Stillleben: Realistic scene synthesis for deep learning in robotics

M Schwarz, S Behnke - 2020 IEEE International Conference on …, 2020 - ieeexplore.ieee.org
Training data is the key ingredient for deep learning approaches, but difficult to obtain for the
specialized domains often encountered in robotics. We describe a synthesis pipeline …

One-shot imitation learning via interaction warping

O Biza, S Thompson, KR Pagidi, A Kumar… - arXiv preprint arXiv …, 2023 - arxiv.org
Imitation learning of robot policies from few demonstrations is crucial in open-ended
applications. We propose a new method, Interaction Warping, for learning SE (3) robotic …

Deep reinforcement learning of dexterous pre-grasp manipulation for human-like functional categorical grasping

D Pavlichenko, S Behnke - 2023 IEEE 19th International …, 2023 - ieeexplore.ieee.org
Many objects such as tools and household items can be used only if grasped in a very
specific way-grasped functionally. Often, a direct functional grasp is not possible, though. We …

Pre-grasp manipulation planning to secure space for power grasping

I Baek, K Shin, H Kim, S Hwang, E Demeester… - Ieee …, 2021 - ieeexplore.ieee.org
An object can be gripped firmly through power grasping, in which the gripper fingers and
palm are wrapped around the object. However, it is difficult to power-grasp an object if it is …

Manipulation and Handover Planning for Dual-Arm Robots*

M Colombo, L Beretta, AM Zanchettin… - 2024 IEEE 20th …, 2024 - ieeexplore.ieee.org
Object manipulation without relying on complex fixtures remains a largely unresolved issue
in industrial robotics, being generally limited to pick-and-place operations of easy to grasp …

Category-level 3D non-rigid registration from single-view RGB images

D Rodriguez, F Huber, S Behnke - 2020 IEEE/RSJ International …, 2020 - ieeexplore.ieee.org
In this paper, we propose a novel approach to solve the 3D non-rigid registration problem
from RGB images using Convolutional Neural Networks (CNNs). Our objective is to find a …

Multi-Stage Book Perception and Bimanual Manipulation for Rearranging Book Shelves

B Sygo, SC Liu, F Wieczorek, M Koshil… - International Conference …, 2023 - Springer
This paper presents an autonomous robotic system for rearranging books on a shelf. We
combine a filtered multi-stage perception approach with a collision-aware manipulation …

Mapless Humanoid Navigation Using Learned Latent Dynamics

A Brandenburger, D Rodriguez… - 2021 IEEE/RSJ …, 2021 - ieeexplore.ieee.org
In this paper, we propose a novel Deep Reinforcement Learning approach to address the
mapless navigation problem, in which the locomotion actions of a humanoid robot are taken …

[PDF][PDF] Online Path Planning by using Learned Latent Dynamics

Efficient and collision-free navigation is an essential requirement for deploying robots in
quotidian scenarios. In the robotics community, Reinforcement Learning (RL) approaches …