to reduce uncertainty. The manipulation literature refers to this as funneling: a methodology for increasing reliability and robustness by leveraging haptic feedback and control of environmental interaction. However, there is a fundamental gap between traditional approaches to trajectory optimization and this concept of robustness by funneling: traditional trajectory optimizers do not discover force feedback strategies. From a POMDP perspective, these behaviors could be regarded as explicit obser- vation actions planned to sufficiently reduce uncertainty thereby enabling a task. While we are sympathetic to the full POMDP view, solving full continuous-space POMDPs in high-dimensions is hard. In this paper, we propose an alternative approach in which trajectory optimization objectives are augmented with new terms that reward uncertainty reduction through contacts, explicitly promoting funneling. This augmentation shifts the responsibility of robustness toward the actual execution of the optimized trajectories. Directly tracing trajectories through configuration space would lose all robustnessâ??dual execution achieves robustness by devising force controllers to reproduce the temporal interaction profile encoded in the dual solution of the optimization problem. This work introduces dual execution in depth and analyze its performance through robustness experiments in both simulation and on a real-world robotic platform.

am mg

PDF Video DOI Project Page [BibTex]

2014

am mg Toussaint, M., Ratliff, N., Bohg, J., Righetti, L., Englert, P., Schaal, S. Dual Execution of Optimized Contact Interaction Trajectories In Proceedings of the International Conference on Intelligent Robots and Systems, Chicago, IL, October 2014 (inproceedings)

PDF Video DOI Project Page [BibTex]

Balancing experiments on a torque-controlled humanoid with hierarchical inverse dynamics

Herzog, A., Righetti, L., Grimminger, F., Pastor, P., Schaal, S.

Proceedings of the IEEE International Conference on Intelligent Robotics Systems, Chicago, IL, September 2014 (conference)

Abstract

Recently several hierarchical inverse dynamicscontrollers based on cascades of quadratic programs havebeen proposed for application on torque controlled robots.They have important theoretical benefits but have never beenimplemented on a torque controlled robot where model inaccuraciesand real-time computation requirements can beproblematic. In this contribution we present an experimentalevaluation of these algorithms in the context of balance controlfor a humanoid robot. The presented experiments demonstratethe applicability of the approach under real robot conditions(i.e. model uncertainty, estimation errors, etc). We propose asimplification of the optimization problem that allows us todecrease computation time enough to implement it in a fasttorque control loop. We implement a momentum-based balancecontroller which shows robust performance in face of unknowndisturbances, even when the robot is standing on only onefoot. In a second experiment, a tracking task is evaluatedto demonstrate the performance of the controller with morecomplicated hierarchies. Our results show that hierarchicalinverse dynamics controllers can be used for feedback controlof humanoid robots and that momentum-based balance controlcan be efficiently implemented on a real robot.

am mg

Video pdf DOI Project Page [BibTex]

am mg Herzog, A., Righetti, L., Grimminger, F., Pastor, P., Schaal, S. Balancing experiments on a torque-controlled humanoid with hierarchical inverse dynamics Proceedings of the IEEE International Conference on Intelligent Robotics Systems, Chicago, IL, September 2014 (conference)

Video pdf DOI Project Page [BibTex]

An autonomous manipulation system based on force control and optimization

Righetti, L., Kalakrishnan, M., Pastor, P., Binney, J., Kelly, J., Voorhies, R. C., Sukhatme, G. S., Schaal, S.

Autonomous Robots, 36(1-2):11-30, Springer US, Febuary 2014, clmc (article)

Abstract

In this paper we present an architecture for autonomous manipulation. Our approach is based on the belief that contact interactions during manipulation should be exploited to improve dexterity and that optimizing motion plans is useful to create more robust and repeatable manipu- lation behaviors. We therefore propose an architecture where state of the art force/torque control and optimization-based motion planning are the core components of the system. We give a detailed description of the modules that constitute the complete system and discuss the challenges inherent to creat- ing such a system. We present experimental results for several grasping and manipulation tasks to demonstrate the perfor- mance and robustness of our approach.

am mg

Web Video link (url) DOI Project Page [BibTex]

am mg Righetti, L., Kalakrishnan, M., Pastor, P., Binney, J., Kelly, J., Voorhies, R. C., Sukhatme, G. S., Schaal, S. An autonomous manipulation system based on force control and optimization Autonomous Robots, 36(1-2):11-30, Springer US, Febuary 2014, clmc (article)

Web Video link (url) DOI Project Page [BibTex]

Learning of Grasp Selection based on Shape-Templates

Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T., Schaal, S.

