ConSens: Continuous and Unified Vision-Tactile Sensing for Dexterous Manipulation

Zhixuan Xu, Yichen Li, Xuanye Wu, Tianyu Qiu, Lin Shao

In Submission

ConSens is a compact vision-tactile sensor that provides continuous feedback from pre-contact to post-contact, enabling dexterous manipulation through multi-sensor imitation learning and sim-to-real generalization.

\(\mathcal{T(R,O)}\) Grasp: Efficient Graph Diffusion of Robot-Object Spatial Transformation for Cross-Embodiment Dexterous Grasping

Xin Fei^*, Zhixuan Xu^*, Huaicong Fang, Tianrui Zhang, Lin Shao

International Conference on Robotics and Automation (ICRA) 2026

\(\mathcal{T(R,O)}\) Grasp is a diffusion-based framework with a unified hand-object graph representation for fast, accurate, and embodiment-general dexterous grasp synthesis, achieving 94.83% success at 0.21 s inference.

\(\mathcal{D(R,O)}\) Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping

Zhenyu Wei*, Zhixuan Xu*, Jingxiang Guo, Yiwen Hou, Chongkai Gao, Zhehao Cai, Jiayu Luo, Lin Shao

International Conference on Robotics and Automation (ICRA) 2025

Best Paper Award on Robot Manipulation and Locomotion @ ICRA 2025

Best Paper Award Finalist @ ICRA 2025

Best Robotics Paper Award @ CoRL 2024 Workshop MAPoDeL

Oral Presentation @ CoRL 2024 Workshop LFDM

Oral Presentation @ CoRL 2024 Workshop MAPoDeL

Introduce a novel representation, \(\mathcal{D(R,O)}\) for dexterous grasping tasks. This interaction-centric formulation transcends conventional robot-centric and object-centric paradigms, facilitating generalization across diverse robotic hands and objects.

ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots

Zhixuan Xu*, Chongkai Gao*, Zixuan Liu*, Gang Yang*, Chenrui Tie, Haozhuo Zheng, Haoyu Zhou, Weikun Peng, Debang Wang, Tianrun Hu, Tianyi Chen, Zhouliang Yu, Lin Shao

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024

Oral Presentation

Introduce a framework taking contact synthesis as a unified task representation that can generalizes over objects, robots, and manipulation tasks.

DexSinGrasp: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Cluttered Environments

Lixin Xu, Zixuan Liu, Zhewei Gui, Jingxiang Guo, Zeyu Jiang, Zhixuan Xu, Chongkai Gao, Lin Shao

IEEE Robotics and Automation Letters (RA-L) 2025

Introduce a unified policy for dexterous object singulation and grasping via clutter arrangement curriculum learning.

MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model

Haonan Chen*, Junxiao Li*, Ruihai Wu, Yiwei Liu, Yiwen Hou, Zhixuan Xu, Jingxiang Guo, Chongkai Gao, Zhenyu Wei, Shensi Xu, Jiaqi Huang, Lin Shao

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

Oral Presentation

Disentangle folding tasks into language-guided point cloud trajectory generation and low-level action prediction.

TelePreview: A User-Friendly Teleoperation System with Virtual Arm Assistance for Enhanced Effectiveness

Jingxiang Guo*, Jiayu Luo*, Zhenyu Wei*, Yiwen Hou, Zhixuan Xu, Xiaoyi Lin, Chongkai Gao, Lin Shao

Best Paper Award @ ICRA 2025 Workshop on Human-Centric Teleoperation

Spotlight Presentation @ ICRA 2025 Workshop on Human-Centric Teleoperation

Implement a low-cost teleoperation system utilizing data gloves and IMU sensors, paired with an assistant module that improves data collection process by visualizing future robot operations through visual previews.

Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions

Hongyi Chen*, Yunchao Yao*, Yufei Ye, Zhixuan Xu, Homanga Bharadhwaj, Jiashun Wang, Shubham Tulsiani, Zackory Erickson, Jeffrey Ichnowski

Propose extracting human grasp from web images, from which we retarget, align, and enhance to create a robot grasp dataset.

FLIP: Flow-Centric Generative Planning for General-Purpose Manipulation Tasks

Chongkai Gao, Haozhuo Zhang, Zhixuan Xu, Zhehao Cai, Lin Shao

International Conference on Learning Representations (ICLR) 2025

Oral Presentation @ CoRL 2024 Workshop LEAP

Propose flow-centric generative planning (FLIP) as an interactive world model for general-purpose model-based planning for manipulation tasks.

Diff-LfD: Contact-aware Model-based Learning from Visual Demonstration for Robotic Manipulation via Differentiable Physics-based Simulation and Rendering

Xinghao Zhu, Jinghan Ke, Zhixuan Xu, Zhixin Sun, Bizhe Bai, Jun Lv, Qingtao Liu, Yuwei Zeng, Qi Ye, Cewu Lu, Masayoshi Tomizuka, Lin Shao

Conference on Robot Learning (CoRL) 2023

Oral Presentation

Propose a pipeline to learn dexterous manipulation from human video demonstrations. It includes self-supervised pose and shape estimation via differentiable rendering and contact sequence generation via differentiable simulation.

Zhenyu Wei (intern 2024), PhD student, University of North Carolina at Chapel Hill

Conference Reviewer

• IEEE International Conference on Robotics and Automation (ICRA)

Journal Reviewer

• IEEE Transactions on Robotics (T-RO)
• IEEE Robotics and Automation Letters (RA-L)
• IEEE/ASME Transactions on Mechatronics (TMECH)