|
Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation
Shengzeng Huo, Anqing Duan, Lijun Han, Luyin Hu, Hesheng Wang and David Navarro-Alarcon
preprint, 2023  
arxiv
To facilitate the efficient learning of robot manipulation skills, in this work, we propose a new approach comprised of
three modules: (1) learning of general prior knowledge with random explorations in simulation, including state representations, dynamic models, and the constrained action space of the task; (2) extraction of a state alignment-based reward function from a single demonstration video; (3) real-time optimization of the imitation policy under systematic safety constraints with sampling-based model predictive control
|
|
Rearranging Deformable Linear Objects for Implicit Goals with Self-Supervised Planning and Control
Shengzeng Huo,Fangyuan Wang, Luyin Hu, Peng Zhou, Jihong Zhu, Hesheng Wang and David Navarro-Alarcon
Advanced Intelligent System, 2024  
arxiv
To develop advanced robotic manipulation
capabilities in unstructured environments that avoid these
assumptions, we propose a novel long-horizon framework that
exploits contrastive planning in finding promising collaborative
actions.
|
|
Keypoint-Based Bimanual Shaping of Deformable Linear Objects under Environmental Constraints using Hierarchical Action Planning
Shengzeng Huo,
Anqing Duan, Chengxi Li, Peng Zhou, Wanyu Ma, Hesheng Wang and David Navarro-Alarcon
RAL, 2022  
IEEE
/
arxiv
This letter addresses the problem of contact-based manipulation of deformable linear objects (DLOs) towards desired shapes with a dual-arm robotic system.
|
|
A Sensor-Based Robotic Line Scan System with Adaptive ROI for Inspection of Defects over Convex Free-form Specular Surfaces
Shengzeng Huo, Bin Zhang, Muhammad Muddassir, David T. W. Chik and David Navarro-Alarcon.
IEEE Sensor Journal, 2021  
ieee
/
pdf
/
We present a novel sensor-based system to perform defect inspection tasks automatically over free-form specular surfaces.
|
|
LaSeSOM: A Latent Representation Framework for Semantic Soft Object Manipulation
Peng Zhou, Jihong Zhu,
Shengzeng Huo*,
and David Navarro-Alarcon.
RAL, 2021  
ieee
/
pdf
We proposed latent framework to enable soft object representation more generic (independent from the object’s geometry and its mechanical properties) and scalable (it can work with 1D/2D/3D tasks). I
|
|
A Robotic Defect Inspection System for Free-Form Specular Surfaces
Shengzeng Huo,
David.T.W. Chik and David Navarro-Alarcon
ICRA, 2021  
ieee
/
pdf
We present a robotic system to automatically perform defect inspection tasks over free-form specular surfaces, which the image acquisition sub-system is equipped with a 6-DOF robot manipulator to achieve flexible scanning.
|
|
Action Planning for Packaging Long Linear Elastic Objects with Bimanual Robotic Manipulation
Wanyu Ma, Bin Zhang, Lijun Han,
Shengzeng Huo, Hesheng Wang and David Navarro-Alarcon
TMech,2022  
arxiv
/
IEEE
we propose a new action planning approach to automatically pack long linear elastic objects into common-size boxes with a bimanual robotic system.
|
|
An AR-Assisted Deep Reinforcement Learning-Based Approach Towards Mutual-Cognitive Safe Human-Robot Interaction
Chengxi Li, Pai Zheng, Yue Yin, Yat Ming Pang,
Shengzeng Huo
RCIM,2022  
ELSEVIER
To achieve symbiotic human-robot interaction (HRI), this work proposes a mutual-cognitive safe HRI approach including worker visual augmentation, robot velocity control, Digital Twin-enabled motion preview and collision detection, and Deep Reinforcement Learning-based
robot collision avoidance motion planning in the Augmented Reality-assisted manner.
|
|