Autonomous Robots, 36(1-2):51-65, Springer US, January 2014 (article)

Abstract

The ability to grasp unknown objects still remains an unsolved problem in the robotics community. One of the challenges is to choose an appropriate grasp configu- ration, i.e., the 6D pose of the hand relative to the object and its finger configuration. In this paper, we introduce an algo- rithm that is based on the assumption that similarly shaped objects can be grasped in a similar way. It is able to synthe- size good grasp poses for unknown objects by finding the best matching object shape templates associated with previously demonstrated grasps. The grasp selection algorithm is able to improve over time by using the information of previous grasp attempts to adapt the ranking of the templates to new situa- tions. We tested our approach on two different platforms, the Willow Garage PR2 and the Barrett WAM robot, which have very different hand kinematics. Furthermore, we compared our algorithm with other grasp planners and demonstrated its superior performance. The results presented in this paper show that the algorithm is able to find good grasp configura- tions for a large set of unknown objects from a relatively small set of demonstrations, and does improve its performance over time.

am mg

video pdf DOI Project Page Project Page [BibTex]

am mg Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T., Schaal, S. Learning of Grasp Selection based on Shape-Templates Autonomous Robots, 36(1-2):51-65, Springer US, January 2014 (article)

video pdf DOI Project Page Project Page [BibTex]

Experiments with Hierarchical Inverse Dynamics Controllers on a Torque Controlled Humanoid

Herzog, A., Righetti, L., Grimminger, F., Schaal, S.

In Proceedings of Dynamic Walking, Zürich, Switzerland, 2014, clmc (inproceedings)

Abstract

We expect autonomous legged robots to perform complex tasks in persistent interaction with an uncertain and changing environment (e.g. in a disaster relief scenario). Therefore, we need to design algorithms that can generate precise but compliant motions while optimizing the interactions with the environment. In this context, torque control algorithms often offer high performance for motion control while guaranteeing a certain level of compliance. In addition they allow for direct control of interaction forces with the environment. Recent contributions have demonstrated the relevance of torque con- trol approaches for humanoid robots, for example for balanc- ing capabilities [5, 6]. Among those we find passivity-based approaches [5] that regulate the position of the Center of Mass (CoM) by applying admissible contact forces under the quasi- static assumption. On the one hand, these approaches do not rely on a precise dynamic model of the robot while natu- rally guaranteeing robustness due to the passivity property of the controller. On the other hand the quasi-static assumption might be limiting for dynamic motions. A promising way of leveraging this limitation are control algorithms that take the full dynamic model into account [6]. However, the need for a precise dynamic model, sensor noise (particularly in the ve- locities) and limited torque bandwidth makes them more chal- lenging to implement. Moreover, it is generally required to simplify the optimization process to meet time requirements of fast control loops (typically 1 kHz on modern torque con- trolled robots). Practical evaluations of both approaches are still rare due to the lack of torque controlled humanoid plat- forms and the complexity in conducting such robot experiments.

am mg

PDF link (url) [BibTex]

am mg Herzog, A., Righetti, L., Grimminger, F., Schaal, S. Experiments with Hierarchical Inverse Dynamics Controllers on a Torque Controlled Humanoid In Proceedings of Dynamic Walking, Zürich, Switzerland, 2014, clmc (inproceedings)

PDF link (url) [BibTex]

Full Dynamics LQR Control of a Humanoid Robot: An Experimental Study on Balancing and Squatting

Mason, S., Righetti, L., Schaal, S.

In 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2014 (inproceedings)

am mg

Project Page [BibTex]

am mg Mason, S., Righetti, L., Schaal, S. Full Dynamics LQR Control of a Humanoid Robot: An Experimental Study on Balancing and Squatting In 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2014 (inproceedings)

Project Page [BibTex]

Towards Full System Linear Quadratic Regulators for Humanoid Control

Mason, S., Righetti, L., Schaal, S.

In Proceedings of Dynamic Walking, Zurich, Switzerland, 2014, clmc (inproceedings)

Abstract

Robots that are to locomote in a human like fashion requirecontrol of high degree of freedom (DOF) motions potentiallycoupled in a complex way. It remains challenging to expressthe task objective in an intuitive way and simultaneously generatefeedback gains guaranteeing some level of optimality.In response to this, a number of different simplified modelshave been developed to highlight different aspects of the humanoidâ??sdynamics that are important for specific tasks. Ashort list of some of the models used to represent a humanoidinclude the cart-table, double inverted pendulum, reactionmass pendulum, and automatically generated task specific reducedmodels [4]. These simplified models make planningeasier but come at the cost of modelling error and limitationson motion. In addition, one is tasked with finding mappingsbetween the full system to the reduced system. These mappingscan potentially destroy the intuition surrounding the useof the simplified model as they may not always behave as expected.By working with the full dynamics, one obtains anincrease in generality, accuracy, and eliminates the need formappings.

am mg

PDF link (url) [BibTex]

am mg Mason, S., Righetti, L., Schaal, S. Towards Full System Linear Quadratic Regulators for Humanoid Control In Proceedings of Dynamic Walking, Zurich, Switzerland, 2014, clmc (inproceedings)

PDF link (url) [BibTex]

State Estimation for a Humanoid Robot

Rotella, N., Bloesch, M., Righetti, L., Schaal, S.

