Quentin Le Lidec
I am a postdoctoral researcher at the Courant Institute of Mathematical Sciences at New York University, working with Yann LeCun on learning world models for robotics.
My research interests are in machine learning, optimization, and computer vision, particularly as applied to robotics. I also work on the open-source Pinocchio and Simple libraries, making differentiable physics tools accessible for the robotics community.
Prior to that, I received my PhD in computer science from ENS Paris where I was working under the supervision of Justin Carpentier, Ivan Laptev, and Cordelia Schmid. Even before that, I received an engineering degree from École Polytechnique and an MSc in Mathematics, Computer Vision, and Machine Learning from École Normale Supérieure Paris-Saclay.
Email /
Scholar /
Github /
LinkedIn
|
Research
I'm interested in machine learning, optimization, and computer vision, particularly as applied to robotics. My work focuses on differentiable physics simulation, contact modeling, and learning-based approaches for robot control and manipulation.
|
Sobolev Diffusion Policy
Théotime Le Hellard*,
Franki Nguimatsia Tiofack*,
Quentin Le Lidec,
Justin Carpentier
preprint, 2025
pdf
/
bibtex
A novel framework combining diffusion policy with trajectory optimization, using gradient-based solvers to generate locally optimal trajectories and leveraging their feedback gains to enrich Sobolev training with first-order information for more efficient policy learning.
|
Differentiable optimization for robotics: simulation, learning and control
Quentin Le Lidec
PhD thesis at Ecole Normale Supérieure, 2024
hal
/
pdf
/
bibtex
Optimization is ubiquitous in modern robotics. This thesis aims to bring fundamental robotics tools to the differentiable programming paradigm, looking at robot simulation through the lens of numerical optimization techniques and proposing approaches for learning controllers.
|
End-to-End and Highly-Efficient Differentiable Simulation for Robotics
Quentin Le Lidec,
Louis Montaut,
Yann De Mont-Marin,
Justin Carpentier
preprint, 2024
project page
/
arXiv
/
pdf
/
code
/
bibtex
A unified and efficient algorithmic solution for computing analytical derivatives of robotic simulators, achieving state-of-the-art timings from 5 microseconds for a 7-dof manipulator up to 95 microseconds for 36-dof humanoid.
|
From Compliant to Rigid Contact Simulation: a Unified and Efficient Approach
Justin Carpentier,
Quentin Le Lidec,
Louis Montaut
Robotics: Science and Systems (RSS), 2024
project page
/
arXiv
/
pdf
/
code
/
bibtex
A unified approach to solving contact interactions using ADMM and proximal algorithms, handling both compliant and rigid contact interfaces with automatic hyperparameter adaptation.
|
GJK++: Leveraging Acceleration Methods for Faster Collision Detection
Louis Montaut,
Quentin Le Lidec,
Vladimir Petrik,
Josef Sivic,
Justin Carpentier
IEEE Transactions on Robotics, 2024
project page
/
hal
/
pdf
/
bibtex
Accelerated collision detection by establishing GJK as a Frank-Wolfe algorithm and introducing Nesterov acceleration, leading to up to two times faster computation.
|
Reconciling RaiSim with the Maximum Dissipation Principle
Quentin Le Lidec,
Justin Carpentier
IEEE Transactions on Robotics, 2024
project page
/
hal
/
pdf
/
bibtex
Algorithmic correction of the RaiSim contact algorithm to properly handle the maximum dissipation principle for more physically-consistent simulation.
|
Contact Models in Robotics: a Comparative Analysis
Quentin Le Lidec,
Wilson Jallet,
Louis Montaut,
Ivan Laptev,
Cordelia Schmid,
Justin Carpentier
IEEE Transactions on Robotics, 2023
project page
/
hal
/
pdf
/
code
/
bibtex
Comprehensive survey and benchmark of contact models in robotics simulators, exposing physical relaxations and computational limitations with open-source implementations.
