Two Graduate Students Graduated This Summer

It is special summer season for me this year. Not only I am closing my chapter at the University of Arkansas and start a new chapter at the University of Texas at Austin, both both my first PhD student, Laxmi Poudel and my first Master student Jared Pow both graduated this summer. Congratulations, Laxmi and Jared!

Laxmi’s research is focused on cooperative 3D printing and scheduling. His research has laid down the foundation for the realization of the swarm manufacturing of the future. In his dissertation, Laxmi developed the computational frameworks that enables the key technologies for task division, manufacturing scheduling, and multi-robot path planning in cooperative 3D printing. Check his dissertation HERE for more detail.

Jared’s research is focused on computer vision of thermal imaging. Particularly, his Master thesis contributed the knowledge in understanding the limitation and advantages for material detection using thermal imaging, compared to traditional computer vision techniques that heavily rely on RGM images. Jared is now working at L3 Technologies as a Mechanical and Testing Engineer. Check his Master defense presentation below and the thesis HERE for more detail.

It was a great memory working with both talented students and I wish them all the best in their future endeavors!

SiDi will Move to UT-Austin in Fall 2021

I’m very excited to share with you, my friends and colleagues, that I’ll be joining The University of Texas at Austin this coming fall in the J. Mike Walker Department of Mechanical Engineering! I see the new opportunities and challenges ahead of me, and I very much look forward to collaborating with you in my future endeavors. Meanwhile, I am extremely grateful to all my colleagues at The University of Arkansas who have provided tremendous support to me during the last four years. The experience in the mechanical engineering department at UARK provided me with a unique opportunity to prepare myself as an educator and create my own identity as an independent researcher in design science and system science. I will miss you all!

Paper Published on Journal of Mechanical Design

Our paper titled “Resource-Constrained Scheduling for Multi-Robot Cooperative Three-Dimensional Printing” is now published on the July issue of Journal of Mechanical Design – a Special Issue on Design Engineering in the Age of Industry 4.0. The preprint can be downloaded HERE.

Quoted from the Guest Editorial of this special issue “The coordination of autonomous resources within a smart manufacturing enterprise is an important enabler for Industry 4.0. Decentralized cooperative manufacturing for 3D printing results in increased throughput and efficiency but poses new coordination challenges. To address these challenges, Poudel et al. presented a method for scheduling multi-robot cooperative 3D printing in their paper titled “Resource-Constrained Scheduling for Multi-Robot Cooperative Three-Dimensional Printing.” The authors demonstrated the algorithms using different geometrical shapes.”

Research Featured by CBS

Our research on Cooperative 3D Printing and Swarm Manufacturing was recently featured over the weekend on CBS’ Innovation Nation! The Ph.D. candidate Laxmi Poudel is a key contributor to this project. Congratulations!

Check our publications on this project:

E. Saivipulteja, L. Poudel, W. Zhou, Z. Sha, “Enabling Multi-Robot Cooperative Additive Manufacturing: Centralized vs. Decentralized Approaches“, ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, Virtual Conference, Aug. 17-20, 2021.

L. Poudel, W. Zhou, Z. Sha, “Resource-Constrained Scheduling for Multi-Robot Cooperative 3D Printing”, Journal of Mechanical Design, Transactions of the ASME, volume 143, issue 7, pp: 072002 (12), July 2021: https://doi.org/10.1115/1.4050380.

L. Poudel, L. G. Marques, R. A. Williams, Z. Hyden, P. Guerra, O. L. Fowler, S. J. Moquin, Z. Sha, W. Zhou, “Architecting The Cooperative 3D Printing System”, ASME 2020 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, St. Louis, MO, Aug. 16-19, 2020.

L. Poudel, W. Zhou, Z. Sha, “A Generative Framework for Scheduling Multi-Robot Cooperative 3D Printing“, Journal of Computing and Information Science in Engineering, Transactions of the ASME, volume 20, issue 6, pp: 061011 (12), Dec 2020.

S. Elagandula, L. Poudel, Z. Sha, W. Zhou, “Multi-Robot Path Planning for Cooperative 3D Printing“, The ASME 2020 15th International Manufacturing Science and Engineering Conference (MSEC), June 22-26, 2020, Cincinnati, OH.

L. Poudel, C. Bair, J. McPerson, Z. Sha, W. Zhou, “A Heuristic Scaling Strategy for Multi-Robot Cooperative 3D Printing”, Journal of Computing and Information Science in Engineering, Transactions of the ASME, volume 20, issue 12, pp: 041002 (12), 2020.

Z. Zhang, L. Poudel, Z. Sha, W. Zhou, D. Wu, “Data-Driven Predictive Modeling of Tensile Behavior of Parts Fabricated by Cooperative 3D Printing”, Journal of Computing and Information Science in Engineering, Transactions of the ASME, volume 20, issue 4, pp: 021002 (10), 2020.

