Hanwen Cao 曹瀚文
I am a Ph.D. student at University of California, San Diego (UCSD). I do research at Extential Robotics Laboratory and am fortunate to be advised by Prof. Nikolay Atanasov.
Before moving to UCSD, I obtained my B.E. degree from Shanghai Jiaotong University, Shanghai, China. My undergraduate supervisor is Prof. Cewu Lu.
Email  / 
Google Scholar  / 
Github
|
|
Research
I'm interested in robotics and computer vision.
|
|
PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking>
Hanwen Cao,
George J. Pappas,
Nikolay Atanasov,
under review
project page /
paper /
Probabilistic data association Kalman filter for multi-object tracking (MOT).
|
|
MISO: Multiresolution Submap Optimization for Efficient Globally Consistent Neural Implicit Reconstruction>
Yulun Tian,
Hanwen Cao,
Sunghwan Kim
Nikolay Atanasov,
RSS 2025
paper /
Deep SDF SLAM with neural implicit grid features.
|
|
Multi-Robot Object SLAM Using Distributed Variational Inference>
Hanwen Cao,
Sriram Shreedharan,
Nikolay Atanasov,
Robotics and Automation Letter (RA-L), 2024
project page /
paper /
Distributed MSCKF (Multi-State Constrained Kalman Filter) for multi-robot SLAM.
|
|
SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping
Hanwen Cao,
Hao-Shu Fang,
Wenhai Liu,
Cewu Lu
RA-L, 2021
project page /
paper /
A large-scale real-world dataset for suction grasping in cluttered scenes.
|
|
ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
Hanwen Cao,
Yongyi Lu,
Cewu Lu
Bo Pang,
Gongshen Liu,
Alan Yuille
BMVC, 2020
paper /
code /
A flexible module for point cloud sequence segmentation.
|
|
Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts
Bo Pang,
Kaiwen Zha,
Hanwen Cao,
Jiajun Tang,
Minghui Yu,
Cewu Lu
Nature Machine Intelligence, 2020
paper
A general model for complex sequential understanding.
|
|
Deep RNN Framework for Visual Sequential Applications
Bo Pang,
Kaiwen Zha,
Hanwen Cao,
Cewu Lu
CVPR, 2019
paper /
code /
A new deep RNN framework with better performance on visual sequential applications.
|
|