3 citations · 6 across the 25 of their papers we have counts for
14 papers · 1 filter
Large Video Planner Enables Generalizable Robot Control
Boyuan Chen, Tianyuan Zhang, Haoran Geng +9
General-purpose robots require decision-making models that generalize across diverse tasks and environments. Recent works build robot foundation models by extending multimodal larg…
How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?
Lexi Foland, Thomas Cohn, Adam Wei +3
Diffusion policies have shown impressive results in robot imitation learning, even for tasks that require satisfaction of kinematic equality constraints. However, task performance…
Mixed Discrete and Continuous Planning using Shortest Walks in Graphs of Convex Sets
Savva Morozov, Tobia Marcucci, Bernhard Paus Graesdal +3
We study the Shortest-Walk Problem (SWP) in a Graph of Convex Sets (GCS). A GCS is a graph where each vertex is paired with a convex program, and each edge couples adjacent program…
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
TRI LBM Team, Jose Barreiros, Andrew Beaulieu +79
Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently…
Steerable Scene Generation with Post Training and Inference-Time Search
Nicholas Pfaff, Hongkai Dai, Sergey Zakharov +2
Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as hi…
Dexterous Contact-Rich Manipulation via the Contact Trust Region
H. J. Terry Suh, Tao Pang, Tong Zhao +1
What is a good local description of contact dynamics for contact-rich manipulation, and where can we trust this local description? While many approaches often rely on the Taylor ap…
A New Semidefinite Relaxation for Linear and Piecewise-Affine Optimal Control with Time Scaling
Lujie Yang, Tobia Marcucci, Pablo A. Parrilo +1
We introduce a semidefinite relaxation for optimal control of linear systems with time scaling. These problems are inherently nonconvex, since the system dynamics involves bilinear…
Superfast Configuration-Space Convex Set Computation on GPUs for Online Motion Planning
Peter Werner, Richard Cheng, Tom Stewart +2
In this work, we leverage GPUs to construct probabilistically collision-free convex sets in robot configuration space on the fly. This extends the use of modern motion planning alg…
Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setups
Nicholas Pfaff, Evelyn Fu, Jeremy Binagia +2
Simulating object dynamics from real-world perception shows great promise for digital twins and robotic manipulation but often demands labor-intensive measurements and expertise. W…
Should VLMs be Pre-trained with Image Data?
Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre +8
Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capabil…
Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels
Adam Wei, Abhinav Agarwal, Boyuan Chen +3
Cotraining with demonstration data generated both in simulation and on real hardware has emerged as a promising recipe for scaling imitation learning in robotics. This work seeks t…
Sampling-Based Motion Planning with Discrete Configuration-Space Symmetries
Thomas Cohn, Russ Tedrake
When planning motions in a configuration space that has underlying symmetries (e.g. when manipulating one or multiple symmetric objects), the ideal planning algorithm should take a…
Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization
Lujie Yang, H. J. Terry Suh, Tong Zhao +5
We present a low-cost data generation pipeline that integrates physics-based simulation, human demonstrations, and model-based planning to efficiently generate large-scale, high-qu…
History-Guided Video Diffusion
Kiwhan Song, Boyuan Chen, Max Simchowitz +3
Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is nat…