In Proceedings of the 2014 IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 952-958, Chicago, IL, 2014 (inproceedings)

Abstract

This paper introduces a framework for state estimation on a humanoid robot platform using only common proprioceptive sensors and knowledge of leg kinematics. The presented approach extends that detailed in prior work on a point-foot quadruped platform by adding the rotational constraints imposed by the humanoidâ??s flat feet. As in previous work, the proposed Extended Kalman Filter accommodates contact switching and makes no assumptions about gait or terrain, making it applicable on any humanoid platform for use in any task. A nonlinear observability analysis is performed on both the point-foot and flat-foot filters and it is concluded that the addition of rotational constraints significantly simplifies singular cases and improves the observability characteristics of the system. Results on a simulated walking dataset demonstrate the performance gain of the flat-foot filter as well as confirm the results of the presented observability analysis.

am mg

PDF link (url) Project Page Project Page [BibTex]

am mg Rotella, N., Bloesch, M., Righetti, L., Schaal, S. State Estimation for a Humanoid Robot In Proceedings of the 2014 IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 952-958, Chicago, IL, 2014 (inproceedings)

PDF link (url) Project Page Project Page [BibTex]

State Estimation for Walking Humanoids on Unknown Terrain

Rotella, N., Bloesch, M., Righetti, L., Schaal, S.

In Proceedings of Dynamic Walking, Zürich, Switzerland, 2014, clmc (inproceedings)

Abstract

State estimation plays a crucial role in humanoid locomotion;accurate estimates of the pose and velocity of the robotâ??s baseare necessary for walking tasks. Estimation in robotics haslong been focused on mobile robot localization, where wheelodometry and exteroceptive sensor data are fused to provideestimates of absolute position and yaw. While wheeled robotsare assumed to remain stable and in contact at all times,legged locomotion inherently involves intermittent contacts.This makes stability a concern and complicates odometrybasedapproaches, distinguishing estimation for legged systemsfrom that for wheeled robots. More recent approacheson quadruped and hexapod platforms make unreasonable assumptionsabout walking gaits, assume knowledge of the terrainand use exteroceptive sensor data for corrections. However,the utility of such platforms is their potential for operationin unstructured environments in which gaits are reactive,the terrain is unknown and such sensors are unfit for use. Motivatedby the task of providing robust and generic state estimationfor humanoid robots walking on unknown terrain, weintroduce an estimation framework [1] which employs onlyproprioceptive sensors and knowledge of leg kinematics.

am mg

PDF link (url) Project Page [BibTex]

am mg Rotella, N., Bloesch, M., Righetti, L., Schaal, S. State Estimation for Walking Humanoids on Unknown Terrain In Proceedings of Dynamic Walking, Zürich, Switzerland, 2014, clmc (inproceedings)

PDF link (url) Project Page [BibTex]

2013

Controlled Reduction with Unactuated Cyclic Variables: Application to 3D Bipedal Walking with Passive Yaw Rotation

Gregg, R., Righetti, L.

IEEE Transactions on Automatic Control, 58(10):2679-2685, October 2013 (article)

am mg

[BibTex]

2013

am mg Gregg, R., Righetti, L. Controlled Reduction with Unactuated Cyclic Variables: Application to 3D Bipedal Walking with Passive Yaw Rotation IEEE Transactions on Automatic Control, 58(10):2679-2685, October 2013 (article)

[BibTex]

AGILITY – Dynamic Full Body Locomotion and Manipulation with Autonomous Legged Robots

Hutter, M., Bloesch, M., Buchli, J., Semini, C., Bazeille, S., Righetti, L., Bohg, J.

In IEEE International Symposium on Safety, Security, and Rescue Robotics, pages: 1-4, Linköping, 2013 (inproceedings)

am mg

[BibTex]

am mg Hutter, M., Bloesch, M., Buchli, J., Semini, C., Bazeille, S., Righetti, L., Bohg, J. AGILITY – Dynamic Full Body Locomotion and Manipulation with Autonomous Legged Robots In IEEE International Symposium on Safety, Security, and Rescue Robotics, pages: 1-4, Linköping, 2013 (inproceedings)

[BibTex]

Markov Random Fields for Stochastic Trajectory Optimization and Learning with Constraints

Kalakrishnan, M., Herzog, A., Righetti, L., Schaal, S.

