| Event Information
Lockheed Martin Robotics Seminar: Data-driven design of soft robotic sensors
Data-driven design of soft robotic sensors
Emerging soft machines require high-performance strain sensors to achieve closed-loop feedback control. Predicting the performance of a soft robotic sensor from its composition and morphology is nearly impossible with traditional computational approaches. Machine learning (ML) is a versatile tool to uncover complex correlations between fabrication recipes and sensor performance, yet the limited acquisition rate of high-quality data hinders the development of high-accuracy prediction models at the device level. In this talk, I will demonstrate our recent work of using an ML model to predict device-level performance and recommend new material compositions for soft machine applications. I will present a three-stage ML framework to construct a prediction model capable of automating the design of strain sensors across a wide strain range from10,000 virtual data points followed by genetic algorithm-based selection to optimize the prediction accuracy of ML model. An ultimate prediction model is finally constructed and able to (1) predict sensor characteristics based on fabrication recipes and (2) recommend feasible fabrication recipes for adequate strain sensors. As final demonstrations, model-suggested strain sensors are integrated into soft gripper and batoid-like swimmer to endow them with real-time sensing capabilities.
Dr. Po-Yen Chen is currently an Assistant Professor in the Department of Chemical and Biomolecular Engineering at University of Maryland (UMD), College Park. Dr. Chen is also affiliated in Maryland Robotics Center (MRC). He received a B.S. degree in Chemical Engineering from National Taiwan University (NTU) and a Ph.D. in Chemical Engineering from Massachusetts Institute of Technology (MIT). After his Ph.D., he was awarded Hibbitt Early Career Fellowship and served as an independent researcher at Brown University for 2 years, and then he worked as an Assistant Professor in the Department of Chemical and Biomolecular Engineering at National University of Singapore (NUS) for 2.5 years before he joined UMD. He received AME Young Investigator Award in 2018 and AIChE SLS Outstanding Young Principal Investigator Award in 2019. In 2020, Po-Yen was named as Innovators Under 35 in Asia by MIT Technology Review and received AIChE 35 under 35 Award. Recently, he is elected to Global Young Academy (GYA) and Fellow of Vebleo. His research focuses on the intersections of nanomaterials self-assembly, machine intelligence, and soft robotics/machines. He seeks to create the synergy between machine intelligence and automated robots to construct high-accuracy prediction models enabling automatic design of functional soft matter for soft robot/machine applications. By implementing data augmentation and statistical analyses, he can reveal the underlying nanomaterial self-assembly mechanisms that dictate data-driven design principles. The insights gained from machine intelligence-guided experiments can be utilized to fabricate stretchable electronics for wearable technologies and smart soft machines.
Host: Derek Paley