Asee peer logo

Enhancing Student Learning in Robot Path Planning Optimization through Graph-Based Methods

Download Paper |

Conference

2024 ASEE Annual Conference & Exposition

Location

Portland, Oregon

Publication Date

June 23, 2024

Start Date

June 23, 2024

End Date

June 26, 2024

Conference Session

Technical Proficiency and Cybersecurity Awareness in ECE Education

Tagged Division

Electrical and Computer Engineering Division (ECE)

Page Count

15

DOI

10.18260/1-2--47317

Permanent URL

https://peer.asee.org/47317

Download Count

73

Paper Authors

biography

Timothy Sellers Mississippi State University Orcid 16x16 orcid.org/0000-0001-8344-9804

visit author page

Timothy Sellers received the B.S. degree in robotics and automation technology and applied science in electro-mechanical engineering from the Alcorn State University, Lorman, MS, USA in 2020. He is currently pursuing a Ph.D. degree in the Department of Electrical and Computer Engineering at Mississippi State University, Mississippi State, MS, USA. He is currently a Graduate Teaching Assistant for Senior Design II (ECE4542/ECE4522) and was for Advance Circuits (ECE3434) at the undergraduate level and as guest lecturer delivered graduate-level courses, Advanced Robotics (ECE 8743) and Computational Intelligence (ECE 8833). He received the ECE Outstanding Teaching Assistant Award from the Department of Electrical and Computer Engineering, Mississippi State University in 2021. He received the Research Travel Award from Bagley College of Engineering, Mississippi State University in 2024. He has also received the Bagley College of Engineering Student Hall of Fame award in 2024. He won three poster presentation awards at multiple conferences. Mr. Sellers has served on the technical program committee for numerous international conferences and journals, such as IJMLC, ICSI, and PRIS, etc. He has extensively published journal and conference papers in engineering education and robotics fields. His research interests include engineering education, robotics and autonomous systems, human robot interaction, deep learning, and computational intelligence.

visit author page

biography

Tingjun Lei Mississippi State University Orcid 16x16 orcid.org/0000-0002-9043-5600

visit author page

Dr. Tingjun Lei is currently a Postdoctoral Research Fellow in the Department of Electrical and Computer Engineering at the Mississippi State University (MSU). He received his Ph.D. degree in electrical and computer engineering with the Department of Electrical and Computer Engineering, Mississippi State University, Mississippi State, MS, USA., in 2023, his M.S. degree in electrical and computer engineering from the New York Institute of Technology, Old Westbury, NY, USA, in 2016, and the B.S. degree in intelligent transportation engineering from Shanghai Maritime University, Shanghai, China, in 2014. He was Graduate Teaching Assistant for ECE1013 Foundations in ECE, ECE1022 Foundations in Design, ECE4713/6713 Computer Architecture, and ECE4753/6753 Introduction to Robotics at the undergraduate level and as a guest lecturer delivered graduate-level courses, ECE 8743 Advanced Robotics and ECE8833 Computational Intelligence. He received the ECE Best Graduate Researcher Award from the Department of Electrical and Computer Engineering, Mississippi State University in 2023. He received the Research Travel Award from Bagley College of Engineering, Mississippi State University in 2023. His two papers have been selected and featured as cover articles on Intelligence & Robotics Journal. He won six oral and poster presentation awards at multiple conferences. Dr. Lei received the Best Paper Award in 2022 International Conference on Swarm Intelligence. Dr. Lei serves as Youth Editorial Board Member of Intelligence and Robotics. Dr. Lei has served on the technical program committee for numerous international conferences, such as IEEE-CEC, IEEE-IJCNN, ICSI, and PRIS, etc. Dr. Lei has extensively published journal and conference papers in robotics, intelligent systems, and engineering education areas. His research interests include engineering education, robotics and autonomous systems, human robot interaction, deep learning, intelligent transportation systems, and evolutionary computation.

visit author page

biography

Chaomin Luo Mississippi State University Orcid 16x16 orcid.org/0000-0002-7578-3631

visit author page

Dr. Chaomin Luo (Senior Member, IEEE) holds a Ph.D. degree in electrical and computer engineering from the Department of Electrical and Computer Engineering at the University of Waterloo, Canada in 2008. He also earned an M.Sc. degree in engineering systems and computing from the University of Guelph, Canada in 2002, and a B.Sc. in electrical engineering from Southeast University. Currently, he is an Associate Professor in the Department of Electrical and Computer Engineering at Mississippi State University. His research interests include engineering education, intelligent systems, control and automation, robotics, and autonomous systems. He is Associate Editor in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019). He is Tutorials Co-Chair in the 2020 IEEE Symposium Series on Computational Intelligence. Dr. Luo was the recipient of the Best Paper Awards in IEEE International Conference on Information and Automation, International Conference on Swarm Intelligence, and SWORD Conference. His research interests include Robotics, Autonomous Systems, and Control and Automation. Dr. Luo is an IEEE senior member, INFORMS, and ASEE member. Dr. Luo is active nationally and internationally in his research field. He was the Program Co-Chair in 2018 IEEE International Conference on Information and Automation (IEEE-ICIA’2018). He was the Plenary Session Co-Chair in the 2021 and 2019 International Conference on Swarm Intelligence, and he was the Invited Session Co-Chair in the 2017 International Conference on Swarm Intelligence. He was the General Co-Chair of the 1st IEEE International Workshop on Computational Intelligence in Smart Technologies (IEEE-CIST 2015), and Journal Special Issues Chair, IEEE 2016 International Conference on Smart Technologies (IEEE-SmarTech), Cleveland, OH, USA. He was Chair and Vice Chair of IEEE SEM - Computational Intelligence Chapter and was a Chair of IEEE SEM - Computational Intelligence Chapter and Chair of Education Committee of IEEE SEM. He has organized and chaired several special sessions on topics of Intelligent Vehicle Systems and Bio-inspired Intelligence in reputed international conferences such as IJCNN, IEEE-SSCI, IEEE-CEC, IEEE-CASE, and IEEE-Fuzzy, etc. He has extensively published in reputed journals and conference proceedings, such as IEEE Transactions on Industrial Electronics, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on SMC, IEEE Transactions on Cybernetics, IEEE-ICRA, and IEEE-IROS, etc. Dr. Luo serves as Associate Editor of IEEE Transactions on Cognitive and Developmental Systems, International journal of Robotics and Automation, and Associate Editor of International Journal of Swarm Intelligence Research (IJSIR).

