Simultaneous Tracking and Reconstruction of Objects and its Application in Educational Robotics Laboratories

Mingshao Zhang; Zhou Zhang; Yizhe Chang; Sven K. Esche

Download Paper | Permalink

Conference: 2015 ASEE Annual Conference & Exposition
Location: Seattle, Washington
Publication Date: June 14, 2015
Start Date: June 14, 2015
End Date: June 17, 2015
ISBN: 978-0-692-50180-1
ISSN: 2153-5965
Conference Session: Instrumentation Division Technical Session 1
Tagged Division: Instrumentation
Tagged Topic: Diversity
Page Count: 14
Page Numbers: 26.1376.1 - 26.1376.14
DOI: 10.18260/p.24713
Permanent URL: https://peer.asee.org/24713
Download Count: 509

Request a correction

Paper Authors

biography

Mingshao Zhang Stevens Institute of Technology orcid.org/0000-0002-6331-4010

visit author page

Mingshao Zhang is currently a Ph.D. student in Mechanical Engineering Department, Stevens Institute of Technology. Before joining Stevens, he received bachelor's degrees from University of Science and Technology of China. His Current research interests include Microsoft Kinect, Computer Vision, Educational Laboratories, Desktop Virtual Reality and etc.

visit author page

biography

Zhou Zhang Stevens Institute of Technology orcid.org/0000-0003-4599-4339

visit author page

Ph.D Candidate, Mechanical Engineering Department, Stevens Institute of Technology, Hoboken, NJ, 07030.

Email: zzhang11@stevens.edu

visit author page

author page

Yizhe Chang Stevens Institute of Technology (School of Engineering and Science)

author page

Sven K. Esche Stevens Institute of Technology (School of Engineering and Science)

Download Paper | Permalink

Abstract

Simultaneous Tracking and Reconstruction of Objects and its Application in Educational Robotics LaboratoriesMany educational and industrial applications that involve robots require the location informationfor the robots. This necessitates both the ability to globally localize the robots in the absence of anyprior data as well as to track the robots’ current positions once their initial locations are known.Various approaches have been used to solve these problems, such as encoders, inertial navigation,range sensing and vision-based approaches. Among those state-of-the-art robot localizationmethods, vision-based techniques are considered effective, and they can be enhanced significantlyby obtaining additional supporting information from signal processing techniques and its relatedalgorithm developments. However, many challenges associated with the use of vision-based robottracking systems in uncontrolled environments remain. For example, hardware components ofvisual odometry systems are difficult to implement and tend to be expensive; it is difficult tochoose the most suitable algorithms and analysis methods and those algorithms are considered tobe computationally expensive.In this paper, a visual odometry system implemented using a low-cost and user-friendly 3-Dscanner (the Microsoft Kinect) is presented. A traditional approach for robot tracking based onobject recognition was applied, which includes building an object database, and extracting,describing and matching keypoints between the database and the scene. The advantages anddisadvantages of using the Kinect in these approaches were studied. Then, a technique forsimultaneously tracking and reconstructing objects was developed and tested. This technique wasinspired by the simultaneous localization and mapping (SLAM) approach, and it was implementedusing the Kinect and an iRobot Create platform. The prototype implementation shows that thissimultaneous tracking and reconstruction technique is feasible and suitable to be used ineducational robotics laboratories. This technique also has multiple advantages, such as low cost,straightforward setup and minimal need for preparation work by the laboratory instructor.

Citation
Format

Zhang, M., & Zhang, Z., & Chang, Y., & Esche, S. K. (2015, June), Simultaneous Tracking and Reconstruction of Objects and its Application in Educational Robotics Laboratories Paper presented at 2015 ASEE Annual Conference & Exposition, Seattle, Washington. 10.18260/p.24713

TY  - CPAPER
AB  -  Simultaneous Tracking and Reconstruction of Objects and its Application in                    Educational Robotics LaboratoriesMany educational and industrial applications that involve robots require the location informationfor the robots. This necessitates both the ability to globally localize the robots in the absence of anyprior data as well as to track the robots’ current positions once their initial locations are known.Various approaches have been used to solve these problems, such as encoders, inertial navigation,range sensing and vision-based approaches. Among those state-of-the-art robot localizationmethods, vision-based techniques are considered effective, and they can be enhanced significantlyby obtaining additional supporting information from signal processing techniques and its relatedalgorithm developments. However, many challenges associated with the use of vision-based robottracking systems in uncontrolled environments remain. For example, hardware components ofvisual odometry systems are difficult to implement and tend to be expensive; it is difficult tochoose the most suitable algorithms and analysis methods and those algorithms are considered tobe computationally expensive.In this paper, a visual odometry system implemented using a low-cost and user-friendly 3-Dscanner (the Microsoft Kinect) is presented. A traditional approach for robot tracking based onobject recognition was applied, which includes building an object database, and extracting,describing and matching keypoints between the database and the scene. The advantages anddisadvantages of using the Kinect in these approaches were studied. Then, a technique forsimultaneously tracking and reconstructing objects was developed and tested. This technique wasinspired by the simultaneous localization and mapping (SLAM) approach, and it was implementedusing the Kinect and an iRobot Create platform. The prototype implementation shows that thissimultaneous tracking and reconstruction technique is feasible and suitable to be used ineducational robotics laboratories. This technique also has multiple advantages, such as low cost,straightforward setup and minimal need for preparation work by the laboratory instructor.
AU  - Mingshao Zhang
AU  - Zhou Zhang
AU  - Yizhe Chang
AU  - Sven K. Esche
CY  - Seattle, Washington
DA  - 2015/06/14
PB  - ASEE Conferences
TI  - Simultaneous Tracking and Reconstruction of Objects and its Application in Educational Robotics Laboratories
UR  - https://peer.asee.org/24713
DO  - 10.18260/p.24713
ER  -