Bundletrack: 6d pose tracking for novel objects without instance or category-level 3d models

B Wen, K Bekris - 2021 IEEE/RSJ International Conference on …, 2021‏ - ieeexplore.ieee.org
Tracking the 6D pose of objects in video sequences is important for robot manipulation. Most
prior efforts, however, often assume that the target object's CAD model, at least at a category …

Catgrasp: Learning category-level task-relevant gras** in clutter from simulation

B Wen, W Lian, K Bekris… - … Conference on Robotics …, 2022‏ - ieeexplore.ieee.org
Task-relevant gras** is critical for industrial assembly, where downstream manipulation
tasks constrain the set of valid grasps. Learning how to perform this task, however, is …

You only demonstrate once: Category-level manipulation from single visual demonstration

B Wen, W Lian, K Bekris, S Schaal - arxiv preprint arxiv:2201.12716, 2022‏ - arxiv.org
Promising results have been achieved recently in category-level manipulation that
generalizes across object instances. Nevertheless, it often requires expensive real-world …

se (3)-tracknet: Data-driven 6d pose tracking by calibrating image residuals in synthetic domains

B Wen, C Mitash, B Ren… - 2020 IEEE/RSJ …, 2020‏ - ieeexplore.ieee.org
Tracking the 6D pose of objects in video sequences is important for robot manipulation. This
task, however, introduces multiple challenges:(i) robot manipulation involves significant …

Robust, occlusion-aware pose estimation for objects grasped by adaptive hands

B Wen, C Mitash, S Soorian, A Kimmel… - … on Robotics and …, 2020‏ - ieeexplore.ieee.org
Many manipulation tasks, such as placement or within-hand manipulation, require the
object's pose relative to a robot hand. The task is difficult when the hand significantly …

Task-driven perception and manipulation for constrained placement of unknown objects

C Mitash, R Shome, B Wen… - IEEE Robotics and …, 2020‏ - ieeexplore.ieee.org
Recent progress in robotic manipulation has dealt with the case of previously unknown
objects in the context of relatively simple tasks, such as bin-picking. Existing methods for …

Dual projection generative adversarial networks for conditional image generation

L Han, MR Min, A Stathopoulos… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Abstract Conditional Generative Adversarial Networks (cGANs) extend the standard
unconditional GAN framework to learning joint data-label distributions from samples, and …

Interleaving monte carlo tree search and self-supervised learning for object retrieval in clutter

B Huang, T Guo, A Boularias… - … Conference on Robotics …, 2022‏ - ieeexplore.ieee.org
In this study, working with the task of object retrieval in clutter, we have developed a robot
learning framework in which Monte Carlo Tree Search (MCTS) is first applied to enable a …

Learning sensorimotor primitives of sequential manipulation tasks from visual demonstrations

J Liang, B Wen, K Bekris… - … Conference on Robotics …, 2022‏ - ieeexplore.ieee.org
This work aims to learn how to perform complex robot manipulation tasks that are composed
of several, consecutively executed low-level sub-tasks, given as input a few visual …

Mono-star: Mono-camera scene-level tracking and reconstruction

H Chang, DM Ramesh, S Geng, Y Gan… - … on Robotics and …, 2023‏ - ieeexplore.ieee.org
We present Mono-STAR, the first real-time 3D reconstruction system that simultaneously
supports semantic fusion, fast motion tracking, non-rigid object deformation, and topological …