Xiansheng Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiansheng Yang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Yunjiang Lou
School of Intelligent Science and Engineering, Harbin Institute of Technology Shenzhen, Shenzhen, China
7 shared publications - Haopeng Hu
Harbin Institute of Technology Shenzhen
3 shared publications - Xiaogang Xiong
School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China
3 shared publications - Zhenyu Zou
Harbin Institute of Technology Shenzhen, Shenzhen, China
2 shared publications - Genliang Chen
META Robotics Institute, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Guoyuan Liang
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
1 shared publication
Latest Publications
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Multipole Magnetic Tactile Sensor With Super-Resolution for 3-D Pose Estimation
Magnetic tactile sensors are widely used in tactile servo and robotic manipulations because of their compact size and high sensitivity. However, their spatial resolution is constrained by the number of Hall elements in a contact area, while their limited capacity to perceive 3D information hinders their broader applications. This paper introduces a grid multipole magnetization method for magnetic tactile sensors that achieves super-resolution and 3D pose perception without increasing the density of Hall elements. By magnetizing the soft contact surface with the proposed grid multipole magnetization method and equipping with different deep neural networks (DNNs), this newly fabricated magnetic-based tactile sensor offers improved 3D sensing capabilities at a sampling frequency of 380 Hz of all 5 Hall sensors within a compact size of 20 × 20mm and a thickness of 3.5 mm. It accurately perceives single-point contacts (contact force ranging from 0 to 2.5 N, with spatial and force resolutions of 0.1 mm and 0.05 N, respectively), as well as providing measurements for 2D rotation angles (−90° to 90°, resolution: 0.33°) and capturing 3D pose features (roll, pitch, yaw angle resolutions: 0.046°, 0.128°, and 0.096° over ranges from −5° to 5°). The effectiveness of this methodology is validated through experiments demonstrating a remarkable improvement in spatial super-resolution by a factor of 70, offering innovative solutions for robotic tactile sensors with numerous potential applications in dexterous manipulation.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Multipole Magnetic Tactile Sensor With Super-Resolution for 3-D Pose Estimation
Magnetic tactile sensors are widely used in tactile servo and robotic manipulations because of their compact size and high sensitivity. However, their spatial resolution is constrained by the number of Hall elements in a contact area, while their limited capacity to perceive 3D information hinders their broader applications. This paper introduces a grid multipole magnetization method for magnetic tactile sensors that achieves super-resolution and 3D pose perception without increasing the density of Hall elements. By magnetizing the soft contact surface with the proposed grid multipole magnetization method and equipping with different deep neural networks (DNNs), this newly fabricated magnetic-based tactile sensor offers improved 3D sensing capabilities at a sampling frequency of 380 Hz of all 5 Hall sensors within a compact size of 20 × 20mm and a thickness of 3.5 mm. It accurately perceives single-point contacts (contact force ranging from 0 to 2.5 N, with spatial and force resolutions of 0.1 mm and 0.05 N, respectively), as well as providing measurements for 2D rotation angles (−90° to 90°, resolution: 0.33°) and capturing 3D pose features (roll, pitch, yaw angle resolutions: 0.046°, 0.128°, and 0.096° over ranges from −5° to 5°). The effectiveness of this methodology is validated through experiments demonstrating a remarkable improvement in spatial super-resolution by a factor of 70, offering innovative solutions for robotic tactile sensors with numerous potential applications in dexterous manipulation.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (4) , 2685-2696
Robot Learning From Demonstration for Assembly With Sequential Assembly Movement Primitives
To facilitate the labor-consuming flexible assembly lines with robots, the robot learning from demonstration (LfD) is the promising way to efficiently impart human assembly skills to robots. Aiming at the challenging complex precise assembly tasks, which are contact-rich and require 6-D movement, an LfD method is proposed here. Due to the inconsistent requirements for the robot's assembly movement, the whole robotic assembly processes are composed of three phases, namely, the approaching, aligning, and assembling phase. The policies, which are prestructured by the proposed sequential assembly movement primitives, are learned exclusively to guide the robot's movement in each phase. In the approaching phase, the policy generates a reliable path for the robot to accurately track. However, in the aligning and assembling phase, the polices enable the robot's active compliant behavior to accomplish the complex precise assembly task. Robotic assembly experiments with four objects are conducted to validate the proposed LfD methods with a torque-controlled robot. Experiment results indicate that the proposed LfD method applied with the proposed policies achieves high reliability and efficiency.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (4) , 2685-2696