visit author page

biography

Zhuming Bi Purdue University, Fort Wayne Orcid 16x16 orcid.org/0000-0002-8145-7883

visit author page

Zhuming Bi (Senior Member, IEEE) received the Ph.D. degree from the Harbin Institute of Technology, Harbin, China, in 1994, and the Ph.D. degree from the University of Saskatchewan, Saskatoon, SK, Canada, in 2002. He has international work experience in Mainland China, Hong Kong, Singapore, Canada, UK, Finland, and USA. He is currently a professor of Mechanical Engineering with Purdue University Fort Wayne, Fort Wayne, IN, USA. His current research interests include robotics, mechatronics, Internet of Things (IoT), digital manufacturing, automatic robotic processing, and enterprise information systems. He has published 6 research books and over 180 journal publications in these fields.

visit author page

biography

Gene Eu Jan Tainan National University of the Arts

visit author page

Gene Eu Jan (M’00) received the B.S. degree in electrical engineering from National Taiwan University, Taipei, Taiwan, in 1982 and the M.S. and Ph.D. degrees in electrical and computer engineering from the University of Maryland, College Park, MD, USA, in 1988 and 1992, respectively.
He has been a Professor with the Departments of Computer Science and Electrical Engineering, National Taipei University, New Taipei City, Taiwan since 2004, where he also served as the Dean of the College of Electrical Engineering and Computer Science from 2007 to 2009. Currently, he is the president of Tainan National University of the Arts. He has published more than 270 articles related to parallel
computer systems, interconnection networks, path planning, electronic design
automation, and VLSI systems design in journals, conference proceedings, and books.

visit author page

Download Paper |

Abstract

Optimizing robot path planning, a key domain within computational intelligence and robotics, is gaining significant prominence today. Graph-based models for robot path planning optimization represent a highly impactful advancement in both research and educational aspects of computational intelligence. Nonetheless, teaching this subject within a computational intelligence curriculum is a challenging task. In general, graph-based techniques for robot path planning are highly versatile and extensively utilized, offering a structured approach to analyze intricate environments and determine efficient and safe robot paths. Their adaptability to diverse robot types and environments positions them as fundamental tools in the fields of computational intelligence and robotics. In this study, we introduce a pedagogical approach that integrates sparrow-dissection and scaffolding (SDS) with active learning and ongoing project-based methods. This approach aims to assist students in the design, implementation, debugging, and operation of graph-based techniques for robot path planning. We teach a visibility graph-based approach for robot path planning in the classroom and provide students with the corresponding source code. Students are expected to review and adapt the provided source code in order to apply the visibility graph-based method to their robot path planning tasks. In our Computational Intelligence course for graduate students, we introduce a visibility graph-based model for robot path planning along with its source code, serving as a foundation for students to dissect and understand the optimization of this method. We collaboratively guide students in revising and customizing the source code for their specific robot path planning needs. As students’ progress through a series of assigned projects centered on the application of the visibility graph-based method, they gradually gain independence and eventually complete projects on their own. Throughout the course, students are given a set of projects that require them to employ graph-based methods for robot path planning. We actively seek feedback after each project to assess their implementation, development, and application of these models in robot path planning. Our approach promotes active learning, encouraging students to participate, ask questions, and engage with both the instructor and their peers to explore the effective application of graph-based methods in optimizing robot path planning. This ongoing involvement of students in projects greatly enhances their comprehension of the subject matter. We assess the efficacy of graph-based methods for robot path planning through a series of milestone assignments, presentations, and interactive activities. We also gather student feedback on their comprehension of graph-based concepts before and after each project, as well as their input on the development and application of neural network models, accomplished through the revision of the initial source code. Our teaching and learning strategies, underpinned by integrated pedagogical approaches, are closely linked to the learning outcomes of this course. This connection is established through an in-depth analysis of the projects involving graph-based methods for robot path planning. When evaluating the overall course effectiveness, we integrate this data with information from our course evaluation system. The combination of these insights underscores the effectiveness of the graph-based method and the high learning quality achieved through our integrated approach, which combines 'sparrow-dissection' and scaffolding pedagogies.

Sellers, T., & Lei, T., & Luo, C., & Bi, Z., & Jan, G. E. (2024, June), Enhancing Student Learning in Robot Path Planning Optimization through Graph-Based Methods Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. 10.18260/1-2--47317

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2024 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015