Search Results for author: Ludovic Righetti

Found 18 papers, 8 papers with code

Model Based Meta Learning of Critics for Policy Gradients

no code implementations5 Apr 2022 Sarah Bechtle, Ludovic Righetti, Franziska Meier

In this paper we present a framework to meta-learn the critic for gradient-based policy learning.

Meta-Learning

Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimization

no code implementations14 Jul 2021 Miroslav Bogdanovic, Majid Khadiv, Ludovic Righetti

We present a general, two-stage reinforcement learning approach to create robust policies that can be deployed on real robots without any additional training using a single demonstration generated by trajectory optimization.

reinforcement-learning

Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting

1 code implementation22 Jun 2021 Armand Jordana, Justin Carpentier, Ludovic Righetti

In this work, we introduce a generic and scalable method based on multiple shooting to learn latent representations of indirectly observed dynamical systems.

Simultaneous Navigation and Construction Benchmarking Environments

1 code implementation31 Mar 2021 Wenyu Han, Chen Feng, Haoran Wu, Alexander Gao, Armand Jordana, Dong Liu, Lerrel Pinto, Ludovic Righetti

We need intelligent robots for mobile construction, the process of navigating in an environment and modifying its structure according to a geometric design.

Visual Navigation

Mobile Construction Benchmark

no code implementations1 Jan 2021 Wenyu Han, Chen Feng, Haoran Wu, Alexander Gao, Armand Jordana, Dongdong Liu, Lerrel Pinto, Ludovic Righetti

We need intelligent robots to perform mobile construction, the process of moving in an environment and modifying its geometry according to a design plan.

Robot Learning with Crash Constraints

1 code implementation16 Oct 2020 Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe

We consider failing behaviors as those that violate a constraint and address the problem of learning with crash constraints, where no data is obtained upon constraint violation.

Robust walking based on MPC with viability guarantees

no code implementations9 Oct 2020 Mohammad Hasan Yeganegi, Majid Khadiv, Andrea Del Prete, S. Ali A. Moosavian, Ludovic Righetti

In this approach, instead of adding a (conservative) terminal constraint to the problem, we propose to use the measured state projected to the viability kernel in the OCP solved at each control cycle.

Robotics

An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research

1 code implementation30 Sep 2019 Felix Grimminger, Avadesh Meduri, Majid Khadiv, Julian Viereck, Manuel Wüthrich, Maximilien Naveau, Vincent Berenz, Steve Heim, Felix Widmaier, Thomas Flayols, Jonathan Fiene, Alexander Badri-Spröwitz, Ludovic Righetti

Finally, to demonstrate the capabilities of the quadruped, we present a novel controller which combines feedforward contact forces computed from a kino-dynamic optimizer with impedance control of the center of mass and base orientation.

Robotics

Meta Learning via Learned Loss

no code implementations25 Sep 2019 Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav Sukhatme, Franziska Meier

We present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures.

Meta-Learning reinforcement-learning

Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control

1 code implementation11 Sep 2019 Carlos Mastalli, Rohan Budhiraja, Wolfgang Merkt, Guilhem Saurel, Bilal Hammoud, Maximilien Naveau, Justin Carpentier, Ludovic Righetti, Sethu Vijayakumar, Nicolas Mansard

Additionally, we propose a novel optimal control algorithm called Feasibility-driven Differential Dynamic Programming (FDDP).

Robotics Optimization and Control

Learning to Explore in Motion and Interaction Tasks

no code implementations10 Aug 2019 Miroslav Bogdanovic, Ludovic Righetti

In this paper we present a novel approach for efficient exploration that leverages previously learned tasks.

Efficient Exploration

Learning Variable Impedance Control for Contact Sensitive Tasks

no code implementations17 Jul 2019 Miroslav Bogdanovic, Majid Khadiv, Ludovic Righetti

We propose learning a policy giving as output impedance and desired position in joint space and compare the performance of that approach to torque and position control under different contact uncertainties.

Meta-Learning via Learned Loss

1 code implementation12 Jun 2019 Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav Sukhatme, Franziska Meier

This information shapes the learned loss function such that the environment does not need to provide this information during meta-test time.

Meta-Learning

Curious iLQR: Resolving Uncertainty in Model-based RL

no code implementations15 Apr 2019 Sarah Bechtle, Yixin Lin, Akshara Rai, Ludovic Righetti, Franziska Meier

In this work, we propose a model-based reinforcement learning (MBRL) framework that combines Bayesian modeling of the system dynamics with curious iLQR, an iterative LQR approach that considers model uncertainty.

Model-based Reinforcement Learning reinforcement-learning

Leveraging Contact Forces for Learning to Grasp

1 code implementation19 Sep 2018 Hamza Merzic, Miroslav Bogdanovic, Daniel Kappler, Ludovic Righetti, Jeannette Bohg

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.

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

no code implementations28 Jul 2016 Brahayam Ponton, Alexander Herzog, Stefan Schaal, Ludovic Righetti

This model is non-linear and non-convex; however, we find a relaxation of the problem that allows us to formulate it as a single convex quadratically-constrained quadratic program (QCQP) that can be very efficiently optimized.

Robotics

Cannot find the paper you are looking for? You can Submit a new open access paper.