activity
20152022
most citedPoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

52 citations · 73 across the 8 of their papers we have counts for

collaborators

18 papers

cs.RO20221 cited

HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers

Yu-Wei Chao, Chris Paxton, Yu Xiang +6

We introduce a new simulation benchmark "HandoverSim" for human-to-robot object handovers. To simulate the giver's motion, we leverage a recent motion capture dataset of hand grasp…

cs.CV20213 cited

RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks

Christopher Xie, Arsalan Mousavian, Yu Xiang +1

Segmenting unseen object instances in cluttered environments is an important capability that robots need when functioning in unstructured environments. While previous methods have…

cs.CV20217 cited

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

Yu-Wei Chao, Wei Yang, Yu Xiang +9

We introduce DexYCB, a new dataset for capturing hand grasping of objects. We first compare DexYCB with a related one through cross-dataset evaluation. We then present a thorough b…

cs.CV20214 cited

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

Luyang Zhu, Arsalan Mousavian, Yu Xiang +4

Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to…

cs.RO2021

Learning Composable Behavior Embeddings for Long-horizon Visual Navigation

Xiangyun Meng, Yu Xiang, Dieter Fox

Learning high-level navigation behaviors has important implications: it enables robots to build compact visual memory for repeating demonstrations and to build sparse topological m…

cs.RO2020

Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds

Lirui Wang, Yu Xiang, Wei Yang +2

6D robotic grasping beyond top-down bin-picking scenarios is a challenging task. Previous solutions based on 6D grasp synthesis with robot motion planning usually operate in an ope…