Shuaijun Wang

Shuaijun Wang

Auto-generated profile, based on publicly available information

Shuaijun Wang

State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150080, P. R. China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 February 2022 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
SWShuaijun Wang
Shuaijun Wang
WHWenbin Hu
Wenbin Hu
LSLining Sun
Lining Sun
XWXin Wang
Xin Wang
ZLZhibin Li
Zhibin Li
This article studied a learning-based approach to learn grasping policies from teleoperated human demonstrations, which can achieve adaptive grasping using three different neural network (NN) structures. To transfer human grasping skills effectively, we used multisensing state within a sliding time window to learn the state–action mapping. By teleoperating an anthropomorphic robotic hand using human hand tracking, we collected training datasets from representative grasping of various objects, which were used to train grasping policies with three proposed NN structures. The learned policies can grasp objects with varying sizes, shapes, and stiffness. We benchmarked the grasping performance of all policies, and experimental validations showed significant advantages of using the sequential history states, compared to the instantaneous feedback. Based on the benchmark, we further validated the best NN structure to conduct extensive experiments of grasping hundreds of unseen objects with adaptive motions and grasping forces.

1 October 2018
Verified
Conference Paper
Closed access
SZShuai Zhang
Shuai Zhang
RHRuihua Han
Ruihua Han
WHWankuan Huang
Wankuan Huang
SWShuaijun Wang
Shuaijun Wang
QHQi Hao
Qi Hao
In this paper, we propose an improved UWB based indoor localization system using Bayesian filtering techniques. The system contains two key components: (1) miniaturized, high updating rate and highly reconfigurable UWB sensors with a linear regression model to calibrate range measurement errors; (2) a set of Bayesian filters which can improve the localization precision by utilizing the spatial correlation between the stationary UWB base stations and the mobile UWB station. Furthermore, a novel measurement transform is proposed to reduce the computational complexity. Experiments are performed in an indoor environment with the ground truth obtained by the motion capture system to validate and evaluate the proposed indoor localization system.

26 January 2024 in International Journal of Humanoid Robotics
Verified
Journal Article
Closed access
SWShuaijun Wang
Shuaijun Wang
LSLining Sun
Lining Sun
MLMantian Li
Mantian Li
PWPengfei Wang
Pengfei Wang
FZFusheng Zha
Fusheng Zha
Qiang LiQiang Li
Qiang Li

1 November 2017
Verified
Conference Paper
Closed access
SZShuai Zhang
Shuai Zhang
SWShuaijun Wang
Shuaijun Wang
CLChengyang Li
Chengyang Li
GLGuocheng Liu
Guocheng Liu
QHQi Hao
Qi Hao
The autonomous navigation of unmanned aerial vehicles (UAVs) require a lot of sensing modalities to improve their cruise efficiency. This paper presents a system for autonomous navigation and path planning of UAVs in GPS-denied environment based on the fusion of geo-registered 3D point clouds with proprioceptive sensors (IMU, odometry and barometer) and the 2D Google maps. The contributions of this paper are illustrated as follows: 1) combination of 2D map and geo-registered 3D point clouds; 2) registration of local point cloud to global geo-registered 3D point clouds; 3) integration of visual odometry, IMU, GPS and barometer. Experiment and simulation results demonstrate the efficacy and robustness of the proposed system.

1 July 2015
Verified
Conference Paper
Closed access
YLYunfei Long
Yunfei Long
SWShuaijun Wang
Shuaijun Wang
WWWei Wu
Wei Wu
XYXiaomin Yang
Xiaomin Yang
Gwanggil JeonGwanggil Jeon
Gwanggil Jeon
KLKai Liu
Kai Liu
With fast speed and reliable capability of depth recovery, two-frequency phase measuring profilometry (PMP) is widely used for reconstructing 3-D surface. However, it suffers from random noise when the number of patterns is less. In this paper, we propose a hybrid pattern coding scheme which embeds Gray coding patterns into high-frequency PMP patterns through amplitude modulation. From captured modulated images, wrapped phase and fringe orders can be simultaneously obtained, and then absolute phase will be computed from the wrapped phase with the fringe orders. Both theoretical analysis and experimental results demonstrate that, compared with standard 3-step PMP, the presented strategy can achieve higher accuracy.

19 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
RHRuihua Han
Ruihua Han
SCShengduo Chen
Shengduo Chen
SWShuaijun Wang
Shuaijun Wang
ZZZeqing Zhang
Zeqing Zhang
RGRui Gao
Rui Gao
JPJia Pan
Jia Pan
The challenges to solving the collision avoidance problem lie in adaptively choosing optimal robot velocities in complex scenarios full of interactive obstacles. In this paper, we propose a distributed approach for multi-robot navigation which combines the concept of reciprocal velocity obstacle (RVO) and the scheme of deep reinforcement learning (DRL) to solve the reciprocal collision avoidance problem under limited information. The novelty of this work is threefold: (1) using a set of sequential VO and RVO vectors to represent the interactive environmental states of static and dynamic obstacles, respectively; (2) developing a bidirectional recurrent module based neural network, which maps the states of a varying number of surrounding obstacles to the actions directly; (3) developing a RVO area and expected collision time based reward function to encourage reciprocal collision avoidance behaviors and trade off between collision risk and travel time. The proposed policy is trained through simulated scenarios and updated by the actor-critic based DRL algorithm. We validate the policy in complex environments with various numbers of differential drive robots and obstacles. The experiment results demonstrate that our approach outperforms the state-of-art methods and other learning based approaches in terms of the success rate, travel time, and average speed. Source code of this approach is available at https://github.com/hanruihua/rl_rvo_nav.