Hongzhuo Liang
YOU?
Author Swipe
View article: Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses
Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses Open
Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge…
View article: Learning 6-DoF Task-oriented Grasp Detection via Implicit Estimation and Visual Affordance
Learning 6-DoF Task-oriented Grasp Detection via Implicit Estimation and Visual Affordance Open
Currently, task-oriented grasp detection approaches are mostly based on pixel-level affordance detection and semantic segmentation. These pixel-level approaches heavily rely on the accuracy of a 2D affordance mask, and the generated grasp …
View article: A Dexterous Hand-Arm Teleoperation System Based on Hand Pose Estimation and Active Vision
A Dexterous Hand-Arm Teleoperation System Based on Hand Pose Estimation and Active Vision Open
Markerless vision-based teleoperation that leverages innovations in computer vision offers the advantages of allowing natural and noninvasive finger motions for multifingered robot hands. However, current pose estimation methods still face…
View article: Reinforcement Learning With Vision-Proprioception Model for Robot Planar Pushing
Reinforcement Learning With Vision-Proprioception Model for Robot Planar Pushing Open
We propose a vision-proprioception model for planar object pushing, efficiently integrating all necessary information from the environment. A Variational Autoencoder (VAE) is used to extract compact representations from the task-relevant p…
View article: Improving Object Grasp Performance via Transformer-Based Sparse Shape Completion
Improving Object Grasp Performance via Transformer-Based Sparse Shape Completion Open
Currently, robotic grasping methods based on sparse partial point clouds have attained excellent grasping performance on various objects. However, they often generate wrong grasping candidates due to the lack of geometric information on th…
View article: Multifingered Grasping Based on Multimodal Reinforcement Learning
Multifingered Grasping Based on Multimodal Reinforcement Learning Open
In this work, we tackle the challenging problem of grasping novel objects using a high-DoF anthropomorphic hand-arm system. Combining fingertip tactile sensing, joint torques and proprioception, a multimodal agent is trained in simulation …
View article: MeshLab 2021.10
MeshLab 2021.10 Open
The open source mesh processing system
View article: TransSC: Transformer-based Shape Completion for Grasp Evaluation
TransSC: Transformer-based Shape Completion for Grasp Evaluation Open
Currently, robotic grasping methods based on sparse partial point clouds have attained a great grasping performance on various objects while they often generate wrong grasping candidates due to the lack of geometric information on the obje…
View article: Self-Adapting Recurrent Models for Object Pushing from Learning in Simulation
Self-Adapting Recurrent Models for Object Pushing from Learning in Simulation Open
Planar pushing remains a challenging research topic, where building the dynamic model of the interaction is the core issue. Even an accurate analytical dynamic model is inherently unstable because physics parameters such as inertia and fri…
View article: Intention-Related Natural Language Grounding via Object Affordance Detection and Intention Semantic Extraction
Intention-Related Natural Language Grounding via Object Affordance Detection and Intention Semantic Extraction Open
Similar to specific natural language instructions, intention-related natural language queries also play an essential role in our daily life communication. Inspired by the psychology term "affordance" and its applications in Human-Robot int…
View article: A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU Open
In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU-based arm tracking method. Transteleop observes the human hand through a low-cos…
View article: Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network
Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network Open
In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands. Robot joint angles are directly generated from depth images of the human hand that …