Robot Learning From Demonstration for Assembly With Sequential Assembly Movement Primitives
To facilitate the labor-consuming flexible assembly lines with robots, the robot learning from demonstration (LfD) is the promising way to efficiently impart human assembly skills to robots. Aiming at the challenging complex precise assembly tasks, which are contact-rich and require 6-D movement, an LfD method is proposed here. Due to the inconsistent requirements for the robot's assembly movement, the whole robotic assembly processes are composed of three phases, namely, the approaching, aligning, and assembling phase. The policies, which are prestructured by the proposed sequential assembly movement primitives, are learned exclusively to guide the robot's movement in each phase. In the approaching phase, the policy generates a reliable path for the robot to accurately track. However, in the aligning and assembling phase, the polices enable the robot's active compliant behavior to accomplish the complex precise assembly task. Robotic assembly experiments with four objects are conducted to validate the proposed LfD methods with a torque-controlled robot. Experiment results indicate that the proposed LfD method applied with the proposed policies achieves high reliability and efficiency.
- 20 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (8) , 8388-8397
Semi-Implicit Euler Digital Implementation of Conditioned Super-Twisting Algorithm With Actuation Saturation
The standard super-twisting algorithm (STA) suffers from the windup problem when the actuator of the underlying controlled system is saturated. In the literature, an extension of the standard STA called conditioned STA, was proposed to eliminate the windup effect through the feedback of the saturated control action. However, as with the standard STA, the digital realizations of the conditioned STA with explicit-Euler methods are prone to result in chattering and zigzag oscillations, which degenerate the control performance when the gains of STA are large or the sampling time-step increases. This paper proposes a semi-implicit Euler realization for the conditioned STA to avoid these problems. The control accuracy and robustness of the proposed algorithm are analyzed in a discrete-time manner and it shows the proposed realization algorithm is consistent with the standard STA in terms of control accuracy. In addition, the proposed implementation method does not increase the magnitudes of numerical chattering when the gains of conditioned STA are overestimated and when the sampling time-step is large. The advantages of the proposed algorithm are demonstrated numerically with comparisons with other STA realization schemes through simulations and experiments with a platform of linear motor systems with saturated actuation.
- 20 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (8) , 8388-8397
Semi-Implicit Euler Digital Implementation of Conditioned Super-Twisting Algorithm With Actuation Saturation
The standard super-twisting algorithm (STA) suffers from the windup problem when the actuator of the underlying controlled system is saturated. In the literature, an extension of the standard STA called conditioned STA, was proposed to eliminate the windup effect through the feedback of the saturated control action. However, as with the standard STA, the digital realizations of the conditioned STA with explicit-Euler methods are prone to result in chattering and zigzag oscillations, which degenerate the control performance when the gains of STA are large or the sampling time-step increases. This paper proposes a semi-implicit Euler realization for the conditioned STA to avoid these problems. The control accuracy and robustness of the proposed algorithm are analyzed in a discrete-time manner and it shows the proposed realization algorithm is consistent with the standard STA in terms of control accuracy. In addition, the proposed implementation method does not increase the magnitudes of numerical chattering when the gains of conditioned STA are overestimated and when the sampling time-step is large. The advantages of the proposed algorithm are demonstrated numerically with comparisons with other STA realization schemes through simulations and experiments with a platform of linear motor systems with saturated actuation.
- 14 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (11) , 4443-4447
Discrete-Time Multivariable Super-Twisting Algorithm With Semi-Implicit Euler Method
The classical super-twisting algorithm (STA) has many advantages, such as the simplicity, finite-time convergence, high accuracy, and robustness. However, its scalar input and output may hinder its applications in affine systems with multiple inputs and multiple outputs (MIMO). Therefore, the classical STA has been extended into multivariable versions in the literature to overcome such a limitation. The problem is that, the multivariable STA inherits another downside of the classical STA during implementation, that is, the numerical chattering for large sizes of the sampling period or gains of the STA, which deteriorates the control performance in MIMO systems. This brief proposes a new discrete-time implementation scheme for the multivariable STA with a semi-implicit Euler discretization approach. It attenuates the numerical chattering while reserving the robustness of the multivariable STA. The advantages of the proposed scheme are demonstrated numerically with comparisons with the classical STA and the multivariable STA implementation method through simulations.
