Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot

Chunxu Li; Chenguang Yang; Jian Wan; Andy Annamalai; Angelo Cangelosi

doi:10.23919/IConAC.2017.8081985

Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot

Chunxu Li, Chenguang Yang, Jian Wan, Andy Annamalai, Angelo Cangelosi

Mechanical, Biomedical & Design Engineering

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

In this paper, Kalman filter has been successfully carried out to fuse the data obtained from a Kinect sensor and a pair of MYO armbands. To do this, the Kinect sensor is used to capture movements of operators which is programmed by Microsoft Visual Studio. Operator wears two MYO armbands with the inertial measurement unit (IMU) embedded to measure the angular velocity of upper arm motion for the human operator. Additionally a neural networks (NN) control upgraded Teaching by Demonstration (TbD) technology has been designed and it also has been actualized on the Baxter robot. A series of experiments have been completed to test the performance of the proposed technique, which has been proved to be an executed approach for the Baxter robot's TbD has been designed.

Original language	English
Title of host publication	2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9780701702601
DOIs	https://doi.org/10.23919/IConAC.2017.8081985
Publication status	Published - 26 Oct 2017
Event	23rd IEEE International Conference on Automation and Computing, ICAC 2017 - Huddersfield, United Kingdom Duration: 7 Sept 2017 → 8 Sept 2017

Conference

Conference	23rd IEEE International Conference on Automation and Computing, ICAC 2017
Country/Territory	United Kingdom
City	Huddersfield
Period	7/09/17 → 8/09/17

Keywords

Robot sensing systems
Kalman filters
Robot kinematics
Mathematical model
Shoulder
Elbow

Access to Document

10.23919/IConAC.2017.8081985

http://hdl.handle.net/10026.1/15864Licence: Unspecified

Cite this

@inproceedings{9eabc0ad264e455499665bbe3c32b27b,

title = "Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot",

abstract = "In this paper, Kalman filter has been successfully carried out to fuse the data obtained from a Kinect sensor and a pair of MYO armbands. To do this, the Kinect sensor is used to capture movements of operators which is programmed by Microsoft Visual Studio. Operator wears two MYO armbands with the inertial measurement unit (IMU) embedded to measure the angular velocity of upper arm motion for the human operator. Additionally a neural networks (NN) control upgraded Teaching by Demonstration (TbD) technology has been designed and it also has been actualized on the Baxter robot. A series of experiments have been completed to test the performance of the proposed technique, which has been proved to be an executed approach for the Baxter robot's TbD has been designed.",

keywords = "Robot sensing systems, Kalman filters, Robot kinematics, Mathematical model, Shoulder, Elbow",

author = "Chunxu Li and Chenguang Yang and Jian Wan and Andy Annamalai and Angelo Cangelosi",

year = "2017",

month = oct,

day = "26",

doi = "10.23919/IConAC.2017.8081985",

language = "English",

booktitle = "2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing",

publisher = "IEEE",

address = "United States",

note = "23rd IEEE International Conference on Automation and Computing, ICAC 2017 ; Conference date: 07-09-2017 Through 08-09-2017",

}

Li, C, Yang, C, Wan, J, Annamalai, A & Cangelosi, A 2017, Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot. in 2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing. IEEE, 23rd IEEE International Conference on Automation and Computing, ICAC 2017, Huddersfield, United Kingdom, 7/09/17. https://doi.org/10.23919/IConAC.2017.8081985

Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot. / Li, Chunxu; Yang, Chenguang; Wan, Jian et al.
2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing. IEEE, 2017.

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot

AU - Li, Chunxu

AU - Yang, Chenguang

AU - Wan, Jian

AU - Annamalai, Andy

AU - Cangelosi, Angelo

PY - 2017/10/26

Y1 - 2017/10/26

N2 - In this paper, Kalman filter has been successfully carried out to fuse the data obtained from a Kinect sensor and a pair of MYO armbands. To do this, the Kinect sensor is used to capture movements of operators which is programmed by Microsoft Visual Studio. Operator wears two MYO armbands with the inertial measurement unit (IMU) embedded to measure the angular velocity of upper arm motion for the human operator. Additionally a neural networks (NN) control upgraded Teaching by Demonstration (TbD) technology has been designed and it also has been actualized on the Baxter robot. A series of experiments have been completed to test the performance of the proposed technique, which has been proved to be an executed approach for the Baxter robot's TbD has been designed.

AB - In this paper, Kalman filter has been successfully carried out to fuse the data obtained from a Kinect sensor and a pair of MYO armbands. To do this, the Kinect sensor is used to capture movements of operators which is programmed by Microsoft Visual Studio. Operator wears two MYO armbands with the inertial measurement unit (IMU) embedded to measure the angular velocity of upper arm motion for the human operator. Additionally a neural networks (NN) control upgraded Teaching by Demonstration (TbD) technology has been designed and it also has been actualized on the Baxter robot. A series of experiments have been completed to test the performance of the proposed technique, which has been proved to be an executed approach for the Baxter robot's TbD has been designed.

KW - Robot sensing systems

KW - Kalman filters

KW - Robot kinematics

KW - Mathematical model

KW - Shoulder

KW - Elbow

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85040005970&partnerID=MN8TOARS

UR - https://ieeexplore.ieee.org/document/8081985

U2 - 10.23919/IConAC.2017.8081985

DO - 10.23919/IConAC.2017.8081985

M3 - Conference publication

BT - 2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing

PB - IEEE

T2 - 23rd IEEE International Conference on Automation and Computing, ICAC 2017

Y2 - 7 September 2017 through 8 September 2017

ER -

Neural learning and Kalman filtering enhanced teaching by demonstration for a Baxter robot

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this