L. Poudel, W. Zhou, Z. Sha, “Computational Design of Scheduling Strategies for Multi-Robot Cooperative 3D Printing“, ASME 2019 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, Anaheim, CA, Aug. 18-21, 2019.

L. Poudel, Z. Sha, W. Zhou, “Mechanical Strength of Chunk-Based 3D Printed Parts for Cooperative 3D Printing“, Procedia Manufacturing, vol. 26, pp. 962-972, 2018.

PhD Candidate Laxmi Poudel Receives the Excellence in Research Award

The PhD Candidate at SiDi Lab, Laxmi Poudel, has been selected as the recipient of the Excellence in Research Award by the Graduate Professional Student Congress at the University of Arkansas. This award is awarded to one Graduate or Professional student engaged in outstanding academic research, regardless of department, that has caused honor to be bestowed upon said individual and graduate and professional programs at the University of Arkansas within the current academic year through significant contributions to sciences or humanities. Congratulations to Laxmi, and check his recent publications on cooperative and swarm manufacturing.

L. Poudel, W. Zhou, Z. Sha, “Resource-Constrained Scheduling for Multi-Robot Cooperative 3D Printing”, Journal of Mechanical Design, Transactions of the ASME, volume 143, issue 7, pp: 072002 (12), July 2021.

L. Poudel, W. Zhou, Z. Sha, “A Generative Framework for Scheduling Multi-Robot Cooperative 3D Printing“, Journal of Computing and Information Science in Engineering, Transactions of the ASME, volume 20, issue 6, pp: 061011 (12), Dec 2020.

L. Poudel, C. Bair, J. McPerson, Z. Sha, W. Zhou, “A Heuristic Scaling Strategy for Multi-Robot Cooperative 3D Printing”, Journal of Computing and Information Science in Engineering, Transactions of the ASME, volume 20, issue 12, pp: 041002 (12), 2020.

Call For Papers – Intelligence Augmentation for Human Systems Integration

The Systems Engineering Information & Knowledge Management Technical Committee and the Design Theory and Methodology Technical Committee of ASME is organizing a special joint session on the topic of “Intelligence Augmentation for Human Systems Integration” for The ASME 2021 Virtual International Design Engineering Technical Conferences & Computers and Information in Engineering Conference. See the call for papers for details.

Paper Nominated for Best Paper Award

Our paper titled “Part-Aware Product Design Agent Using Deep Generative Network and Local Linear Embedding”, led by PhD student Xingang Li, is recently nominated to receive the Best Paper Award by tracks on The 54th Hawaii International Conference on System Sciences. The work came out to be one of the very best of the 1,449 papers submitted for this year.

In this study, we present a data-driven generative design approach that can augment human creativity in product shape design with the objective of improving system performance. The approach consists of two modules: 1) a 3D mesh generative design module that can generate part-aware 3D objects using variational auto-encoder (VAE), and 2) a low-fidelity evaluation module that can rapidly assess the engineering performance of 3D objects based on locally linear embedding (LLE). This approach has two unique features. First, it generates 3D meshes that can better capture surface details (e.g., smoothness and curvature) given individual parts’ interconnection and constraints (i.e., part-aware), as opposed to generating holistic 3D shapes. Second, the LLE-based solver can assess the engineering performance of the generated 3D shapes to realize real-time evaluation. Our approach is applied to car design to reduce air drag for optimal aerodynamic performance.

Collaborative Work Published by Journal of Mechanical Design

Our paper titled “Integrating Sequence Learning and Game Theory to Predict Design Decisions under Competition”, is recently accepted by the Journal of Mechanical Design, Transactions of the ASME.

This paper presents an approach for predicting designers’ future search behaviors in a sequential design process under an unknown objective function by combining sequence learning with game theory. While the majority of existing studies focus on analyzing sequential design decisions from the descriptive and prescriptive point of view, this study is motivated to develop a predictive framework. We use data containing designers’ actual sequential search decisions under competition collected from a black-box function optimization game developed previously. We integrate the long short-term memory networks with the Delta method to predict the next sampling point with a distribution, and combine this model with a non-cooperative game to predict whether a designer will stop searching the design space or not based on their belief of the opponent’s best design. In the function optimization game, the proposed model accurately predicts 82% of the next design variable values and 92% of the next function values in the test data with an upper and lower bound, suggesting that a long short-term memory network can effectively predict the next design decisions based on their past decisions. Further, the game-theoretic model predicts that 60.8% of the participants stop searching for designs sooner than they actually do while accurately predicting when the remaining 39.2% of the participants stop. These results suggest that a majority of the designers show a strong tendency to overestimate their opponents’ performance, leading them to spend more on searching for better designs than they would have, had they known their opponents’ actual performance.

This study was performed in collaboration with Dr. ‪Alparslan Emrah Bayrak from Stevens Institute of Technology.