- 14 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (11) , 4443-4447
Discrete-Time Multivariable Super-Twisting Algorithm With Semi-Implicit Euler Method
The classical super-twisting algorithm (STA) has many advantages, such as the simplicity, finite-time convergence, high accuracy, and robustness. However, its scalar input and output may hinder its applications in affine systems with multiple inputs and multiple outputs (MIMO). Therefore, the classical STA has been extended into multivariable versions in the literature to overcome such a limitation. The problem is that, the multivariable STA inherits another downside of the classical STA during implementation, that is, the numerical chattering for large sizes of the sampling period or gains of the STA, which deteriorates the control performance in MIMO systems. This brief proposes a new discrete-time implementation scheme for the multivariable STA with a semi-implicit Euler discretization approach. It attenuates the numerical chattering while reserving the robustness of the multivariable STA. The advantages of the proposed scheme are demonstrated numerically with comparisons with the classical STA and the multivariable STA implementation method through simulations.
- Open Access
- 20 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 61444-61454
Performance Evaluation of Optical Motion Capture Sensors for Assembly Motion Capturing
The optical motion capture (MoCap) sensor provides an effective way to capture human motions and transform them into valuable data that can be applied to certain tasks, e.g. robot learning from demonstration (LfD). In spite of the wide utilization of optical MoCaps in LfD studies, there are few works that explore their potentiality in small parts robotic assembly. Robot manipulation skill learning from demonstration has gained the attention of researchers recently and robotic 3C (Computer, Communication, and Consumer Electronics) product assembly turns out to be a promising application thanks to the increasing consumption of 3C products. To further explore the potential of optical MoCaps in robotic 3C product assembly. This work proposes a performance evaluation protocol that takes the characters of both optical MoCaps and 3C product assembly operations into account. The proposed evaluation protocol includes static and trajectory evaluations. The former refers to the widely used evaluation indicators such as precision and accuracy. Meanwhile, the trajectory evaluation takes contour error as an error metric. Three popular optical MoCaps are studied in the experiment. Experiment results show that the static performance of all of the three optical MoCaps can meet the requirements of the 3C product assembly task. What's more, Prime X41 possesses the best trajectory performance. This work sheds light on the wider usage of optical MoCaps in manufacturing industries.
- 20 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 61444-61454
Open AccessPerformance Evaluation of Optical Motion Capture Sensors for Assembly Motion Capturing
The optical motion capture (MoCap) sensor provides an effective way to capture human motions and transform them into valuable data that can be applied to certain tasks, e.g. robot learning from demonstration (LfD). In spite of the wide utilization of optical MoCaps in LfD studies, there are few works that explore their potentiality in small parts robotic assembly. Robot manipulation skill learning from demonstration has gained the attention of researchers recently and robotic 3C (Computer, Communication, and Consumer Electronics) product assembly turns out to be a promising application thanks to the increasing consumption of 3C products. To further explore the potential of optical MoCaps in robotic 3C product assembly. This work proposes a performance evaluation protocol that takes the characters of both optical MoCaps and 3C product assembly operations into account. The proposed evaluation protocol includes static and trajectory evaluations. The former refers to the widely used evaluation indicators such as precision and accuracy. Meanwhile, the trajectory evaluation takes contour error as an error metric. Three popular optical MoCaps are studied in the experiment. Experiment results show that the static performance of all of the three optical MoCaps can meet the requirements of the 3C product assembly task. What's more, Prime X41 possesses the best trajectory performance. This work sheds light on the wider usage of optical MoCaps in manufacturing industries.