In Workshop: Hierarchical and Structured Learning for Robotics, RSS 2013, pages: 1-1, Berlin, 2013 (inproceedings)

am mg

[BibTex]

am mg Kalakrishnan, M., Herzog, A., Righetti, L., Schaal, S. Markov Random Fields for Stochastic Trajectory Optimization and Learning with Constraints In Workshop: Hierarchical and Structured Learning for Robotics, RSS 2013, pages: 1-1, Berlin, 2013 (inproceedings)

[BibTex]

Optimal distribution of contact forces with inverse dynamics control

Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S.

The International Journal of Robotics Research, 32(3):280-298, 2013, clmc (article)

Abstract

The development of legged robots for complex environments requires controllers that guarantee both high tracking performance and compliance with the environment. More specifically the control of the contact interaction with the environment is of crucial importance to ensure stable, robust and safe motions. In this contribution we develop an inverse-dynamics controller for floating-base robots under contact constraints that can minimize any combination of linear and quadratic costs in the contact constraints and the commands. Our main result is the exact analytical derivation of the controller. Such a result is particularly relevant for legged robots as it allows us to use torque redundancy to directly optimize contact interactions. For example, given a desired locomotion behavior, we can guarantee the minimization of contact forces to reduce slipping on difficult terrains while ensuring high tracking performance of the desired motion. The main advantages of the controller are its simplicity, computational efficiency and robustness to model inaccuracies. We present detailed experimental results on simulated humanoid and quadruped robots as well as a real quadruped robot. The experiments demonstrate that the controller can greatly improve the robustness of locomotion of the robots.

am mg

PDF Project Page [BibTex]

am mg Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S. Optimal distribution of contact forces with inverse dynamics control The International Journal of Robotics Research, 32(3):280-298, 2013, clmc (article)

PDF Project Page [BibTex]

Learning Task Error Models for Manipulation

Pastor, P., Kalakrishnan, M., Binney, J., Kelly, J., Righetti, L., Sukhatme, G., Schaal, S.

In IEEE International Conference on Robotics and Automation, 2013 (inproceedings)

Abstract

Precise kinematic forward models are important for robots to successfully perform dexterous grasping and manipula- tion tasks, especially when visual servoing is rendered infeasible due to occlusions. A lot of research has been conducted to estimate geometric and non-geometric parameters of kinematic chains to minimize reconstruction errors. However, kinematic chains can include non-linearities, e.g. due to cable stretch and motor-side encoders, that result in significantly different errors for different parts of the state space. Previous work either does not consider such non-linearities or proposes to estimate non-geometric parameters of carefully engineered models that are robot specific. We propose a data-driven approach that learns task error models that account for such unmodeled non-linearities. We argue that in the context of grasping and manipulation, it is sufficient to achieve high accuracy in the task relevant state space. We identify this relevant state space using previously executed joint configurations and learn error corrections for those. Therefore, our system is developed to generate subsequent executions that are similar to previous ones. The experiments show that our method successfully captures the non-linearities in the head kinematic chain (due to a counter- balancing spring) and the arm kinematic chains (due to cable stretch) of the considered experimental platform, see Fig. 1. The feasibility of the presented error learning approach has also been evaluated in independent DARPA ARM-S testing contributing to successfully complete 67 out of 72 grasping and manipulation tasks.

am mg

PDF video Project Page [BibTex]

am mg Pastor, P., Kalakrishnan, M., Binney, J., Kelly, J., Righetti, L., Sukhatme, G., Schaal, S. Learning Task Error Models for Manipulation In IEEE International Conference on Robotics and Automation, 2013 (inproceedings)

PDF video Project Page [BibTex]

Using Torque Redundancy to Optimize Contact Forces in Legged Robots

Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S.

In Redundancy in Robot Manipulators and Multi-Robot Systems, pages: 35-51, (Editors: Dejan Milutinović and Jacob Rosen), Springer-Verlag Berlin Heidelberg, 2013, clmc (inbook)

Abstract

The development of legged robots for complex environments requires controllers that guarantee both high tracking performance and compliance with the environment. More specifically the control of contact interaction with the environment is of crucial importance to ensure stable, robust and safe motions. In the following, we present an inverse dynamics controller that exploits torque redundancy to directly and explicitly minimize any combination of linear and quadratic costs in the contact constraints and in the commands. Such a result is particularly relevant for legged robots as it allows to use torque redundancy to directly optimize contact interactions. For example, given a desired locomotion behavior, it can guarantee the minimization of contact forces to reduce slipping on difficult terrains while ensuring high tracking performance of the desired motion. The proposed controller is very simple and computationally efficient, and most importantly it can greatly improve the performance of legged locomotion on difficult terrains as can be seen in the experimental results.

