Publications
Scientific Papers
Multi-Contact Task and Motion Planning Guided by Video Demonstration
Differentiable Collision Detection: a Randomized Smoothing Approach
Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Contact Models in Robotics: a Comparative Analysis
GJK++: Leveraging Acceleration Methods for Faster Collision Detection
QPLayer: efficient differentiation of convex quadratic optimization
Companion Report of PROXQP: an Efficient and Versatile Quadratic Programming Solver for Real-Time Robotics Applications and Beyond
PROXQP: an Efficient and Versatile Quadratic Programming Solver for Real-Time Robotics Applications and Beyond
MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
Visually Guided Model Predictive Robot Control via 6D Object Pose Localization and Tracking
Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems
Model predictive control under hard collision avoidance constraints for a robotic arm
Authors: Arthur Haffemayer, Armand Jordana, Médéric Fourmy, Krzysztof Wojciechowski, Guilhem Saurel, VladimÃr PetrÃk, Florent Lamiraux, Nicolas Mansar
From Compliant to Rigid Contact Simulation: a Unified and Efficient Approach
Authors: Justin Carpentier, Quentin Le Lide, Louis Montaut.
PROXDDP: Proximal Constrained Trajectory Optimization
Authors: Wilson Jallet, Antoine Bambade, Etienne Arlaud, Sarah El-Kazdadi, Nicolas Mansard, Justin Carpentier.
Parallel and Proximal Constrained Linear-Quadratic Methods for Real-Time Nonlinear MPC
Authors: .Wilson Jallet, Ewen Dantec, Etienne Arlaud, Justin Carpentier, Nicolas Mansard.
Linear-time Differential Inverse Kinematics: an Augmented Lagrangian Perspective
Authors: Bruce Wingo, Ajay Sathya, Stéphane Caron, Seth Hutchinson, Justin Carpentier.
Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
Antoine Bambade, Fabian Schramm, Adrien Taylor, Justin Carpentier.