- Open Access
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 17161-17173
On-Line Precision Calibration of Mobile Manipulators Based on the Multi-Level Measurement Strategy
Autonomous industrial mobile manipulator (AIMM), which is composed of a mobile platform and a robot arm of six degrees of freedom (DoFs), can move autonomously and perform dexterous tasks independently in the industrial environment. A novel on-line calibration system for AIMM in real manufacturing workshop is proposed in this paper. Compared to calibration scenarios of fixed-base robot, we focus on the large-space autonomous calibration for AIMM. To cope with the issue of high precision calibration in large space, we propose a multi-level guided-based measurement strategy, which includes the low-cost vision positioning and guidance system, and the high-precision distributed base station (BS) measurement system. The corresponding experiment proves that the total uncertainty of measurement system is less than 0.1 mm. Based on the measured data of end-effector installed at the end of robot arm, the AIMM can perform on-line calibration tasks anywhere automatically without taking into account the expensive devices for the high-precision location of mobile platform and the downtime for the robotic off-line calibration. The mean positioning error of AIMM after calibration reduces 93% based on the calibration experiment.
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 17161-17173
Open AccessOn-Line Precision Calibration of Mobile Manipulators Based on the Multi-Level Measurement Strategy
Autonomous industrial mobile manipulator (AIMM), which is composed of a mobile platform and a robot arm of six degrees of freedom (DoFs), can move autonomously and perform dexterous tasks independently in the industrial environment. A novel on-line calibration system for AIMM in real manufacturing workshop is proposed in this paper. Compared to calibration scenarios of fixed-base robot, we focus on the large-space autonomous calibration for AIMM. To cope with the issue of high precision calibration in large space, we propose a multi-level guided-based measurement strategy, which includes the low-cost vision positioning and guidance system, and the high-precision distributed base station (BS) measurement system. The corresponding experiment proves that the total uncertainty of measurement system is less than 0.1 mm. Based on the measured data of end-effector installed at the end of robot arm, the AIMM can perform on-line calibration tasks anywhere automatically without taking into account the expensive devices for the high-precision location of mobile platform and the downtime for the robotic off-line calibration. The mean positioning error of AIMM after calibration reduces 93% based on the calibration experiment.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, 458-463
Actor-Critic Method-Based Search Strategy for High Precision Peg-in-Hole Tasks
In the field of 3C(Computer/Communication/Consumer Electronic) product assembly, Peg-in-hole task, such as fiber assembly, is widely used. However, it remains as a big challenge for robots to automatically execute peg-in-hole tasks. Building a contact model is the traditional idea, which requires lots of time and effort. However, the model suffers low accuracy in the situation with tighter clearance. Currently, the most learning-based methods do not take into account the particularity of such assembly tasks, which lead to slow convergence. In this paper, we propose a new search strategy based on reinforcement learning for high precision peg-in-hole assembly tasks. The assembly task is divided into two steps: search and insert. Afterwards, a Markov Decision Process (MDP) is designed for the two steps according to different assembly features and solved by an Actor-Critic method. The robot can learn how to choose the optimal action and accomplish peg-in-hole task with less training and execute steps, high success rate and smaller contact force. Moreover, the proposed method can be applied to the multi-hole task without retraining. The results of simulation and experiment demonstrate its fast and stable performance.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, 458-463
Actor-Critic Method-Based Search Strategy for High Precision Peg-in-Hole Tasks
In the field of 3C(Computer/Communication/Consumer Electronic) product assembly, Peg-in-hole task, such as fiber assembly, is widely used. However, it remains as a big challenge for robots to automatically execute peg-in-hole tasks. Building a contact model is the traditional idea, which requires lots of time and effort. However, the model suffers low accuracy in the situation with tighter clearance. Currently, the most learning-based methods do not take into account the particularity of such assembly tasks, which lead to slow convergence. In this paper, we propose a new search strategy based on reinforcement learning for high precision peg-in-hole assembly tasks. The assembly task is divided into two steps: search and insert. Afterwards, a Markov Decision Process (MDP) is designed for the two steps according to different assembly features and solved by an Actor-Critic method. The robot can learn how to choose the optimal action and accomplish peg-in-hole task with less training and execute steps, high success rate and smaller contact force. Moreover, the proposed method can be applied to the multi-hole task without retraining. The results of simulation and experiment demonstrate its fast and stable performance.