am mg

PDF [BibTex]

am mg Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S. Using Torque Redundancy to Optimize Contact Forces in Legged Robots In Redundancy in Robot Manipulators and Multi-Robot Systems, pages: 35-51, (Editors: Dejan Milutinović and Jacob Rosen), Springer-Verlag Berlin Heidelberg, 2013, clmc (inbook)

PDF [BibTex]

Learning Objective Functions for Manipulation

Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In IEEE International Conference on Robotics and Automation, 2013, clmc (inproceedings)

Abstract

We present an approach to learning objective func- tions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning al- gorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the re- sulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization- based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.

am mg

PDF Project Page Project Page [BibTex]

am mg Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S. Learning Objective Functions for Manipulation In IEEE International Conference on Robotics and Automation, 2013, clmc (inproceedings)

PDF Project Page Project Page [BibTex]

2012

Template-based learning of grasp selection

Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Asfour, T., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), pages: 2379-2384, May 2012 (inproceedings)

Abstract

The ability to grasp unknown objects is an important skill for personal robots, which has been addressed by many present and past research projects, but still remains an open problem. A crucial aspect of grasping is choosing an appropriate grasp configuration, i.e. the 6d pose of the hand relative to the object and its finger configuration. Finding feasible grasp configurations for novel objects, however, is challenging because of the huge variety in shape and size of these objects. Moreover, possible configurations also depend on the specific kinematics of the robotic arm and hand in use. In this paper, we introduce a new grasp selection algorithm able to find object grasp poses based on previously demonstrated grasps. Assuming that objects with similar shapes can be grasped in a similar way, we associate to each demonstrated grasp a grasp template. The template is a local shape descriptor for a possible grasp pose and is constructed using 3d information from depth sensors. For each new object to grasp, the algorithm then finds the best grasp candidate in the library of templates. The grasp selection is also able to improve over time using the information of previous grasp attempts to adapt the ranking of the templates. We tested the algorithm on two different platforms, the Willow Garage PR2 and the Barrett WAM arm which have very different hands. Our results show that the algorithm is able to find good grasp configurations for a large set of objects from a relatively small set of demonstrations, and does indeed improve its performance over time. View full abstract

am mg

video pdf DOI Project Page [BibTex]

2012

am mg Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Asfour, T., Schaal, S. Template-based learning of grasp selection In IEEE International Conference on Robotics and Automation (ICRA), pages: 2379-2384, May 2012 (inproceedings)

video pdf DOI Project Page [BibTex]

Learning Force Control Policies for Compliant Robotic Manipulation

Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S.

In International Conference on Machine Learning (ICML), 2012, clmc (inproceedings)

Abstract

In this abstract, we present an approach to learning manipulation tasks on compliant robots through re- inforcement learning. We demonstrate our approach on two different manipulation tasks: opening a door with a lever door handle, and picking up a pen off the table (Fig. 1). We show that our approach can learn the force control policies required to achieve both tasks successfully. The contributions of this work are two-fold: (1) we demonstrate that learning force con- trol policies enables compliant execution of manipu- lation tasks with increased robustness as opposed to stiff position control, and (2) we introduce a policy parameterization that uses finely discretized trajectories coupled with a cost function that ensures smoothness during exploration and learning.

am mg

link (url) [BibTex]

am mg Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S. Learning Force Control Policies for Compliant Robotic Manipulation In International Conference on Machine Learning (ICML), 2012, clmc (inproceedings)

link (url) [BibTex]

Towards Associative Skill Memories

Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S.

In IEEE-RAS International Conference on Humanoid Robots, 2012, clmc (inproceedings)

Abstract

Movement primitives as basis of movement planning and control have become a popular topic in recent years. The key idea of movement primitives is that a rather small set of stereotypical movements should suffice to create a large set of complex manipulation skills. An interesting side effect of stereotypical movement is that it also creates stereotypical sensory events, e.g., in terms of kinesthetic variables, haptic variables, or, if processed appropriately, visual variables. Thus, a movement primitive executed towards a particular object in the environment will associate a large number of sensory variables that are typical for this manipulation skill. These association can be used to increase robustness towards perturbations, and they also allow failure detection and switching towards other behaviors. We call such movement primitives augmented with sensory associations {em Associative Skill Memories} (ASM). This paper addresses how ASMs can be acquired by imitation learning and how they can create robust manipulation skill by determining subsequent ASMs extit{online} to achieve a particular manipulation goal. Evaluation for grasping and manipulation with a Barrett WAM/Hand illustrate our approach.

