9 papers
Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control
Denis Shcherba, Adrian Abel, Eckart Cobo-Briesewitz +3
Simulation-trained manipulation policies can exploit privileged state information to learn effective contact-rich behaviours, but deployment requires acting from partial observatio…
Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation
Marc Toussaint, Cornelius V. Braun, Armand Jordana +5
Training non-prehensile manipulation policies in contact-rich settings is a core challenge in robotics. While Reinforcement Learning (RL) has demonstrated its strength in such sett…
Variance-Reduced Model Predictive Path Integral via Quadratic Model Approximation
Fabian Schramm, Franki Nguimatsia Tiofack, Nicolas Perrin-Gilbert +2
Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance and low sample efficiency. To a…
Masked Registration and Autoencoding of CT Images for Predictive Tibia Reconstruction
Hongyou Zhou, Cederic Aßmann, Alaa Bejaoui +8
Surgical planning for complex tibial fractures can be challenging for surgeons, as the 3D structure of the later desirable bone alignment may be difficult to imagine. To assist in…
SVN-ICP: Uncertainty Estimation of ICP-based LiDAR Odometry using Stein Variational Newton
Shiping Ma, Haoming Zhang, Marc Toussaint
This letter introduces SVN-ICP, a novel Iterative Closest Point (ICP) algorithm with uncertainty estimation that leverages Stein Variational Newton (SVN) on manifold. Designed spec…
Trajectory First: A Curriculum for Discovering Diverse Policies
Cornelius V. Braun, Sayantan Auddy, Marc Toussaint
Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has becom…
Meta-Optimization and Program Search using Language Models for Task and Motion Planning
Denis Shcherba, Eckart Cobo-Briesewitz, Cornelius V. Braun +1
Intelligent interaction with the real world requires robotic agents to jointly reason over high-level plans and low-level controls. Task and motion planning (TAMP) addresses this b…
RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
Charles Xu, Qiyang Li, Jianlan Luo +1
Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, th…
Stein Variational Evolution Strategies
Cornelius V. Braun, Robert T. Lange, Marc Toussaint
Stein Variational Gradient Descent (SVGD) is a highly efficient method to sample from an unnormalized probability distribution. However, the SVGD update relies on gradients of the…