Publications (12)
Diffusion Models for Robotic Manipulation: A Survey
Rosa Wolf, Yitian Shi, Sheng Liu +1
Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in ro…
AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation
Claudius Kienle, Benjamin Alt, Finn Schneider +3
Despite the widespread adoption of industrial robots in automotive assembly, wire harness installation remains a largely manual process, as it requires precise and flexible manipul…
Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey
Edgar Welte, Rania Rayyes
Dexterous manipulation is a crucial yet highly complex challenge in humanoid robotics, demanding precise, adaptable, and sample-efficient learning methods. As humanoid robots are u…
Human-Interpretable Uncertainty Explanations for Point Cloud Registration
Johannes A. Gaus, Loris Schneider, Yitian Shi +3
In this paper, we address the point cloud registration problem, where well-known methods like ICP fail under uncertainty arising from sensor noise, pose-estimation errors, and part…
PAWS: Preference Learning with Advantage-Weighted Segments
Aleksandar Taranovic, Onur Celik, Niklas Freymuth +6
Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods…
Tracing Back Error Sources to Explain and Mitigate Pose Estimation Failures
Loris Schneider, Yitian Shi, Rosa Wolf +3
Robust estimation of object poses in robotic manipulation is often addressed using foundational general estimators, that aim to handle diverse error sources naively within a single…
vMF-Contact: Uncertainty-aware Evidential Learning for Probabilistic Contact-grasp in Noisy Clutter
Yitian Shi, Edgar Welte, Maximilian Gilles +1
Grasp learning in noisy environments, such as occlusions, sensor noise, and out-of-distribution (OOD) objects, poses significant challenges. Recent learning-based approaches focus…
HOGraspFlow: Taxonomy-Aware Hand-Object Retargeting for Multi-Modal SE(3) Grasp Generation
Yitian Shi, Zicheng Guo, Rosa Wolf +2
We propose Hand-Object\emph{(HO)GraspFlow}, an affordance-centric approach that retargets a single RGB with hand-object interaction (HOI) into multi-modal executable parallel jaw g…
VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility
Yitian Shi, Di Wen, Guanqi Chen +5
We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveragi…
Learning Inverse Statics Models Efficiently
Rania Rayyes, Daniel Kubus, Carsten Hartmann +1
Online Goal Babbling and Direction Sampling are recently proposed methods for direct learning of inverse kinematics mappings from scratch even in high-dimensional sensorimotor spac…
Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization
Yitian Shi, Di Wen, Zhengqi Han +6
Learning from human video demonstrations remains challenging due to noisy hand-object interactions, unseen objects with partial observation, and cross-embodiment discrepancy. To ad…
FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
Edgar Welte, Yitian Shi, Rosa Wolf +2
Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and w…