am mg

PDF Project Page [BibTex]

am mg Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S. Towards Associative Skill Memories In IEEE-RAS International Conference on Humanoid Robots, 2012, clmc (inproceedings)

PDF Project Page [BibTex]

Probabilistic depth image registration incorporating nonvisual information

Wüthrich, M., Pastor, P., Righetti, L., Billard, A., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), pages: 3637-3644, 2012, clmc (inproceedings)

Abstract

In this paper, we derive a probabilistic registration algorithm for object modeling and tracking. In many robotics applications, such as manipulation tasks, nonvisual information about the movement of the object is available, which we will combine with the visual information. Furthermore we do not only consider observations of the object, but we also take space into account which has been observed to not be part of the object. Furthermore we are computing a posterior distribution over the relative alignment and not a point estimate as typically done in for example Iterative Closest Point (ICP). To our knowledge no existing algorithm meets these three conditions and we thus derive a novel registration algorithm in a Bayesian framework. Experimental results suggest that the proposed methods perform favorably in comparison to PCL [1] implementations of feature mapping and ICP, especially if nonvisual information is available. View full abstract

am mg

Web DOI [BibTex]

am mg Wüthrich, M., Pastor, P., Righetti, L., Billard, A., Schaal, S. Probabilistic depth image registration incorporating nonvisual information In IEEE International Conference on Robotics and Automation (ICRA), pages: 3637-3644, 2012, clmc (inproceedings)

Web DOI [BibTex]

Quadratic programming for inverse dynamics with optimal distribution of contact forces

Righetti, L., Schaal, S.

In 2012 IEEE-RAS International Conference on Humanoid Robots, pages: 538-543, Osaka, 2012, clmc (inproceedings)

Abstract

In this contribution we propose an inverse dynamics controller for a humanoid robot that exploits torque redundancy to minimize any combination of linear and quadratic costs in the contact forces and the commands. In addition the controller satisfies linear equality and inequality constraints in the contact forces and the commands such as torque limits, unilateral contacts or friction cones limits. The originality of our approach resides in the formulation of the problem as a quadratic program where we only need to solve for the control commands and where the contact forces are optimized implicitly. Furthermore, we do not need a structured representation of the dynamics of the robot (i.e. an explicit computation of the inertia matrix). It is in contrast with existing methods based on quadratic programs. The controller is then robust to uncertainty in the estimation of the dynamics model and the optimization is fast enough to be implemented in high bandwidth torque control loops that are increasingly available on humanoid platforms. We demonstrate properties of our controller with simulations of a human size humanoid robot.

am mg

PDF [BibTex]

am mg Righetti, L., Schaal, S. Quadratic programming for inverse dynamics with optimal distribution of contact forces In 2012 IEEE-RAS International Conference on Humanoid Robots, pages: 538-543, Osaka, 2012, clmc (inproceedings)

PDF [BibTex]

Encoding of Periodic and their Transient Motions by a Single Dynamic Movement Primitive

Ernesti, J., Righetti, L., Do, M., Asfour, T., Schaal, S.

In 2012 IEEE-RAS International Conference on Humanoid Robots, pages: 57-64, Osaka, 2012, clmc (inproceedings)

Abstract

Present formulations of periodic dynamic move- ment primitives (DMPs) do not encode the transient behavior required to start the rhythmic motion, although these transient movements are an important part of the rhythmic movements (i.e. when walking, there is always a first step that is very different from the subsequent ones). An ad-hoc procedure is then necessary to get the robot into the periodic motion. In this contribution we present a novel representation for rhythmic Dynamic Movement Primitives (DMPs) that encodes both the rhythmic motion and its transient behaviors. As with previously proposed DMPs, we use a dynamical system approach where an asymptotically stable limit cycle represents the periodic pattern. Transients are then represented as trajectories converg- ing towards the limit cycle, different trajectories representing varying transients from different initial conditions. Our ap- proach thus constitutes a generalization of previously proposed rhythmic DMPs. Experiments conducted on the humanoid robot ARMAR-III demonstrate the applicability of the approach for movement generation.

am mg

PDF Project Page [BibTex]

am mg Ernesti, J., Righetti, L., Do, M., Asfour, T., Schaal, S. Encoding of Periodic and their Transient Motions by a Single Dynamic Movement Primitive In 2012 IEEE-RAS International Conference on Humanoid Robots, pages: 57-64, Osaka, 2012, clmc (inproceedings)

PDF Project Page [BibTex]