|
Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control
Quentin Le Lidec,
Wilson Jallet,
Ivan Laptev,
Cordelia Schmid,
Justin Carpentier
IEEE International Conference on Robotics and Automation (ICRA), 2023
project page
/
hal
/
pdf
/
bibtex
Combining reinforcement learning and trajectory optimization using Sobolev learning and augmented Lagrangian techniques to learn global control policies faster.
|
Differentiable Collision Detection: a Randomized Smoothing Approach
Louis Montaut,
Quentin Le Lidec,
Antoine Bambade,
Vladimir Petrik,
Josef Sivic,
Justin Carpentier
IEEE International Conference on Robotics and Automation (ICRA), 2023
arXiv
/
pdf
/
bibtex
Generic approach to compute derivatives of collision detection for convex shapes using randomized smoothing techniques, with microsecond computation times.
|
Collision Detection Accelerated: An Optimization Perspective
Louis Montaut,
Quentin Le Lidec,
Vladimir PetrĂk,
Josef Sivic,
Justin Carpentier
Robotics: Science and Systems (RSS), 2022
project page
/
pdf
/
code
/
bibtex
Showing collision detection is fundamentally a convex optimization problem and introducing accelerated collision detection using Nesterov acceleration.
|
Augmenting differentiable physics with randomized smoothing
Quentin Le Lidec,
Louis Montaut,
Cordelia Schmid,
Ivan Laptev,
Justin Carpentier
RSS Workshop on Differentiable Simulation For Robotics, 2022
arXiv
/
pdf
/
bibtex
Leveraging randomized smoothing to estimate gradients in optimization problems involving non-smooth physical processes for mesh reconstruction and optimal control.
|
Leveraging randomized smoothing for optimal control of nonsmooth dynamical systems
Quentin Le Lidec,
Fabian Schramm,
Louis Montaut,
Cordelia Schmid,
Ivan Laptev,
Justin Carpentier
Nonlinear Analysis: Hybrid Systems, 2021
hal
/
pdf
/
bibtex
Introducing Randomized Differential Dynamic Programming (R-DDP) to handle nonsmooth dynamics with contacts and friction in a sample-efficient way.
|
Differentiable rendering with perturbed optimizers
Quentin Le Lidec,
Ivan Laptev,
Cordelia Schmid,
Justin Carpentier
Advances in Neural Information Processing Systems (NeurIPS), 2021
pdf
/
code
/
bibtex
Studying differentiable renderers through randomized optimization and perturbed optimizers, with applications to 6D pose estimation and 3D mesh reconstruction.
|
Differentiable simulation for physical system identification
Quentin Le Lidec,
Igor Kalevatykh,
Ivan Laptev,
Cordelia Schmid,
Justin Carpentier
IEEE Robotics and Automation Letters, 2021
pdf
/
code
/
bibtex
Differentiable simulation framework for accurate estimation of friction coefficients and object masses using staggered projections and analytical derivatives.
|
Code
I contribute to several open-source robotics libraries, making differentiable physics tools accessible for the robotics community.
|
Simple
github
/
documentation
A highly efficient library for differentiable simulation of multibody systems with contacts. Simple provides analytical derivatives for rigid body dynamics and contact interactions, enabling gradient-based optimization for robotics applications.
|
Pinocchio
github
/
documentation
A fast and flexible implementation of rigid body dynamics algorithms and their analytical derivatives. Pinocchio is widely used in robotics for motion planning, control, and simulation of complex robotic systems.
|
ContactBench
github
This repository contains C++ implementations of physical formulations of contacts and their associated numerical solvers. It also provides benchmarks between these different contact formulations to evaluate their physical accuracy and computational efficiency.
|
diffqcqp
github
A simple differentiable QCQP (Quadratically Constrained Quadratic Programming) solver with Python bindings that can be used in PyTorch for end-to-end optimization workflows.
|
Miscellanea
Academic Service: Reviewer for NeurIPS, ICML, RSS, ICRA, IROS, T-RO, RA-L, L4DC, Humanoids.
Teaching: Teaching assistant for "Convex optimization" course at MSc MVA, ENS Paris-Saclay.
|
|