H
Hong Liu
Researcher at Harbin Institute of Technology
Publications - 315
Citations - 3521
Hong Liu is an academic researcher from Harbin Institute of Technology. The author has contributed to research in topics: Robot & Control theory. The author has an hindex of 25, co-authored 302 publications receiving 2450 citations. Previous affiliations of Hong Liu include Zhejiang University City College.
Papers
More filters
Journal ArticleDOI
Robot grasp detection using multimodal deep convolutional neural networks
TL;DR: A novel robot grasp detection system that maps a pair of RGB-D images of novel objects to best grasping pose of a robotic gripper and presents a two-stage closed-loop grasping candidate estimator to accelerate the searching efficiency of grasping-candidate generation.
Journal ArticleDOI
Switching-State Phase Shift Method for Three-Phase-Current Reconstruction With a Single DC-Link Current Sensor
TL;DR: A new phase-current reconstruction method, switching-state phase shift (SSPS), is proposed based on the PWM pattern modification, which can realize high-quality reconstruction to the phase current with less impacts on the output current ripples and switching losses.
Journal ArticleDOI
The Modular Multisensory DLR-HIT-Hand: Hardware and Software Architecture
TL;DR: A hierarchical software structure has been established to perform all data processing and the control of the hand and provides basic air position indicator functions and skills to access all hardware resources for data acquisition, computation, and teleoperation.
Journal ArticleDOI
Robust EMG pattern recognition in the presence of confounding factors: features, classifiers and adaptive learning
TL;DR: This paper investigated EMG pattern recognition of compound confounding factors including electrode shift, force variation, limb posture and temporary drift, and showed that the features extracted from the frequency domain improved the CA by 30% in comparison with their original time-domain representations.
Journal ArticleDOI
Combined Use of FSR Sensor Array and SVM Classifier for Finger Motion Recognition Based on Pressure Distribution Map
TL;DR: A large variety of finger motions are discriminated based on the diversities of the pressure distribution produced by the mechanical actions of muscles on the forearm to suggest that the proposed method has great application prospects for the control of multi-DOF dexterous hand prosthesis.