2011

Learning force control policies for compliant manipulation

Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

Abstract

Developing robots capable of fine manipulation skills is of major importance in order to build truly assistive robots. These robots need to be compliant in their actuation and control in order to operate safely in human environments. Manip-ulation tasks imply complex contact interactions with the external world, and in-volve reasoning about the forces and torques to be applied. Planning under con-tact conditions is usually impractical due to computational complexity, and a lack of precise dynamics models of the environment. We present an approach to acquiring manipulation skills on compliant robots through reinforcement learn-ing. The initial position control policy for manipulation is initialized through kinesthetic demonstration. We augment this policy with a force/torque profile to be controlled in combination with the position trajectories. We use the Policy Improvement with Path Integrals (PI2) algorithm to learn these force/torque pro-files by optimizing a cost function that measures task success. We demonstrate our approach on the Barrett WAM robot arm equipped with a 6-DOF force/torque sensor on two different manipulation tasks: opening a door with a lever door handle, and picking up a pen off the table. We show that the learnt force control policies allow successful, robust execution of the tasks.

am mg

link (url) Project Page [BibTex]

2011

am mg Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S. Learning force control policies for compliant manipulation In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

link (url) Project Page [BibTex]

Online movement adaptation based on previous sensor experiences

Pastor, P., Righetti, L., Kalakrishnan, M., Schaal, S.

In IEEE International Conference on Intelligent Robots and Systems (IROS), pages: 365-371, 2011 (inproceedings)

am mg

Project Page Project Page Project Page [BibTex]

am mg Pastor, P., Righetti, L., Kalakrishnan, M., Schaal, S. Online movement adaptation based on previous sensor experiences In IEEE International Conference on Intelligent Robots and Systems (IROS), pages: 365-371, 2011 (inproceedings)

Project Page Project Page Project Page [BibTex]

Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives

Degallier, S., Righetti, L., Gay, S., Ijspeert, A.

Autonomous Robots, 31(2-3):155-181, 2011 (article)

am mg

[BibTex]

am mg Degallier, S., Righetti, L., Gay, S., Ijspeert, A. Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives Autonomous Robots, 31(2-3):155-181, 2011 (article)

[BibTex]

Inverse dynamics control of floating-base robots with external contraints: an unified view

Righetti, L., Mistry, M., Buchli, J., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract

Inverse dynamics controllers and operational space controllers have proved to be very efficient for compliant control of fully actuated robots such as fixed base manipulators. However legged robots such as humanoids are inherently different as they are underactuated and subject to switching external contact constraints. Recently several methods have been proposed to create inverse dynamics controllers and operational space controllers for these robots. In an attempt to compare these different approaches, we develop a general framework for inverse dynamics control and show that these methods lead to very similar controllers. We are then able to greatly simplify recent whole-body controllers based on operational space approaches using kinematic projections, bringing them closer to efficient practical implementations. We also generalize these controllers such that they can be optimal under an arbitrary quadratic cost in the commands.

am mg

link (url) [BibTex]

am mg Righetti, L., Mistry, M., Buchli, J., Schaal, S. Inverse dynamics control of floating-base robots with external contraints: an unified view In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

link (url) [BibTex]

Operational Space Control of Constrained and Underactuated Systems

Mistry, M., Righetti, L.

In Proceedings of Robotics: Science and Systems, Los Angeles, CA, USA, 2011 (inproceedings)

am mg

Project Page [BibTex]

am mg Mistry, M., Righetti, L. Operational Space Control of Constrained and Underactuated Systems In Proceedings of Robotics: Science and Systems, Los Angeles, CA, USA, 2011 (inproceedings)

Project Page [BibTex]

Control of legged robots with optimal distribution of contact forces

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In 2011 11th IEEE-RAS International Conference on Humanoid Robots, pages: 318 - 324, 2011, clmc (inproceedings)

Abstract

The development of agile and safe humanoid robots require controllers that guarantee both high tracking performance and compliance with the environment. More specifically, the control of contact interaction is of crucial importance for robots that will actively interact with their environment. Model-based controllers such as inverse dynamics or operational space control are very appealing as they offer both high tracking performance and compliance. However, while widely used for fully actuated systems such as manipulators, they are not yet standard controllers for legged robots such as humanoids. Indeed such robots are fundamentally different from manipulators as they are underactuated due to their floating-base and subject to switching contact constraints. In this paper we present an inverse dynamics controller for legged robots that use torque redundancy to create an optimal distribution of contact constraints. The resulting controller is able to minimize, given a desired motion, any quadratic cost of the contact constraints at each instant of time. In particular we show how this can be used to minimize tangential forces during locomotion, therefore significantly improving the locomotion of legged robots on difficult terrains. In addition to the theoretical result, we present simulations of a humanoid and a quadruped robot, as well as experiments on a real quadruped robot that demonstrate the advantages of the controller.

am mg

PDF [BibTex]

am mg Righetti, L., Buchli, J., Mistry, M., Schaal, S. Control of legged robots with optimal distribution of contact forces In 2011 11th IEEE-RAS International Conference on Humanoid Robots, pages: 318 - 324, 2011, clmc (inproceedings)

PDF [BibTex]

Learning motion primitive goals for robust manipulation

Stulp, F., Theodorou, E., Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

Abstract

Applying model-free reinforcement learning to manipulation remains challeng-ing for several reasons. First, manipulation involves physical contact, which causes discontinuous cost functions. Second, in manipulation, the end-point of the movement must be chosen carefully, as it represents a grasp which must be adapted to the pose and shape of the object. Finally, there is uncertainty in the object pose, and even the most carefully planned movement may fail if the object is not at the expected position. To address these challenges we 1) present a simplified, computationally more ef-ficient version of our model-free reinforcement learning algorithm PI2; 2) extend PI2 so that it simultaneously learns shape parameters and goal parameters of mo-tion primitives; 3) use shape and goal learning to acquire motion primitives that are robust to object pose uncertainty. We evaluate these contributions on a ma-nipulation platform consisting of a 7-DOF arm with a 4-DOF hand.

am mg

link (url) Project Page [BibTex]

am mg Stulp, F., Theodorou, E., Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S. Learning motion primitive goals for robust manipulation In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

link (url) Project Page [BibTex]

2010

Constrained accelerations for controlled geometric reduction: Sagittal-plane decoupling for bipedal locomotion

Gregg, R. D., Righetti, L., Buchli, J., Schaal, S.

In Humanoid Robots (Humanoids), 2010 10th IEEE-RAS International Conference on, pages: 1-7, December 2010, clmc (inproceedings)

Abstract

Energy-shaping control methods have produced strong theoretical results for asymptotically stable 3D bipedal dynamic walking in the literature. In particular, geometric controlled reduction exploits robot symmetries to control momentum conservation laws that decouple the sagittal-plane dynamics, which are easier to stabilize. However, the associated control laws require high-dimensional matrix inverses multiplied with complicated energy-shaping terms, often making these control theories difficult to apply to highly-redundant humanoid robots. This paper presents a first step towards the application of energy-shaping methods on real robots by casting controlled reduction into a framework of constrained accelerations for inverse dynamics control. By representing momentum conservation laws as constraints in acceleration space, we construct a general expression for desired joint accelerations that render the constraint surface invariant. By appropriately choosing an orthogonal projection, we show that the unconstrained (reduced) dynamics are decoupled from the constrained dynamics. Any acceleration-based controller can then be used to stabilize this planar subsystem, including passivity-based methods. The resulting control law is surprisingly simple and represents a practical way to employ control theoretic stability results in robotic platforms. Simulated walking of a 3D compass-gait biped show correspondence between the new and original controllers, and simulated motions of a 16-DOF humanoid demonstrate the applicability of this method.

am mg

link (url) [BibTex]

2010

am mg Gregg, R. D., Righetti, L., Buchli, J., Schaal, S. Constrained accelerations for controlled geometric reduction: Sagittal-plane decoupling for bipedal locomotion In Humanoid Robots (Humanoids), 2010 10th IEEE-RAS International Conference on, pages: 1-7, December 2010, clmc (inproceedings)

link (url) [BibTex]

Inverse dynamics with optimal distribution of ground reaction forces for legged robots

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In Proceedings of the international conference on climbing and walking robots (CLAWAR) 2010, Nagoya, Japan, Aug.31-Sept.3, 2010, clmc (inproceedings)

Abstract

The control of the interaction of legged robots with their environment is of crucial importance in the design of locomotion controllers. We need to control the effects of the robots movement on the contact reaction forces to prevent slipping, for example. In this contribution, we extend a recent inverse dynamics algorithm for floating base robots to optimize the distribution of contact forces while achieving precise trajectory tracking. The resulting controller is algorithmically simple as compared to other approaches. Numerical simulations show that this result significantly increases the range of possible movements of a humanoid robot as compared to the previous inverse dynamics algorithm. We also present a simplification of the result for practical use on a real robot. Such an algorithm becomes particularly relevant for agile locomotion of robots on difficult terrains where the contacts with the environment are critical, such as walking over rough or slippery terrain

am mg

link (url) [BibTex]

am mg Righetti, L., Buchli, J., Mistry, M., Schaal, S. Inverse dynamics with optimal distribution of ground reaction forces for legged robots In Proceedings of the international conference on climbing and walking robots (CLAWAR) 2010, Nagoya, Japan, Aug.31-Sept.3, 2010, clmc (inproceedings)

link (url) [BibTex]